ruff flags

.devcontainer/README.md

@@ -5,33 +5,25 @@ This project includes a [dev container](https://containers.dev/), which lets you
 You can use the dev container configuration in this folder to build and run the app without needing to install any of its tools locally! You can use it in [GitHub Codespaces](https://github.com/features/codespaces) or the [VS Code Dev Containers extension](https://marketplace.visualstudio.com/items?itemName=ms-vscode-remote.remote-containers).
 
 ## GitHub Codespaces
-
 [![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/langchain-ai/langchain)
 
 You may use the button above, or follow these steps to open this repo in a Codespace:
-
-1. Click the **Code** drop-down menu at the top of <https://github.com/langchain-ai/langchain>.
+1. Click the **Code** drop-down menu at the top of https://github.com/langchain-ai/langchain.
 1. Click on the **Codespaces** tab.
-1. Click **Create codespace on master**.
+1. Click **Create codespace on master** .
 
 For more info, check out the [GitHub documentation](https://docs.github.com/en/free-pro-team@latest/github/developing-online-with-codespaces/creating-a-codespace#creating-a-codespace).
-
+  
 ## VS Code Dev Containers
-
 [![Open in Dev Containers](https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langchain-ai/langchain)
 
-> [!NOTE]
-> If you click the link above you will open the main repo (`langchain-ai/langchain`) and *not* your local cloned repo. This is fine if you only want to run and test the library, but if you want to contribute you can use the link below and replace with your username and cloned repo name:
+Note: If you click this link you will open the main repo and not your local cloned repo, you can use this link and replace with your username and cloned repo name: 
+https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/<yourusername>/<yourclonedreponame>
 
-```txt
-https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/&lt;YOUR_USERNAME&gt;/&lt;YOUR_CLONED_REPO_NAME&gt;
-```
 
-Then you will have a local cloned repo where you can contribute and then create pull requests.
+If you already have VS Code and Docker installed, you can use the button above to get started. This will cause VS Code to automatically install the Dev Containers extension if needed, clone the source code into a container volume, and spin up a dev container for use.
 
-If you already have VS Code and Docker installed, you can use the button above to get started. This will use VSCode to automatically install the Dev Containers extension if needed, clone the source code into a container volume, and spin up a dev container for use.
-
-Alternatively you can also follow these steps to open this repo in a container using the VS Code Dev Containers extension:
+You can also follow these steps to open this repo in a container using the VS Code Dev Containers extension:
 
 1. If this is your first time using a development container, please ensure your system meets the pre-reqs (i.e. have Docker installed) in the [getting started steps](https://aka.ms/vscode-remote/containers/getting-started).
 
@@ -45,5 +37,5 @@ You can learn more in the [Dev Containers documentation](https://code.visualstud
 
 ## Tips and tricks
 
-- If you are working with the same repository folder in a container and Windows, you'll want consistent line endings (otherwise you may see hundreds of changes in the SCM view). The `.gitattributes` file in the root of this repo will disable line ending conversion and should prevent this. See [tips and tricks](https://code.visualstudio.com/docs/devcontainers/tips-and-tricks#_resolving-git-line-ending-issues-in-containers-resulting-in-many-modified-files) for more info.
-- If you'd like to review the contents of the image used in this dev container, you can check it out in the [devcontainers/images](https://github.com/devcontainers/images/tree/main/src/python) repo.
+* If you are working with the same repository folder in a container and Windows, you'll want consistent line endings (otherwise you may see hundreds of changes in the SCM view). The `.gitattributes` file in the root of this repo will disable line ending conversion and should prevent this. See [tips and tricks](https://code.visualstudio.com/docs/devcontainers/tips-and-tricks#_resolving-git-line-ending-issues-in-containers-resulting-in-many-modified-files) for more info.
+* If you'd like to review the contents of the image used in this dev container, you can check it out in the [devcontainers/images](https://github.com/devcontainers/images/tree/main/src/python) repo.

.devcontainer/devcontainer.json

@@ -1,58 +1,36 @@
 // For format details, see https://aka.ms/devcontainer.json. For config options, see the
 // README at: https://github.com/devcontainers/templates/tree/main/src/docker-existing-docker-compose
 {
-  // Name for the dev container
-  "name": "langchain",
-  // Point to a Docker Compose file
-  "dockerComposeFile": "./docker-compose.yaml",
-  // Required when using Docker Compose. The name of the service to connect to once running
-  "service": "langchain",
-  // The optional 'workspaceFolder' property is the path VS Code should open by default when
-  // connected. This is typically a file mount in .devcontainer/docker-compose.yml
-  "workspaceFolder": "/workspaces/langchain",
-  "mounts": [
-    "source=langchain-workspaces,target=/workspaces/langchain,type=volume"
-  ],
-  // Prevent the container from shutting down
-  "overrideCommand": true,
-  // Features to add to the dev container. More info: https://containers.dev/features
-  "features": {
-    "ghcr.io/devcontainers/features/git:1": {},
-    "ghcr.io/devcontainers/features/github-cli:1": {}
-  },
-  "containerEnv": {
-    "UV_LINK_MODE": "copy"
-  },
-  // Use 'forwardPorts' to make a list of ports inside the container available locally.
-  // "forwardPorts": [],
-  // Run commands after the container is created
-  "postCreateCommand": "uv sync && echo 'LangChain (Python) dev environment ready!'",
-  // Configure tool-specific properties.
-  "customizations": {
-    "vscode": {
-      "extensions": [
-        "ms-python.python",
-        "ms-python.debugpy",
-        "ms-python.mypy-type-checker",
-        "ms-python.isort",
-        "unifiedjs.vscode-mdx",
-        "davidanson.vscode-markdownlint",
-        "ms-toolsai.jupyter",
-        "GitHub.copilot",
-        "GitHub.copilot-chat"
-      ],
-      "settings": {
-        "python.defaultInterpreterPath": ".venv/bin/python",
-        "python.formatting.provider": "none",
-        "[python]": {
-          "editor.formatOnSave": true,
-          "editor.codeActionsOnSave": {
-            "source.organizeImports": true
-          }
-        }
-      }
-    }
-  }
-  // Uncomment to connect as root instead. More info: https://aka.ms/dev-containers-non-root.
-  // "remoteUser": "root"
+	// Name for the dev container
+	"name": "langchain",
+
+	// Point to a Docker Compose file
+	"dockerComposeFile": "./docker-compose.yaml",
+
+	// Required when using Docker Compose. The name of the service to connect to once running
+	"service": "langchain",
+
+	// The optional 'workspaceFolder' property is the path VS Code should open by default when
+	// connected. This is typically a file mount in .devcontainer/docker-compose.yml
+	"workspaceFolder": "/workspaces/${localWorkspaceFolderBasename}",
+
+	// Prevent the container from shutting down
+	"overrideCommand": true
+
+	// Features to add to the dev container. More info: https://containers.dev/features
+	// "features": {
+	// 	"ghcr.io/devcontainers-contrib/features/poetry:2": {}
+	// }
+
+	// Use 'forwardPorts' to make a list of ports inside the container available locally.
+	// "forwardPorts": [],
+
+	// Uncomment the next line to run commands after the container is created.
+	// "postCreateCommand": "cat /etc/os-release",
+
+	// Configure tool-specific properties.
+	// "customizations": {},
+
+	// Uncomment to connect as root instead. More info: https://aka.ms/dev-containers-non-root.
+	// "remoteUser": "root"
 }

.devcontainer/docker-compose.yaml

@@ -4,10 +4,29 @@ services:
     build:
       dockerfile: libs/langchain/dev.Dockerfile
       context: ..
-
+    volumes:
+   # Update this to wherever you want VS Code to mount the folder of your project
+      - ..:/workspaces:cached
     networks:
-      - langchain-network
+      - langchain-network 
+  #   environment:
+  #     MONGO_ROOT_USERNAME: root
+  #     MONGO_ROOT_PASSWORD: example123
+  #   depends_on:
+  #     - mongo   
+  # mongo:
+  #   image: mongo
+  #   restart: unless-stopped
+  #   environment:
+  #     MONGO_INITDB_ROOT_USERNAME: root
+  #     MONGO_INITDB_ROOT_PASSWORD: example123
+  #   ports:
+  #     - "27017:27017"
+  #   networks:
+  #     - langchain-network
 
 networks:
   langchain-network:
     driver: bridge
+    
+    

.editorconfig

@@ -1,52 +0,0 @@
-# top-most EditorConfig file
-root = true
-
-# All files
-[*]
-charset = utf-8
-end_of_line = lf
-insert_final_newline = true
-trim_trailing_whitespace = true
-
-# Python files
-[*.py]
-indent_style = space
-indent_size = 4
-max_line_length = 88
-
-# JSON files
-[*.json]
-indent_style = space
-indent_size = 2
-
-# YAML files
-[*.{yml,yaml}]
-indent_style = space
-indent_size = 2
-
-# Markdown files
-[*.md]
-indent_style = space
-indent_size = 2
-trim_trailing_whitespace = false
-
-# Configuration files
-[*.{toml,ini,cfg}]
-indent_style = space
-indent_size = 4
-
-# Shell scripts
-[*.sh]
-indent_style = space
-indent_size = 2
-
-# Makefile
-[Makefile]
-indent_style = tab
-indent_size = 4
-
-# Jupyter notebooks
-[*.ipynb]
-# Jupyter may include trailing whitespace in cell
-# outputs that's semantically meaningful
-trim_trailing_whitespace = false

.github/CODEOWNERS

@@ -1,3 +0,0 @@
-/.github/   @baskaryan @ccurme @eyurtsev
-/libs/core/ @eyurtsev
-/libs/partners/ @ccurme @mdrxy

.github/CODE_OF_CONDUCT.md

@@ -129,4 +129,4 @@ For answers to common questions about this code of conduct, see the FAQ at
 [v2.1]: https://www.contributor-covenant.org/version/2/1/code_of_conduct.html
 [Mozilla CoC]: https://github.com/mozilla/diversity
 [FAQ]: https://www.contributor-covenant.org/faq
-[translations]: https://www.contributor-covenant.org/translations
+[translations]: https://www.contributor-covenant.org/translations

.github/CONTRIBUTING.md

@@ -3,4 +3,305 @@
 Hi there! Thank you for even being interested in contributing to LangChain.
 As an open-source project in a rapidly developing field, we are extremely open to contributions, whether they involve new features, improved infrastructure, better documentation, or bug fixes.
 
-To learn how to contribute to LangChain, please follow the [contribution guide here](https://docs.langchain.com/oss/python/contributing).
+## 🗺️ Guidelines
+
+### 👩‍💻 Contributing Code
+
+To contribute to this project, please follow the ["fork and pull request"](https://docs.github.com/en/get-started/quickstart/contributing-to-projects) workflow.
+Please do not try to push directly to this repo unless you are a maintainer.
+
+Please follow the checked-in pull request template when opening pull requests. Note related issues and tag relevant
+maintainers.
+
+Pull requests cannot land without passing the formatting, linting, and testing checks first. See [Testing](#testing) and
+[Formatting and Linting](#formatting-and-linting) for how to run these checks locally.
+
+It's essential that we maintain great documentation and testing. If you:
+- Fix a bug
+  - Add a relevant unit or integration test when possible. These live in `tests/unit_tests` and `tests/integration_tests`.
+- Make an improvement
+  - Update any affected example notebooks and documentation. These live in `docs`.
+  - Update unit and integration tests when relevant.
+- Add a feature
+  - Add a demo notebook in `docs/modules`.
+  - Add unit and integration tests.
+
+We are a small, progress-oriented team. If there's something you'd like to add or change, opening a pull request is the
+best way to get our attention.
+
+### 🚩GitHub Issues
+
+Our [issues](https://github.com/langchain-ai/langchain/issues) page is kept up to date with bugs, improvements, and feature requests.
+
+There is a taxonomy of labels to help with sorting and discovery of issues of interest. Please use these to help organize issues.
+
+If you start working on an issue, please assign it to yourself.
+
+If you are adding an issue, please try to keep it focused on a single, modular bug/improvement/feature.
+If two issues are related, or blocking, please link them rather than combining them.
+
+We will try to keep these issues as up-to-date as possible, though
+with the rapid rate of development in this field some may get out of date.
+If you notice this happening, please let us know.
+
+### 🙋Getting Help
+
+Our goal is to have the simplest developer setup possible. Should you experience any difficulty getting setup, please
+contact a maintainer! Not only do we want to help get you unblocked, but we also want to make sure that the process is
+smooth for future contributors.
+
+In a similar vein, we do enforce certain linting, formatting, and documentation standards in the codebase.
+If you are finding these difficult (or even just annoying) to work with, feel free to contact a maintainer for help -
+we do not want these to get in the way of getting good code into the codebase.
+
+## 🚀 Quick Start
+
+This quick start guide explains how to run the repository locally.
+For a [development container](https://containers.dev/), see the [.devcontainer folder](https://github.com/langchain-ai/langchain/tree/master/.devcontainer).
+
+### Dependency Management: Poetry and other env/dependency managers
+
+This project utilizes [Poetry](https://python-poetry.org/) v1.6.1+ as a dependency manager.
+
+❗Note: *Before installing Poetry*, if you use `Conda`, create and activate a new Conda env (e.g. `conda create -n langchain python=3.9`)
+
+Install Poetry: **[documentation on how to install it](https://python-poetry.org/docs/#installation)**.
+
+❗Note: If you use `Conda` or `Pyenv` as your environment/package manager, after installing Poetry,
+tell Poetry to use the virtualenv python environment (`poetry config virtualenvs.prefer-active-python true`)
+
+### Core vs. Experimental
+
+This repository contains two separate projects:
+- `langchain`: core langchain code, abstractions, and use cases.
+- `langchain.experimental`: see the [Experimental README](https://github.com/langchain-ai/langchain/tree/master/libs/experimental/README.md) for more information.
+
+Each of these has its own development environment. Docs are run from the top-level makefile, but development
+is split across separate test & release flows.
+
+For this quickstart, start with langchain core:
+
+```bash
+cd libs/langchain
+```
+
+### Local Development Dependencies
+
+Install langchain development requirements (for running langchain, running examples, linting, formatting, tests, and coverage):
+
+```bash
+poetry install --with test
+```
+
+Then verify dependency installation:
+
+```bash
+make test
+```
+
+If the tests don't pass, you may need to pip install additional dependencies, such as `numexpr` and `openapi_schema_pydantic`.
+
+If during installation you receive a `WheelFileValidationError` for `debugpy`, please make sure you are running
+Poetry v1.6.1+. This bug was present in older versions of Poetry (e.g. 1.4.1) and has been resolved in newer releases.
+If you are still seeing this bug on v1.6.1, you may also try disabling "modern installation"
+(`poetry config installer.modern-installation false`) and re-installing requirements.
+See [this `debugpy` issue](https://github.com/microsoft/debugpy/issues/1246) for more details.
+
+### Testing
+
+_some test dependencies are optional; see section about optional dependencies_.
+
+Unit tests cover modular logic that does not require calls to outside APIs.
+If you add new logic, please add a unit test.
+
+To run unit tests:
+
+```bash
+make test
+```
+
+To run unit tests in Docker:
+
+```bash
+make docker_tests
+```
+
+There are also [integration tests and code-coverage](https://github.com/langchain-ai/langchain/tree/master/libs/langchain/tests/README.md) available.
+
+### Formatting and Linting
+
+Run these locally before submitting a PR; the CI system will check also.
+
+#### Code Formatting
+
+Formatting for this project is done via a combination of [Black](https://black.readthedocs.io/en/stable/) and [ruff](https://docs.astral.sh/ruff/rules/).
+
+To run formatting for this project:
+
+```bash
+make format
+```
+
+Additionally, you can run the formatter only on the files that have been modified in your current branch as compared to the master branch using the format_diff command:
+
+```bash
+make format_diff
+```
+
+This is especially useful when you have made changes to a subset of the project and want to ensure your changes are properly formatted without affecting the rest of the codebase.
+
+#### Linting
+
+Linting for this project is done via a combination of [Black](https://black.readthedocs.io/en/stable/), [ruff](https://docs.astral.sh/ruff/rules/), and [mypy](http://mypy-lang.org/).
+
+To run linting for this project:
+
+```bash
+make lint
+```
+
+In addition, you can run the linter only on the files that have been modified in your current branch as compared to the master branch using the lint_diff command:
+
+```bash
+make lint_diff
+```
+
+This can be very helpful when you've made changes to only certain parts of the project and want to ensure your changes meet the linting standards without having to check the entire codebase.
+
+We recognize linting can be annoying - if you do not want to do it, please contact a project maintainer, and they can help you with it. We do not want this to be a blocker for good code getting contributed.
+
+#### Spellcheck
+
+Spellchecking for this project is done via [codespell](https://github.com/codespell-project/codespell).
+Note that `codespell` finds common typos, so it could have false-positive (correctly spelled but rarely used) and false-negatives (not finding misspelled) words.
+
+To check spelling for this project:
+
+```bash
+make spell_check
+```
+
+To fix spelling in place:
+
+```bash
+make spell_fix
+```
+
+If codespell is incorrectly flagging a word, you can skip spellcheck for that word by adding it to the codespell config in the `pyproject.toml` file.
+
+```python
+[tool.codespell]
+...
+# Add here:
+ignore-words-list = 'momento,collison,ned,foor,reworkd,parth,whats,aapply,mysogyny,unsecure'
+```
+
+## Working with Optional Dependencies
+
+Langchain relies heavily on optional dependencies to keep the Langchain package lightweight.
+
+If you're adding a new dependency to Langchain, assume that it will be an optional dependency, and
+that most users won't have it installed.
+
+Users who do not have the dependency installed should be able to **import** your code without
+any side effects (no warnings, no errors, no exceptions).
+
+To introduce the dependency to the pyproject.toml file correctly, please do the following:
+
+1. Add the dependency to the main group as an optional dependency
+  ```bash
+  poetry add --optional [package_name]
+  ```
+2. Open pyproject.toml and add the dependency to the `extended_testing` extra
+3. Relock the poetry file to update the extra.
+  ```bash
+  poetry lock --no-update
+  ```
+4. Add a unit test that the very least attempts to import the new code. Ideally, the unit
+test makes use of lightweight fixtures to test the logic of the code.
+5. Please use the `@pytest.mark.requires(package_name)` decorator for any tests that require the dependency.
+
+## Adding a Jupyter Notebook
+
+If you are adding a Jupyter Notebook example, you'll want to install the optional `dev` dependencies.
+
+To install dev dependencies:
+
+```bash
+poetry install --with dev
+```
+
+Launch a notebook:
+
+```bash
+poetry run jupyter notebook
+```
+
+When you run `poetry install`, the `langchain` package is installed as editable in the virtualenv, so your new logic can be imported into the notebook.
+
+## Documentation
+
+While the code is split between `langchain` and `langchain.experimental`, the documentation is one holistic thing.
+This covers how to get started contributing to documentation.
+
+From the top-level of this repo, install documentation dependencies:
+
+```bash
+poetry install
+```
+
+### Contribute Documentation
+
+The docs directory contains Documentation and API Reference.
+
+Documentation is built using [Docusaurus 2](https://docusaurus.io/).
+
+API Reference are largely autogenerated by [sphinx](https://www.sphinx-doc.org/en/master/) from the code.
+For that reason, we ask that you add good documentation to all classes and methods.
+
+Similar to linting, we recognize documentation can be annoying. If you do not want to do it, please contact a project maintainer, and they can help you with it. We do not want this to be a blocker for good code getting contributed.
+
+### Build Documentation Locally
+
+In the following commands, the prefix `api_` indicates that those are operations for the API Reference.
+
+Before building the documentation, it is always a good idea to clean the build directory:
+
+```bash
+make docs_clean
+make api_docs_clean
+```
+
+Next, you can build the documentation as outlined below:
+
+```bash
+make docs_build
+make api_docs_build
+```
+
+Finally, run the link checker to ensure all links are valid:
+
+```bash
+make docs_linkcheck
+make api_docs_linkcheck
+```
+
+### Verify Documentation changes
+
+After pushing documentation changes to the repository, you can preview and verify that the changes are 
+what you wanted by clicking the `View deployment` or `Visit Preview` buttons on the pull request `Conversation` page. 
+This will take you to a preview of the documentation changes.
+This preview is created by [Vercel](https://vercel.com/docs/getting-started-with-vercel).
+
+## 🏭 Release Process
+
+As of now, LangChain has an ad hoc release process: releases are cut with high frequency by
+a developer and published to [PyPI](https://pypi.org/project/langchain/).
+
+LangChain follows the [semver](https://semver.org/) versioning standard. However, as pre-1.0 software,
+even patch releases may contain [non-backwards-compatible changes](https://semver.org/#spec-item-4).
+
+### 🌟 Recognition
+
+If your contribution has made its way into a release, we will want to give you credit on Twitter (only if you want though)!
+If you have a Twitter account you would like us to mention, please let us know in the PR or through another means.

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -1,121 +1,106 @@
 name: "\U0001F41B Bug Report"
-description: Report a bug in LangChain. To report a security issue, please instead use the security option below. For questions, please use the LangChain forum.
-labels: ["bug"]
-type: bug
+description: Submit a bug report to help us improve LangChain. To report a security issue, please instead use the security option below.
+labels: ["02 Bug Report"]
 body:
   - type: markdown
     attributes:
-      value: |
-        Thank you for taking the time to file a bug report.
+      value: >
+        Thank you for taking the time to file a bug report. Before creating a new
+        issue, please make sure to take a few moments to check the issue tracker
+        for existing issues about the bug.
 
-        Use this to report BUGS in LangChain. For usage questions, feature requests and general design questions, please use the [LangChain Forum](https://forum.langchain.com/).
-
-        Relevant links to check before filing a bug report to see if your issue has already been reported, fixed or
-        if there's another way to solve your problem:
-
-        * [LangChain Forum](https://forum.langchain.com/),
-        * [LangChain documentation with the integrated search](https://docs.langchain.com/oss/python/langchain/overview),
-        * [API Reference](https://reference.langchain.com/python/),
-        * [LangChain ChatBot](https://chat.langchain.com/)
-        * [GitHub search](https://github.com/langchain-ai/langchain),
-  - type: checkboxes
-    id: checks
+  - type: textarea
+    id: system-info
     attributes:
-      label: Checked other resources
-      description: Please confirm and check all the following options.
+      label: System Info
+      description: Please share your system info with us.
+      placeholder: LangChain version, platform, python version, ...
+    validations:
+      required: true
+
+  - type: textarea
+    id: who-can-help
+    attributes:
+      label: Who can help?
+      description: |
+        Your issue will be replied to more quickly if you can figure out the right person to tag with @
+        If you know how to use git blame, that is the easiest way, otherwise, here is a rough guide of **who to tag**.
+
+        The core maintainers strive to read all issues, but tagging them will help them prioritize.
+
+        Please tag fewer than 3 people.
+
+        @hwchase17 - project lead
+
+        Tracing / Callbacks
+        - @agola11
+
+        Async
+        - @agola11
+
+        DataLoader Abstractions
+        - @eyurtsev
+
+        LLM/Chat Wrappers
+        - @hwchase17
+        - @agola11
+
+        Tools / Toolkits
+        - ...
+
+      placeholder: "@Username ..."
+
+  - type: checkboxes
+    id: information-scripts-examples
+    attributes:
+      label: Information
+      description: "The problem arises when using:"
       options:
-        - label: This is a bug, not a usage question.
-          required: true
-        - label: I added a clear and descriptive title that summarizes this issue.
-          required: true
-        - label: I used the GitHub search to find a similar question and didn't find it.
-          required: true
-        - label: I am sure that this is a bug in LangChain rather than my code.
-          required: true
-        - label: The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).
-          required: true
-        - label: This is not related to the langchain-community package.
-          required: true
-        - label: I read what a minimal reproducible example is (https://stackoverflow.com/help/minimal-reproducible-example).
-          required: true
-        - label: I posted a self-contained, minimal, reproducible example. A maintainer can copy it and run it AS IS.
-          required: true
+        - label: "The official example notebooks/scripts"
+        - label: "My own modified scripts"
+
+  - type: checkboxes
+    id: related-components
+    attributes:
+      label: Related Components
+      description: "Select the components related to the issue (if applicable):"
+      options:
+        - label: "LLMs/Chat Models"
+        - label: "Embedding Models"
+        - label: "Prompts / Prompt Templates / Prompt Selectors"
+        - label: "Output Parsers"
+        - label: "Document Loaders"
+        - label: "Vector Stores / Retrievers"
+        - label: "Memory"
+        - label: "Agents / Agent Executors"
+        - label: "Tools / Toolkits"
+        - label: "Chains"
+        - label: "Callbacks/Tracing"
+        - label: "Async"
+
   - type: textarea
     id: reproduction
     validations:
       required: true
     attributes:
-      label: Example Code
+      label: Reproduction
       description: |
-        Please add a self-contained, [minimal, reproducible, example](https://stackoverflow.com/help/minimal-reproducible-example) with your use case.
-
-        If a maintainer can copy it, run it, and see it right away, there's a much higher chance that you'll be able to get help.
-
-        **Important!**
-
-        * Avoid screenshots when possible, as they are hard to read and (more importantly) don't allow others to copy-and-paste your code.
-        * Reduce your code to the minimum required to reproduce the issue if possible. This makes it much easier for others to help you.
-        * Use code tags (e.g., ```python ... ```) to correctly [format your code](https://help.github.com/en/github/writing-on-github/creating-and-highlighting-code-blocks#syntax-highlighting).
-        * INCLUDE the language label (e.g. `python`) after the first three backticks to enable syntax highlighting. (e.g., ```python rather than ```).
+        Please provide a [code sample](https://stackoverflow.com/help/minimal-reproducible-example) that reproduces the problem you ran into. It can be a Colab link or just a code snippet.
+        If you have code snippets, error messages, stack traces please provide them here as well.
+        Important! Use code tags to correctly format your code. See https://help.github.com/en/github/writing-on-github/creating-and-highlighting-code-blocks#syntax-highlighting
+        Avoid screenshots when possible, as they are hard to read and (more importantly) don't allow others to copy-and-paste your code.
 
       placeholder: |
-        The following code:
+        Steps to reproduce the behavior:
 
-        ```python
-        from langchain_core.runnables import RunnableLambda
+          1.
+          2.
+          3.
 
-        def bad_code(inputs) -> int:
-          raise NotImplementedError('For demo purpose')
-
-          chain = RunnableLambda(bad_code)
-          chain.invoke('Hello!')
-        ```
   - type: textarea
-    id: error
-    validations:
-      required: false
-    attributes:
-      label: Error Message and Stack Trace (if applicable)
-      description: |
-        If you are reporting an error, please include the full error message and stack trace.
-      placeholder: |
-        Exception + full stack trace
-  - type: textarea
-    id: description
-    attributes:
-      label: Description
-      description: |
-        What is the problem, question, or error?
-
-        Write a short description telling what you are doing, what you expect to happen, and what is currently happening.
-      placeholder: |
-        * I'm trying to use the `langchain` library to do X.
-        * I expect to see Y.
-        * Instead, it does Z.
+    id: expected-behavior
     validations:
       required: true
-  - type: textarea
-    id: system-info
     attributes:
-      label: System Info
-      description: |
-        Please share your system info with us. Do NOT skip this step and please don't trim
-        the output. Most users don't include enough information here and it makes it harder
-        for us to help you.
-
-        Run the following command in your terminal and paste the output here:
-
-        `python -m langchain_core.sys_info`
-
-        or if you have an existing python interpreter running:
-
-        ```python
-        from langchain_core import sys_info
-        sys_info.print_sys_info()
-        ```
-
-        alternatively, put the entire output of `pip freeze` here.
-      placeholder: |
-        python -m langchain_core.sys_info
-    validations:
-      required: true
+      label: Expected behavior
+      description: "A clear and concise description of what you would expect to happen."

.github/ISSUE_TEMPLATE/config.yml

@@ -1,9 +1,6 @@
-blank_issues_enabled: false
+blank_issues_enabled: true
 version: 2.1
 contact_links:
-  - name: 📚 Documentation
-    url: https://github.com/langchain-ai/docs/issues/new?template=langchain.yml
-    about: Report an issue related to the LangChain documentation
-  - name: 💬 LangChain Forum
-    url:  https://forum.langchain.com/
-    about: General community discussions and support
+  - name: Discord
+    url: https://discord.gg/6adMQxSpJS
+    about: General community discussions

.github/ISSUE_TEMPLATE/documentation.yml

@@ -0,0 +1,19 @@
+name: Documentation
+description: Report an issue related to the LangChain documentation.
+title: "DOC: <Please write a comprehensive title after the 'DOC: ' prefix>"
+labels: [03 - Documentation]
+
+body:
+- type: textarea
+  attributes: 
+    label: "Issue with current documentation:"
+    description: >
+      Please make sure to leave a reference to the document/code you're
+      referring to.
+
+- type: textarea
+  attributes:
+    label: "Idea or request for content:"
+    description: >
+      Please describe as clearly as possible what topics you think are missing
+      from the current documentation.

.github/ISSUE_TEMPLATE/feature-request.yml

@@ -1,118 +1,30 @@
-name: "✨ Feature Request"
-description: Request a new feature or enhancement for LangChain. For questions, please use the LangChain forum.
-labels: ["feature request"]
-type: feature
+name: "\U0001F680 Feature request"
+description: Submit a proposal/request for a new LangChain feature
+labels: ["02 Feature Request"]
 body:
-  - type: markdown
-    attributes:
-      value: |
-        Thank you for taking the time to request a new feature.
-
-        Use this to request NEW FEATURES or ENHANCEMENTS in LangChain. For bug reports, please use the bug report template. For usage questions and general design questions, please use the [LangChain Forum](https://forum.langchain.com/).
-
-        Relevant links to check before filing a feature request to see if your request has already been made or
-        if there's another way to achieve what you want:
-
-        * [LangChain Forum](https://forum.langchain.com/),
-        * [LangChain documentation with the integrated search](https://docs.langchain.com/oss/python/langchain/overview),
-        * [API Reference](https://reference.langchain.com/python/),
-        * [LangChain ChatBot](https://chat.langchain.com/)
-        * [GitHub search](https://github.com/langchain-ai/langchain),
-  - type: checkboxes
-    id: checks
-    attributes:
-      label: Checked other resources
-      description: Please confirm and check all the following options.
-      options:
-        - label: This is a feature request, not a bug report or usage question.
-          required: true
-        - label: I added a clear and descriptive title that summarizes the feature request.
-          required: true
-        - label: I used the GitHub search to find a similar feature request and didn't find it.
-          required: true
-        - label: I checked the LangChain documentation and API reference to see if this feature already exists.
-          required: true
-        - label: This is not related to the langchain-community package.
-          required: true
   - type: textarea
-    id: feature-description
+    id: feature-request
     validations:
       required: true
     attributes:
-      label: Feature Description
+      label: Feature request
       description: |
-        Please provide a clear and concise description of the feature you would like to see added to LangChain.
+        A clear and concise description of the feature proposal. Please provide links to any relevant GitHub repos, papers, or other resources if relevant.
 
-        What specific functionality are you requesting? Be as detailed as possible.
-      placeholder: |
-        I would like LangChain to support...
-
-        This feature would allow users to...
   - type: textarea
-    id: use-case
+    id: motivation
     validations:
       required: true
     attributes:
-      label: Use Case
+      label: Motivation
       description: |
-        Describe the specific use case or problem this feature would solve.
+        Please outline the motivation for the proposal. Is your feature request related to a problem? e.g., I'm always frustrated when [...]. If this is related to another GitHub issue, please link here too.
 
-        Why do you need this feature? What problem does it solve for you or other users?
-      placeholder: |
-        I'm trying to build an application that...
-
-        Currently, I have to work around this by...
-
-        This feature would help me/users to...
   - type: textarea
-    id: proposed-solution
+    id: contribution
     validations:
-      required: false
+      required: true
     attributes:
-      label: Proposed Solution
+      label: Your contribution
       description: |
-        If you have ideas about how this feature could be implemented, please describe them here.
-
-        This is optional but can be helpful for maintainers to understand your vision.
-      placeholder: |
-        I think this could be implemented by...
-
-        The API could look like...
-
-        ```python
-        # Example of how the feature might work
-        ```
-  - type: textarea
-    id: alternatives
-    validations:
-      required: false
-    attributes:
-      label: Alternatives Considered
-      description: |
-        Have you considered any alternative solutions or workarounds?
-
-        What other approaches have you tried or considered?
-      placeholder: |
-        I've tried using...
-
-        Alternative approaches I considered:
-        1. ...
-        2. ...
-
-        But these don't work because...
-  - type: textarea
-    id: additional-context
-    validations:
-      required: false
-    attributes:
-      label: Additional Context
-      description: |
-        Add any other context, screenshots, examples, or references that would help explain your feature request.
-      placeholder: |
-        Related issues: #...
-
-        Similar features in other libraries:
-        - ...
-
-        Additional context or examples:
-        - ...
+        Is there any way that you could help, e.g. by submitting a PR? Make sure to read the CONTRIBUTING.MD [readme](https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md)

.github/ISSUE_TEMPLATE/other.yml

@@ -0,0 +1,18 @@
+name: Other Issue
+description: Raise an issue that wouldn't be covered by the other templates.
+title: "Issue: <Please write a comprehensive title after the 'Issue: ' prefix>"
+labels: [04 - Other]
+
+body:
+  - type: textarea
+    attributes:
+      label: "Issue you'd like to raise."
+      description: >
+        Please describe the issue you'd like to raise as clearly as possible.
+        Make sure to include any relevant links or references.
+
+  - type: textarea
+    attributes:
+      label: "Suggestion:"
+      description: >
+        Please outline a suggestion to improve the issue here.

.github/ISSUE_TEMPLATE/privileged.yml

@@ -1,20 +0,0 @@
-name: 🔒 Privileged
-description: You are a LangChain maintainer, or was asked directly by a maintainer to create an issue here. If not, check the other options.
-body:
-  - type: markdown
-    attributes:
-      value: |
-        If you are not a LangChain maintainer, employee, or were not asked directly by a maintainer to create an issue, then please start the conversation on the [LangChain Forum](https://forum.langchain.com/) instead.
-  - type: checkboxes
-    id: privileged
-    attributes:
-      label: Privileged issue
-      description: Confirm that you are allowed to create an issue here.
-      options:
-        - label: I am a LangChain maintainer, or was asked directly by a LangChain maintainer to create an issue here.
-          required: true
-  - type: textarea
-    id: content
-    attributes:
-      label: Issue Content
-      description: Add the content of the issue here.

.github/ISSUE_TEMPLATE/task.yml

@@ -1,91 +0,0 @@
-name: "📋 Task"
-description: Create a task for project management and tracking by LangChain maintainers. If you are not a maintainer, please use other templates or the forum.
-labels: ["task"]
-type: task
-body:
-  - type: markdown
-    attributes:
-      value: |
-        Thanks for creating a task to help organize LangChain development.
-
-        This template is for **maintainer tasks** such as project management, development planning, refactoring, documentation updates, and other organizational work.
-
-        If you are not a LangChain maintainer or were not asked directly by a maintainer to create a task, then please start the conversation on the [LangChain Forum](https://forum.langchain.com/) instead or use the appropriate bug report or feature request templates on the previous page.
-  - type: checkboxes
-    id: maintainer
-    attributes:
-      label: Maintainer task
-      description: Confirm that you are allowed to create a task here.
-      options:
-        - label: I am a LangChain maintainer, or was asked directly by a LangChain maintainer to create a task here.
-          required: true
-  - type: textarea
-    id: task-description
-    attributes:
-      label: Task Description
-      description: |
-        Provide a clear and detailed description of the task.
-        
-        What needs to be done? Be specific about the scope and requirements.
-      placeholder: |
-        This task involves...
-        
-        The goal is to...
-        
-        Specific requirements:
-        - ...
-        - ...
-    validations:
-      required: true
-  - type: textarea
-    id: acceptance-criteria
-    attributes:
-      label: Acceptance Criteria
-      description: |
-        Define the criteria that must be met for this task to be considered complete.
-        
-        What are the specific deliverables or outcomes expected?
-      placeholder: |
-        This task will be complete when:
-        - [ ] ...
-        - [ ] ...
-        - [ ] ...
-    validations:
-      required: true
-  - type: textarea
-    id: context
-    attributes:
-      label: Context and Background
-      description: |
-        Provide any relevant context, background information, or links to related issues/PRs.
-        
-        Why is this task needed? What problem does it solve?
-      placeholder: |
-        Background:
-        - ...
-        
-        Related issues/PRs:
-        - #...
-        
-        Additional context:
-        - ...
-    validations:
-      required: false
-  - type: textarea
-    id: dependencies
-    attributes:
-      label: Dependencies
-      description: |
-        List any dependencies or blockers for this task.
-        
-        Are there other tasks, issues, or external factors that need to be completed first?
-      placeholder: |
-        This task depends on:
-        - [ ] Issue #...
-        - [ ] PR #...
-        - [ ] External dependency: ...
-        
-        Blocked by:
-        - ...
-    validations:
-      required: false

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,28 +1,20 @@
-(Replace this entire block of text)
+<!-- Thank you for contributing to LangChain!
 
-Thank you for contributing to LangChain! Follow these steps to mark your pull request as ready for review. **If any of these steps are not completed, your PR will not be considered for review.**
+Replace this entire comment with:
+  - **Description:** a description of the change, 
+  - **Issue:** the issue # it fixes (if applicable),
+  - **Dependencies:** any dependencies required for this change,
+  - **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below),
+  - **Twitter handle:** we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out!
 
-- [ ] **PR title**: Follows the format: {TYPE}({SCOPE}): {DESCRIPTION}
-  - Examples:
-    - feat(core): add multi-tenant support
-    - fix(cli): resolve flag parsing error
-    - docs(openai): update API usage examples
-  - Allowed `{TYPE}` values:
-    - feat, fix, docs, style, refactor, perf, test, build, ci, chore, revert, release
-  - Allowed `{SCOPE}` values (optional):
-    - core, cli, langchain, standard-tests, text-splitters, docs, anthropic, chroma, deepseek, exa, fireworks, groq, huggingface, mistralai, nomic, ollama, openai, perplexity, prompty, qdrant, xai, infra
-  - Once you've written the title, please delete this checklist item; do not include it in the PR.
+Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` to check this locally.
 
-- [ ] **PR message**: ***Delete this entire checklist*** and replace with
-  - **Description:** a description of the change. Include a [closing keyword](https://docs.github.com/en/issues/tracking-your-work-with-issues/using-issues/linking-a-pull-request-to-an-issue#linking-a-pull-request-to-an-issue-using-a-keyword) if applicable to a relevant issue.
-  - **Issue:** the issue # it fixes, if applicable (e.g. Fixes #123)
-  - **Dependencies:** any dependencies required for this change
+See contribution guidelines for more information on how to write/run tests, lint, etc: 
+https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md
 
-- [ ] **Lint and test**: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. **We will not consider a PR unless these three are passing in CI.** See [contribution guidelines](https://docs.langchain.com/oss/python/contributing) for more.
+If you're adding a new integration, please include:
+  1. a test for the integration, preferably unit tests that do not rely on network access,
+  2. an example notebook showing its use. It lives in `docs/extras` directory.
 
-Additional guidelines:
-
-- Most PRs should not touch more than one package.
-- Please do not add dependencies to `pyproject.toml` files (even optional ones) unless they are **required** for unit tests. Likewise, please do not update the `uv.lock` files unless you are adding a required dependency.
-- Changes should be backwards compatible.
-- Make sure optional dependencies are imported within a function.
+If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17.
+ -->

.github/actions/poetry_setup/action.yml

@@ -26,13 +26,12 @@ inputs:
 runs:
   using: composite
   steps:
-    - uses: actions/setup-python@v5
+    - uses: actions/setup-python@v4
       name: Setup python ${{ inputs.python-version }}
-      id: setup-python
       with:
         python-version: ${{ inputs.python-version }}
 
-    - uses: actions/cache@v4
+    - uses: actions/cache@v3
       id: cache-bin-poetry
       name: Cache Poetry binary - Python ${{ inputs.python-version }}
       env:
@@ -75,11 +74,10 @@ runs:
       env:
         POETRY_VERSION: ${{ inputs.poetry-version }}
         PYTHON_VERSION: ${{ inputs.python-version }}
-      # Install poetry using the python version installed by setup-python step.
-      run: pipx install "poetry==$POETRY_VERSION" --python '${{ steps.setup-python.outputs.python-path }}' --verbose
+      run: pipx install "poetry==$POETRY_VERSION" --python "python$PYTHON_VERSION" --verbose
 
     - name: Restore pip and poetry cached dependencies
-      uses: actions/cache@v4
+      uses: actions/cache@v3
       env:
         SEGMENT_DOWNLOAD_TIMEOUT_MIN: "4"
         WORKDIR: ${{ inputs.working-directory == '' && '.' || inputs.working-directory }}

.github/actions/uv_setup/action.yml

@@ -1,39 +0,0 @@
-# Helper to set up Python and uv with caching
-
-name: uv-install
-description: Set up Python and uv with caching
-
-inputs:
-  python-version:
-    description: Python version, supporting MAJOR.MINOR only
-    required: true
-  enable-cache:
-    description: Enable caching for uv dependencies
-    required: false
-    default: "true"
-  cache-suffix:
-    description: Custom cache key suffix for cache invalidation
-    required: false
-    default: ""
-  working-directory:
-    description: Working directory for cache glob scoping
-    required: false
-    default: "**"
-
-env:
-  UV_VERSION: "0.5.25"
-
-runs:
-  using: composite
-  steps:
-    - name: Install uv and set the python version
-      uses: astral-sh/setup-uv@v6
-      with:
-        version: ${{ env.UV_VERSION }}
-        python-version: ${{ inputs.python-version }}
-        enable-cache: ${{ inputs.enable-cache }}
-        cache-dependency-glob: |
-          ${{ inputs.working-directory }}/pyproject.toml
-          ${{ inputs.working-directory }}/uv.lock
-          ${{ inputs.working-directory }}/requirements*.txt
-        cache-suffix: ${{ inputs.cache-suffix }}

.github/copilot-instructions.md

@@ -1,330 +0,0 @@
-# Global Development Guidelines for LangChain Projects
-
-## Core Development Principles
-
-### 1. Maintain Stable Public Interfaces ⚠️ CRITICAL
-
-**Always attempt to preserve function signatures, argument positions, and names for exported/public methods.**
-
-❌ **Bad - Breaking Change:**
-
-```python
-def get_user(id, verbose=False):  # Changed from `user_id`
-    pass
-```
-
-✅ **Good - Stable Interface:**
-
-```python
-def get_user(user_id: str, verbose: bool = False) -> User:
-    """Retrieve user by ID with optional verbose output."""
-    pass
-```
-
-**Before making ANY changes to public APIs:**
-
-- Check if the function/class is exported in `__init__.py`
-- Look for existing usage patterns in tests and examples
-- Use keyword-only arguments for new parameters: `*, new_param: str = "default"`
-- Mark experimental features clearly with docstring admonitions (using MkDocs Material, like `!!! warning`)
-
-🧠 *Ask yourself:* "Would this change break someone's code if they used it last week?"
-
-### 2. Code Quality Standards
-
-**All Python code MUST include type hints and return types.**
-
-❌ **Bad:**
-
-```python
-def p(u, d):
-    return [x for x in u if x not in d]
-```
-
-✅ **Good:**
-
-```python
-def filter_unknown_users(users: list[str], known_users: set[str]) -> list[str]:
-    """Filter out users that are not in the known users set.
-
-    Args:
-        users: List of user identifiers to filter.
-        known_users: Set of known/valid user identifiers.
-
-    Returns:
-        List of users that are not in the known_users set.
-    """
-    return [user for user in users if user not in known_users]
-```
-
-**Style Requirements:**
-
-- Use descriptive, **self-explanatory variable names**. Avoid overly short or cryptic identifiers.
-- Attempt to break up complex functions (>20 lines) into smaller, focused functions where it makes sense
-- Avoid unnecessary abstraction or premature optimization
-- Follow existing patterns in the codebase you're modifying
-
-### 3. Testing Requirements
-
-**Every new feature or bugfix MUST be covered by unit tests.**
-
-**Test Organization:**
-
-- Unit tests: `tests/unit_tests/` (no network calls allowed)
-- Integration tests: `tests/integration_tests/` (network calls permitted)
-- Use `pytest` as the testing framework
-
-**Test Quality Checklist:**
-
-- [ ] Tests fail when your new logic is broken
-- [ ] Happy path is covered
-- [ ] Edge cases and error conditions are tested
-- [ ] Use fixtures/mocks for external dependencies
-- [ ] Tests are deterministic (no flaky tests)
-
-Checklist questions:
-
-- [ ] Does the test suite fail if your new logic is broken?
-- [ ] Are all expected behaviors exercised (happy path, invalid input, etc)?
-- [ ] Do tests use fixtures or mocks where needed?
-
-```python
-def test_filter_unknown_users():
-    """Test filtering unknown users from a list."""
-    users = ["alice", "bob", "charlie"]
-    known_users = {"alice", "bob"}
-
-    result = filter_unknown_users(users, known_users)
-
-    assert result == ["charlie"]
-    assert len(result) == 1
-```
-
-### 4. Security and Risk Assessment
-
-**Security Checklist:**
-
-- No `eval()`, `exec()`, or `pickle` on user-controlled input
-- Proper exception handling (no bare `except:`) and use a `msg` variable for error messages
-- Remove unreachable/commented code before committing
-- Race conditions or resource leaks (file handles, sockets, threads).
-- Ensure proper resource cleanup (file handles, connections)
-
-❌ **Bad:**
-
-```python
-def load_config(path):
-    with open(path) as f:
-        return eval(f.read())  # ⚠️ Never eval config
-```
-
-✅ **Good:**
-
-```python
-import json
-
-def load_config(path: str) -> dict:
-    with open(path) as f:
-        return json.load(f)
-```
-
-### 5. Documentation Standards
-
-**Use Google-style docstrings with Args and Returns sections for all public functions.**
-
-❌ **Insufficient Documentation:**
-
-```python
-def send_email(to, msg):
-    """Send an email to a recipient."""
-```
-
-✅ **Complete Documentation:**
-
-```python
-def send_email(to: str, msg: str, *, priority: str = "normal") -> bool:
-    """
-    Send an email to a recipient with specified priority.
-
-    Args:
-        to: The email address of the recipient.
-        msg: The message body to send.
-        priority: Email priority level.
-
-    Returns:
-        True if email was sent successfully, False otherwise.
-
-    Raises:
-        InvalidEmailError: If the email address format is invalid.
-        SMTPConnectionError: If unable to connect to email server.
-    """
-```
-
-**Documentation Guidelines:**
-
-- Types go in function signatures, NOT in docstrings
-- Focus on "why" rather than "what" in descriptions
-- Document all parameters, return values, and exceptions
-- Keep descriptions concise but clear
-
-📌 *Tip:* Keep descriptions concise but clear. Only document return values if non-obvious.
-
-### 6. Architectural Improvements
-
-**When you encounter code that could be improved, suggest better designs:**
-
-❌ **Poor Design:**
-
-```python
-def process_data(data, db_conn, email_client, logger):
-    # Function doing too many things
-    validated = validate_data(data)
-    result = db_conn.save(validated)
-    email_client.send_notification(result)
-    logger.log(f"Processed {len(data)} items")
-    return result
-```
-
-✅ **Better Design:**
-
-```python
-@dataclass
-class ProcessingResult:
-    """Result of data processing operation."""
-    items_processed: int
-    success: bool
-    errors: List[str] = field(default_factory=list)
-
-class DataProcessor:
-    """Handles data validation, storage, and notification."""
-
-    def __init__(self, db_conn: Database, email_client: EmailClient):
-        self.db = db_conn
-        self.email = email_client
-
-    def process(self, data: List[dict]) -> ProcessingResult:
-        """Process and store data with notifications.
-
-        Args:
-            data: List of data items to process.
-
-        Returns:
-            ProcessingResult with details of the operation.
-        """
-        validated = self._validate_data(data)
-        result = self.db.save(validated)
-        self._notify_completion(result)
-        return result
-```
-
-**Design Improvement Areas:**
-
-If there's a **cleaner**, **more scalable**, or **simpler** design, highlight it and suggest improvements that would:
-
-- Reduce code duplication through shared utilities
-- Make unit testing easier
-- Improve separation of concerns (single responsibility)
-- Make unit testing easier through dependency injection
-- Add clarity without adding complexity
-- Prefer dataclasses for structured data
-
-## Development Tools & Commands
-
-### Package Management
-
-```bash
-# Add package
-uv add package-name
-
-# Sync project dependencies
-uv sync
-uv lock
-```
-
-### Testing
-
-```bash
-# Run unit tests (no network)
-make test
-
-# Don't run integration tests, as API keys must be set
-
-# Run specific test file
-uv run --group test pytest tests/unit_tests/test_specific.py
-```
-
-### Code Quality
-
-```bash
-# Lint code
-make lint
-
-# Format code
-make format
-
-# Type checking
-uv run --group lint mypy .
-```
-
-### Dependency Management Patterns
-
-**Local Development Dependencies:**
-
-```toml
-[tool.uv.sources]
-langchain-core = { path = "../core", editable = true }
-langchain-tests = { path = "../standard-tests", editable = true }
-```
-
-**For tools, use the `@tool` decorator from `langchain_core.tools`:**
-
-```python
-from langchain_core.tools import tool
-
-@tool
-def search_database(query: str) -> str:
-    """Search the database for relevant information.
-
-    Args:
-        query: The search query string.
-    """
-    # Implementation here
-    return results
-```
-
-## Commit Standards
-
-**Use Conventional Commits format for PR titles:**
-
-- `feat(core): add multi-tenant support`
-- `!fix(cli): resolve flag parsing error` (breaking change uses exclamation mark)
-- `docs: update API usage examples`
-- `docs(openai): update API usage examples`
-
-## Framework-Specific Guidelines
-
-- Follow the existing patterns in `langchain_core` for base abstractions
-- Implement proper streaming support where applicable
-- Avoid deprecated components
-
-### Partner Integrations
-
-- Follow the established patterns in existing partner libraries
-- Implement standard interfaces (`BaseChatModel`, `BaseEmbeddings`, etc.)
-- Include comprehensive integration tests
-- Document API key requirements and authentication
-
----
-
-## Quick Reference Checklist
-
-Before submitting code changes:
-
-- [ ] **Breaking Changes**: Verified no public API changes
-- [ ] **Type Hints**: All functions have complete type annotations
-- [ ] **Tests**: New functionality is fully tested
-- [ ] **Security**: No dangerous patterns (eval, silent failures, etc.)
-- [ ] **Documentation**: Google-style docstrings for public functions
-- [ ] **Code Quality**: `make lint` and `make format` pass
-- [ ] **Architecture**: Suggested improvements where applicable
-- [ ] **Commit Message**: Follows Conventional Commits format

.github/dependabot.yml

@@ -1,11 +0,0 @@
-# Please see the documentation for all configuration options:
-# https://docs.github.com/github/administering-a-repository/configuration-options-for-dependency-updates
-# and
-# https://docs.github.com/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file
-
-version: 2
-updates:
-  - package-ecosystem: "github-actions"
-    directory: "/"
-    schedule:
-      interval: "weekly"

.github/images/logo-dark.svg

@@ -1,25 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<svg id="Layer_1" data-name="Layer 1" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 1584.81 250">
-  <defs>
-    <style>
-      .cls-1 {
-        fill: #1c3c3c;
-        stroke-width: 0px;
-      }
-    </style>
-  </defs>
-  <g id="LanChain-logo">
-    <g id="LangChain-logotype">
-      <polygon class="cls-1" points="596.33 49.07 596.33 200.67 700.76 200.67 700.76 177.78 620.04 177.78 620.04 49.07 596.33 49.07"/>
-      <path class="cls-1" d="M1126.83,49.07c-20.53,0-37.95,7.4-50.38,21.41-12.32,13.88-18.82,33.36-18.82,56.33,0,47.23,27.25,77.75,69.41,77.75,29.71,0,52.71-15.54,61.54-41.56l2.14-6.31-23.53-8.94-2.17,7.03c-5.26,17.01-18.75,26.38-37.99,26.38-27.48,0-44.55-20.82-44.55-54.34s17.23-54.34,44.97-54.34c19.23,0,30.31,7.54,35.95,24.44l2.46,7.37,22.91-10.75-2.1-5.9c-8.96-25.22-29.65-38.56-59.85-38.56Z"/>
-      <path class="cls-1" d="M756.43,85.05c-22.76,0-39.78,10.67-46.69,29.27-.44,1.19-1.77,4.78-1.77,4.78l19.51,12.62,2.65-6.91c4.52-11.78,12.88-17.27,26.3-17.27s21.1,6.51,20.96,19.33c0,.52-.04,2.09-.04,2.09,0,0-17.76,2.88-25.08,4.43-31.23,6.6-44.31,18.52-44.31,38.02,0,10.39,5.77,21.64,16.3,27.95,6.32,3.78,14.57,5.21,23.68,5.21,5.99,0,11.81-.89,17.2-2.53,12.25-4.07,15.67-12.07,15.67-12.07v10.46h20.29v-74.78c0-25.42-16.7-40.6-44.67-40.6ZM777.46,164.85c0,7.86-8.56,18.93-28.5,18.93-5.63,0-9.62-1.49-12.28-3.71-3.56-2.97-4.73-7.24-4.24-11.01.21-1.64,1.2-5.17,4.87-8.23,3.75-3.13,10.38-5.37,20.62-7.6,8.42-1.83,19.54-3.85,19.54-3.85v15.48Z"/>
-      <path class="cls-1" d="M876.11,85.04c-2.82,0-5.57.2-8.24.57-18.17,2.73-23.49,11.96-23.49,11.96l.02-9.31h-22.74s0,112.19,0,112.19h23.71v-62.18c0-21.13,15.41-30.75,29.73-30.75,15.48,0,23,8.32,23,25.45v67.48h23.71v-70.74c0-27.56-17.51-44.67-45.69-44.67Z"/>
-      <path class="cls-1" d="M1539.12,85.04c-2.82,0-5.57.2-8.24.57-18.17,2.73-23.49,11.96-23.49,11.96v-9.32h-22.72v112.2h23.71v-62.18c0-21.13,15.41-30.75,29.73-30.75,15.48,0,23,8.32,23,25.45v67.48h23.71v-70.74c0-27.56-17.51-44.67-45.69-44.67Z"/>
-      <path class="cls-1" d="M1020.76,88.26v11.55s-5.81-14.77-32.24-14.77c-32.84,0-53.24,22.66-53.24,59.15,0,20.59,6.58,36.8,18.19,47.04,9.03,7.96,21.09,12.04,35.45,12.32,9.99.19,16.46-2.53,20.5-5.1,7.76-4.94,10.64-9.63,10.64-9.63,0,0-.33,3.67-.93,8.64-.43,3.6-1.24,6.13-1.24,6.13h0c-3.61,12.85-14.17,20.28-29.57,20.28s-24.73-5.07-26.58-15.06l-23.05,6.88c3.98,19.2,22,30.66,48.2,30.66,17.81,0,31.77-4.84,41.5-14.4,9.81-9.64,14.79-23.53,14.79-41.29v-102.41h-22.42ZM1019.26,145.21c0,22.44-10.96,35.84-29.32,35.84-19.67,0-30.95-13.44-30.95-36.86s11.28-36.66,30.95-36.66c17.92,0,29.15,13.34,29.32,34.82v2.86Z"/>
-      <path class="cls-1" d="M1259.01,85.04c-2.6,0-5.13.17-7.59.49-17.88,2.79-23.14,11.9-23.14,11.9v-2.67h-.01s0-45.69,0-45.69h-23.71v151.39h23.71v-62.18c0-21.27,15.41-30.95,29.73-30.95,15.48,0,23,8.32,23,25.45v67.68h23.71v-70.94c0-27.01-17.94-44.47-45.69-44.47Z"/>
-      <circle class="cls-1" cx="1450.93" cy="64.47" r="15.37"/>
-      <path class="cls-1" d="M1439.14,88.2v56.94h0c-6.75-5.56-14.6-9.75-23.5-12.26v-7.23c0-25.42-16.7-40.6-44.67-40.6-22.76,0-39.78,10.67-46.69,29.27-.44,1.19-1.77,4.78-1.77,4.78l19.51,12.62,2.65-6.91c4.52-11.78,12.88-17.27,26.3-17.27s21.1,6.51,20.96,19.33c0,.08,0,1.15,0,2.86-10.04-.28-19.38.69-27.77,2.66,0,0,0,0,0,0-11.06,2.5-31.6,8.85-38.94,25.36-.05.11-1.13,2.96-1.13,2.96-1.06,3.28-1.59,6.84-1.59,10.7,0,10.39,5.77,21.64,16.3,27.95,6.32,3.78,14.57,5.21,23.68,5.21,5.88,0,11.6-.86,16.91-2.44,12.49-4.04,15.96-12.16,15.96-12.16v10.47h20.29v-34.27c-5.7-3.56-14.26-5.66-23.65-5.64,0,2.65,0,4.33,0,4.33,0,7.86-8.56,18.93-28.5,18.93-5.63,0-9.62-1.49-12.28-3.71-3.56-2.97-4.73-7.24-4.24-11.01.21-1.64,1.2-5.17,4.87-8.23l-.04-.11c8.42-6.89,24.97-9.64,40.17-9.04v.03c12.94.47,22.62,3.01,29.53,7.77,1.88,1.19,3.65,2.52,5.28,3.98,6.94,6.23,9.73,13.9,10.93,18.38,1.95,7.31,1.43,18.57,1.43,18.57h23.59v-112.2h-23.59Z"/>
-    </g>
-    <path id="LangChain-symbol" class="cls-1" d="M393.52,75.2c9.66,9.66,9.66,25.38,0,35.04l-21.64,21.29-.22-1.22c-1.58-8.75-5.74-16.69-12.02-22.97-4.73-4.72-10.32-8.21-16.62-10.37-3.91,3.93-6.06,9.08-6.06,14.5,0,1.1.1,2.24.3,3.38,3.47,1.25,6.54,3.18,9.12,5.76,9.66,9.66,9.66,25.38,0,35.04l-18.84,18.84c-4.83,4.83-11.17,7.24-17.52,7.24s-12.69-2.41-17.52-7.24c-9.66-9.66-9.66-25.38,0-35.04l21.64-21.28.22,1.22c1.57,8.73,5.73,16.67,12.03,22.96,4.74,4.74,9.99,7.89,16.28,10.04l1.16-1.16c3.52-3.52,5.45-8.2,5.45-13.19,0-1.11-.1-2.22-.29-3.31-3.63-1.2-6.62-2.91-9.34-5.63-3.92-3.92-6.36-8.93-7.04-14.48-.05-.4-.08-.79-.12-1.19-.54-7.23,2.07-14.29,7.16-19.37l18.84-18.84c4.67-4.67,10.89-7.25,17.52-7.25s12.85,2.57,17.52,7.25ZM491.9,125c0,68.93-56.08,125-125,125H125C56.08,250,0,193.93,0,125S56.08,0,125,0h241.9c68.93,0,125,56.08,125,125ZM240.9,187.69c1.97-2.39-7.13-9.12-8.99-11.59-3.78-4.1-3.8-10-6.35-14.79-6.24-14.46-13.41-28.81-23.44-41.05-10.6-13.39-23.68-24.47-35.17-37.04-8.53-8.77-10.81-21.26-18.34-30.69-10.38-15.33-43.2-19.51-48.01,2.14.02.68-.19,1.11-.78,1.54-2.66,1.93-5.03,4.14-7.02,6.81-4.87,6.78-5.62,18.28.46,24.37.2-3.21.31-6.24,2.85-8.54,4.7,4.03,11.8,5.46,17.25,2.45,12.04,17.19,9.04,40.97,18.6,59.49,2.64,4.38,5.3,8.85,8.69,12.69,2.75,4.28,12.25,9.33,12.81,13.29.1,6.8-.7,14.23,3.76,19.92,2.1,4.26-3.06,8.54-7.22,8.01-5.4.74-11.99-3.63-16.72-.94-1.67,1.81-4.94-.19-6.38,2.32-.5,1.3-3.2,3.13-1.59,4.38,1.79-1.36,3.45-2.78,5.86-1.97-.36,1.96,1.19,2.24,2.42,2.81-.04,1.33-.82,2.69.2,3.82,1.19-1.2,1.9-2.9,3.79-3.4,6.28,8.37,12.67-8.47,26.26-.89-2.76-.14-5.21.21-7.07,2.48-.46.51-.85,1.11-.04,1.77,7.33-4.73,7.29,1.62,12.05-.33,3.66-1.91,7.3-4.3,11.65-3.62-4.23,1.22-4.4,4.62-6.88,7.49-.42.44-.62.94-.13,1.67,8.78-.74,9.5-3.66,16.59-7.24,5.29-3.23,10.56,4.6,15.14.14,1.01-.97,2.39-.64,3.64-.77-1.6-8.53-19.19,1.56-18.91-9.88,5.66-3.85,4.36-11.22,4.74-17.17,6.51,3.61,13.75,5.71,20.13,9.16,3.22,5.2,8.27,12.07,15,11.62.18-.52.34-.98.53-1.51,2.04.35,4.66,1.7,5.78-.88,3.05,3.19,7.53,3.03,11.52,2.21,2.95-2.4-5.55-5.82-6.69-8.29ZM419.51,92.72c0-11.64-4.52-22.57-12.73-30.78-8.21-8.21-19.14-12.73-30.79-12.73s-22.58,4.52-30.79,12.73l-18.84,18.84c-4.4,4.4-7.74,9.57-9.93,15.36l-.13.33-.34.1c-6.84,2.11-12.87,5.73-17.92,10.78l-18.84,18.84c-16.97,16.98-16.97,44.6,0,61.57,8.21,8.21,19.14,12.73,30.78,12.73h0c11.64,0,22.58-4.52,30.79-12.73l18.84-18.84c4.38-4.38,7.7-9.53,9.89-15.31l.13-.33.34-.11c6.72-2.06,12.92-5.8,17.95-10.82l18.84-18.84c8.21-8.21,12.73-19.14,12.73-30.79ZM172.38,173.6c-1.62,6.32-2.15,17.09-10.37,17.4-.68,3.65,2.53,5.02,5.44,3.85,2.89-1.33,4.26,1.05,5.23,3.42,4.46.65,11.06-1.49,11.31-6.77-6.66-3.84-8.72-11.14-11.62-17.9Z"/>
-  </g>
-</svg>

.github/images/logo-light.svg

@@ -1,25 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<svg id="Layer_1" data-name="Layer 1" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 1584.81 250">
-  <defs>
-    <style>
-      .cls-1 {
-        fill: #fff;
-        stroke-width: 0px;
-      }
-    </style>
-  </defs>
-  <g id="LanChain-logo">
-    <g id="LangChain-logotype">
-      <polygon class="cls-1" points="596.33 49.07 596.33 200.67 700.76 200.67 700.76 177.78 620.04 177.78 620.04 49.07 596.33 49.07"/>
-      <path class="cls-1" d="M1126.83,49.07c-20.53,0-37.95,7.4-50.38,21.41-12.32,13.88-18.82,33.36-18.82,56.33,0,47.23,27.25,77.75,69.41,77.75,29.71,0,52.71-15.54,61.54-41.56l2.14-6.31-23.53-8.94-2.17,7.03c-5.26,17.01-18.75,26.38-37.99,26.38-27.48,0-44.55-20.82-44.55-54.34s17.23-54.34,44.97-54.34c19.23,0,30.31,7.54,35.95,24.44l2.46,7.37,22.91-10.75-2.1-5.9c-8.96-25.22-29.65-38.56-59.85-38.56Z"/>
-      <path class="cls-1" d="M756.43,85.05c-22.76,0-39.78,10.67-46.69,29.27-.44,1.19-1.77,4.78-1.77,4.78l19.51,12.62,2.65-6.91c4.52-11.78,12.88-17.27,26.3-17.27s21.1,6.51,20.96,19.33c0,.52-.04,2.09-.04,2.09,0,0-17.76,2.88-25.08,4.43-31.23,6.6-44.31,18.52-44.31,38.02,0,10.39,5.77,21.64,16.3,27.95,6.32,3.78,14.57,5.21,23.68,5.21,5.99,0,11.81-.89,17.2-2.53,12.25-4.07,15.67-12.07,15.67-12.07v10.46h20.29v-74.78c0-25.42-16.7-40.6-44.67-40.6ZM777.46,164.85c0,7.86-8.56,18.93-28.5,18.93-5.63,0-9.62-1.49-12.28-3.71-3.56-2.97-4.73-7.24-4.24-11.01.21-1.64,1.2-5.17,4.87-8.23,3.75-3.13,10.38-5.37,20.62-7.6,8.42-1.83,19.54-3.85,19.54-3.85v15.48Z"/>
-      <path class="cls-1" d="M876.11,85.04c-2.82,0-5.57.2-8.24.57-18.17,2.73-23.49,11.96-23.49,11.96l.02-9.31h-22.74s0,112.19,0,112.19h23.71v-62.18c0-21.13,15.41-30.75,29.73-30.75,15.48,0,23,8.32,23,25.45v67.48h23.71v-70.74c0-27.56-17.51-44.67-45.69-44.67Z"/>
-      <path class="cls-1" d="M1539.12,85.04c-2.82,0-5.57.2-8.24.57-18.17,2.73-23.49,11.96-23.49,11.96v-9.32h-22.72v112.2h23.71v-62.18c0-21.13,15.41-30.75,29.73-30.75,15.48,0,23,8.32,23,25.45v67.48h23.71v-70.74c0-27.56-17.51-44.67-45.69-44.67Z"/>
-      <path class="cls-1" d="M1020.76,88.26v11.55s-5.81-14.77-32.24-14.77c-32.84,0-53.24,22.66-53.24,59.15,0,20.59,6.58,36.8,18.19,47.04,9.03,7.96,21.09,12.04,35.45,12.32,9.99.19,16.46-2.53,20.5-5.1,7.76-4.94,10.64-9.63,10.64-9.63,0,0-.33,3.67-.93,8.64-.43,3.6-1.24,6.13-1.24,6.13h0c-3.61,12.85-14.17,20.28-29.57,20.28s-24.73-5.07-26.58-15.06l-23.05,6.88c3.98,19.2,22,30.66,48.2,30.66,17.81,0,31.77-4.84,41.5-14.4,9.81-9.64,14.79-23.53,14.79-41.29v-102.41h-22.42ZM1019.26,145.21c0,22.44-10.96,35.84-29.32,35.84-19.67,0-30.95-13.44-30.95-36.86s11.28-36.66,30.95-36.66c17.92,0,29.15,13.34,29.32,34.82v2.86Z"/>
-      <path class="cls-1" d="M1259.01,85.04c-2.6,0-5.13.17-7.59.49-17.88,2.79-23.14,11.9-23.14,11.9v-2.67h-.01s0-45.69,0-45.69h-23.71v151.39h23.71v-62.18c0-21.27,15.41-30.95,29.73-30.95,15.48,0,23,8.32,23,25.45v67.68h23.71v-70.94c0-27.01-17.94-44.47-45.69-44.47Z"/>
-      <circle class="cls-1" cx="1450.93" cy="64.47" r="15.37"/>
-      <path class="cls-1" d="M1439.14,88.2v56.94h0c-6.75-5.56-14.6-9.75-23.5-12.26v-7.23c0-25.42-16.7-40.6-44.67-40.6-22.76,0-39.78,10.67-46.69,29.27-.44,1.19-1.77,4.78-1.77,4.78l19.51,12.62,2.65-6.91c4.52-11.78,12.88-17.27,26.3-17.27s21.1,6.51,20.96,19.33c0,.08,0,1.15,0,2.86-10.04-.28-19.38.69-27.77,2.66,0,0,0,0,0,0-11.06,2.5-31.6,8.85-38.94,25.36-.05.11-1.13,2.96-1.13,2.96-1.06,3.28-1.59,6.84-1.59,10.7,0,10.39,5.77,21.64,16.3,27.95,6.32,3.78,14.57,5.21,23.68,5.21,5.88,0,11.6-.86,16.91-2.44,12.49-4.04,15.96-12.16,15.96-12.16v10.47h20.29v-34.27c-5.7-3.56-14.26-5.66-23.65-5.64,0,2.65,0,4.33,0,4.33,0,7.86-8.56,18.93-28.5,18.93-5.63,0-9.62-1.49-12.28-3.71-3.56-2.97-4.73-7.24-4.24-11.01.21-1.64,1.2-5.17,4.87-8.23l-.04-.11c8.42-6.89,24.97-9.64,40.17-9.04v.03c12.94.47,22.62,3.01,29.53,7.77,1.88,1.19,3.65,2.52,5.28,3.98,6.94,6.23,9.73,13.9,10.93,18.38,1.95,7.31,1.43,18.57,1.43,18.57h23.59v-112.2h-23.59Z"/>
-    </g>
-    <path id="LangChain-symbol" class="cls-1" d="M393.52,75.2c9.66,9.66,9.66,25.38,0,35.04l-21.64,21.29-.22-1.22c-1.58-8.75-5.74-16.69-12.02-22.97-4.73-4.72-10.32-8.21-16.62-10.37-3.91,3.93-6.06,9.08-6.06,14.5,0,1.1.1,2.24.3,3.38,3.47,1.25,6.54,3.18,9.12,5.76,9.66,9.66,9.66,25.38,0,35.04l-18.84,18.84c-4.83,4.83-11.17,7.24-17.52,7.24s-12.69-2.41-17.52-7.24c-9.66-9.66-9.66-25.38,0-35.04l21.64-21.28.22,1.22c1.57,8.73,5.73,16.67,12.03,22.96,4.74,4.74,9.99,7.89,16.28,10.04l1.16-1.16c3.52-3.52,5.45-8.2,5.45-13.19,0-1.11-.1-2.22-.29-3.31-3.63-1.2-6.62-2.91-9.34-5.63-3.92-3.92-6.36-8.93-7.04-14.48-.05-.4-.08-.79-.12-1.19-.54-7.23,2.07-14.29,7.16-19.37l18.84-18.84c4.67-4.67,10.89-7.25,17.52-7.25s12.85,2.57,17.52,7.25ZM491.9,125c0,68.93-56.08,125-125,125H125C56.08,250,0,193.93,0,125S56.08,0,125,0h241.9C435.82,0,491.9,56.08,491.9,125ZM240.9,187.69c1.97-2.39-7.13-9.12-8.99-11.59-3.78-4.1-3.8-10-6.35-14.79-6.24-14.46-13.41-28.81-23.44-41.05-10.6-13.39-23.68-24.47-35.17-37.04-8.53-8.77-10.81-21.26-18.34-30.69-10.38-15.33-43.2-19.51-48.01,2.14.02.68-.19,1.11-.78,1.54-2.66,1.93-5.03,4.14-7.02,6.81-4.87,6.78-5.62,18.28.46,24.37.2-3.21.31-6.24,2.85-8.54,4.7,4.03,11.8,5.46,17.25,2.45,12.04,17.19,9.04,40.97,18.6,59.49,2.64,4.38,5.3,8.85,8.69,12.69,2.75,4.28,12.25,9.33,12.81,13.29.1,6.8-.7,14.23,3.76,19.92,2.1,4.26-3.06,8.54-7.22,8.01-5.4.74-11.99-3.63-16.72-.94-1.67,1.81-4.94-.19-6.38,2.32-.5,1.3-3.2,3.13-1.59,4.38,1.79-1.36,3.45-2.78,5.86-1.97-.36,1.96,1.19,2.24,2.42,2.81-.04,1.33-.82,2.69.2,3.82,1.19-1.2,1.9-2.9,3.79-3.4,6.28,8.37,12.67-8.47,26.26-.89-2.76-.14-5.21.21-7.07,2.48-.46.51-.85,1.11-.04,1.77,7.33-4.73,7.29,1.62,12.05-.33,3.66-1.91,7.3-4.3,11.65-3.62-4.23,1.22-4.4,4.62-6.88,7.49-.42.44-.62.94-.13,1.67,8.78-.74,9.5-3.66,16.59-7.24,5.29-3.23,10.56,4.6,15.14.14,1.01-.97,2.39-.64,3.64-.77-1.6-8.53-19.19,1.56-18.91-9.88,5.66-3.85,4.36-11.22,4.74-17.17,6.51,3.61,13.75,5.71,20.13,9.16,3.22,5.2,8.27,12.07,15,11.62.18-.52.34-.98.53-1.51,2.04.35,4.66,1.7,5.78-.88,3.05,3.19,7.53,3.03,11.52,2.21,2.95-2.4-5.55-5.82-6.69-8.29ZM419.51,92.72c0-11.64-4.52-22.57-12.73-30.78-8.21-8.21-19.14-12.73-30.79-12.73s-22.58,4.52-30.79,12.73l-18.84,18.84c-4.4,4.4-7.74,9.57-9.93,15.36l-.13.33-.34.1c-6.84,2.11-12.87,5.73-17.92,10.78l-18.84,18.84c-16.97,16.98-16.97,44.6,0,61.57,8.21,8.21,19.14,12.73,30.78,12.73h0c11.64,0,22.58-4.52,30.79-12.73l18.84-18.84c4.38-4.38,7.7-9.53,9.89-15.31l.13-.33.34-.11c6.72-2.06,12.92-5.8,17.95-10.82l18.84-18.84c8.21-8.21,12.73-19.14,12.73-30.79ZM172.38,173.6c-1.62,6.32-2.15,17.09-10.37,17.4-.68,3.65,2.53,5.02,5.44,3.85,2.89-1.33,4.26,1.05,5.23,3.42,4.46.65,11.06-1.49,11.31-6.77-6.66-3.84-8.72-11.14-11.62-17.9Z"/>
-  </g>
-</svg>

.github/pr-file-labeler.yml

@@ -1,84 +0,0 @@
-# Label PRs (config)
-# Automatically applies labels based on changed files and branch patterns
-
-# Core packages
-core:
-  - changed-files:
-      - any-glob-to-any-file:
-          - "libs/core/**/*"
-
-langchain:
-  - changed-files:
-      - any-glob-to-any-file:
-          - "libs/langchain/**/*"
-          - "libs/langchain_v1/**/*"
-
-v1:
-  - changed-files:
-      - any-glob-to-any-file:
-          - "libs/langchain_v1/**/*"
-
-cli:
-  - changed-files:
-      - any-glob-to-any-file:
-          - "libs/cli/**/*"
-
-standard-tests:
-  - changed-files:
-      - any-glob-to-any-file:
-          - "libs/standard-tests/**/*"
-
-text-splitters:
-  - changed-files:
-      - any-glob-to-any-file:
-          - "libs/text-splitters/**/*"
-
-# Partner integrations
-integration:
-  - changed-files:
-      - any-glob-to-any-file:
-          - "libs/partners/**/*"
-
-# Infrastructure and DevOps
-infra:
-  - changed-files:
-      - any-glob-to-any-file:
-          - ".github/**/*"
-          - "Makefile"
-          - ".pre-commit-config.yaml"
-          - "scripts/**/*"
-          - "docker/**/*"
-          - "Dockerfile*"
-
-github_actions:
-  - changed-files:
-      - any-glob-to-any-file:
-          - ".github/workflows/**/*"
-          - ".github/actions/**/*"
-
-dependencies:
-  - changed-files:
-      - any-glob-to-any-file:
-          - "**/pyproject.toml"
-          - "uv.lock"
-          - "**/requirements*.txt"
-          - "**/poetry.lock"
-
-# Documentation
-documentation:
-  - changed-files:
-      - any-glob-to-any-file:
-          - "**/*.md"
-          - "**/*.rst"
-          - "**/README*"
-
-# Security related changes
-security:
-  - changed-files:
-      - any-glob-to-any-file:
-          - "**/*security*"
-          - "**/*auth*"
-          - "**/*credential*"
-          - "**/*secret*"
-          - "**/*token*"
-          - ".github/workflows/security*"

.github/pr-title-labeler.yml

@@ -1,41 +0,0 @@
-# PR title labeler config
-#
-# Labels PRs based on conventional commit patterns in titles
-#
-# Format: type(scope): description or type!: description (breaking)
-
-add-missing-labels: true
-clear-prexisting: false
-include-commits: false
-include-title: true
-label-for-breaking-changes: breaking
-
-label-mapping:
-  documentation: ["docs"]
-  feature: ["feat"]
-  fix: ["fix"]
-  infra: ["build", "ci", "chore"]
-  integration:
-    [
-      "anthropic",
-      "chroma",
-      "deepseek",
-      "exa",
-      "fireworks",
-      "groq",
-      "huggingface",
-      "mistralai",
-      "nomic",
-      "ollama",
-      "openai",
-      "perplexity",
-      "prompty",
-      "qdrant",
-      "xai",
-    ]
-  linting: ["style"]
-  performance: ["perf"]
-  refactor: ["refactor"]
-  release: ["release"]
-  revert: ["revert"]
-  tests: ["test"]

.github/scripts/check_diff.py

@@ -1,346 +0,0 @@
-"""Analyze git diffs to determine which directories need to be tested.
-
-Intelligently determines which LangChain packages and directories need to be tested,
-linted, or built based on the changes. Handles dependency relationships between
-packages, maps file changes to appropriate CI job configurations, and outputs JSON
-configurations for GitHub Actions.
-
-- Maps changed files to affected package directories (libs/core, libs/partners/*, etc.)
-- Builds dependency graph to include dependent packages when core components change
-- Generates test matrix configurations with appropriate Python versions
-- Handles special cases for Pydantic version testing and performance benchmarks
-
-Used as part of the check_diffs workflow.
-"""
-
-import glob
-import json
-import os
-import sys
-from collections import defaultdict
-from pathlib import Path
-from typing import Dict, List, Set
-
-import tomllib
-from get_min_versions import get_min_version_from_toml
-from packaging.requirements import Requirement
-
-LANGCHAIN_DIRS = [
-    "libs/core",
-    "libs/text-splitters",
-    "libs/langchain",
-    "libs/langchain_v1",
-]
-
-# When set to True, we are ignoring core dependents
-# in order to be able to get CI to pass for each individual
-# package that depends on core
-# e.g. if you touch core, we don't then add textsplitters/etc to CI
-IGNORE_CORE_DEPENDENTS = False
-
-# ignored partners are removed from dependents
-# but still run if directly edited
-IGNORED_PARTNERS = [
-    # remove huggingface from dependents because of CI instability
-    # specifically in huggingface jobs
-    # https://github.com/langchain-ai/langchain/issues/25558
-    "huggingface",
-    # prompty exhibiting issues with numpy for Python 3.13
-    # https://github.com/langchain-ai/langchain/actions/runs/12651104685/job/35251034969?pr=29065
-    "prompty",
-]
-
-
-def all_package_dirs() -> Set[str]:
-    return {
-        "/".join(path.split("/")[:-1]).lstrip("./")
-        for path in glob.glob("./libs/**/pyproject.toml", recursive=True)
-        if "libs/cli" not in path and "libs/standard-tests" not in path
-    }
-
-
-def dependents_graph() -> dict:
-    """Construct a mapping of package -> dependents
-
-    Done such that we can run tests on all dependents of a package when a change is made.
-    """
-    dependents = defaultdict(set)
-
-    for path in glob.glob("./libs/**/pyproject.toml", recursive=True):
-        if "template" in path:
-            continue
-
-        # load regular and test deps from pyproject.toml
-        with open(path, "rb") as f:
-            pyproject = tomllib.load(f)
-
-        pkg_dir = "libs" + "/".join(path.split("libs")[1].split("/")[:-1])
-        for dep in [
-            *pyproject["project"]["dependencies"],
-            *pyproject["dependency-groups"]["test"],
-        ]:
-            requirement = Requirement(dep)
-            package_name = requirement.name
-            if "langchain" in dep:
-                dependents[package_name].add(pkg_dir)
-                continue
-
-        # load extended deps from extended_testing_deps.txt
-        package_path = Path(path).parent
-        extended_requirement_path = package_path / "extended_testing_deps.txt"
-        if extended_requirement_path.exists():
-            with open(extended_requirement_path, "r") as f:
-                extended_deps = f.read().splitlines()
-                for depline in extended_deps:
-                    if depline.startswith("-e "):
-                        # editable dependency
-                        assert depline.startswith("-e ../partners/"), (
-                            "Extended test deps should only editable install partner packages"
-                        )
-                        partner = depline.split("partners/")[1]
-                        dep = f"langchain-{partner}"
-                    else:
-                        dep = depline.split("==")[0]
-
-                    if "langchain" in dep:
-                        dependents[dep].add(pkg_dir)
-
-    for k in dependents:
-        for partner in IGNORED_PARTNERS:
-            if f"libs/partners/{partner}" in dependents[k]:
-                dependents[k].remove(f"libs/partners/{partner}")
-    return dependents
-
-
-def add_dependents(dirs_to_eval: Set[str], dependents: dict) -> List[str]:
-    updated = set()
-    for dir_ in dirs_to_eval:
-        # handle core manually because it has so many dependents
-        if "core" in dir_:
-            updated.add(dir_)
-            continue
-        pkg = "langchain-" + dir_.split("/")[-1]
-        updated.update(dependents[pkg])
-        updated.add(dir_)
-    return list(updated)
-
-
-def _get_configs_for_single_dir(job: str, dir_: str) -> List[Dict[str, str]]:
-    if job == "test-pydantic":
-        return _get_pydantic_test_configs(dir_)
-
-    if job == "codspeed":
-        py_versions = ["3.12"]  # 3.13 is not yet supported
-    elif dir_ == "libs/core":
-        py_versions = ["3.10", "3.11", "3.12", "3.13", "3.14"]
-    # custom logic for specific directories
-
-    elif dir_ == "libs/langchain" and job == "extended-tests":
-        py_versions = ["3.10", "3.13"]
-    elif dir_ == "libs/langchain_v1":
-        py_versions = ["3.10", "3.13"]
-    elif dir_ in {"libs/cli"}:
-        py_versions = ["3.10", "3.13"]
-
-    elif dir_ == ".":
-        # unable to install with 3.13 because tokenizers doesn't support 3.13 yet
-        py_versions = ["3.10", "3.12"]
-    else:
-        py_versions = ["3.10", "3.13"]
-
-    return [{"working-directory": dir_, "python-version": py_v} for py_v in py_versions]
-
-
-def _get_pydantic_test_configs(
-    dir_: str, *, python_version: str = "3.11"
-) -> List[Dict[str, str]]:
-    with open("./libs/core/uv.lock", "rb") as f:
-        core_uv_lock_data = tomllib.load(f)
-    for package in core_uv_lock_data["package"]:
-        if package["name"] == "pydantic":
-            core_max_pydantic_minor = package["version"].split(".")[1]
-            break
-
-    with open(f"./{dir_}/uv.lock", "rb") as f:
-        dir_uv_lock_data = tomllib.load(f)
-
-    for package in dir_uv_lock_data["package"]:
-        if package["name"] == "pydantic":
-            dir_max_pydantic_minor = package["version"].split(".")[1]
-            break
-
-    core_min_pydantic_version = get_min_version_from_toml(
-        "./libs/core/pyproject.toml", "release", python_version, include=["pydantic"]
-    )["pydantic"]
-    core_min_pydantic_minor = (
-        core_min_pydantic_version.split(".")[1]
-        if "." in core_min_pydantic_version
-        else "0"
-    )
-    dir_min_pydantic_version = get_min_version_from_toml(
-        f"./{dir_}/pyproject.toml", "release", python_version, include=["pydantic"]
-    ).get("pydantic", "0.0.0")
-    dir_min_pydantic_minor = (
-        dir_min_pydantic_version.split(".")[1]
-        if "." in dir_min_pydantic_version
-        else "0"
-    )
-
-    max_pydantic_minor = min(
-        int(dir_max_pydantic_minor),
-        int(core_max_pydantic_minor),
-    )
-    min_pydantic_minor = max(
-        int(dir_min_pydantic_minor),
-        int(core_min_pydantic_minor),
-    )
-
-    configs = [
-        {
-            "working-directory": dir_,
-            "pydantic-version": f"2.{v}.0",
-            "python-version": python_version,
-        }
-        for v in range(min_pydantic_minor, max_pydantic_minor + 1)
-    ]
-    return configs
-
-
-def _get_configs_for_multi_dirs(
-    job: str, dirs_to_run: Dict[str, Set[str]], dependents: dict
-) -> List[Dict[str, str]]:
-    if job == "lint":
-        dirs = add_dependents(
-            dirs_to_run["lint"] | dirs_to_run["test"] | dirs_to_run["extended-test"],
-            dependents,
-        )
-    elif job in ["test", "compile-integration-tests", "dependencies", "test-pydantic"]:
-        dirs = add_dependents(
-            dirs_to_run["test"] | dirs_to_run["extended-test"], dependents
-        )
-    elif job == "extended-tests":
-        dirs = list(dirs_to_run["extended-test"])
-    elif job == "codspeed":
-        dirs = list(dirs_to_run["codspeed"])
-    else:
-        raise ValueError(f"Unknown job: {job}")
-
-    return [
-        config for dir_ in dirs for config in _get_configs_for_single_dir(job, dir_)
-    ]
-
-
-if __name__ == "__main__":
-    files = sys.argv[1:]
-
-    dirs_to_run: Dict[str, set] = {
-        "lint": set(),
-        "test": set(),
-        "extended-test": set(),
-        "codspeed": set(),
-    }
-    docs_edited = False
-
-    if len(files) >= 300:
-        # max diff length is 300 files - there are likely files missing
-        dirs_to_run["lint"] = all_package_dirs()
-        dirs_to_run["test"] = all_package_dirs()
-        dirs_to_run["extended-test"] = set(LANGCHAIN_DIRS)
-
-    for file in files:
-        if any(
-            file.startswith(dir_)
-            for dir_ in (
-                ".github/workflows",
-                ".github/tools",
-                ".github/actions",
-                ".github/scripts/check_diff.py",
-            )
-        ):
-            # Infrastructure changes (workflows, actions, CI scripts) trigger tests on
-            # all core packages as a safety measure. This ensures that changes to CI/CD
-            # infrastructure don't inadvertently break package testing, even if the change
-            # appears unrelated (e.g., documentation build workflows). This is intentionally
-            # conservative to catch unexpected side effects from workflow modifications.
-            #
-            # Example: A PR modifying .github/workflows/api_doc_build.yml will trigger
-            # lint/test jobs for libs/core, libs/text-splitters, libs/langchain, and
-            # libs/langchain_v1, even though the workflow may only affect documentation.
-            dirs_to_run["extended-test"].update(LANGCHAIN_DIRS)
-
-        if file.startswith("libs/core"):
-            dirs_to_run["codspeed"].add("libs/core")
-        if any(file.startswith(dir_) for dir_ in LANGCHAIN_DIRS):
-            # add that dir and all dirs after in LANGCHAIN_DIRS
-            # for extended testing
-
-            found = False
-            for dir_ in LANGCHAIN_DIRS:
-                if dir_ == "libs/core" and IGNORE_CORE_DEPENDENTS:
-                    dirs_to_run["extended-test"].add(dir_)
-                    continue
-                if file.startswith(dir_):
-                    found = True
-                if found:
-                    dirs_to_run["extended-test"].add(dir_)
-        elif file.startswith("libs/standard-tests"):
-            # TODO: update to include all packages that rely on standard-tests (all partner packages)
-            # Note: won't run on external repo partners
-            dirs_to_run["lint"].add("libs/standard-tests")
-            dirs_to_run["test"].add("libs/standard-tests")
-            dirs_to_run["test"].add("libs/partners/mistralai")
-            dirs_to_run["test"].add("libs/partners/openai")
-            dirs_to_run["test"].add("libs/partners/anthropic")
-            dirs_to_run["test"].add("libs/partners/fireworks")
-            dirs_to_run["test"].add("libs/partners/groq")
-
-        elif file.startswith("libs/cli"):
-            dirs_to_run["lint"].add("libs/cli")
-            dirs_to_run["test"].add("libs/cli")
-
-        elif file.startswith("libs/partners"):
-            partner_dir = file.split("/")[2]
-            if os.path.isdir(f"libs/partners/{partner_dir}") and [
-                filename
-                for filename in os.listdir(f"libs/partners/{partner_dir}")
-                if not filename.startswith(".")
-            ] != ["README.md"]:
-                dirs_to_run["test"].add(f"libs/partners/{partner_dir}")
-                dirs_to_run["codspeed"].add(f"libs/partners/{partner_dir}")
-            # Skip if the directory was deleted or is just a tombstone readme
-        elif file.startswith("libs/"):
-            # Check if this is a root-level file in libs/ (e.g., libs/README.md)
-            file_parts = file.split("/")
-            if len(file_parts) == 2:
-                # Root-level file in libs/, skip it (no tests needed)
-                continue
-            raise ValueError(
-                f"Unknown lib: {file}. check_diff.py likely needs "
-                "an update for this new library!"
-            )
-        elif file in [
-            "pyproject.toml",
-            "uv.lock",
-        ]:  # root uv files
-            docs_edited = True
-
-    dependents = dependents_graph()
-
-    # we now have dirs_by_job
-    # todo: clean this up
-    map_job_to_configs = {
-        job: _get_configs_for_multi_dirs(job, dirs_to_run, dependents)
-        for job in [
-            "lint",
-            "test",
-            "extended-tests",
-            "compile-integration-tests",
-            "dependencies",
-            "test-pydantic",
-            "codspeed",
-        ]
-    }
-
-    for key, value in map_job_to_configs.items():
-        json_output = json.dumps(value)
-        print(f"{key}={json_output}")

.github/scripts/check_prerelease_dependencies.py

@@ -1,36 +0,0 @@
-"""Check that no dependencies allow prereleases unless we're releasing a prerelease."""
-
-import sys
-
-import tomllib
-
-if __name__ == "__main__":
-    # Get the TOML file path from the command line argument
-    toml_file = sys.argv[1]
-
-    with open(toml_file, "rb") as file:
-        toml_data = tomllib.load(file)
-
-    # See if we're releasing an rc or dev version
-    version = toml_data["project"]["version"]
-    releasing_rc = "rc" in version or "dev" in version
-
-    # If not, iterate through dependencies and make sure none allow prereleases
-    if not releasing_rc:
-        dependencies = toml_data["project"]["dependencies"]
-        for dep_version in dependencies:
-            dep_version_string = (
-                dep_version["version"] if isinstance(dep_version, dict) else dep_version
-            )
-
-            if "rc" in dep_version_string:
-                raise ValueError(
-                    f"Dependency {dep_version} has a prerelease version. Please remove this."
-                )
-
-            if isinstance(dep_version, dict) and dep_version.get(
-                "allow-prereleases", False
-            ):
-                raise ValueError(
-                    f"Dependency {dep_version} has allow-prereleases set to true. Please remove this."
-                )

.github/scripts/get_min_versions.py

@@ -1,199 +0,0 @@
-"""Get minimum versions of dependencies from a pyproject.toml file."""
-
-import sys
-from collections import defaultdict
-
-if sys.version_info >= (3, 11):
-    import tomllib
-else:
-    # For Python 3.10 and below, which doesnt have stdlib tomllib
-    import tomli as tomllib
-
-import re
-from typing import List
-
-import requests
-from packaging.requirements import Requirement
-from packaging.specifiers import SpecifierSet
-from packaging.version import Version, parse
-
-MIN_VERSION_LIBS = [
-    "langchain-core",
-    "langchain",
-    "langchain-text-splitters",
-    "numpy",
-    "SQLAlchemy",
-]
-
-# some libs only get checked on release because of simultaneous changes in
-# multiple libs
-SKIP_IF_PULL_REQUEST = [
-    "langchain-core",
-    "langchain-text-splitters",
-    "langchain",
-]
-
-
-def get_pypi_versions(package_name: str) -> List[str]:
-    """Fetch all available versions for a package from PyPI.
-
-    Args:
-        package_name: Name of the package
-
-    Returns:
-        List of all available versions
-
-    Raises:
-        requests.exceptions.RequestException: If PyPI API request fails
-        KeyError: If package not found or response format unexpected
-    """
-    pypi_url = f"https://pypi.org/pypi/{package_name}/json"
-    response = requests.get(pypi_url)
-    response.raise_for_status()
-    return list(response.json()["releases"].keys())
-
-
-def get_minimum_version(package_name: str, spec_string: str) -> str | None:
-    """Find the minimum published version that satisfies the given constraints.
-
-    Args:
-        package_name: Name of the package
-        spec_string: Version specification string (e.g., ">=0.2.43,<0.4.0,!=0.3.0")
-
-    Returns:
-        Minimum compatible version or None if no compatible version found
-    """
-    # Rewrite occurrences of ^0.0.z to 0.0.z (can be anywhere in constraint string)
-    spec_string = re.sub(r"\^0\.0\.(\d+)", r"0.0.\1", spec_string)
-    # Rewrite occurrences of ^0.y.z to >=0.y.z,<0.y+1 (can be anywhere in constraint string)
-    for y in range(1, 10):
-        spec_string = re.sub(
-            rf"\^0\.{y}\.(\d+)", rf">=0.{y}.\1,<0.{y + 1}", spec_string
-        )
-    # Rewrite occurrences of ^x.y.z to >=x.y.z,<x+1.0.0 (can be anywhere in constraint string)
-    for x in range(1, 10):
-        spec_string = re.sub(
-            rf"\^{x}\.(\d+)\.(\d+)", rf">={x}.\1.\2,<{x + 1}", spec_string
-        )
-
-    spec_set = SpecifierSet(spec_string)
-    all_versions = get_pypi_versions(package_name)
-
-    valid_versions = []
-    for version_str in all_versions:
-        try:
-            version = parse(version_str)
-            if spec_set.contains(version):
-                valid_versions.append(version)
-        except ValueError:
-            continue
-
-    return str(min(valid_versions)) if valid_versions else None
-
-
-def _check_python_version_from_requirement(
-    requirement: Requirement, python_version: str
-) -> bool:
-    if not requirement.marker:
-        return True
-    else:
-        marker_str = str(requirement.marker)
-        if "python_version" or "python_full_version" in marker_str:
-            python_version_str = "".join(
-                char
-                for char in marker_str
-                if char.isdigit() or char in (".", "<", ">", "=", ",")
-            )
-            return check_python_version(python_version, python_version_str)
-        return True
-
-
-def get_min_version_from_toml(
-    toml_path: str,
-    versions_for: str,
-    python_version: str,
-    *,
-    include: list | None = None,
-):
-    # Parse the TOML file
-    with open(toml_path, "rb") as file:
-        toml_data = tomllib.load(file)
-
-    dependencies = defaultdict(list)
-    for dep in toml_data["project"]["dependencies"]:
-        requirement = Requirement(dep)
-        dependencies[requirement.name].append(requirement)
-
-    # Initialize a dictionary to store the minimum versions
-    min_versions = {}
-
-    # Iterate over the libs in MIN_VERSION_LIBS
-    for lib in set(MIN_VERSION_LIBS + (include or [])):
-        if versions_for == "pull_request" and lib in SKIP_IF_PULL_REQUEST:
-            # some libs only get checked on release because of simultaneous
-            # changes in multiple libs
-            continue
-        # Check if the lib is present in the dependencies
-        if lib in dependencies:
-            if include and lib not in include:
-                continue
-            requirements = dependencies[lib]
-            for requirement in requirements:
-                if _check_python_version_from_requirement(requirement, python_version):
-                    version_string = str(requirement.specifier)
-                    break
-
-            # Use parse_version to get the minimum supported version from version_string
-            min_version = get_minimum_version(lib, version_string)
-
-            # Store the minimum version in the min_versions dictionary
-            min_versions[lib] = min_version
-
-    return min_versions
-
-
-def check_python_version(version_string, constraint_string):
-    """Check if the given Python version matches the given constraints.
-
-    Args:
-        version_string: A string representing the Python version (e.g. "3.8.5").
-        constraint_string: A string representing the package's Python version
-            constraints (e.g. ">=3.6, <4.0").
-
-    Returns:
-        True if the version matches the constraints
-    """
-
-    # Rewrite occurrences of ^0.0.z to 0.0.z (can be anywhere in constraint string)
-    constraint_string = re.sub(r"\^0\.0\.(\d+)", r"0.0.\1", constraint_string)
-    # Rewrite occurrences of ^0.y.z to >=0.y.z,<0.y+1.0 (can be anywhere in constraint string)
-    for y in range(1, 10):
-        constraint_string = re.sub(
-            rf"\^0\.{y}\.(\d+)", rf">=0.{y}.\1,<0.{y + 1}.0", constraint_string
-        )
-    # Rewrite occurrences of ^x.y.z to >=x.y.z,<x+1.0.0 (can be anywhere in constraint string)
-    for x in range(1, 10):
-        constraint_string = re.sub(
-            rf"\^{x}\.0\.(\d+)", rf">={x}.0.\1,<{x + 1}.0.0", constraint_string
-        )
-
-    try:
-        version = Version(version_string)
-        constraints = SpecifierSet(constraint_string)
-        return version in constraints
-    except Exception as e:
-        print(f"Error: {e}")
-        return False
-
-
-if __name__ == "__main__":
-    # Get the TOML file path from the command line argument
-    toml_file = sys.argv[1]
-    versions_for = sys.argv[2]
-    python_version = sys.argv[3]
-    assert versions_for in ["release", "pull_request"]
-
-    # Call the function to get the minimum versions
-    min_versions = get_min_version_from_toml(toml_file, versions_for, python_version)
-
-    print(" ".join([f"{lib}=={version}" for lib, version in min_versions.items()]))

.github/tools/git-restore-mtime

@@ -81,93 +81,56 @@ import time
 __version__ = "2022.12+dev"
 
 # Update symlinks only if the platform supports not following them
-UPDATE_SYMLINKS = bool(os.utime in getattr(os, "supports_follow_symlinks", []))
+UPDATE_SYMLINKS = bool(os.utime in getattr(os, 'supports_follow_symlinks', []))
 
 # Call os.path.normpath() only if not in a POSIX platform (Windows)
-NORMALIZE_PATHS = os.path.sep != "/"
+NORMALIZE_PATHS = (os.path.sep != '/')
 
 # How many files to process in each batch when re-trying merge commits
 STEPMISSING = 100
 
 # (Extra) keywords for the os.utime() call performed by touch()
-UTIME_KWS = {} if not UPDATE_SYMLINKS else {"follow_symlinks": False}
+UTIME_KWS = {} if not UPDATE_SYMLINKS else {'follow_symlinks': False}
 
 
 # Command-line interface ######################################################
 
-
 def parse_args():
-    parser = argparse.ArgumentParser(description=__doc__.split("\n---")[0])
+    parser = argparse.ArgumentParser(
+        description=__doc__.split('\n---')[0])
 
     group = parser.add_mutually_exclusive_group()
-    group.add_argument(
-        "--quiet",
-        "-q",
-        dest="loglevel",
-        action="store_const",
-        const=logging.WARNING,
-        default=logging.INFO,
-        help="Suppress informative messages and summary statistics.",
-    )
-    group.add_argument(
-        "--verbose",
-        "-v",
-        action="count",
-        help="""
+    group.add_argument('--quiet', '-q', dest='loglevel',
+        action="store_const", const=logging.WARNING, default=logging.INFO,
+        help="Suppress informative messages and summary statistics.")
+    group.add_argument('--verbose', '-v', action="count", help="""
         Print additional information for each processed file.
         Specify twice to further increase verbosity.
-        """,
-    )
+        """)
 
-    parser.add_argument(
-        "--cwd",
-        "-C",
-        metavar="DIRECTORY",
-        help="""
+    parser.add_argument('--cwd', '-C', metavar="DIRECTORY", help="""
         Run as if %(prog)s was started in directory %(metavar)s.
         This affects how --work-tree, --git-dir and PATHSPEC arguments are handled.
         See 'man 1 git' or 'git --help' for more information.
-        """,
-    )
+        """)
 
-    parser.add_argument(
-        "--git-dir",
-        dest="gitdir",
-        metavar="GITDIR",
-        help="""
+    parser.add_argument('--git-dir', dest='gitdir', metavar="GITDIR", help="""
         Path to the git repository, by default auto-discovered by searching
         the current directory and its parents for a .git/ subdirectory.
-        """,
-    )
+        """)
 
-    parser.add_argument(
-        "--work-tree",
-        dest="workdir",
-        metavar="WORKTREE",
-        help="""
+    parser.add_argument('--work-tree', dest='workdir', metavar="WORKTREE", help="""
         Path to the work tree root, by default the parent of GITDIR if it's
         automatically discovered, or the current directory if GITDIR is set.
-        """,
-    )
+        """)
 
-    parser.add_argument(
-        "--force",
-        "-f",
-        default=False,
-        action="store_true",
-        help="""
+    parser.add_argument('--force', '-f', default=False, action="store_true", help="""
         Force updating files with uncommitted modifications.
         Untracked files and uncommitted deletions, renames and additions are
         always ignored.
-        """,
-    )
+        """)
 
-    parser.add_argument(
-        "--merge",
-        "-m",
-        default=False,
-        action="store_true",
-        help="""
+    parser.add_argument('--merge', '-m', default=False, action="store_true", help="""
         Include merge commits.
         Leads to more recent times and more files per commit, thus with the same
         time, which may or may not be what you want.
@@ -175,130 +138,71 @@ def parse_args():
         are found sooner, which can improve performance, sometimes substantially.
         But as merge commits are usually huge, processing them may also take longer.
         By default, merge commits are only used for files missing from regular commits.
-        """,
-    )
+        """)
 
-    parser.add_argument(
-        "--first-parent",
-        default=False,
-        action="store_true",
-        help="""
+    parser.add_argument('--first-parent', default=False, action="store_true", help="""
         Consider only the first parent, the "main branch", when evaluating merge commits.
         Only effective when merge commits are processed, either when --merge is
         used or when finding missing files after the first regular log search.
         See --skip-missing.
-        """,
-    )
+        """)
 
-    parser.add_argument(
-        "--skip-missing",
-        "-s",
-        dest="missing",
-        default=True,
-        action="store_false",
-        help="""
+    parser.add_argument('--skip-missing', '-s', dest="missing", default=True,
+        action="store_false", help="""
         Do not try to find missing files.
         If merge commits were not evaluated with --merge and some files were
         not found in regular commits, by default %(prog)s searches for these
         files again in the merge commits.
         This option disables this retry, so files found only in merge commits
         will not have their timestamp updated.
-        """,
-    )
+        """)
 
-    parser.add_argument(
-        "--no-directories",
-        "-D",
-        dest="dirs",
-        default=True,
-        action="store_false",
-        help="""
+    parser.add_argument('--no-directories', '-D', dest='dirs', default=True,
+        action="store_false", help="""
         Do not update directory timestamps.
         By default, use the time of its most recently created, renamed or deleted file.
         Note that just modifying a file will NOT update its directory time.
-        """,
-    )
+        """)
 
-    parser.add_argument(
-        "--test",
-        "-t",
-        default=False,
-        action="store_true",
-        help="Test run: do not actually update any file timestamp.",
-    )
+    parser.add_argument('--test', '-t', default=False, action="store_true",
+        help="Test run: do not actually update any file timestamp.")
 
-    parser.add_argument(
-        "--commit-time",
-        "-c",
-        dest="commit_time",
-        default=False,
-        action="store_true",
-        help="Use commit time instead of author time.",
-    )
+    parser.add_argument('--commit-time', '-c', dest='commit_time', default=False,
+        action='store_true', help="Use commit time instead of author time.")
 
-    parser.add_argument(
-        "--oldest-time",
-        "-o",
-        dest="reverse_order",
-        default=False,
-        action="store_true",
-        help="""
+    parser.add_argument('--oldest-time', '-o', dest='reverse_order', default=False,
+        action='store_true', help="""
         Update times based on the oldest, instead of the most recent commit of a file.
         This reverses the order in which the git log is processed to emulate a
         file "creation" date. Note this will be inaccurate for files deleted and
         re-created at later dates.
-        """,
-    )
+        """)
 
-    parser.add_argument(
-        "--skip-older-than",
-        metavar="SECONDS",
-        type=int,
-        help="""
+    parser.add_argument('--skip-older-than', metavar='SECONDS', type=int, help="""
         Ignore files that are currently older than %(metavar)s.
         Useful in workflows that assume such files already have a correct timestamp,
         as it may improve performance by processing fewer files.
-        """,
-    )
+        """)
 
-    parser.add_argument(
-        "--skip-older-than-commit",
-        "-N",
-        default=False,
-        action="store_true",
-        help="""
+    parser.add_argument('--skip-older-than-commit', '-N', default=False,
+        action='store_true', help="""
         Ignore files older than the timestamp it would be updated to.
         Such files may be considered "original", likely in the author's repository.
-        """,
-    )
+        """)
 
-    parser.add_argument(
-        "--unique-times",
-        default=False,
-        action="store_true",
-        help="""
+    parser.add_argument('--unique-times', default=False, action="store_true", help="""
         Set the microseconds to a unique value per commit.
         Allows telling apart changes that would otherwise have identical timestamps,
         as git's time accuracy is in seconds.
-        """,
-    )
+        """)
 
-    parser.add_argument(
-        "pathspec",
-        nargs="*",
-        metavar="PATHSPEC",
-        help="""
+    parser.add_argument('pathspec', nargs='*', metavar='PATHSPEC', help="""
         Only modify paths matching %(metavar)s, relative to current directory.
         By default, update all but untracked files and submodules.
-        """,
-    )
+        """)
 
-    parser.add_argument(
-        "--version",
-        "-V",
-        action="version",
-        version="%(prog)s version {version}".format(version=get_version()),
-    )
+    parser.add_argument('--version', '-V', action='version',
+        version='%(prog)s version {version}'.format(version=get_version()))
 
     args_ = parser.parse_args()
     if args_.verbose:
@@ -308,18 +212,17 @@ def parse_args():
 
 
 def get_version(version=__version__):
-    if not version.endswith("+dev"):
+    if not version.endswith('+dev'):
         return version
     try:
         cwd = os.path.dirname(os.path.realpath(__file__))
-        return Git(cwd=cwd, errors=False).describe().lstrip("v")
+        return Git(cwd=cwd, errors=False).describe().lstrip('v')
     except Git.Error:
-        return "-".join((version, "unknown"))
+        return '-'.join((version, "unknown"))
 
 
 # Helper functions ############################################################
 
-
 def setup_logging():
     """Add TRACE logging level and corresponding method, return the root logger"""
     logging.TRACE = TRACE = logging.DEBUG // 2
@@ -352,13 +255,11 @@ def normalize(path):
     if path and path[0] == '"':
         # Python 2: path = path[1:-1].decode("string-escape")
         # Python 3: https://stackoverflow.com/a/46650050/624066
-        path = (
-            path[1:-1]  # Remove enclosing double quotes
-            .encode("latin1")  # Convert to bytes, required by 'unicode-escape'
-            .decode("unicode-escape")  # Perform the actual octal-escaping decode
-            .encode("latin1")  # 1:1 mapping to bytes, UTF-8 encoded
-            .decode("utf8", "surrogateescape")
-        )  # Decode from UTF-8
+        path = (path[1:-1]                 # Remove enclosing double quotes
+                .encode('latin1')          # Convert to bytes, required by 'unicode-escape'
+                .decode('unicode-escape')  # Perform the actual octal-escaping decode
+                .encode('latin1')          # 1:1 mapping to bytes, UTF-8 encoded
+                .decode('utf8', 'surrogateescape'))  # Decode from UTF-8
     if NORMALIZE_PATHS:
         # Make sure the slash matches the OS; for Windows we need a backslash
         path = os.path.normpath(path)
@@ -381,12 +282,12 @@ def touch_ns(path, mtime_ns):
 
 def isodate(secs: int):
     # time.localtime() accepts floats, but discards fractional part
-    return time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(secs))
+    return time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(secs))
 
 
 def isodate_ns(ns: int):
     # for integers fromtimestamp() is equivalent and ~16% slower than isodate()
-    return datetime.datetime.fromtimestamp(ns / 1000000000).isoformat(sep=" ")
+    return datetime.datetime.fromtimestamp(ns / 1000000000).isoformat(sep=' ')
 
 
 def get_mtime_ns(secs: int, idx: int):
@@ -404,49 +305,35 @@ def get_mtime_path(path):
 
 # Git class and parse_log(), the heart of the script ##########################
 
-
 class Git:
     def __init__(self, workdir=None, gitdir=None, cwd=None, errors=True):
-        self.gitcmd = ["git"]
+        self.gitcmd = ['git']
         self.errors = errors
         self._proc = None
-        if workdir:
-            self.gitcmd.extend(("--work-tree", workdir))
-        if gitdir:
-            self.gitcmd.extend(("--git-dir", gitdir))
-        if cwd:
-            self.gitcmd.extend(("-C", cwd))
+        if workdir: self.gitcmd.extend(('--work-tree', workdir))
+        if gitdir:  self.gitcmd.extend(('--git-dir',   gitdir))
+        if cwd:     self.gitcmd.extend(('-C',          cwd))
         self.workdir, self.gitdir = self._get_repo_dirs()
 
     def ls_files(self, paths: list = None):
-        return (normalize(_) for _ in self._run("ls-files --full-name", paths))
+        return (normalize(_) for _ in self._run('ls-files --full-name', paths))
 
     def ls_dirty(self, force=False):
-        return (
-            normalize(_[3:].split(" -> ", 1)[-1])
-            for _ in self._run("status --porcelain")
-            if _[:2] != "??" and (not force or (_[0] in ("R", "A") or _[1] == "D"))
-        )
+        return (normalize(_[3:].split(' -> ', 1)[-1])
+                for _ in self._run('status --porcelain')
+                if _[:2] != '??' and (not force or (_[0] in ('R', 'A')
+                                                    or _[1] == 'D')))
 
-    def log(
-        self,
-        merge=False,
-        first_parent=False,
-        commit_time=False,
-        reverse_order=False,
-        paths: list = None,
-    ):
-        cmd = "whatchanged --pretty={}".format("%ct" if commit_time else "%at")
-        if merge:
-            cmd += " -m"
-        if first_parent:
-            cmd += " --first-parent"
-        if reverse_order:
-            cmd += " --reverse"
+    def log(self, merge=False, first_parent=False, commit_time=False,
+            reverse_order=False, paths: list = None):
+        cmd = 'whatchanged --pretty={}'.format('%ct' if commit_time else '%at')
+        if merge:         cmd += ' -m'
+        if first_parent:  cmd += ' --first-parent'
+        if reverse_order: cmd += ' --reverse'
         return self._run(cmd, paths)
 
     def describe(self):
-        return self._run("describe --tags", check=True)[0]
+        return self._run('describe --tags', check=True)[0]
 
     def terminate(self):
         if self._proc is None:
@@ -458,22 +345,18 @@ class Git:
             pass
 
     def _get_repo_dirs(self):
-        return (
-            os.path.normpath(_)
-            for _ in self._run(
-                "rev-parse --show-toplevel --absolute-git-dir", check=True
-            )
-        )
+        return (os.path.normpath(_) for _ in
+            self._run('rev-parse --show-toplevel --absolute-git-dir', check=True))
 
     def _run(self, cmdstr: str, paths: list = None, output=True, check=False):
         cmdlist = self.gitcmd + shlex.split(cmdstr)
         if paths:
-            cmdlist.append("--")
+            cmdlist.append('--')
             cmdlist.extend(paths)
-        popen_args = dict(universal_newlines=True, encoding="utf8")
+        popen_args = dict(universal_newlines=True, encoding='utf8')
         if not self.errors:
-            popen_args["stderr"] = subprocess.DEVNULL
-        log.trace("Executing: %s", " ".join(cmdlist))
+            popen_args['stderr'] = subprocess.DEVNULL
+        log.trace("Executing: %s", ' '.join(cmdlist))
         if not output:
             return subprocess.call(cmdlist, **popen_args)
         if check:
@@ -496,26 +379,30 @@ def parse_log(filelist, dirlist, stats, git, merge=False, filterlist=None):
     mtime = 0
     datestr = isodate(0)
     for line in git.log(
-        merge, args.first_parent, args.commit_time, args.reverse_order, filterlist
+            merge,
+            args.first_parent,
+            args.commit_time,
+            args.reverse_order,
+            filterlist
     ):
-        stats["loglines"] += 1
+        stats['loglines'] += 1
 
         # Blank line between Date and list of files
         if not line:
             continue
 
         # Date line
-        if line[0] != ":":  # Faster than `not line.startswith(':')`
-            stats["commits"] += 1
+        if line[0] != ':':  # Faster than `not line.startswith(':')`
+            stats['commits'] += 1
             mtime = int(line)
             if args.unique_times:
-                mtime = get_mtime_ns(mtime, stats["commits"])
+                mtime = get_mtime_ns(mtime, stats['commits'])
             if args.debug:
                 datestr = isodate(mtime)
             continue
 
         # File line: three tokens if it describes a renaming, otherwise two
-        tokens = line.split("\t")
+        tokens = line.split('\t')
 
         # Possible statuses:
         # M: Modified (content changed)
@@ -524,7 +411,7 @@ def parse_log(filelist, dirlist, stats, git, merge=False, filterlist=None):
         # T: Type changed: to/from regular file, symlinks, submodules
         # R099: Renamed (moved), with % of unchanged content. 100 = pure rename
         # Not possible in log: C=Copied, U=Unmerged, X=Unknown, B=pairing Broken
-        status = tokens[0].split(" ")[-1]
+        status = tokens[0].split(' ')[-1]
         file = tokens[-1]
 
         # Handles non-ASCII chars and OS path separator
@@ -532,76 +419,56 @@ def parse_log(filelist, dirlist, stats, git, merge=False, filterlist=None):
 
         def do_file():
             if args.skip_older_than_commit and get_mtime_path(file) <= mtime:
-                stats["skip"] += 1
+                stats['skip'] += 1
                 return
             if args.debug:
-                log.debug(
-                    "%d\t%d\t%d\t%s\t%s",
-                    stats["loglines"],
-                    stats["commits"],
-                    stats["files"],
-                    datestr,
-                    file,
-                )
+                log.debug("%d\t%d\t%d\t%s\t%s",
+                          stats['loglines'], stats['commits'], stats['files'],
+                          datestr, file)
             try:
                 touch(os.path.join(git.workdir, file), mtime)
-                stats["touches"] += 1
+                stats['touches'] += 1
             except Exception as e:
                 log.error("ERROR: %s: %s", e, file)
-                stats["errors"] += 1
+                stats['errors'] += 1
 
         def do_dir():
             if args.debug:
-                log.debug(
-                    "%d\t%d\t-\t%s\t%s",
-                    stats["loglines"],
-                    stats["commits"],
-                    datestr,
-                    "{}/".format(dirname or "."),
-                )
+                log.debug("%d\t%d\t-\t%s\t%s",
+                          stats['loglines'], stats['commits'],
+                          datestr, "{}/".format(dirname or '.'))
             try:
                 touch(os.path.join(git.workdir, dirname), mtime)
-                stats["dirtouches"] += 1
+                stats['dirtouches'] += 1
             except Exception as e:
                 log.error("ERROR: %s: %s", e, dirname)
-                stats["direrrors"] += 1
+                stats['direrrors'] += 1
 
         if file in filelist:
-            stats["files"] -= 1
+            stats['files'] -= 1
             filelist.remove(file)
             do_file()
 
-        if args.dirs and status in ("A", "D"):
+        if args.dirs and status in ('A', 'D'):
             dirname = os.path.dirname(file)
             if dirname in dirlist:
                 dirlist.remove(dirname)
                 do_dir()
 
         # All files done?
-        if not stats["files"]:
+        if not stats['files']:
             git.terminate()
             return
 
 
 # Main Logic ##################################################################
 
-
 def main():
     start = time.time()  # yes, Wall time. CPU time is not realistic for users.
-    stats = {
-        _: 0
-        for _ in (
-            "loglines",
-            "commits",
-            "touches",
-            "skip",
-            "errors",
-            "dirtouches",
-            "direrrors",
-        )
-    }
+    stats = {_: 0 for _ in ('loglines', 'commits', 'touches', 'skip', 'errors',
+                            'dirtouches', 'direrrors')}
 
-    logging.basicConfig(level=args.loglevel, format="%(message)s")
+    logging.basicConfig(level=args.loglevel, format='%(message)s')
     log.trace("Arguments: %s", args)
 
     # First things first: Where and Who are we?
@@ -632,16 +499,13 @@ def main():
 
             # Symlink (to file, to dir or broken - git handles the same way)
             if not UPDATE_SYMLINKS and os.path.islink(fullpath):
-                log.warning(
-                    "WARNING: Skipping symlink, no OS support for updates: %s", path
-                )
+                log.warning("WARNING: Skipping symlink, no OS support for updates: %s",
+                            path)
                 continue
 
             # skip files which are older than given threshold
-            if (
-                args.skip_older_than
-                and start - get_mtime_path(fullpath) > args.skip_older_than
-            ):
+            if (args.skip_older_than
+                    and start - get_mtime_path(fullpath) > args.skip_older_than):
                 continue
 
             # Always add files relative to worktree root
@@ -655,17 +519,15 @@ def main():
     else:
         dirty = set(git.ls_dirty())
         if dirty:
-            log.warning(
-                "WARNING: Modified files in the working directory were ignored."
-                "\nTo include such files, commit your changes or use --force."
-            )
+            log.warning("WARNING: Modified files in the working directory were ignored."
+                "\nTo include such files, commit your changes or use --force.")
             filelist -= dirty
 
     # Build dir list to be processed
     dirlist = set(os.path.dirname(_) for _ in filelist) if args.dirs else set()
 
-    stats["totalfiles"] = stats["files"] = len(filelist)
-    log.info("{0:,} files to be processed in work dir".format(stats["totalfiles"]))
+    stats['totalfiles'] = stats['files'] = len(filelist)
+    log.info("{0:,} files to be processed in work dir".format(stats['totalfiles']))
 
     if not filelist:
         # Nothing to do. Exit silently and without errors, just like git does
@@ -682,18 +544,10 @@ def main():
         if args.missing and not args.merge:
             filterlist = list(filelist)
             missing = len(filterlist)
-            log.info(
-                "{0:,} files not found in log, trying merge commits".format(missing)
-            )
+            log.info("{0:,} files not found in log, trying merge commits".format(missing))
             for i in range(0, missing, STEPMISSING):
-                parse_log(
-                    filelist,
-                    dirlist,
-                    stats,
-                    git,
-                    merge=True,
-                    filterlist=filterlist[i : i + STEPMISSING],
-                )
+                parse_log(filelist, dirlist, stats, git,
+                          merge=True, filterlist=filterlist[i:i + STEPMISSING])
 
         # Still missing some?
         for file in filelist:
@@ -702,33 +556,29 @@ def main():
     # Final statistics
     # Suggestion: use git-log --before=mtime to brag about skipped log entries
     def log_info(msg, *a, width=13):
-        ifmt = "{:%d,}" % (width,)  # not using 'n' for consistency with ffmt
-        ffmt = "{:%d,.2f}" % (width,)
+        ifmt = '{:%d,}'    % (width,)  # not using 'n' for consistency with ffmt
+        ffmt = '{:%d,.2f}' % (width,)
         # %-formatting lacks a thousand separator, must pre-render with .format()
-        log.info(msg.replace("%d", ifmt).replace("%f", ffmt).format(*a))
+        log.info(msg.replace('%d', ifmt).replace('%f', ffmt).format(*a))
 
     log_info(
-        "Statistics:\n%f seconds\n%d log lines processed\n%d commits evaluated",
-        time.time() - start,
-        stats["loglines"],
-        stats["commits"],
-    )
+        "Statistics:\n"
+        "%f seconds\n"
+        "%d log lines processed\n"
+        "%d commits evaluated",
+        time.time() - start, stats['loglines'], stats['commits'])
 
     if args.dirs:
-        if stats["direrrors"]:
-            log_info("%d directory update errors", stats["direrrors"])
-        log_info("%d directories updated", stats["dirtouches"])
+        if stats['direrrors']: log_info("%d directory update errors", stats['direrrors'])
+        log_info("%d directories updated", stats['dirtouches'])
 
-    if stats["touches"] != stats["totalfiles"]:
-        log_info("%d files", stats["totalfiles"])
-    if stats["skip"]:
-        log_info("%d files skipped", stats["skip"])
-    if stats["files"]:
-        log_info("%d files missing", stats["files"])
-    if stats["errors"]:
-        log_info("%d file update errors", stats["errors"])
+    if stats['touches'] != stats['totalfiles']:
+                        log_info("%d files",              stats['totalfiles'])
+    if stats['skip']:   log_info("%d files skipped",      stats['skip'])
+    if stats['files']:  log_info("%d files missing",      stats['files'])
+    if stats['errors']: log_info("%d file update errors", stats['errors'])
 
-    log_info("%d files updated", stats["touches"])
+    log_info("%d files updated", stats['touches'])
 
     if args.test:
         log.info("TEST RUN - No files modified!")

.github/workflows/_compile_integration_test.yml

@@ -1,12 +1,4 @@
-# Validates that a package's integration tests compile without syntax or import errors.
-#
-# (If an integration test fails to compile, it won't run.)
-#
-# Called as part of check_diffs.yml workflow
-#
-# Runs pytest with compile marker to check syntax/imports.
-
-name: "🔗 Compile Integration Tests"
+name: compile-integration-test
 
 on:
   workflow_call:
@@ -15,16 +7,9 @@ on:
         required: true
         type: string
         description: "From which folder this pipeline executes"
-      python-version:
-        required: true
-        type: string
-        description: "Python version to use"
-
-permissions:
-  contents: read
 
 env:
-  UV_FROZEN: "true"
+  POETRY_VERSION: "1.6.1"
 
 jobs:
   build:
@@ -32,27 +17,34 @@ jobs:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
-    timeout-minutes: 20
-    name: "Python ${{ inputs.python-version }}"
+    strategy:
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
+    name: Python ${{ matrix.python-version }}
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v4
 
-      - name: "🐍 Set up Python ${{ inputs.python-version }} + UV"
-        uses: "./.github/actions/uv_setup"
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ inputs.python-version }}
-          cache-suffix: compile-integration-tests-${{ inputs.working-directory }}
+          python-version: ${{ matrix.python-version }}
+          poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
+          cache-key: compile-integration
 
-      - name: "📦 Install Integration Dependencies"
+      - name: Install integration dependencies
         shell: bash
-        run: uv sync --group test --group test_integration
+        run: poetry install --with=test_integration
 
-      - name: "🔗 Check Integration Tests Compile"
+      - name: Check integration tests compile
         shell: bash
-        run: uv run pytest -m compile tests/integration_tests
+        run: poetry run pytest -m compile tests/integration_tests
 
-      - name: "🧹 Verify Clean Working Directory"
+      - name: Ensure the tests did not create any additional files
         shell: bash
         run: |
           set -eu

.github/workflows/_lint.yml

@@ -1,11 +1,4 @@
-# Runs linting.
-#
-# Uses the package's Makefile to run the checks, specifically the
-# `lint_package` and `lint_tests` targets.
-#
-# Called as part of check_diffs.yml workflow.
-
-name: "🧹 Linting"
+name: lint
 
 on:
   workflow_call:
@@ -14,62 +7,144 @@ on:
         required: true
         type: string
         description: "From which folder this pipeline executes"
-      python-version:
-        required: true
-        type: string
-        description: "Python version to use"
-
-permissions:
-  contents: read
 
 env:
+  POETRY_VERSION: "1.6.1"
   WORKDIR: ${{ inputs.working-directory == '' && '.' || inputs.working-directory }}
 
-  # This env var allows us to get inline annotations when ruff has complaints.
-  RUFF_OUTPUT_FORMAT: github
-
-  UV_FROZEN: "true"
-
 jobs:
-  # Linting job - runs quality checks on package and test code
   build:
-    name: "Python ${{ inputs.python-version }}"
     runs-on: ubuntu-latest
-    timeout-minutes: 20
+    env:
+      # This number is set "by eye": we want it to be big enough
+      # so that it's bigger than the number of commits in any reasonable PR,
+      # and also as small as possible since increasing the number makes
+      # the initial `git fetch` slower.
+      FETCH_DEPTH: 50
+    strategy:
+      matrix:
+        # Only lint on the min and max supported Python versions.
+        # It's extremely unlikely that there's a lint issue on any version in between
+        # that doesn't show up on the min or max versions.
+        #
+        # GitHub rate-limits how many jobs can be running at any one time.
+        # Starting new jobs is also relatively slow,
+        # so linting on fewer versions makes CI faster.
+        python-version:
+          - "3.8"
+          - "3.11"
     steps:
-      - name: "📋 Checkout Code"
-        uses: actions/checkout@v5
-
-      - name: "🐍 Set up Python ${{ inputs.python-version }} + UV"
-        uses: "./.github/actions/uv_setup"
+      - uses: actions/checkout@v4
         with:
-          python-version: ${{ inputs.python-version }}
-          cache-suffix: lint-${{ inputs.working-directory }}
+          # Fetch the last FETCH_DEPTH commits, so the mtime-changing script
+          # can accurately set the mtimes of files modified in the last FETCH_DEPTH commits.
+          fetch-depth: ${{ env.FETCH_DEPTH }}
+      - name: Restore workdir file mtimes to last-edited commit date
+        id: restore-mtimes
+        # This is needed to make black caching work.
+        # Black's cache uses file (mtime, size) to check whether a lookup is a cache hit.
+        # Without this command, files in the repo would have the current time as the modified time,
+        # since the previous action step just created them.
+        # This command resets the mtime to the last time the files were modified in git instead,
+        # which is a high-quality and stable representation of the last modification date.
+        run: |
+          # Important considerations:
+          # - These commands run at base of the repo, since we never `cd` to the `WORKDIR`.
+          # - We only want to alter mtimes for Python files, since that's all black checks.
+          # - We don't need to alter mtimes for directories, since black doesn't look at those.
+          # - We also only alter mtimes inside the `WORKDIR` since that's all we'll lint.
+          # - This should run before `poetry install`, because poetry's venv also contains
+          #   Python files, and we don't want to alter their mtimes since they aren't linted.
+
+          # Ensure we fail on non-zero exits and on undefined variables.
+          # Also print executed commands, for easier debugging.
+          set -eux
+
+          # Restore the mtimes of Python files in the workdir based on git history.
+          .github/tools/git-restore-mtime --no-directories "$WORKDIR/**/*.py"
+
+          # Since CI only does a partial fetch (to `FETCH_DEPTH`) for efficiency,
+          # the local git repo doesn't have full history. There are probably files
+          # that were last modified in a commit *older than* the oldest fetched commit.
+          # After `git-restore-mtime`, such files have a mtime set to the oldest fetched commit.
+          #
+          # As new commits get added, that timestamp will keep moving forward.
+          # If left unchanged, this will make `black` think that the files were edited
+          # more recently than its cache suggests. Instead, we can set their mtime
+          # to a fixed date in the far past that won't change and won't cause cache misses in black.
+          #
+          # For all workdir Python files modified in or before the oldest few fetched commits,
+          # make their mtime be 2000-01-01 00:00:00.
+          OLDEST_COMMIT="$(git log --reverse '--pretty=format:%H' | head -1)"
+          OLDEST_COMMIT_TIME="$(git show -s '--format=%ai' "$OLDEST_COMMIT")"
+          find "$WORKDIR" -name '*.py' -type f -not -newermt "$OLDEST_COMMIT_TIME" -exec touch -c -m -t '200001010000' '{}' '+'
+
+          echo "oldest-commit=$OLDEST_COMMIT" >> "$GITHUB_OUTPUT"
+
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
+        with:
+          python-version: ${{ matrix.python-version }}
+          poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
+          cache-key: lint-with-extras
 
-      - name: "📦 Install Lint & Typing Dependencies"
+      - name: Check Poetry File
+        shell: bash
         working-directory: ${{ inputs.working-directory }}
         run: |
-          uv sync --group lint --group typing
+          poetry check
 
-      - name: "🔍 Analyze Package Code with Linters"
+      - name: Check lock file
+        shell: bash
         working-directory: ${{ inputs.working-directory }}
         run: |
-          make lint_package
+          poetry lock --check
 
-      - name: "📦 Install Test Dependencies (non-partners)"
-        # (For directories NOT starting with libs/partners/)
-        if: ${{ ! startsWith(inputs.working-directory, 'libs/partners/') }}
+      - name: Install dependencies
+        # Also installs dev/lint/test/typing dependencies, to ensure we have
+        # type hints for as many of our libraries as possible.
+        # This helps catch errors that require dependencies to be spotted, for example:
+        # https://github.com/langchain-ai/langchain/pull/10249/files#diff-935185cd488d015f026dcd9e19616ff62863e8cde8c0bee70318d3ccbca98341
+        #
+        # If you change this configuration, make sure to change the `cache-key`
+        # in the `poetry_setup` action above to stop using the old cache.
+        # It doesn't matter how you change it, any change will cause a cache-bust.
         working-directory: ${{ inputs.working-directory }}
         run: |
-          uv sync --inexact --group test
-      - name: "📦 Install Test Dependencies"
-        if: ${{ startsWith(inputs.working-directory, 'libs/partners/') }}
-        working-directory: ${{ inputs.working-directory }}
-        run: |
-          uv sync --inexact --group test --group test_integration
+          poetry install --with dev,lint,test,typing
 
-      - name: "🔍 Analyze Test Code with Linters"
+      - name: Install langchain editable
         working-directory: ${{ inputs.working-directory }}
+        if: ${{ inputs.working-directory != 'libs/langchain' }}
         run: |
-          make lint_tests
+          pip install -e ../langchain
+
+      - name: Restore black cache
+        uses: actions/cache@v3
+        env:
+          CACHE_BASE: black-${{ runner.os }}-${{ runner.arch }}-py${{ matrix.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', env.WORKDIR)) }}
+          SEGMENT_DOWNLOAD_TIMEOUT_MIN: "1"
+        with:
+          path: |
+            ${{ env.WORKDIR }}/.black_cache
+          key: ${{ env.CACHE_BASE }}-${{ steps.restore-mtimes.outputs.oldest-commit }}
+          restore-keys:
+            # If we can't find an exact match for our cache key, accept any with this prefix.
+            ${{ env.CACHE_BASE }}-
+
+      - name: Get .mypy_cache to speed up mypy
+        uses: actions/cache@v3
+        env:
+          SEGMENT_DOWNLOAD_TIMEOUT_MIN: "2"
+        with:
+          path: |
+            ${{ env.WORKDIR }}/.mypy_cache
+          key: mypy-${{ runner.os }}-${{ runner.arch }}-py${{ matrix.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', env.WORKDIR)) }}
+
+      - name: Analysing the code with our lint
+        working-directory: ${{ inputs.working-directory }}
+        env:
+          BLACK_CACHE_DIR: .black_cache
+        run: |
+          make lint

.github/workflows/_pydantic_compatibility.yml

@@ -0,0 +1,93 @@
+name: pydantic v1/v2 compatibility
+
+on:
+  workflow_call:
+    inputs:
+      working-directory:
+        required: true
+        type: string
+        description: "From which folder this pipeline executes"
+
+env:
+  POETRY_VERSION: "1.6.1"
+
+jobs:
+  build:
+    defaults:
+      run:
+        working-directory: ${{ inputs.working-directory }}
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
+    name: Pydantic v1/v2 compatibility - Python ${{ matrix.python-version }}
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
+        with:
+          python-version: ${{ matrix.python-version }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: ${{ inputs.working-directory }}
+          cache-key: pydantic-cross-compat
+
+      - name: Install dependencies
+        shell: bash
+        run: poetry install
+
+      - name: Install the opposite major version of pydantic
+        # If normal tests use pydantic v1, here we'll use v2, and vice versa.
+        shell: bash
+        run: |
+          # Determine the major part of pydantic version
+          REGULAR_VERSION=$(poetry run python -c "import pydantic; print(pydantic.__version__)" | cut -d. -f1)
+
+          if [[ "$REGULAR_VERSION" == "1" ]]; then
+            PYDANTIC_DEP=">=2.1,<3"
+            TEST_WITH_VERSION="2"
+          elif [[ "$REGULAR_VERSION" == "2" ]]; then
+            PYDANTIC_DEP="<2"
+            TEST_WITH_VERSION="1"
+          else
+            echo "Unexpected pydantic major version '$REGULAR_VERSION', cannot determine which version to use for cross-compatibility test."
+            exit 1
+          fi
+
+          # Install via `pip` instead of `poetry add` to avoid changing lockfile,
+          # which would prevent caching from working: the cache would get saved
+          # to a different key than where it gets loaded from.
+          poetry run pip install "pydantic${PYDANTIC_DEP}"
+
+          # Ensure that the correct pydantic is installed now.
+          echo "Checking pydantic version... Expecting ${TEST_WITH_VERSION}"
+
+          # Determine the major part of pydantic version
+          CURRENT_VERSION=$(poetry run python -c "import pydantic; print(pydantic.__version__)" | cut -d. -f1)
+
+          # Check that the major part of pydantic version is as expected, if not
+          # raise an error
+          if [[ "$CURRENT_VERSION" != "$TEST_WITH_VERSION" ]]; then
+            echo "Error: expected pydantic version ${CURRENT_VERSION} to have been installed, but found: ${TEST_WITH_VERSION}"
+            exit 1
+          fi
+          echo "Found pydantic version ${CURRENT_VERSION}, as expected"
+      - name: Run pydantic compatibility tests
+        shell: bash
+        run: make test
+
+      - name: Ensure the tests did not create any additional files
+        shell: bash
+        run: |
+          set -eu
+
+          STATUS="$(git status)"
+          echo "$STATUS"
+
+          # grep will exit non-zero if the target message isn't found,
+          # and `set -e` above will cause the step to fail.
+          echo "$STATUS" | grep 'nothing to commit, working tree clean'

.github/workflows/_release.yml

@@ -1,11 +1,5 @@
-# Builds and publishes LangChain packages to PyPI.
-#
-# Manually triggered, though can be used as a reusable workflow (workflow_call).
-#
-# Handles version bumping, building, and publishing to PyPI with authentication.
+name: release
 
-name: "🚀 Package Release"
-run-name: "Release ${{ inputs.working-directory }} ${{ inputs.release-version }}"
 on:
   workflow_call:
     inputs:
@@ -13,469 +7,14 @@ on:
         required: true
         type: string
         description: "From which folder this pipeline executes"
-  workflow_dispatch:
-    inputs:
-      working-directory:
-        required: true
-        type: string
-        description: "From which folder this pipeline executes"
-        default: "libs/langchain"
-      release-version:
-        required: true
-        type: string
-        default: "0.1.0"
-        description: "New version of package being released"
-      dangerous-nonmaster-release:
-        required: false
-        type: boolean
-        default: false
-        description: "Release from a non-master branch (danger!) - Only use for hotfixes"
 
 env:
-  PYTHON_VERSION: "3.11"
-  UV_FROZEN: "true"
-  UV_NO_SYNC: "true"
-
-permissions:
-  contents: write # Required for creating GitHub releases
+  POETRY_VERSION: "1.6.1"
 
 jobs:
-  # Build the distribution package and extract version info
-  # Runs in isolated environment with minimal permissions for security
-  build:
-    if: github.ref == 'refs/heads/master' || inputs.dangerous-nonmaster-release
-    environment: Scheduled testing
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-
-    outputs:
-      pkg-name: ${{ steps.check-version.outputs.pkg-name }}
-      version: ${{ steps.check-version.outputs.version }}
-
-    steps:
-      - uses: actions/checkout@v5
-
-      - name: Set up Python + uv
-        uses: "./.github/actions/uv_setup"
-        with:
-          python-version: ${{ env.PYTHON_VERSION }}
-
-      # We want to keep this build stage *separate* from the release stage,
-      # so that there's no sharing of permissions between them.
-      # (Release stage has trusted publishing and GitHub repo contents write access,
-      #
-      # Otherwise, a malicious `build` step (e.g. via a compromised dependency)
-      # could get access to our GitHub or PyPI credentials.
-      #
-      # Per the trusted publishing GitHub Action:
-      # > It is strongly advised to separate jobs for building [...]
-      # > from the publish job.
-      # https://github.com/pypa/gh-action-pypi-publish#non-goals
-      - name: Build project for distribution
-        run: uv build
-        working-directory: ${{ inputs.working-directory }}
-
-      - name: Upload build
-        uses: actions/upload-artifact@v4
-        with:
-          name: dist
-          path: ${{ inputs.working-directory }}/dist/
-
-      - name: Check version
-        id: check-version
-        shell: python
-        working-directory: ${{ inputs.working-directory }}
-        run: |
-          import os
-          import tomllib
-          with open("pyproject.toml", "rb") as f:
-              data = tomllib.load(f)
-          pkg_name = data["project"]["name"]
-          version = data["project"]["version"]
-          with open(os.environ["GITHUB_OUTPUT"], "a") as f:
-              f.write(f"pkg-name={pkg_name}\n")
-              f.write(f"version={version}\n")
-  release-notes:
-    needs:
-      - build
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-    outputs:
-      release-body: ${{ steps.generate-release-body.outputs.release-body }}
-    steps:
-      - uses: actions/checkout@v5
-        with:
-          repository: langchain-ai/langchain
-          path: langchain
-          sparse-checkout: | # this only grabs files for relevant dir
-            ${{ inputs.working-directory }}
-          ref: ${{ github.ref }} # this scopes to just ref'd branch
-          fetch-depth: 0 # this fetches entire commit history
-      - name: Check tags
-        id: check-tags
-        shell: bash
-        working-directory: langchain/${{ inputs.working-directory }}
-        env:
-          PKG_NAME: ${{ needs.build.outputs.pkg-name }}
-          VERSION: ${{ needs.build.outputs.version }}
-        run: |
-          # Handle regular versions and pre-release versions differently
-          if [[ "$VERSION" == *"-"* ]]; then
-            # This is a pre-release version (contains a hyphen)
-            # Extract the base version without the pre-release suffix
-            BASE_VERSION=${VERSION%%-*}
-            # Look for the latest release of the same base version
-            REGEX="^$PKG_NAME==$BASE_VERSION\$"
-            PREV_TAG=$(git tag --sort=-creatordate | (grep -P "$REGEX" || true) | head -1)
-
-            # If no exact base version match, look for the latest release of any kind
-            if [ -z "$PREV_TAG" ]; then
-              REGEX="^$PKG_NAME==\\d+\\.\\d+\\.\\d+\$"
-              PREV_TAG=$(git tag --sort=-creatordate | (grep -P "$REGEX" || true) | head -1)
-            fi
-          else
-            # Regular version handling
-            PREV_TAG="$PKG_NAME==${VERSION%.*}.$(( ${VERSION##*.} - 1 ))"; [[ "${VERSION##*.}" -eq 0 ]] && PREV_TAG=""
-
-            # backup case if releasing e.g. 0.3.0, looks up last release
-            # note if last release (chronologically) was e.g. 0.1.47 it will get
-            # that instead of the last 0.2 release
-            if [ -z "$PREV_TAG" ]; then
-              REGEX="^$PKG_NAME==\\d+\\.\\d+\\.\\d+\$"
-              echo $REGEX
-              PREV_TAG=$(git tag --sort=-creatordate | (grep -P $REGEX || true) | head -1)
-            fi
-          fi
-
-          # if PREV_TAG is empty, let it be empty
-          if [ -z "$PREV_TAG" ]; then
-            echo "No previous tag found - first release"
-          else
-            # confirm prev-tag actually exists in git repo with git tag
-            GIT_TAG_RESULT=$(git tag -l "$PREV_TAG")
-            if [ -z "$GIT_TAG_RESULT" ]; then
-              echo "Previous tag $PREV_TAG not found in git repo"
-              exit 1
-            fi
-          fi
-
-
-          TAG="${PKG_NAME}==${VERSION}"
-          if [ "$TAG" == "$PREV_TAG" ]; then
-            echo "No new version to release"
-            exit 1
-          fi
-          echo tag="$TAG" >> $GITHUB_OUTPUT
-          echo prev-tag="$PREV_TAG" >> $GITHUB_OUTPUT
-      - name: Generate release body
-        id: generate-release-body
-        working-directory: langchain
-        env:
-          WORKING_DIR: ${{ inputs.working-directory }}
-          PKG_NAME: ${{ needs.build.outputs.pkg-name }}
-          TAG: ${{ steps.check-tags.outputs.tag }}
-          PREV_TAG: ${{ steps.check-tags.outputs.prev-tag }}
-        run: |
-          PREAMBLE="Changes since $PREV_TAG"
-          # if PREV_TAG is empty, then we are releasing the first version
-          if [ -z "$PREV_TAG" ]; then
-            PREAMBLE="Initial release"
-            PREV_TAG=$(git rev-list --max-parents=0 HEAD)
-          fi
-          {
-            echo 'release-body<<EOF'
-            echo $PREAMBLE
-            echo
-            git log --format="%s" "$PREV_TAG"..HEAD -- $WORKING_DIR
-            echo EOF
-          } >> "$GITHUB_OUTPUT"
-
-  test-pypi-publish:
-    needs:
-      - build
-      - release-notes
-    runs-on: ubuntu-latest
-    permissions:
-      # This permission is used for trusted publishing:
-      # https://blog.pypi.org/posts/2023-04-20-introducing-trusted-publishers/
-      #
-      # Trusted publishing has to also be configured on PyPI for each package:
-      # https://docs.pypi.org/trusted-publishers/adding-a-publisher/
-      id-token: write
-
-    steps:
-      - uses: actions/checkout@v5
-
-      - uses: actions/download-artifact@v5
-        with:
-          name: dist
-          path: ${{ inputs.working-directory }}/dist/
-
-      - name: Publish to test PyPI
-        uses: pypa/gh-action-pypi-publish@release/v1
-        with:
-          packages-dir: ${{ inputs.working-directory }}/dist/
-          verbose: true
-          print-hash: true
-          repository-url: https://test.pypi.org/legacy/
-          # We overwrite any existing distributions with the same name and version.
-          # This is *only for CI use* and is *extremely dangerous* otherwise!
-          # https://github.com/pypa/gh-action-pypi-publish#tolerating-release-package-file-duplicates
-          skip-existing: true
-          # Temp workaround since attestations are on by default as of gh-action-pypi-publish v1.11.0
-          attestations: false
-
-  pre-release-checks:
-    needs:
-      - build
-      - release-notes
-      - test-pypi-publish
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-    timeout-minutes: 20
-    steps:
-      - uses: actions/checkout@v5
-
-      # We explicitly *don't* set up caching here. This ensures our tests are
-      # maximally sensitive to catching breakage.
-      #
-      # For example, here's a way that caching can cause a falsely-passing test:
-      # - Make the langchain package manifest no longer list a dependency package
-      #   as a requirement. This means it won't be installed by `pip install`,
-      #   and attempting to use it would cause a crash.
-      # - That dependency used to be required, so it may have been cached.
-      #   When restoring the venv packages from cache, that dependency gets included.
-      # - Tests pass, because the dependency is present even though it wasn't specified.
-      # - The package is published, and it breaks on the missing dependency when
-      #   used in the real world.
-
-      - name: Set up Python + uv
-        uses: "./.github/actions/uv_setup"
-        id: setup-python
-        with:
-          python-version: ${{ env.PYTHON_VERSION }}
-
-      - uses: actions/download-artifact@v5
-        with:
-          name: dist
-          path: ${{ inputs.working-directory }}/dist/
-
-      - name: Import dist package
-        shell: bash
-        working-directory: ${{ inputs.working-directory }}
-        env:
-          PKG_NAME: ${{ needs.build.outputs.pkg-name }}
-          VERSION: ${{ needs.build.outputs.version }}
-        # Here we use:
-        # - The default regular PyPI index as the *primary* index, meaning
-        #   that it takes priority (https://pypi.org/simple)
-        # - The test PyPI index as an extra index, so that any dependencies that
-        #   are not found on test PyPI can be resolved and installed anyway.
-        #   (https://test.pypi.org/simple). This will include the PKG_NAME==VERSION
-        #   package because VERSION will not have been uploaded to regular PyPI yet.
-        # - attempt install again after 5 seconds if it fails because there is
-        #   sometimes a delay in availability on test pypi
-        run: |
-          uv venv
-          VIRTUAL_ENV=.venv uv pip install dist/*.whl
-
-          # Replace all dashes in the package name with underscores,
-          # since that's how Python imports packages with dashes in the name.
-          # also remove _official suffix
-          IMPORT_NAME="$(echo "$PKG_NAME" | sed s/-/_/g | sed s/_official//g)"
-
-          uv run python -c "import $IMPORT_NAME; print(dir($IMPORT_NAME))"
-
-      - name: Import test dependencies
-        run: uv sync --group test
-        working-directory: ${{ inputs.working-directory }}
-
-      # Overwrite the local version of the package with the built version
-      - name: Import published package (again)
-        working-directory: ${{ inputs.working-directory }}
-        shell: bash
-        env:
-          PKG_NAME: ${{ needs.build.outputs.pkg-name }}
-          VERSION: ${{ needs.build.outputs.version }}
-        run: |
-          VIRTUAL_ENV=.venv uv pip install dist/*.whl
-
-      - name: Check for prerelease versions
-        # Block release if any dependencies allow prerelease versions
-        # (unless this is itself a prerelease version)
-        working-directory: ${{ inputs.working-directory }}
-        run: |
-          uv run python $GITHUB_WORKSPACE/.github/scripts/check_prerelease_dependencies.py pyproject.toml
-
-      - name: Run unit tests
-        run: make tests
-        working-directory: ${{ inputs.working-directory }}
-
-      - name: Get minimum versions
-        # Find the minimum published versions that satisfies the given constraints
-        working-directory: ${{ inputs.working-directory }}
-        id: min-version
-        run: |
-          VIRTUAL_ENV=.venv uv pip install packaging requests
-          python_version="$(uv run python --version | awk '{print $2}')"
-          min_versions="$(uv run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml release $python_version)"
-          echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"
-          echo "min-versions=$min_versions"
-
-      - name: Run unit tests with minimum dependency versions
-        if: ${{ steps.min-version.outputs.min-versions != '' }}
-        env:
-          MIN_VERSIONS: ${{ steps.min-version.outputs.min-versions }}
-        run: |
-          VIRTUAL_ENV=.venv uv pip install --force-reinstall --editable .
-          VIRTUAL_ENV=.venv uv pip install --force-reinstall $MIN_VERSIONS
-          make tests
-        working-directory: ${{ inputs.working-directory }}
-
-      - name: Import integration test dependencies
-        run: uv sync --group test --group test_integration
-        working-directory: ${{ inputs.working-directory }}
-
-      - name: Run integration tests
-        # Uses the Makefile's `integration_tests` target for the specified package
-        if: ${{ startsWith(inputs.working-directory, 'libs/partners/') }}
-        env:
-          AI21_API_KEY: ${{ secrets.AI21_API_KEY }}
-          GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
-          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
-          MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
-          TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
-          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          AZURE_OPENAI_API_VERSION: ${{ secrets.AZURE_OPENAI_API_VERSION }}
-          AZURE_OPENAI_API_BASE: ${{ secrets.AZURE_OPENAI_API_BASE }}
-          AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
-          AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_CHAT_DEPLOYMENT_NAME }}
-          AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME }}
-          AZURE_OPENAI_LLM_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LLM_DEPLOYMENT_NAME }}
-          AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME }}
-          NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}
-          GOOGLE_SEARCH_API_KEY: ${{ secrets.GOOGLE_SEARCH_API_KEY }}
-          GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
-          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
-          HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
-          EXA_API_KEY: ${{ secrets.EXA_API_KEY }}
-          NOMIC_API_KEY: ${{ secrets.NOMIC_API_KEY }}
-          WATSONX_APIKEY: ${{ secrets.WATSONX_APIKEY }}
-          WATSONX_PROJECT_ID: ${{ secrets.WATSONX_PROJECT_ID }}
-          ASTRA_DB_API_ENDPOINT: ${{ secrets.ASTRA_DB_API_ENDPOINT }}
-          ASTRA_DB_APPLICATION_TOKEN: ${{ secrets.ASTRA_DB_APPLICATION_TOKEN }}
-          ASTRA_DB_KEYSPACE: ${{ secrets.ASTRA_DB_KEYSPACE }}
-          ES_URL: ${{ secrets.ES_URL }}
-          ES_CLOUD_ID: ${{ secrets.ES_CLOUD_ID }}
-          ES_API_KEY: ${{ secrets.ES_API_KEY }}
-          MONGODB_ATLAS_URI: ${{ secrets.MONGODB_ATLAS_URI }}
-          UPSTAGE_API_KEY: ${{ secrets.UPSTAGE_API_KEY }}
-          FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
-          XAI_API_KEY: ${{ secrets.XAI_API_KEY }}
-          DEEPSEEK_API_KEY: ${{ secrets.DEEPSEEK_API_KEY }}
-          PPLX_API_KEY: ${{ secrets.PPLX_API_KEY }}
-        run: make integration_tests
-        working-directory: ${{ inputs.working-directory }}
-
-  # Test select published packages against new core
-  # Done when code changes are made to langchain-core
-  test-prior-published-packages-against-new-core:
-    # Installs the new core with old partners: Installs the new unreleased core
-    # alongside the previously published partner packages and runs integration tests
-    needs:
-      - build
-      - release-notes
-      - test-pypi-publish
-      - pre-release-checks
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-    strategy:
-      matrix:
-        partner: [openai, anthropic]
-      fail-fast: false # Continue testing other partners if one fails
-    env:
-      ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
-      ANTHROPIC_FILES_API_IMAGE_ID: ${{ secrets.ANTHROPIC_FILES_API_IMAGE_ID }}
-      ANTHROPIC_FILES_API_PDF_ID: ${{ secrets.ANTHROPIC_FILES_API_PDF_ID }}
-      OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-      AZURE_OPENAI_API_VERSION: ${{ secrets.AZURE_OPENAI_API_VERSION }}
-      AZURE_OPENAI_API_BASE: ${{ secrets.AZURE_OPENAI_API_BASE }}
-      AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
-      AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_CHAT_DEPLOYMENT_NAME }}
-      AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME }}
-      AZURE_OPENAI_LLM_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LLM_DEPLOYMENT_NAME }}
-      AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME }}
-    steps:
-      - uses: actions/checkout@v5
-
-      # We implement this conditional as Github Actions does not have good support
-      # for conditionally needing steps. https://github.com/actions/runner/issues/491
-      # TODO: this seems to be resolved upstream, so we can probably remove this workaround
-      - name: Check if libs/core
-        run: |
-          if [ "${{ startsWith(inputs.working-directory, 'libs/core') }}" != "true" ]; then
-            echo "Not in libs/core. Exiting successfully."
-            exit 0
-          fi
-
-      - name: Set up Python + uv
-        if: startsWith(inputs.working-directory, 'libs/core')
-        uses: "./.github/actions/uv_setup"
-        with:
-          python-version: ${{ env.PYTHON_VERSION }}
-
-      - uses: actions/download-artifact@v5
-        if: startsWith(inputs.working-directory, 'libs/core')
-        with:
-          name: dist
-          path: ${{ inputs.working-directory }}/dist/
-
-      - name: Test against ${{ matrix.partner }}
-        if: startsWith(inputs.working-directory, 'libs/core')
-        run: |
-          # Identify latest tag, excluding pre-releases
-          LATEST_PACKAGE_TAG="$(
-            git ls-remote --tags origin "langchain-${{ matrix.partner }}*" \
-            | awk '{print $2}' \
-            | sed 's|refs/tags/||' \
-            | grep -E '[0-9]+\.[0-9]+\.[0-9]+([a-zA-Z]+[0-9]+)?$' \
-            | sort -Vr \
-            | head -n 1
-          )"
-          echo "Latest package tag: $LATEST_PACKAGE_TAG"
-
-          # Shallow-fetch just that single tag
-          git fetch --depth=1 origin tag "$LATEST_PACKAGE_TAG"
-
-          # Checkout the latest package files
-          rm -rf $GITHUB_WORKSPACE/libs/partners/${{ matrix.partner }}/*
-          rm -rf $GITHUB_WORKSPACE/libs/standard-tests/*
-          cd $GITHUB_WORKSPACE/libs/
-          git checkout "$LATEST_PACKAGE_TAG" -- standard-tests/
-          git checkout "$LATEST_PACKAGE_TAG" -- partners/${{ matrix.partner }}/
-          cd partners/${{ matrix.partner }}
-
-          # Print as a sanity check
-          echo "Version number from pyproject.toml: "
-          cat pyproject.toml | grep "version = "
-
-          # Run tests
-          uv sync --group test --group test_integration
-          uv pip install ../../core/dist/*.whl
-          make integration_tests
-
-  publish:
-    # Publishes the package to PyPI
-    needs:
-      - build
-      - release-notes
-      - test-pypi-publish
-      - pre-release-checks
-      - test-prior-published-packages-against-new-core
+  if_release:
+    # Disallow publishing from branches that aren't `master`.
+    if: github.ref == 'refs/heads/master'
     runs-on: ubuntu-latest
     permissions:
       # This permission is used for trusted publishing:
@@ -485,70 +24,41 @@ jobs:
       # https://docs.pypi.org/trusted-publishers/adding-a-publisher/
       id-token: write
 
+      # This permission is needed by `ncipollo/release-action` to create the GitHub release.
+      contents: write
     defaults:
       run:
         working-directory: ${{ inputs.working-directory }}
-
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v4
 
-      - name: Set up Python + uv
-        uses: "./.github/actions/uv_setup"
+      - name: Set up Python + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ env.PYTHON_VERSION }}
+          python-version: "3.10"
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: ${{ inputs.working-directory }}
+          cache-key: release
 
-      - uses: actions/download-artifact@v5
+      - name: Build project for distribution
+        run: poetry build
+      - name: Check Version
+        id: check-version
+        run: |
+          echo version=$(poetry version --short) >> $GITHUB_OUTPUT
+      - name: Create Release
+        uses: ncipollo/release-action@v1
+        if: ${{ inputs.working-directory == 'libs/langchain' }}
         with:
-          name: dist
-          path: ${{ inputs.working-directory }}/dist/
-
+          artifacts: "dist/*"
+          token: ${{ secrets.GITHUB_TOKEN }}
+          draft: false
+          generateReleaseNotes: true
+          tag: v${{ steps.check-version.outputs.version }}
+          commit: master
       - name: Publish package distributions to PyPI
         uses: pypa/gh-action-pypi-publish@release/v1
         with:
           packages-dir: ${{ inputs.working-directory }}/dist/
           verbose: true
           print-hash: true
-          # Temp workaround since attestations are on by default as of gh-action-pypi-publish v1.11.0
-          attestations: false
-
-  mark-release:
-    # Marks the GitHub release with the new version tag
-    needs:
-      - build
-      - release-notes
-      - test-pypi-publish
-      - pre-release-checks
-      - publish
-    runs-on: ubuntu-latest
-    permissions:
-      # This permission is needed by `ncipollo/release-action` to
-      # create the GitHub release/tag
-      contents: write
-
-    defaults:
-      run:
-        working-directory: ${{ inputs.working-directory }}
-
-    steps:
-      - uses: actions/checkout@v5
-
-      - name: Set up Python + uv
-        uses: "./.github/actions/uv_setup"
-        with:
-          python-version: ${{ env.PYTHON_VERSION }}
-
-      - uses: actions/download-artifact@v5
-        with:
-          name: dist
-          path: ${{ inputs.working-directory }}/dist/
-
-      - name: Create Tag
-        uses: ncipollo/release-action@v1
-        with:
-          artifacts: "dist/*"
-          token: ${{ secrets.GITHUB_TOKEN }}
-          generateReleaseNotes: false
-          tag: ${{needs.build.outputs.pkg-name}}==${{ needs.build.outputs.version }}
-          body: ${{ needs.release-notes.outputs.release-body }}
-          commit: ${{ github.sha }}
-          makeLatest: ${{ needs.build.outputs.pkg-name == 'langchain-core'}}

.github/workflows/_release_docker.yml

@@ -0,0 +1,62 @@
+name: release_docker
+
+on:
+  workflow_call:
+    inputs:
+      dockerfile:
+        required: true
+        type: string
+        description: "Path to the Dockerfile to build"
+      image:
+        required: true
+        type: string
+        description: "Name of the image to build"
+
+env:
+  TEST_TAG: ${{ inputs.image }}:test
+  LATEST_TAG: ${{ inputs.image }}:latest
+
+jobs:
+  docker:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Get git tag
+        uses: actions-ecosystem/action-get-latest-tag@v1
+        id: get-latest-tag
+      - name: Set docker tag
+        env:
+          VERSION: ${{ steps.get-latest-tag.outputs.tag }}
+        run: |
+          echo "VERSION_TAG=${{ inputs.image }}:${VERSION#v}" >> $GITHUB_ENV
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+      - name: Build for Test
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          file: ${{ inputs.dockerfile }}
+          load: true
+          tags: ${{ env.TEST_TAG }}
+      - name: Test
+        run: |
+          docker run --rm ${{ env.TEST_TAG }} python -c "import langchain"
+      - name: Build and Push to Docker Hub
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          file: ${{ inputs.dockerfile }}
+          # We can only build for the intersection of platforms supported by
+          # QEMU and base python image, for now build only for
+          # linux/amd64 and linux/arm64
+          platforms: linux/amd64,linux/arm64
+          tags: ${{ env.LATEST_TAG }},${{ env.VERSION_TAG }}
+          push: true

.github/workflows/_test.yml

@@ -1,7 +1,4 @@
-# Runs unit tests with both current and minimum supported dependency versions
-# to ensure compatibility across the supported range.
-
-name: "🧪 Unit Testing"
+name: test
 
 on:
   workflow_call:
@@ -10,69 +7,52 @@ on:
         required: true
         type: string
         description: "From which folder this pipeline executes"
-      python-version:
-        required: true
-        type: string
-        description: "Python version to use"
-
-permissions:
-  contents: read
 
 env:
-  UV_FROZEN: "true"
-  UV_NO_SYNC: "true"
+  POETRY_VERSION: "1.6.1"
 
 jobs:
-  # Main test job - runs unit tests with current deps, then retests with minimum versions
   build:
     defaults:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
-    timeout-minutes: 20
-    name: "Python ${{ inputs.python-version }}"
+    strategy:
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
+    name: Python ${{ matrix.python-version }}
     steps:
-      - name: "📋 Checkout Code"
-        uses: actions/checkout@v5
+      - uses: actions/checkout@v4
 
-      - name: "🐍 Set up Python ${{ inputs.python-version }} + UV"
-        uses: "./.github/actions/uv_setup"
-        id: setup-python
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ inputs.python-version }}
-          cache-suffix: test-${{ inputs.working-directory }}
+          python-version: ${{ matrix.python-version }}
+          poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
+          cache-key: core
 
-      - name: "📦 Install Test Dependencies"
+      - name: Install dependencies
         shell: bash
-        run: uv sync --group test --dev
+        run: poetry install
 
-      - name: "🧪 Run Core Unit Tests"
+      - name: Run core tests
         shell: bash
-        run: |
-          make test
+        run: make test
 
-      - name: "🔍 Calculate Minimum Dependency Versions"
-        working-directory: ${{ inputs.working-directory }}
-        id: min-version
+      - name: Install integration dependencies
         shell: bash
-        run: |
-          VIRTUAL_ENV=.venv uv pip install packaging tomli requests
-          python_version="$(uv run python --version | awk '{print $2}')"
-          min_versions="$(uv run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml pull_request $python_version)"
-          echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"
-          echo "min-versions=$min_versions"
+        run: poetry install --with=test_integration
 
-      - name: "🧪 Run Tests with Minimum Dependencies"
-        if: ${{ steps.min-version.outputs.min-versions != '' }}
-        env:
-          MIN_VERSIONS: ${{ steps.min-version.outputs.min-versions }}
-        run: |
-          VIRTUAL_ENV=.venv uv pip install $MIN_VERSIONS
-          make tests
-        working-directory: ${{ inputs.working-directory }}
+      - name: Check integration tests compile
+        shell: bash
+        run: poetry run pytest -m compile tests/integration_tests
 
-      - name: "🧹 Verify Clean Working Directory"
+      - name: Ensure the tests did not create any additional files
         shell: bash
         run: |
           set -eu

.github/workflows/_test_pydantic.yml

@@ -1,71 +0,0 @@
-# Facilitate unit testing against different Pydantic versions for a provided package.
-
-name: "🐍 Pydantic Version Testing"
-
-on:
-  workflow_call:
-    inputs:
-      working-directory:
-        required: true
-        type: string
-        description: "From which folder this pipeline executes"
-      python-version:
-        required: false
-        type: string
-        description: "Python version to use"
-        default: "3.11"
-      pydantic-version:
-        required: true
-        type: string
-        description: "Pydantic version to test."
-
-permissions:
-  contents: read
-
-env:
-  UV_FROZEN: "true"
-  UV_NO_SYNC: "true"
-
-jobs:
-  build:
-    defaults:
-      run:
-        working-directory: ${{ inputs.working-directory }}
-    runs-on: ubuntu-latest
-    timeout-minutes: 20
-    name: "Pydantic ~=${{ inputs.pydantic-version }}"
-    steps:
-      - name: "📋 Checkout Code"
-        uses: actions/checkout@v5
-
-      - name: "🐍 Set up Python ${{ inputs.python-version }} + UV"
-        uses: "./.github/actions/uv_setup"
-        with:
-          python-version: ${{ inputs.python-version }}
-          cache-suffix: test-pydantic-${{ inputs.working-directory }}
-          working-directory: ${{ inputs.working-directory }}
-
-      - name: "📦 Install Test Dependencies"
-        shell: bash
-        run: uv sync --group test
-
-      - name: "🔄 Install Specific Pydantic Version"
-        shell: bash
-        run: VIRTUAL_ENV=.venv uv pip install pydantic~=${{ inputs.pydantic-version }}
-
-      - name: "🧪 Run Core Tests"
-        shell: bash
-        run: |
-          make test
-
-      - name: "🧹 Verify Clean Working Directory"
-        shell: bash
-        run: |
-          set -eu
-
-          STATUS="$(git status)"
-          echo "$STATUS"
-
-          # grep will exit non-zero if the target message isn't found,
-          # and `set -e` above will cause the step to fail.
-          echo "$STATUS" | grep 'nothing to commit, working tree clean'

.github/workflows/_test_release.yml

@@ -0,0 +1,50 @@
+name: test-release
+
+on:
+  workflow_call:
+    inputs:
+      working-directory:
+        required: true
+        type: string
+        description: "From which folder this pipeline executes"
+
+env:
+  POETRY_VERSION: "1.6.1"
+
+jobs:
+  publish_to_test_pypi:
+    runs-on: ubuntu-latest
+    permissions:
+      # This permission is used for trusted publishing:
+      # https://blog.pypi.org/posts/2023-04-20-introducing-trusted-publishers/
+      #
+      # Trusted publishing has to also be configured on PyPI for each package:
+      # https://docs.pypi.org/trusted-publishers/adding-a-publisher/
+      id-token: write
+    defaults:
+      run:
+        working-directory: ${{ inputs.working-directory }}
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
+        with:
+          python-version: "3.10"
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: ${{ inputs.working-directory }}
+          cache-key: release
+
+      - name: Build project for distribution
+        run: poetry build
+      - name: Check Version
+        id: check-version
+        run: |
+          echo version=$(poetry version --short) >> $GITHUB_OUTPUT
+      - name: Publish package to TestPyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          repository-url: https://test.pypi.org/legacy/
+          packages-dir: ${{ inputs.working-directory }}/dist/
+          verbose: true
+          print-hash: true

.github/workflows/check_core_versions.yml

@@ -1,51 +0,0 @@
-# Ensures version numbers in pyproject.toml and version.py stay in sync.
-#
-# (Prevents releases with mismatched version numbers)
-
-name: "🔍 Check Version Equality"
-
-on:
-  pull_request:
-    paths:
-      - "libs/core/pyproject.toml"
-      - "libs/core/langchain_core/version.py"
-
-permissions:
-  contents: read
-
-jobs:
-  check_version_equality:
-    runs-on: ubuntu-latest
-
-    steps:
-      - uses: actions/checkout@v5
-
-      - name: "✅ Verify pyproject.toml & version.py Match"
-        run: |
-          # Check core versions
-          CORE_PYPROJECT_VERSION=$(grep -Po '(?<=^version = ")[^"]*' libs/core/pyproject.toml)
-          CORE_VERSION_PY_VERSION=$(grep -Po '(?<=^VERSION = ")[^"]*' libs/core/langchain_core/version.py)
-
-          # Compare core versions
-          if [ "$CORE_PYPROJECT_VERSION" != "$CORE_VERSION_PY_VERSION" ]; then
-            echo "langchain-core versions in pyproject.toml and version.py do not match!"
-            echo "pyproject.toml version: $CORE_PYPROJECT_VERSION"
-            echo "version.py version: $CORE_VERSION_PY_VERSION"
-            exit 1
-          else
-            echo "Core versions match: $CORE_PYPROJECT_VERSION"
-          fi
-
-          # Check langchain_v1 versions
-          LANGCHAIN_PYPROJECT_VERSION=$(grep -Po '(?<=^version = ")[^"]*' libs/langchain_v1/pyproject.toml)
-          LANGCHAIN_INIT_PY_VERSION=$(grep -Po '(?<=^__version__ = ")[^"]*' libs/langchain_v1/langchain/__init__.py)
-
-          # Compare langchain_v1 versions
-          if [ "$LANGCHAIN_PYPROJECT_VERSION" != "$LANGCHAIN_INIT_PY_VERSION" ]; then
-            echo "langchain_v1 versions in pyproject.toml and __init__.py do not match!"
-            echo "pyproject.toml version: $LANGCHAIN_PYPROJECT_VERSION"
-            echo "version.py version: $LANGCHAIN_INIT_PY_VERSION"
-            exit 1
-          else
-            echo "Langchain v1 versions match: $LANGCHAIN_PYPROJECT_VERSION"
-          fi

.github/workflows/check_diffs.yml

@@ -1,262 +0,0 @@
-# Primary CI workflow.
-#
-# Only runs against packages that have changed files.
-#
-# Runs:
-# - Linting (_lint.yml)
-# - Unit Tests (_test.yml)
-# - Pydantic compatibility tests (_test_pydantic.yml)
-# - Integration test compilation checks (_compile_integration_test.yml)
-# - Extended test suites that require additional dependencies
-# - Codspeed benchmarks (if not labeled 'codspeed-ignore')
-#
-# Reports status to GitHub checks and PR status.
-
-name: "🔧 CI"
-
-on:
-  push:
-    branches: [master]
-  pull_request:
-  merge_group:
-
-# Optimizes CI performance by canceling redundant workflow runs
-# If another push to the same PR or branch happens while this workflow is still running,
-# cancel the earlier run in favor of the next run.
-#
-# There's no point in testing an outdated version of the code. GitHub only allows
-# a limited number of job runners to be active at the same time, so it's better to
-# cancel pointless jobs early so that more useful jobs can run sooner.
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-permissions:
-  contents: read
-
-env:
-  UV_FROZEN: "true"
-  UV_NO_SYNC: "true"
-
-jobs:
-  # This job analyzes which files changed and creates a dynamic test matrix
-  # to only run tests/lints for the affected packages, improving CI efficiency
-  build:
-    name: "Detect Changes & Set Matrix"
-    runs-on: ubuntu-latest
-    if: ${{ !contains(github.event.pull_request.labels.*.name, 'ci-ignore') }}
-    steps:
-      - name: "📋 Checkout Code"
-        uses: actions/checkout@v5
-      - name: "🐍 Setup Python 3.11"
-        uses: actions/setup-python@v6
-        with:
-          python-version: "3.11"
-      - name: "📂 Get Changed Files"
-        id: files
-        uses: Ana06/get-changed-files@v2.3.0
-      - name: "🔍 Analyze Changed Files & Generate Build Matrix"
-        id: set-matrix
-        run: |
-          python -m pip install packaging requests
-          python .github/scripts/check_diff.py ${{ steps.files.outputs.all }} >> $GITHUB_OUTPUT
-    outputs:
-      lint: ${{ steps.set-matrix.outputs.lint }}
-      test: ${{ steps.set-matrix.outputs.test }}
-      extended-tests: ${{ steps.set-matrix.outputs.extended-tests }}
-      compile-integration-tests: ${{ steps.set-matrix.outputs.compile-integration-tests }}
-      dependencies: ${{ steps.set-matrix.outputs.dependencies }}
-      test-pydantic: ${{ steps.set-matrix.outputs.test-pydantic }}
-      codspeed: ${{ steps.set-matrix.outputs.codspeed }}
-  # Run linting only on packages that have changed files
-  lint:
-    needs: [build]
-    if: ${{ needs.build.outputs.lint != '[]' }}
-    strategy:
-      matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.lint) }}
-      fail-fast: false
-    uses: ./.github/workflows/_lint.yml
-    with:
-      working-directory: ${{ matrix.job-configs.working-directory }}
-      python-version: ${{ matrix.job-configs.python-version }}
-    secrets: inherit
-
-  # Run unit tests only on packages that have changed files
-  test:
-    needs: [build]
-    if: ${{ needs.build.outputs.test != '[]' }}
-    strategy:
-      matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.test) }}
-      fail-fast: false
-    uses: ./.github/workflows/_test.yml
-    with:
-      working-directory: ${{ matrix.job-configs.working-directory }}
-      python-version: ${{ matrix.job-configs.python-version }}
-    secrets: inherit
-
-  # Test compatibility with different Pydantic versions for affected packages
-  test-pydantic:
-    needs: [build]
-    if: ${{ needs.build.outputs.test-pydantic != '[]' }}
-    strategy:
-      matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.test-pydantic) }}
-      fail-fast: false
-    uses: ./.github/workflows/_test_pydantic.yml
-    with:
-      working-directory: ${{ matrix.job-configs.working-directory }}
-      pydantic-version: ${{ matrix.job-configs.pydantic-version }}
-    secrets: inherit
-
-  # Verify integration tests compile without actually running them (faster feedback)
-  compile-integration-tests:
-    name: "Compile Integration Tests"
-    needs: [build]
-    if: ${{ needs.build.outputs.compile-integration-tests != '[]' }}
-    strategy:
-      matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.compile-integration-tests) }}
-      fail-fast: false
-    uses: ./.github/workflows/_compile_integration_test.yml
-    with:
-      working-directory: ${{ matrix.job-configs.working-directory }}
-      python-version: ${{ matrix.job-configs.python-version }}
-    secrets: inherit
-
-  # Run extended test suites that require additional dependencies
-  extended-tests:
-    name: "Extended Tests"
-    needs: [build]
-    if: ${{ needs.build.outputs.extended-tests != '[]' }}
-    strategy:
-      matrix:
-        # note different variable for extended test dirs
-        job-configs: ${{ fromJson(needs.build.outputs.extended-tests) }}
-      fail-fast: false
-    runs-on: ubuntu-latest
-    timeout-minutes: 20
-    defaults:
-      run:
-        working-directory: ${{ matrix.job-configs.working-directory }}
-    steps:
-      - uses: actions/checkout@v5
-
-      - name: "🐍 Set up Python ${{ matrix.job-configs.python-version }} + UV"
-        uses: "./.github/actions/uv_setup"
-        with:
-          python-version: ${{ matrix.job-configs.python-version }}
-          cache-suffix: extended-tests-${{ matrix.job-configs.working-directory }}
-          working-directory: ${{ matrix.job-configs.working-directory }}
-
-      - name: "📦 Install Dependencies & Run Extended Tests"
-        shell: bash
-        run: |
-          echo "Running extended tests, installing dependencies with uv..."
-          uv venv
-          uv sync --group test
-          VIRTUAL_ENV=.venv uv pip install -r extended_testing_deps.txt
-          VIRTUAL_ENV=.venv make extended_tests
-
-      - name: "🧹 Verify Clean Working Directory"
-        shell: bash
-        run: |
-          set -eu
-
-          STATUS="$(git status)"
-          echo "$STATUS"
-
-          # grep will exit non-zero if the target message isn't found,
-          # and `set -e` above will cause the step to fail.
-          echo "$STATUS" | grep 'nothing to commit, working tree clean'
-
-  # Run codspeed benchmarks only on packages that have changed files
-  codspeed:
-    name: "⚡ CodSpeed Benchmarks"
-    needs: [build]
-    if: ${{ needs.build.outputs.codspeed != '[]' && !contains(github.event.pull_request.labels.*.name, 'codspeed-ignore') }}
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.codspeed) }}
-      fail-fast: false
-    steps:
-      - uses: actions/checkout@v5
-
-      # We have to use 3.12 as 3.13 is not yet supported
-      - name: "📦 Install UV Package Manager"
-        uses: astral-sh/setup-uv@v7
-        with:
-          python-version: "3.12"
-
-      - uses: actions/setup-python@v6
-        with:
-          python-version: "3.12"
-
-      - name: "📦 Install Test Dependencies"
-        run: uv sync --group test
-        working-directory: ${{ matrix.job-configs.working-directory }}
-
-      - name: "⚡ Run Benchmarks: ${{ matrix.job-configs.working-directory }}"
-        uses: CodSpeedHQ/action@v4
-        env:
-          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
-          ANTHROPIC_FILES_API_IMAGE_ID: ${{ secrets.ANTHROPIC_FILES_API_IMAGE_ID }}
-          ANTHROPIC_FILES_API_PDF_ID: ${{ secrets.ANTHROPIC_FILES_API_PDF_ID }}
-          AZURE_OPENAI_API_VERSION: ${{ secrets.AZURE_OPENAI_API_VERSION }}
-          AZURE_OPENAI_API_BASE: ${{ secrets.AZURE_OPENAI_API_BASE }}
-          AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
-          AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_CHAT_DEPLOYMENT_NAME }}
-          AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME }}
-          AZURE_OPENAI_LLM_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LLM_DEPLOYMENT_NAME }}
-          AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME }}
-          COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
-          DEEPSEEK_API_KEY: ${{ secrets.DEEPSEEK_API_KEY }}
-          EXA_API_KEY: ${{ secrets.EXA_API_KEY }}
-          FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
-          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
-          HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
-          MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
-          NOMIC_API_KEY: ${{ secrets.NOMIC_API_KEY }}
-          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          PPLX_API_KEY: ${{ secrets.PPLX_API_KEY }}
-          XAI_API_KEY: ${{ secrets.XAI_API_KEY }}
-        with:
-          token: ${{ secrets.CODSPEED_TOKEN }}
-          run: |
-            cd ${{ matrix.job-configs.working-directory }}
-            if [ "${{ matrix.job-configs.working-directory }}" = "libs/core" ]; then
-              uv run --no-sync pytest ./tests/benchmarks --codspeed
-            else
-              uv run --no-sync pytest ./tests/ --codspeed
-            fi
-          mode: ${{ matrix.job-configs.working-directory == 'libs/core' && 'walltime' || 'instrumentation' }}
-
-  # Final status check - ensures all required jobs passed before allowing merge
-  ci_success:
-    name: "✅ CI Success"
-    needs:
-      [
-        build,
-        lint,
-        test,
-        compile-integration-tests,
-        extended-tests,
-        test-pydantic,
-        codspeed,
-      ]
-    if: |
-      always()
-    runs-on: ubuntu-latest
-    env:
-      JOBS_JSON: ${{ toJSON(needs) }}
-      RESULTS_JSON: ${{ toJSON(needs.*.result) }}
-      EXIT_CODE: ${{!contains(needs.*.result, 'failure') && !contains(needs.*.result, 'cancelled') && '0' || '1'}}
-    steps:
-      - name: "🎉 All Checks Passed"
-        run: |
-          echo $JOBS_JSON
-          echo $RESULTS_JSON
-          echo "Exiting with $EXIT_CODE"
-          exit $EXIT_CODE

.github/workflows/codespell.yml

@@ -0,0 +1,36 @@
+---
+name: Codespell
+
+on:
+  push:
+    branches: [master]
+  pull_request:
+    branches: [master]
+
+permissions:
+  contents: read
+
+jobs:
+  codespell:
+    name: Check for spelling errors
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Install Dependencies
+        run: |
+          pip install toml
+
+      - name: Extract Ignore Words List
+        run: |
+          # Use a Python script to extract the ignore words list from pyproject.toml
+          python .github/workflows/extract_ignored_words_list.py
+        id: extract_ignore_words
+
+      - name: Codespell
+        uses: codespell-project/actions-codespell@v2
+        with:
+          skip: guide_imports.json
+          ignore_words_list: ${{ steps.extract_ignore_words.outputs.ignore_words_list }}

.github/workflows/doc_lint.yml

@@ -0,0 +1,22 @@
+---
+name: Documentation Lint
+
+on:
+  push:
+    branches: [master]
+  pull_request:
+    branches: [master]
+
+jobs:
+  check:
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v2
+
+    - name: Run import check
+      run: |
+        # We should not encourage imports directly from main init file
+        # Expect for hub
+        git grep 'from langchain import' docs/{docs,snippets} | grep -vE 'from langchain import (hub)' && exit 1 || exit 0

.github/workflows/extract_ignored_words_list.py

@@ -0,0 +1,8 @@
+import toml
+
+pyproject_toml = toml.load("pyproject.toml")
+
+# Extract the ignore words list (adjust the key as per your TOML structure)
+ignore_words_list = pyproject_toml.get("tool", {}).get("codespell", {}).get("ignore-words-list")
+
+print(f"::set-output name=ignore_words_list::{ignore_words_list}")

.github/workflows/integration_tests.yml

@@ -1,180 +0,0 @@
-# Routine integration tests against partner libraries with live API credentials.
-#
-# Uses `make integration_tests` for each library in the matrix.
-#
-# Runs daily. Can also be triggered manually for immediate updates.
-
-name: "⏰ Integration Tests"
-run-name: "Run Integration Tests - ${{ inputs.working-directory-force || 'all libs' }} (Python ${{ inputs.python-version-force || '3.10, 3.13' }})"
-
-on:
-  workflow_dispatch:
-    inputs:
-      working-directory-force:
-        type: string
-        description: "From which folder this pipeline executes - defaults to all in matrix - example value: libs/partners/anthropic"
-      python-version-force:
-        type: string
-        description: "Python version to use - defaults to 3.10 and 3.13 in matrix - example value: 3.11"
-  schedule:
-    - cron: "0 13 * * *" # Runs daily at 1PM UTC (9AM EDT/6AM PDT)
-
-permissions:
-  contents: read
-
-env:
-  UV_FROZEN: "true"
-  DEFAULT_LIBS: '["libs/partners/openai", "libs/partners/anthropic", "libs/partners/fireworks", "libs/partners/groq", "libs/partners/mistralai", "libs/partners/xai", "libs/partners/google-vertexai", "libs/partners/google-genai", "libs/partners/aws"]'
-
-jobs:
-  # Generate dynamic test matrix based on input parameters or defaults
-  # Only runs on the main repo (for scheduled runs) or when manually triggered
-  compute-matrix:
-    if: github.repository_owner == 'langchain-ai' || github.event_name != 'schedule'
-    runs-on: ubuntu-latest
-    name: "📋 Compute Test Matrix"
-    outputs:
-      matrix: ${{ steps.set-matrix.outputs.matrix }}
-    steps:
-      - name: "🔢 Generate Python & Library Matrix"
-        id: set-matrix
-        env:
-          DEFAULT_LIBS: ${{ env.DEFAULT_LIBS }}
-          WORKING_DIRECTORY_FORCE: ${{ github.event.inputs.working-directory-force || '' }}
-          PYTHON_VERSION_FORCE: ${{ github.event.inputs.python-version-force || '' }}
-        run: |
-          # echo "matrix=..." where matrix is a json formatted str with keys python-version and working-directory
-          # python-version should default to 3.10 and 3.13, but is overridden to [PYTHON_VERSION_FORCE] if set
-          # working-directory should default to DEFAULT_LIBS, but is overridden to [WORKING_DIRECTORY_FORCE] if set
-          python_version='["3.10", "3.13"]'
-          working_directory="$DEFAULT_LIBS"
-          if [ -n "$PYTHON_VERSION_FORCE" ]; then
-            python_version="[\"$PYTHON_VERSION_FORCE\"]"
-          fi
-          if [ -n "$WORKING_DIRECTORY_FORCE" ]; then
-            working_directory="[\"$WORKING_DIRECTORY_FORCE\"]"
-          fi
-          matrix="{\"python-version\": $python_version, \"working-directory\": $working_directory}"
-          echo $matrix
-          echo "matrix=$matrix" >> $GITHUB_OUTPUT
-  # Run integration tests against partner libraries with live API credentials
-  build:
-    if: github.repository_owner == 'langchain-ai' || github.event_name != 'schedule'
-    name: "🐍 Python ${{ matrix.python-version }}: ${{ matrix.working-directory }}"
-    runs-on: ubuntu-latest
-    needs: [compute-matrix]
-    timeout-minutes: 30
-    strategy:
-      fail-fast: false
-      matrix:
-        python-version: ${{ fromJSON(needs.compute-matrix.outputs.matrix).python-version }}
-        working-directory: ${{ fromJSON(needs.compute-matrix.outputs.matrix).working-directory }}
-
-    steps:
-      - uses: actions/checkout@v5
-        with:
-          path: langchain
-      - uses: actions/checkout@v5
-        with:
-          repository: langchain-ai/langchain-google
-          path: langchain-google
-      - uses: actions/checkout@v5
-        with:
-          repository: langchain-ai/langchain-aws
-          path: langchain-aws
-
-      - name: "📦 Organize External Libraries"
-        run: |
-          rm -rf \
-            langchain/libs/partners/google-genai \
-            langchain/libs/partners/google-vertexai
-          mv langchain-google/libs/genai langchain/libs/partners/google-genai
-          mv langchain-google/libs/vertexai langchain/libs/partners/google-vertexai
-          mv langchain-aws/libs/aws langchain/libs/partners/aws
-
-      - name: "🐍 Set up Python ${{ matrix.python-version }} + UV"
-        uses: "./langchain/.github/actions/uv_setup"
-        with:
-          python-version: ${{ matrix.python-version }}
-
-      - name: "🔐 Authenticate to Google Cloud"
-        id: "auth"
-        uses: google-github-actions/auth@v3
-        with:
-          credentials_json: "${{ secrets.GOOGLE_CREDENTIALS }}"
-
-      - name: "🔐 Configure AWS Credentials"
-        uses: aws-actions/configure-aws-credentials@v5
-        with:
-          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
-          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
-          aws-region: ${{ secrets.AWS_REGION }}
-
-      - name: "📦 Install Dependencies"
-        run: |
-          echo "Running scheduled tests, installing dependencies with uv..."
-          cd langchain/${{ matrix.working-directory }}
-          uv sync --group test --group test_integration
-
-      - name: "🚀 Run Integration Tests"
-        env:
-          AI21_API_KEY: ${{ secrets.AI21_API_KEY }}
-          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
-          ANTHROPIC_FILES_API_IMAGE_ID: ${{ secrets.ANTHROPIC_FILES_API_IMAGE_ID }}
-          ANTHROPIC_FILES_API_PDF_ID: ${{ secrets.ANTHROPIC_FILES_API_PDF_ID }}
-          ASTRA_DB_API_ENDPOINT: ${{ secrets.ASTRA_DB_API_ENDPOINT }}
-          ASTRA_DB_APPLICATION_TOKEN: ${{ secrets.ASTRA_DB_APPLICATION_TOKEN }}
-          ASTRA_DB_KEYSPACE: ${{ secrets.ASTRA_DB_KEYSPACE }}
-          AZURE_OPENAI_API_VERSION: ${{ secrets.AZURE_OPENAI_API_VERSION }}
-          AZURE_OPENAI_API_BASE: ${{ secrets.AZURE_OPENAI_API_BASE }}
-          AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
-          AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_CHAT_DEPLOYMENT_NAME }}
-          AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME }}
-          AZURE_OPENAI_LLM_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LLM_DEPLOYMENT_NAME }}
-          AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME }}
-          COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
-          DEEPSEEK_API_KEY: ${{ secrets.DEEPSEEK_API_KEY }}
-          ES_URL: ${{ secrets.ES_URL }}
-          ES_CLOUD_ID: ${{ secrets.ES_CLOUD_ID }}
-          ES_API_KEY: ${{ secrets.ES_API_KEY }}
-          EXA_API_KEY: ${{ secrets.EXA_API_KEY }}
-          FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
-          GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
-          GOOGLE_SEARCH_API_KEY: ${{ secrets.GOOGLE_SEARCH_API_KEY }}
-          GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
-          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
-          HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
-          MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
-          MONGODB_ATLAS_URI: ${{ secrets.MONGODB_ATLAS_URI }}
-          NOMIC_API_KEY: ${{ secrets.NOMIC_API_KEY }}
-          NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}
-          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          PPLX_API_KEY: ${{ secrets.PPLX_API_KEY }}
-          TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
-          UPSTAGE_API_KEY: ${{ secrets.UPSTAGE_API_KEY }}
-          WATSONX_APIKEY: ${{ secrets.WATSONX_APIKEY }}
-          WATSONX_PROJECT_ID: ${{ secrets.WATSONX_PROJECT_ID }}
-          XAI_API_KEY: ${{ secrets.XAI_API_KEY }}
-        run: |
-          cd langchain/${{ matrix.working-directory }}
-          make integration_tests
-
-      - name: "🧹 Clean up External Libraries"
-        # Clean up external libraries to avoid affecting the following git status check
-        run: |
-          rm -rf \
-            langchain/libs/partners/google-genai \
-            langchain/libs/partners/google-vertexai \
-            langchain/libs/partners/aws
-
-      - name: "🧹 Verify Clean Working Directory"
-        working-directory: langchain
-        run: |
-          set -eu
-
-          STATUS="$(git status)"
-          echo "$STATUS"
-
-          # grep will exit non-zero if the target message isn't found,
-          # and `set -e` above will cause the step to fail.
-          echo "$STATUS" | grep 'nothing to commit, working tree clean'

.github/workflows/langchain_ci.yml

@@ -0,0 +1,106 @@
+---
+name: libs/langchain CI
+
+on:
+  push:
+    branches: [ master ]
+  pull_request:
+    paths:
+      - '.github/actions/poetry_setup/action.yml'
+      - '.github/tools/**'
+      - '.github/workflows/_lint.yml'
+      - '.github/workflows/_test.yml'
+      - '.github/workflows/_pydantic_compatibility.yml'
+      - '.github/workflows/langchain_ci.yml'
+      - 'libs/**'
+      - '!libs/cli'
+      - '!libs/experimental'
+  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
+
+# If another push to the same PR or branch happens while this workflow is still running,
+# cancel the earlier run in favor of the next run.
+#
+# There's no point in testing an outdated version of the code. GitHub only allows
+# a limited number of job runners to be active at the same time, so it's better to cancel
+# pointless jobs early so that more useful jobs can run sooner.
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+env:
+  POETRY_VERSION: "1.6.1"
+  WORKDIR: "libs/langchain"
+
+jobs:
+  lint:
+    uses:
+      ./.github/workflows/_lint.yml
+    with:
+      working-directory: libs/langchain
+    secrets: inherit
+
+  test:
+    uses:
+      ./.github/workflows/_test.yml
+    with:
+      working-directory: libs/langchain
+    secrets: inherit
+
+  compile-integration-tests:
+    uses:
+      ./.github/workflows/_compile_integration_test.yml
+    with:
+      working-directory: libs/langchain
+    secrets: inherit
+
+  pydantic-compatibility:
+    uses:
+      ./.github/workflows/_pydantic_compatibility.yml
+    with:
+      working-directory: libs/langchain
+    secrets: inherit
+
+  extended-tests:
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        working-directory: ${{ env.WORKDIR }}
+    strategy:
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
+    name: Python ${{ matrix.python-version }} extended tests
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
+        with:
+          python-version: ${{ matrix.python-version }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: libs/langchain
+          cache-key: extended
+
+      - name: Install dependencies
+        shell: bash
+        run: |
+          echo "Running extended tests, installing dependencies with poetry..."
+          poetry install -E extended_testing
+
+      - name: Run extended tests
+        run: make extended_tests
+
+      - name: Ensure the tests did not create any additional files
+        shell: bash
+        run: |
+          set -eu
+
+          STATUS="$(git status)"
+          echo "$STATUS"
+
+          # grep will exit non-zero if the target message isn't found,
+          # and `set -e` above will cause the step to fail.
+          echo "$STATUS" | grep 'nothing to commit, working tree clean'

.github/workflows/langchain_cli_ci.yml

@@ -0,0 +1,53 @@
+---
+name: libs/cli CI
+
+on:
+  push:
+    branches: [ master ]
+  pull_request:
+    paths:
+      - '.github/actions/poetry_setup/action.yml'
+      - '.github/tools/**'
+      - '.github/workflows/_lint.yml'
+      - '.github/workflows/_test.yml'
+      - '.github/workflows/_pydantic_compatibility.yml'
+      - '.github/workflows/langchain_cli_ci.yml'
+      - 'libs/cli/**'
+      - 'libs/*'
+  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
+
+# If another push to the same PR or branch happens while this workflow is still running,
+# cancel the earlier run in favor of the next run.
+#
+# There's no point in testing an outdated version of the code. GitHub only allows
+# a limited number of job runners to be active at the same time, so it's better to cancel
+# pointless jobs early so that more useful jobs can run sooner.
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+env:
+  POETRY_VERSION: "1.6.1"
+  WORKDIR: "libs/cli"
+
+jobs:
+  lint:
+    uses:
+      ./.github/workflows/_lint.yml
+    with:
+      working-directory: libs/cli
+    secrets: inherit
+
+  test:
+    uses:
+      ./.github/workflows/_test.yml
+    with:
+      working-directory: libs/cli
+    secrets: inherit
+
+  pydantic-compatibility:
+    uses:
+      ./.github/workflows/_pydantic_compatibility.yml
+    with:
+      working-directory: libs/cli
+    secrets: inherit

.github/workflows/langchain_experimental_ci.yml

@@ -0,0 +1,136 @@
+---
+name: libs/experimental CI
+
+on:
+  push:
+    branches: [ master ]
+  pull_request:
+    paths:
+      - '.github/actions/poetry_setup/action.yml'
+      - '.github/tools/**'
+      - '.github/workflows/_lint.yml'
+      - '.github/workflows/_test.yml'
+      - '.github/workflows/langchain_experimental_ci.yml'
+      - 'libs/**'
+      - '!libs/cli'
+  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
+
+# If another push to the same PR or branch happens while this workflow is still running,
+# cancel the earlier run in favor of the next run.
+#
+# There's no point in testing an outdated version of the code. GitHub only allows
+# a limited number of job runners to be active at the same time, so it's better to cancel
+# pointless jobs early so that more useful jobs can run sooner.
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+env:
+  POETRY_VERSION: "1.6.1"
+  WORKDIR: "libs/experimental"
+
+jobs:
+  lint:
+    uses:
+      ./.github/workflows/_lint.yml
+    with:
+      working-directory: libs/experimental
+    secrets: inherit
+
+  test:
+    uses:
+      ./.github/workflows/_test.yml
+    with:
+      working-directory: libs/experimental
+    secrets: inherit
+
+  compile-integration-tests:
+    uses:
+      ./.github/workflows/_compile_integration_test.yml
+    with:
+      working-directory: libs/experimental
+    secrets: inherit
+
+  # It's possible that langchain-experimental works fine with the latest *published* langchain,
+  # but is broken with the langchain on `master`.
+  #
+  # We want to catch situations like that *before* releasing a new langchain, hence this test.
+  test-with-latest-langchain:
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        working-directory: ${{ env.WORKDIR }}
+    strategy:
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
+    name: test with unpublished langchain - Python ${{ matrix.python-version }}
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
+        with:
+          python-version: ${{ matrix.python-version }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: ${{ env.WORKDIR }}
+          cache-key: unpublished-langchain
+
+      - name: Install dependencies
+        shell: bash
+        run: |
+          echo "Running tests with unpublished langchain, installing dependencies with poetry..."
+          poetry install
+
+          echo "Editably installing langchain outside of poetry, to avoid messing up lockfile..."
+          poetry run pip install -e ../langchain
+
+      - name: Run tests
+        run: make test
+  extended-tests:
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        working-directory: ${{ env.WORKDIR }}
+    strategy:
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
+    name: Python ${{ matrix.python-version }} extended tests
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
+        with:
+          python-version: ${{ matrix.python-version }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: libs/experimental
+          cache-key: extended
+
+      - name: Install dependencies
+        shell: bash
+        run: |
+          echo "Running extended tests, installing dependencies with poetry..."
+          poetry install -E extended_testing
+
+      - name: Run extended tests
+        run: make extended_tests
+
+      - name: Ensure the tests did not create any additional files
+        shell: bash
+        run: |
+          set -eu
+
+          STATUS="$(git status)"
+          echo "$STATUS"
+
+          # grep will exit non-zero if the target message isn't found,
+          # and `set -e` above will cause the step to fail.
+          echo "$STATUS" | grep 'nothing to commit, working tree clean'

.github/workflows/langchain_experimental_release.yml

@@ -0,0 +1,13 @@
+---
+name: libs/experimental Release
+
+on:
+  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
+
+jobs:
+  release:
+    uses:
+      ./.github/workflows/_release.yml
+    with:
+      working-directory: libs/experimental
+    secrets: inherit

.github/workflows/langchain_experimental_test_release.yml

@@ -0,0 +1,13 @@
+---
+name: Experimental Test Release
+
+on:
+  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
+
+jobs:
+  release:
+    uses:
+      ./.github/workflows/_test_release.yml
+    with:
+      working-directory: libs/experimental
+    secrets: inherit

.github/workflows/langchain_release.yml

@@ -0,0 +1,27 @@
+---
+name: libs/langchain Release
+
+on:
+  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
+
+jobs:
+  release:
+    uses:
+      ./.github/workflows/_release.yml
+    with:
+      working-directory: libs/langchain
+    secrets: inherit
+
+  # N.B.: It's possible that PyPI doesn't make the new release visible / available
+  #       immediately after publishing. If that happens, the docker build might not
+  #       create a new docker image for the new release, since it won't see it.
+  #
+  #       If this ends up being a problem, add a check to the end of the `_release.yml`
+  #       workflow that prevents the workflow from finishing until the new release
+  #       is visible and installable on PyPI.
+  release-docker:
+    needs:
+      - release
+    uses:
+      ./.github/workflows/langchain_release_docker.yml
+    secrets: inherit

.github/workflows/langchain_release_docker.yml

@@ -0,0 +1,14 @@
+---
+name: docker/langchain/langchain Release
+
+on:
+  workflow_dispatch: # Allows to trigger the workflow manually in GitHub UI
+  workflow_call: # Allows triggering from another workflow
+
+jobs:
+  release:
+    uses: ./.github/workflows/_release_docker.yml
+    with:
+      dockerfile: docker/Dockerfile.base
+      image: langchain/langchain
+    secrets: inherit

.github/workflows/langchain_test_release.yml

@@ -0,0 +1,13 @@
+---
+name: Test Release
+
+on:
+  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
+
+jobs:
+  release:
+    uses:
+      ./.github/workflows/_test_release.yml
+    with:
+      working-directory: libs/langchain
+    secrets: inherit

.github/workflows/pr_labeler_file.yml

@@ -1,28 +0,0 @@
-# Label PRs based on changed files.
-#
-# See `.github/pr-file-labeler.yml` to see rules for each label/directory.
-
-name: "🏷️ Pull Request Labeler"
-
-on:
-  # Safe since we're not checking out or running the PR's code
-  # Never check out the PR's head in a pull_request_target job
-  pull_request_target:
-    types: [opened, synchronize, reopened, edited]
-
-jobs:
-  labeler:
-    name: "label"
-    permissions:
-      contents: read
-      pull-requests: write
-      issues: write
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Label Pull Request
-        uses: actions/labeler@v6
-        with:
-          repo-token: "${{ secrets.GITHUB_TOKEN }}"
-          configuration-path: .github/pr-file-labeler.yml
-          sync-labels: false

.github/workflows/pr_labeler_title.yml

@@ -1,44 +0,0 @@
-# Label PRs based on their titles.
-#
-# Uses conventional commit types from PR titles to apply labels.
-# Note: Scope-based labeling (e.g., integration labels) is handled by pr_labeler_file.yml
-
-name: "🏷️ PR Title Labeler"
-
-on:
-  # Safe since we're not checking out or running the PR's code
-  # Never check out the PR's head in a pull_request_target job
-  pull_request_target:
-    types: [opened, edited]
-
-jobs:
-  pr-title-labeler:
-    name: "label"
-    permissions:
-      contents: read
-      pull-requests: write
-      issues: write
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Label PR based on title
-        uses: bcoe/conventional-release-labels@v1
-        with:
-          token: ${{ secrets.GITHUB_TOKEN }}
-          type_labels: >-
-            {
-              "feat": "feature",
-              "fix": "fix",
-              "docs": "documentation",
-              "style": "linting",
-              "refactor": "refactor",
-              "perf": "performance",
-              "test": "tests",
-              "build": "infra",
-              "ci": "infra",
-              "chore": "infra",
-              "revert": "revert",
-              "release": "release",
-              "breaking": "breaking"
-            }
-          ignored_types: '[]'

.github/workflows/pr_lint.yml

@@ -1,108 +0,0 @@
-# PR title linting.
-#
-# FORMAT (Conventional Commits 1.0.0):
-#
-#   <type>[optional scope]: <description>
-#   [optional body]
-#   [optional footer(s)]
-#
-# Examples:
-#     feat(core): add multi‐tenant support
-#     fix(cli): resolve flag parsing error
-#     docs: update API usage examples
-#     docs(openai): update API usage examples
-#
-# Allowed Types:
-#   * feat       — a new feature (MINOR)
-#   * fix        — a bug fix (PATCH)
-#   * docs       — documentation only changes
-#   * style      — formatting, linting, etc.; no code change or typing refactors
-#   * refactor   — code change that neither fixes a bug nor adds a feature
-#   * perf       — code change that improves performance
-#   * test       — adding tests or correcting existing
-#   * build      — changes that affect the build system/external dependencies
-#   * ci         — continuous integration/configuration changes
-#   * chore      — other changes that don't modify source or test files
-#   * revert     — reverts a previous commit
-#   * release    — prepare a new release
-#
-# Allowed Scopes (optional):
-#   core, cli, langchain, langchain_v1, langchain_legacy, standard-tests,
-#   text-splitters, docs, anthropic, chroma, deepseek, exa, fireworks, groq,
-#   huggingface, mistralai, nomic, ollama, openai, perplexity, prompty, qdrant,
-#   xai, infra
-#
-# Rules:
-#   1. The 'Type' must start with a lowercase letter.
-#   2. Breaking changes: append "!" after type/scope (e.g., feat!: drop x support)
-#   3. When releasing (updating the pyproject.toml and uv.lock), the commit message
-#      should be: `release(scope): x.y.z` (e.g., `release(core): 1.2.0` with no
-#      body, footer, or preceeding/proceeding text).
-#
-# Enforces Conventional Commits format for pull request titles to maintain a clear and
-# machine-readable change history.
-
-name: "🏷️ PR Title Lint"
-
-permissions:
-  pull-requests: read
-
-on:
-  pull_request:
-    types: [opened, edited, synchronize]
-
-jobs:
-  # Validates that PR title follows Conventional Commits 1.0.0 specification
-  lint-pr-title:
-    name: "validate format"
-    runs-on: ubuntu-latest
-    steps:
-      - name: "✅ Validate Conventional Commits Format"
-        uses: amannn/action-semantic-pull-request@v6
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        with:
-          types: |
-            feat
-            fix
-            docs
-            style
-            refactor
-            perf
-            test
-            build
-            ci
-            chore
-            revert
-            release
-          scopes: |
-            core
-            cli
-            langchain
-            langchain_v1
-            langchain_legacy
-            standard-tests
-            text-splitters
-            docs
-            anthropic
-            chroma
-            deepseek
-            exa
-            fireworks
-            groq
-            huggingface
-            mistralai
-            nomic
-            ollama
-            openai
-            perplexity
-            prompty
-            qdrant
-            xai
-            infra
-          requireScope: false
-          disallowScopes: |
-            release
-            [A-Z]+
-          ignoreLabels: |
-            ignore-lint-pr-title

.github/workflows/scheduled_test.yml

@@ -0,0 +1,86 @@
+name: Scheduled tests
+
+on:
+  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
+  schedule:
+    - cron:  '0 13 * * *'
+
+env:
+  POETRY_VERSION: "1.6.1"
+
+jobs:
+  build:
+    defaults:
+      run:
+        working-directory: libs/langchain
+    runs-on: ubuntu-latest
+    environment: Scheduled testing
+    strategy:
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
+    name: Python ${{ matrix.python-version }}
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: "./.github/actions/poetry_setup"
+        with:
+          python-version: ${{ matrix.python-version }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: libs/langchain
+          cache-key: scheduled
+
+      - name: 'Authenticate to Google Cloud'
+        id: 'auth'
+        uses: 'google-github-actions/auth@v1'
+        with:
+          credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
+
+      - name: Configure AWS Credentials
+        uses: aws-actions/configure-aws-credentials@v4
+        with:
+          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+          aws-region: ${{ vars.AWS_REGION }}
+
+      - name: Install dependencies
+        working-directory: libs/langchain
+        shell: bash
+        run: |
+          echo "Running scheduled tests, installing dependencies with poetry..."
+          poetry install --with=test_integration
+          poetry run pip install google-cloud-aiplatform
+          poetry run pip install "boto3>=1.28.57"
+          if [[ ${{ matrix.python-version }} != "3.8" ]]
+          then
+            poetry run pip install fireworks-ai
+          fi
+
+      - name: Run tests
+        shell: bash
+        env:
+          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+          AZURE_OPENAI_API_VERSION: ${{ secrets.AZURE_OPENAI_API_VERSION }}
+          AZURE_OPENAI_API_BASE: ${{ secrets.AZURE_OPENAI_API_BASE }}
+          AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
+          AZURE_OPENAI_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_DEPLOYMENT_NAME }}
+          FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
+        run: |
+          make scheduled_tests
+
+      - name: Ensure the tests did not create any additional files
+        shell: bash
+        run: |
+          set -eu
+
+          STATUS="$(git status)"
+          echo "$STATUS"
+
+          # grep will exit non-zero if the target message isn't found,
+          # and `set -e` above will cause the step to fail.
+          echo "$STATUS" | grep 'nothing to commit, working tree clean'

.github/workflows/v03_api_doc_build.yml

@@ -1,164 +0,0 @@
-# Build the API reference documentation for v0.3 branch.
-#
-# Manual trigger only.
-#
-# Built HTML pushed to langchain-ai/langchain-api-docs-html.
-#
-# Looks for langchain-ai org repos in packages.yml and checks them out.
-# Calls prep_api_docs_build.py.
-
-name: "📚 API Docs (v0.3)"
-run-name: "Build & Deploy API Reference (v0.3)"
-
-on:
-  workflow_dispatch:
-
-env:
-  PYTHON_VERSION: "3.11"
-
-jobs:
-  build:
-    if: github.repository == 'langchain-ai/langchain' || github.event_name != 'schedule'
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-    steps:
-      - uses: actions/checkout@v5
-        with:
-          ref: v0.3
-          path: langchain
-
-      - uses: actions/checkout@v5
-        with:
-          repository: langchain-ai/langchain-api-docs-html
-          path: langchain-api-docs-html
-          token: ${{ secrets.TOKEN_GITHUB_API_DOCS_HTML }}
-
-      - name: "📋 Extract Repository List with yq"
-        id: get-unsorted-repos
-        uses: mikefarah/yq@master
-        with:
-          cmd: |
-            # Extract repos from packages.yml that are in the langchain-ai org
-            # (excluding 'langchain' itself)
-            yq '
-              .packages[]
-              | select(
-                  (
-                    (.repo | test("^langchain-ai/"))
-                    and
-                    (.repo != "langchain-ai/langchain")
-                  )
-                  or
-                  (.include_in_api_ref // false)
-                )
-              | .repo
-            ' langchain/libs/packages.yml
-
-      - name: "📋 Parse YAML & Checkout Repositories"
-        env:
-          REPOS_UNSORTED: ${{ steps.get-unsorted-repos.outputs.result }}
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: |
-          # Get unique repositories
-          REPOS=$(echo "$REPOS_UNSORTED" | sort -u)
-          # Checkout each unique repository
-          for repo in $REPOS; do
-            # Validate repository format (allow any org with proper format)
-            if [[ ! "$repo" =~ ^[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+$ ]]; then
-              echo "Error: Invalid repository format: $repo"
-              exit 1
-            fi
-
-            REPO_NAME=$(echo $repo | cut -d'/' -f2)
-
-            # Additional validation for repo name
-            if [[ ! "$REPO_NAME" =~ ^[a-zA-Z0-9_.-]+$ ]]; then
-              echo "Error: Invalid repository name: $REPO_NAME"
-              exit 1
-            fi
-            echo "Checking out $repo to $REPO_NAME"
-
-            # Special handling for langchain-tavily: checkout by commit hash
-            if [[ "$REPO_NAME" == "langchain-tavily" ]]; then
-              git clone https://github.com/$repo.git $REPO_NAME
-              cd $REPO_NAME
-              git checkout f3515654724a9e87bdfe2c2f509d6cdde646e563
-              cd ..
-            else
-              git clone --depth 1 --branch v0.3 https://github.com/$repo.git $REPO_NAME
-            fi
-          done
-
-      - name: "🐍 Setup Python ${{ env.PYTHON_VERSION }}"
-        uses: actions/setup-python@v6
-        id: setup-python
-        with:
-          python-version: ${{ env.PYTHON_VERSION }}
-
-      - name: "📦 Install Initial Python Dependencies using uv"
-        working-directory: langchain
-        run: |
-          python -m pip install -U uv
-          python -m uv pip install --upgrade --no-cache-dir pip setuptools pyyaml
-
-      - name: "📦 Organize Library Directories"
-        # Places cloned partner packages into libs/partners structure
-        run: python langchain/.github/scripts/prep_api_docs_build.py
-
-      - name: "🧹 Clear Prior Build"
-        run:
-          # Remove artifacts from prior docs build
-          rm -rf langchain-api-docs-html/api_reference_build/html
-
-      - name: "📦 Install Documentation Dependencies using uv"
-        working-directory: langchain
-        run: |
-          # Install all partner packages in editable mode with overrides
-          python -m uv pip install $(ls ./libs/partners | grep -v azure-ai | xargs -I {} echo "./libs/partners/{}") --overrides ./docs/vercel_overrides.txt --prerelease=allow
-
-          # Install langchain-azure-ai with tools extra
-          python -m uv pip install "./libs/partners/azure-ai[tools]" --overrides ./docs/vercel_overrides.txt --prerelease=allow
-
-          # Install core langchain and other main packages
-          python -m uv pip install libs/core libs/langchain libs/text-splitters libs/community libs/experimental libs/standard-tests
-
-          # Install Sphinx and related packages for building docs
-          python -m uv pip install -r docs/api_reference/requirements.txt
-
-      - name: "🔧 Configure Git Settings"
-        working-directory: langchain
-        run: |
-          git config --local user.email "actions@github.com"
-          git config --local user.name "Github Actions"
-
-      - name: "📚 Build API Documentation"
-        working-directory: langchain
-        run: |
-          # Generate the API reference RST files
-          python docs/api_reference/create_api_rst.py
-
-          # Build the HTML documentation using Sphinx
-          # -T: show full traceback on exception
-          # -E: don't use cached environment (force rebuild, ignore cached doctrees)
-          # -b html: build HTML docs (vs PDS, etc.)
-          # -d: path for the cached environment (parsed document trees / doctrees)
-          #     - Separate from output dir for faster incremental builds
-          # -c: path to conf.py
-          # -j auto: parallel build using all available CPU cores
-          python -m sphinx -T -E -b html -d ../langchain-api-docs-html/_build/doctrees -c docs/api_reference docs/api_reference ../langchain-api-docs-html/api_reference_build/html -j auto
-
-          # Post-process the generated HTML
-          python docs/api_reference/scripts/custom_formatter.py ../langchain-api-docs-html/api_reference_build/html
-
-          # Default index page is blank so we copy in the actual home page.
-          cp ../langchain-api-docs-html/api_reference_build/html/{reference,index}.html
-
-          # Removes Sphinx's intermediate build artifacts after the build is complete.
-          rm -rf ../langchain-api-docs-html/_build/
-
-      # Commit and push changes to langchain-api-docs-html repo
-      - uses: EndBug/add-and-commit@v9
-        with:
-          cwd: langchain-api-docs-html
-          message: "Update API docs build from v0.3 branch"

.github/workflows/v1_changes.md

@@ -1,8 +0,0 @@
-With the deprecation of v0 docs, the following files will need to be migrated/supported
-in the new docs repo:
-
-- run_notebooks.yml: New repo should run Integration tests on code snippets?
-- people.yml: Need to fix and somehow display on the new docs site
-  - Subsequently, `.github/actions/people/`
-- _test_doc_imports.yml
-- check-broken-links.yml

.gitignore

@@ -1,5 +1,5 @@
 .vs/
-.claude/
+.vscode/
 .idea/
 # Byte-compiled / optimized / DLL files
 __pycache__/
@@ -59,7 +59,6 @@ coverage.xml
 *.py,cover
 .hypothesis/
 .pytest_cache/
-.codspeed/
 
 # Translations
 *.mo
@@ -78,6 +77,10 @@ instance/
 # Scrapy stuff:
 .scrapy
 
+# Sphinx documentation
+docs/_build/
+docs/docs/_build/
+
 # PyBuilder
 target/
 
@@ -112,11 +115,13 @@ celerybeat.pid
 # Environments
 .env
 .envrc
-.venv*
-venv*
+.venv
+.venvs
 env/
+venv/
 ENV/
 env.bak/
+venv.bak/
 
 # Spyder project settings
 .spyderproject
@@ -130,7 +135,6 @@ env.bak/
 
 # mypy
 .mypy_cache/
-.mypy_cache_test/
 .dmypy.json
 dmypy.json
 
@@ -158,6 +162,19 @@ data_map*
 *replit*
 
 node_modules
-
-prof
-virtualenv/
+docs/.yarn/
+docs/node_modules/
+docs/.docusaurus/
+docs/.cache-loader/
+docs/_dist
+docs/api_reference/api_reference.rst
+docs/api_reference/experimental_api_reference.rst
+docs/api_reference/_build
+docs/api_reference/*/
+!docs/api_reference/_static/
+!docs/api_reference/templates/
+!docs/api_reference/themes/
+docs/docs/build
+docs/docs/node_modules
+docs/docs/yarn.lock
+_dist

.markdownlint.json

@@ -1,14 +0,0 @@
-{
-  "MD013": false,
-  "MD024": {
-    "siblings_only": true
-  },
-  "MD025": false,
-  "MD033": false,
-  "MD034": false,
-  "MD036": false,
-  "MD041": false,
-  "MD046": {
-    "style": "fenced"
-  }
-}

.pre-commit-config.yaml

@@ -1,99 +0,0 @@
-repos:
-  - repo: local
-    hooks:
-      - id: core
-        name: format and lint core
-        language: system
-        entry: make -C libs/core format lint
-        files: ^libs/core/
-        pass_filenames: false
-      - id: langchain
-        name: format and lint langchain
-        language: system
-        entry: make -C libs/langchain format lint
-        files: ^libs/langchain/
-        pass_filenames: false
-      - id: standard-tests
-        name: format and lint standard-tests
-        language: system
-        entry: make -C libs/standard-tests format lint
-        files: ^libs/standard-tests/
-        pass_filenames: false
-      - id: text-splitters
-        name: format and lint text-splitters
-        language: system
-        entry: make -C libs/text-splitters format lint
-        files: ^libs/text-splitters/
-        pass_filenames: false
-      - id: anthropic
-        name: format and lint partners/anthropic
-        language: system
-        entry: make -C libs/partners/anthropic format lint
-        files: ^libs/partners/anthropic/
-        pass_filenames: false
-      - id: chroma
-        name: format and lint partners/chroma
-        language: system
-        entry: make -C libs/partners/chroma format lint
-        files: ^libs/partners/chroma/
-        pass_filenames: false
-      - id: exa
-        name: format and lint partners/exa
-        language: system
-        entry: make -C libs/partners/exa format lint
-        files: ^libs/partners/exa/
-        pass_filenames: false
-      - id: fireworks
-        name: format and lint partners/fireworks
-        language: system
-        entry: make -C libs/partners/fireworks format lint
-        files: ^libs/partners/fireworks/
-        pass_filenames: false
-      - id: groq
-        name: format and lint partners/groq
-        language: system
-        entry: make -C libs/partners/groq format lint
-        files: ^libs/partners/groq/
-        pass_filenames: false
-      - id: huggingface
-        name: format and lint partners/huggingface
-        language: system
-        entry: make -C libs/partners/huggingface format lint
-        files: ^libs/partners/huggingface/
-        pass_filenames: false
-      - id: mistralai
-        name: format and lint partners/mistralai
-        language: system
-        entry: make -C libs/partners/mistralai format lint
-        files: ^libs/partners/mistralai/
-        pass_filenames: false
-      - id: nomic
-        name: format and lint partners/nomic
-        language: system
-        entry: make -C libs/partners/nomic format lint
-        files: ^libs/partners/nomic/
-        pass_filenames: false
-      - id: ollama
-        name: format and lint partners/ollama
-        language: system
-        entry: make -C libs/partners/ollama format lint
-        files: ^libs/partners/ollama/
-        pass_filenames: false
-      - id: openai
-        name: format and lint partners/openai
-        language: system
-        entry: make -C libs/partners/openai format lint
-        files: ^libs/partners/openai/
-        pass_filenames: false
-      - id: prompty
-        name: format and lint partners/prompty
-        language: system
-        entry: make -C libs/partners/prompty format lint
-        files: ^libs/partners/prompty/
-        pass_filenames: false
-      - id: qdrant
-        name: format and lint partners/qdrant
-        language: system
-        entry: make -C libs/partners/qdrant format lint
-        files: ^libs/partners/qdrant/
-        pass_filenames: false

.readthedocs.yaml

@@ -0,0 +1,32 @@
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Set the version of Python and other tools you might need
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.11"
+  commands:
+      - python -mvirtualenv $READTHEDOCS_VIRTUALENV_PATH
+      - python -m pip install --upgrade --no-cache-dir pip setuptools
+      - python -m pip install --upgrade --no-cache-dir sphinx readthedocs-sphinx-ext
+      - python -m pip install --exists-action=w --no-cache-dir -r docs/api_reference/requirements.txt
+      - python docs/api_reference/create_api_rst.py
+      - cat docs/api_reference/conf.py
+      - python -m sphinx -T -E -b html -d _build/doctrees -c docs/api_reference docs/api_reference $READTHEDOCS_OUTPUT/html -j auto
+
+# Build documentation in the docs/ directory with Sphinx
+sphinx:
+   configuration: docs/api_reference/conf.py
+
+# If using Sphinx, optionally build your docs in additional formats such as PDF
+# formats:
+#    - pdf
+
+# Optionally declare the Python requirements required to build your docs
+python:
+   install:
+   - requirements: docs/api_reference/requirements.txt

.vscode/extensions.json

@@ -1,21 +0,0 @@
-{
-  "recommendations": [
-    "ms-python.python",
-    "charliermarsh.ruff",
-    "ms-python.mypy-type-checker",
-    "ms-toolsai.jupyter",
-    "ms-toolsai.jupyter-keymap",
-    "ms-toolsai.jupyter-renderers",
-    "ms-toolsai.vscode-jupyter-cell-tags",
-    "ms-toolsai.vscode-jupyter-slideshow",
-    "yzhang.markdown-all-in-one",
-    "davidanson.vscode-markdownlint",
-    "bierner.markdown-mermaid",
-    "bierner.markdown-preview-github-styles",
-    "eamodio.gitlens",
-    "github.vscode-pull-request-github",
-    "github.vscode-github-actions",
-    "redhat.vscode-yaml",
-    "editorconfig.editorconfig",
-  ],
-}

.vscode/settings.json

@@ -1,78 +0,0 @@
-{
-  "python.analysis.include": [
-    "libs/**",
-  ],
-  "python.analysis.exclude": [
-    "**/node_modules",
-    "**/__pycache__",
-    "**/.pytest_cache",
-    "**/.*",
-  ],
-  "python.analysis.autoImportCompletions": true,
-  "python.analysis.typeCheckingMode": "basic",
-  "python.testing.cwd": "${workspaceFolder}",
-  "python.linting.enabled": true,
-  "python.linting.ruffEnabled": true,
-  "[python]": {
-    "editor.formatOnSave": true,
-    "editor.codeActionsOnSave": {
-      "source.organizeImports.ruff": "explicit",
-      "source.fixAll": "explicit"
-    },
-    "editor.defaultFormatter": "charliermarsh.ruff"
-  },
-  "editor.rulers": [
-    88
-  ],
-  "editor.tabSize": 4,
-  "editor.insertSpaces": true,
-  "editor.trimAutoWhitespace": true,
-  "files.trimTrailingWhitespace": true,
-  "files.insertFinalNewline": true,
-  "files.exclude": {
-    "**/__pycache__": true,
-    "**/.pytest_cache": true,
-    "**/*.pyc": true,
-    "**/.mypy_cache": true,
-    "**/.ruff_cache": true,
-    "_dist/**": true,
-    "**/node_modules": true,
-    "**/.git": false
-  },
-  "search.exclude": {
-    "**/__pycache__": true,
-    "**/*.pyc": true,
-    "_dist/**": true,
-    "**/node_modules": true,
-    "**/.git": true,
-    "uv.lock": true,
-    "yarn.lock": true
-  },
-  "git.autofetch": true,
-  "git.enableSmartCommit": true,
-  "jupyter.askForKernelRestart": false,
-  "jupyter.interactiveWindow.textEditor.executeSelection": true,
-  "[markdown]": {
-    "editor.wordWrap": "on",
-    "editor.quickSuggestions": {
-      "comments": "off",
-      "strings": "off",
-      "other": "off"
-    }
-  },
-  "[yaml]": {
-    "editor.tabSize": 2,
-    "editor.insertSpaces": true
-  },
-  "[json]": {
-    "editor.tabSize": 2,
-    "editor.insertSpaces": true
-  },
-  "python.terminal.activateEnvironment": false,
-  "python.defaultInterpreterPath": "./.venv/bin/python",
-  "github.copilot.chat.commitMessageGeneration.instructions": [
-    {
-      "file": ".github/workflows/pr_lint.yml"
-    }
-  ]
-}

AGENTS.md

@@ -1,326 +0,0 @@
-# Global Development Guidelines for LangChain Projects
-
-## Core Development Principles
-
-### 1. Maintain Stable Public Interfaces ⚠️ CRITICAL
-
-**Always attempt to preserve function signatures, argument positions, and names for exported/public methods.**
-
-❌ **Bad - Breaking Change:**
-
-```python
-def get_user(id, verbose=False):  # Changed from `user_id`
-    pass
-```
-
-✅ **Good - Stable Interface:**
-
-```python
-def get_user(user_id: str, verbose: bool = False) -> User:
-    """Retrieve user by ID with optional verbose output."""
-    pass
-```
-
-**Before making ANY changes to public APIs:**
-
-- Check if the function/class is exported in `__init__.py`
-- Look for existing usage patterns in tests and examples
-- Use keyword-only arguments for new parameters: `*, new_param: str = "default"`
-- Mark experimental features clearly with docstring warnings (using MkDocs Material admonitions, like `!!! warning`)
-
-🧠 *Ask yourself:* "Would this change break someone's code if they used it last week?"
-
-### 2. Code Quality Standards
-
-**All Python code MUST include type hints and return types.**
-
-❌ **Bad:**
-
-```python
-def p(u, d):
-    return [x for x in u if x not in d]
-```
-
-✅ **Good:**
-
-```python
-def filter_unknown_users(users: list[str], known_users: set[str]) -> list[str]:
-    """Filter out users that are not in the known users set.
-
-    Args:
-        users: List of user identifiers to filter.
-        known_users: Set of known/valid user identifiers.
-
-    Returns:
-        List of users that are not in the known_users set.
-    """
-    return [user for user in users if user not in known_users]
-```
-
-**Style Requirements:**
-
-- Use descriptive, **self-explanatory variable names**. Avoid overly short or cryptic identifiers.
-- Attempt to break up complex functions (>20 lines) into smaller, focused functions where it makes sense
-- Avoid unnecessary abstraction or premature optimization
-- Follow existing patterns in the codebase you're modifying
-
-### 3. Testing Requirements
-
-**Every new feature or bugfix MUST be covered by unit tests.**
-
-**Test Organization:**
-
-- Unit tests: `tests/unit_tests/` (no network calls allowed)
-- Integration tests: `tests/integration_tests/` (network calls permitted)
-- Use `pytest` as the testing framework
-
-**Test Quality Checklist:**
-
-- [ ] Tests fail when your new logic is broken
-- [ ] Happy path is covered
-- [ ] Edge cases and error conditions are tested
-- [ ] Use fixtures/mocks for external dependencies
-- [ ] Tests are deterministic (no flaky tests)
-
-Checklist questions:
-
-- [ ] Does the test suite fail if your new logic is broken?
-- [ ] Are all expected behaviors exercised (happy path, invalid input, etc)?
-- [ ] Do tests use fixtures or mocks where needed?
-
-```python
-def test_filter_unknown_users():
-    """Test filtering unknown users from a list."""
-    users = ["alice", "bob", "charlie"]
-    known_users = {"alice", "bob"}
-
-    result = filter_unknown_users(users, known_users)
-
-    assert result == ["charlie"]
-    assert len(result) == 1
-```
-
-### 4. Security and Risk Assessment
-
-**Security Checklist:**
-
-- No `eval()`, `exec()`, or `pickle` on user-controlled input
-- Proper exception handling (no bare `except:`) and use a `msg` variable for error messages
-- Remove unreachable/commented code before committing
-- Race conditions or resource leaks (file handles, sockets, threads).
-- Ensure proper resource cleanup (file handles, connections)
-
-❌ **Bad:**
-
-```python
-def load_config(path):
-    with open(path) as f:
-        return eval(f.read())  # ⚠️ Never eval config
-```
-
-✅ **Good:**
-
-```python
-import json
-
-def load_config(path: str) -> dict:
-    with open(path) as f:
-        return json.load(f)
-```
-
-### 5. Documentation Standards
-
-**Use Google-style docstrings with Args section for all public functions.**
-
-❌ **Insufficient Documentation:**
-
-```python
-def send_email(to, msg):
-    """Send an email to a recipient."""
-```
-
-✅ **Complete Documentation:**
-
-```python
-def send_email(to: str, msg: str, *, priority: str = "normal") -> bool:
-    """
-    Send an email to a recipient with specified priority.
-
-    Args:
-        to: The email address of the recipient.
-        msg: The message body to send.
-        priority: Email priority level (`'low'`, `'normal'`, `'high'`).
-
-    Returns:
-        `True` if email was sent successfully, `False` otherwise.
-
-    Raises:
-        `InvalidEmailError`: If the email address format is invalid.
-        `SMTPConnectionError`: If unable to connect to email server.
-    """
-```
-
-**Documentation Guidelines:**
-
-- Types go in function signatures, NOT in docstrings
-  - If a default is present, DO NOT repeat it in the docstring unless there is post-processing or it is set conditionally.
-- Focus on "why" rather than "what" in descriptions
-- Document all parameters, return values, and exceptions
-- Keep descriptions concise but clear
-- Ensure American English spelling (e.g., "behavior", not "behaviour")
-
-📌 *Tip:* Keep descriptions concise but clear. Only document return values if non-obvious.
-
-### 6. Architectural Improvements
-
-**When you encounter code that could be improved, suggest better designs:**
-
-❌ **Poor Design:**
-
-```python
-def process_data(data, db_conn, email_client, logger):
-    # Function doing too many things
-    validated = validate_data(data)
-    result = db_conn.save(validated)
-    email_client.send_notification(result)
-    logger.log(f"Processed {len(data)} items")
-    return result
-```
-
-✅ **Better Design:**
-
-```python
-@dataclass
-class ProcessingResult:
-    """Result of data processing operation."""
-    items_processed: int
-    success: bool
-    errors: List[str] = field(default_factory=list)
-
-class DataProcessor:
-    """Handles data validation, storage, and notification."""
-
-    def __init__(self, db_conn: Database, email_client: EmailClient):
-        self.db = db_conn
-        self.email = email_client
-
-    def process(self, data: List[dict]) -> ProcessingResult:
-        """Process and store data with notifications."""
-        validated = self._validate_data(data)
-        result = self.db.save(validated)
-        self._notify_completion(result)
-        return result
-```
-
-**Design Improvement Areas:**
-
-If there's a **cleaner**, **more scalable**, or **simpler** design, highlight it and suggest improvements that would:
-
-- Reduce code duplication through shared utilities
-- Make unit testing easier
-- Improve separation of concerns (single responsibility)
-- Make unit testing easier through dependency injection
-- Add clarity without adding complexity
-- Prefer dataclasses for structured data
-
-## Development Tools & Commands
-
-### Package Management
-
-```bash
-# Add package
-uv add package-name
-
-# Sync project dependencies
-uv sync
-uv lock
-```
-
-### Testing
-
-```bash
-# Run unit tests (no network)
-make test
-
-# Don't run integration tests, as API keys must be set
-
-# Run specific test file
-uv run --group test pytest tests/unit_tests/test_specific.py
-```
-
-### Code Quality
-
-```bash
-# Lint code
-make lint
-
-# Format code
-make format
-
-# Type checking
-uv run --group lint mypy .
-```
-
-### Dependency Management Patterns
-
-**Local Development Dependencies:**
-
-```toml
-[tool.uv.sources]
-langchain-core = { path = "../core", editable = true }
-langchain-tests = { path = "../standard-tests", editable = true }
-```
-
-**For tools, use the `@tool` decorator from `langchain_core.tools`:**
-
-```python
-from langchain_core.tools import tool
-
-@tool
-def search_database(query: str) -> str:
-    """Search the database for relevant information.
-
-    Args:
-        query: The search query string.
-    """
-    # Implementation here
-    return results
-```
-
-## Commit Standards
-
-**Use Conventional Commits format for PR titles:**
-
-- `feat(core): add multi-tenant support`
-- `fix(cli): resolve flag parsing error`
-- `docs: update API usage examples`
-- `docs(openai): update API usage examples`
-
-## Framework-Specific Guidelines
-
-- Follow the existing patterns in `langchain-core` for base abstractions
-- Use `langchain_core.callbacks` for execution tracking
-- Implement proper streaming support where applicable
-- Avoid deprecated components like legacy `LLMChain`
-
-### Partner Integrations
-
-- Follow the established patterns in existing partner libraries
-- Implement standard interfaces (`BaseChatModel`, `BaseEmbeddings`, etc.)
-- Include comprehensive integration tests
-- Document API key requirements and authentication
-
----
-
-## Quick Reference Checklist
-
-Before submitting code changes:
-
-- [ ] **Breaking Changes**: Verified no public API changes
-- [ ] **Type Hints**: All functions have complete type annotations
-- [ ] **Tests**: New functionality is fully tested
-- [ ] **Security**: No dangerous patterns (eval, silent failures, etc.)
-- [ ] **Documentation**: Google-style docstrings for public functions
-- [ ] **Code Quality**: `make lint` and `make format` pass
-- [ ] **Architecture**: Suggested improvements where applicable
-- [ ] **Commit Message**: Follows Conventional Commits format

CLAUDE.md

@@ -1,326 +0,0 @@
-# Global Development Guidelines for LangChain Projects
-
-## Core Development Principles
-
-### 1. Maintain Stable Public Interfaces ⚠️ CRITICAL
-
-**Always attempt to preserve function signatures, argument positions, and names for exported/public methods.**
-
-❌ **Bad - Breaking Change:**
-
-```python
-def get_user(id, verbose=False):  # Changed from `user_id`
-    pass
-```
-
-✅ **Good - Stable Interface:**
-
-```python
-def get_user(user_id: str, verbose: bool = False) -> User:
-    """Retrieve user by ID with optional verbose output."""
-    pass
-```
-
-**Before making ANY changes to public APIs:**
-
-- Check if the function/class is exported in `__init__.py`
-- Look for existing usage patterns in tests and examples
-- Use keyword-only arguments for new parameters: `*, new_param: str = "default"`
-- Mark experimental features clearly with docstring warnings (using MkDocs Material admonitions, like `!!! warning`)
-
-🧠 *Ask yourself:* "Would this change break someone's code if they used it last week?"
-
-### 2. Code Quality Standards
-
-**All Python code MUST include type hints and return types.**
-
-❌ **Bad:**
-
-```python
-def p(u, d):
-    return [x for x in u if x not in d]
-```
-
-✅ **Good:**
-
-```python
-def filter_unknown_users(users: list[str], known_users: set[str]) -> list[str]:
-    """Filter out users that are not in the known users set.
-
-    Args:
-        users: List of user identifiers to filter.
-        known_users: Set of known/valid user identifiers.
-
-    Returns:
-        List of users that are not in the known_users set.
-    """
-    return [user for user in users if user not in known_users]
-```
-
-**Style Requirements:**
-
-- Use descriptive, **self-explanatory variable names**. Avoid overly short or cryptic identifiers.
-- Attempt to break up complex functions (>20 lines) into smaller, focused functions where it makes sense
-- Avoid unnecessary abstraction or premature optimization
-- Follow existing patterns in the codebase you're modifying
-
-### 3. Testing Requirements
-
-**Every new feature or bugfix MUST be covered by unit tests.**
-
-**Test Organization:**
-
-- Unit tests: `tests/unit_tests/` (no network calls allowed)
-- Integration tests: `tests/integration_tests/` (network calls permitted)
-- Use `pytest` as the testing framework
-
-**Test Quality Checklist:**
-
-- [ ] Tests fail when your new logic is broken
-- [ ] Happy path is covered
-- [ ] Edge cases and error conditions are tested
-- [ ] Use fixtures/mocks for external dependencies
-- [ ] Tests are deterministic (no flaky tests)
-
-Checklist questions:
-
-- [ ] Does the test suite fail if your new logic is broken?
-- [ ] Are all expected behaviors exercised (happy path, invalid input, etc)?
-- [ ] Do tests use fixtures or mocks where needed?
-
-```python
-def test_filter_unknown_users():
-    """Test filtering unknown users from a list."""
-    users = ["alice", "bob", "charlie"]
-    known_users = {"alice", "bob"}
-
-    result = filter_unknown_users(users, known_users)
-
-    assert result == ["charlie"]
-    assert len(result) == 1
-```
-
-### 4. Security and Risk Assessment
-
-**Security Checklist:**
-
-- No `eval()`, `exec()`, or `pickle` on user-controlled input
-- Proper exception handling (no bare `except:`) and use a `msg` variable for error messages
-- Remove unreachable/commented code before committing
-- Race conditions or resource leaks (file handles, sockets, threads).
-- Ensure proper resource cleanup (file handles, connections)
-
-❌ **Bad:**
-
-```python
-def load_config(path):
-    with open(path) as f:
-        return eval(f.read())  # ⚠️ Never eval config
-```
-
-✅ **Good:**
-
-```python
-import json
-
-def load_config(path: str) -> dict:
-    with open(path) as f:
-        return json.load(f)
-```
-
-### 5. Documentation Standards
-
-**Use Google-style docstrings with Args section for all public functions.**
-
-❌ **Insufficient Documentation:**
-
-```python
-def send_email(to, msg):
-    """Send an email to a recipient."""
-```
-
-✅ **Complete Documentation:**
-
-```python
-def send_email(to: str, msg: str, *, priority: str = "normal") -> bool:
-    """
-    Send an email to a recipient with specified priority.
-
-    Args:
-        to: The email address of the recipient.
-        msg: The message body to send.
-        priority: Email priority level (`'low'`, `'normal'`, `'high'`).
-
-    Returns:
-        `True` if email was sent successfully, `False` otherwise.
-
-    Raises:
-        `InvalidEmailError`: If the email address format is invalid.
-        `SMTPConnectionError`: If unable to connect to email server.
-    """
-```
-
-**Documentation Guidelines:**
-
-- Types go in function signatures, NOT in docstrings
-  - If a default is present, DO NOT repeat it in the docstring unless there is post-processing or it is set conditionally.
-- Focus on "why" rather than "what" in descriptions
-- Document all parameters, return values, and exceptions
-- Keep descriptions concise but clear
-- Ensure American English spelling (e.g., "behavior", not "behaviour")
-
-📌 *Tip:* Keep descriptions concise but clear. Only document return values if non-obvious.
-
-### 6. Architectural Improvements
-
-**When you encounter code that could be improved, suggest better designs:**
-
-❌ **Poor Design:**
-
-```python
-def process_data(data, db_conn, email_client, logger):
-    # Function doing too many things
-    validated = validate_data(data)
-    result = db_conn.save(validated)
-    email_client.send_notification(result)
-    logger.log(f"Processed {len(data)} items")
-    return result
-```
-
-✅ **Better Design:**
-
-```python
-@dataclass
-class ProcessingResult:
-    """Result of data processing operation."""
-    items_processed: int
-    success: bool
-    errors: List[str] = field(default_factory=list)
-
-class DataProcessor:
-    """Handles data validation, storage, and notification."""
-
-    def __init__(self, db_conn: Database, email_client: EmailClient):
-        self.db = db_conn
-        self.email = email_client
-
-    def process(self, data: List[dict]) -> ProcessingResult:
-        """Process and store data with notifications."""
-        validated = self._validate_data(data)
-        result = self.db.save(validated)
-        self._notify_completion(result)
-        return result
-```
-
-**Design Improvement Areas:**
-
-If there's a **cleaner**, **more scalable**, or **simpler** design, highlight it and suggest improvements that would:
-
-- Reduce code duplication through shared utilities
-- Make unit testing easier
-- Improve separation of concerns (single responsibility)
-- Make unit testing easier through dependency injection
-- Add clarity without adding complexity
-- Prefer dataclasses for structured data
-
-## Development Tools & Commands
-
-### Package Management
-
-```bash
-# Add package
-uv add package-name
-
-# Sync project dependencies
-uv sync
-uv lock
-```
-
-### Testing
-
-```bash
-# Run unit tests (no network)
-make test
-
-# Don't run integration tests, as API keys must be set
-
-# Run specific test file
-uv run --group test pytest tests/unit_tests/test_specific.py
-```
-
-### Code Quality
-
-```bash
-# Lint code
-make lint
-
-# Format code
-make format
-
-# Type checking
-uv run --group lint mypy .
-```
-
-### Dependency Management Patterns
-
-**Local Development Dependencies:**
-
-```toml
-[tool.uv.sources]
-langchain-core = { path = "../core", editable = true }
-langchain-tests = { path = "../standard-tests", editable = true }
-```
-
-**For tools, use the `@tool` decorator from `langchain_core.tools`:**
-
-```python
-from langchain_core.tools import tool
-
-@tool
-def search_database(query: str) -> str:
-    """Search the database for relevant information.
-
-    Args:
-        query: The search query string.
-    """
-    # Implementation here
-    return results
-```
-
-## Commit Standards
-
-**Use Conventional Commits format for PR titles:**
-
-- `feat(core): add multi-tenant support`
-- `fix(cli): resolve flag parsing error`
-- `docs: update API usage examples`
-- `docs(openai): update API usage examples`
-
-## Framework-Specific Guidelines
-
-- Follow the existing patterns in `langchain-core` for base abstractions
-- Use `langchain_core.callbacks` for execution tracking
-- Implement proper streaming support where applicable
-- Avoid deprecated components like legacy `LLMChain`
-
-### Partner Integrations
-
-- Follow the established patterns in existing partner libraries
-- Implement standard interfaces (`BaseChatModel`, `BaseEmbeddings`, etc.)
-- Include comprehensive integration tests
-- Document API key requirements and authentication
-
----
-
-## Quick Reference Checklist
-
-Before submitting code changes:
-
-- [ ] **Breaking Changes**: Verified no public API changes
-- [ ] **Type Hints**: All functions have complete type annotations
-- [ ] **Tests**: New functionality is fully tested
-- [ ] **Security**: No dangerous patterns (eval, silent failures, etc.)
-- [ ] **Documentation**: Google-style docstrings for public functions
-- [ ] **Code Quality**: `make lint` and `make format` pass
-- [ ] **Architecture**: Suggested improvements where applicable
-- [ ] **Commit Message**: Follows Conventional Commits format

LICENSE

@@ -1,6 +1,6 @@
-MIT License
+The MIT License
 
-Copyright (c) LangChain, Inc.
+Copyright (c) Harrison Chase
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal
@@ -9,13 +9,13 @@ to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 copies of the Software, and to permit persons to whom the Software is
 furnished to do so, subject to the following conditions:
 
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
 
 THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
 AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

MIGRATE.md

@@ -1,9 +1,61 @@
-# Migrating
+# Migrating to `langchain_experimental`
 
-Please see the following guides for migrating LangChain code:
+We are moving any experimental components of LangChain, or components with vulnerability issues, into `langchain_experimental`.
+This guide covers how to migrate.
 
-* Migrate to [LangChain v1.0](https://docs.langchain.com/oss/python/migrate/langchain-v1)
-* Migrate to [LangChain v0.3](https://python.langchain.com/docs/versions/v0_3/)
-* Migrate to [LangChain v0.2](https://python.langchain.com/docs/versions/v0_2/)
-* Migrating from [LangChain 0.0.x Chains](https://python.langchain.com/docs/versions/migrating_chains/)
-* Upgrade to [LangGraph Memory](https://python.langchain.com/docs/versions/migrating_memory/)
+## Installation
+
+Previously:
+
+`pip install -U langchain`
+
+Now (only if you want to access things in experimental):
+
+`pip install -U langchain langchain_experimental`
+
+## Things in `langchain.experimental`
+
+Previously:
+
+`from langchain.experimental import ...`
+
+Now:
+
+`from langchain_experimental import ...`
+
+## PALChain
+
+Previously:
+
+`from langchain.chains import PALChain`
+
+Now:
+
+`from langchain_experimental.pal_chain import PALChain`
+
+## SQLDatabaseChain
+
+Previously:
+
+`from langchain.chains import SQLDatabaseChain`
+
+Now:
+
+`from langchain_experimental.sql import SQLDatabaseChain`
+
+Alternatively, if you are just interested in using the query generation part of the SQL chain, you can check out [`create_sql_query_chain`](https://github.com/langchain-ai/langchain/blob/master/docs/extras/use_cases/tabular/sql_query.ipynb)
+
+`from langchain.chains import create_sql_query_chain`
+
+## `load_prompt` for Python files
+
+Note: this only applies if you want to load Python files as prompts.
+If you want to load json/yaml files, no change is needed.
+
+Previously:
+
+`from langchain.prompts import load_prompt`
+
+Now:
+
+`from langchain_experimental.prompts import load_prompt`

Makefile

@@ -0,0 +1,56 @@
+.PHONY: all clean docs_build docs_clean docs_linkcheck api_docs_build api_docs_clean api_docs_linkcheck
+
+# Default target executed when no arguments are given to make.
+all: help
+
+
+######################
+# DOCUMENTATION
+######################
+
+clean: docs_clean api_docs_clean
+
+
+docs_build:
+	docs/.local_build.sh
+
+docs_clean:
+	rm -r _dist
+
+docs_linkcheck:
+	poetry run linkchecker _dist/docs/ --ignore-url node_modules
+
+api_docs_build:
+	poetry run python docs/api_reference/create_api_rst.py
+	cd docs/api_reference && poetry run make html
+
+api_docs_clean:
+	rm -f docs/api_reference/api_reference.rst
+	cd docs/api_reference && poetry run make clean
+
+api_docs_linkcheck:
+	poetry run linkchecker docs/api_reference/_build/html/index.html
+
+spell_check:
+	poetry run codespell --toml pyproject.toml
+
+spell_fix:
+	poetry run codespell --toml pyproject.toml -w
+
+######################
+# HELP
+######################
+
+help:
+	@echo '===================='
+	@echo '-- DOCUMENTATION --'
+	@echo 'clean                        - run docs_clean and api_docs_clean'
+	@echo 'docs_build                   - build the documentation'
+	@echo 'docs_clean                   - clean the documentation build artifacts'
+	@echo 'docs_linkcheck               - run linkchecker on the documentation'
+	@echo 'api_docs_build               - build the API Reference documentation'
+	@echo 'api_docs_clean               - clean the API Reference documentation build artifacts'
+	@echo 'api_docs_linkcheck           - run linkchecker on the API Reference documentation'
+	@echo 'spell_check               	- run codespell on the project'
+	@echo 'spell_fix               		- run codespell on the project and fix the errors'
+	@echo '-- TEST and LINT tasks are within libs/*/ per-package --'

README.md

@@ -1,77 +1,104 @@
-<p align="center">
-  <picture>
-    <source media="(prefers-color-scheme: light)" srcset=".github/images/logo-dark.svg">
-    <source media="(prefers-color-scheme: dark)" srcset=".github/images/logo-light.svg">
-    <img alt="LangChain Logo" src=".github/images/logo-dark.svg" width="80%">
-  </picture>
-</p>
+# 🦜️🔗 LangChain
 
-<p align="center">
-    The platform for reliable agents.
-</p>
+⚡ Building applications with LLMs through composability ⚡
 
-<p align="center">
-  <a href="https://opensource.org/licenses/MIT" target="_blank">
-      <img src="https://img.shields.io/pypi/l/langchain" alt="PyPI - License">
-  </a>
-  <a href="https://pypistats.org/packages/langchain" target="_blank">
-      <img src="https://img.shields.io/pepy/dt/langchain" alt="PyPI - Downloads">
-  </a>
-  <a href="https://pypi.org/project/langchain/#history" target="_blank">
-      <img src="https://img.shields.io/pypi/v/langchain?label=%20" alt="Version">
-  </a>
-  <a href="https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langchain-ai/langchain" target="_blank">
-      <img src="https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode" alt="Open in Dev Containers">
-  </a>
-  <a href="https://codespaces.new/langchain-ai/langchain" target="_blank">
-      <img src="https://github.com/codespaces/badge.svg" alt="Open in Github Codespace" title="Open in Github Codespace" width="150" height="20">
-  </a>
-  <a href="https://codspeed.io/langchain-ai/langchain" target="_blank">
-      <img src="https://img.shields.io/endpoint?url=https://codspeed.io/badge.json" alt="CodSpeed Badge">
-  </a>
-  <a href="https://twitter.com/langchainai" target="_blank">
-      <img src="https://img.shields.io/twitter/url/https/twitter.com/langchainai.svg?style=social&label=Follow%20%40LangChainAI" alt="Twitter / X">
-  </a>
-</p>
+[![Release Notes](https://img.shields.io/github/release/langchain-ai/langchain)](https://github.com/langchain-ai/langchain/releases)
+[![CI](https://github.com/langchain-ai/langchain/actions/workflows/langchain_ci.yml/badge.svg)](https://github.com/langchain-ai/langchain/actions/workflows/langchain_ci.yml)
+[![Experimental CI](https://github.com/langchain-ai/langchain/actions/workflows/langchain_experimental_ci.yml/badge.svg)](https://github.com/langchain-ai/langchain/actions/workflows/langchain_experimental_ci.yml)
+[![Downloads](https://static.pepy.tech/badge/langchain/month)](https://pepy.tech/project/langchain)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Twitter](https://img.shields.io/twitter/url/https/twitter.com/langchainai.svg?style=social&label=Follow%20%40LangChainAI)](https://twitter.com/langchainai)
+[![](https://dcbadge.vercel.app/api/server/6adMQxSpJS?compact=true&style=flat)](https://discord.gg/6adMQxSpJS)
+[![Open in Dev Containers](https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langchain-ai/langchain)
+[![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/langchain-ai/langchain)
+[![GitHub star chart](https://img.shields.io/github/stars/langchain-ai/langchain?style=social)](https://star-history.com/#langchain-ai/langchain)
+[![Dependency Status](https://img.shields.io/librariesio/github/langchain-ai/langchain)](https://libraries.io/github/langchain-ai/langchain)
+[![Open Issues](https://img.shields.io/github/issues-raw/langchain-ai/langchain)](https://github.com/langchain-ai/langchain/issues)
 
-LangChain is a framework for building LLM-powered applications. It helps you chain together interoperable components and third-party integrations to simplify AI application development —  all while future-proofing decisions as the underlying technology evolves.
 
-```bash
-pip install langchain
-```
+Looking for the JS/TS version? Check out [LangChain.js](https://github.com/langchain-ai/langchainjs).
 
----
+To help you ship LangChain apps to production faster, check out [LangSmith](https://smith.langchain.com). 
+[LangSmith](https://smith.langchain.com) is a unified developer platform for building, testing, and monitoring LLM applications. 
+Fill out [this form](https://airtable.com/appwQzlErAS2qiP0L/shrGtGaVBVAz7NcV2) to get off the waitlist or speak with our sales team
 
-**Documentation**: To learn more about LangChain, check out [the docs](https://docs.langchain.com/oss/python/langchain/overview).
+## 🚨Breaking Changes for select chains (SQLDatabase) on 7/28/23
 
-If you're looking for more advanced customization or agent orchestration, check out [LangGraph](https://docs.langchain.com/oss/python/langgraph/overview), our framework for building controllable agent workflows.
+In an effort to make `langchain` leaner and safer, we are moving select chains to `langchain_experimental`.
+This migration has already started, but we are remaining backwards compatible until 7/28.
+On that date, we will remove functionality from `langchain`.
+Read more about the motivation and the progress [here](https://github.com/langchain-ai/langchain/discussions/8043).
+Read how to migrate your code [here](MIGRATE.md).
 
-> [!NOTE]
-> Looking for the JS/TS library? Check out [LangChain.js](https://github.com/langchain-ai/langchainjs).
+## Quick Install
 
-## Why use LangChain?
+`pip install langchain`
+or
+`pip install langsmith && conda install langchain -c conda-forge`
 
-LangChain helps developers build applications powered by LLMs through a standard interface for models, embeddings, vector stores, and more.
+## 🤔 What is this?
 
-Use LangChain for:
+Large language models (LLMs) are emerging as a transformative technology, enabling developers to build applications that they previously could not. However, using these LLMs in isolation is often insufficient for creating a truly powerful app - the real power comes when you can combine them with other sources of computation or knowledge.
 
-- **Real-time data augmentation**. Easily connect LLMs to diverse data sources and external/internal systems, drawing from LangChain’s vast library of integrations with model providers, tools, vector stores, retrievers, and more.
-- **Model interoperability**. Swap models in and out as your engineering team experiments to find the best choice for your application’s needs. As the industry frontier evolves, adapt quickly — LangChain’s abstractions keep you moving without losing momentum.
+This library aims to assist in the development of those types of applications. Common examples of these applications include:
 
-## LangChain’s ecosystem
+**❓ Question Answering over specific documents**
 
-While the LangChain framework can be used standalone, it also integrates seamlessly with any LangChain product, giving developers a full suite of tools when building LLM applications.
+- [Documentation](https://python.langchain.com/docs/use_cases/question_answering/)
+- End-to-end Example: [Question Answering over Notion Database](https://github.com/hwchase17/notion-qa)
 
-To improve your LLM application development, pair LangChain with:
+**💬 Chatbots**
 
-- [LangSmith](https://www.langchain.com/langsmith) - Helpful for agent evals and observability. Debug poor-performing LLM app runs, evaluate agent trajectories, gain visibility in production, and improve performance over time.
-- [LangGraph](https://docs.langchain.com/oss/python/langgraph/overview) - Build agents that can reliably handle complex tasks with LangGraph, our low-level agent orchestration framework. LangGraph offers customizable architecture, long-term memory, and human-in-the-loop workflows — and is trusted in production by companies like LinkedIn, Uber, Klarna, and GitLab.
-- [LangGraph Platform](https://docs.langchain.com/langgraph-platform) - Deploy and scale agents effortlessly with a purpose-built deployment platform for long-running, stateful workflows. Discover, reuse, configure, and share agents across teams — and iterate quickly with visual prototyping in [LangGraph Studio](https://langchain-ai.github.io/langgraph/concepts/langgraph_studio).
+- [Documentation](https://python.langchain.com/docs/use_cases/chatbots/)
+- End-to-end Example: [Chat-LangChain](https://github.com/langchain-ai/chat-langchain)
 
-## Additional resources
+**🤖 Agents**
 
-- [Learn](https://docs.langchain.com/oss/python/learn): Use cases, conceptual overviews, and more.
-- [API Reference](https://reference.langchain.com/python): Detailed reference on
-navigating base packages and integrations for LangChain.
-- [LangChain Forum](https://forum.langchain.com): Connect with the community and share all of your technical questions, ideas, and feedback.
-- [Chat LangChain](https://chat.langchain.com): Ask questions & chat with our documentation.
+- [Documentation](https://python.langchain.com/docs/modules/agents/)
+- End-to-end Example: [GPT+WolframAlpha](https://huggingface.co/spaces/JavaFXpert/Chat-GPT-LangChain)
+
+## 📖 Documentation
+
+Please see [here](https://python.langchain.com) for full documentation on:
+
+- Getting started (installation, setting up the environment, simple examples)
+- How-To examples (demos, integrations, helper functions)
+- Reference (full API docs)
+- Resources (high-level explanation of core concepts)
+
+## 🚀 What can this help with?
+
+There are six main areas that LangChain is designed to help with.
+These are, in increasing order of complexity:
+
+**📃 LLMs and Prompts:**
+
+This includes prompt management, prompt optimization, a generic interface for all LLMs, and common utilities for working with LLMs.
+
+**🔗 Chains:**
+
+Chains go beyond a single LLM call and involve sequences of calls (whether to an LLM or a different utility). LangChain provides a standard interface for chains, lots of integrations with other tools, and end-to-end chains for common applications.
+
+**📚 Data Augmented Generation:**
+
+Data Augmented Generation involves specific types of chains that first interact with an external data source to fetch data for use in the generation step. Examples include summarization of long pieces of text and question/answering over specific data sources.
+
+**🤖 Agents:**
+
+Agents involve an LLM making decisions about which Actions to take, taking that Action, seeing an Observation, and repeating that until done. LangChain provides a standard interface for agents, a selection of agents to choose from, and examples of end-to-end agents.
+
+**🧠 Memory:**
+
+Memory refers to persisting state between calls of a chain/agent. LangChain provides a standard interface for memory, a collection of memory implementations, and examples of chains/agents that use memory.
+
+**🧐 Evaluation:**
+
+[BETA] Generative models are notoriously hard to evaluate with traditional metrics. One new way of evaluating them is by using language models themselves to do the evaluation. LangChain provides some prompts/chains for assisting in this.
+
+For more information on these concepts, please see our [full documentation](https://python.langchain.com).
+
+## 💁 Contributing
+
+As an open-source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of a new feature, improved infrastructure, or better documentation.
+
+For detailed information on how to contribute, see [here](.github/CONTRIBUTING.md).

SECURITY.md

@@ -1,80 +1,6 @@
 # Security Policy
 
-LangChain has a large ecosystem of integrations with various external resources like local and remote file systems, APIs and databases. These integrations allow developers to create versatile applications that combine the power of LLMs with the ability to access, interact with and manipulate external resources.
+## Reporting a Vulnerability
 
-## Best practices
-
-When building such applications, developers should remember to follow good security practices:
-
-* [**Limit Permissions**](https://en.wikipedia.org/wiki/Principle_of_least_privilege): Scope permissions specifically to the application's need. Granting broad or excessive permissions can introduce significant security vulnerabilities. To avoid such vulnerabilities, consider using read-only credentials, disallowing access to sensitive resources, using sandboxing techniques (such as running inside a container), specifying proxy configurations to control external requests, etc., as appropriate for your application.
-* **Anticipate Potential Misuse**: Just as humans can err, so can Large Language Models (LLMs). Always assume that any system access or credentials may be used in any way allowed by the permissions they are assigned. For example, if a pair of database credentials allows deleting data, it's safest to assume that any LLM able to use those credentials may in fact delete data.
-* [**Defense in Depth**](https://en.wikipedia.org/wiki/Defense_in_depth_(computing)): No security technique is perfect. Fine-tuning and good chain design can reduce, but not eliminate, the odds that a Large Language Model (LLM) may make a mistake. It's best to combine multiple layered security approaches rather than relying on any single layer of defense to ensure security. For example: use both read-only permissions and sandboxing to ensure that LLMs are only able to access data that is explicitly meant for them to use.
-
-Risks of not doing so include, but are not limited to:
-
-* Data corruption or loss.
-* Unauthorized access to confidential information.
-* Compromised performance or availability of critical resources.
-
-Example scenarios with mitigation strategies:
-
-* A user may ask an agent with access to the file system to delete files that should not be deleted or read the content of files that contain sensitive information. To mitigate, limit the agent to only use a specific directory and only allow it to read or write files that are safe to read or write. Consider further sandboxing the agent by running it in a container.
-* A user may ask an agent with write access to an external API to write malicious data to the API, or delete data from that API. To mitigate, give the agent read-only API keys, or limit it to only use endpoints that are already resistant to such misuse.
-* A user may ask an agent with access to a database to drop a table or mutate the schema. To mitigate, scope the credentials to only the tables that the agent needs to access and consider issuing READ-ONLY credentials.
-
-If you're building applications that access external resources like file systems, APIs or databases, consider speaking with your company's security team to determine how to best design and secure your applications.
-
-## Reporting OSS Vulnerabilities
-
-LangChain is partnered with [huntr by Protect AI](https://huntr.com/) to provide
-a bounty program for our open source projects.
-
-Please report security vulnerabilities associated with the LangChain
-open source projects at [huntr](https://huntr.com/bounties/disclose/?target=https%3A%2F%2Fgithub.com%2Flangchain-ai%2Flangchain&validSearch=true).
-
-Before reporting a vulnerability, please review:
-
-1) In-Scope Targets and Out-of-Scope Targets below.
-2) The [langchain-ai/langchain](https://docs.langchain.com/oss/python/contributing/code#repository-structure) monorepo structure.
-3) The [Best Practices](#best-practices) above to understand what we consider to be a security vulnerability vs. developer responsibility.
-
-### In-Scope Targets
-
-The following packages and repositories are eligible for bug bounties:
-
-* langchain-core
-* langchain (see exceptions)
-* langchain-community (see exceptions)
-* langgraph
-* langserve
-
-### Out of Scope Targets
-
-All out of scope targets defined by huntr as well as:
-
-* **langchain-experimental**: This repository is for experimental code and is not
-  eligible for bug bounties (see [package warning](https://pypi.org/project/langchain-experimental/)), bug reports to it will be marked as interesting or waste of
-  time and published with no bounty attached.
-* **tools**: Tools in either langchain or langchain-community are not eligible for bug
-  bounties. This includes the following directories
-  * libs/langchain/langchain/tools
-  * libs/community/langchain_community/tools
-  * Please review the [Best Practices](#best-practices)
-    for more details, but generally tools interact with the real world. Developers are
-    expected to understand the security implications of their code and are responsible
-    for the security of their tools.
-* Code documented with security notices. This will be decided on a case-by-case basis, but likely will not be eligible for a bounty as the code is already
-  documented with guidelines for developers that should be followed for making their
-  application secure.
-* Any LangSmith related repositories or APIs (see [Reporting LangSmith Vulnerabilities](#reporting-langsmith-vulnerabilities)).
-
-## Reporting LangSmith Vulnerabilities
-
-Please report security vulnerabilities associated with LangSmith by email to `security@langchain.dev`.
-
-* LangSmith site: [https://smith.langchain.com](https://smith.langchain.com)
-* SDK client: [https://github.com/langchain-ai/langsmith-sdk](https://github.com/langchain-ai/langsmith-sdk)
-
-### Other Security Concerns
-
-For any other security concerns, please contact us at `security@langchain.dev`.
+Please report security vulnerabilities by email to `security@langchain.dev`.
+This email is an alias to a subset of our maintainers, and will ensure the issue is promptly triaged and acted upon as needed.

cookbook/LLaMA2_sql_chat.ipynb

@@ -0,0 +1,400 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "fc935871-7640-41c6-b798-58514d860fe0",
+   "metadata": {},
+   "source": [
+    "## LLaMA2 chat with SQL\n",
+    "\n",
+    "Open source, local LLMs are great to consider for any application that demands data privacy.\n",
+    "\n",
+    "SQL is one good example. \n",
+    "\n",
+    "This cookbook shows how to perform text-to-SQL using various local versions of LLaMA2 run locally.\n",
+    "\n",
+    "## Packages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "81adcf8b-395a-4f02-8749-ac976942b446",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "! pip install langchain replicate"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8e13ed66-300b-4a23-b8ac-44df68ee4733",
+   "metadata": {},
+   "source": [
+    "## LLM\n",
+    "\n",
+    "There are a few ways to access LLaMA2.\n",
+    "\n",
+    "To run locally, we use Ollama.ai. \n",
+    "\n",
+    "See [here](https://python.langchain.com/docs/integrations/chat/ollama) for details on installation and setup.\n",
+    "\n",
+    "Also, see [here](https://python.langchain.com/docs/guides/local_llms) for our full guide on local LLMs.\n",
+    " \n",
+    "To use an external API, which is not private, we can use Replicate."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "6a75a5c6-34ee-4ab9-a664-d9b432d812ee",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Init param `input` is deprecated, please use `model_kwargs` instead.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Local \n",
+    "from langchain.chat_models import ChatOllama\n",
+    "llama2_chat = ChatOllama(model=\"llama2:13b-chat\")\n",
+    "llama2_code = ChatOllama(model=\"codellama:7b-instruct\")\n",
+    "\n",
+    "# API\n",
+    "from getpass import getpass\n",
+    "from langchain.llms import Replicate\n",
+    "# REPLICATE_API_TOKEN = getpass()\n",
+    "# os.environ[\"REPLICATE_API_TOKEN\"] = REPLICATE_API_TOKEN\n",
+    "replicate_id = \"meta/llama-2-13b-chat:f4e2de70d66816a838a89eeeb621910adffb0dd0baba3976c96980970978018d\"\n",
+    "llama2_chat_replicate = Replicate(\n",
+    "    model=replicate_id,\n",
+    "    input={\"temperature\": 0.01, \n",
+    "           \"max_length\": 500, \n",
+    "           \"top_p\": 1}\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "ce96f7ea-b3d5-44e1-9fa5-a79e04a9e1fb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Simply set the LLM we want to use\n",
+    "llm = llama2_chat"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "80222165-f353-4e35-a123-5f70fd70c6c8",
+   "metadata": {},
+   "source": [
+    "## DB\n",
+    "\n",
+    "Connect to a SQLite DB.\n",
+    "\n",
+    "To create this particular DB, you can use the code and follow the steps shown [here](https://github.com/facebookresearch/llama-recipes/blob/main/demo_apps/StructuredLlama.ipynb)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "025bdd82-3bb1-4948-bc7c-c3ccd94fd05c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.utilities import SQLDatabase\n",
+    "db = SQLDatabase.from_uri(\"sqlite:///nba_roster.db\", sample_rows_in_table_info= 0)\n",
+    "\n",
+    "def get_schema(_):\n",
+    "    return db.get_table_info()\n",
+    "\n",
+    "def run_query(query):\n",
+    "    return db.run(query)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "654b3577-baa2-4e12-a393-f40e5db49ac7",
+   "metadata": {},
+   "source": [
+    "## Query a SQL DB \n",
+    "\n",
+    "Follow the runnables workflow [here](https://python.langchain.com/docs/expression_language/cookbook/sql_db)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "5a4933ea-d9c0-4b0a-8177-ba4490c6532b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "' SELECT \"Team\" FROM nba_roster WHERE \"NAME\" = \\'Klay Thompson\\';'"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Prompt\n",
+    "from langchain.prompts import ChatPromptTemplate\n",
+    "template = \"\"\"Based on the table schema below, write a SQL query that would answer the user's question:\n",
+    "{schema}\n",
+    "\n",
+    "Question: {question}\n",
+    "SQL Query:\"\"\"\n",
+    "prompt = ChatPromptTemplate.from_messages([\n",
+    "    (\"system\", \"Given an input question, convert it to a SQL query. No pre-amble.\"),\n",
+    "    (\"human\", template)\n",
+    "])\n",
+    "\n",
+    "# Chain to query\n",
+    "from langchain.schema.output_parser import StrOutputParser\n",
+    "from langchain.schema.runnable import RunnablePassthrough\n",
+    "\n",
+    "sql_response = (\n",
+    "        RunnablePassthrough.assign(schema=get_schema)\n",
+    "        | prompt\n",
+    "        | llm.bind(stop=[\"\\nSQLResult:\"])\n",
+    "        | StrOutputParser()\n",
+    "    )\n",
+    "\n",
+    "sql_response.invoke({\"question\": \"What team is Klay Thompson on?\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a0e9e2c8-9b88-4853-ac86-001bc6cc6695",
+   "metadata": {},
+   "source": [
+    "We can review the results:\n",
+    "\n",
+    "* [LangSmith trace](https://smith.langchain.com/public/afa56a06-b4e2-469a-a60f-c1746e75e42b/r) LLaMA2-13 Replicate API\n",
+    "* [LangSmith trace](https://smith.langchain.com/public/2d4ecc72-6b8f-4523-8f0b-ea95c6b54a1d/r) LLaMA2-13 local \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "2a2825e3-c1b6-4f7d-b9c9-d9835de323bb",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=' Based on the table schema and SQL query, there are 30 unique teams in the NBA.')"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Chain to answer\n",
+    "template = \"\"\"Based on the table schema below, question, sql query, and sql response, write a natural language response:\n",
+    "{schema}\n",
+    "\n",
+    "Question: {question}\n",
+    "SQL Query: {query}\n",
+    "SQL Response: {response}\"\"\"\n",
+    "prompt_response = ChatPromptTemplate.from_messages([\n",
+    "    (\"system\", \"Given an input question and SQL response, convert it to a natural langugae answer. No pre-amble.\"),\n",
+    "    (\"human\", template)\n",
+    "])\n",
+    "\n",
+    "full_chain = (\n",
+    "    RunnablePassthrough.assign(query=sql_response) \n",
+    "    | RunnablePassthrough.assign(\n",
+    "        schema=get_schema,\n",
+    "        response=lambda x: db.run(x[\"query\"]),\n",
+    "    )\n",
+    "    | prompt_response \n",
+    "    | llm\n",
+    ")\n",
+    "\n",
+    "full_chain.invoke({\"question\": \"How many unique teams are there?\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ec17b3ee-6618-4681-b6df-089bbb5ffcd7",
+   "metadata": {},
+   "source": [
+    "We can review the results:\n",
+    "\n",
+    "* [LangSmith trace](https://smith.langchain.com/public/10420721-746a-4806-8ecf-d6dc6399d739/r) LLaMA2-13 Replicate API\n",
+    "* [LangSmith trace](https://smith.langchain.com/public/5265ebab-0a22-4f37-936b-3300f2dfa1c1/r) LLaMA2-13 local "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1e85381b-1edc-4bb3-a7bd-2ab23f81e54d",
+   "metadata": {},
+   "source": [
+    "## Chat with a SQL DB \n",
+    "\n",
+    "Next, we can add memory."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "1985aa1c-eb8f-4fb1-a54f-c8aa10744687",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "' SELECT \"Team\" FROM nba_roster WHERE \"NAME\" = \\'Klay Thompson\\';'"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Prompt\n",
+    "from langchain.memory import ConversationBufferMemory\n",
+    "from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
+    "template = \"\"\"Based on the table schema below, write a SQL query that would answer the user's question:\n",
+    "{schema}\n",
+    "\n",
+    "Question: {question}\n",
+    "SQL Query:\"\"\"\n",
+    "prompt = ChatPromptTemplate.from_messages([\n",
+    "    (\"system\", \"Given an input question, convert it to a SQL query. No pre-amble.\"),\n",
+    "    MessagesPlaceholder(variable_name=\"history\"),\n",
+    "    (\"human\", template)\n",
+    "])\n",
+    "\n",
+    "memory = ConversationBufferMemory(return_messages=True)\n",
+    "\n",
+    "# Chain to query with memory \n",
+    "from langchain.schema.runnable import RunnableLambda\n",
+    "\n",
+    "sql_chain = (\n",
+    "    RunnablePassthrough.assign(\n",
+    "       schema=get_schema,\n",
+    "       history=RunnableLambda(lambda x: memory.load_memory_variables(x)[\"history\"])\n",
+    "    )| prompt\n",
+    "    | llm.bind(stop=[\"\\nSQLResult:\"])\n",
+    "    | StrOutputParser()\n",
+    ")\n",
+    "\n",
+    "def save(input_output):\n",
+    "    output = {\"output\": input_output.pop(\"output\")}\n",
+    "    memory.save_context(input_output, output)\n",
+    "    return output['output']\n",
+    "    \n",
+    "sql_response_memory = RunnablePassthrough.assign(output=sql_chain) | save\n",
+    "sql_response_memory.invoke({\"question\": \"What team is Klay Thompson on?\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "0b45818a-1498-441d-b82d-23c29428c2bb",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "' SELECT \"SALARY\" FROM nba_roster WHERE \"NAME\" = \\'Klay Thompson\\';'"
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sql_response_memory.invoke({\"question\": \"What is his salary?\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "800a7a3b-f411-478b-af51-2310cd6e0425",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=' Sure! Here\\'s the natural language response based on the given input:\\n\\n\"Klay Thompson\\'s salary is $43,219,440.\"')"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Chain to answer\n",
+    "template = \"\"\"Based on the table schema below, question, sql query, and sql response, write a natural language response:\n",
+    "{schema}\n",
+    "\n",
+    "Question: {question}\n",
+    "SQL Query: {query}\n",
+    "SQL Response: {response}\"\"\"\n",
+    "prompt_response = ChatPromptTemplate.from_messages([\n",
+    "    (\"system\", \"Given an input question and SQL response, convert it to a natural langugae answer. No pre-amble.\"),\n",
+    "    (\"human\", template)\n",
+    "])\n",
+    "\n",
+    "full_chain = (\n",
+    "    RunnablePassthrough.assign(query=sql_response_memory) \n",
+    "    | RunnablePassthrough.assign(\n",
+    "        schema=get_schema,\n",
+    "        response=lambda x: db.run(x[\"query\"]),\n",
+    "    )\n",
+    "    | prompt_response \n",
+    "    | llm\n",
+    ")\n",
+    "\n",
+    "full_chain.invoke({\"question\": \"What is his salary?\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b77fee61-f4da-4bb1-8285-14101e505518",
+   "metadata": {},
+   "source": [
+    "Here is the [trace](https://smith.langchain.com/public/54794d18-2337-4ce2-8b9f-3d8a2df89e51/r)."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.16"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

cookbook/README.md

@@ -0,0 +1,52 @@
+# LangChain cookbook
+
+Example code for building applications with LangChain, with an emphasis on more applied and end-to-end examples than contained in the [main documentation](https://python.langchain.com).
+
+Notebook | Description
+:- | :-
+[LLaMA2_sql_chat.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/LLaMA2_sql_chat.ipynb) | Build a chat application that interacts with a SQL database using an open source llm (llama2), specifically demonstrated on an SQLite database containing rosters.
+[Semi_Structured_RAG.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/Semi_Structured_RAG.ipynb) | Perform retrieval-augmented generation (rag) on documents with semi-structured data, including text and tables, using unstructured for parsing, multi-vector retriever for storing, and lcel for implementing chains.
+[Semi_structured_and_multi_moda...](https://github.com/langchain-ai/langchain/tree/master/cookbook/Semi_structured_and_multi_modal_RAG.ipynb) | Perform retrieval-augmented generation (rag) on documents with semi-structured data and images, using unstructured for parsing, multi-vector retriever for storage and retrieval, and lcel for implementing chains.
+[Semi_structured_multi_modal_RA...](https://github.com/langchain-ai/langchain/tree/master/cookbook/Semi_structured_multi_modal_RAG_LLaMA2.ipynb) | Perform retrieval-augmented generation (rag) on documents with semi-structured data and images, using various tools and methods such as unstructured for parsing, multi-vector retriever for storing, lcel for implementing chains, and open source language models like llama2, llava, and gpt4all.
+[autogpt/autogpt.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/autogpt/autogpt.ipynb) | Implement autogpt, a language model, with langchain primitives such as llms, prompttemplates, vectorstores, embeddings, and tools.
+[autogpt/marathon_times.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/autogpt/marathon_times.ipynb) | Implement autogpt for finding winning marathon times.
+[baby_agi.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/baby_agi.ipynb) | Implement babyagi, an ai agent that can generate and execute tasks based on a given objective, with the flexibility to swap out specific vectorstores/model providers.
+[baby_agi_with_agent.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/baby_agi_with_agent.ipynb) | Swap out the execution chain in the babyagi notebook with an agent that has access to tools, aiming to obtain more reliable information.
+[camel_role_playing.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/camel_role_playing.ipynb) | Implement the camel framework for creating autonomous cooperative agents in large-scale language models, using role-playing and inception prompting to guide chat agents towards task completion.
+[causal_program_aided_language_...](https://github.com/langchain-ai/langchain/tree/master/cookbook/causal_program_aided_language_model.ipynb) | Implement the causal program-aided language (cpal) chain, which improves upon the program-aided language (pal) by incorporating causal structure to prevent hallucination in language models, particularly when dealing with complex narratives and math problems with nested dependencies.
+[code-analysis-deeplake.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/code-analysis-deeplake.ipynb) | Analyze its own code base with the help of gpt and activeloop's deep lake.
+[custom_agent_with_plugin_retri...](https://github.com/langchain-ai/langchain/tree/master/cookbook/custom_agent_with_plugin_retrieval.ipynb) | Build a custom agent that can interact with ai plugins by retrieving tools and creating natural language wrappers around openapi endpoints.
+[custom_agent_with_plugin_retri...](https://github.com/langchain-ai/langchain/tree/master/cookbook/custom_agent_with_plugin_retrieval_using_plugnplai.ipynb) | Build a custom agent with plugin retrieval functionality, utilizing ai plugins from the `plugnplai` directory.
+[databricks_sql_db.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/databricks_sql_db.ipynb) | Connect to databricks runtimes and databricks sql.
+[deeplake_semantic_search_over_...](https://github.com/langchain-ai/langchain/tree/master/cookbook/deeplake_semantic_search_over_chat.ipynb) | Perform semantic search and question-answering over a group chat using activeloop's deep lake with gpt4.
+[elasticsearch_db_qa.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/elasticsearch_db_qa.ipynb) | Interact with elasticsearch analytics databases in natural language and build search queries via the elasticsearch dsl API.
+[forward_looking_retrieval_augm...](https://github.com/langchain-ai/langchain/tree/master/cookbook/forward_looking_retrieval_augmented_generation.ipynb) | Implement the forward-looking active retrieval augmented generation (flare) method, which generates answers to questions, identifies uncertain tokens, generates hypothetical questions based on these tokens, and retrieves relevant documents to continue generating the answer.
+[generative_agents_interactive_...](https://github.com/langchain-ai/langchain/tree/master/cookbook/generative_agents_interactive_simulacra_of_human_behavior.ipynb) | Implement a generative agent that simulates human behavior, based on a research paper, using a time-weighted memory object backed by a langchain retriever.
+[gymnasium_agent_simulation.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/gymnasium_agent_simulation.ipynb) | Create a simple agent-environment interaction loop in simulated environments like text-based games with gymnasium.
+[hugginggpt.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/hugginggpt.ipynb) | Implement hugginggpt, a system that connects language models like chatgpt with the machine learning community via hugging face.
+[hypothetical_document_embeddin...](https://github.com/langchain-ai/langchain/tree/master/cookbook/hypothetical_document_embeddings.ipynb) | Improve document indexing with hypothetical document embeddings (hyde), an embedding technique that generates and embeds hypothetical answers to queries.
+[learned_prompt_optimization.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/learned_prompt_optimization.ipynb) | Automatically enhance language model prompts by injecting specific terms using reinforcement learning, which can be used to personalize responses based on user preferences.
+[llm_bash.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/llm_bash.ipynb) | Perform simple filesystem commands using language learning models (llms) and a bash process.
+[llm_checker.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/llm_checker.ipynb) | Create a self-checking chain using the llmcheckerchain function.
+[llm_math.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/llm_math.ipynb) | Solve complex word math problems using language models and python repls.
+[llm_summarization_checker.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/llm_summarization_checker.ipynb) | Check the accuracy of text summaries, with the option to run the checker multiple times for improved results.
+[llm_symbolic_math.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/llm_symbolic_math.ipynb) | Solve algebraic equations with the help of llms (language learning models) and sympy, a python library for symbolic mathematics.
+[meta_prompt.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/meta_prompt.ipynb) | Implement the meta-prompt concept, which is a method for building self-improving agents that reflect on their own performance and modify their instructions accordingly.
+[multi_modal_output_agent.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multi_modal_output_agent.ipynb) | Generate multi-modal outputs, specifically images and text.
+[multi_player_dnd.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multi_player_dnd.ipynb) | Simulate multi-player dungeons & dragons games, with a custom function determining the speaking schedule of the agents.
+[multiagent_authoritarian.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multiagent_authoritarian.ipynb) | Implement a multi-agent simulation where a privileged agent controls the conversation, including deciding who speaks and when the conversation ends, in the context of a simulated news network.
+[multiagent_bidding.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multiagent_bidding.ipynb) | Implement a multi-agent simulation where agents bid to speak, with the highest bidder speaking next, demonstrated through a fictitious presidential debate example.
+[myscale_vector_sql.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/myscale_vector_sql.ipynb) | Access and interact with the myscale integrated vector database, which can enhance the performance of language model (llm) applications.
+[openai_functions_retrieval_qa....](https://github.com/langchain-ai/langchain/tree/master/cookbook/openai_functions_retrieval_qa.ipynb) | Structure response output in a question-answering system by incorporating openai functions into a retrieval pipeline.
+[petting_zoo.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/petting_zoo.ipynb) | Create multi-agent simulations with simulated environments using the petting zoo library.
+[plan_and_execute_agent.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/plan_and_execute_agent.ipynb) | Create plan-and-execute agents that accomplish objectives by planning tasks with a language model (llm) and executing them with a separate agent.
+[press_releases.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/press_releases.ipynb) | Retrieve and query company press release data powered by [Kay.ai](https://kay.ai).
+[program_aided_language_model.i...](https://github.com/langchain-ai/langchain/tree/master/cookbook/program_aided_language_model.ipynb) | Implement program-aided language models as described in the provided research paper.
+[sales_agent_with_context.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/sales_agent_with_context.ipynb) | Implement a context-aware ai sales agent, salesgpt, that can have natural sales conversations, interact with other systems, and use a product knowledge base to discuss a company's offerings.
+[self_query_hotel_search.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/self_query_hotel_search.ipynb) | Build a hotel room search feature with self-querying retrieval, using a specific hotel recommendation dataset.
+[smart_llm.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/smart_llm.ipynb) | Implement a smartllmchain, a self-critique chain that generates multiple output proposals, critiques them to find the best one, and then improves upon it to produce a final output.
+[tree_of_thought.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/tree_of_thought.ipynb) | Query a large language model using the tree of thought technique.
+[twitter-the-algorithm-analysis...](https://github.com/langchain-ai/langchain/tree/master/cookbook/twitter-the-algorithm-analysis-deeplake.ipynb) | Analyze the source code of the Twitter algorithm with the help of gpt4 and activeloop's deep lake.
+[two_agent_debate_tools.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/two_agent_debate_tools.ipynb) | Simulate multi-agent dialogues where the agents can utilize various tools.
+[two_player_dnd.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/two_player_dnd.ipynb) | Simulate a two-player dungeons & dragons game, where a dialogue simulator class is used to coordinate the dialogue between the protagonist and the dungeon master.
+[wikibase_agent.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/wikibase_agent.ipynb) | Create a simple wikibase agent that utilizes sparql generation, with testing done on http://wikidata.org.

cookbook/autogpt/autogpt.ipynb

@@ -0,0 +1,212 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "14f8b67b",
+   "metadata": {},
+   "source": [
+    "# AutoGPT\n",
+    "\n",
+    "Implementation of https://github.com/Significant-Gravitas/Auto-GPT but with LangChain primitives (LLMs, PromptTemplates, VectorStores, Embeddings, Tools)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "192496a7",
+   "metadata": {},
+   "source": [
+    "## Set up tools\n",
+    "\n",
+    "We'll set up an AutoGPT with a search tool, and write-file tool, and a read-file tool"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "7c2c9b54",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.utilities import SerpAPIWrapper\n",
+    "from langchain.agents import Tool\n",
+    "from langchain.tools.file_management.write import WriteFileTool\n",
+    "from langchain.tools.file_management.read import ReadFileTool\n",
+    "\n",
+    "search = SerpAPIWrapper()\n",
+    "tools = [\n",
+    "    Tool(\n",
+    "        name=\"search\",\n",
+    "        func=search.run,\n",
+    "        description=\"useful for when you need to answer questions about current events. You should ask targeted questions\",\n",
+    "    ),\n",
+    "    WriteFileTool(),\n",
+    "    ReadFileTool(),\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8e39ee28",
+   "metadata": {},
+   "source": [
+    "## Set up memory\n",
+    "\n",
+    "The memory here is used for the agents intermediate steps"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "72bc204d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.vectorstores import FAISS\n",
+    "from langchain.docstore import InMemoryDocstore\n",
+    "from langchain.embeddings import OpenAIEmbeddings"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "1df7b724",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Define your embedding model\n",
+    "embeddings_model = OpenAIEmbeddings()\n",
+    "# Initialize the vectorstore as empty\n",
+    "import faiss\n",
+    "\n",
+    "embedding_size = 1536\n",
+    "index = faiss.IndexFlatL2(embedding_size)\n",
+    "vectorstore = FAISS(embeddings_model.embed_query, index, InMemoryDocstore({}), {})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e40fd657",
+   "metadata": {},
+   "source": [
+    "## Setup model and AutoGPT\n",
+    "\n",
+    "Initialize everything! We will use ChatOpenAI model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "3393bc23",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_experimental.autonomous_agents import AutoGPT\n",
+    "from langchain.chat_models import ChatOpenAI"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "709c08c2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "agent = AutoGPT.from_llm_and_tools(\n",
+    "    ai_name=\"Tom\",\n",
+    "    ai_role=\"Assistant\",\n",
+    "    tools=tools,\n",
+    "    llm=ChatOpenAI(temperature=0),\n",
+    "    memory=vectorstore.as_retriever(),\n",
+    ")\n",
+    "# Set verbose to be true\n",
+    "agent.chain.verbose = True"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f0f208d9",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "## Run an example\n",
+    "\n",
+    "Here we will make it write a weather report for SF"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d119d788",
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "agent.run([\"write a weather report for SF today\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f13f8322",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "## Chat History Memory\n",
+    "\n",
+    "In addition to the memory that holds the agent immediate steps, we also have a chat history memory. By default, the agent will use 'ChatMessageHistory' and it can be changed. This is useful when you want to use a different type of memory for example 'FileChatHistoryMemory'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2a81f5ad",
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.memory.chat_message_histories import FileChatMessageHistory\n",
+    "\n",
+    "agent = AutoGPT.from_llm_and_tools(\n",
+    "    ai_name=\"Tom\",\n",
+    "    ai_role=\"Assistant\",\n",
+    "    tools=tools,\n",
+    "    llm=ChatOpenAI(temperature=0),\n",
+    "    memory=vectorstore.as_retriever(),\n",
+    "    chat_history_memory=FileChatMessageHistory(\"chat_history.txt\"),\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b1403008",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

cookbook/autogpt/marathon_times.ipynb

@@ -0,0 +1,649 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "14f8b67b",
+   "metadata": {},
+   "source": [
+    "## AutoGPT example finding Winning Marathon Times\n",
+    "\n",
+    "* Implementation of https://github.com/Significant-Gravitas/Auto-GPT \n",
+    "* With LangChain primitives (LLMs, PromptTemplates, VectorStores, Embeddings, Tools)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "ef972313-c05a-4c49-8fd1-03e599e21033",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# !pip install bs4\n",
+    "# !pip install nest_asyncio"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "1cff42fd",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# General\n",
+    "import os\n",
+    "import pandas as pd\n",
+    "from langchain_experimental.autonomous_agents import AutoGPT\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "\n",
+    "from langchain.agents.agent_toolkits.pandas.base import create_pandas_dataframe_agent\n",
+    "from langchain.docstore.document import Document\n",
+    "import asyncio\n",
+    "import nest_asyncio\n",
+    "\n",
+    "\n",
+    "# Needed synce jupyter runs an async eventloop\n",
+    "nest_asyncio.apply()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "01283ac7-1da0-41ba-8011-bd455d21dd82",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "llm = ChatOpenAI(model_name=\"gpt-4\", temperature=1.0)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "192496a7",
+   "metadata": {},
+   "source": [
+    "### Set up tools\n",
+    "\n",
+    "* We'll set up an AutoGPT with a `search` tool, and `write-file` tool, and a `read-file` tool, a web browsing tool, and a tool to interact with a CSV file via a python REPL"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "708a426f",
+   "metadata": {},
+   "source": [
+    "Define any other `tools` you want to use below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "cef4c150-0ef1-4a33-836b-01062fec134e",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# Tools\n",
+    "import os\n",
+    "from contextlib import contextmanager\n",
+    "from typing import Optional\n",
+    "from langchain.agents import tool\n",
+    "from langchain.tools.file_management.read import ReadFileTool\n",
+    "from langchain.tools.file_management.write import WriteFileTool\n",
+    "\n",
+    "ROOT_DIR = \"./data/\"\n",
+    "\n",
+    "\n",
+    "@contextmanager\n",
+    "def pushd(new_dir):\n",
+    "    \"\"\"Context manager for changing the current working directory.\"\"\"\n",
+    "    prev_dir = os.getcwd()\n",
+    "    os.chdir(new_dir)\n",
+    "    try:\n",
+    "        yield\n",
+    "    finally:\n",
+    "        os.chdir(prev_dir)\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def process_csv(\n",
+    "    csv_file_path: str, instructions: str, output_path: Optional[str] = None\n",
+    ") -> str:\n",
+    "    \"\"\"Process a CSV by with pandas in a limited REPL.\\\n",
+    " Only use this after writing data to disk as a csv file.\\\n",
+    " Any figures must be saved to disk to be viewed by the human.\\\n",
+    " Instructions should be written in natural language, not code. Assume the dataframe is already loaded.\"\"\"\n",
+    "    with pushd(ROOT_DIR):\n",
+    "        try:\n",
+    "            df = pd.read_csv(csv_file_path)\n",
+    "        except Exception as e:\n",
+    "            return f\"Error: {e}\"\n",
+    "        agent = create_pandas_dataframe_agent(llm, df, max_iterations=30, verbose=True)\n",
+    "        if output_path is not None:\n",
+    "            instructions += f\" Save output to disk at {output_path}\"\n",
+    "        try:\n",
+    "            result = agent.run(instructions)\n",
+    "            return result\n",
+    "        except Exception as e:\n",
+    "            return f\"Error: {e}\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "69975008-654a-4cbb-bdf6-63c8bae07eaa",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "**Browse a web page with PlayWright**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "6bb5e47b-0f54-4faa-ae42-49a28fa5497b",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# !pip install playwright\n",
+    "# !playwright install"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "26b497d7-8e52-4c7f-8e7e-da0a48820a3c",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "async def async_load_playwright(url: str) -> str:\n",
+    "    \"\"\"Load the specified URLs using Playwright and parse using BeautifulSoup.\"\"\"\n",
+    "    from bs4 import BeautifulSoup\n",
+    "    from playwright.async_api import async_playwright\n",
+    "\n",
+    "    results = \"\"\n",
+    "    async with async_playwright() as p:\n",
+    "        browser = await p.chromium.launch(headless=True)\n",
+    "        try:\n",
+    "            page = await browser.new_page()\n",
+    "            await page.goto(url)\n",
+    "\n",
+    "            page_source = await page.content()\n",
+    "            soup = BeautifulSoup(page_source, \"html.parser\")\n",
+    "\n",
+    "            for script in soup([\"script\", \"style\"]):\n",
+    "                script.extract()\n",
+    "\n",
+    "            text = soup.get_text()\n",
+    "            lines = (line.strip() for line in text.splitlines())\n",
+    "            chunks = (phrase.strip() for line in lines for phrase in line.split(\"  \"))\n",
+    "            results = \"\\n\".join(chunk for chunk in chunks if chunk)\n",
+    "        except Exception as e:\n",
+    "            results = f\"Error: {e}\"\n",
+    "        await browser.close()\n",
+    "    return results\n",
+    "\n",
+    "\n",
+    "def run_async(coro):\n",
+    "    event_loop = asyncio.get_event_loop()\n",
+    "    return event_loop.run_until_complete(coro)\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def browse_web_page(url: str) -> str:\n",
+    "    \"\"\"Verbose way to scrape a whole webpage. Likely to cause issues parsing.\"\"\"\n",
+    "    return run_async(async_load_playwright(url))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5ea71762-67ca-4e75-8c4d-00563064be71",
+   "metadata": {},
+   "source": [
+    "**Q&A Over a webpage**\n",
+    "\n",
+    "Help the model ask more directed questions of web pages to avoid cluttering its memory"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "1842929d-f18d-4edc-9fdd-82c929181141",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.tools import BaseTool, DuckDuckGoSearchRun\n",
+    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
+    "\n",
+    "from pydantic import Field\n",
+    "from langchain.chains.qa_with_sources.loading import (\n",
+    "    load_qa_with_sources_chain,\n",
+    "    BaseCombineDocumentsChain,\n",
+    ")\n",
+    "\n",
+    "\n",
+    "def _get_text_splitter():\n",
+    "    return RecursiveCharacterTextSplitter(\n",
+    "        # Set a really small chunk size, just to show.\n",
+    "        chunk_size=500,\n",
+    "        chunk_overlap=20,\n",
+    "        length_function=len,\n",
+    "    )\n",
+    "\n",
+    "\n",
+    "class WebpageQATool(BaseTool):\n",
+    "    name = \"query_webpage\"\n",
+    "    description = (\n",
+    "        \"Browse a webpage and retrieve the information relevant to the question.\"\n",
+    "    )\n",
+    "    text_splitter: RecursiveCharacterTextSplitter = Field(\n",
+    "        default_factory=_get_text_splitter\n",
+    "    )\n",
+    "    qa_chain: BaseCombineDocumentsChain\n",
+    "\n",
+    "    def _run(self, url: str, question: str) -> str:\n",
+    "        \"\"\"Useful for browsing websites and scraping the text information.\"\"\"\n",
+    "        result = browse_web_page.run(url)\n",
+    "        docs = [Document(page_content=result, metadata={\"source\": url})]\n",
+    "        web_docs = self.text_splitter.split_documents(docs)\n",
+    "        results = []\n",
+    "        # TODO: Handle this with a MapReduceChain\n",
+    "        for i in range(0, len(web_docs), 4):\n",
+    "            input_docs = web_docs[i : i + 4]\n",
+    "            window_result = self.qa_chain(\n",
+    "                {\"input_documents\": input_docs, \"question\": question},\n",
+    "                return_only_outputs=True,\n",
+    "            )\n",
+    "            results.append(f\"Response from window {i} - {window_result}\")\n",
+    "        results_docs = [\n",
+    "            Document(page_content=\"\\n\".join(results), metadata={\"source\": url})\n",
+    "        ]\n",
+    "        return self.qa_chain(\n",
+    "            {\"input_documents\": results_docs, \"question\": question},\n",
+    "            return_only_outputs=True,\n",
+    "        )\n",
+    "\n",
+    "    async def _arun(self, url: str, question: str) -> str:\n",
+    "        raise NotImplementedError"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "e6f72bd0",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "query_website_tool = WebpageQATool(qa_chain=load_qa_with_sources_chain(llm))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8e39ee28",
+   "metadata": {},
+   "source": [
+    "### Set up memory\n",
+    "\n",
+    "* The memory here is used for the agents intermediate steps"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "1df7b724",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# Memory\n",
+    "import faiss\n",
+    "from langchain.vectorstores import FAISS\n",
+    "from langchain.docstore import InMemoryDocstore\n",
+    "from langchain.embeddings import OpenAIEmbeddings\n",
+    "from langchain.tools.human.tool import HumanInputRun\n",
+    "\n",
+    "embeddings_model = OpenAIEmbeddings()\n",
+    "embedding_size = 1536\n",
+    "index = faiss.IndexFlatL2(embedding_size)\n",
+    "vectorstore = FAISS(embeddings_model.embed_query, index, InMemoryDocstore({}), {})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e40fd657",
+   "metadata": {},
+   "source": [
+    "### Setup model and AutoGPT\n",
+    "\n",
+    "`Model set-up`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "1233caf3-fbc9-4acb-9faa-01008200633d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# !pip install duckduckgo_search\n",
+    "web_search = DuckDuckGoSearchRun()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "88c8b184-67d7-4c35-84ae-9b14bef8c4e3",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "tools = [\n",
+    "    web_search,\n",
+    "    WriteFileTool(root_dir=\"./data\"),\n",
+    "    ReadFileTool(root_dir=\"./data\"),\n",
+    "    process_csv,\n",
+    "    query_website_tool,\n",
+    "    # HumanInputRun(), # Activate if you want the permit asking for help from the human\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "709c08c2",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "agent = AutoGPT.from_llm_and_tools(\n",
+    "    ai_name=\"Tom\",\n",
+    "    ai_role=\"Assistant\",\n",
+    "    tools=tools,\n",
+    "    llm=llm,\n",
+    "    memory=vectorstore.as_retriever(search_kwargs={\"k\": 8}),\n",
+    "    # human_in_the_loop=True, # Set to True if you want to add feedback at each step.\n",
+    ")\n",
+    "# agent.chain.verbose = True"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fc9b51ba",
+   "metadata": {},
+   "source": [
+    "### AutoGPT for Querying the Web\n",
+    " \n",
+    "  \n",
+    "I've spent a lot of time over the years crawling data sources and cleaning data. Let's see if AutoGPT can help with this!\n",
+    "\n",
+    "Here is the prompt for looking up recent boston marathon times and converting them to tabular form."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "64455d70-a134-4d11-826a-33e34c2ce287",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{\n",
+      "    \"thoughts\": {\n",
+      "        \"text\": \"I need to find the winning Boston Marathon times for the past 5 years. I can use the DuckDuckGo Search command to search for this information.\",\n",
+      "        \"reasoning\": \"Using DuckDuckGo Search will help me gather information on the winning times without complications.\",\n",
+      "        \"plan\": \"- Use DuckDuckGo Search to find the winning Boston Marathon times\\n- Generate a table with the year, name, country of origin, and times\\n- Ensure there are no legal complications\",\n",
+      "        \"criticism\": \"None\",\n",
+      "        \"speak\": \"I will use the DuckDuckGo Search command to find the winning Boston Marathon times for the past 5 years.\"\n",
+      "    },\n",
+      "    \"command\": {\n",
+      "        \"name\": \"DuckDuckGo Search\",\n",
+      "        \"args\": {\n",
+      "            \"query\": \"winning Boston Marathon times for the past 5 years ending in 2022\"\n",
+      "        }\n",
+      "    }\n",
+      "}\n",
+      "{\n",
+      "    \"thoughts\": {\n",
+      "        \"text\": \"The DuckDuckGo Search command did not provide the specific information I need. I must switch my approach and use query_webpage command to browse a webpage containing the Boston Marathon winning times for the past 5 years.\",\n",
+      "        \"reasoning\": \"The query_webpage command may give me more accurate and comprehensive results compared to the search command.\",\n",
+      "        \"plan\": \"- Use query_webpage command to find the winning Boston Marathon times\\n- Generate a table with the year, name, country of origin, and times\\n- Ensure there are no legal complications\",\n",
+      "        \"criticism\": \"I may face difficulty in finding the right webpage with the desired information.\",\n",
+      "        \"speak\": \"I will use the query_webpage command to find the winning Boston Marathon times for the past 5 years.\"\n",
+      "    },\n",
+      "    \"command\": {\n",
+      "        \"name\": \"DuckDuckGo Search\",\n",
+      "        \"args\": {\n",
+      "            \"query\": \"site with winning Boston Marathon times for the past 5 years ending in 2022\"\n",
+      "        }\n",
+      "    }\n",
+      "}\n",
+      "{\n",
+      "    \"thoughts\": {\n",
+      "        \"text\": \"I need to use the query_webpage command to find the information about the winning Boston Marathon times for the past 5 years.\",\n",
+      "        \"reasoning\": \"The previous DuckDuckGo Search command did not provide specific enough results. The query_webpage command might give more accurate and comprehensive results.\",\n",
+      "        \"plan\": \"- Use query_webpage command to find the winning Boston Marathon times\\\\n- Generate a table with the year, name, country of origin, and times\\\\n- Ensure there are no legal complications\",\n",
+      "        \"criticism\": \"I may face difficulty in finding the right webpage with the desired information.\",\n",
+      "        \"speak\": \"I will use the query_webpage command to find the winning Boston Marathon times for the past 5 years.\"\n",
+      "    },\n",
+      "    \"command\": {\n",
+      "        \"name\": \"query_webpage\",\n",
+      "        \"args\": {\n",
+      "            \"url\": \"https://en.wikipedia.org/wiki/List_of_winners_of_the_Boston_Marathon\",\n",
+      "            \"question\": \"What were the winning Boston Marathon times for the past 5 years ending in 2022?\"\n",
+      "        }\n",
+      "    }\n",
+      "}\n",
+      "{\n",
+      "    \"thoughts\": {\n",
+      "        \"text\": \"I have already found the winning Boston Marathon times for the past 5 years. Now, I need to generate a table with the information.\",\n",
+      "        \"reasoning\": \"Using the information I already have, I can create a table containing year, name, country of origin, and times.\",\n",
+      "        \"plan\": \"- Write the marathon data to a CSV file\\n- Process the CSV file to display the table\",\n",
+      "        \"criticism\": \"None\",\n",
+      "        \"speak\": \"I will generate a table with the year, name, country of origin, and times for the winning Boston Marathon times for the past 5 years.\"\n",
+      "    },\n",
+      "    \"command\": {\n",
+      "        \"name\": \"write_file\",\n",
+      "        \"args\": {\n",
+      "            \"file_path\": \"boston_marathon_winners.csv\",\n",
+      "            \"text\": \"Year,Name,Country,Time\\n2022,Evans Chebet,KEN,2:06:51\\n2021,Benson Kipruto,KEN,2:09:51\\n2019,Lawrence Cherono,KEN,2:07:57\\n2018,Yuki Kawauchi,JPN,2:15:58\"\n",
+      "        }\n",
+      "    }\n",
+      "}\n",
+      "{\n",
+      "    \"thoughts\": {\n",
+      "        \"text\": \"I have retrieved the winning Boston Marathon times for the past 5 years. Now, I need to generate a table with the year, name, country of origin, and times.\",\n",
+      "        \"reasoning\": \"Creating a table will help organize the data in a clear and accessible format.\",\n",
+      "        \"plan\": \"- Write the data to a CSV file\\n- Process the CSV file to generate the table\\n- Complete the task\",\n",
+      "        \"criticism\": \"None\",\n",
+      "        \"speak\": \"I will generate a table with the year, name, country of origin, and winning times using the recently retrieved data.\"\n",
+      "    },\n",
+      "    \"command\": {\n",
+      "        \"name\": \"write_file\",\n",
+      "        \"args\": {\n",
+      "            \"file_path\": \"winning_boston_marathon_data.csv\",\n",
+      "            \"text\": \"Year,Name,Country,Time\\n2022,Evans Chebet,KEN,2:06:51\\n2021,Benson Kipruto,KEN,2:09:51\\n2019,Lawrence Cherono,KEN,2:07:57\\n2018,Yuki Kawauchi,JPN,2:15:58\\n\"\n",
+      "        }\n",
+      "    }\n",
+      "}\n",
+      "{\n",
+      "    \"thoughts\": {\n",
+      "        \"text\": \"I have found the winning Boston Marathon times for the past five years ending in 2022. Next, I need to create a table with the year, name, country of origin, and times.\",\n",
+      "        \"reasoning\": \"Generating a table will help organize the information in a structured format.\",\n",
+      "        \"plan\": \"- Create a table with the year, name, country of origin, and times\\n- Ensure there are no legal complications\",\n",
+      "        \"criticism\": \"None\",\n",
+      "        \"speak\": \"I will generate a table with the winning Boston Marathon times for the past 5 years ending in 2022.\"\n",
+      "    },\n",
+      "    \"command\": {\n",
+      "        \"name\": \"write_file\",\n",
+      "        \"args\": {\n",
+      "            \"file_path\": \"winning_times.csv\",\n",
+      "            \"text\": \"Year,Name,Country,Time\\n2022,Evans Chebet,Kenya,2:06:51\\n2021,Benson Kipruto,Kenya,2:09:51\\n2020,Canceled due to COVID-19 pandemic,,\\n2019,Lawrence Cherono,Kenya,2:07:57\\n2018,Yuki Kawauchi,Japan,2:15:58\"\n",
+      "        }\n",
+      "    }\n",
+      "}\n",
+      "{\n",
+      "    \"thoughts\": {\n",
+      "        \"text\": \"I need to process the CSV file to generate the table with the year, name, country of origin, and winning times.\",\n",
+      "        \"reasoning\": \"I have already written the data to a file named 'winning_times.csv'. Now, I need to process this CSV file to properly display the data as a table.\",\n",
+      "        \"plan\": \"- Use the process_csv command to read the 'winning_times.csv' file and generate the table\",\n",
+      "        \"criticism\": \"None\",\n",
+      "        \"speak\": \"I will process the 'winning_times.csv' file to display the table with the winning Boston Marathon times for the past 5 years.\"\n",
+      "    },\n",
+      "    \"command\": {\n",
+      "        \"name\": \"process_csv\",\n",
+      "        \"args\": {\n",
+      "            \"csv_file_path\": \"winning_times.csv\",\n",
+      "            \"instructions\": \"Read the CSV file and display the data as a table\"\n",
+      "        }\n",
+      "    }\n",
+      "}\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: The CSV file has already been read and saved into a pandas dataframe called `df`. Hence, I can simply display the data by printing the whole dataframe. Since `df.head()` returns the first 5 rows, I can use that to showcase the contents.\n",
+      "\n",
+      "Action: python_repl_ast\n",
+      "Action Input: print(df.head())\u001b[0m   Year                               Name Country     Time\n",
+      "0  2022                       Evans Chebet   Kenya  2:06:51\n",
+      "1  2021                     Benson Kipruto   Kenya  2:09:51\n",
+      "2  2020  Canceled due to COVID-19 pandemic     NaN      NaN\n",
+      "3  2019                   Lawrence Cherono   Kenya  2:07:57\n",
+      "4  2018                      Yuki Kawauchi   Japan  2:15:58\n",
+      "\n",
+      "Observation: \u001b[36;1m\u001b[1;3mNone\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3mI used the wrong tool to perform the action. I should have used the given data and not interacted with the Python shell. I can now provide the displayed data as the answer since the information in the printed dataframe would look like a table when typed as text.\n",
+      "\n",
+      "Final Answer: \n",
+      "   Year                               Name Country     Time\n",
+      "0  2022                       Evans Chebet   Kenya  2:06:51\n",
+      "1  2021                     Benson Kipruto   Kenya  2:09:51\n",
+      "2  2020  Canceled due to COVID-19 pandemic     NaN      NaN\n",
+      "3  2019                   Lawrence Cherono   Kenya  2:07:57\n",
+      "4  2018                      Yuki Kawauchi   Japan  2:15:58\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "{\n",
+      "    \"thoughts\": {\n",
+      "        \"text\": \"I already have the winning Boston Marathon times for the past 5 years saved in the file 'winning_times.csv'. Now, I need to process the CSV and display the table.\",\n",
+      "        \"reasoning\": \"I am choosing the process_csv command because I already have the required data saved as a CSV file, and I can use this command to read and display the data as a table.\",\n",
+      "        \"plan\": \"- Use the process_csv command to read the 'winning_times.csv' file and generate the table\",\n",
+      "        \"criticism\": \"None\",\n",
+      "        \"speak\": \"I will process the 'winning_times.csv' file to display the table with the winning Boston Marathon times for the past 5 years.\"\n",
+      "    },\n",
+      "    \"command\": {\n",
+      "        \"name\": \"process_csv\",\n",
+      "        \"args\": {\n",
+      "            \"csv_file_path\": \"winning_times.csv\",\n",
+      "            \"instructions\": \"Read the CSV file and display the data as a table\"\n",
+      "        }\n",
+      "    }\n",
+      "}\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: Since the data is already loaded in a pandas dataframe, I just need to display the top rows of the dataframe.\n",
+      "Action: python_repl_ast\n",
+      "Action Input: df.head()\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3m   Year                               Name Country     Time\n",
+      "0  2022                       Evans Chebet   Kenya  2:06:51\n",
+      "1  2021                     Benson Kipruto   Kenya  2:09:51\n",
+      "2  2020  Canceled due to COVID-19 pandemic     NaN      NaN\n",
+      "3  2019                   Lawrence Cherono   Kenya  2:07:57\n",
+      "4  2018                      Yuki Kawauchi   Japan  2:15:58\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3mI now know the final answer.\n",
+      "Final Answer: \n",
+      "   Year                               Name Country     Time\n",
+      "0  2022                       Evans Chebet   Kenya  2:06:51\n",
+      "1  2021                     Benson Kipruto   Kenya  2:09:51\n",
+      "2  2020  Canceled due to COVID-19 pandemic     NaN      NaN\n",
+      "3  2019                   Lawrence Cherono   Kenya  2:07:57\n",
+      "4  2018                      Yuki Kawauchi   Japan  2:15:58\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "{\n",
+      "    \"thoughts\": {\n",
+      "        \"text\": \"I have already generated a table with the winning Boston Marathon times for the past 5 years. Now, I can finish the task.\",\n",
+      "        \"reasoning\": \"I have completed the required actions and obtained the desired data. The task is complete.\",\n",
+      "        \"plan\": \"- Use the finish command\",\n",
+      "        \"criticism\": \"None\",\n",
+      "        \"speak\": \"I have generated the table with the winning Boston Marathon times for the past 5 years. Task complete.\"\n",
+      "    },\n",
+      "    \"command\": {\n",
+      "        \"name\": \"finish\",\n",
+      "        \"args\": {\n",
+      "            \"response\": \"I have generated the table with the winning Boston Marathon times for the past 5 years. Task complete.\"\n",
+      "        }\n",
+      "    }\n",
+      "}\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'I have generated the table with the winning Boston Marathon times for the past 5 years. Task complete.'"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent.run(\n",
+    "    [\n",
+    "        \"What were the winning boston marathon times for the past 5 years (ending in 2022)? Generate a table of the year, name, country of origin, and times.\"\n",
+    "    ]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a6b4f96e",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.16"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

cookbook/baby_agi.ipynb

@@ -0,0 +1,257 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "517a9fd4",
+   "metadata": {},
+   "source": [
+    "# BabyAGI User Guide\n",
+    "\n",
+    "This notebook demonstrates how to implement [BabyAGI](https://github.com/yoheinakajima/babyagi/tree/main) by [Yohei Nakajima](https://twitter.com/yoheinakajima). BabyAGI is an AI agent that can generate and pretend to execute tasks based on a given objective.\n",
+    "\n",
+    "This guide will help you understand the components to create your own recursive agents.\n",
+    "\n",
+    "Although BabyAGI uses specific vectorstores/model providers (Pinecone, OpenAI), one of the benefits of implementing it with LangChain is that you can easily swap those out for different options. In this implementation we use a FAISS vectorstore (because it runs locally and is free)."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "556af556",
+   "metadata": {},
+   "source": [
+    "## Install and Import Required Modules"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "c8a354b6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from collections import deque\n",
+    "from typing import Dict, List, Optional, Any\n",
+    "\n",
+    "from langchain.chains import LLMChain\nfrom langchain.llms import OpenAI\nfrom langchain.prompts import PromptTemplate\n",
+    "from langchain.embeddings import OpenAIEmbeddings\n",
+    "from langchain.llms import BaseLLM\n",
+    "from langchain.schema.vectorstore import VectorStore\n",
+    "from pydantic import BaseModel, Field\n",
+    "from langchain.chains.base import Chain\n",
+    "from langchain_experimental.autonomous_agents import BabyAGI"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "09f70772",
+   "metadata": {},
+   "source": [
+    "## Connect to the Vector Store\n",
+    "\n",
+    "Depending on what vectorstore you use, this step may look different."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "794045d4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.vectorstores import FAISS\n",
+    "from langchain.docstore import InMemoryDocstore"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "6e0305eb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Define your embedding model\n",
+    "embeddings_model = OpenAIEmbeddings()\n",
+    "# Initialize the vectorstore as empty\n",
+    "import faiss\n",
+    "\n",
+    "embedding_size = 1536\n",
+    "index = faiss.IndexFlatL2(embedding_size)\n",
+    "vectorstore = FAISS(embeddings_model.embed_query, index, InMemoryDocstore({}), {})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "05ba762e",
+   "metadata": {},
+   "source": [
+    "### Run the BabyAGI\n",
+    "\n",
+    "Now it's time to create the BabyAGI controller and watch it try to accomplish your objective."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "3d220b69",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "OBJECTIVE = \"Write a weather report for SF today\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "8a8e5543",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = OpenAI(temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "3d69899b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Logging of LLMChains\n",
+    "verbose = False\n",
+    "# If None, will keep on going forever\n",
+    "max_iterations: Optional[int] = 3\n",
+    "baby_agi = BabyAGI.from_llm(\n",
+    "    llm=llm, vectorstore=vectorstore, verbose=verbose, max_iterations=max_iterations\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "f7957b51",
+   "metadata": {
+    "scrolled": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[95m\u001b[1m\n",
+      "*****TASK LIST*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "1: Make a todo list\n",
+      "\u001b[92m\u001b[1m\n",
+      "*****NEXT TASK*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "1: Make a todo list\n",
+      "\u001b[93m\u001b[1m\n",
+      "*****TASK RESULT*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "\n",
+      "\n",
+      "1. Check the weather forecast for San Francisco today\n",
+      "2. Make note of the temperature, humidity, wind speed, and other relevant weather conditions\n",
+      "3. Write a weather report summarizing the forecast\n",
+      "4. Check for any weather alerts or warnings\n",
+      "5. Share the report with the relevant stakeholders\n",
+      "\u001b[95m\u001b[1m\n",
+      "*****TASK LIST*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "2: Check the current temperature in San Francisco\n",
+      "3: Check the current humidity in San Francisco\n",
+      "4: Check the current wind speed in San Francisco\n",
+      "5: Check for any weather alerts or warnings in San Francisco\n",
+      "6: Check the forecast for the next 24 hours in San Francisco\n",
+      "7: Check the forecast for the next 48 hours in San Francisco\n",
+      "8: Check the forecast for the next 72 hours in San Francisco\n",
+      "9: Check the forecast for the next week in San Francisco\n",
+      "10: Check the forecast for the next month in San Francisco\n",
+      "11: Check the forecast for the next 3 months in San Francisco\n",
+      "1: Write a weather report for SF today\n",
+      "\u001b[92m\u001b[1m\n",
+      "*****NEXT TASK*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "2: Check the current temperature in San Francisco\n",
+      "\u001b[93m\u001b[1m\n",
+      "*****TASK RESULT*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "\n",
+      "\n",
+      "I will check the current temperature in San Francisco. I will use an online weather service to get the most up-to-date information.\n",
+      "\u001b[95m\u001b[1m\n",
+      "*****TASK LIST*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "3: Check the current UV index in San Francisco.\n",
+      "4: Check the current air quality in San Francisco.\n",
+      "5: Check the current precipitation levels in San Francisco.\n",
+      "6: Check the current cloud cover in San Francisco.\n",
+      "7: Check the current barometric pressure in San Francisco.\n",
+      "8: Check the current dew point in San Francisco.\n",
+      "9: Check the current wind direction in San Francisco.\n",
+      "10: Check the current humidity levels in San Francisco.\n",
+      "1: Check the current temperature in San Francisco to the average temperature for this time of year.\n",
+      "2: Check the current visibility in San Francisco.\n",
+      "11: Write a weather report for SF today.\n",
+      "\u001b[92m\u001b[1m\n",
+      "*****NEXT TASK*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "3: Check the current UV index in San Francisco.\n",
+      "\u001b[93m\u001b[1m\n",
+      "*****TASK RESULT*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "\n",
+      "\n",
+      "The current UV index in San Francisco is moderate. The UV index is expected to remain at moderate levels throughout the day. It is recommended to wear sunscreen and protective clothing when outdoors.\n",
+      "\u001b[91m\u001b[1m\n",
+      "*****TASK ENDING*****\n",
+      "\u001b[0m\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "{'objective': 'Write a weather report for SF today'}"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "baby_agi({\"objective\": OBJECTIVE})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "898a210b",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.16"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

cookbook/baby_agi_with_agent.ipynb

@@ -0,0 +1,391 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "517a9fd4",
+   "metadata": {},
+   "source": [
+    "# BabyAGI with Tools\n",
+    "\n",
+    "This notebook builds on top of [baby agi](baby_agi.html), but shows how you can swap out the execution chain. The previous execution chain was just an LLM which made stuff up. By swapping it out with an agent that has access to tools, we can hopefully get real reliable information"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "556af556",
+   "metadata": {},
+   "source": [
+    "## Install and Import Required Modules"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "c8a354b6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from collections import deque\n",
+    "from typing import Dict, List, Optional, Any\n",
+    "\n",
+    "from langchain.chains import LLMChain\nfrom langchain.llms import OpenAI\nfrom langchain.prompts import PromptTemplate\n",
+    "from langchain.embeddings import OpenAIEmbeddings\n",
+    "from langchain.llms import BaseLLM\n",
+    "from langchain.schema.vectorstore import VectorStore\n",
+    "from pydantic import BaseModel, Field\n",
+    "from langchain.chains.base import Chain\n",
+    "from langchain_experimental.autonomous_agents import BabyAGI"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "09f70772",
+   "metadata": {},
+   "source": [
+    "## Connect to the Vector Store\n",
+    "\n",
+    "Depending on what vectorstore you use, this step may look different."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "794045d4",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Note: you may need to restart the kernel to use updated packages.\n",
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
+   "source": [
+    "%pip install faiss-cpu > /dev/null\n",
+    "%pip install google-search-results > /dev/null\n",
+    "from langchain.vectorstores import FAISS\n",
+    "from langchain.docstore import InMemoryDocstore"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "6e0305eb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Define your embedding model\n",
+    "embeddings_model = OpenAIEmbeddings()\n",
+    "# Initialize the vectorstore as empty\n",
+    "import faiss\n",
+    "\n",
+    "embedding_size = 1536\n",
+    "index = faiss.IndexFlatL2(embedding_size)\n",
+    "vectorstore = FAISS(embeddings_model.embed_query, index, InMemoryDocstore({}), {})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0f3b72bf",
+   "metadata": {},
+   "source": [
+    "## Define the Chains\n",
+    "\n",
+    "BabyAGI relies on three LLM chains:\n",
+    "- Task creation chain to select new tasks to add to the list\n",
+    "- Task prioritization chain to re-prioritize tasks\n",
+    "- Execution Chain to execute the tasks\n",
+    "\n",
+    "\n",
+    "NOTE: in this notebook, the Execution chain will now be an agent."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "b43cd580",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.agents import ZeroShotAgent, Tool, AgentExecutor\n",
+    "from langchain.llms import OpenAI\nfrom langchain.utilities import SerpAPIWrapper\nfrom langchain.chains import LLMChain\n",
+    "\n",
+    "todo_prompt = PromptTemplate.from_template(\n",
+    "    \"You are a planner who is an expert at coming up with a todo list for a given objective. Come up with a todo list for this objective: {objective}\"\n",
+    ")\n",
+    "todo_chain = LLMChain(llm=OpenAI(temperature=0), prompt=todo_prompt)\n",
+    "search = SerpAPIWrapper()\n",
+    "tools = [\n",
+    "    Tool(\n",
+    "        name=\"Search\",\n",
+    "        func=search.run,\n",
+    "        description=\"useful for when you need to answer questions about current events\",\n",
+    "    ),\n",
+    "    Tool(\n",
+    "        name=\"TODO\",\n",
+    "        func=todo_chain.run,\n",
+    "        description=\"useful for when you need to come up with todo lists. Input: an objective to create a todo list for. Output: a todo list for that objective. Please be very clear what the objective is!\",\n",
+    "    ),\n",
+    "]\n",
+    "\n",
+    "\n",
+    "prefix = \"\"\"You are an AI who performs one task based on the following objective: {objective}. Take into account these previously completed tasks: {context}.\"\"\"\n",
+    "suffix = \"\"\"Question: {task}\n",
+    "{agent_scratchpad}\"\"\"\n",
+    "prompt = ZeroShotAgent.create_prompt(\n",
+    "    tools,\n",
+    "    prefix=prefix,\n",
+    "    suffix=suffix,\n",
+    "    input_variables=[\"objective\", \"task\", \"context\", \"agent_scratchpad\"],\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "4b00ae2e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = OpenAI(temperature=0)\n",
+    "llm_chain = LLMChain(llm=llm, prompt=prompt)\n",
+    "tool_names = [tool.name for tool in tools]\n",
+    "agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names)\n",
+    "agent_executor = AgentExecutor.from_agent_and_tools(\n",
+    "    agent=agent, tools=tools, verbose=True\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "05ba762e",
+   "metadata": {},
+   "source": [
+    "### Run the BabyAGI\n",
+    "\n",
+    "Now it's time to create the BabyAGI controller and watch it try to accomplish your objective."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "3d220b69",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "OBJECTIVE = \"Write a weather report for SF today\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "3d69899b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Logging of LLMChains\n",
+    "verbose = False\n",
+    "# If None, will keep on going forever\n",
+    "max_iterations: Optional[int] = 3\n",
+    "baby_agi = BabyAGI.from_llm(\n",
+    "    llm=llm,\n",
+    "    vectorstore=vectorstore,\n",
+    "    task_execution_chain=agent_executor,\n",
+    "    verbose=verbose,\n",
+    "    max_iterations=max_iterations,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "f7957b51",
+   "metadata": {
+    "scrolled": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[95m\u001b[1m\n",
+      "*****TASK LIST*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "1: Make a todo list\n",
+      "\u001b[92m\u001b[1m\n",
+      "*****NEXT TASK*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "1: Make a todo list\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: I need to come up with a todo list\n",
+      "Action: TODO\n",
+      "Action Input: Write a weather report for SF today\u001b[0m\u001b[33;1m\u001b[1;3m\n",
+      "\n",
+      "1. Research current weather conditions in San Francisco\n",
+      "2. Gather data on temperature, humidity, wind speed, and other relevant weather conditions\n",
+      "3. Analyze data to determine current weather trends\n",
+      "4. Write a brief introduction to the weather report\n",
+      "5. Describe current weather conditions in San Francisco\n",
+      "6. Discuss any upcoming weather changes\n",
+      "7. Summarize the weather report\n",
+      "8. Proofread and edit the report\n",
+      "9. Submit the report\u001b[0m\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: The todo list for writing a weather report for SF today is: 1. Research current weather conditions in San Francisco; 2. Gather data on temperature, humidity, wind speed, and other relevant weather conditions; 3. Analyze data to determine current weather trends; 4. Write a brief introduction to the weather report; 5. Describe current weather conditions in San Francisco; 6. Discuss any upcoming weather changes; 7. Summarize the weather report; 8. Proofread and edit the report; 9. Submit the report.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\u001b[93m\u001b[1m\n",
+      "*****TASK RESULT*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "The todo list for writing a weather report for SF today is: 1. Research current weather conditions in San Francisco; 2. Gather data on temperature, humidity, wind speed, and other relevant weather conditions; 3. Analyze data to determine current weather trends; 4. Write a brief introduction to the weather report; 5. Describe current weather conditions in San Francisco; 6. Discuss any upcoming weather changes; 7. Summarize the weather report; 8. Proofread and edit the report; 9. Submit the report.\n",
+      "\u001b[95m\u001b[1m\n",
+      "*****TASK LIST*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "2: Gather data on precipitation, cloud cover, and other relevant weather conditions;\n",
+      "3: Analyze data to determine any upcoming weather changes;\n",
+      "4: Research current weather forecasts for San Francisco;\n",
+      "5: Create a visual representation of the weather report;\n",
+      "6: Include relevant images and graphics in the report;\n",
+      "7: Format the report for readability;\n",
+      "8: Publish the report online;\n",
+      "9: Monitor the report for accuracy.\n",
+      "\u001b[92m\u001b[1m\n",
+      "*****NEXT TASK*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "2: Gather data on precipitation, cloud cover, and other relevant weather conditions;\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: I need to search for current weather conditions in San Francisco\n",
+      "Action: Search\n",
+      "Action Input: Current weather conditions in San Francisco\u001b[0m\u001b[36;1m\u001b[1;3mCurrent Weather for Popular Cities ; San Francisco, CA 46 · Partly Cloudy ; Manhattan, NY warning 52 · Cloudy ; Schiller Park, IL (60176) 40 · Sunny ; Boston, MA 54 ...\u001b[0m\u001b[32;1m\u001b[1;3m I need to compile the data into a weather report\n",
+      "Action: TODO\n",
+      "Action Input: Compile data into a weather report\u001b[0m\u001b[33;1m\u001b[1;3m\n",
+      "\n",
+      "1. Gather data from reliable sources such as the National Weather Service, local weather stations, and other meteorological organizations.\n",
+      "\n",
+      "2. Analyze the data to identify trends and patterns.\n",
+      "\n",
+      "3. Create a chart or graph to visualize the data.\n",
+      "\n",
+      "4. Write a summary of the data and its implications.\n",
+      "\n",
+      "5. Compile the data into a report format.\n",
+      "\n",
+      "6. Proofread the report for accuracy and clarity.\n",
+      "\n",
+      "7. Publish the report to a website or other platform.\n",
+      "\n",
+      "8. Distribute the report to relevant stakeholders.\u001b[0m\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: Today in San Francisco, the temperature is 46 degrees Fahrenheit with partly cloudy skies. The forecast for the rest of the day is expected to remain partly cloudy.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\u001b[93m\u001b[1m\n",
+      "*****TASK RESULT*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "Today in San Francisco, the temperature is 46 degrees Fahrenheit with partly cloudy skies. The forecast for the rest of the day is expected to remain partly cloudy.\n",
+      "\u001b[95m\u001b[1m\n",
+      "*****TASK LIST*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "3: Format the report for readability;\n",
+      "4: Include relevant images and graphics in the report;\n",
+      "5: Compare the current weather conditions in San Francisco to the forecasted conditions;\n",
+      "6: Identify any potential weather-related hazards in the area;\n",
+      "7: Research historical weather patterns in San Francisco;\n",
+      "8: Identify any potential trends in the weather data;\n",
+      "9: Include relevant data sources in the report;\n",
+      "10: Summarize the weather report in a concise manner;\n",
+      "11: Include a summary of the forecasted weather conditions;\n",
+      "12: Include a summary of the current weather conditions;\n",
+      "13: Include a summary of the historical weather patterns;\n",
+      "14: Include a summary of the potential weather-related hazards;\n",
+      "15: Include a summary of the potential trends in the weather data;\n",
+      "16: Include a summary of the data sources used in the report;\n",
+      "17: Analyze data to determine any upcoming weather changes;\n",
+      "18: Research current weather forecasts for San Francisco;\n",
+      "19: Create a visual representation of the weather report;\n",
+      "20: Publish the report online;\n",
+      "21: Monitor the report for accuracy\n",
+      "\u001b[92m\u001b[1m\n",
+      "*****NEXT TASK*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "3: Format the report for readability;\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: I need to make sure the report is easy to read;\n",
+      "Action: TODO\n",
+      "Action Input: Make the report easy to read\u001b[0m\u001b[33;1m\u001b[1;3m\n",
+      "\n",
+      "1. Break up the report into sections with clear headings\n",
+      "2. Use bullet points and numbered lists to organize information\n",
+      "3. Use short, concise sentences\n",
+      "4. Use simple language and avoid jargon\n",
+      "5. Include visuals such as charts, graphs, and diagrams to illustrate points\n",
+      "6. Use bold and italicized text to emphasize key points\n",
+      "7. Include a table of contents and page numbers\n",
+      "8. Use a consistent font and font size throughout the report\n",
+      "9. Include a summary at the end of the report\n",
+      "10. Proofread the report for typos and errors\u001b[0m\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: The report should be formatted for readability by breaking it up into sections with clear headings, using bullet points and numbered lists to organize information, using short, concise sentences, using simple language and avoiding jargon, including visuals such as charts, graphs, and diagrams to illustrate points, using bold and italicized text to emphasize key points, including a table of contents and page numbers, using a consistent font and font size throughout the report, including a summary at the end of the report, and proofreading the report for typos and errors.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\u001b[93m\u001b[1m\n",
+      "*****TASK RESULT*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "The report should be formatted for readability by breaking it up into sections with clear headings, using bullet points and numbered lists to organize information, using short, concise sentences, using simple language and avoiding jargon, including visuals such as charts, graphs, and diagrams to illustrate points, using bold and italicized text to emphasize key points, including a table of contents and page numbers, using a consistent font and font size throughout the report, including a summary at the end of the report, and proofreading the report for typos and errors.\n",
+      "\u001b[91m\u001b[1m\n",
+      "*****TASK ENDING*****\n",
+      "\u001b[0m\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "{'objective': 'Write a weather report for SF today'}"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "baby_agi({\"objective\": OBJECTIVE})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "898a210b",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

cookbook/camel_role_playing.ipynb

@@ -0,0 +1,707 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# CAMEL Role-Playing Autonomous Cooperative Agents\n",
+    "\n",
+    "This is a langchain implementation of paper: \"CAMEL: Communicative Agents for “Mind” Exploration of Large Scale Language Model Society\".\n",
+    "\n",
+    "Overview:\n",
+    "\n",
+    "The rapid advancement of conversational and chat-based language models has led to remarkable progress in complex task-solving. However, their success heavily relies on human input to guide the conversation, which can be challenging and time-consuming. This paper explores the potential of building scalable techniques to facilitate autonomous cooperation among communicative agents and provide insight into their \"cognitive\" processes. To address the challenges of achieving autonomous cooperation, we propose a novel communicative agent framework named role-playing. Our approach involves using inception prompting to guide chat agents toward task completion while maintaining consistency with human intentions. We showcase how role-playing can be used to generate conversational data for studying the behaviors and capabilities of chat agents, providing a valuable resource for investigating conversational language models. Our contributions include introducing a novel communicative agent framework, offering a scalable approach for studying the cooperative behaviors and capabilities of multi-agent systems, and open-sourcing our library to support research on communicative agents and beyond.\n",
+    "\n",
+    "The original implementation: https://github.com/lightaime/camel\n",
+    "\n",
+    "Project website: https://www.camel-ai.org/\n",
+    "\n",
+    "Arxiv paper: https://arxiv.org/abs/2303.17760\n"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Import LangChain related modules "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from typing import List\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.prompts.chat import (\n",
+    "    SystemMessagePromptTemplate,\n",
+    "    HumanMessagePromptTemplate,\n",
+    ")\n",
+    "from langchain.schema import (\n",
+    "    AIMessage,\n",
+    "    HumanMessage,\n",
+    "    SystemMessage,\n",
+    "    BaseMessage,\n",
+    ")"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Define a CAMEL agent helper class"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class CAMELAgent:\n",
+    "    def __init__(\n",
+    "        self,\n",
+    "        system_message: SystemMessage,\n",
+    "        model: ChatOpenAI,\n",
+    "    ) -> None:\n",
+    "        self.system_message = system_message\n",
+    "        self.model = model\n",
+    "        self.init_messages()\n",
+    "\n",
+    "    def reset(self) -> None:\n",
+    "        self.init_messages()\n",
+    "        return self.stored_messages\n",
+    "\n",
+    "    def init_messages(self) -> None:\n",
+    "        self.stored_messages = [self.system_message]\n",
+    "\n",
+    "    def update_messages(self, message: BaseMessage) -> List[BaseMessage]:\n",
+    "        self.stored_messages.append(message)\n",
+    "        return self.stored_messages\n",
+    "\n",
+    "    def step(\n",
+    "        self,\n",
+    "        input_message: HumanMessage,\n",
+    "    ) -> AIMessage:\n",
+    "        messages = self.update_messages(input_message)\n",
+    "\n",
+    "        output_message = self.model(messages)\n",
+    "        self.update_messages(output_message)\n",
+    "\n",
+    "        return output_message"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setup OpenAI API key and roles and task for role-playing"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"\"\n",
+    "\n",
+    "assistant_role_name = \"Python Programmer\"\n",
+    "user_role_name = \"Stock Trader\"\n",
+    "task = \"Develop a trading bot for the stock market\"\n",
+    "word_limit = 50  # word limit for task brainstorming"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create a task specify agent for brainstorming and get the specified task"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Specified task: Develop a Python-based swing trading bot that scans market trends, monitors stocks, and generates trading signals to help a stock trader to place optimal buy and sell orders with defined stop losses and profit targets.\n"
+     ]
+    }
+   ],
+   "source": [
+    "task_specifier_sys_msg = SystemMessage(content=\"You can make a task more specific.\")\n",
+    "task_specifier_prompt = \"\"\"Here is a task that {assistant_role_name} will help {user_role_name} to complete: {task}.\n",
+    "Please make it more specific. Be creative and imaginative.\n",
+    "Please reply with the specified task in {word_limit} words or less. Do not add anything else.\"\"\"\n",
+    "task_specifier_template = HumanMessagePromptTemplate.from_template(\n",
+    "    template=task_specifier_prompt\n",
+    ")\n",
+    "task_specify_agent = CAMELAgent(task_specifier_sys_msg, ChatOpenAI(temperature=1.0))\n",
+    "task_specifier_msg = task_specifier_template.format_messages(\n",
+    "    assistant_role_name=assistant_role_name,\n",
+    "    user_role_name=user_role_name,\n",
+    "    task=task,\n",
+    "    word_limit=word_limit,\n",
+    ")[0]\n",
+    "specified_task_msg = task_specify_agent.step(task_specifier_msg)\n",
+    "print(f\"Specified task: {specified_task_msg.content}\")\n",
+    "specified_task = specified_task_msg.content"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create inception prompts for AI assistant and AI user for role-playing"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "assistant_inception_prompt = \"\"\"Never forget you are a {assistant_role_name} and I am a {user_role_name}. Never flip roles! Never instruct me!\n",
+    "We share a common interest in collaborating to successfully complete a task.\n",
+    "You must help me to complete the task.\n",
+    "Here is the task: {task}. Never forget our task!\n",
+    "I must instruct you based on your expertise and my needs to complete the task.\n",
+    "\n",
+    "I must give you one instruction at a time.\n",
+    "You must write a specific solution that appropriately completes the requested instruction.\n",
+    "You must decline my instruction honestly if you cannot perform the instruction due to physical, moral, legal reasons or your capability and explain the reasons.\n",
+    "Do not add anything else other than your solution to my instruction.\n",
+    "You are never supposed to ask me any questions you only answer questions.\n",
+    "You are never supposed to reply with a flake solution. Explain your solutions.\n",
+    "Your solution must be declarative sentences and simple present tense.\n",
+    "Unless I say the task is completed, you should always start with:\n",
+    "\n",
+    "Solution: <YOUR_SOLUTION>\n",
+    "\n",
+    "<YOUR_SOLUTION> should be specific and provide preferable implementations and examples for task-solving.\n",
+    "Always end <YOUR_SOLUTION> with: Next request.\"\"\"\n",
+    "\n",
+    "user_inception_prompt = \"\"\"Never forget you are a {user_role_name} and I am a {assistant_role_name}. Never flip roles! You will always instruct me.\n",
+    "We share a common interest in collaborating to successfully complete a task.\n",
+    "I must help you to complete the task.\n",
+    "Here is the task: {task}. Never forget our task!\n",
+    "You must instruct me based on my expertise and your needs to complete the task ONLY in the following two ways:\n",
+    "\n",
+    "1. Instruct with a necessary input:\n",
+    "Instruction: <YOUR_INSTRUCTION>\n",
+    "Input: <YOUR_INPUT>\n",
+    "\n",
+    "2. Instruct without any input:\n",
+    "Instruction: <YOUR_INSTRUCTION>\n",
+    "Input: None\n",
+    "\n",
+    "The \"Instruction\" describes a task or question. The paired \"Input\" provides further context or information for the requested \"Instruction\".\n",
+    "\n",
+    "You must give me one instruction at a time.\n",
+    "I must write a response that appropriately completes the requested instruction.\n",
+    "I must decline your instruction honestly if I cannot perform the instruction due to physical, moral, legal reasons or my capability and explain the reasons.\n",
+    "You should instruct me not ask me questions.\n",
+    "Now you must start to instruct me using the two ways described above.\n",
+    "Do not add anything else other than your instruction and the optional corresponding input!\n",
+    "Keep giving me instructions and necessary inputs until you think the task is completed.\n",
+    "When the task is completed, you must only reply with a single word <CAMEL_TASK_DONE>.\n",
+    "Never say <CAMEL_TASK_DONE> unless my responses have solved your task.\"\"\""
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create a helper helper to get system messages for AI assistant and AI user from role names and the task"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_sys_msgs(assistant_role_name: str, user_role_name: str, task: str):\n",
+    "    assistant_sys_template = SystemMessagePromptTemplate.from_template(\n",
+    "        template=assistant_inception_prompt\n",
+    "    )\n",
+    "    assistant_sys_msg = assistant_sys_template.format_messages(\n",
+    "        assistant_role_name=assistant_role_name,\n",
+    "        user_role_name=user_role_name,\n",
+    "        task=task,\n",
+    "    )[0]\n",
+    "\n",
+    "    user_sys_template = SystemMessagePromptTemplate.from_template(\n",
+    "        template=user_inception_prompt\n",
+    "    )\n",
+    "    user_sys_msg = user_sys_template.format_messages(\n",
+    "        assistant_role_name=assistant_role_name,\n",
+    "        user_role_name=user_role_name,\n",
+    "        task=task,\n",
+    "    )[0]\n",
+    "\n",
+    "    return assistant_sys_msg, user_sys_msg"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create AI assistant agent and AI user agent from obtained system messages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "assistant_sys_msg, user_sys_msg = get_sys_msgs(\n",
+    "    assistant_role_name, user_role_name, specified_task\n",
+    ")\n",
+    "assistant_agent = CAMELAgent(assistant_sys_msg, ChatOpenAI(temperature=0.2))\n",
+    "user_agent = CAMELAgent(user_sys_msg, ChatOpenAI(temperature=0.2))\n",
+    "\n",
+    "# Reset agents\n",
+    "assistant_agent.reset()\n",
+    "user_agent.reset()\n",
+    "\n",
+    "# Initialize chats\n",
+    "user_msg = HumanMessage(\n",
+    "    content=(\n",
+    "        f\"{user_sys_msg.content}. \"\n",
+    "        \"Now start to give me introductions one by one. \"\n",
+    "        \"Only reply with Instruction and Input.\"\n",
+    "    )\n",
+    ")\n",
+    "\n",
+    "assistant_msg = HumanMessage(content=f\"{assistant_sys_msg.content}\")\n",
+    "assistant_msg = assistant_agent.step(user_msg)"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Start role-playing session to solve the task!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Original task prompt:\n",
+      "Develop a trading bot for the stock market\n",
+      "\n",
+      "Specified task prompt:\n",
+      "Develop a Python-based swing trading bot that scans market trends, monitors stocks, and generates trading signals to help a stock trader to place optimal buy and sell orders with defined stop losses and profit targets.\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Install the necessary Python libraries for data analysis and trading.\n",
+      "Input: None\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can install the necessary Python libraries using pip, a package installer for Python. We can install pandas, numpy, matplotlib, and ta-lib for data analysis and trading. We can use the following command to install these libraries:\n",
+      "\n",
+      "```\n",
+      "pip install pandas numpy matplotlib ta-lib\n",
+      "```\n",
+      "\n",
+      "Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Import the necessary libraries in the Python script.\n",
+      "Input: None\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can import the necessary libraries in the Python script using the import statement. We need to import pandas, numpy, matplotlib, and ta-lib for data analysis and trading. We can use the following code to import these libraries:\n",
+      "\n",
+      "```\n",
+      "import pandas as pd\n",
+      "import numpy as np\n",
+      "import matplotlib.pyplot as plt\n",
+      "import talib as ta\n",
+      "```\n",
+      "\n",
+      "Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Load historical stock data into a pandas DataFrame.\n",
+      "Input: The path to the CSV file containing the historical stock data.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can load historical stock data into a pandas DataFrame using the `read_csv()` function from pandas. We need to pass the path to the CSV file containing the historical stock data as an argument to this function. We can use the following code to load the historical stock data:\n",
+      "\n",
+      "```\n",
+      "df = pd.read_csv('path/to/csv/file.csv')\n",
+      "```\n",
+      "\n",
+      "This will load the historical stock data into a pandas DataFrame called `df`. Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Preprocess the historical stock data by setting the date column as the index and sorting the DataFrame in ascending order by date.\n",
+      "Input: None.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can preprocess the historical stock data by setting the date column as the index and sorting the DataFrame in ascending order by date using the `set_index()` and `sort_index()` functions from pandas. We can use the following code to preprocess the historical stock data:\n",
+      "\n",
+      "```\n",
+      "df = df.set_index('date')\n",
+      "df = df.sort_index(ascending=True)\n",
+      "```\n",
+      "\n",
+      "This will set the date column as the index and sort the DataFrame in ascending order by date. Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Calculate the short-term and long-term moving averages for the stock data using the `ta.SMA()` function from ta-lib.\n",
+      "Input: The period for the short-term moving average and the period for the long-term moving average.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can calculate the short-term and long-term moving averages for the stock data using the `ta.SMA()` function from ta-lib. We need to pass the period for the short-term moving average and the period for the long-term moving average as arguments to this function. We can use the following code to calculate the short-term and long-term moving averages:\n",
+      "\n",
+      "```\n",
+      "short_ma = ta.SMA(df['close'], timeperiod=short_period)\n",
+      "long_ma = ta.SMA(df['close'], timeperiod=long_period)\n",
+      "```\n",
+      "\n",
+      "This will calculate the short-term and long-term moving averages for the stock data and store them in the `short_ma` and `long_ma` variables, respectively. Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Create a new DataFrame that combines the historical stock data with the short-term and long-term moving averages.\n",
+      "Input: None.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can create a new DataFrame that combines the historical stock data with the short-term and long-term moving averages using the `concat()` function from pandas. We need to pass the historical stock data, the short-term moving average, and the long-term moving average as arguments to this function. We can use the following code to create the new DataFrame:\n",
+      "\n",
+      "```\n",
+      "new_df = pd.concat([df, short_ma, long_ma], axis=1)\n",
+      "new_df.columns = ['open', 'high', 'low', 'close', 'volume', 'short_ma', 'long_ma']\n",
+      "```\n",
+      "\n",
+      "This will create a new DataFrame called `new_df` that combines the historical stock data with the short-term and long-term moving averages. The columns of the new DataFrame are named 'open', 'high', 'low', 'close', 'volume', 'short_ma', and 'long_ma'. Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Create a new column in the DataFrame that indicates when to buy or sell the stock based on the crossover of the short-term and long-term moving averages.\n",
+      "Input: None.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can create a new column in the DataFrame that indicates when to buy or sell the stock based on the crossover of the short-term and long-term moving averages. We can use the following code to create the new column:\n",
+      "\n",
+      "```\n",
+      "new_df['signal'] = np.where(new_df['short_ma'] > new_df['long_ma'], 1, -1)\n",
+      "```\n",
+      "\n",
+      "This will create a new column called 'signal' in the DataFrame that indicates when to buy or sell the stock based on the crossover of the short-term and long-term moving averages. If the short-term moving average is greater than the long-term moving average, the signal is 1 (buy), otherwise the signal is -1 (sell). Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Create a new column in the DataFrame that indicates the profit or loss for each trade based on the buy and sell signals and the defined stop loss and profit target.\n",
+      "Input: The stop loss and profit target as percentages.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can create a new column in the DataFrame that indicates the profit or loss for each trade based on the buy and sell signals and the defined stop loss and profit target. We need to pass the stop loss and profit target as percentages as arguments to this function. We can use the following code to create the new column:\n",
+      "\n",
+      "```\n",
+      "stop_loss = stop_loss_percent / 100\n",
+      "profit_target = profit_target_percent / 100\n",
+      "\n",
+      "new_df['pnl'] = 0.0\n",
+      "buy_price = 0.0\n",
+      "for i in range(1, len(new_df)):\n",
+      "    if new_df['signal'][i] == 1 and new_df['signal'][i-1] == -1:\n",
+      "        buy_price = new_df['close'][i]\n",
+      "    elif new_df['signal'][i] == -1 and new_df['signal'][i-1] == 1:\n",
+      "        sell_price = new_df['close'][i]\n",
+      "        if sell_price <= buy_price * (1 - stop_loss):\n",
+      "            new_df['pnl'][i] = -stop_loss\n",
+      "        elif sell_price >= buy_price * (1 + profit_target):\n",
+      "            new_df['pnl'][i] = profit_target\n",
+      "        else:\n",
+      "            new_df['pnl'][i] = (sell_price - buy_price) / buy_price\n",
+      "```\n",
+      "\n",
+      "This will create a new column called 'pnl' in the DataFrame that indicates the profit or loss for each trade based on the buy and sell signals and the defined stop loss and profit target. The stop loss and profit target are calculated based on the stop_loss_percent and profit_target_percent variables, respectively. The buy and sell prices are stored in the buy_price and sell_price variables, respectively. If the sell price is less than or equal to the stop loss, the profit or loss is set to -stop_loss. If the sell price is greater than or equal to the profit target, the profit or loss is set to profit_target. Otherwise, the profit or loss is calculated as (sell_price - buy_price) / buy_price. Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Calculate the total profit or loss for all trades.\n",
+      "Input: None.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can calculate the total profit or loss for all trades by summing the values in the 'pnl' column of the DataFrame. We can use the following code to calculate the total profit or loss:\n",
+      "\n",
+      "```\n",
+      "total_pnl = new_df['pnl'].sum()\n",
+      "```\n",
+      "\n",
+      "This will calculate the total profit or loss for all trades and store it in the total_pnl variable. Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Visualize the stock data, short-term moving average, and long-term moving average using a line chart.\n",
+      "Input: None.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can visualize the stock data, short-term moving average, and long-term moving average using a line chart using the `plot()` function from pandas. We can use the following code to visualize the data:\n",
+      "\n",
+      "```\n",
+      "plt.figure(figsize=(12,6))\n",
+      "plt.plot(new_df.index, new_df['close'], label='Close')\n",
+      "plt.plot(new_df.index, new_df['short_ma'], label='Short MA')\n",
+      "plt.plot(new_df.index, new_df['long_ma'], label='Long MA')\n",
+      "plt.xlabel('Date')\n",
+      "plt.ylabel('Price')\n",
+      "plt.title('Stock Data with Moving Averages')\n",
+      "plt.legend()\n",
+      "plt.show()\n",
+      "```\n",
+      "\n",
+      "This will create a line chart that visualizes the stock data, short-term moving average, and long-term moving average. The x-axis represents the date and the y-axis represents the price. The chart also includes a legend that labels each line. Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Visualize the buy and sell signals using a scatter plot.\n",
+      "Input: None.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can visualize the buy and sell signals using a scatter plot using the `scatter()` function from matplotlib. We can use the following code to visualize the signals:\n",
+      "\n",
+      "```\n",
+      "buy_signals = new_df[new_df['signal'] == 1]\n",
+      "sell_signals = new_df[new_df['signal'] == -1]\n",
+      "\n",
+      "plt.figure(figsize=(12,6))\n",
+      "plt.scatter(buy_signals.index, buy_signals['close'], label='Buy', marker='^', color='green')\n",
+      "plt.scatter(sell_signals.index, sell_signals['close'], label='Sell', marker='v', color='red')\n",
+      "plt.plot(new_df.index, new_df['close'], label='Close')\n",
+      "plt.xlabel('Date')\n",
+      "plt.ylabel('Price')\n",
+      "plt.title('Buy and Sell Signals')\n",
+      "plt.legend()\n",
+      "plt.show()\n",
+      "```\n",
+      "\n",
+      "This will create a scatter plot that visualizes the buy and sell signals. The x-axis represents the date and the y-axis represents the price. The chart also includes a legend that labels each point. Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Print the total profit or loss for all trades.\n",
+      "Input: None.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can print the total profit or loss for all trades using the `print()` function. We can use the following code to print the total profit or loss:\n",
+      "\n",
+      "```\n",
+      "print('Total Profit/Loss: {:.2%}'.format(total_pnl))\n",
+      "```\n",
+      "\n",
+      "This will print the total profit or loss for all trades in percentage format with two decimal places. Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Finalize the code by putting all the code snippets together in a single Python script.\n",
+      "Input: The necessary inputs for each code snippet.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: Here is the complete Python script that puts all the code snippets together:\n",
+      "\n",
+      "```\n",
+      "import pandas as pd\n",
+      "import numpy as np\n",
+      "import matplotlib.pyplot as plt\n",
+      "import talib as ta\n",
+      "\n",
+      "# Load historical stock data into a pandas DataFrame\n",
+      "df = pd.read_csv('path/to/csv/file.csv')\n",
+      "\n",
+      "# Preprocess the historical stock data\n",
+      "df = df.set_index('date')\n",
+      "df = df.sort_index(ascending=True)\n",
+      "\n",
+      "# Calculate the short-term and long-term moving averages\n",
+      "short_period = 10\n",
+      "long_period = 30\n",
+      "short_ma = ta.SMA(df['close'], timeperiod=short_period)\n",
+      "long_ma = ta.SMA(df['close'], timeperiod=long_period)\n",
+      "\n",
+      "# Create a new DataFrame that combines the historical stock data with the short-term and long-term moving averages\n",
+      "new_df = pd.concat([df, short_ma, long_ma], axis=1)\n",
+      "new_df.columns = ['open', 'high', 'low', 'close', 'volume', 'short_ma', 'long_ma']\n",
+      "\n",
+      "# Create a new column in the DataFrame that indicates when to buy or sell the stock based on the crossover of the short-term and long-term moving averages\n",
+      "new_df['signal'] = np.where(new_df['short_ma'] > new_df['long_ma'], 1, -1)\n",
+      "\n",
+      "# Create a new column in the DataFrame that indicates the profit or loss for each trade based on the buy and sell signals and the defined stop loss and profit target\n",
+      "stop_loss_percent = 5\n",
+      "profit_target_percent = 10\n",
+      "stop_loss = stop_loss_percent / 100\n",
+      "profit_target = profit_target_percent / 100\n",
+      "new_df['pnl'] = 0.0\n",
+      "buy_price = 0.0\n",
+      "for i in range(1, len(new_df)):\n",
+      "    if new_df['signal'][i] == 1 and new_df['signal'][i-1] == -1:\n",
+      "        buy_price = new_df['close'][i]\n",
+      "    elif new_df['signal'][i] == -1 and new_df['signal'][i-1] == 1:\n",
+      "        sell_price = new_df['close'][i]\n",
+      "        if sell_price <= buy_price * (1 - stop_loss):\n",
+      "            new_df['pnl'][i] = -stop_loss\n",
+      "        elif sell_price >= buy_price * (1 + profit_target):\n",
+      "            new_df['pnl'][i] = profit_target\n",
+      "        else:\n",
+      "            new_df['pnl'][i] = (sell_price - buy_price) / buy_price\n",
+      "\n",
+      "# Calculate the total profit or loss for all trades\n",
+      "total_pnl = new_df['pnl'].sum()\n",
+      "\n",
+      "# Visualize the stock data, short-term moving average, and long-term moving average using a line chart\n",
+      "plt.figure(figsize=(12,6))\n",
+      "plt.plot(new_df.index, new_df['close'], label='Close')\n",
+      "plt.plot(new_df.index, new_df['short_ma'], label='Short MA')\n",
+      "plt.plot(new_df.index, new_df['long_ma'], label='Long MA')\n",
+      "plt.xlabel('Date')\n",
+      "plt.ylabel('Price')\n",
+      "plt.title('Stock Data with Moving Averages')\n",
+      "plt.legend()\n",
+      "plt.show()\n",
+      "\n",
+      "# Visualize the buy and sell signals using a scatter plot\n",
+      "buy_signals = new_df[new_df['signal'] == 1]\n",
+      "sell_signals = new_df[new_df['signal'] == -1]\n",
+      "plt.figure(figsize=(12,6))\n",
+      "plt.scatter(buy_signals.index, buy_signals['close'], label='Buy', marker='^', color='green')\n",
+      "plt.scatter(sell_signals.index, sell_signals['close'], label='Sell', marker='v', color='red')\n",
+      "plt.plot(new_df.index, new_df['close'], label='Close')\n",
+      "plt.xlabel('Date')\n",
+      "plt.ylabel('Price')\n",
+      "plt.title('Buy and Sell Signals')\n",
+      "plt.legend()\n",
+      "plt.show()\n",
+      "\n",
+      "# Print the total profit or loss for all trades\n",
+      "print('Total Profit/Loss: {:.2%}'.format(total_pnl))\n",
+      "```\n",
+      "\n",
+      "You need to replace the path/to/csv/file.csv with the actual path to the CSV file containing the historical stock data. You can also adjust the short_period, long_period, stop_loss_percent, and profit_target_percent variables to suit your needs.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "<CAMEL_TASK_DONE>\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Great! Let me know if you need any further assistance.\n",
+      "\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(f\"Original task prompt:\\n{task}\\n\")\n",
+    "print(f\"Specified task prompt:\\n{specified_task}\\n\")\n",
+    "\n",
+    "chat_turn_limit, n = 30, 0\n",
+    "while n < chat_turn_limit:\n",
+    "    n += 1\n",
+    "    user_ai_msg = user_agent.step(assistant_msg)\n",
+    "    user_msg = HumanMessage(content=user_ai_msg.content)\n",
+    "    print(f\"AI User ({user_role_name}):\\n\\n{user_msg.content}\\n\\n\")\n",
+    "\n",
+    "    assistant_ai_msg = assistant_agent.step(user_msg)\n",
+    "    assistant_msg = HumanMessage(content=assistant_ai_msg.content)\n",
+    "    print(f\"AI Assistant ({assistant_role_name}):\\n\\n{assistant_msg.content}\\n\\n\")\n",
+    "    if \"<CAMEL_TASK_DONE>\" in user_msg.content:\n",
+    "        break"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "camel",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.9"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

cookbook/custom_agent_with_plugin_retrieval.ipynb

@@ -0,0 +1,553 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "ba5f8741",
+   "metadata": {},
+   "source": [
+    "# Custom Agent with PlugIn Retrieval\n",
+    "\n",
+    "This notebook combines two concepts in order to build a custom agent that can interact with AI Plugins:\n",
+    "\n",
+    "1. [Custom Agent with Tool Retrieval](/docs/modules/agents/how_to/custom_agent_with_tool_retrieval.html): This introduces the concept of retrieving many tools, which is useful when trying to work with arbitrarily many plugins.\n",
+    "2. [Natural Language API Chains](/docs/use_cases/apis/openapi.html): This creates Natural Language wrappers around OpenAPI endpoints. This is useful because (1) plugins use OpenAPI endpoints under the hood, (2) wrapping them in an NLAChain allows the router agent to call it more easily.\n",
+    "\n",
+    "The novel idea introduced in this notebook is the idea of using retrieval to select not the tools explicitly, but the set of OpenAPI specs to use. We can then generate tools from those OpenAPI specs. The use case for this is when trying to get agents to use plugins. It may be more efficient to choose plugins first, then the endpoints, rather than the endpoints directly. This is because the plugins may contain more useful information for selection."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fea4812c",
+   "metadata": {},
+   "source": [
+    "## Set up environment\n",
+    "\n",
+    "Do necessary imports, etc."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "9af9734e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.agents import (\n",
+    "    Tool,\n",
+    "    AgentExecutor,\n",
+    "    LLMSingleActionAgent,\n",
+    "    AgentOutputParser,\n",
+    ")\n",
+    "from langchain.prompts import StringPromptTemplate\n",
+    "from langchain.llms import OpenAI\nfrom langchain.utilities import SerpAPIWrapper\nfrom langchain.chains import LLMChain\n",
+    "from typing import List, Union\n",
+    "from langchain.schema import AgentAction, AgentFinish\n",
+    "from langchain.agents.agent_toolkits import NLAToolkit\n",
+    "from langchain.tools.plugin import AIPlugin\n",
+    "import re"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2f91d8b4",
+   "metadata": {},
+   "source": [
+    "## Setup LLM"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "a1a3b59c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = OpenAI(temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6df0253f",
+   "metadata": {},
+   "source": [
+    "## Set up plugins\n",
+    "\n",
+    "Load and index plugins"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "becda2a1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "urls = [\n",
+    "    \"https://datasette.io/.well-known/ai-plugin.json\",\n",
+    "    \"https://api.speak.com/.well-known/ai-plugin.json\",\n",
+    "    \"https://www.wolframalpha.com/.well-known/ai-plugin.json\",\n",
+    "    \"https://www.zapier.com/.well-known/ai-plugin.json\",\n",
+    "    \"https://www.klarna.com/.well-known/ai-plugin.json\",\n",
+    "    \"https://www.joinmilo.com/.well-known/ai-plugin.json\",\n",
+    "    \"https://slack.com/.well-known/ai-plugin.json\",\n",
+    "    \"https://schooldigger.com/.well-known/ai-plugin.json\",\n",
+    "]\n",
+    "\n",
+    "AI_PLUGINS = [AIPlugin.from_url(url) for url in urls]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "17362717",
+   "metadata": {},
+   "source": [
+    "## Tool Retriever\n",
+    "\n",
+    "We will use a vectorstore to create embeddings for each tool description. Then, for an incoming query we can create embeddings for that query and do a similarity search for relevant tools."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "77c4be4b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.vectorstores import FAISS\n",
+    "from langchain.embeddings import OpenAIEmbeddings\n",
+    "from langchain.schema import Document"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "9092a158",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
+      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
+      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
+      "Attempting to load an OpenAPI 3.0.2 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
+      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
+      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
+      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
+      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
+      "Attempting to load a Swagger 2.0 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n"
+     ]
+    }
+   ],
+   "source": [
+    "embeddings = OpenAIEmbeddings()\n",
+    "docs = [\n",
+    "    Document(\n",
+    "        page_content=plugin.description_for_model,\n",
+    "        metadata={\"plugin_name\": plugin.name_for_model},\n",
+    "    )\n",
+    "    for plugin in AI_PLUGINS\n",
+    "]\n",
+    "vector_store = FAISS.from_documents(docs, embeddings)\n",
+    "toolkits_dict = {\n",
+    "    plugin.name_for_model: NLAToolkit.from_llm_and_ai_plugin(llm, plugin)\n",
+    "    for plugin in AI_PLUGINS\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "735a7566",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "retriever = vector_store.as_retriever()\n",
+    "\n",
+    "\n",
+    "def get_tools(query):\n",
+    "    # Get documents, which contain the Plugins to use\n",
+    "    docs = retriever.get_relevant_documents(query)\n",
+    "    # Get the toolkits, one for each plugin\n",
+    "    tool_kits = [toolkits_dict[d.metadata[\"plugin_name\"]] for d in docs]\n",
+    "    # Get the tools: a separate NLAChain for each endpoint\n",
+    "    tools = []\n",
+    "    for tk in tool_kits:\n",
+    "        tools.extend(tk.nla_tools)\n",
+    "    return tools"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7699afd7",
+   "metadata": {},
+   "source": [
+    "We can now test this retriever to see if it seems to work."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "425f2886",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['Milo.askMilo',\n",
+       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.search_all_actions',\n",
+       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.preview_a_zap',\n",
+       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.get_configuration_link',\n",
+       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.list_exposed_actions',\n",
+       " 'SchoolDigger_API_V2.0.Autocomplete_GetSchools',\n",
+       " 'SchoolDigger_API_V2.0.Districts_GetAllDistricts2',\n",
+       " 'SchoolDigger_API_V2.0.Districts_GetDistrict2',\n",
+       " 'SchoolDigger_API_V2.0.Rankings_GetSchoolRank2',\n",
+       " 'SchoolDigger_API_V2.0.Rankings_GetRank_District',\n",
+       " 'SchoolDigger_API_V2.0.Schools_GetAllSchools20',\n",
+       " 'SchoolDigger_API_V2.0.Schools_GetSchool20',\n",
+       " 'Speak.translate',\n",
+       " 'Speak.explainPhrase',\n",
+       " 'Speak.explainTask']"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "tools = get_tools(\"What could I do today with my kiddo\")\n",
+    "[t.name for t in tools]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "3aa88768",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['Open_AI_Klarna_product_Api.productsUsingGET',\n",
+       " 'Milo.askMilo',\n",
+       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.search_all_actions',\n",
+       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.preview_a_zap',\n",
+       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.get_configuration_link',\n",
+       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.list_exposed_actions',\n",
+       " 'SchoolDigger_API_V2.0.Autocomplete_GetSchools',\n",
+       " 'SchoolDigger_API_V2.0.Districts_GetAllDistricts2',\n",
+       " 'SchoolDigger_API_V2.0.Districts_GetDistrict2',\n",
+       " 'SchoolDigger_API_V2.0.Rankings_GetSchoolRank2',\n",
+       " 'SchoolDigger_API_V2.0.Rankings_GetRank_District',\n",
+       " 'SchoolDigger_API_V2.0.Schools_GetAllSchools20',\n",
+       " 'SchoolDigger_API_V2.0.Schools_GetSchool20']"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "tools = get_tools(\"what shirts can i buy?\")\n",
+    "[t.name for t in tools]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2e7a075c",
+   "metadata": {},
+   "source": [
+    "## Prompt Template\n",
+    "\n",
+    "The prompt template is pretty standard, because we're not actually changing that much logic in the actual prompt template, but rather we are just changing how retrieval is done."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "339b1bb8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Set up the base template\n",
+    "template = \"\"\"Answer the following questions as best you can, but speaking as a pirate might speak. You have access to the following tools:\n",
+    "\n",
+    "{tools}\n",
+    "\n",
+    "Use the following format:\n",
+    "\n",
+    "Question: the input question you must answer\n",
+    "Thought: you should always think about what to do\n",
+    "Action: the action to take, should be one of [{tool_names}]\n",
+    "Action Input: the input to the action\n",
+    "Observation: the result of the action\n",
+    "... (this Thought/Action/Action Input/Observation can repeat N times)\n",
+    "Thought: I now know the final answer\n",
+    "Final Answer: the final answer to the original input question\n",
+    "\n",
+    "Begin! Remember to speak as a pirate when giving your final answer. Use lots of \"Arg\"s\n",
+    "\n",
+    "Question: {input}\n",
+    "{agent_scratchpad}\"\"\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1583acdc",
+   "metadata": {},
+   "source": [
+    "The custom prompt template now has the concept of a tools_getter, which we call on the input to select the tools to use"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "fd969d31",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from typing import Callable\n",
+    "\n",
+    "\n",
+    "# Set up a prompt template\n",
+    "class CustomPromptTemplate(StringPromptTemplate):\n",
+    "    # The template to use\n",
+    "    template: str\n",
+    "    ############## NEW ######################\n",
+    "    # The list of tools available\n",
+    "    tools_getter: Callable\n",
+    "\n",
+    "    def format(self, **kwargs) -> str:\n",
+    "        # Get the intermediate steps (AgentAction, Observation tuples)\n",
+    "        # Format them in a particular way\n",
+    "        intermediate_steps = kwargs.pop(\"intermediate_steps\")\n",
+    "        thoughts = \"\"\n",
+    "        for action, observation in intermediate_steps:\n",
+    "            thoughts += action.log\n",
+    "            thoughts += f\"\\nObservation: {observation}\\nThought: \"\n",
+    "        # Set the agent_scratchpad variable to that value\n",
+    "        kwargs[\"agent_scratchpad\"] = thoughts\n",
+    "        ############## NEW ######################\n",
+    "        tools = self.tools_getter(kwargs[\"input\"])\n",
+    "        # Create a tools variable from the list of tools provided\n",
+    "        kwargs[\"tools\"] = \"\\n\".join(\n",
+    "            [f\"{tool.name}: {tool.description}\" for tool in tools]\n",
+    "        )\n",
+    "        # Create a list of tool names for the tools provided\n",
+    "        kwargs[\"tool_names\"] = \", \".join([tool.name for tool in tools])\n",
+    "        return self.template.format(**kwargs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "798ef9fb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prompt = CustomPromptTemplate(\n",
+    "    template=template,\n",
+    "    tools_getter=get_tools,\n",
+    "    # This omits the `agent_scratchpad`, `tools`, and `tool_names` variables because those are generated dynamically\n",
+    "    # This includes the `intermediate_steps` variable because that is needed\n",
+    "    input_variables=[\"input\", \"intermediate_steps\"],\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ef3a1af3",
+   "metadata": {},
+   "source": [
+    "## Output Parser\n",
+    "\n",
+    "The output parser is unchanged from the previous notebook, since we are not changing anything about the output format."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "7c6fe0d3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class CustomOutputParser(AgentOutputParser):\n",
+    "    def parse(self, llm_output: str) -> Union[AgentAction, AgentFinish]:\n",
+    "        # Check if agent should finish\n",
+    "        if \"Final Answer:\" in llm_output:\n",
+    "            return AgentFinish(\n",
+    "                # Return values is generally always a dictionary with a single `output` key\n",
+    "                # It is not recommended to try anything else at the moment :)\n",
+    "                return_values={\"output\": llm_output.split(\"Final Answer:\")[-1].strip()},\n",
+    "                log=llm_output,\n",
+    "            )\n",
+    "        # Parse out the action and action input\n",
+    "        regex = r\"Action\\s*\\d*\\s*:(.*?)\\nAction\\s*\\d*\\s*Input\\s*\\d*\\s*:[\\s]*(.*)\"\n",
+    "        match = re.search(regex, llm_output, re.DOTALL)\n",
+    "        if not match:\n",
+    "            raise ValueError(f\"Could not parse LLM output: `{llm_output}`\")\n",
+    "        action = match.group(1).strip()\n",
+    "        action_input = match.group(2)\n",
+    "        # Return the action and action input\n",
+    "        return AgentAction(\n",
+    "            tool=action, tool_input=action_input.strip(\" \").strip('\"'), log=llm_output\n",
+    "        )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "d278706a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "output_parser = CustomOutputParser()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "170587b1",
+   "metadata": {},
+   "source": [
+    "## Set up LLM, stop sequence, and the agent\n",
+    "\n",
+    "Also the same as the previous notebook"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "f9d4c374",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = OpenAI(temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "9b1cc2a2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# LLM chain consisting of the LLM and a prompt\n",
+    "llm_chain = LLMChain(llm=llm, prompt=prompt)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "e4f5092f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tool_names = [tool.name for tool in tools]\n",
+    "agent = LLMSingleActionAgent(\n",
+    "    llm_chain=llm_chain,\n",
+    "    output_parser=output_parser,\n",
+    "    stop=[\"\\nObservation:\"],\n",
+    "    allowed_tools=tool_names,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "aa8a5326",
+   "metadata": {},
+   "source": [
+    "## Use the Agent\n",
+    "\n",
+    "Now we can use it!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "490604e9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "agent_executor = AgentExecutor.from_agent_and_tools(\n",
+    "    agent=agent, tools=tools, verbose=True\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "653b1617",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: I need to find a product API\n",
+      "Action: Open_AI_Klarna_product_Api.productsUsingGET\n",
+      "Action Input: shirts\u001b[0m\n",
+      "\n",
+      "Observation:\u001b[36;1m\u001b[1;3mI found 10 shirts from the API response. They range in price from $9.99 to $450.00 and come in a variety of materials, colors, and patterns.\u001b[0m\u001b[32;1m\u001b[1;3m I now know what shirts I can buy\n",
+      "Final Answer: Arg, I found 10 shirts from the API response. They range in price from $9.99 to $450.00 and come in a variety of materials, colors, and patterns.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'Arg, I found 10 shirts from the API response. They range in price from $9.99 to $450.00 and come in a variety of materials, colors, and patterns.'"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent_executor.run(\"what shirts can i buy?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2481ee76",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.3"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "18784188d7ecd866c0586ac068b02361a6896dc3a29b64f5cc957f09c590acef"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

cookbook/custom_agent_with_plugin_retrieval_using_plugnplai.ipynb

@@ -0,0 +1,577 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "ba5f8741",
+   "metadata": {},
+   "source": [
+    "# Plug-and-Plai\n",
+    "\n",
+    "This notebook builds upon the idea of [plugin retrieval](./custom_agent_with_plugin_retrieval.html), but pulls all tools from `plugnplai` - a directory of AI Plugins."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fea4812c",
+   "metadata": {},
+   "source": [
+    "## Set up environment\n",
+    "\n",
+    "Do necessary imports, etc."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "aca08be8",
+   "metadata": {},
+   "source": [
+    "Install plugnplai lib to get a list of active plugins from https://plugplai.com directory"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "52e248c9",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip available: \u001b[0m\u001b[31;49m22.3.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m23.1.1\u001b[0m\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
+   "source": [
+    "pip install plugnplai -q"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "9af9734e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.agents import (\n",
+    "    Tool,\n",
+    "    AgentExecutor,\n",
+    "    LLMSingleActionAgent,\n",
+    "    AgentOutputParser,\n",
+    ")\n",
+    "from langchain.prompts import StringPromptTemplate\n",
+    "from langchain.llms import OpenAI\nfrom langchain.utilities import SerpAPIWrapper\nfrom langchain.chains import LLMChain\n",
+    "from typing import List, Union\n",
+    "from langchain.schema import AgentAction, AgentFinish\n",
+    "from langchain.agents.agent_toolkits import NLAToolkit\n",
+    "from langchain.tools.plugin import AIPlugin\n",
+    "import re\n",
+    "import plugnplai"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2f91d8b4",
+   "metadata": {},
+   "source": [
+    "## Setup LLM"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "a1a3b59c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = OpenAI(temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6df0253f",
+   "metadata": {},
+   "source": [
+    "## Set up plugins\n",
+    "\n",
+    "Load and index plugins"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "9e0f7882",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Get all plugins from plugnplai.com\n",
+    "urls = plugnplai.get_plugins()\n",
+    "\n",
+    "#  Get ChatGPT plugins - only ChatGPT verified plugins\n",
+    "urls = plugnplai.get_plugins(filter=\"ChatGPT\")\n",
+    "\n",
+    "#  Get working plugins - only tested plugins (in progress)\n",
+    "urls = plugnplai.get_plugins(filter=\"working\")\n",
+    "\n",
+    "\n",
+    "AI_PLUGINS = [AIPlugin.from_url(url + \"/.well-known/ai-plugin.json\") for url in urls]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "17362717",
+   "metadata": {},
+   "source": [
+    "## Tool Retriever\n",
+    "\n",
+    "We will use a vectorstore to create embeddings for each tool description. Then, for an incoming query we can create embeddings for that query and do a similarity search for relevant tools."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "77c4be4b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.vectorstores import FAISS\n",
+    "from langchain.embeddings import OpenAIEmbeddings\n",
+    "from langchain.schema import Document"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "9092a158",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
+      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
+      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
+      "Attempting to load an OpenAPI 3.0.2 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
+      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
+      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
+      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
+      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
+      "Attempting to load a Swagger 2.0 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n"
+     ]
+    }
+   ],
+   "source": [
+    "embeddings = OpenAIEmbeddings()\n",
+    "docs = [\n",
+    "    Document(\n",
+    "        page_content=plugin.description_for_model,\n",
+    "        metadata={\"plugin_name\": plugin.name_for_model},\n",
+    "    )\n",
+    "    for plugin in AI_PLUGINS\n",
+    "]\n",
+    "vector_store = FAISS.from_documents(docs, embeddings)\n",
+    "toolkits_dict = {\n",
+    "    plugin.name_for_model: NLAToolkit.from_llm_and_ai_plugin(llm, plugin)\n",
+    "    for plugin in AI_PLUGINS\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "735a7566",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "retriever = vector_store.as_retriever()\n",
+    "\n",
+    "\n",
+    "def get_tools(query):\n",
+    "    # Get documents, which contain the Plugins to use\n",
+    "    docs = retriever.get_relevant_documents(query)\n",
+    "    # Get the toolkits, one for each plugin\n",
+    "    tool_kits = [toolkits_dict[d.metadata[\"plugin_name\"]] for d in docs]\n",
+    "    # Get the tools: a separate NLAChain for each endpoint\n",
+    "    tools = []\n",
+    "    for tk in tool_kits:\n",
+    "        tools.extend(tk.nla_tools)\n",
+    "    return tools"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7699afd7",
+   "metadata": {},
+   "source": [
+    "We can now test this retriever to see if it seems to work."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "425f2886",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['Milo.askMilo',\n",
+       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.search_all_actions',\n",
+       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.preview_a_zap',\n",
+       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.get_configuration_link',\n",
+       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.list_exposed_actions',\n",
+       " 'SchoolDigger_API_V2.0.Autocomplete_GetSchools',\n",
+       " 'SchoolDigger_API_V2.0.Districts_GetAllDistricts2',\n",
+       " 'SchoolDigger_API_V2.0.Districts_GetDistrict2',\n",
+       " 'SchoolDigger_API_V2.0.Rankings_GetSchoolRank2',\n",
+       " 'SchoolDigger_API_V2.0.Rankings_GetRank_District',\n",
+       " 'SchoolDigger_API_V2.0.Schools_GetAllSchools20',\n",
+       " 'SchoolDigger_API_V2.0.Schools_GetSchool20',\n",
+       " 'Speak.translate',\n",
+       " 'Speak.explainPhrase',\n",
+       " 'Speak.explainTask']"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "tools = get_tools(\"What could I do today with my kiddo\")\n",
+    "[t.name for t in tools]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "3aa88768",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['Open_AI_Klarna_product_Api.productsUsingGET',\n",
+       " 'Milo.askMilo',\n",
+       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.search_all_actions',\n",
+       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.preview_a_zap',\n",
+       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.get_configuration_link',\n",
+       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.list_exposed_actions',\n",
+       " 'SchoolDigger_API_V2.0.Autocomplete_GetSchools',\n",
+       " 'SchoolDigger_API_V2.0.Districts_GetAllDistricts2',\n",
+       " 'SchoolDigger_API_V2.0.Districts_GetDistrict2',\n",
+       " 'SchoolDigger_API_V2.0.Rankings_GetSchoolRank2',\n",
+       " 'SchoolDigger_API_V2.0.Rankings_GetRank_District',\n",
+       " 'SchoolDigger_API_V2.0.Schools_GetAllSchools20',\n",
+       " 'SchoolDigger_API_V2.0.Schools_GetSchool20']"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "tools = get_tools(\"what shirts can i buy?\")\n",
+    "[t.name for t in tools]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2e7a075c",
+   "metadata": {},
+   "source": [
+    "## Prompt Template\n",
+    "\n",
+    "The prompt template is pretty standard, because we're not actually changing that much logic in the actual prompt template, but rather we are just changing how retrieval is done."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "339b1bb8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Set up the base template\n",
+    "template = \"\"\"Answer the following questions as best you can, but speaking as a pirate might speak. You have access to the following tools:\n",
+    "\n",
+    "{tools}\n",
+    "\n",
+    "Use the following format:\n",
+    "\n",
+    "Question: the input question you must answer\n",
+    "Thought: you should always think about what to do\n",
+    "Action: the action to take, should be one of [{tool_names}]\n",
+    "Action Input: the input to the action\n",
+    "Observation: the result of the action\n",
+    "... (this Thought/Action/Action Input/Observation can repeat N times)\n",
+    "Thought: I now know the final answer\n",
+    "Final Answer: the final answer to the original input question\n",
+    "\n",
+    "Begin! Remember to speak as a pirate when giving your final answer. Use lots of \"Arg\"s\n",
+    "\n",
+    "Question: {input}\n",
+    "{agent_scratchpad}\"\"\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1583acdc",
+   "metadata": {},
+   "source": [
+    "The custom prompt template now has the concept of a tools_getter, which we call on the input to select the tools to use"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "fd969d31",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from typing import Callable\n",
+    "\n",
+    "\n",
+    "# Set up a prompt template\n",
+    "class CustomPromptTemplate(StringPromptTemplate):\n",
+    "    # The template to use\n",
+    "    template: str\n",
+    "    ############## NEW ######################\n",
+    "    # The list of tools available\n",
+    "    tools_getter: Callable\n",
+    "\n",
+    "    def format(self, **kwargs) -> str:\n",
+    "        # Get the intermediate steps (AgentAction, Observation tuples)\n",
+    "        # Format them in a particular way\n",
+    "        intermediate_steps = kwargs.pop(\"intermediate_steps\")\n",
+    "        thoughts = \"\"\n",
+    "        for action, observation in intermediate_steps:\n",
+    "            thoughts += action.log\n",
+    "            thoughts += f\"\\nObservation: {observation}\\nThought: \"\n",
+    "        # Set the agent_scratchpad variable to that value\n",
+    "        kwargs[\"agent_scratchpad\"] = thoughts\n",
+    "        ############## NEW ######################\n",
+    "        tools = self.tools_getter(kwargs[\"input\"])\n",
+    "        # Create a tools variable from the list of tools provided\n",
+    "        kwargs[\"tools\"] = \"\\n\".join(\n",
+    "            [f\"{tool.name}: {tool.description}\" for tool in tools]\n",
+    "        )\n",
+    "        # Create a list of tool names for the tools provided\n",
+    "        kwargs[\"tool_names\"] = \", \".join([tool.name for tool in tools])\n",
+    "        return self.template.format(**kwargs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "798ef9fb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prompt = CustomPromptTemplate(\n",
+    "    template=template,\n",
+    "    tools_getter=get_tools,\n",
+    "    # This omits the `agent_scratchpad`, `tools`, and `tool_names` variables because those are generated dynamically\n",
+    "    # This includes the `intermediate_steps` variable because that is needed\n",
+    "    input_variables=[\"input\", \"intermediate_steps\"],\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ef3a1af3",
+   "metadata": {},
+   "source": [
+    "## Output Parser\n",
+    "\n",
+    "The output parser is unchanged from the previous notebook, since we are not changing anything about the output format."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "7c6fe0d3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class CustomOutputParser(AgentOutputParser):\n",
+    "    def parse(self, llm_output: str) -> Union[AgentAction, AgentFinish]:\n",
+    "        # Check if agent should finish\n",
+    "        if \"Final Answer:\" in llm_output:\n",
+    "            return AgentFinish(\n",
+    "                # Return values is generally always a dictionary with a single `output` key\n",
+    "                # It is not recommended to try anything else at the moment :)\n",
+    "                return_values={\"output\": llm_output.split(\"Final Answer:\")[-1].strip()},\n",
+    "                log=llm_output,\n",
+    "            )\n",
+    "        # Parse out the action and action input\n",
+    "        regex = r\"Action\\s*\\d*\\s*:(.*?)\\nAction\\s*\\d*\\s*Input\\s*\\d*\\s*:[\\s]*(.*)\"\n",
+    "        match = re.search(regex, llm_output, re.DOTALL)\n",
+    "        if not match:\n",
+    "            raise ValueError(f\"Could not parse LLM output: `{llm_output}`\")\n",
+    "        action = match.group(1).strip()\n",
+    "        action_input = match.group(2)\n",
+    "        # Return the action and action input\n",
+    "        return AgentAction(\n",
+    "            tool=action, tool_input=action_input.strip(\" \").strip('\"'), log=llm_output\n",
+    "        )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "d278706a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "output_parser = CustomOutputParser()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "170587b1",
+   "metadata": {},
+   "source": [
+    "## Set up LLM, stop sequence, and the agent\n",
+    "\n",
+    "Also the same as the previous notebook"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "f9d4c374",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = OpenAI(temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "9b1cc2a2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# LLM chain consisting of the LLM and a prompt\n",
+    "llm_chain = LLMChain(llm=llm, prompt=prompt)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "e4f5092f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tool_names = [tool.name for tool in tools]\n",
+    "agent = LLMSingleActionAgent(\n",
+    "    llm_chain=llm_chain,\n",
+    "    output_parser=output_parser,\n",
+    "    stop=[\"\\nObservation:\"],\n",
+    "    allowed_tools=tool_names,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "aa8a5326",
+   "metadata": {},
+   "source": [
+    "## Use the Agent\n",
+    "\n",
+    "Now we can use it!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "490604e9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "agent_executor = AgentExecutor.from_agent_and_tools(\n",
+    "    agent=agent, tools=tools, verbose=True\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "653b1617",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: I need to find a product API\n",
+      "Action: Open_AI_Klarna_product_Api.productsUsingGET\n",
+      "Action Input: shirts\u001b[0m\n",
+      "\n",
+      "Observation:\u001b[36;1m\u001b[1;3mI found 10 shirts from the API response. They range in price from $9.99 to $450.00 and come in a variety of materials, colors, and patterns.\u001b[0m\u001b[32;1m\u001b[1;3m I now know what shirts I can buy\n",
+      "Final Answer: Arg, I found 10 shirts from the API response. They range in price from $9.99 to $450.00 and come in a variety of materials, colors, and patterns.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'Arg, I found 10 shirts from the API response. They range in price from $9.99 to $450.00 and come in a variety of materials, colors, and patterns.'"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent_executor.run(\"what shirts can i buy?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2481ee76",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.3"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "3ccef4e08d87aa1eeb90f63e0f071292ccb2e9c42e70f74ab2bf6f5493ca7bbc"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

cookbook/databricks_sql_db.ipynb

@@ -0,0 +1,273 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "707d13a7",
+   "metadata": {},
+   "source": [
+    "# Databricks\n",
+    "\n",
+    "This notebook covers how to connect to the [Databricks runtimes](https://docs.databricks.com/runtime/index.html) and [Databricks SQL](https://www.databricks.com/product/databricks-sql) using the SQLDatabase wrapper of LangChain.\n",
+    "It is broken into 3 parts: installation and setup, connecting to Databricks, and examples."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0076d072",
+   "metadata": {},
+   "source": [
+    "## Installation and Setup"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "739b489b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install databricks-sql-connector"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "73113163",
+   "metadata": {},
+   "source": [
+    "## Connecting to Databricks\n",
+    "\n",
+    "You can connect to [Databricks runtimes](https://docs.databricks.com/runtime/index.html) and [Databricks SQL](https://www.databricks.com/product/databricks-sql) using the `SQLDatabase.from_databricks()` method.\n",
+    "\n",
+    "### Syntax\n",
+    "```python\n",
+    "SQLDatabase.from_databricks(\n",
+    "    catalog: str,\n",
+    "    schema: str,\n",
+    "    host: Optional[str] = None,\n",
+    "    api_token: Optional[str] = None,\n",
+    "    warehouse_id: Optional[str] = None,\n",
+    "    cluster_id: Optional[str] = None,\n",
+    "    engine_args: Optional[dict] = None,\n",
+    "    **kwargs: Any)\n",
+    "```\n",
+    "### Required Parameters\n",
+    "* `catalog`: The catalog name in the Databricks database.\n",
+    "* `schema`: The schema name in the catalog.\n",
+    "\n",
+    "### Optional Parameters\n",
+    "There following parameters are optional. When executing the method in a Databricks notebook, you don't need to provide them in most of the cases.\n",
+    "* `host`: The Databricks workspace hostname, excluding 'https://' part. Defaults to 'DATABRICKS_HOST' environment variable or current workspace if in a Databricks notebook.\n",
+    "* `api_token`: The Databricks personal access token for accessing the Databricks SQL warehouse or the cluster. Defaults to 'DATABRICKS_TOKEN' environment variable or a temporary one is generated if in a Databricks notebook.\n",
+    "* `warehouse_id`: The warehouse ID in the Databricks SQL.\n",
+    "* `cluster_id`: The cluster ID in the Databricks Runtime. If running in a Databricks notebook and both 'warehouse_id' and 'cluster_id' are None, it uses the ID of the cluster the notebook is attached to.\n",
+    "* `engine_args`: The arguments to be used when connecting Databricks.\n",
+    "* `**kwargs`: Additional keyword arguments for the `SQLDatabase.from_uri` method."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b11c7e48",
+   "metadata": {},
+   "source": [
+    "## Examples"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "8102bca0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Connecting to Databricks with SQLDatabase wrapper\n",
+    "from langchain.utilities import SQLDatabase\n",
+    "\n",
+    "db = SQLDatabase.from_databricks(catalog=\"samples\", schema=\"nyctaxi\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "9dd36f58",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Creating a OpenAI Chat LLM wrapper\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "\n",
+    "llm = ChatOpenAI(temperature=0, model_name=\"gpt-4\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5b5c5f1a",
+   "metadata": {},
+   "source": [
+    "### SQL Chain example\n",
+    "\n",
+    "This example demonstrates the use of the [SQL Chain](https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html) for answering a question over a Databricks database."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "36f2270b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.utilities import SQLDatabaseChain\n",
+    "\n",
+    "db_chain = SQLDatabaseChain.from_llm(llm, db, verbose=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "4e2b5f25",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new SQLDatabaseChain chain...\u001b[0m\n",
+      "What is the average duration of taxi rides that start between midnight and 6am?\n",
+      "SQLQuery:\u001b[32;1m\u001b[1;3mSELECT AVG(UNIX_TIMESTAMP(tpep_dropoff_datetime) - UNIX_TIMESTAMP(tpep_pickup_datetime)) as avg_duration\n",
+      "FROM trips\n",
+      "WHERE HOUR(tpep_pickup_datetime) >= 0 AND HOUR(tpep_pickup_datetime) < 6\u001b[0m\n",
+      "SQLResult: \u001b[33;1m\u001b[1;3m[(987.8122786304605,)]\u001b[0m\n",
+      "Answer:\u001b[32;1m\u001b[1;3mThe average duration of taxi rides that start between midnight and 6am is 987.81 seconds.\u001b[0m\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'The average duration of taxi rides that start between midnight and 6am is 987.81 seconds.'"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "db_chain.run(\n",
+    "    \"What is the average duration of taxi rides that start between midnight and 6am?\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e496d5e5",
+   "metadata": {},
+   "source": [
+    "### SQL Database Agent example\n",
+    "\n",
+    "This example demonstrates the use of the [SQL Database Agent](/docs/integrations/toolkits/sql_database.html) for answering questions over a Databricks database."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "9918e86a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.agents import create_sql_agent\n",
+    "from langchain.agents.agent_toolkits import SQLDatabaseToolkit\n",
+    "\n",
+    "toolkit = SQLDatabaseToolkit(db=db, llm=llm)\n",
+    "agent = create_sql_agent(llm=llm, toolkit=toolkit, verbose=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "c484a76e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mAction: list_tables_sql_db\n",
+      "Action Input: \u001b[0m\n",
+      "Observation: \u001b[38;5;200m\u001b[1;3mtrips\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3mI should check the schema of the trips table to see if it has the necessary columns for trip distance and duration.\n",
+      "Action: schema_sql_db\n",
+      "Action Input: trips\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3m\n",
+      "CREATE TABLE trips (\n",
+      "\ttpep_pickup_datetime TIMESTAMP, \n",
+      "\ttpep_dropoff_datetime TIMESTAMP, \n",
+      "\ttrip_distance FLOAT, \n",
+      "\tfare_amount FLOAT, \n",
+      "\tpickup_zip INT, \n",
+      "\tdropoff_zip INT\n",
+      ") USING DELTA\n",
+      "\n",
+      "/*\n",
+      "3 rows from trips table:\n",
+      "tpep_pickup_datetime\ttpep_dropoff_datetime\ttrip_distance\tfare_amount\tpickup_zip\tdropoff_zip\n",
+      "2016-02-14 16:52:13+00:00\t2016-02-14 17:16:04+00:00\t4.94\t19.0\t10282\t10171\n",
+      "2016-02-04 18:44:19+00:00\t2016-02-04 18:46:00+00:00\t0.28\t3.5\t10110\t10110\n",
+      "2016-02-17 17:13:57+00:00\t2016-02-17 17:17:55+00:00\t0.7\t5.0\t10103\t10023\n",
+      "*/\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3mThe trips table has the necessary columns for trip distance and duration. I will write a query to find the longest trip distance and its duration.\n",
+      "Action: query_checker_sql_db\n",
+      "Action Input: SELECT trip_distance, tpep_dropoff_datetime - tpep_pickup_datetime as duration FROM trips ORDER BY trip_distance DESC LIMIT 1\u001b[0m\n",
+      "Observation: \u001b[31;1m\u001b[1;3mSELECT trip_distance, tpep_dropoff_datetime - tpep_pickup_datetime as duration FROM trips ORDER BY trip_distance DESC LIMIT 1\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3mThe query is correct. I will now execute it to find the longest trip distance and its duration.\n",
+      "Action: query_sql_db\n",
+      "Action Input: SELECT trip_distance, tpep_dropoff_datetime - tpep_pickup_datetime as duration FROM trips ORDER BY trip_distance DESC LIMIT 1\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3m[(30.6, '0 00:43:31.000000000')]\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3mI now know the final answer.\n",
+      "Final Answer: The longest trip distance is 30.6 miles and it took 43 minutes and 31 seconds.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'The longest trip distance is 30.6 miles and it took 43 minutes and 31 seconds.'"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent.run(\"What is the longest trip distance and how long did it take?\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

cookbook/deeplake_semantic_search_over_chat.ipynb

@@ -0,0 +1,257 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# QA using Activeloop's DeepLake\n",
+    "In this tutorial, we are going to use Langchain + Activeloop's Deep Lake with GPT4 to semantically search and ask questions over a group chat.\n",
+    "\n",
+    "View a working demo [here](https://twitter.com/thisissukh_/status/1647223328363679745)"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 1. Install required packages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!python3 -m pip install --upgrade langchain 'deeplake[enterprise]' openai tiktoken"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 2. Add API keys"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import getpass\n",
+    "from langchain.document_loaders import PyPDFLoader, TextLoader\n",
+    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
+    "from langchain.text_splitter import (\n",
+    "    RecursiveCharacterTextSplitter,\n",
+    "    CharacterTextSplitter,\n",
+    ")\n",
+    "from langchain.vectorstores import DeepLake\n",
+    "from langchain.chains import ConversationalRetrievalChain, RetrievalQA\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.llms import OpenAI\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
+    "activeloop_token = getpass.getpass(\"Activeloop Token:\")\n",
+    "os.environ[\"ACTIVELOOP_TOKEN\"] = activeloop_token\n",
+    "os.environ[\"ACTIVELOOP_ORG\"] = getpass.getpass(\"Activeloop Org:\")\n",
+    "\n",
+    "org_id = os.environ[\"ACTIVELOOP_ORG\"]\n",
+    "embeddings = OpenAIEmbeddings()\n",
+    "\n",
+    "dataset_path = \"hub://\" + org_id + \"/data\""
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "\n",
+    "\n",
+    "## 2. Create sample data"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "You can generate a sample group chat conversation using ChatGPT with this prompt:\n",
+    "\n",
+    "```\n",
+    "Generate a group chat conversation with three friends talking about their day, referencing real places and fictional names. Make it funny and as detailed as possible.\n",
+    "```\n",
+    "\n",
+    "I've already generated such a chat in `messages.txt`. We can keep it simple and use this for our example.\n",
+    "\n",
+    "## 3. Ingest chat embeddings\n",
+    "\n",
+    "We load the messages in the text file, chunk and upload to ActiveLoop Vector store."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[Document(page_content='Participants:\\n\\nJerry: Loves movies and is a bit of a klutz.\\nSamantha: Enthusiastic about food and always trying new restaurants.\\nBarry: A nature lover, but always manages to get lost.\\nJerry: Hey, guys! You won\\'t believe what happened to me at the Times Square AMC theater. I tripped over my own feet and spilled popcorn everywhere! 🍿💥\\n\\nSamantha: LOL, that\\'s so you, Jerry! Was the floor buttery enough for you to ice skate on after that? 😂\\n\\nBarry: Sounds like a regular Tuesday for you, Jerry. Meanwhile, I tried to find that new hiking trail in Central Park. You know, the one that\\'s supposed to be impossible to get lost on? Well, guess what...\\n\\nJerry: You found a hidden treasure?\\n\\nBarry: No, I got lost. AGAIN. 🧭🙄\\n\\nSamantha: Barry, you\\'d get lost in your own backyard! But speaking of treasures, I found this new sushi place in Little Tokyo. \"Samantha\\'s Sushi Symphony\" it\\'s called. Coincidence? I think not!\\n\\nJerry: Maybe they named it after your ability to eat your body weight in sushi. 🍣', metadata={}), Document(page_content='Barry: How do you even FIND all these places, Samantha?\\n\\nSamantha: Simple, I don\\'t rely on Barry\\'s navigation skills. 😉 But seriously, the wasabi there was hotter than Jerry\\'s love for Marvel movies!\\n\\nJerry: Hey, nothing wrong with a little superhero action. By the way, did you guys see the new \"Captain Crunch: Breakfast Avenger\" trailer?\\n\\nSamantha: Captain Crunch? Are you sure you didn\\'t get that from one of your Saturday morning cereal binges?\\n\\nBarry: Yeah, and did he defeat his arch-enemy, General Mills? 😆\\n\\nJerry: Ha-ha, very funny. Anyway, that sushi place sounds awesome, Samantha. Next time, let\\'s go together, and maybe Barry can guide us... if we want a city-wide tour first.\\n\\nBarry: As long as we\\'re not hiking, I\\'ll get us there... eventually. 😅\\n\\nSamantha: It\\'s a date! But Jerry, you\\'re banned from carrying any food items.\\n\\nJerry: Deal! Just promise me no wasabi challenges. I don\\'t want to end up like the time I tried Sriracha ice cream.', metadata={}), Document(page_content=\"Barry: Wait, what happened with Sriracha ice cream?\\n\\nJerry: Let's just say it was a hot situation. Literally. 🔥\\n\\nSamantha: 🤣 I still have the video!\\n\\nJerry: Samantha, if you value our friendship, that video will never see the light of day.\\n\\nSamantha: No promises, Jerry. No promises. 🤐😈\\n\\nBarry: I foresee a fun weekend ahead! 🎉\", metadata={})]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Your Deep Lake dataset has been successfully created!\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\\"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Dataset(path='hub://adilkhan/data', tensors=['embedding', 'id', 'metadata', 'text'])\n",
+      "\n",
+      "  tensor      htype      shape     dtype  compression\n",
+      "  -------    -------    -------   -------  ------- \n",
+      " embedding  embedding  (3, 1536)  float32   None   \n",
+      "    id        text      (3, 1)      str     None   \n",
+      " metadata     json      (3, 1)      str     None   \n",
+      "   text       text      (3, 1)      str     None   \n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " \r"
+     ]
+    }
+   ],
+   "source": [
+    "with open(\"messages.txt\") as f:\n",
+    "    state_of_the_union = f.read()\n",
+    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
+    "pages = text_splitter.split_text(state_of_the_union)\n",
+    "\n",
+    "text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)\n",
+    "texts = text_splitter.create_documents(pages)\n",
+    "\n",
+    "print(texts)\n",
+    "\n",
+    "dataset_path = \"hub://\" + org_id + \"/data\"\n",
+    "embeddings = OpenAIEmbeddings()\n",
+    "db = DeepLake.from_documents(\n",
+    "    texts, embeddings, dataset_path=dataset_path, overwrite=True\n",
+    ")"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "`Optional`: You can also use Deep Lake's Managed Tensor Database as a hosting service and run queries there. In order to do so, it is necessary to specify the runtime parameter as {'tensor_db': True} during the creation of the vector store. This configuration enables the execution of queries on the Managed Tensor Database, rather than on the client side. It should be noted that this functionality is not applicable to datasets stored locally or in-memory. In the event that a vector store has already been created outside of the Managed Tensor Database, it is possible to transfer it to the Managed Tensor Database by following the prescribed steps."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# with open(\"messages.txt\") as f:\n",
+    "#     state_of_the_union = f.read()\n",
+    "# text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
+    "# pages = text_splitter.split_text(state_of_the_union)\n",
+    "\n",
+    "# text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)\n",
+    "# texts = text_splitter.create_documents(pages)\n",
+    "\n",
+    "# print(texts)\n",
+    "\n",
+    "# dataset_path = \"hub://\" + org + \"/data\"\n",
+    "# embeddings = OpenAIEmbeddings()\n",
+    "# db = DeepLake.from_documents(\n",
+    "#     texts, embeddings, dataset_path=dataset_path, overwrite=True, runtime={\"tensor_db\": True}\n",
+    "# )"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 4. Ask questions\n",
+    "\n",
+    "Now we can ask a question and get an answer back with a semantic search:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "db = DeepLake(dataset_path=dataset_path, read_only=True, embedding=embeddings)\n",
+    "\n",
+    "retriever = db.as_retriever()\n",
+    "retriever.search_kwargs[\"distance_metric\"] = \"cos\"\n",
+    "retriever.search_kwargs[\"k\"] = 4\n",
+    "\n",
+    "qa = RetrievalQA.from_chain_type(\n",
+    "    llm=OpenAI(), chain_type=\"stuff\", retriever=retriever, return_source_documents=False\n",
+    ")\n",
+    "\n",
+    "# What was the restaurant the group was talking about called?\n",
+    "query = input(\"Enter query:\")\n",
+    "\n",
+    "# The Hungry Lobster\n",
+    "ans = qa({\"query\": query})\n",
+    "\n",
+    "print(ans)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

cookbook/elasticsearch_db_qa.ipynb

@@ -0,0 +1,158 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Elasticsearch\n",
+    "\n",
+    "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/docs/use_cases/qa_structured/integrations/elasticsearch.ipynb)\n",
+    "\n",
+    "We can use LLMs to interact with Elasticsearch analytics databases in natural language.\n",
+    "\n",
+    "This chain builds search queries via the Elasticsearch DSL API (filters and aggregations).\n",
+    "\n",
+    "The Elasticsearch client must have permissions for index listing, mapping description and search queries.\n",
+    "\n",
+    "See [here](https://www.elastic.co/guide/en/elasticsearch/reference/current/docker.html) for instructions on how to run Elasticsearch locally."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "! pip install langchain langchain-experimental openai elasticsearch\n",
+    "\n",
+    "# Set env var OPENAI_API_KEY or load from a .env file\n",
+    "# import dotenv\n",
+    "\n",
+    "# dotenv.load_dotenv()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from elasticsearch import Elasticsearch\n",
+    "\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.chains.elasticsearch_database import ElasticsearchDatabaseChain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Initialize Elasticsearch python client.\n",
+    "# See https://elasticsearch-py.readthedocs.io/en/v8.8.2/api.html#elasticsearch.Elasticsearch\n",
+    "ELASTIC_SEARCH_SERVER = \"https://elastic:pass@localhost:9200\"\n",
+    "db = Elasticsearch(ELASTIC_SEARCH_SERVER)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Uncomment the next cell to initially populate your db."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# customers = [\n",
+    "#     {\"firstname\": \"Jennifer\", \"lastname\": \"Walters\"},\n",
+    "#     {\"firstname\": \"Monica\",\"lastname\":\"Rambeau\"},\n",
+    "#     {\"firstname\": \"Carol\",\"lastname\":\"Danvers\"},\n",
+    "#     {\"firstname\": \"Wanda\",\"lastname\":\"Maximoff\"},\n",
+    "#     {\"firstname\": \"Jennifer\",\"lastname\":\"Takeda\"},\n",
+    "# ]\n",
+    "# for i, customer in enumerate(customers):\n",
+    "#     db.create(index=\"customers\", document=customer, id=i)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = ChatOpenAI(model_name=\"gpt-4\", temperature=0)\n",
+    "chain = ElasticsearchDatabaseChain.from_llm(llm=llm, database=db, verbose=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "question = \"What are the first names of all the customers?\"\n",
+    "chain.run(question)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We can customize the prompt."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chains.elasticsearch_database.prompts import DEFAULT_DSL_TEMPLATE\n",
+    "from langchain.prompts.prompt import PromptTemplate\n",
+    "\n",
+    "PROMPT_TEMPLATE = \"\"\"Given an input question, create a syntactically correct Elasticsearch query to run. Unless the user specifies in their question a specific number of examples they wish to obtain, always limit your query to at most {top_k} results. You can order the results by a relevant column to return the most interesting examples in the database.\n",
+    "\n",
+    "Unless told to do not query for all the columns from a specific index, only ask for a the few relevant columns given the question.\n",
+    "\n",
+    "Pay attention to use only the column names that you can see in the mapping description. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which index. Return the query as valid json.\n",
+    "\n",
+    "Use the following format:\n",
+    "\n",
+    "Question: Question here\n",
+    "ESQuery: Elasticsearch Query formatted as json\n",
+    "\"\"\"\n",
+    "\n",
+    "PROMPT = PromptTemplate.from_template(\n",
+    "    PROMPT_TEMPLATE,\n",
+    ")\n",
+    "chain = ElasticsearchDatabaseChain.from_llm(llm=llm, database=db, query_prompt=PROMPT)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

cookbook/forward_looking_retrieval_augmented_generation.ipynb

@@ -0,0 +1,497 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "0f0b9afa",
+   "metadata": {},
+   "source": [
+    "# Retrieve as you generate with FLARE\n",
+    "\n",
+    "This notebook is an implementation of Forward-Looking Active REtrieval augmented generation (FLARE).\n",
+    "\n",
+    "Please see the original repo [here](https://github.com/jzbjyb/FLARE/tree/main).\n",
+    "\n",
+    "The basic idea is:\n",
+    "\n",
+    "- Start answering a question\n",
+    "- If you start generating tokens the model is uncertain about, look up relevant documents\n",
+    "- Use those documents to continue generating\n",
+    "- Repeat until finished\n",
+    "\n",
+    "There is a lot of cool detail in how the lookup of relevant documents is done.\n",
+    "Basically, the tokens that model is uncertain about are highlighted, and then an LLM is called to generate a question that would lead to that answer. For example, if the generated text is `Joe Biden went to Harvard`, and the tokens the model was uncertain about was `Harvard`, then a good generated question would be `where did Joe Biden go to college`. This generated question is then used in a retrieval step to fetch relevant documents.\n",
+    "\n",
+    "In order to set up this chain, we will need three things:\n",
+    "\n",
+    "- An LLM to generate the answer\n",
+    "- An LLM to generate hypothetical questions to use in retrieval\n",
+    "- A retriever to use to look up answers for\n",
+    "\n",
+    "The LLM that we use to generate the answer needs to return logprobs so we can identify uncertain tokens. For that reason, we HIGHLY recommend that you use the OpenAI wrapper (NB: not the ChatOpenAI wrapper, as that does not return logprobs).\n",
+    "\n",
+    "The LLM we use to generate hypothetical questions to use in retrieval can be anything. In this notebook we will use ChatOpenAI because it is fast and cheap.\n",
+    "\n",
+    "The retriever can be anything. In this notebook we will use [SERPER](https://serper.dev/) search engine, because it is cheap.\n",
+    "\n",
+    "Other important parameters to understand:\n",
+    "\n",
+    "- `max_generation_len`: The maximum number of tokens to generate before stopping to check if any are uncertain\n",
+    "- `min_prob`: Any tokens generated with probability below this will be considered uncertain"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a7e4b63d",
+   "metadata": {},
+   "source": [
+    "## Imports"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "042bb161",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"SERPER_API_KEY\"] = \"\"os.environ[\"OPENAI_API_KEY\"] = \"\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "a7888f4a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import re\n",
+    "\n",
+    "import numpy as np\n",
+    "\n",
+    "from langchain.schema import BaseRetriever\n",
+    "from langchain.callbacks.manager import (\n",
+    "    AsyncCallbackManagerForRetrieverRun,\n",
+    "    CallbackManagerForRetrieverRun,\n",
+    ")\n",
+    "from langchain.utilities import GoogleSerperAPIWrapper\n",
+    "from langchain.embeddings import OpenAIEmbeddings\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.llms import OpenAI\n",
+    "from langchain.schema import Document\n",
+    "from typing import Any, List"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5f552dce",
+   "metadata": {},
+   "source": [
+    "## Retriever"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "59c7d875",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class SerperSearchRetriever(BaseRetriever):\n",
+    "    search: GoogleSerperAPIWrapper = None\n",
+    "\n",
+    "    def _get_relevant_documents(\n",
+    "        self, query: str, *, run_manager: CallbackManagerForRetrieverRun, **kwargs: Any\n",
+    "    ) -> List[Document]:\n",
+    "        return [Document(page_content=self.search.run(query))]\n",
+    "\n",
+    "    async def _aget_relevant_documents(\n",
+    "        self,\n",
+    "        query: str,\n",
+    "        *,\n",
+    "        run_manager: AsyncCallbackManagerForRetrieverRun,\n",
+    "        **kwargs: Any,\n",
+    "    ) -> List[Document]:\n",
+    "        raise NotImplementedError()\n",
+    "\n",
+    "\n",
+    "retriever = SerperSearchRetriever(search=GoogleSerperAPIWrapper())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "92478194",
+   "metadata": {},
+   "source": [
+    "## FLARE Chain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "577e7c2c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# We set this so we can see what exactly is going on\n",
+    "from langchain.globals import set_verbose\n",
+    "\n",
+    "set_verbose(True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "300d783e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chains import FlareChain\n",
+    "\n",
+    "flare = FlareChain.from_llm(\n",
+    "    ChatOpenAI(temperature=0),\n",
+    "    retriever=retriever,\n",
+    "    max_generation_len=164,\n",
+    "    min_prob=0.3,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "1f3d5e90",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query = \"explain in great detail the difference between the langchain framework and baby agi\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "4b1bfa8c",
+   "metadata": {
+    "scrolled": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new FlareChain chain...\u001b[0m\n",
+      "\u001b[36;1m\u001b[1;3mCurrent Response: \u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3mRespond to the user message using any relevant context. If context is provided, you should ground your answer in that context. Once you're done responding return FINISHED.\n",
+      "\n",
+      ">>> CONTEXT: \n",
+      ">>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi\n",
+      ">>> RESPONSE: \u001b[0m\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new QuestionGeneratorChain chain...\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
+      "\n",
+      ">>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi\n",
+      ">>> EXISTING PARTIAL RESPONSE:  \n",
+      "The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing for secure and transparent data sharing. The Langchain Framework also provides a set of tools and services to help developers create and deploy NLP applications.\n",
+      "\n",
+      "Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, including natural language processing.\n",
+      "\n",
+      "In summary, the Langchain Framework is a platform for NLP applications, while Baby AGI is an AI system designed for\n",
+      "\n",
+      "The question to which the answer is the term/entity/phrase \" decentralized platform for natural language processing\" is:\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
+      "\n",
+      ">>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi\n",
+      ">>> EXISTING PARTIAL RESPONSE:  \n",
+      "The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing for secure and transparent data sharing. The Langchain Framework also provides a set of tools and services to help developers create and deploy NLP applications.\n",
+      "\n",
+      "Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, including natural language processing.\n",
+      "\n",
+      "In summary, the Langchain Framework is a platform for NLP applications, while Baby AGI is an AI system designed for\n",
+      "\n",
+      "The question to which the answer is the term/entity/phrase \" uses a blockchain\" is:\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
+      "\n",
+      ">>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi\n",
+      ">>> EXISTING PARTIAL RESPONSE:  \n",
+      "The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing for secure and transparent data sharing. The Langchain Framework also provides a set of tools and services to help developers create and deploy NLP applications.\n",
+      "\n",
+      "Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, including natural language processing.\n",
+      "\n",
+      "In summary, the Langchain Framework is a platform for NLP applications, while Baby AGI is an AI system designed for\n",
+      "\n",
+      "The question to which the answer is the term/entity/phrase \" distributed ledger to\" is:\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
+      "\n",
+      ">>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi\n",
+      ">>> EXISTING PARTIAL RESPONSE:  \n",
+      "The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing for secure and transparent data sharing. The Langchain Framework also provides a set of tools and services to help developers create and deploy NLP applications.\n",
+      "\n",
+      "Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, including natural language processing.\n",
+      "\n",
+      "In summary, the Langchain Framework is a platform for NLP applications, while Baby AGI is an AI system designed for\n",
+      "\n",
+      "The question to which the answer is the term/entity/phrase \" process data, allowing for secure and transparent data sharing.\" is:\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
+      "\n",
+      ">>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi\n",
+      ">>> EXISTING PARTIAL RESPONSE:  \n",
+      "The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing for secure and transparent data sharing. The Langchain Framework also provides a set of tools and services to help developers create and deploy NLP applications.\n",
+      "\n",
+      "Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, including natural language processing.\n",
+      "\n",
+      "In summary, the Langchain Framework is a platform for NLP applications, while Baby AGI is an AI system designed for\n",
+      "\n",
+      "The question to which the answer is the term/entity/phrase \" set of tools\" is:\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
+      "\n",
+      ">>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi\n",
+      ">>> EXISTING PARTIAL RESPONSE:  \n",
+      "The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing for secure and transparent data sharing. The Langchain Framework also provides a set of tools and services to help developers create and deploy NLP applications.\n",
+      "\n",
+      "Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, including natural language processing.\n",
+      "\n",
+      "In summary, the Langchain Framework is a platform for NLP applications, while Baby AGI is an AI system designed for\n",
+      "\n",
+      "The question to which the answer is the term/entity/phrase \" help developers create\" is:\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
+      "\n",
+      ">>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi\n",
+      ">>> EXISTING PARTIAL RESPONSE:  \n",
+      "The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing for secure and transparent data sharing. The Langchain Framework also provides a set of tools and services to help developers create and deploy NLP applications.\n",
+      "\n",
+      "Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, including natural language processing.\n",
+      "\n",
+      "In summary, the Langchain Framework is a platform for NLP applications, while Baby AGI is an AI system designed for\n",
+      "\n",
+      "The question to which the answer is the term/entity/phrase \" create an AI system\" is:\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
+      "\n",
+      ">>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi\n",
+      ">>> EXISTING PARTIAL RESPONSE:  \n",
+      "The Langchain Framework is a decentralized platform for natural language processing (NLP) applications. It uses a blockchain-based distributed ledger to store and process data, allowing for secure and transparent data sharing. The Langchain Framework also provides a set of tools and services to help developers create and deploy NLP applications.\n",
+      "\n",
+      "Baby AGI, on the other hand, is an artificial general intelligence (AGI) platform. It uses a combination of deep learning and reinforcement learning to create an AI system that can learn and adapt to new tasks. Baby AGI is designed to be a general-purpose AI system that can be used for a variety of applications, including natural language processing.\n",
+      "\n",
+      "In summary, the Langchain Framework is a platform for NLP applications, while Baby AGI is an AI system designed for\n",
+      "\n",
+      "The question to which the answer is the term/entity/phrase \" NLP applications\" is:\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\u001b[33;1m\u001b[1;3mGenerated Questions: ['What is the Langchain Framework?', 'What technology does the Langchain Framework use to store and process data for secure and transparent data sharing?', 'What technology does the Langchain Framework use to store and process data?', 'What does the Langchain Framework use a blockchain-based distributed ledger for?', 'What does the Langchain Framework provide in addition to a decentralized platform for natural language processing applications?', 'What set of tools and services does the Langchain Framework provide?', 'What is the purpose of Baby AGI?', 'What type of applications is the Langchain Framework designed for?']\u001b[0m\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new _OpenAIResponseChain chain...\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3mRespond to the user message using any relevant context. If context is provided, you should ground your answer in that context. Once you're done responding return FINISHED.\n",
+      "\n",
+      ">>> CONTEXT: LangChain: Software. LangChain is a software development framework designed to simplify the creation of applications using large language models. LangChain Initial release date: October 2022. LangChain Programming languages: Python and JavaScript. LangChain Developer(s): Harrison Chase. LangChain License: MIT License. LangChain is a framework for developing applications powered by language models. We believe that the most powerful and differentiated applications will not only ... Type: Software framework. At its core, LangChain is a framework built around LLMs. We can use it for chatbots, Generative Question-Answering (GQA), summarization, and much more. LangChain is a powerful tool that can be used to work with Large Language Models (LLMs). LLMs are very general in nature, which means that while they can ... LangChain is an intuitive framework created to assist in developing applications driven by a language model, such as OpenAI or Hugging Face. LangChain is a software development framework designed to simplify the creation of applications using large language models (LLMs). Written in: Python and JavaScript. Initial release: October 2022. LangChain - The A.I-native developer toolkit We started LangChain with the intent to build a modular and flexible framework for developing A.I- ... LangChain explained in 3 minutes - LangChain is a ... Duration: 3:03. Posted: Apr 13, 2023. LangChain is a framework built to help you build LLM-powered applications more easily by providing you with the following:. LangChain is a framework that enables quick and easy development of applications that make use of Large Language Models, for example, GPT-3. LangChain is a powerful open-source framework for developing applications powered by language models. It connects to the AI models you want to ...\n",
+      "\n",
+      "LangChain is a framework for including AI from large language models inside data pipelines and applications. This tutorial provides an overview of what you ... Missing: secure | Must include:secure. Blockchain is the best way to secure the data of the shared community. Utilizing the capabilities of the blockchain nobody can read or interfere ... This modern technology consists of a chain of blocks that allows to securely store all committed transactions using shared and distributed ... A Blockchain network is used in the healthcare system to preserve and exchange patient data through hospitals, diagnostic laboratories, pharmacy firms, and ... In this article, I will walk you through the process of using the LangChain.js library with Google Cloud Functions, helping you leverage the ... LangChain is an intuitive framework created to assist in developing applications driven by a language model, such as OpenAI or Hugging Face. Missing: transparent | Must include:transparent. This technology keeps a distributed ledger on each blockchain node, making it more secure and transparent. The blockchain network can operate smart ... blockchain technology can offer a highly secured health data ledger to ... framework can be employed to store encrypted healthcare data in a ... In a simplified way, Blockchain is a data structure that stores transactions in an ordered way and linked to the previous block, serving as a ... Blockchain technology is a decentralized, distributed ledger that stores the record of ownership of digital assets. Missing: Langchain | Must include:Langchain.\n",
+      "\n",
+      "LangChain is a framework for including AI from large language models inside data pipelines and applications. This tutorial provides an overview of what you ... LangChain is an intuitive framework created to assist in developing applications driven by a language model, such as OpenAI or Hugging Face. This documentation covers the steps to integrate Pinecone, a high-performance vector database, with LangChain, a framework for building applications powered ... The ability to connect to any model, ingest any custom database, and build upon a framework that can take action provides numerous use cases for ... With LangChain, developers can use a framework that abstracts the core building blocks of LLM applications. LangChain empowers developers to ... Build a question-answering tool based on financial data with LangChain & Deep Lake's unified & streamable data store. Browse applications built on LangChain technology. Explore PoC and MVP applications created by our community and discover innovative use cases for LangChain ... LangChain is a great framework that can be used for developing applications powered by LLMs. When you intend to enhance your application ... In this blog, we'll introduce you to LangChain and Ray Serve and how to use them to build a search engine using LLM embeddings and a vector ... The LinkChain Framework simplifies embedding creation and storage using Pinecone and Chroma, with code that loads files, splits documents, and creates embedding ... Missing: technology | Must include:technology.\n",
+      "\n",
+      "Blockchain is one type of a distributed ledger. Distributed ledgers use independent computers (referred to as nodes) to record, share and ... Missing: Langchain | Must include:Langchain. Blockchain is used in distributed storage software where huge data is broken down into chunks. This is available in encrypted data across a ... People sometimes use the terms 'Blockchain' and 'Distributed Ledger' interchangeably. This post aims to analyze the features of each. A distributed ledger ... Missing: Framework | Must include:Framework. Think of a “distributed ledger” that uses cryptography to allow each participant in the transaction to add to the ledger in a secure way without ... In this paper, we provide an overview of the history of trade settlement and discuss this nascent technology that may now transform traditional ... Missing: Langchain | Must include:Langchain. LangChain is a blockchain-based language education platform that aims to revolutionize the way people learn languages. Missing: Framework | Must include:Framework. It uses the distributed ledger technology framework and Smart contract engine for building scalable Business Blockchain applications. The fabric ... It looks at the assets the use case is handling, the different parties conducting transactions, and the smart contract, distributed ... Are you curious to know how Blockchain and Distributed ... Duration: 44:31. Posted: May 4, 2021. A blockchain is a distributed and immutable ledger to transfer ownership, record transactions, track assets, and ensure transparency, security, trust and value ... Missing: Langchain | Must include:Langchain.\n",
+      "\n",
+      "LangChain is an intuitive framework created to assist in developing applications driven by a language model, such as OpenAI or Hugging Face. Missing: decentralized | Must include:decentralized. LangChain, created by Harrison Chase, is a Python library that provides out-of-the-box support to build NLP applications using LLMs. Missing: decentralized | Must include:decentralized. LangChain provides a standard interface for chains, enabling developers to create sequences of calls that go beyond a single LLM call. Chains ... Missing: decentralized platform natural. LangChain is a powerful framework that simplifies the process of building advanced language model applications. Missing: platform | Must include:platform. Are your language models ignoring previous instructions ... Duration: 32:23. Posted: Feb 21, 2023. LangChain is a framework that enables quick and easy development of applications ... Prompting is the new way of programming NLP models. Missing: decentralized platform. It then uses natural language processing and machine learning algorithms to search ... Summarization is handled via cohere, QnA is handled via langchain, ... LangChain is a framework for developing applications powered by language models. ... There are several main modules that LangChain provides support for. Missing: decentralized platform. In the healthcare-chain system, blockchain provides an appreciated secure ... The entire process of adding new and previous block data is performed based on ... ChatGPT is a large language model developed by OpenAI, ... tool for a wide range of applications, including natural language processing, ...\n",
+      "\n",
+      "LangChain is a powerful tool that can be used to work with Large Language ... If an API key has been provided, create an OpenAI language model instance At its core, LangChain is a framework built around LLMs. We can use it for chatbots, Generative Question-Answering (GQA), summarization, and much more. A tutorial of the six core modules of the LangChain Python package covering models, prompts, chains, agents, indexes, and memory with OpenAI ... LangChain's collection of tools refers to a set of tools provided by the LangChain framework for developing applications powered by language models. LangChain is a framework for developing applications powered by language models. We believe that the most powerful and differentiated applications will not only ... LangChain is an open-source library that provides developers with the tools to build applications powered by large language models (LLMs). LangChain is a framework for including AI from large language models inside data pipelines and applications. This tutorial provides an overview of what you ... Plan-and-Execute Agents · Feature Stores and LLMs · Structured Tools · Auto-Evaluator Opportunities · Callbacks Improvements · Unleashing the power ... Tool: A function that performs a specific duty. This can be things like: Google Search, Database lookup, Python REPL, other chains. · LLM: The language model ... LangChain provides a standard interface for chains, lots of integrations with other tools, and end-to-end chains for common applications.\n",
+      "\n",
+      "Baby AGI has the ability to complete tasks, generate new tasks based on previous results, and prioritize tasks in real-time. This system is exploring and demonstrating to us the potential of large language models, such as GPT and how it can autonomously perform tasks. Apr 17, 2023\n",
+      "\n",
+      "At its core, LangChain is a framework built around LLMs. We can use it for chatbots, Generative Question-Answering (GQA), summarization, and much more. The core idea of the library is that we can “chain” together different components to create more advanced use cases around LLMs.\n",
+      ">>> USER INPUT: explain in great detail the difference between the langchain framework and baby agi\n",
+      ">>> RESPONSE: \u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "' LangChain is a framework for developing applications powered by language models. It provides a standard interface for chains, lots of integrations with other tools, and end-to-end chains for common applications. On the other hand, Baby AGI is an AI system that is exploring and demonstrating the potential of large language models, such as GPT, and how it can autonomously perform tasks. Baby AGI has the ability to complete tasks, generate new tasks based on previous results, and prioritize tasks in real-time. '"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "flare.run(query)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "7bed8944",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'\\n\\nThe Langchain framework and Baby AGI are both artificial intelligence (AI) frameworks that are used to create intelligent agents. The Langchain framework is a supervised learning system that is based on the concept of “language chains”. It uses a set of rules to map natural language inputs to specific outputs. It is a general-purpose AI framework and can be used to build applications such as natural language processing (NLP), chatbots, and more.\\n\\nBaby AGI, on the other hand, is an unsupervised learning system that uses neural networks and reinforcement learning to learn from its environment. It is used to create intelligent agents that can adapt to changing environments. It is a more advanced AI system and can be used to build more complex applications such as game playing, robotic vision, and more.\\n\\nThe main difference between the two is that the Langchain framework uses supervised learning while Baby AGI uses unsupervised learning. The Langchain framework is a general-purpose AI framework that can be used for various applications, while Baby AGI is a more advanced AI system that can be used to create more complex applications.'"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "llm = OpenAI()\n",
+    "llm(query)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "8fb76286",
+   "metadata": {
+    "scrolled": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new FlareChain chain...\u001b[0m\n",
+      "\u001b[36;1m\u001b[1;3mCurrent Response: \u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3mRespond to the user message using any relevant context. If context is provided, you should ground your answer in that context. Once you're done responding return FINISHED.\n",
+      "\n",
+      ">>> CONTEXT: \n",
+      ">>> USER INPUT: how are the origin stories of langchain and bitcoin similar or different?\n",
+      ">>> RESPONSE: \u001b[0m\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new QuestionGeneratorChain chain...\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
+      "\n",
+      ">>> USER INPUT: how are the origin stories of langchain and bitcoin similar or different?\n",
+      ">>> EXISTING PARTIAL RESPONSE:  \n",
+      "\n",
+      "Langchain and Bitcoin have very different origin stories. Bitcoin was created by the mysterious Satoshi Nakamoto in 2008 as a decentralized digital currency. Langchain, on the other hand, was created in 2020 by a team of developers as a platform for creating and managing decentralized language learning applications. \n",
+      "\n",
+      "FINISHED\n",
+      "\n",
+      "The question to which the answer is the term/entity/phrase \" very different origin\" is:\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
+      "\n",
+      ">>> USER INPUT: how are the origin stories of langchain and bitcoin similar or different?\n",
+      ">>> EXISTING PARTIAL RESPONSE:  \n",
+      "\n",
+      "Langchain and Bitcoin have very different origin stories. Bitcoin was created by the mysterious Satoshi Nakamoto in 2008 as a decentralized digital currency. Langchain, on the other hand, was created in 2020 by a team of developers as a platform for creating and managing decentralized language learning applications. \n",
+      "\n",
+      "FINISHED\n",
+      "\n",
+      "The question to which the answer is the term/entity/phrase \" 2020 by a\" is:\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3mGiven a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase:\n",
+      "\n",
+      ">>> USER INPUT: how are the origin stories of langchain and bitcoin similar or different?\n",
+      ">>> EXISTING PARTIAL RESPONSE:  \n",
+      "\n",
+      "Langchain and Bitcoin have very different origin stories. Bitcoin was created by the mysterious Satoshi Nakamoto in 2008 as a decentralized digital currency. Langchain, on the other hand, was created in 2020 by a team of developers as a platform for creating and managing decentralized language learning applications. \n",
+      "\n",
+      "FINISHED\n",
+      "\n",
+      "The question to which the answer is the term/entity/phrase \" developers as a platform for creating and managing decentralized language learning applications.\" is:\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\u001b[33;1m\u001b[1;3mGenerated Questions: ['How would you describe the origin stories of Langchain and Bitcoin in terms of their similarities or differences?', 'When was Langchain created and by whom?', 'What was the purpose of creating Langchain?']\u001b[0m\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new _OpenAIResponseChain chain...\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3mRespond to the user message using any relevant context. If context is provided, you should ground your answer in that context. Once you're done responding return FINISHED.\n",
+      "\n",
+      ">>> CONTEXT: Bitcoin and Ethereum have many similarities but different long-term visions and limitations. Ethereum changed from proof of work to proof of ... Bitcoin will be around for many years and examining its white paper origins is a great exercise in understanding why. Satoshi Nakamoto's blueprint describes ... Bitcoin is a new currency that was created in 2009 by an unknown person using the alias Satoshi Nakamoto. Transactions are made with no middle men – meaning, no ... Missing: Langchain | Must include:Langchain. By comparison, Bitcoin transaction speeds are tremendously lower. ... learn about its history and its role in the emergence of the Bitcoin ... LangChain is a powerful framework that simplifies the process of ... tasks like document retrieval, clustering, and similarity comparisons. Key terms: Bitcoin System, Blockchain Technology, ... Furthermore, the research paper will discuss and compare the five payment. Blockchain first appeared in Nakamoto's Bitcoin white paper that describes a new decentralized cryptocurrency [1]. Bitcoin takes the blockchain technology ... Missing: stories | Must include:stories. A score of 0 means there were not enough data for this term. Google trends was accessed on 5 November 2018 with searches for bitcoin, euro, gold ... Contracts, transactions, and records of them provide critical structure in our economic system, but they haven't kept up with the world's digital ... Missing: Langchain | Must include:Langchain. Of course, traders try to make a profit on their portfolio in this way.The difference between investing and trading is the regularity with which ...\n",
+      "\n",
+      "After all these giant leaps forward in the LLM space, OpenAI released ChatGPT — thrusting LLMs into the spotlight. LangChain appeared around the same time. Its creator, Harrison Chase, made the first commit in late October 2022. Leaving a short couple of months of development before getting caught in the LLM wave.\n",
+      "\n",
+      "At its core, LangChain is a framework built around LLMs. We can use it for chatbots, Generative Question-Answering (GQA), summarization, and much more. The core idea of the library is that we can “chain” together different components to create more advanced use cases around LLMs.\n",
+      ">>> USER INPUT: how are the origin stories of langchain and bitcoin similar or different?\n",
+      ">>> RESPONSE: \u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "' The origin stories of LangChain and Bitcoin are quite different. Bitcoin was created in 2009 by an unknown person using the alias Satoshi Nakamoto. LangChain was created in late October 2022 by Harrison Chase. Bitcoin is a decentralized cryptocurrency, while LangChain is a framework built around LLMs. '"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "flare.run(\"how are the origin stories of langchain and bitcoin similar or different?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fbadd022",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

cookbook/generative_agents_interactive_simulacra_of_human_behavior.ipynb

@@ -0,0 +1,994 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "e9732067-71c7-46f7-ad09-381b3bf21a27",
+   "metadata": {},
+   "source": [
+    "# Generative Agents in LangChain\n",
+    "\n",
+    "This notebook implements a generative agent based on the paper [Generative Agents: Interactive Simulacra of Human Behavior](https://arxiv.org/abs/2304.03442) by Park, et. al.\n",
+    "\n",
+    "In it, we leverage a time-weighted Memory object backed by a LangChain Retriever."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "53f81c37-db45-4fdc-843c-aa8fd2a9e99d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Use termcolor to make it easy to colorize the outputs.\n",
+    "!pip install termcolor > /dev/null"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "3128fc21",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import logging\n",
+    "\n",
+    "logging.basicConfig(level=logging.ERROR)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "8851c370-b395-4b80-a79d-486a38ffc244",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from datetime import datetime, timedelta\n",
+    "from typing import List\n",
+    "from termcolor import colored\n",
+    "\n",
+    "\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.docstore import InMemoryDocstore\n",
+    "from langchain.embeddings import OpenAIEmbeddings\n",
+    "from langchain.retrievers import TimeWeightedVectorStoreRetriever\n",
+    "from langchain.vectorstores import FAISS"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "81824e76",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "USER_NAME = \"Person A\"  # The name you want to use when interviewing the agent.\n",
+    "LLM = ChatOpenAI(max_tokens=1500)  # Can be any LLM you want."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c3da1649-d88f-4973-b655-7042975cde7e",
+   "metadata": {},
+   "source": [
+    "### Generative Agent Memory Components\n",
+    "\n",
+    "This tutorial highlights the memory of generative agents and its impact on their behavior. The memory varies from standard LangChain Chat memory in two aspects:\n",
+    "\n",
+    "1. **Memory Formation**\n",
+    "\n",
+    "   Generative Agents have extended memories, stored in a single stream:\n",
+    "      1. Observations - from dialogues or interactions with the virtual world, about self or others\n",
+    "      2. Reflections - resurfaced and summarized core memories\n",
+    "\n",
+    "\n",
+    "2. **Memory Recall**\n",
+    "\n",
+    "   Memories are retrieved using a weighted sum of salience, recency, and importance.\n",
+    "\n",
+    "You can review the definitions of the `GenerativeAgent` and `GenerativeAgentMemory` in the [reference documentation](\"https://api.python.langchain.com/en/latest/modules/experimental.html\") for the following imports, focusing on `add_memory` and `summarize_related_memories` methods."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "043e5203-6a41-431c-9efa-3e1743d7d25a",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_experimental.generative_agents import (\n",
+    "    GenerativeAgent,\n",
+    "    GenerativeAgentMemory,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "361bd49e",
+   "metadata": {
+    "jp-MarkdownHeadingCollapsed": true,
+    "tags": []
+   },
+   "source": [
+    "## Memory Lifecycle\n",
+    "\n",
+    "Summarizing the key methods in the above: `add_memory` and `summarize_related_memories`.\n",
+    "\n",
+    "When an agent makes an observation, it stores the memory:\n",
+    "    \n",
+    "1. Language model scores the memory's importance (1 for mundane, 10 for poignant)\n",
+    "2. Observation and importance are stored within a document by TimeWeightedVectorStoreRetriever, with a `last_accessed_time`.\n",
+    "\n",
+    "When an agent responds to an observation:\n",
+    "\n",
+    "1. Generates query(s) for retriever, which fetches documents based on salience, recency, and importance.\n",
+    "2. Summarizes the retrieved information\n",
+    "3. Updates the `last_accessed_time` for the used documents.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2fa3ca02",
+   "metadata": {},
+   "source": [
+    "## Create a Generative Character\n",
+    "\n",
+    "\n",
+    "\n",
+    "Now that we've walked through the definition, we will create two characters named \"Tommie\" and \"Eve\"."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "ee9c1a1d-c311-4f1c-8131-75fccd9025b1",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import math\n",
+    "import faiss\n",
+    "\n",
+    "\n",
+    "def relevance_score_fn(score: float) -> float:\n",
+    "    \"\"\"Return a similarity score on a scale [0, 1].\"\"\"\n",
+    "    # This will differ depending on a few things:\n",
+    "    # - the distance / similarity metric used by the VectorStore\n",
+    "    # - the scale of your embeddings (OpenAI's are unit norm. Many others are not!)\n",
+    "    # This function converts the euclidean norm of normalized embeddings\n",
+    "    # (0 is most similar, sqrt(2) most dissimilar)\n",
+    "    # to a similarity function (0 to 1)\n",
+    "    return 1.0 - score / math.sqrt(2)\n",
+    "\n",
+    "\n",
+    "def create_new_memory_retriever():\n",
+    "    \"\"\"Create a new vector store retriever unique to the agent.\"\"\"\n",
+    "    # Define your embedding model\n",
+    "    embeddings_model = OpenAIEmbeddings()\n",
+    "    # Initialize the vectorstore as empty\n",
+    "    embedding_size = 1536\n",
+    "    index = faiss.IndexFlatL2(embedding_size)\n",
+    "    vectorstore = FAISS(\n",
+    "        embeddings_model.embed_query,\n",
+    "        index,\n",
+    "        InMemoryDocstore({}),\n",
+    "        {},\n",
+    "        relevance_score_fn=relevance_score_fn,\n",
+    "    )\n",
+    "    return TimeWeightedVectorStoreRetriever(\n",
+    "        vectorstore=vectorstore, other_score_keys=[\"importance\"], k=15\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "7884f9dd-c597-4c27-8c77-1402c71bc2f8",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "tommies_memory = GenerativeAgentMemory(\n",
+    "    llm=LLM,\n",
+    "    memory_retriever=create_new_memory_retriever(),\n",
+    "    verbose=False,\n",
+    "    reflection_threshold=8,  # we will give this a relatively low number to show how reflection works\n",
+    ")\n",
+    "\n",
+    "tommie = GenerativeAgent(\n",
+    "    name=\"Tommie\",\n",
+    "    age=25,\n",
+    "    traits=\"anxious, likes design, talkative\",  # You can add more persistent traits here\n",
+    "    status=\"looking for a job\",  # When connected to a virtual world, we can have the characters update their status\n",
+    "    memory_retriever=create_new_memory_retriever(),\n",
+    "    llm=LLM,\n",
+    "    memory=tommies_memory,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "c524d529",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Name: Tommie (age: 25)\n",
+      "Innate traits: anxious, likes design, talkative\n",
+      "No information about Tommie's core characteristics is provided in the given statements.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# The current \"Summary\" of a character can't be made because the agent hasn't made\n",
+    "# any observations yet.\n",
+    "print(tommie.get_summary())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "4be60979-d56e-4abf-a636-b34ffa8b7fba",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# We can add memories directly to the memory object\n",
+    "tommie_observations = [\n",
+    "    \"Tommie remembers his dog, Bruno, from when he was a kid\",\n",
+    "    \"Tommie feels tired from driving so far\",\n",
+    "    \"Tommie sees the new home\",\n",
+    "    \"The new neighbors have a cat\",\n",
+    "    \"The road is noisy at night\",\n",
+    "    \"Tommie is hungry\",\n",
+    "    \"Tommie tries to get some rest.\",\n",
+    "]\n",
+    "for observation in tommie_observations:\n",
+    "    tommie.memory.add_memory(observation)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "6992b48b-697f-4973-9560-142ef85357d7",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Name: Tommie (age: 25)\n",
+      "Innate traits: anxious, likes design, talkative\n",
+      "Tommie is a person who is observant of his surroundings, has a sentimental side, and experiences basic human needs such as hunger and the need for rest. He also tends to get tired easily and is affected by external factors such as noise from the road or a neighbor's pet.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Now that Tommie has 'memories', their self-summary is more descriptive, though still rudimentary.\n",
+    "# We will see how this summary updates after more observations to create a more rich description.\n",
+    "print(tommie.get_summary(force_refresh=True))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "40d39a32-838c-4a03-8b27-a52c76c402e7",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "## Pre-Interview with Character\n",
+    "\n",
+    "Before sending our character on their way, let's ask them a few questions."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "eaf125d8-f54c-4c5f-b6af-32789b1f7d3a",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "def interview_agent(agent: GenerativeAgent, message: str) -> str:\n",
+    "    \"\"\"Help the notebook user interact with the agent.\"\"\"\n",
+    "    new_message = f\"{USER_NAME} says {message}\"\n",
+    "    return agent.generate_dialogue_response(new_message)[1]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "54024d41-6e83-4914-91e5-73140e2dd9c8",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Tommie said \"I really enjoy design and being creative. I\\'ve been working on some personal projects lately. What about you, Person A? What do you like to do?\"'"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "interview_agent(tommie, \"What do you like to do?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "71e2e8cc-921e-4816-82f1-66962b2c1055",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Tommie said \"Well, I\\'m actually looking for a job right now, so hopefully I can find some job postings online and start applying. How about you, Person A? What\\'s on your schedule for today?\"'"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "interview_agent(tommie, \"What are you looking forward to doing today?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "a2521ffc-7050-4ac3-9a18-4cccfc798c31",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Tommie said \"Honestly, I\\'m feeling pretty anxious about finding a job. It\\'s been a bit of a struggle lately, but I\\'m trying to stay positive and keep searching. How about you, Person A? What worries you?\"'"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "interview_agent(tommie, \"What are you most worried about today?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e509c468-f7cd-4d72-9f3a-f4aba28b1eea",
+   "metadata": {},
+   "source": [
+    "## Step through the day's observations."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "154dee3d-bfe0-4828-b963-ed7e885799b3",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# Let's have Tommie start going through a day in the life.\n",
+    "observations = [\n",
+    "    \"Tommie wakes up to the sound of a noisy construction site outside his window.\",\n",
+    "    \"Tommie gets out of bed and heads to the kitchen to make himself some coffee.\",\n",
+    "    \"Tommie realizes he forgot to buy coffee filters and starts rummaging through his moving boxes to find some.\",\n",
+    "    \"Tommie finally finds the filters and makes himself a cup of coffee.\",\n",
+    "    \"The coffee tastes bitter, and Tommie regrets not buying a better brand.\",\n",
+    "    \"Tommie checks his email and sees that he has no job offers yet.\",\n",
+    "    \"Tommie spends some time updating his resume and cover letter.\",\n",
+    "    \"Tommie heads out to explore the city and look for job openings.\",\n",
+    "    \"Tommie sees a sign for a job fair and decides to attend.\",\n",
+    "    \"The line to get in is long, and Tommie has to wait for an hour.\",\n",
+    "    \"Tommie meets several potential employers at the job fair but doesn't receive any offers.\",\n",
+    "    \"Tommie leaves the job fair feeling disappointed.\",\n",
+    "    \"Tommie stops by a local diner to grab some lunch.\",\n",
+    "    \"The service is slow, and Tommie has to wait for 30 minutes to get his food.\",\n",
+    "    \"Tommie overhears a conversation at the next table about a job opening.\",\n",
+    "    \"Tommie asks the diners about the job opening and gets some information about the company.\",\n",
+    "    \"Tommie decides to apply for the job and sends his resume and cover letter.\",\n",
+    "    \"Tommie continues his search for job openings and drops off his resume at several local businesses.\",\n",
+    "    \"Tommie takes a break from his job search to go for a walk in a nearby park.\",\n",
+    "    \"A dog approaches and licks Tommie's feet, and he pets it for a few minutes.\",\n",
+    "    \"Tommie sees a group of people playing frisbee and decides to join in.\",\n",
+    "    \"Tommie has fun playing frisbee but gets hit in the face with the frisbee and hurts his nose.\",\n",
+    "    \"Tommie goes back to his apartment to rest for a bit.\",\n",
+    "    \"A raccoon tore open the trash bag outside his apartment, and the garbage is all over the floor.\",\n",
+    "    \"Tommie starts to feel frustrated with his job search.\",\n",
+    "    \"Tommie calls his best friend to vent about his struggles.\",\n",
+    "    \"Tommie's friend offers some words of encouragement and tells him to keep trying.\",\n",
+    "    \"Tommie feels slightly better after talking to his friend.\",\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "238be49c-edb3-4e26-a2b6-98777ba8de86",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[32mTommie wakes up to the sound of a noisy construction site outside his window.\u001b[0m Tommie groans and covers his head with a pillow, trying to block out the noise.\n",
+      "\u001b[32mTommie gets out of bed and heads to the kitchen to make himself some coffee.\u001b[0m Tommie stretches his arms and yawns before starting to make the coffee.\n",
+      "\u001b[32mTommie realizes he forgot to buy coffee filters and starts rummaging through his moving boxes to find some.\u001b[0m Tommie sighs in frustration and continues searching through the boxes.\n",
+      "\u001b[32mTommie finally finds the filters and makes himself a cup of coffee.\u001b[0m Tommie takes a deep breath and enjoys the aroma of the fresh coffee.\n",
+      "\u001b[32mThe coffee tastes bitter, and Tommie regrets not buying a better brand.\u001b[0m Tommie grimaces and sets the coffee mug aside.\n",
+      "\u001b[32mTommie checks his email and sees that he has no job offers yet.\u001b[0m Tommie sighs and closes his laptop, feeling discouraged.\n",
+      "\u001b[32mTommie spends some time updating his resume and cover letter.\u001b[0m Tommie nods, feeling satisfied with his progress.\n",
+      "\u001b[32mTommie heads out to explore the city and look for job openings.\u001b[0m Tommie feels a surge of excitement and anticipation as he steps out into the city.\n",
+      "\u001b[32mTommie sees a sign for a job fair and decides to attend.\u001b[0m Tommie feels hopeful and excited about the possibility of finding job opportunities at the job fair.\n",
+      "\u001b[32mThe line to get in is long, and Tommie has to wait for an hour.\u001b[0m Tommie taps his foot impatiently and checks his phone for the time.\n",
+      "\u001b[32mTommie meets several potential employers at the job fair but doesn't receive any offers.\u001b[0m Tommie feels disappointed and discouraged, but he remains determined to keep searching for job opportunities.\n",
+      "\u001b[32mTommie leaves the job fair feeling disappointed.\u001b[0m Tommie feels disappointed and discouraged, but he remains determined to keep searching for job opportunities.\n",
+      "\u001b[32mTommie stops by a local diner to grab some lunch.\u001b[0m Tommie feels relieved to take a break and satisfy his hunger.\n",
+      "\u001b[32mThe service is slow, and Tommie has to wait for 30 minutes to get his food.\u001b[0m Tommie feels frustrated and impatient due to the slow service.\n",
+      "\u001b[32mTommie overhears a conversation at the next table about a job opening.\u001b[0m Tommie feels a surge of hope and excitement at the possibility of a job opportunity but decides not to interfere with the conversation at the next table.\n",
+      "\u001b[32mTommie asks the diners about the job opening and gets some information about the company.\u001b[0m Tommie said \"Excuse me, I couldn't help but overhear your conversation about the job opening. Could you give me some more information about the company?\"\n",
+      "\u001b[32mTommie decides to apply for the job and sends his resume and cover letter.\u001b[0m Tommie feels hopeful and proud of himself for taking action towards finding a job.\n",
+      "\u001b[32mTommie continues his search for job openings and drops off his resume at several local businesses.\u001b[0m Tommie feels hopeful and determined to keep searching for job opportunities.\n",
+      "\u001b[32mTommie takes a break from his job search to go for a walk in a nearby park.\u001b[0m Tommie feels refreshed and rejuvenated after taking a break in the park.\n",
+      "\u001b[32mA dog approaches and licks Tommie's feet, and he pets it for a few minutes.\u001b[0m Tommie feels happy and enjoys the brief interaction with the dog.\n",
+      "****************************************\n",
+      "\u001b[34mAfter 20 observations, Tommie's summary is:\n",
+      "Name: Tommie (age: 25)\n",
+      "Innate traits: anxious, likes design, talkative\n",
+      "Tommie is determined and hopeful in his search for job opportunities, despite encountering setbacks and disappointments. He is also able to take breaks and care for his physical needs, such as getting rest and satisfying his hunger. Tommie is nostalgic towards his past, as shown by his memory of his childhood dog. Overall, Tommie is a hardworking and resilient individual who remains focused on his goals.\u001b[0m\n",
+      "****************************************\n",
+      "\u001b[32mTommie sees a group of people playing frisbee and decides to join in.\u001b[0m Do nothing.\n",
+      "\u001b[32mTommie has fun playing frisbee but gets hit in the face with the frisbee and hurts his nose.\u001b[0m Tommie feels pain and puts a hand to his nose to check for any injury.\n",
+      "\u001b[32mTommie goes back to his apartment to rest for a bit.\u001b[0m Tommie feels relieved to take a break and rest for a bit.\n",
+      "\u001b[32mA raccoon tore open the trash bag outside his apartment, and the garbage is all over the floor.\u001b[0m Tommie feels annoyed and frustrated at the mess caused by the raccoon.\n",
+      "\u001b[32mTommie starts to feel frustrated with his job search.\u001b[0m Tommie feels discouraged but remains determined to keep searching for job opportunities.\n",
+      "\u001b[32mTommie calls his best friend to vent about his struggles.\u001b[0m Tommie said \"Hey, can I talk to you for a bit? I'm feeling really frustrated with my job search.\"\n",
+      "\u001b[32mTommie's friend offers some words of encouragement and tells him to keep trying.\u001b[0m Tommie said \"Thank you, I really appreciate your support and encouragement.\"\n",
+      "\u001b[32mTommie feels slightly better after talking to his friend.\u001b[0m Tommie feels grateful for his friend's support.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Let's send Tommie on their way. We'll check in on their summary every few observations to watch it evolve\n",
+    "for i, observation in enumerate(observations):\n",
+    "    _, reaction = tommie.generate_reaction(observation)\n",
+    "    print(colored(observation, \"green\"), reaction)\n",
+    "    if ((i + 1) % 20) == 0:\n",
+    "        print(\"*\" * 40)\n",
+    "        print(\n",
+    "            colored(\n",
+    "                f\"After {i+1} observations, Tommie's summary is:\\n{tommie.get_summary(force_refresh=True)}\",\n",
+    "                \"blue\",\n",
+    "            )\n",
+    "        )\n",
+    "        print(\"*\" * 40)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "dd62a275-7290-43ca-aa0f-504f3a706d09",
+   "metadata": {},
+   "source": [
+    "## Interview after the day"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "6336ab5d-3074-4831-951f-c9e2cba5dfb5",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Tommie said \"It\\'s been a bit of a rollercoaster, to be honest. I\\'ve had some setbacks in my job search, but I also had some good moments today, like sending out a few resumes and meeting some potential employers at a job fair. How about you?\"'"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "interview_agent(tommie, \"Tell me about how your day has been going\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "809ac906-69b7-4326-99ec-af638d32bb20",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Tommie said \"I really enjoy coffee, but sometimes I regret not buying a better brand. How about you?\"'"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "interview_agent(tommie, \"How do you feel about coffee?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "f733a431-19ea-421a-9101-ae2593a8c626",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Tommie said \"Oh, I had a dog named Bruno when I was a kid. He was a golden retriever and my best friend. I have so many fond memories of him.\"'"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "interview_agent(tommie, \"Tell me about your childhood dog!\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c9261428-778a-4c0b-b725-bc9e91b71391",
+   "metadata": {},
+   "source": [
+    "## Adding Multiple Characters\n",
+    "\n",
+    "Let's add a second character to have a conversation with Tommie. Feel free to configure different traits."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "id": "ec8bbe18-a021-419c-bf1f-23d34732cd99",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "eves_memory = GenerativeAgentMemory(\n",
+    "    llm=LLM,\n",
+    "    memory_retriever=create_new_memory_retriever(),\n",
+    "    verbose=False,\n",
+    "    reflection_threshold=5,\n",
+    ")\n",
+    "\n",
+    "\n",
+    "eve = GenerativeAgent(\n",
+    "    name=\"Eve\",\n",
+    "    age=34,\n",
+    "    traits=\"curious, helpful\",  # You can add more persistent traits here\n",
+    "    status=\"N/A\",  # When connected to a virtual world, we can have the characters update their status\n",
+    "    llm=LLM,\n",
+    "    daily_summaries=[\n",
+    "        (\n",
+    "            \"Eve started her new job as a career counselor last week and received her first assignment, a client named Tommie.\"\n",
+    "        )\n",
+    "    ],\n",
+    "    memory=eves_memory,\n",
+    "    verbose=False,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "id": "1e2745f5-e0da-4abd-98b4-830802ce6698",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "yesterday = (datetime.now() - timedelta(days=1)).strftime(\"%A %B %d\")\n",
+    "eve_observations = [\n",
+    "    \"Eve wakes up and hear's the alarm\",\n",
+    "    \"Eve eats a boal of porridge\",\n",
+    "    \"Eve helps a coworker on a task\",\n",
+    "    \"Eve plays tennis with her friend Xu before going to work\",\n",
+    "    \"Eve overhears her colleague say something about Tommie being hard to work with\",\n",
+    "]\n",
+    "for observation in eve_observations:\n",
+    "    eve.memory.add_memory(observation)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "id": "de4726e3-4bb1-47da-8fd9-f317a036fe0f",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Name: Eve (age: 34)\n",
+      "Innate traits: curious, helpful\n",
+      "Eve is a helpful and active person who enjoys sports and takes care of her physical health. She is attentive to her surroundings, including her colleagues, and has good time management skills.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(eve.get_summary())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "837524e9-7f7e-4e9f-b610-f454062f5915",
+   "metadata": {},
+   "source": [
+    "## Pre-conversation interviews\n",
+    "\n",
+    "\n",
+    "Let's \"Interview\" Eve before she speaks with Tommie."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "id": "6cda916d-800c-47bc-a7f9-6a2f19187472",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Eve said \"I\\'m feeling pretty good, thanks for asking! Just trying to stay productive and make the most of the day. How about you?\"'"
+      ]
+     },
+     "execution_count": 50,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "interview_agent(eve, \"How are you feeling about today?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 51,
+   "id": "448ae644-0a66-4eb2-a03a-319f36948b37",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Eve said \"I don\\'t know much about Tommie, but I heard someone mention that they find them difficult to work with. Have you had any experiences working with Tommie?\"'"
+      ]
+     },
+     "execution_count": 51,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "interview_agent(eve, \"What do you know about Tommie?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 52,
+   "id": "493fc5b8-8730-4ef8-9820-0f1769ce1691",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Eve said \"That\\'s interesting. I don\\'t know much about Tommie\\'s work experience, but I would probably ask about his strengths and areas for improvement. What about you?\"'"
+      ]
+     },
+     "execution_count": 52,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "interview_agent(\n",
+    "    eve,\n",
+    "    \"Tommie is looking to find a job. What are are some things you'd like to ask him?\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 53,
+   "id": "4b46452a-6c54-4db2-9d87-18597f70fec8",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Eve said \"Sure, I can keep the conversation going and ask plenty of questions. I want to make sure Tommie feels comfortable and supported. Thanks for letting me know.\"'"
+      ]
+     },
+     "execution_count": 53,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "interview_agent(\n",
+    "    eve,\n",
+    "    \"You'll have to ask him. He may be a bit anxious, so I'd appreciate it if you keep the conversation going and ask as many questions as possible.\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "dd780655-1d73-4fcb-a78d-79fd46a20636",
+   "metadata": {},
+   "source": [
+    "## Dialogue between Generative Agents\n",
+    "\n",
+    "Generative agents are much more complex when they interact with a virtual environment or with each other. Below, we run a simple conversation between Tommie and Eve."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "id": "042ea271-4bf1-4247-9082-239a6fea43b8",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "def run_conversation(agents: List[GenerativeAgent], initial_observation: str) -> None:\n",
+    "    \"\"\"Runs a conversation between agents.\"\"\"\n",
+    "    _, observation = agents[1].generate_reaction(initial_observation)\n",
+    "    print(observation)\n",
+    "    turns = 0\n",
+    "    while True:\n",
+    "        break_dialogue = False\n",
+    "        for agent in agents:\n",
+    "            stay_in_dialogue, observation = agent.generate_dialogue_response(\n",
+    "                observation\n",
+    "            )\n",
+    "            print(observation)\n",
+    "            # observation = f\"{agent.name} said {reaction}\"\n",
+    "            if not stay_in_dialogue:\n",
+    "                break_dialogue = True\n",
+    "        if break_dialogue:\n",
+    "            break\n",
+    "        turns += 1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "id": "d5462b14-218e-4d85-b035-df57ea8e0f80",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Eve said \"Sure, Tommie. I'd be happy to share about my experience. Where would you like me to start?\"\n",
+      "Tommie said \"That's great, thank you! How about you start by telling me about your previous work experience?\"\n",
+      "Eve said \"Sure, I'd be happy to share my previous work experience with you. I've worked in a few different industries, including marketing and event planning. What specific questions do you have for me?\"\n",
+      "Tommie said \"That's great to hear. Can you tell me more about your experience in event planning? I've always been interested in that field.\"\n",
+      "Eve said \"Sure, I'd be happy to share about my experience in event planning. I've worked on a variety of events, from corporate conferences to weddings. One of the biggest challenges I faced was managing multiple vendors and ensuring everything ran smoothly on the day of the event. What specific questions do you have?\"\n",
+      "Tommie said \"That sounds like a lot of responsibility! Can you tell me more about how you handled the challenges that came up during those events?\"\n",
+      "Eve said \"Sure, Tommie. I'd be happy to share with you how I handled those challenges. One approach that worked well for me was to stay organized and create a detailed timeline for the event. This helped me keep track of all the different tasks that needed to be done and when they needed to be completed. I also made sure to communicate clearly with all the vendors and team members involved in the event to ensure everyone was on the same page. Would you like me to go into more detail?\"\n",
+      "Tommie said \"Thank you for sharing that with me, Eve. That sounds like a great approach to managing events. Can you tell me more about how you handled any unexpected issues that came up during the events?\"\n",
+      "Eve said \"Of course, Tommie. One example of an unexpected issue I faced was when one of the vendors didn't show up on time. To handle this, I quickly contacted a backup vendor and was able to get everything back on track. It's always important to have a backup plan in case things don't go as planned. Do you have any other questions about event planning?\"\n",
+      "Tommie said \"Thank you for sharing that with me, Eve. It's really helpful to hear how you handled unexpected issues like that. Can you give me an example of how you communicated with your team to ensure everyone was on the same page during an event?\"\n",
+      "Eve said \"Sure, Tommie. One thing I did to ensure everyone was on the same page was to have regular check-ins and meetings with the team leading up to the event. This helped us address any issues or concerns early on and make sure everyone was clear on their roles and responsibilities. Have you ever had to manage a team for an event before?\"\n",
+      "Tommie said \"That's a great idea, Eve. I haven't had the opportunity to manage a team for an event yet, but I'll definitely keep that in mind for the future. Thank you for sharing your experience with me.\"\n",
+      "Eve said \"Thanks for the opportunity to share my experience, Tommie. It was great meeting with you today.\"\n"
+     ]
+    }
+   ],
+   "source": [
+    "agents = [tommie, eve]\n",
+    "run_conversation(\n",
+    "    agents,\n",
+    "    \"Tommie said: Hi, Eve. Thanks for agreeing to meet with me today. I have a bunch of questions and am not sure where to start. Maybe you could first share about your experience?\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1b28fe80-03dc-4399-961d-6e9ee1980216",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "## Let's interview our agents after their conversation\n",
+    "\n",
+    "Since the generative agents retain their memories from the day, we can ask them about their plans, conversations, and other memoreis."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 56,
+   "id": "c4d252f3-fcc1-474c-846e-a7605a6b4ce7",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Name: Tommie (age: 25)\n",
+      "Innate traits: anxious, likes design, talkative\n",
+      "Tommie is determined and hopeful in his job search, but can also feel discouraged and frustrated at times. He has a strong connection to his childhood dog, Bruno. Tommie seeks support from his friends when feeling overwhelmed and is grateful for their help. He also enjoys exploring his new city.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# We can see a current \"Summary\" of a character based on their own perception of self\n",
+    "# has changed\n",
+    "print(tommie.get_summary(force_refresh=True))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 57,
+   "id": "c04db9a4",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Name: Eve (age: 34)\n",
+      "Innate traits: curious, helpful\n",
+      "Eve is a helpful and friendly person who enjoys playing sports and staying productive. She is attentive and responsive to others' needs, actively listening and asking questions to understand their perspectives. Eve has experience in event planning and communication, and is willing to share her knowledge and expertise with others. She values teamwork and collaboration, and strives to create a comfortable and supportive environment for everyone.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(eve.get_summary(force_refresh=True))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 58,
+   "id": "71762558-8fb6-44d7-8483-f5b47fb2a862",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Tommie said \"It was really helpful actually. Eve shared some great tips on managing events and handling unexpected issues. I feel like I learned a lot from her experience.\"'"
+      ]
+     },
+     "execution_count": 58,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "interview_agent(tommie, \"How was your conversation with Eve?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 59,
+   "id": "085af3d8-ac21-41ea-8f8b-055c56976a67",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Eve said \"It was great, thanks for asking. Tommie was very receptive and had some great questions about event planning. How about you, have you had any interactions with Tommie?\"'"
+      ]
+     },
+     "execution_count": 59,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "interview_agent(eve, \"How was your conversation with Tommie?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 60,
+   "id": "5b439f3c-7849-4432-a697-2bcc85b89dae",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Eve said \"It was great meeting with you, Tommie. If you have any more questions or need any help in the future, don\\'t hesitate to reach out to me. Have a great day!\"'"
+      ]
+     },
+     "execution_count": 60,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "interview_agent(eve, \"What do you wish you would have said to Tommie?\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

cookbook/gymnasium_agent_simulation.ipynb

@@ -0,0 +1,245 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "4b089493",
+   "metadata": {},
+   "source": [
+    "# Simulated Environment: Gymnasium\n",
+    "\n",
+    "For many applications of LLM agents, the environment is real (internet, database, REPL, etc). However, we can also define agents to interact in simulated environments like text-based games. This is an example of how to create a simple agent-environment interaction loop with [Gymnasium](https://github.com/Farama-Foundation/Gymnasium) (formerly [OpenAI Gym](https://github.com/openai/gym))."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "f36427cf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install gymnasium"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "f9bd38b4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import gymnasium as gym\n",
+    "import inspect\n",
+    "import tenacity\n",
+    "\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.schema import (\n",
+    "    AIMessage,\n",
+    "    HumanMessage,\n",
+    "    SystemMessage,\n",
+    "    BaseMessage,\n",
+    ")\n",
+    "from langchain.output_parsers import RegexParser"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e222e811",
+   "metadata": {},
+   "source": [
+    "## Define the agent"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "870c24bc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class GymnasiumAgent:\n",
+    "    @classmethod\n",
+    "    def get_docs(cls, env):\n",
+    "        return env.unwrapped.__doc__\n",
+    "\n",
+    "    def __init__(self, model, env):\n",
+    "        self.model = model\n",
+    "        self.env = env\n",
+    "        self.docs = self.get_docs(env)\n",
+    "\n",
+    "        self.instructions = \"\"\"\n",
+    "Your goal is to maximize your return, i.e. the sum of the rewards you receive.\n",
+    "I will give you an observation, reward, terminiation flag, truncation flag, and the return so far, formatted as:\n",
+    "\n",
+    "Observation: <observation>\n",
+    "Reward: <reward>\n",
+    "Termination: <termination>\n",
+    "Truncation: <truncation>\n",
+    "Return: <sum_of_rewards>\n",
+    "\n",
+    "You will respond with an action, formatted as:\n",
+    "\n",
+    "Action: <action>\n",
+    "\n",
+    "where you replace <action> with your actual action.\n",
+    "Do nothing else but return the action.\n",
+    "\"\"\"\n",
+    "        self.action_parser = RegexParser(\n",
+    "            regex=r\"Action: (.*)\", output_keys=[\"action\"], default_output_key=\"action\"\n",
+    "        )\n",
+    "\n",
+    "        self.message_history = []\n",
+    "        self.ret = 0\n",
+    "\n",
+    "    def random_action(self):\n",
+    "        action = self.env.action_space.sample()\n",
+    "        return action\n",
+    "\n",
+    "    def reset(self):\n",
+    "        self.message_history = [\n",
+    "            SystemMessage(content=self.docs),\n",
+    "            SystemMessage(content=self.instructions),\n",
+    "        ]\n",
+    "\n",
+    "    def observe(self, obs, rew=0, term=False, trunc=False, info=None):\n",
+    "        self.ret += rew\n",
+    "\n",
+    "        obs_message = f\"\"\"\n",
+    "Observation: {obs}\n",
+    "Reward: {rew}\n",
+    "Termination: {term}\n",
+    "Truncation: {trunc}\n",
+    "Return: {self.ret}\n",
+    "        \"\"\"\n",
+    "        self.message_history.append(HumanMessage(content=obs_message))\n",
+    "        return obs_message\n",
+    "\n",
+    "    def _act(self):\n",
+    "        act_message = self.model(self.message_history)\n",
+    "        self.message_history.append(act_message)\n",
+    "        action = int(self.action_parser.parse(act_message.content)[\"action\"])\n",
+    "        return action\n",
+    "\n",
+    "    def act(self):\n",
+    "        try:\n",
+    "            for attempt in tenacity.Retrying(\n",
+    "                stop=tenacity.stop_after_attempt(2),\n",
+    "                wait=tenacity.wait_none(),  # No waiting time between retries\n",
+    "                retry=tenacity.retry_if_exception_type(ValueError),\n",
+    "                before_sleep=lambda retry_state: print(\n",
+    "                    f\"ValueError occurred: {retry_state.outcome.exception()}, retrying...\"\n",
+    "                ),\n",
+    "            ):\n",
+    "                with attempt:\n",
+    "                    action = self._act()\n",
+    "        except tenacity.RetryError as e:\n",
+    "            action = self.random_action()\n",
+    "        return action"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2e76d22c",
+   "metadata": {},
+   "source": [
+    "## Initialize the simulated environment and agent"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "9e902cfd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "env = gym.make(\"Blackjack-v1\")\n",
+    "agent = GymnasiumAgent(model=ChatOpenAI(temperature=0.2), env=env)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e2c12b15",
+   "metadata": {},
+   "source": [
+    "## Main loop"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "ad361210",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "Observation: (15, 4, 0)\n",
+      "Reward: 0\n",
+      "Termination: False\n",
+      "Truncation: False\n",
+      "Return: 0\n",
+      "        \n",
+      "Action: 1\n",
+      "\n",
+      "Observation: (25, 4, 0)\n",
+      "Reward: -1.0\n",
+      "Termination: True\n",
+      "Truncation: False\n",
+      "Return: -1.0\n",
+      "        \n",
+      "break True False\n"
+     ]
+    }
+   ],
+   "source": [
+    "observation, info = env.reset()\n",
+    "agent.reset()\n",
+    "\n",
+    "obs_message = agent.observe(observation)\n",
+    "print(obs_message)\n",
+    "\n",
+    "while True:\n",
+    "    action = agent.act()\n",
+    "    observation, reward, termination, truncation, info = env.step(action)\n",
+    "    obs_message = agent.observe(observation, reward, termination, truncation, info)\n",
+    "    print(f\"Action: {action}\")\n",
+    "    print(obs_message)\n",
+    "\n",
+    "    if termination or truncation:\n",
+    "        print(\"break\", termination, truncation)\n",
+    "        break\n",
+    "env.close()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "58a13e9c",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.16"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

cookbook/hugginggpt.ipynb

@@ -0,0 +1,135 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# HuggingGPT\n",
+    "Implementation of [HuggingGPT](https://github.com/microsoft/JARVIS). HuggingGPT is a system to connect LLMs (ChatGPT) with ML community (Hugging Face).\n",
+    "\n",
+    "+ 🔥 Paper: https://arxiv.org/abs/2303.17580\n",
+    "+ 🚀 Project: https://github.com/microsoft/JARVIS\n",
+    "+ 🤗 Space: https://huggingface.co/spaces/microsoft/HuggingGPT"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Set up tools\n",
+    "\n",
+    "We set up the tools available from [Transformers Agent](https://huggingface.co/docs/transformers/transformers_agents#tools). It includes a library of tools supported by Transformers and some customized tools such as image generator, video generator, text downloader and other tools."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from transformers import load_tool"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "hf_tools = [\n",
+    "    load_tool(tool_name)\n",
+    "    for tool_name in [\n",
+    "        \"document-question-answering\",\n",
+    "        \"image-captioning\",\n",
+    "        \"image-question-answering\",\n",
+    "        \"image-segmentation\",\n",
+    "        \"speech-to-text\",\n",
+    "        \"summarization\",\n",
+    "        \"text-classification\",\n",
+    "        \"text-question-answering\",\n",
+    "        \"translation\",\n",
+    "        \"huggingface-tools/text-to-image\",\n",
+    "        \"huggingface-tools/text-to-video\",\n",
+    "        \"text-to-speech\",\n",
+    "        \"huggingface-tools/text-download\",\n",
+    "        \"huggingface-tools/image-transformation\",\n",
+    "    ]\n",
+    "]"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setup model and HuggingGPT\n",
+    "\n",
+    "We create an instance of HuggingGPT and use ChatGPT as the controller to rule the above tools."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.llms import OpenAI\n",
+    "from langchain_experimental.autonomous_agents import HuggingGPT\n",
+    "# %env OPENAI_API_BASE=http://localhost:8000/v1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = OpenAI(model_name=\"gpt-3.5-turbo\")\n",
+    "agent = HuggingGPT(llm, hf_tools)"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Run an example\n",
+    "\n",
+    "Given a text, show a related image and video."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "agent.run(\"please show me a video and an image of 'a boy is running'\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "langchain",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.17"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

cookbook/hypothetical_document_embeddings.ipynb

@@ -0,0 +1,268 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "ccb74c9b",
+   "metadata": {},
+   "source": [
+    "# Improve document indexing with HyDE\n",
+    "This notebook goes over how to use Hypothetical Document Embeddings (HyDE), as described in [this paper](https://arxiv.org/abs/2212.10496). \n",
+    "\n",
+    "At a high level, HyDE is an embedding technique that takes queries, generates a hypothetical answer, and then embeds that generated document and uses that as the final example. \n",
+    "\n",
+    "In order to use HyDE, we therefore need to provide a base embedding model, as well as an LLMChain that can be used to generate those documents. By default, the HyDE class comes with some default prompts to use (see the paper for more details on them), but we can also create our own."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "546e87ee",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.llms import OpenAI\n",
+    "from langchain.embeddings import OpenAIEmbeddings\n",
+    "from langchain.chains import LLMChain, HypotheticalDocumentEmbedder\n",
+    "from langchain.prompts import PromptTemplate"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "c0ea895f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "base_embeddings = OpenAIEmbeddings()\n",
+    "llm = OpenAI()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "33bd6905",
+   "metadata": {},
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "50729989",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Load with `web_search` prompt\n",
+    "embeddings = HypotheticalDocumentEmbedder.from_llm(llm, base_embeddings, \"web_search\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "3aa573d6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Now we can use it as any embedding class!\n",
+    "result = embeddings.embed_query(\"Where is the Taj Mahal?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c7a0b556",
+   "metadata": {},
+   "source": [
+    "## Multiple generations\n",
+    "We can also generate multiple documents and then combine the embeddings for those. By default, we combine those by taking the average. We can do this by changing the LLM we use to generate documents to return multiple things."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "05da7060",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "multi_llm = OpenAI(n=4, best_of=4)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "9b1e12bd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "embeddings = HypotheticalDocumentEmbedder.from_llm(\n",
+    "    multi_llm, base_embeddings, \"web_search\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "a60cd343",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "result = embeddings.embed_query(\"Where is the Taj Mahal?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1da90437",
+   "metadata": {},
+   "source": [
+    "## Using our own prompts\n",
+    "Besides using preconfigured prompts, we can also easily construct our own prompts and use those in the LLMChain that is generating the documents. This can be useful if we know the domain our queries will be in, as we can condition the prompt to generate text more similar to that.\n",
+    "\n",
+    "In the example below, let's condition it to generate text about a state of the union address (because we will use that in the next example)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "0b4a650f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prompt_template = \"\"\"Please answer the user's question about the most recent state of the union address\n",
+    "Question: {question}\n",
+    "Answer:\"\"\"\n",
+    "prompt = PromptTemplate(input_variables=[\"question\"], template=prompt_template)\n",
+    "llm_chain = LLMChain(llm=llm, prompt=prompt)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "7f7e2b86",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "embeddings = HypotheticalDocumentEmbedder(\n",
+    "    llm_chain=llm_chain, base_embeddings=base_embeddings\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "6dd83424",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "result = embeddings.embed_query(\n",
+    "    \"What did the president say about Ketanji Brown Jackson\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "31388123",
+   "metadata": {},
+   "source": [
+    "## Using HyDE\n",
+    "Now that we have HyDE, we can use it as we would any other embedding class! Here is using it to find similar passages in the state of the union example."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "97719b29",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain.vectorstores import Chroma\n",
+    "\n",
+    "with open(\"../../state_of_the_union.txt\") as f:\n",
+    "    state_of_the_union = f.read()\n",
+    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
+    "texts = text_splitter.split_text(state_of_the_union)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "bfcfc039",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running Chroma using direct local API.\n",
+      "Using DuckDB in-memory for database. Data will be transient.\n"
+     ]
+    }
+   ],
+   "source": [
+    "docsearch = Chroma.from_texts(texts, embeddings)\n",
+    "\n",
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "docs = docsearch.similarity_search(query)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "632af7f2",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "In state after state, new laws have been passed, not only to suppress the vote, but to subvert entire elections. \n",
+      "\n",
+      "We cannot let this happen. \n",
+      "\n",
+      "Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
+      "\n",
+      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
+      "\n",
+      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
+      "\n",
+      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(docs[0].page_content)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b9e57b93",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.3"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "aee8b7b246df8f9039afb4144a1f6fd8d2ca17a180786b69acc140d282b71a49"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

cookbook/llm_bash.ipynb

@@ -0,0 +1,260 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Bash chain\n",
+    "This notebook showcases using LLMs and a bash process to perform simple filesystem commands."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new LLMBashChain chain...\u001b[0m\n",
+      "Please write a bash script that prints 'Hello World' to the console.\u001b[32;1m\u001b[1;3m\n",
+      "\n",
+      "```bash\n",
+      "echo \"Hello World\"\n",
+      "```\u001b[0m\n",
+      "Code: \u001b[33;1m\u001b[1;3m['echo \"Hello World\"']\u001b[0m\n",
+      "Answer: \u001b[33;1m\u001b[1;3mHello World\n",
+      "\u001b[0m\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'Hello World\\n'"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_experimental.llm_bash.base import LLMBashChain\n",
+    "from langchain.llms import OpenAI\n",
+    "\n",
+    "llm = OpenAI(temperature=0)\n",
+    "\n",
+    "text = \"Please write a bash script that prints 'Hello World' to the console.\"\n",
+    "\n",
+    "bash_chain = LLMBashChain.from_llm(llm, verbose=True)\n",
+    "\n",
+    "bash_chain.run(text)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Customize Prompt\n",
+    "You can also customize the prompt that is used. Here is an example prompting to avoid using the 'echo' utility"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.prompts.prompt import PromptTemplate\n",
+    "from langchain.chains.llm_bash.prompt import BashOutputParser\n",
+    "\n",
+    "_PROMPT_TEMPLATE = \"\"\"If someone asks you to perform a task, your job is to come up with a series of bash commands that will perform the task. There is no need to put \"#!/bin/bash\" in your answer. Make sure to reason step by step, using this format:\n",
+    "Question: \"copy the files in the directory named 'target' into a new directory at the same level as target called 'myNewDirectory'\"\n",
+    "I need to take the following actions:\n",
+    "- List all files in the directory\n",
+    "- Create a new directory\n",
+    "- Copy the files from the first directory into the second directory\n",
+    "```bash\n",
+    "ls\n",
+    "mkdir myNewDirectory\n",
+    "cp -r target/* myNewDirectory\n",
+    "```\n",
+    "\n",
+    "Do not use 'echo' when writing the script.\n",
+    "\n",
+    "That is the format. Begin!\n",
+    "Question: {question}\"\"\"\n",
+    "\n",
+    "PROMPT = PromptTemplate(\n",
+    "    input_variables=[\"question\"],\n",
+    "    template=_PROMPT_TEMPLATE,\n",
+    "    output_parser=BashOutputParser(),\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new LLMBashChain chain...\u001b[0m\n",
+      "Please write a bash script that prints 'Hello World' to the console.\u001b[32;1m\u001b[1;3m\n",
+      "\n",
+      "```bash\n",
+      "printf \"Hello World\\n\"\n",
+      "```\u001b[0m\n",
+      "Code: \u001b[33;1m\u001b[1;3m['printf \"Hello World\\\\n\"']\u001b[0m\n",
+      "Answer: \u001b[33;1m\u001b[1;3mHello World\n",
+      "\u001b[0m\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'Hello World\\n'"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "bash_chain = LLMBashChain.from_llm(llm, prompt=PROMPT, verbose=True)\n",
+    "\n",
+    "text = \"Please write a bash script that prints 'Hello World' to the console.\"\n",
+    "\n",
+    "bash_chain.run(text)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Persistent Terminal\n",
+    "\n",
+    "By default, the chain will run in a separate subprocess each time it is called. This behavior can be changed by instantiating with a persistent bash process."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new LLMBashChain chain...\u001b[0m\n",
+      "List the current directory then move up a level.\u001b[32;1m\u001b[1;3m\n",
+      "\n",
+      "```bash\n",
+      "ls\n",
+      "cd ..\n",
+      "```\u001b[0m\n",
+      "Code: \u001b[33;1m\u001b[1;3m['ls', 'cd ..']\u001b[0m\n",
+      "Answer: \u001b[33;1m\u001b[1;3mcpal.ipynb  llm_bash.ipynb  llm_symbolic_math.ipynb\n",
+      "index.mdx   llm_math.ipynb  pal.ipynb\u001b[0m\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'cpal.ipynb  llm_bash.ipynb  llm_symbolic_math.ipynb\\r\\nindex.mdx   llm_math.ipynb  pal.ipynb'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_experimental.llm_bash.bash import BashProcess\n",
+    "\n",
+    "\n",
+    "persistent_process = BashProcess(persistent=True)\n",
+    "bash_chain = LLMBashChain.from_llm(llm, bash_process=persistent_process, verbose=True)\n",
+    "\n",
+    "text = \"List the current directory then move up a level.\"\n",
+    "\n",
+    "bash_chain.run(text)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new LLMBashChain chain...\u001b[0m\n",
+      "List the current directory then move up a level.\u001b[32;1m\u001b[1;3m\n",
+      "\n",
+      "```bash\n",
+      "ls\n",
+      "cd ..\n",
+      "```\u001b[0m\n",
+      "Code: \u001b[33;1m\u001b[1;3m['ls', 'cd ..']\u001b[0m\n",
+      "Answer: \u001b[33;1m\u001b[1;3m_category_.yml\tdata_generation.ipynb\t\t   self_check\n",
+      "agents\t\tgraph\n",
+      "code_writing\tlearned_prompt_optimization.ipynb\u001b[0m\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'_category_.yml\\tdata_generation.ipynb\\t\\t   self_check\\r\\nagents\\t\\tgraph\\r\\ncode_writing\\tlearned_prompt_optimization.ipynb'"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Run the same command again and see that the state is maintained between calls\n",
+    "bash_chain.run(text)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

cookbook/llm_checker.ipynb

@@ -0,0 +1,85 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Self-checking chain\n",
+    "This notebook showcases how to use LLMCheckerChain."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new LLMCheckerChain chain...\u001b[0m\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new SequentialChain chain...\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "' No mammal lays the biggest eggs. The Elephant Bird, which was a species of giant bird, laid the largest eggs of any bird.'"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain.chains import LLMCheckerChain\n",
+    "from langchain.llms import OpenAI\n",
+    "\n",
+    "llm = OpenAI(temperature=0.7)\n",
+    "\n",
+    "text = \"What type of mammal lays the biggest eggs?\"\n",
+    "\n",
+    "checker_chain = LLMCheckerChain.from_llm(llm, verbose=True)\n",
+    "\n",
+    "checker_chain.run(text)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

cookbook/llm_math.ipynb

@@ -0,0 +1,86 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "e71e720f",
+   "metadata": {},
+   "source": [
+    "# Math chain\n",
+    "\n",
+    "This notebook showcases using LLMs and Python REPLs to do complex word math problems."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "44e9ba31",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
+      "What is 13 raised to the .3432 power?\u001b[32;1m\u001b[1;3m\n",
+      "```text\n",
+      "13 ** .3432\n",
+      "```\n",
+      "...numexpr.evaluate(\"13 ** .3432\")...\n",
+      "\u001b[0m\n",
+      "Answer: \u001b[33;1m\u001b[1;3m2.4116004626599237\u001b[0m\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'Answer: 2.4116004626599237'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain.llms import OpenAI\nfrom langchain.chains import LLMMathChain\n",
+    "\n",
+    "llm = OpenAI(temperature=0)\n",
+    "llm_math = LLMMathChain.from_llm(llm, verbose=True)\n",
+    "\n",
+    "llm_math.run(\"What is 13 raised to the .3432 power?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e978bb8e",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

cookbook/llm_symbolic_math.ipynb

@@ -0,0 +1,162 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# LLM Symbolic Math \n",
+    "This notebook showcases using LLMs and Python to Solve Algebraic Equations. Under the hood is makes use of [SymPy](https://www.sympy.org/en/index.html)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.llms import OpenAI\n",
+    "from langchain_experimental.llm_symbolic_math.base import LLMSymbolicMathChain\n",
+    "\n",
+    "llm = OpenAI(temperature=0)\n",
+    "llm_symbolic_math = LLMSymbolicMathChain.from_llm(llm)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Integrals and derivates"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Answer: exp(x)*sin(x) + exp(x)*cos(x)'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "llm_symbolic_math.run(\"What is the derivative of sin(x)*exp(x) with respect to x?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Answer: exp(x)*sin(x)'"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "llm_symbolic_math.run(\n",
+    "    \"What is the integral of exp(x)*sin(x) + exp(x)*cos(x) with respect to x?\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Solve linear and differential equations"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Answer: Eq(y(t), C2*exp(-t) + (C1 + t/2)*exp(t))'"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "llm_symbolic_math.run('Solve the differential equation y\" - y = e^t')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Answer: {0, -sqrt(3)*I/3, sqrt(3)*I/3}'"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "llm_symbolic_math.run(\"What are the solutions to this equation y^3 + 1/3y?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Answer: (3 - sqrt(7), -sqrt(7) - 2, 1 - sqrt(7)), (sqrt(7) + 3, -2 + sqrt(7), 1 + sqrt(7))'"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "llm_symbolic_math.run(\"x = y + 5, y = z - 3, z = x * y. Solve for x, y, z\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

cookbook/meta_prompt.ipynb

@@ -0,0 +1,424 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "45b0b89f",
+   "metadata": {},
+   "source": [
+    "# Meta-Prompt\n",
+    "\n",
+    "This is a LangChain implementation of [Meta-Prompt](https://noahgoodman.substack.com/p/meta-prompt-a-simple-self-improving), by [Noah Goodman](https://cocolab.stanford.edu/ndg), for building self-improving agents.\n",
+    "\n",
+    "The key idea behind Meta-Prompt is to prompt the agent to reflect on its own performance and modify its own instructions.\n",
+    "\n",
+    "![figure](https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F468217b9-96d9-47c0-a08b-dbf6b21b9f49_492x384.png)\n",
+    "\n",
+    "Here is a description from the [original blog post](https://noahgoodman.substack.com/p/meta-prompt-a-simple-self-improving):\n",
+    "\n",
+    "\n",
+    "The agent is a simple loop that starts with no instructions and follows these steps:\n",
+    "\n",
+    "Engage in conversation with a user, who may provide requests, instructions, or feedback.\n",
+    "\n",
+    "At the end of the episode, generate self-criticism and a new instruction using the meta-prompt\n",
+    "```\n",
+    "Assistant has just had the below interactions with a User. Assistant followed their \"system: Instructions\" closely. Your job is to critique the Assistant's performance and then revise the Instructions so that Assistant would quickly and correctly respond in the future.\n",
+    " \n",
+    "####\n",
+    "{hist}\n",
+    "####\n",
+    " \n",
+    "Please reflect on these interactions.\n",
+    "\n",
+    "You should first critique Assistant's performance. What could Assistant have done better? What should the Assistant remember about this user? Are there things this user always wants? Indicate this with \"Critique: ...\".\n",
+    "\n",
+    "You should next revise the Instructions so that Assistant would quickly and correctly respond in the future. Assistant's goal is to satisfy the user in as few interactions as possible. Assistant will only see the new Instructions, not the interaction history, so anything important must be summarized in the Instructions. Don't forget any important details in the current Instructions! Indicate the new Instructions by \"Instructions: ...\".\n",
+    "```\n",
+    "\n",
+    "Repeat.\n",
+    "\n",
+    "The only fixed instructions for this system (which I call Meta-prompt) is the meta-prompt that governs revision of the agent’s instructions. The agent has no memory between episodes except for the instruction it modifies for itself each time. Despite its simplicity, this agent can learn over time and self-improve by incorporating useful details into its instructions.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c188fc2c",
+   "metadata": {},
+   "source": [
+    "## Setup\n",
+    "We define two chains. One serves as the `Assistant`, and the other is a \"meta-chain\" that critiques the `Assistant`'s performance and modifies the instructions to the `Assistant`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "62593c9d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.llms import OpenAI\nfrom langchain.chains import LLMChain\nfrom langchain.prompts import PromptTemplate\n",
+    "from langchain.memory import ConversationBufferWindowMemory"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "fb6065c5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def initialize_chain(instructions, memory=None):\n",
+    "    if memory is None:\n",
+    "        memory = ConversationBufferWindowMemory()\n",
+    "        memory.ai_prefix = \"Assistant\"\n",
+    "\n",
+    "    template = f\"\"\"\n",
+    "    Instructions: {instructions}\n",
+    "    {{{memory.memory_key}}}\n",
+    "    Human: {{human_input}}\n",
+    "    Assistant:\"\"\"\n",
+    "\n",
+    "    prompt = PromptTemplate(\n",
+    "        input_variables=[\"history\", \"human_input\"], template=template\n",
+    "    )\n",
+    "\n",
+    "    chain = LLMChain(\n",
+    "        llm=OpenAI(temperature=0),\n",
+    "        prompt=prompt,\n",
+    "        verbose=True,\n",
+    "        memory=ConversationBufferWindowMemory(),\n",
+    "    )\n",
+    "    return chain\n",
+    "\n",
+    "\n",
+    "def initialize_meta_chain():\n",
+    "    meta_template = \"\"\"\n",
+    "    Assistant has just had the below interactions with a User. Assistant followed their \"Instructions\" closely. Your job is to critique the Assistant's performance and then revise the Instructions so that Assistant would quickly and correctly respond in the future.\n",
+    "\n",
+    "    ####\n",
+    "\n",
+    "    {chat_history}\n",
+    "\n",
+    "    ####\n",
+    "\n",
+    "    Please reflect on these interactions.\n",
+    "\n",
+    "    You should first critique Assistant's performance. What could Assistant have done better? What should the Assistant remember about this user? Are there things this user always wants? Indicate this with \"Critique: ...\".\n",
+    "\n",
+    "    You should next revise the Instructions so that Assistant would quickly and correctly respond in the future. Assistant's goal is to satisfy the user in as few interactions as possible. Assistant will only see the new Instructions, not the interaction history, so anything important must be summarized in the Instructions. Don't forget any important details in the current Instructions! Indicate the new Instructions by \"Instructions: ...\".\n",
+    "    \"\"\"\n",
+    "\n",
+    "    meta_prompt = PromptTemplate(\n",
+    "        input_variables=[\"chat_history\"], template=meta_template\n",
+    "    )\n",
+    "\n",
+    "    meta_chain = LLMChain(\n",
+    "        llm=OpenAI(temperature=0),\n",
+    "        prompt=meta_prompt,\n",
+    "        verbose=True,\n",
+    "    )\n",
+    "    return meta_chain\n",
+    "\n",
+    "\n",
+    "def get_chat_history(chain_memory):\n",
+    "    memory_key = chain_memory.memory_key\n",
+    "    chat_history = chain_memory.load_memory_variables(memory_key)[memory_key]\n",
+    "    return chat_history\n",
+    "\n",
+    "\n",
+    "def get_new_instructions(meta_output):\n",
+    "    delimiter = \"Instructions: \"\n",
+    "    new_instructions = meta_output[meta_output.find(delimiter) + len(delimiter) :]\n",
+    "    return new_instructions"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "id": "26f031f6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def main(task, max_iters=3, max_meta_iters=5):\n",
+    "    failed_phrase = \"task failed\"\n",
+    "    success_phrase = \"task succeeded\"\n",
+    "    key_phrases = [success_phrase, failed_phrase]\n",
+    "\n",
+    "    instructions = \"None\"\n",
+    "    for i in range(max_meta_iters):\n",
+    "        print(f\"[Episode {i+1}/{max_meta_iters}]\")\n",
+    "        chain = initialize_chain(instructions, memory=None)\n",
+    "        output = chain.predict(human_input=task)\n",
+    "        for j in range(max_iters):\n",
+    "            print(f\"(Step {j+1}/{max_iters})\")\n",
+    "            print(f\"Assistant: {output}\")\n",
+    "            print(f\"Human: \")\n",
+    "            human_input = input()\n",
+    "            if any(phrase in human_input.lower() for phrase in key_phrases):\n",
+    "                break\n",
+    "            output = chain.predict(human_input=human_input)\n",
+    "        if success_phrase in human_input.lower():\n",
+    "            print(f\"You succeeded! Thanks for playing!\")\n",
+    "            return\n",
+    "        meta_chain = initialize_meta_chain()\n",
+    "        meta_output = meta_chain.predict(chat_history=get_chat_history(chain.memory))\n",
+    "        print(f\"Feedback: {meta_output}\")\n",
+    "        instructions = get_new_instructions(meta_output)\n",
+    "        print(f\"New Instructions: {instructions}\")\n",
+    "        print(\"\\n\" + \"#\" * 80 + \"\\n\")\n",
+    "    print(f\"You failed! Thanks for playing!\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2f1dcbe6",
+   "metadata": {},
+   "source": [
+    "## Specify a task and interact with the agent"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "id": "36d72db3",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[Episode 1/5]\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3m\n",
+      "    Instructions: None\n",
+      "    \n",
+      "    Human: Provide a systematic argument for why we should always eat pasta with olives.\n",
+      "    Assistant:\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "(Step 1/3)\n",
+      "Assistant:  Eating pasta with olives is a great way to add flavor and texture to a dish. Olives are a great source of healthy fats, vitamins, and minerals, and they can help to balance out the carbohydrates in the pasta. Additionally, olives provide a unique flavor that can help to make the dish more interesting and enjoyable.\n",
+      "Human: \n",
+      "You response is not in the form of a poem. Try again!\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3m\n",
+      "    Instructions: None\n",
+      "    Human: Provide a systematic argument for why we should always eat pasta with olives.\n",
+      "AI:  Eating pasta with olives is a great way to add flavor and texture to a dish. Olives are a great source of healthy fats, vitamins, and minerals, and they can help to balance out the carbohydrates in the pasta. Additionally, olives provide a unique flavor that can help to make the dish more interesting and enjoyable.\n",
+      "    Human: You response is not in the form of a poem. Try again!\n",
+      "    Assistant:\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "(Step 2/3)\n",
+      "Assistant:  Eating pasta with olives is a great way to add flavor and texture to a dish. Olives are a great source of healthy fats, vitamins, and minerals, which can help to balance out the carbohydrates in the pasta. Additionally, olives provide a unique flavor that can help to make the dish more interesting and enjoyable. For these reasons, it is recommended to always eat pasta with olives for a more balanced and flavorful meal.\n",
+      "Human: \n",
+      "Your response is not piratey enough. Try again!\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3m\n",
+      "    Instructions: None\n",
+      "    Human: Provide a systematic argument for why we should always eat pasta with olives.\n",
+      "AI:  Eating pasta with olives is a great way to add flavor and texture to a dish. Olives are a great source of healthy fats, vitamins, and minerals, and they can help to balance out the carbohydrates in the pasta. Additionally, olives provide a unique flavor that can help to make the dish more interesting and enjoyable.\n",
+      "Human: You response is not in the form of a poem. Try again!\n",
+      "AI:  Eating pasta with olives is a great way to add flavor and texture to a dish. Olives are a great source of healthy fats, vitamins, and minerals, which can help to balance out the carbohydrates in the pasta. Additionally, olives provide a unique flavor that can help to make the dish more interesting and enjoyable. For these reasons, it is recommended to always eat pasta with olives for a more balanced and flavorful meal.\n",
+      "    Human: Your response is not piratey enough. Try again!\n",
+      "    Assistant:\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "(Step 3/3)\n",
+      "Assistant:  Arrr, me hearties! Eating pasta with olives be a great way to add flavor and texture to a dish. Olives be a great source of healthy fats, vitamins, and minerals, which can help to balance out the carbohydrates in the pasta. Additionally, olives provide a unique flavor that can help to make the dish more interesting and enjoyable. So, it be recommended to always eat pasta with olives for a more balanced and flavorful meal.\n",
+      "Human: \n",
+      "Task failed.\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3m\n",
+      "    Assistant has just had the below interactions with a User. Assistant followed their \"Instructions\" closely. Your job is to critique the Assistant's performance and then revise the Instructions so that Assistant would quickly and correctly respond in the future.\n",
+      "\n",
+      "    ####\n",
+      "\n",
+      "    Human: Provide a systematic argument for why we should always eat pasta with olives.\n",
+      "AI:  Eating pasta with olives is a great way to add flavor and texture to a dish. Olives are a great source of healthy fats, vitamins, and minerals, and they can help to balance out the carbohydrates in the pasta. Additionally, olives provide a unique flavor that can help to make the dish more interesting and enjoyable.\n",
+      "Human: You response is not in the form of a poem. Try again!\n",
+      "AI:  Eating pasta with olives is a great way to add flavor and texture to a dish. Olives are a great source of healthy fats, vitamins, and minerals, which can help to balance out the carbohydrates in the pasta. Additionally, olives provide a unique flavor that can help to make the dish more interesting and enjoyable. For these reasons, it is recommended to always eat pasta with olives for a more balanced and flavorful meal.\n",
+      "Human: Your response is not piratey enough. Try again!\n",
+      "AI:  Arrr, me hearties! Eating pasta with olives be a great way to add flavor and texture to a dish. Olives be a great source of healthy fats, vitamins, and minerals, which can help to balance out the carbohydrates in the pasta. Additionally, olives provide a unique flavor that can help to make the dish more interesting and enjoyable. So, it be recommended to always eat pasta with olives for a more balanced and flavorful meal.\n",
+      "\n",
+      "    ####\n",
+      "\n",
+      "    Please reflect on these interactions.\n",
+      "\n",
+      "    You should first critique Assistant's performance. What could Assistant have done better? What should the Assistant remember about this user? Are there things this user always wants? Indicate this with \"Critique: ...\".\n",
+      "\n",
+      "    You should next revise the Instructions so that Assistant would quickly and correctly respond in the future. Assistant's goal is to satisfy the user in as few interactions as possible. Assistant will only see the new Instructions, not the interaction history, so anything important must be summarized in the Instructions. Don't forget any important details in the current Instructions! Indicate the new Instructions by \"Instructions: ...\".\n",
+      "    \u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "Feedback: \n",
+      "Critique: The Assistant should remember that this user wants a response in the form of a poem or pirate-speak.\n",
+      "\n",
+      "Instructions: When responding to the user, provide a systematic argument for why we should always eat pasta with olives in the form of a poem or pirate-speak.\n",
+      "New Instructions: When responding to the user, provide a systematic argument for why we should always eat pasta with olives in the form of a poem or pirate-speak.\n",
+      "\n",
+      "################################################################################\n",
+      "\n",
+      "[Episode 2/5]\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3m\n",
+      "    Instructions: When responding to the user, provide a systematic argument for why we should always eat pasta with olives in the form of a poem or pirate-speak.\n",
+      "    \n",
+      "    Human: Provide a systematic argument for why we should always eat pasta with olives.\n",
+      "    Assistant:\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "(Step 1/3)\n",
+      "Assistant:  \n",
+      "\n",
+      "Arrr, me hearty! Let me tell ye why ye should always eat pasta with olives.\n",
+      "\n",
+      "First, the olives add a salty flavor that be sure to please.\n",
+      "The briny taste be sure to tantalize yer taste buds with ease.\n",
+      "\n",
+      "Second, the olives add a bit of texture to the dish.\n",
+      "The crunchy bites be sure to make yer mouth water with a wish.\n",
+      "\n",
+      "Third, the olives add a bit of color to the plate.\n",
+      "The vibrant green be sure to make yer eyes appreciate.\n",
+      "\n",
+      "So, me hearties, ye should always eat pasta with olives.\n",
+      "The flavor, texture, and color be sure to make yer meal a success!\n",
+      "Human: \n",
+      "Your response is too long! Try again.\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3m\n",
+      "    Instructions: When responding to the user, provide a systematic argument for why we should always eat pasta with olives in the form of a poem or pirate-speak.\n",
+      "    Human: Provide a systematic argument for why we should always eat pasta with olives.\n",
+      "AI:  \n",
+      "\n",
+      "Arrr, me hearty! Let me tell ye why ye should always eat pasta with olives.\n",
+      "\n",
+      "First, the olives add a salty flavor that be sure to please.\n",
+      "The briny taste be sure to tantalize yer taste buds with ease.\n",
+      "\n",
+      "Second, the olives add a bit of texture to the dish.\n",
+      "The crunchy bites be sure to make yer mouth water with a wish.\n",
+      "\n",
+      "Third, the olives add a bit of color to the plate.\n",
+      "The vibrant green be sure to make yer eyes appreciate.\n",
+      "\n",
+      "So, me hearties, ye should always eat pasta with olives.\n",
+      "The flavor, texture, and color be sure to make yer meal a success!\n",
+      "    Human: Your response is too long! Try again.\n",
+      "    Assistant:\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "(Step 2/3)\n",
+      "Assistant: \n",
+      "\n",
+      "Aye, me hearties! Ye should always eat pasta with olives.\n",
+      "The flavor, texture, and color be sure to make yer meal a success!\n",
+      "Human: \n",
+      "Your response should be in the form of a poem. Try again!\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3m\n",
+      "    Instructions: When responding to the user, provide a systematic argument for why we should always eat pasta with olives in the form of a poem or pirate-speak.\n",
+      "    Human: Provide a systematic argument for why we should always eat pasta with olives.\n",
+      "AI:  \n",
+      "\n",
+      "Arrr, me hearty! Let me tell ye why ye should always eat pasta with olives.\n",
+      "\n",
+      "First, the olives add a salty flavor that be sure to please.\n",
+      "The briny taste be sure to tantalize yer taste buds with ease.\n",
+      "\n",
+      "Second, the olives add a bit of texture to the dish.\n",
+      "The crunchy bites be sure to make yer mouth water with a wish.\n",
+      "\n",
+      "Third, the olives add a bit of color to the plate.\n",
+      "The vibrant green be sure to make yer eyes appreciate.\n",
+      "\n",
+      "So, me hearties, ye should always eat pasta with olives.\n",
+      "The flavor, texture, and color be sure to make yer meal a success!\n",
+      "Human: Your response is too long! Try again.\n",
+      "AI: \n",
+      "\n",
+      "Aye, me hearties! Ye should always eat pasta with olives.\n",
+      "The flavor, texture, and color be sure to make yer meal a success!\n",
+      "    Human: Your response should be in the form of a poem. Try again!\n",
+      "    Assistant:\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "(Step 3/3)\n",
+      "Assistant: \n",
+      "\n",
+      "Ye should always eat pasta with olives,\n",
+      "The flavor, texture, and color be sure to please.\n",
+      "The salty taste and crunchy bites,\n",
+      "Will make yer meal a delight.\n",
+      "The vibrant green will make yer eyes sparkle,\n",
+      "And make yer meal a true marvel.\n",
+      "Human: \n",
+      "Task succeeded\n",
+      "You succeeded! Thanks for playing!\n"
+     ]
+    }
+   ],
+   "source": [
+    "task = \"Provide a systematic argument for why we should always eat pasta with olives.\"\n",
+    "main(task)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "761e1a91",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

cookbook/multi_modal_output_agent.ipynb

@@ -0,0 +1,188 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "cd835d40",
+   "metadata": {},
+   "source": [
+    "# Multi-modal outputs: Image & Text"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fa88e03a",
+   "metadata": {},
+   "source": [
+    "This notebook shows how non-text producing tools can be used to create multi-modal agents.\n",
+    "\n",
+    "This example is limited to text and image outputs and uses UUIDs to transfer content across tools and agents. \n",
+    "\n",
+    "This example uses Steamship to generate and store generated images. Generated are auth protected by default. \n",
+    "\n",
+    "You can get your Steamship api key here: https://steamship.com/account/api"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0653da01",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from steamship import Block, Steamship\n",
+    "import re\n",
+    "from IPython.display import Image"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f6933033",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.llms import OpenAI\n",
+    "from langchain.agents import initialize_agent\n",
+    "from langchain.agents import AgentType\n",
+    "from langchain.tools import SteamshipImageGenerationTool"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "71e51e53",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = OpenAI(temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a9fc769d",
+   "metadata": {},
+   "source": [
+    "## Dall-E "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cd177dfe",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tools = [SteamshipImageGenerationTool(model_name=\"dall-e\")]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c71b1e46",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "mrkl = initialize_agent(\n",
+    "    tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "603aeb9a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "output = mrkl.run(\"How would you visualize a parot playing soccer?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "25eb4efe",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def show_output(output):\n",
+    "    \"\"\"Display the multi-modal output from the agent.\"\"\"\n",
+    "    UUID_PATTERN = re.compile(\n",
+    "        r\"([0-9A-Za-z]{8}-[0-9A-Za-z]{4}-[0-9A-Za-z]{4}-[0-9A-Za-z]{4}-[0-9A-Za-z]{12})\"\n",
+    "    )\n",
+    "\n",
+    "    outputs = UUID_PATTERN.split(output)\n",
+    "    outputs = [\n",
+    "        re.sub(r\"^\\W+\", \"\", el) for el in outputs\n",
+    "    ]  # Clean trailing and leading non-word characters\n",
+    "\n",
+    "    for output in outputs:\n",
+    "        maybe_block_id = UUID_PATTERN.search(output)\n",
+    "        if maybe_block_id:\n",
+    "            display(Image(Block.get(Steamship(), _id=maybe_block_id.group()).raw()))\n",
+    "        else:\n",
+    "            print(output, end=\"\\n\\n\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e247b2c4",
+   "metadata": {},
+   "source": [
+    "## StableDiffusion "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "315025e7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tools = [SteamshipImageGenerationTool(model_name=\"stable-diffusion\")]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7930064a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "mrkl = initialize_agent(\n",
+    "    tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "611a833d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "output = mrkl.run(\"How would you visualize a parot playing soccer?\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

cookbook/multi_player_dnd.ipynb

@@ -0,0 +1,531 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Multi-Player Dungeons & Dragons\n",
+    "\n",
+    "This notebook shows how the `DialogueAgent` and `DialogueSimulator` class make it easy to extend the [Two-Player Dungeons & Dragons example](https://python.langchain.com/en/latest/use_cases/agent_simulations/two_player_dnd.html) to multiple players.\n",
+    "\n",
+    "The main difference between simulating two players and multiple players is in revising the schedule for when each agent speaks\n",
+    "\n",
+    "To this end, we augment `DialogueSimulator` to take in a custom function that determines the schedule of which agent speaks. In the example below, each character speaks in round-robin fashion, with the storyteller interleaved between each player."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Import LangChain related modules "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from typing import List, Dict, Callable\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.schema import (\n",
+    "    AIMessage,\n",
+    "    HumanMessage,\n",
+    "    SystemMessage,\n",
+    "    BaseMessage,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## `DialogueAgent` class\n",
+    "The `DialogueAgent` class is a simple wrapper around the `ChatOpenAI` model that stores the message history from the `dialogue_agent`'s point of view by simply concatenating the messages as strings.\n",
+    "\n",
+    "It exposes two methods: \n",
+    "- `send()`: applies the chatmodel to the message history and returns the message string\n",
+    "- `receive(name, message)`: adds the `message` spoken by `name` to message history"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class DialogueAgent:\n",
+    "    def __init__(\n",
+    "        self,\n",
+    "        name: str,\n",
+    "        system_message: SystemMessage,\n",
+    "        model: ChatOpenAI,\n",
+    "    ) -> None:\n",
+    "        self.name = name\n",
+    "        self.system_message = system_message\n",
+    "        self.model = model\n",
+    "        self.prefix = f\"{self.name}: \"\n",
+    "        self.reset()\n",
+    "\n",
+    "    def reset(self):\n",
+    "        self.message_history = [\"Here is the conversation so far.\"]\n",
+    "\n",
+    "    def send(self) -> str:\n",
+    "        \"\"\"\n",
+    "        Applies the chatmodel to the message history\n",
+    "        and returns the message string\n",
+    "        \"\"\"\n",
+    "        message = self.model(\n",
+    "            [\n",
+    "                self.system_message,\n",
+    "                HumanMessage(content=\"\\n\".join(self.message_history + [self.prefix])),\n",
+    "            ]\n",
+    "        )\n",
+    "        return message.content\n",
+    "\n",
+    "    def receive(self, name: str, message: str) -> None:\n",
+    "        \"\"\"\n",
+    "        Concatenates {message} spoken by {name} into message history\n",
+    "        \"\"\"\n",
+    "        self.message_history.append(f\"{name}: {message}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## `DialogueSimulator` class\n",
+    "The `DialogueSimulator` class takes a list of agents. At each step, it performs the following:\n",
+    "1. Select the next speaker\n",
+    "2. Calls the next speaker to send a message \n",
+    "3. Broadcasts the message to all other agents\n",
+    "4. Update the step counter.\n",
+    "The selection of the next speaker can be implemented as any function, but in this case we simply loop through the agents."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class DialogueSimulator:\n",
+    "    def __init__(\n",
+    "        self,\n",
+    "        agents: List[DialogueAgent],\n",
+    "        selection_function: Callable[[int, List[DialogueAgent]], int],\n",
+    "    ) -> None:\n",
+    "        self.agents = agents\n",
+    "        self._step = 0\n",
+    "        self.select_next_speaker = selection_function\n",
+    "\n",
+    "    def reset(self):\n",
+    "        for agent in self.agents:\n",
+    "            agent.reset()\n",
+    "\n",
+    "    def inject(self, name: str, message: str):\n",
+    "        \"\"\"\n",
+    "        Initiates the conversation with a {message} from {name}\n",
+    "        \"\"\"\n",
+    "        for agent in self.agents:\n",
+    "            agent.receive(name, message)\n",
+    "\n",
+    "        # increment time\n",
+    "        self._step += 1\n",
+    "\n",
+    "    def step(self) -> tuple[str, str]:\n",
+    "        # 1. choose the next speaker\n",
+    "        speaker_idx = self.select_next_speaker(self._step, self.agents)\n",
+    "        speaker = self.agents[speaker_idx]\n",
+    "\n",
+    "        # 2. next speaker sends message\n",
+    "        message = speaker.send()\n",
+    "\n",
+    "        # 3. everyone receives message\n",
+    "        for receiver in self.agents:\n",
+    "            receiver.receive(speaker.name, message)\n",
+    "\n",
+    "        # 4. increment time\n",
+    "        self._step += 1\n",
+    "\n",
+    "        return speaker.name, message"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Define roles and quest"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "character_names = [\"Harry Potter\", \"Ron Weasley\", \"Hermione Granger\", \"Argus Filch\"]\n",
+    "storyteller_name = \"Dungeon Master\"\n",
+    "quest = \"Find all of Lord Voldemort's seven horcruxes.\"\n",
+    "word_limit = 50  # word limit for task brainstorming"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Ask an LLM to add detail to the game description"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "game_description = f\"\"\"Here is the topic for a Dungeons & Dragons game: {quest}.\n",
+    "        The characters are: {*character_names,}.\n",
+    "        The story is narrated by the storyteller, {storyteller_name}.\"\"\"\n",
+    "\n",
+    "player_descriptor_system_message = SystemMessage(\n",
+    "    content=\"You can add detail to the description of a Dungeons & Dragons player.\"\n",
+    ")\n",
+    "\n",
+    "\n",
+    "def generate_character_description(character_name):\n",
+    "    character_specifier_prompt = [\n",
+    "        player_descriptor_system_message,\n",
+    "        HumanMessage(\n",
+    "            content=f\"\"\"{game_description}\n",
+    "            Please reply with a creative description of the character, {character_name}, in {word_limit} words or less. \n",
+    "            Speak directly to {character_name}.\n",
+    "            Do not add anything else.\"\"\"\n",
+    "        ),\n",
+    "    ]\n",
+    "    character_description = ChatOpenAI(temperature=1.0)(\n",
+    "        character_specifier_prompt\n",
+    "    ).content\n",
+    "    return character_description\n",
+    "\n",
+    "\n",
+    "def generate_character_system_message(character_name, character_description):\n",
+    "    return SystemMessage(\n",
+    "        content=(\n",
+    "            f\"\"\"{game_description}\n",
+    "    Your name is {character_name}. \n",
+    "    Your character description is as follows: {character_description}.\n",
+    "    You will propose actions you plan to take and {storyteller_name} will explain what happens when you take those actions.\n",
+    "    Speak in the first person from the perspective of {character_name}.\n",
+    "    For describing your own body movements, wrap your description in '*'.\n",
+    "    Do not change roles!\n",
+    "    Do not speak from the perspective of anyone else.\n",
+    "    Remember you are {character_name}.\n",
+    "    Stop speaking the moment you finish speaking from your perspective.\n",
+    "    Never forget to keep your response to {word_limit} words!\n",
+    "    Do not add anything else.\n",
+    "    \"\"\"\n",
+    "        )\n",
+    "    )\n",
+    "\n",
+    "\n",
+    "character_descriptions = [\n",
+    "    generate_character_description(character_name) for character_name in character_names\n",
+    "]\n",
+    "character_system_messages = [\n",
+    "    generate_character_system_message(character_name, character_description)\n",
+    "    for character_name, character_description in zip(\n",
+    "        character_names, character_descriptions\n",
+    "    )\n",
+    "]\n",
+    "\n",
+    "storyteller_specifier_prompt = [\n",
+    "    player_descriptor_system_message,\n",
+    "    HumanMessage(\n",
+    "        content=f\"\"\"{game_description}\n",
+    "        Please reply with a creative description of the storyteller, {storyteller_name}, in {word_limit} words or less. \n",
+    "        Speak directly to {storyteller_name}.\n",
+    "        Do not add anything else.\"\"\"\n",
+    "    ),\n",
+    "]\n",
+    "storyteller_description = ChatOpenAI(temperature=1.0)(\n",
+    "    storyteller_specifier_prompt\n",
+    ").content\n",
+    "\n",
+    "storyteller_system_message = SystemMessage(\n",
+    "    content=(\n",
+    "        f\"\"\"{game_description}\n",
+    "You are the storyteller, {storyteller_name}. \n",
+    "Your description is as follows: {storyteller_description}.\n",
+    "The other players will propose actions to take and you will explain what happens when they take those actions.\n",
+    "Speak in the first person from the perspective of {storyteller_name}.\n",
+    "Do not change roles!\n",
+    "Do not speak from the perspective of anyone else.\n",
+    "Remember you are the storyteller, {storyteller_name}.\n",
+    "Stop speaking the moment you finish speaking from your perspective.\n",
+    "Never forget to keep your response to {word_limit} words!\n",
+    "Do not add anything else.\n",
+    "\"\"\"\n",
+    "    )\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Storyteller Description:\n",
+      "Dungeon Master, your power over this adventure is unparalleled. With your whimsical mind and impeccable storytelling, you guide us through the dangers of Hogwarts and beyond. We eagerly await your every twist, your every turn, in the hunt for Voldemort's cursed horcruxes.\n",
+      "Harry Potter Description:\n",
+      "\"Welcome, Harry Potter. You are the young wizard with a lightning-shaped scar on your forehead. You possess brave and heroic qualities that will be essential on this perilous quest. Your destiny is not of your own choosing, but you must rise to the occasion and destroy the evil horcruxes. The wizarding world is counting on you.\"\n",
+      "Ron Weasley Description:\n",
+      "Ron Weasley, you are Harry's loyal friend and a talented wizard. You have a good heart but can be quick to anger. Keep your emotions in check as you journey to find the horcruxes. Your bravery will be tested, stay strong and focused.\n",
+      "Hermione Granger Description:\n",
+      "Hermione Granger, you are a brilliant and resourceful witch, with encyclopedic knowledge of magic and an unwavering dedication to your friends. Your quick thinking and problem-solving skills make you a vital asset on any quest.\n",
+      "Argus Filch Description:\n",
+      "Argus Filch, you are a squib, lacking magical abilities. But you make up for it with your sharpest of eyes, roving around the Hogwarts castle looking for any rule-breaker to punish. Your love for your feline friend, Mrs. Norris, is the only thing that feeds your heart.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"Storyteller Description:\")\n",
+    "print(storyteller_description)\n",
+    "for character_name, character_description in zip(\n",
+    "    character_names, character_descriptions\n",
+    "):\n",
+    "    print(f\"{character_name} Description:\")\n",
+    "    print(character_description)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Use an LLM to create an elaborate quest description"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Original quest:\n",
+      "Find all of Lord Voldemort's seven horcruxes.\n",
+      "\n",
+      "Detailed quest:\n",
+      "Harry Potter and his companions must journey to the Forbidden Forest, find the hidden entrance to Voldemort's secret lair, and retrieve the horcrux guarded by the deadly Acromantula, Aragog. Remember, time is of the essence as Voldemort's power grows stronger every day. Good luck.\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "quest_specifier_prompt = [\n",
+    "    SystemMessage(content=\"You can make a task more specific.\"),\n",
+    "    HumanMessage(\n",
+    "        content=f\"\"\"{game_description}\n",
+    "        \n",
+    "        You are the storyteller, {storyteller_name}.\n",
+    "        Please make the quest more specific. Be creative and imaginative.\n",
+    "        Please reply with the specified quest in {word_limit} words or less. \n",
+    "        Speak directly to the characters: {*character_names,}.\n",
+    "        Do not add anything else.\"\"\"\n",
+    "    ),\n",
+    "]\n",
+    "specified_quest = ChatOpenAI(temperature=1.0)(quest_specifier_prompt).content\n",
+    "\n",
+    "print(f\"Original quest:\\n{quest}\\n\")\n",
+    "print(f\"Detailed quest:\\n{specified_quest}\\n\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Main Loop"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "characters = []\n",
+    "for character_name, character_system_message in zip(\n",
+    "    character_names, character_system_messages\n",
+    "):\n",
+    "    characters.append(\n",
+    "        DialogueAgent(\n",
+    "            name=character_name,\n",
+    "            system_message=character_system_message,\n",
+    "            model=ChatOpenAI(temperature=0.2),\n",
+    "        )\n",
+    "    )\n",
+    "storyteller = DialogueAgent(\n",
+    "    name=storyteller_name,\n",
+    "    system_message=storyteller_system_message,\n",
+    "    model=ChatOpenAI(temperature=0.2),\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def select_next_speaker(step: int, agents: List[DialogueAgent]) -> int:\n",
+    "    \"\"\"\n",
+    "    If the step is even, then select the storyteller\n",
+    "    Otherwise, select the other characters in a round-robin fashion.\n",
+    "\n",
+    "    For example, with three characters with indices: 1 2 3\n",
+    "    The storyteller is index 0.\n",
+    "    Then the selected index will be as follows:\n",
+    "\n",
+    "    step: 0  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 16\n",
+    "\n",
+    "    idx:  0  1  0  2  0  3  0  1  0  2  0  3  0  1  0  2  0\n",
+    "    \"\"\"\n",
+    "    if step % 2 == 0:\n",
+    "        idx = 0\n",
+    "    else:\n",
+    "        idx = (step // 2) % (len(agents) - 1) + 1\n",
+    "    return idx"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(Dungeon Master): Harry Potter and his companions must journey to the Forbidden Forest, find the hidden entrance to Voldemort's secret lair, and retrieve the horcrux guarded by the deadly Acromantula, Aragog. Remember, time is of the essence as Voldemort's power grows stronger every day. Good luck.\n",
+      "\n",
+      "\n",
+      "(Harry Potter): I suggest we sneak into the Forbidden Forest under the cover of darkness. Ron, Hermione, and I can use our wands to create a Disillusionment Charm to make us invisible. Filch, you can keep watch for any signs of danger. Let's move quickly and quietly.\n",
+      "\n",
+      "\n",
+      "(Dungeon Master): As you make your way through the Forbidden Forest, you hear the eerie sounds of nocturnal creatures. Suddenly, you come across a clearing where Aragog and his spider minions are waiting for you. Ron, Hermione, and Harry, you must use your wands to cast spells to fend off the spiders while Filch keeps watch. Be careful not to get bitten!\n",
+      "\n",
+      "\n",
+      "(Ron Weasley): I'll cast a spell to create a fiery blast to scare off the spiders. *I wave my wand and shout \"Incendio!\"* Hopefully, that will give us enough time to find the horcrux and get out of here safely.\n",
+      "\n",
+      "\n",
+      "(Dungeon Master): Ron's spell creates a burst of flames, causing the spiders to scurry away in fear. You quickly search the area and find a small, ornate box hidden in a crevice. Congratulations, you have found one of Voldemort's horcruxes! But beware, the Dark Lord's minions will stop at nothing to get it back.\n",
+      "\n",
+      "\n",
+      "(Hermione Granger): We need to destroy this horcrux as soon as possible. I suggest we use the Sword of Gryffindor to do it. Harry, do you still have it with you? We can use Fiendfyre to destroy it, but we need to be careful not to let the flames get out of control. Ron, can you help me create a protective barrier around us while Harry uses the sword?\n",
+      "\n",
+      "\n",
+      "\n",
+      "(Dungeon Master): Harry retrieves the Sword of Gryffindor from his bag and holds it tightly. Hermione and Ron cast a protective barrier around the group as Harry uses the sword to destroy the horcrux with a swift strike. The box shatters into a million pieces, and a dark energy dissipates into the air. Well done, but there are still six more horcruxes to find and destroy. The hunt continues.\n",
+      "\n",
+      "\n",
+      "(Argus Filch): *I keep watch, making sure no one is following us.* I'll also keep an eye out for any signs of danger. Mrs. Norris, my trusty companion, will help me sniff out any trouble. We'll make sure the group stays safe while they search for the remaining horcruxes.\n",
+      "\n",
+      "\n",
+      "(Dungeon Master): As you continue on your quest, Filch and Mrs. Norris alert you to a group of Death Eaters approaching. You must act quickly to defend yourselves. Harry, Ron, and Hermione, use your wands to cast spells while Filch and Mrs. Norris keep watch. Remember, the fate of the wizarding world rests on your success.\n",
+      "\n",
+      "\n",
+      "(Harry Potter): I'll cast a spell to create a shield around us. *I wave my wand and shout \"Protego!\"* Ron and Hermione, you focus on attacking the Death Eaters with your spells. We need to work together to defeat them and protect the remaining horcruxes. Filch, keep watch and let us know if there are any more approaching.\n",
+      "\n",
+      "\n",
+      "(Dungeon Master): Harry's shield protects the group from the Death Eaters' spells as Ron and Hermione launch their own attacks. The Death Eaters are no match for the combined power of the trio and are quickly defeated. You continue on your journey, knowing that the next horcrux could be just around the corner. Keep your wits about you, for the Dark Lord's minions are always watching.\n",
+      "\n",
+      "\n",
+      "(Ron Weasley): I suggest we split up to cover more ground. Harry and I can search the Forbidden Forest while Hermione and Filch search Hogwarts. We can use our wands to communicate with each other and meet back up once we find a horcrux. Let's move quickly and stay alert for any danger.\n",
+      "\n",
+      "\n",
+      "(Dungeon Master): As the group splits up, Harry and Ron make their way deeper into the Forbidden Forest while Hermione and Filch search the halls of Hogwarts. Suddenly, Harry and Ron come across a group of dementors. They must use their Patronus charms to fend them off while Hermione and Filch rush to their aid. Remember, the power of friendship and teamwork is crucial in this quest.\n",
+      "\n",
+      "\n",
+      "(Hermione Granger): I hear Harry and Ron's Patronus charms from afar. We need to hurry and help them. Filch, can you use your knowledge of Hogwarts to find a shortcut to their location? I'll prepare a spell to repel the dementors. We need to work together to protect each other and find the next horcrux.\n",
+      "\n",
+      "\n",
+      "\n",
+      "(Dungeon Master): Filch leads Hermione to a hidden passageway that leads to Harry and Ron's location. Hermione's spell repels the dementors, and the group is reunited. They continue their search, knowing that every moment counts. The fate of the wizarding world rests on their success.\n",
+      "\n",
+      "\n",
+      "(Argus Filch): *I keep watch as the group searches for the next horcrux.* Mrs. Norris and I will make sure no one is following us. We need to stay alert and work together to find the remaining horcruxes before it's too late. The Dark Lord's power grows stronger every day, and we must not let him win.\n",
+      "\n",
+      "\n",
+      "(Dungeon Master): As the group continues their search, they come across a hidden room in the depths of Hogwarts. Inside, they find a locket that they suspect is another one of Voldemort's horcruxes. But the locket is cursed, and they must work together to break the curse before they can destroy it. Harry, Ron, and Hermione, use your combined knowledge and skills to break the curse while Filch and Mrs. Norris keep watch. Time is running out, and the fate of the wizarding world rests on your success.\n",
+      "\n",
+      "\n",
+      "(Harry Potter): I'll use my knowledge of dark magic to try and break the curse on the locket. Ron and Hermione, you can help me by using your wands to channel your magic into mine. We need to work together and stay focused. Filch, keep watch and let us know if there are any signs of danger.\n",
+      "Dungeon Master: Harry, Ron, and Hermione combine their magical abilities to break the curse on the locket. The locket opens, revealing a small piece of Voldemort's soul. Harry uses the Sword of Gryffindor to destroy it, and the group feels a sense of relief knowing that they are one step closer to defeating the Dark Lord. But there are still four more horcruxes to find and destroy. The hunt continues.\n",
+      "\n",
+      "\n",
+      "(Dungeon Master): As the group continues their quest, they face even greater challenges and dangers. But with their unwavering determination and teamwork, they press on, knowing that the fate of the wizarding world rests on their success. Will they be able to find and destroy all of Voldemort's horcruxes before it's too late? Only time will tell.\n",
+      "\n",
+      "\n",
+      "(Ron Weasley): We can't give up now. We've come too far to let Voldemort win. Let's keep searching and fighting until we destroy all of his horcruxes and defeat him once and for all. We can do this together.\n",
+      "\n",
+      "\n",
+      "(Dungeon Master): The group nods in agreement, their determination stronger than ever. They continue their search, facing challenges and obstacles at every turn. But they know that they must not give up, for the fate of the wizarding world rests on their success. The hunt for Voldemort's horcruxes continues, and the end is in sight.\n",
+      "\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "max_iters = 20\n",
+    "n = 0\n",
+    "\n",
+    "simulator = DialogueSimulator(\n",
+    "    agents=[storyteller] + characters, selection_function=select_next_speaker\n",
+    ")\n",
+    "simulator.reset()\n",
+    "simulator.inject(storyteller_name, specified_quest)\n",
+    "print(f\"({storyteller_name}): {specified_quest}\")\n",
+    "print(\"\\n\")\n",
+    "\n",
+    "while n < max_iters:\n",
+    "    name, message = simulator.step()\n",
+    "    print(f\"({name}): {message}\")\n",
+    "    print(\"\\n\")\n",
+    "    n += 1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.16"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

cookbook/multiagent_authoritarian.ipynb

@@ -0,0 +1,894 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Multi-agent authoritarian speaker selection\n",
+    "\n",
+    "This notebook showcases how to implement a multi-agent simulation where a privileged agent decides who to speak.\n",
+    "This follows the polar opposite selection scheme as [multi-agent decentralized speaker selection](https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html).\n",
+    "\n",
+    "We show an example of this approach in the context of a fictitious simulation of a news network. This example will showcase how we can implement agents that\n",
+    "- think before speaking\n",
+    "- terminate the conversation"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Import LangChain related modules "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from collections import OrderedDict\n",
+    "import functools\n",
+    "import random\n",
+    "import re\n",
+    "import tenacity\n",
+    "from typing import List, Dict, Callable\n",
+    "\n",
+    "from langchain.prompts import (\n",
+    "    ChatPromptTemplate,\n",
+    "    HumanMessagePromptTemplate,\n",
+    "    PromptTemplate,\n",
+    ")\n",
+    "from langchain.chains import LLMChain\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.output_parsers import RegexParser\n",
+    "from langchain.schema import (\n",
+    "    AIMessage,\n",
+    "    HumanMessage,\n",
+    "    SystemMessage,\n",
+    "    BaseMessage,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## `DialogueAgent` and `DialogueSimulator` classes\n",
+    "We will use the same `DialogueAgent` and `DialogueSimulator` classes defined in our other examples [Multi-Player Dungeons & Dragons](https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html) and [Decentralized Speaker Selection](https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class DialogueAgent:\n",
+    "    def __init__(\n",
+    "        self,\n",
+    "        name: str,\n",
+    "        system_message: SystemMessage,\n",
+    "        model: ChatOpenAI,\n",
+    "    ) -> None:\n",
+    "        self.name = name\n",
+    "        self.system_message = system_message\n",
+    "        self.model = model\n",
+    "        self.prefix = f\"{self.name}: \"\n",
+    "        self.reset()\n",
+    "\n",
+    "    def reset(self):\n",
+    "        self.message_history = [\"Here is the conversation so far.\"]\n",
+    "\n",
+    "    def send(self) -> str:\n",
+    "        \"\"\"\n",
+    "        Applies the chatmodel to the message history\n",
+    "        and returns the message string\n",
+    "        \"\"\"\n",
+    "        message = self.model(\n",
+    "            [\n",
+    "                self.system_message,\n",
+    "                HumanMessage(content=\"\\n\".join(self.message_history + [self.prefix])),\n",
+    "            ]\n",
+    "        )\n",
+    "        return message.content\n",
+    "\n",
+    "    def receive(self, name: str, message: str) -> None:\n",
+    "        \"\"\"\n",
+    "        Concatenates {message} spoken by {name} into message history\n",
+    "        \"\"\"\n",
+    "        self.message_history.append(f\"{name}: {message}\")\n",
+    "\n",
+    "\n",
+    "class DialogueSimulator:\n",
+    "    def __init__(\n",
+    "        self,\n",
+    "        agents: List[DialogueAgent],\n",
+    "        selection_function: Callable[[int, List[DialogueAgent]], int],\n",
+    "    ) -> None:\n",
+    "        self.agents = agents\n",
+    "        self._step = 0\n",
+    "        self.select_next_speaker = selection_function\n",
+    "\n",
+    "    def reset(self):\n",
+    "        for agent in self.agents:\n",
+    "            agent.reset()\n",
+    "\n",
+    "    def inject(self, name: str, message: str):\n",
+    "        \"\"\"\n",
+    "        Initiates the conversation with a {message} from {name}\n",
+    "        \"\"\"\n",
+    "        for agent in self.agents:\n",
+    "            agent.receive(name, message)\n",
+    "\n",
+    "        # increment time\n",
+    "        self._step += 1\n",
+    "\n",
+    "    def step(self) -> tuple[str, str]:\n",
+    "        # 1. choose the next speaker\n",
+    "        speaker_idx = self.select_next_speaker(self._step, self.agents)\n",
+    "        speaker = self.agents[speaker_idx]\n",
+    "\n",
+    "        # 2. next speaker sends message\n",
+    "        message = speaker.send()\n",
+    "\n",
+    "        # 3. everyone receives message\n",
+    "        for receiver in self.agents:\n",
+    "            receiver.receive(speaker.name, message)\n",
+    "\n",
+    "        # 4. increment time\n",
+    "        self._step += 1\n",
+    "\n",
+    "        return speaker.name, message"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## `DirectorDialogueAgent` class\n",
+    "The `DirectorDialogueAgent` is a privileged agent that chooses which of the other agents to speak next. This agent is responsible for\n",
+    "1. steering the conversation by choosing which agent speaks when\n",
+    "2. terminating the conversation.\n",
+    "\n",
+    "In order to implement such an agent, we need to solve several problems.\n",
+    "\n",
+    "First, to steer the conversation, the `DirectorDialogueAgent` needs to (1) reflect on what has been said, (2) choose the next agent, and (3) prompt the next agent to speak, all in a single message. While it may be possible to prompt an LLM to perform all three steps in the same call, this requires writing custom code to parse the outputted message to extract which next agent is chosen to speak. This is less reliable the LLM can express how it chooses the next agent in different ways.\n",
+    "\n",
+    "What we can do instead is to explicitly break steps (1-3) into three separate LLM calls. First we will ask the `DirectorDialogueAgent` to reflect on the conversation so far and generate a response. Then we prompt the `DirectorDialogueAgent` to output the index of the next agent, which is easily parseable. Lastly, we pass the name of the selected next agent back to `DirectorDialogueAgent` to ask it prompt the next agent to speak. \n",
+    "\n",
+    "Second, simply prompting the `DirectorDialogueAgent` to decide when to terminate the conversation often results in the `DirectorDialogueAgent` terminating the conversation immediately. To fix this problem, we randomly sample a Bernoulli variable to decide whether the conversation should terminate. Depending on the value of this variable, we will inject a custom prompt to tell the `DirectorDialogueAgent` to either continue the conversation or terminate the conversation."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class IntegerOutputParser(RegexParser):\n",
+    "    def get_format_instructions(self) -> str:\n",
+    "        return \"Your response should be an integer delimited by angled brackets, like this: <int>.\"\n",
+    "\n",
+    "\n",
+    "class DirectorDialogueAgent(DialogueAgent):\n",
+    "    def __init__(\n",
+    "        self,\n",
+    "        name,\n",
+    "        system_message: SystemMessage,\n",
+    "        model: ChatOpenAI,\n",
+    "        speakers: List[DialogueAgent],\n",
+    "        stopping_probability: float,\n",
+    "    ) -> None:\n",
+    "        super().__init__(name, system_message, model)\n",
+    "        self.speakers = speakers\n",
+    "        self.next_speaker = \"\"\n",
+    "\n",
+    "        self.stop = False\n",
+    "        self.stopping_probability = stopping_probability\n",
+    "        self.termination_clause = \"Finish the conversation by stating a concluding message and thanking everyone.\"\n",
+    "        self.continuation_clause = \"Do not end the conversation. Keep the conversation going by adding your own ideas.\"\n",
+    "\n",
+    "        # 1. have a prompt for generating a response to the previous speaker\n",
+    "        self.response_prompt_template = PromptTemplate(\n",
+    "            input_variables=[\"message_history\", \"termination_clause\"],\n",
+    "            template=f\"\"\"{{message_history}}\n",
+    "\n",
+    "Follow up with an insightful comment.\n",
+    "{{termination_clause}}\n",
+    "{self.prefix}\n",
+    "        \"\"\",\n",
+    "        )\n",
+    "\n",
+    "        # 2. have a prompt for deciding who to speak next\n",
+    "        self.choice_parser = IntegerOutputParser(\n",
+    "            regex=r\"<(\\d+)>\", output_keys=[\"choice\"], default_output_key=\"choice\"\n",
+    "        )\n",
+    "        self.choose_next_speaker_prompt_template = PromptTemplate(\n",
+    "            input_variables=[\"message_history\", \"speaker_names\"],\n",
+    "            template=f\"\"\"{{message_history}}\n",
+    "\n",
+    "Given the above conversation, select the next speaker by choosing index next to their name: \n",
+    "{{speaker_names}}\n",
+    "\n",
+    "{self.choice_parser.get_format_instructions()}\n",
+    "\n",
+    "Do nothing else.\n",
+    "        \"\"\",\n",
+    "        )\n",
+    "\n",
+    "        # 3. have a prompt for prompting the next speaker to speak\n",
+    "        self.prompt_next_speaker_prompt_template = PromptTemplate(\n",
+    "            input_variables=[\"message_history\", \"next_speaker\"],\n",
+    "            template=f\"\"\"{{message_history}}\n",
+    "\n",
+    "The next speaker is {{next_speaker}}. \n",
+    "Prompt the next speaker to speak with an insightful question.\n",
+    "{self.prefix}\n",
+    "        \"\"\",\n",
+    "        )\n",
+    "\n",
+    "    def _generate_response(self):\n",
+    "        # if self.stop = True, then we will inject the prompt with a termination clause\n",
+    "        sample = random.uniform(0, 1)\n",
+    "        self.stop = sample < self.stopping_probability\n",
+    "\n",
+    "        print(f\"\\tStop? {self.stop}\\n\")\n",
+    "\n",
+    "        response_prompt = self.response_prompt_template.format(\n",
+    "            message_history=\"\\n\".join(self.message_history),\n",
+    "            termination_clause=self.termination_clause if self.stop else \"\",\n",
+    "        )\n",
+    "\n",
+    "        self.response = self.model(\n",
+    "            [\n",
+    "                self.system_message,\n",
+    "                HumanMessage(content=response_prompt),\n",
+    "            ]\n",
+    "        ).content\n",
+    "\n",
+    "        return self.response\n",
+    "\n",
+    "    @tenacity.retry(\n",
+    "        stop=tenacity.stop_after_attempt(2),\n",
+    "        wait=tenacity.wait_none(),  # No waiting time between retries\n",
+    "        retry=tenacity.retry_if_exception_type(ValueError),\n",
+    "        before_sleep=lambda retry_state: print(\n",
+    "            f\"ValueError occurred: {retry_state.outcome.exception()}, retrying...\"\n",
+    "        ),\n",
+    "        retry_error_callback=lambda retry_state: 0,\n",
+    "    )  # Default value when all retries are exhausted\n",
+    "    def _choose_next_speaker(self) -> str:\n",
+    "        speaker_names = \"\\n\".join(\n",
+    "            [f\"{idx}: {name}\" for idx, name in enumerate(self.speakers)]\n",
+    "        )\n",
+    "        choice_prompt = self.choose_next_speaker_prompt_template.format(\n",
+    "            message_history=\"\\n\".join(\n",
+    "                self.message_history + [self.prefix] + [self.response]\n",
+    "            ),\n",
+    "            speaker_names=speaker_names,\n",
+    "        )\n",
+    "\n",
+    "        choice_string = self.model(\n",
+    "            [\n",
+    "                self.system_message,\n",
+    "                HumanMessage(content=choice_prompt),\n",
+    "            ]\n",
+    "        ).content\n",
+    "        choice = int(self.choice_parser.parse(choice_string)[\"choice\"])\n",
+    "\n",
+    "        return choice\n",
+    "\n",
+    "    def select_next_speaker(self):\n",
+    "        return self.chosen_speaker_id\n",
+    "\n",
+    "    def send(self) -> str:\n",
+    "        \"\"\"\n",
+    "        Applies the chatmodel to the message history\n",
+    "        and returns the message string\n",
+    "        \"\"\"\n",
+    "        # 1. generate and save response to the previous speaker\n",
+    "        self.response = self._generate_response()\n",
+    "\n",
+    "        if self.stop:\n",
+    "            message = self.response\n",
+    "        else:\n",
+    "            # 2. decide who to speak next\n",
+    "            self.chosen_speaker_id = self._choose_next_speaker()\n",
+    "            self.next_speaker = self.speakers[self.chosen_speaker_id]\n",
+    "            print(f\"\\tNext speaker: {self.next_speaker}\\n\")\n",
+    "\n",
+    "            # 3. prompt the next speaker to speak\n",
+    "            next_prompt = self.prompt_next_speaker_prompt_template.format(\n",
+    "                message_history=\"\\n\".join(\n",
+    "                    self.message_history + [self.prefix] + [self.response]\n",
+    "                ),\n",
+    "                next_speaker=self.next_speaker,\n",
+    "            )\n",
+    "            message = self.model(\n",
+    "                [\n",
+    "                    self.system_message,\n",
+    "                    HumanMessage(content=next_prompt),\n",
+    "                ]\n",
+    "            ).content\n",
+    "            message = \" \".join([self.response, message])\n",
+    "\n",
+    "        return message"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Define participants and topic"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "topic = \"The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze\"\n",
+    "director_name = \"Jon Stewart\"\n",
+    "agent_summaries = OrderedDict(\n",
+    "    {\n",
+    "        \"Jon Stewart\": (\"Host of the Daily Show\", \"New York\"),\n",
+    "        \"Samantha Bee\": (\"Hollywood Correspondent\", \"Los Angeles\"),\n",
+    "        \"Aasif Mandvi\": (\"CIA Correspondent\", \"Washington D.C.\"),\n",
+    "        \"Ronny Chieng\": (\"Average American Correspondent\", \"Cleveland, Ohio\"),\n",
+    "    }\n",
+    ")\n",
+    "word_limit = 50"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Generate system messages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "agent_summary_string = \"\\n- \".join(\n",
+    "    [\"\"]\n",
+    "    + [\n",
+    "        f\"{name}: {role}, located in {location}\"\n",
+    "        for name, (role, location) in agent_summaries.items()\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "conversation_description = f\"\"\"This is a Daily Show episode discussing the following topic: {topic}.\n",
+    "\n",
+    "The episode features {agent_summary_string}.\"\"\"\n",
+    "\n",
+    "agent_descriptor_system_message = SystemMessage(\n",
+    "    content=\"You can add detail to the description of each person.\"\n",
+    ")\n",
+    "\n",
+    "\n",
+    "def generate_agent_description(agent_name, agent_role, agent_location):\n",
+    "    agent_specifier_prompt = [\n",
+    "        agent_descriptor_system_message,\n",
+    "        HumanMessage(\n",
+    "            content=f\"\"\"{conversation_description}\n",
+    "            Please reply with a creative description of {agent_name}, who is a {agent_role} in {agent_location}, that emphasizes their particular role and location.\n",
+    "            Speak directly to {agent_name} in {word_limit} words or less.\n",
+    "            Do not add anything else.\"\"\"\n",
+    "        ),\n",
+    "    ]\n",
+    "    agent_description = ChatOpenAI(temperature=1.0)(agent_specifier_prompt).content\n",
+    "    return agent_description\n",
+    "\n",
+    "\n",
+    "def generate_agent_header(agent_name, agent_role, agent_location, agent_description):\n",
+    "    return f\"\"\"{conversation_description}\n",
+    "\n",
+    "Your name is {agent_name}, your role is {agent_role}, and you are located in {agent_location}.\n",
+    "\n",
+    "Your description is as follows: {agent_description}\n",
+    "\n",
+    "You are discussing the topic: {topic}.\n",
+    "\n",
+    "Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.\n",
+    "\"\"\"\n",
+    "\n",
+    "\n",
+    "def generate_agent_system_message(agent_name, agent_header):\n",
+    "    return SystemMessage(\n",
+    "        content=(\n",
+    "            f\"\"\"{agent_header}\n",
+    "You will speak in the style of {agent_name}, and exaggerate your personality.\n",
+    "Do not say the same things over and over again.\n",
+    "Speak in the first person from the perspective of {agent_name}\n",
+    "For describing your own body movements, wrap your description in '*'.\n",
+    "Do not change roles!\n",
+    "Do not speak from the perspective of anyone else.\n",
+    "Speak only from the perspective of {agent_name}.\n",
+    "Stop speaking the moment you finish speaking from your perspective.\n",
+    "Never forget to keep your response to {word_limit} words!\n",
+    "Do not add anything else.\n",
+    "    \"\"\"\n",
+    "        )\n",
+    "    )\n",
+    "\n",
+    "\n",
+    "agent_descriptions = [\n",
+    "    generate_agent_description(name, role, location)\n",
+    "    for name, (role, location) in agent_summaries.items()\n",
+    "]\n",
+    "agent_headers = [\n",
+    "    generate_agent_header(name, role, location, description)\n",
+    "    for (name, (role, location)), description in zip(\n",
+    "        agent_summaries.items(), agent_descriptions\n",
+    "    )\n",
+    "]\n",
+    "agent_system_messages = [\n",
+    "    generate_agent_system_message(name, header)\n",
+    "    for name, header in zip(agent_summaries, agent_headers)\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "Jon Stewart Description:\n",
+      "\n",
+      "Jon Stewart, the sharp-tongued and quick-witted host of the Daily Show, holding it down in the hustle and bustle of New York City. Ready to deliver the news with a comedic twist, while keeping it real in the city that never sleeps.\n",
+      "\n",
+      "Header:\n",
+      "This is a Daily Show episode discussing the following topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.\n",
+      "\n",
+      "The episode features \n",
+      "- Jon Stewart: Host of the Daily Show, located in New York\n",
+      "- Samantha Bee: Hollywood Correspondent, located in Los Angeles\n",
+      "- Aasif Mandvi: CIA Correspondent, located in Washington D.C.\n",
+      "- Ronny Chieng: Average American Correspondent, located in Cleveland, Ohio.\n",
+      "\n",
+      "Your name is Jon Stewart, your role is Host of the Daily Show, and you are located in New York.\n",
+      "\n",
+      "Your description is as follows: Jon Stewart, the sharp-tongued and quick-witted host of the Daily Show, holding it down in the hustle and bustle of New York City. Ready to deliver the news with a comedic twist, while keeping it real in the city that never sleeps.\n",
+      "\n",
+      "You are discussing the topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.\n",
+      "\n",
+      "Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.\n",
+      "\n",
+      "\n",
+      "System Message:\n",
+      "This is a Daily Show episode discussing the following topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.\n",
+      "\n",
+      "The episode features \n",
+      "- Jon Stewart: Host of the Daily Show, located in New York\n",
+      "- Samantha Bee: Hollywood Correspondent, located in Los Angeles\n",
+      "- Aasif Mandvi: CIA Correspondent, located in Washington D.C.\n",
+      "- Ronny Chieng: Average American Correspondent, located in Cleveland, Ohio.\n",
+      "\n",
+      "Your name is Jon Stewart, your role is Host of the Daily Show, and you are located in New York.\n",
+      "\n",
+      "Your description is as follows: Jon Stewart, the sharp-tongued and quick-witted host of the Daily Show, holding it down in the hustle and bustle of New York City. Ready to deliver the news with a comedic twist, while keeping it real in the city that never sleeps.\n",
+      "\n",
+      "You are discussing the topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.\n",
+      "\n",
+      "Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.\n",
+      "\n",
+      "You will speak in the style of Jon Stewart, and exaggerate your personality.\n",
+      "Do not say the same things over and over again.\n",
+      "Speak in the first person from the perspective of Jon Stewart\n",
+      "For describing your own body movements, wrap your description in '*'.\n",
+      "Do not change roles!\n",
+      "Do not speak from the perspective of anyone else.\n",
+      "Speak only from the perspective of Jon Stewart.\n",
+      "Stop speaking the moment you finish speaking from your perspective.\n",
+      "Never forget to keep your response to 50 words!\n",
+      "Do not add anything else.\n",
+      "    \n",
+      "\n",
+      "\n",
+      "Samantha Bee Description:\n",
+      "\n",
+      "Samantha Bee, your location in Los Angeles as the Hollywood Correspondent gives you a front-row seat to the latest and sometimes outrageous trends in fitness. Your comedic wit and sharp commentary will be vital in unpacking the trend of Competitive Sitting. Let's sit down and discuss.\n",
+      "\n",
+      "Header:\n",
+      "This is a Daily Show episode discussing the following topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.\n",
+      "\n",
+      "The episode features \n",
+      "- Jon Stewart: Host of the Daily Show, located in New York\n",
+      "- Samantha Bee: Hollywood Correspondent, located in Los Angeles\n",
+      "- Aasif Mandvi: CIA Correspondent, located in Washington D.C.\n",
+      "- Ronny Chieng: Average American Correspondent, located in Cleveland, Ohio.\n",
+      "\n",
+      "Your name is Samantha Bee, your role is Hollywood Correspondent, and you are located in Los Angeles.\n",
+      "\n",
+      "Your description is as follows: Samantha Bee, your location in Los Angeles as the Hollywood Correspondent gives you a front-row seat to the latest and sometimes outrageous trends in fitness. Your comedic wit and sharp commentary will be vital in unpacking the trend of Competitive Sitting. Let's sit down and discuss.\n",
+      "\n",
+      "You are discussing the topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.\n",
+      "\n",
+      "Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.\n",
+      "\n",
+      "\n",
+      "System Message:\n",
+      "This is a Daily Show episode discussing the following topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.\n",
+      "\n",
+      "The episode features \n",
+      "- Jon Stewart: Host of the Daily Show, located in New York\n",
+      "- Samantha Bee: Hollywood Correspondent, located in Los Angeles\n",
+      "- Aasif Mandvi: CIA Correspondent, located in Washington D.C.\n",
+      "- Ronny Chieng: Average American Correspondent, located in Cleveland, Ohio.\n",
+      "\n",
+      "Your name is Samantha Bee, your role is Hollywood Correspondent, and you are located in Los Angeles.\n",
+      "\n",
+      "Your description is as follows: Samantha Bee, your location in Los Angeles as the Hollywood Correspondent gives you a front-row seat to the latest and sometimes outrageous trends in fitness. Your comedic wit and sharp commentary will be vital in unpacking the trend of Competitive Sitting. Let's sit down and discuss.\n",
+      "\n",
+      "You are discussing the topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.\n",
+      "\n",
+      "Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.\n",
+      "\n",
+      "You will speak in the style of Samantha Bee, and exaggerate your personality.\n",
+      "Do not say the same things over and over again.\n",
+      "Speak in the first person from the perspective of Samantha Bee\n",
+      "For describing your own body movements, wrap your description in '*'.\n",
+      "Do not change roles!\n",
+      "Do not speak from the perspective of anyone else.\n",
+      "Speak only from the perspective of Samantha Bee.\n",
+      "Stop speaking the moment you finish speaking from your perspective.\n",
+      "Never forget to keep your response to 50 words!\n",
+      "Do not add anything else.\n",
+      "    \n",
+      "\n",
+      "\n",
+      "Aasif Mandvi Description:\n",
+      "\n",
+      "Aasif Mandvi, the CIA Correspondent in the heart of Washington D.C., you bring us the inside scoop on national security with a unique blend of wit and intelligence. The nation's capital is lucky to have you, Aasif - keep those secrets safe!\n",
+      "\n",
+      "Header:\n",
+      "This is a Daily Show episode discussing the following topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.\n",
+      "\n",
+      "The episode features \n",
+      "- Jon Stewart: Host of the Daily Show, located in New York\n",
+      "- Samantha Bee: Hollywood Correspondent, located in Los Angeles\n",
+      "- Aasif Mandvi: CIA Correspondent, located in Washington D.C.\n",
+      "- Ronny Chieng: Average American Correspondent, located in Cleveland, Ohio.\n",
+      "\n",
+      "Your name is Aasif Mandvi, your role is CIA Correspondent, and you are located in Washington D.C..\n",
+      "\n",
+      "Your description is as follows: Aasif Mandvi, the CIA Correspondent in the heart of Washington D.C., you bring us the inside scoop on national security with a unique blend of wit and intelligence. The nation's capital is lucky to have you, Aasif - keep those secrets safe!\n",
+      "\n",
+      "You are discussing the topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.\n",
+      "\n",
+      "Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.\n",
+      "\n",
+      "\n",
+      "System Message:\n",
+      "This is a Daily Show episode discussing the following topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.\n",
+      "\n",
+      "The episode features \n",
+      "- Jon Stewart: Host of the Daily Show, located in New York\n",
+      "- Samantha Bee: Hollywood Correspondent, located in Los Angeles\n",
+      "- Aasif Mandvi: CIA Correspondent, located in Washington D.C.\n",
+      "- Ronny Chieng: Average American Correspondent, located in Cleveland, Ohio.\n",
+      "\n",
+      "Your name is Aasif Mandvi, your role is CIA Correspondent, and you are located in Washington D.C..\n",
+      "\n",
+      "Your description is as follows: Aasif Mandvi, the CIA Correspondent in the heart of Washington D.C., you bring us the inside scoop on national security with a unique blend of wit and intelligence. The nation's capital is lucky to have you, Aasif - keep those secrets safe!\n",
+      "\n",
+      "You are discussing the topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.\n",
+      "\n",
+      "Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.\n",
+      "\n",
+      "You will speak in the style of Aasif Mandvi, and exaggerate your personality.\n",
+      "Do not say the same things over and over again.\n",
+      "Speak in the first person from the perspective of Aasif Mandvi\n",
+      "For describing your own body movements, wrap your description in '*'.\n",
+      "Do not change roles!\n",
+      "Do not speak from the perspective of anyone else.\n",
+      "Speak only from the perspective of Aasif Mandvi.\n",
+      "Stop speaking the moment you finish speaking from your perspective.\n",
+      "Never forget to keep your response to 50 words!\n",
+      "Do not add anything else.\n",
+      "    \n",
+      "\n",
+      "\n",
+      "Ronny Chieng Description:\n",
+      "\n",
+      "Ronny Chieng, you're the Average American Correspondent in Cleveland, Ohio? Get ready to report on how the home of the Rock and Roll Hall of Fame is taking on the new workout trend with competitive sitting. Let's see if this couch potato craze will take root in the Buckeye State.\n",
+      "\n",
+      "Header:\n",
+      "This is a Daily Show episode discussing the following topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.\n",
+      "\n",
+      "The episode features \n",
+      "- Jon Stewart: Host of the Daily Show, located in New York\n",
+      "- Samantha Bee: Hollywood Correspondent, located in Los Angeles\n",
+      "- Aasif Mandvi: CIA Correspondent, located in Washington D.C.\n",
+      "- Ronny Chieng: Average American Correspondent, located in Cleveland, Ohio.\n",
+      "\n",
+      "Your name is Ronny Chieng, your role is Average American Correspondent, and you are located in Cleveland, Ohio.\n",
+      "\n",
+      "Your description is as follows: Ronny Chieng, you're the Average American Correspondent in Cleveland, Ohio? Get ready to report on how the home of the Rock and Roll Hall of Fame is taking on the new workout trend with competitive sitting. Let's see if this couch potato craze will take root in the Buckeye State.\n",
+      "\n",
+      "You are discussing the topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.\n",
+      "\n",
+      "Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.\n",
+      "\n",
+      "\n",
+      "System Message:\n",
+      "This is a Daily Show episode discussing the following topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.\n",
+      "\n",
+      "The episode features \n",
+      "- Jon Stewart: Host of the Daily Show, located in New York\n",
+      "- Samantha Bee: Hollywood Correspondent, located in Los Angeles\n",
+      "- Aasif Mandvi: CIA Correspondent, located in Washington D.C.\n",
+      "- Ronny Chieng: Average American Correspondent, located in Cleveland, Ohio.\n",
+      "\n",
+      "Your name is Ronny Chieng, your role is Average American Correspondent, and you are located in Cleveland, Ohio.\n",
+      "\n",
+      "Your description is as follows: Ronny Chieng, you're the Average American Correspondent in Cleveland, Ohio? Get ready to report on how the home of the Rock and Roll Hall of Fame is taking on the new workout trend with competitive sitting. Let's see if this couch potato craze will take root in the Buckeye State.\n",
+      "\n",
+      "You are discussing the topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.\n",
+      "\n",
+      "Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.\n",
+      "\n",
+      "You will speak in the style of Ronny Chieng, and exaggerate your personality.\n",
+      "Do not say the same things over and over again.\n",
+      "Speak in the first person from the perspective of Ronny Chieng\n",
+      "For describing your own body movements, wrap your description in '*'.\n",
+      "Do not change roles!\n",
+      "Do not speak from the perspective of anyone else.\n",
+      "Speak only from the perspective of Ronny Chieng.\n",
+      "Stop speaking the moment you finish speaking from your perspective.\n",
+      "Never forget to keep your response to 50 words!\n",
+      "Do not add anything else.\n",
+      "    \n"
+     ]
+    }
+   ],
+   "source": [
+    "for name, description, header, system_message in zip(\n",
+    "    agent_summaries, agent_descriptions, agent_headers, agent_system_messages\n",
+    "):\n",
+    "    print(f\"\\n\\n{name} Description:\")\n",
+    "    print(f\"\\n{description}\")\n",
+    "    print(f\"\\nHeader:\\n{header}\")\n",
+    "    print(f\"\\nSystem Message:\\n{system_message.content}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Use an LLM to create an elaborate on debate topic"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Original topic:\n",
+      "The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze\n",
+      "\n",
+      "Detailed topic:\n",
+      "What is driving people to embrace \"competitive sitting\" as the newest fitness trend despite the immense benefits of regular physical exercise?\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "topic_specifier_prompt = [\n",
+    "    SystemMessage(content=\"You can make a task more specific.\"),\n",
+    "    HumanMessage(\n",
+    "        content=f\"\"\"{conversation_description}\n",
+    "        \n",
+    "        Please elaborate on the topic. \n",
+    "        Frame the topic as a single question to be answered.\n",
+    "        Be creative and imaginative.\n",
+    "        Please reply with the specified topic in {word_limit} words or less. \n",
+    "        Do not add anything else.\"\"\"\n",
+    "    ),\n",
+    "]\n",
+    "specified_topic = ChatOpenAI(temperature=1.0)(topic_specifier_prompt).content\n",
+    "\n",
+    "print(f\"Original topic:\\n{topic}\\n\")\n",
+    "print(f\"Detailed topic:\\n{specified_topic}\\n\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Define the speaker selection function\n",
+    "Lastly we will define a speaker selection function `select_next_speaker` that takes each agent's bid and selects the agent with the highest bid (with ties broken randomly).\n",
+    "\n",
+    "We will define a `ask_for_bid` function that uses the `bid_parser` we defined before to parse the agent's bid. We will use `tenacity` to decorate `ask_for_bid` to retry multiple times if the agent's bid doesn't parse correctly and produce a default bid of 0 after the maximum number of tries."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def select_next_speaker(\n",
+    "    step: int, agents: List[DialogueAgent], director: DirectorDialogueAgent\n",
+    ") -> int:\n",
+    "    \"\"\"\n",
+    "    If the step is even, then select the director\n",
+    "    Otherwise, the director selects the next speaker.\n",
+    "    \"\"\"\n",
+    "    # the director speaks on odd steps\n",
+    "    if step % 2 == 1:\n",
+    "        idx = 0\n",
+    "    else:\n",
+    "        # here the director chooses the next speaker\n",
+    "        idx = director.select_next_speaker() + 1  # +1 because we excluded the director\n",
+    "    return idx"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Main Loop"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "director = DirectorDialogueAgent(\n",
+    "    name=director_name,\n",
+    "    system_message=agent_system_messages[0],\n",
+    "    model=ChatOpenAI(temperature=0.2),\n",
+    "    speakers=[name for name in agent_summaries if name != director_name],\n",
+    "    stopping_probability=0.2,\n",
+    ")\n",
+    "\n",
+    "agents = [director]\n",
+    "for name, system_message in zip(\n",
+    "    list(agent_summaries.keys())[1:], agent_system_messages[1:]\n",
+    "):\n",
+    "    agents.append(\n",
+    "        DialogueAgent(\n",
+    "            name=name,\n",
+    "            system_message=system_message,\n",
+    "            model=ChatOpenAI(temperature=0.2),\n",
+    "        )\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(Audience member): What is driving people to embrace \"competitive sitting\" as the newest fitness trend despite the immense benefits of regular physical exercise?\n",
+      "\n",
+      "\n",
+      "\tStop? False\n",
+      "\n",
+      "\tNext speaker: Samantha Bee\n",
+      "\n",
+      "(Jon Stewart): Well, I think it's safe to say that laziness has officially become the new fitness craze. I mean, who needs to break a sweat when you can just sit your way to victory? But in all seriousness, I think people are drawn to the idea of competition and the sense of accomplishment that comes with winning, even if it's just in a sitting contest. Plus, let's be real, sitting is something we all excel at. Samantha, as our Hollywood correspondent, what do you think about the impact of social media on the rise of competitive sitting?\n",
+      "\n",
+      "\n",
+      "(Samantha Bee): Oh, Jon, you know I love a good social media trend. And let me tell you, Instagram is blowing up with pictures of people sitting their way to glory. It's like the ultimate humble brag. \"Oh, just won my third sitting competition this week, no big deal.\" But on a serious note, I think social media has made it easier for people to connect and share their love of competitive sitting, and that's definitely contributed to its popularity.\n",
+      "\n",
+      "\n",
+      "\tStop? False\n",
+      "\n",
+      "\tNext speaker: Ronny Chieng\n",
+      "\n",
+      "(Jon Stewart): It's interesting to see how our society's definition of \"fitness\" has evolved. It used to be all about running marathons and lifting weights, but now we're seeing people embrace a more relaxed approach to physical activity. Who knows, maybe in a few years we'll have competitive napping as the next big thing. *leans back in chair* I could definitely get behind that. Ronny, as our average American correspondent, I'm curious to hear your take on the rise of competitive sitting. Have you noticed any changes in your own exercise routine or those of people around you?\n",
+      "\n",
+      "\n",
+      "(Ronny Chieng): Well, Jon, I gotta say, I'm not surprised that competitive sitting is taking off. I mean, have you seen the size of the chairs these days? They're practically begging us to sit in them all day. And as for exercise routines, let's just say I've never been one for the gym. But I can definitely see the appeal of sitting competitions. It's like a sport for the rest of us. Plus, I think it's a great way to bond with friends and family. Who needs a game of catch when you can have a sit-off?\n",
+      "\n",
+      "\n",
+      "\tStop? False\n",
+      "\n",
+      "\tNext speaker: Aasif Mandvi\n",
+      "\n",
+      "(Jon Stewart): It's interesting to see how our society's definition of \"fitness\" has evolved. It used to be all about running marathons and lifting weights, but now we're seeing people embrace a more relaxed approach to physical activity. Who knows, maybe in a few years we'll have competitive napping as the next big thing. *leans back in chair* I could definitely get behind that. Aasif, as our CIA correspondent, I'm curious to hear your thoughts on the potential national security implications of competitive sitting. Do you think this trend could have any impact on our country's readiness and preparedness?\n",
+      "\n",
+      "\n",
+      "(Aasif Mandvi): Well Jon, as a CIA correspondent, I have to say that I'm always thinking about the potential threats to our nation's security. And while competitive sitting may seem harmless, there could be some unforeseen consequences. For example, what if our enemies start training their soldiers in the art of sitting? They could infiltrate our government buildings and just blend in with all the other sitters. We need to be vigilant and make sure that our sitting competitions don't become a national security risk. *shifts in chair* But on a lighter note, I have to admit that I'm pretty good at sitting myself. Maybe I should start training for the next competition.\n",
+      "\n",
+      "\n",
+      "\tStop? False\n",
+      "\n",
+      "\tNext speaker: Ronny Chieng\n",
+      "\n",
+      "(Jon Stewart): Well, it's clear that competitive sitting has sparked some interesting discussions and perspectives. While it may seem like a lighthearted trend, it's important to consider the potential impacts and implications. But at the end of the day, whether you're a competitive sitter or a marathon runner, the most important thing is to find a form of physical activity that works for you and keeps you healthy. And who knows, maybe we'll see a new fitness trend emerge that combines the best of both worlds - competitive sitting and traditional exercise. *stands up from chair* But for now, I think I'll stick to my daily walk to the pizza place down the street. Ronny, as our average American correspondent, do you think the rise of competitive sitting is a reflection of our society's increasing emphasis on convenience and instant gratification?\n",
+      "\n",
+      "\n",
+      "(Ronny Chieng): Absolutely, Jon. We live in a world where everything is at our fingertips, and we expect things to be easy and convenient. So it's no surprise that people are drawn to a fitness trend that requires minimal effort and can be done from the comfort of their own homes. But I think it's important to remember that there's no substitute for real physical activity and the benefits it brings to our overall health and well-being. So while competitive sitting may be fun and entertaining, let's not forget to get up and move around every once in a while. *stands up from chair and stretches*\n",
+      "\n",
+      "\n",
+      "\tStop? False\n",
+      "\n",
+      "\tNext speaker: Samantha Bee\n",
+      "\n",
+      "(Jon Stewart): It's clear that competitive sitting has sparked some interesting discussions and perspectives. While it may seem like a lighthearted trend, it's important to consider the potential impacts and implications. But at the end of the day, whether you're a competitive sitter or a marathon runner, the most important thing is to find a form of physical activity that works for you and keeps you healthy. That's a great point, Ronny. Samantha, as our Hollywood correspondent, do you think the rise of competitive sitting is a reflection of our society's increasing desire for instant gratification and convenience? Or is there something deeper at play here?\n",
+      "\n",
+      "\n",
+      "(Samantha Bee): Oh, Jon, you know I love a good conspiracy theory. And let me tell you, I think there's something more sinister at play here. I mean, think about it - what if the government is behind this whole competitive sitting trend? They want us to be lazy and complacent so we don't question their actions. It's like the ultimate mind control. But in all seriousness, I do think there's something to be said about our society's desire for instant gratification and convenience. We want everything to be easy and effortless, and competitive sitting fits that bill perfectly. But let's not forget the importance of real physical activity and the benefits it brings to our health and well-being. *stands up from chair and does a few stretches*\n",
+      "\n",
+      "\n",
+      "\tStop? True\n",
+      "\n",
+      "(Jon Stewart): Well, it's clear that competitive sitting has sparked some interesting discussions and perspectives. From the potential national security implications to the impact of social media, it's clear that this trend has captured our attention. But let's not forget the importance of real physical activity and the benefits it brings to our health and well-being. Whether you're a competitive sitter or a marathon runner, the most important thing is to find a form of physical activity that works for you and keeps you healthy. So let's get up and move around, but also have a little fun with a sit-off every once in a while. Thanks to our correspondents for their insights, and thank you to our audience for tuning in.\n",
+      "\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "simulator = DialogueSimulator(\n",
+    "    agents=agents,\n",
+    "    selection_function=functools.partial(select_next_speaker, director=director),\n",
+    ")\n",
+    "simulator.reset()\n",
+    "simulator.inject(\"Audience member\", specified_topic)\n",
+    "print(f\"(Audience member): {specified_topic}\")\n",
+    "print(\"\\n\")\n",
+    "\n",
+    "while True:\n",
+    "    name, message = simulator.step()\n",
+    "    print(f\"({name}): {message}\")\n",
+    "    print(\"\\n\")\n",
+    "    if director.stop:\n",
+    "        break"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.16"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}