Merge branch 'master' into api-reference-agents-functions

.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/packages.yml   @ccurme

.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

@@ -1,125 +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://python.langchain.com/api_reference/),
-        * [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://python.langchain.com/api_reference/),
-        * [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.
-        
-        What specific functionality are you requesting? Be as detailed as possible.
-      placeholder: |
-        I would like LangChain to support...
-        
-        This feature would allow users to...
+        A clear and concise description of the feature proposal. Please provide links to any relevant GitHub repos, papers, or other resources if relevant.
+
   - 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.
-        
-        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...
+        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.
+
   - 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

@@ -1,33 +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, docs, anthropic, chroma, deepseek, exa, fireworks, groq, huggingface, mistralai, nomic, ollama, openai, perplexity, prompty, qdrant, xai
-  - *Note:* the `{DESCRIPTION}` must not start with an uppercase letter.
-  - 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
 
-- [ ] **Add tests and docs**: If you're adding a new integration, you must 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/docs/integrations` directory.
+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.
 
-- [ ] **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://python.langchain.com/docs/contributing/) for more.
-
-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.
-- 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/people/Dockerfile

@@ -1,7 +0,0 @@
-FROM python:3.9
-
-RUN pip install httpx PyGithub "pydantic==2.0.2" pydantic-settings "pyyaml>=5.3.1,<6.0.0"
-
-COPY ./app /app
-
-CMD ["python", "/app/main.py"]

.github/actions/people/action.yml

@@ -1,13 +0,0 @@
-# Adapted from https://github.com/tiangolo/fastapi/blob/master/.github/actions/people/action.yml
-# TODO: fix this, migrate to new docs repo?
-
-name: "Generate LangChain People"
-description: "Generate the data for the LangChain People page"
-author: "Jacob Lee <jacob@langchain.dev>"
-inputs:
-  token:
-    description: "User token, to read the GitHub API. Can be passed in using {{ secrets.LANGCHAIN_PEOPLE_GITHUB_TOKEN }}"
-    required: true
-runs:
-  using: "docker"
-  image: "Dockerfile"

.github/actions/people/app/main.py

@@ -1,646 +0,0 @@
-# Adapted from https://github.com/tiangolo/fastapi/blob/master/.github/actions/people/app/main.py
-
-import logging
-import subprocess
-import sys
-from collections import Counter
-from datetime import datetime, timedelta, timezone
-from pathlib import Path
-from typing import Any, Container, Dict, List, Set, Union
-
-import httpx
-import yaml
-from github import Github
-from pydantic import BaseModel, SecretStr
-from pydantic_settings import BaseSettings
-
-github_graphql_url = "https://api.github.com/graphql"
-questions_category_id = "DIC_kwDOIPDwls4CS6Ve"
-
-# discussions_query = """
-# query Q($after: String, $category_id: ID) {
-#   repository(name: "langchain", owner: "langchain-ai") {
-#     discussions(first: 100, after: $after, categoryId: $category_id) {
-#       edges {
-#         cursor
-#         node {
-#           number
-#           author {
-#             login
-#             avatarUrl
-#             url
-#           }
-#           title
-#           createdAt
-#           comments(first: 100) {
-#             nodes {
-#               createdAt
-#               author {
-#                 login
-#                 avatarUrl
-#                 url
-#               }
-#               isAnswer
-#               replies(first: 10) {
-#                 nodes {
-#                   createdAt
-#                   author {
-#                     login
-#                     avatarUrl
-#                     url
-#                   }
-#                 }
-#               }
-#             }
-#           }
-#         }
-#       }
-#     }
-#   }
-# }
-# """
-
-# issues_query = """
-# query Q($after: String) {
-#   repository(name: "langchain", owner: "langchain-ai") {
-#     issues(first: 100, after: $after) {
-#       edges {
-#         cursor
-#         node {
-#           number
-#           author {
-#             login
-#             avatarUrl
-#             url
-#           }
-#           title
-#           createdAt
-#           state
-#           comments(first: 100) {
-#             nodes {
-#               createdAt
-#               author {
-#                 login
-#                 avatarUrl
-#                 url
-#               }
-#             }
-#           }
-#         }
-#       }
-#     }
-#   }
-# }
-# """
-
-prs_query = """
-query Q($after: String) {
-  repository(name: "langchain", owner: "langchain-ai") {
-    pullRequests(first: 100, after: $after, states: MERGED) {
-      edges {
-        cursor
-        node {
-          changedFiles
-          additions
-          deletions
-          number
-          labels(first: 100) {
-            nodes {
-              name
-            }
-          }
-          author {
-            login
-            avatarUrl
-            url
-            ... on User {
-              twitterUsername
-            }
-          }
-          title
-          createdAt
-          state
-          reviews(first:100) {
-            nodes {
-              author {
-                login
-                avatarUrl
-                url
-                ... on User {
-                  twitterUsername
-                }
-              }
-              state
-            }
-          }
-        }
-      }
-    }
-  }
-}
-"""
-
-
-class Author(BaseModel):
-    login: str
-    avatarUrl: str
-    url: str
-    twitterUsername: Union[str, None] = None
-
-
-# Issues and Discussions
-
-
-class CommentsNode(BaseModel):
-    createdAt: datetime
-    author: Union[Author, None] = None
-
-
-class Replies(BaseModel):
-    nodes: List[CommentsNode]
-
-
-class DiscussionsCommentsNode(CommentsNode):
-    replies: Replies
-
-
-class Comments(BaseModel):
-    nodes: List[CommentsNode]
-
-
-class DiscussionsComments(BaseModel):
-    nodes: List[DiscussionsCommentsNode]
-
-
-class IssuesNode(BaseModel):
-    number: int
-    author: Union[Author, None] = None
-    title: str
-    createdAt: datetime
-    state: str
-    comments: Comments
-
-
-class DiscussionsNode(BaseModel):
-    number: int
-    author: Union[Author, None] = None
-    title: str
-    createdAt: datetime
-    comments: DiscussionsComments
-
-
-class IssuesEdge(BaseModel):
-    cursor: str
-    node: IssuesNode
-
-
-class DiscussionsEdge(BaseModel):
-    cursor: str
-    node: DiscussionsNode
-
-
-class Issues(BaseModel):
-    edges: List[IssuesEdge]
-
-
-class Discussions(BaseModel):
-    edges: List[DiscussionsEdge]
-
-
-class IssuesRepository(BaseModel):
-    issues: Issues
-
-
-class DiscussionsRepository(BaseModel):
-    discussions: Discussions
-
-
-class IssuesResponseData(BaseModel):
-    repository: IssuesRepository
-
-
-class DiscussionsResponseData(BaseModel):
-    repository: DiscussionsRepository
-
-
-class IssuesResponse(BaseModel):
-    data: IssuesResponseData
-
-
-class DiscussionsResponse(BaseModel):
-    data: DiscussionsResponseData
-
-
-# PRs
-
-
-class LabelNode(BaseModel):
-    name: str
-
-
-class Labels(BaseModel):
-    nodes: List[LabelNode]
-
-
-class ReviewNode(BaseModel):
-    author: Union[Author, None] = None
-    state: str
-
-
-class Reviews(BaseModel):
-    nodes: List[ReviewNode]
-
-
-class PullRequestNode(BaseModel):
-    number: int
-    labels: Labels
-    author: Union[Author, None] = None
-    changedFiles: int
-    additions: int
-    deletions: int
-    title: str
-    createdAt: datetime
-    state: str
-    reviews: Reviews
-    # comments: Comments
-
-
-class PullRequestEdge(BaseModel):
-    cursor: str
-    node: PullRequestNode
-
-
-class PullRequests(BaseModel):
-    edges: List[PullRequestEdge]
-
-
-class PRsRepository(BaseModel):
-    pullRequests: PullRequests
-
-
-class PRsResponseData(BaseModel):
-    repository: PRsRepository
-
-
-class PRsResponse(BaseModel):
-    data: PRsResponseData
-
-
-class Settings(BaseSettings):
-    input_token: SecretStr
-    github_repository: str
-    httpx_timeout: int = 30
-
-
-def get_graphql_response(
-    *,
-    settings: Settings,
-    query: str,
-    after: Union[str, None] = None,
-    category_id: Union[str, None] = None,
-) -> Dict[str, Any]:
-    headers = {"Authorization": f"token {settings.input_token.get_secret_value()}"}
-    # category_id is only used by one query, but GraphQL allows unused variables, so
-    # keep it here for simplicity
-    variables = {"after": after, "category_id": category_id}
-    response = httpx.post(
-        github_graphql_url,
-        headers=headers,
-        timeout=settings.httpx_timeout,
-        json={"query": query, "variables": variables, "operationName": "Q"},
-    )
-    if response.status_code != 200:
-        logging.error(
-            f"Response was not 200, after: {after}, category_id: {category_id}"
-        )
-        logging.error(response.text)
-        raise RuntimeError(response.text)
-    data = response.json()
-    if "errors" in data:
-        logging.error(f"Errors in response, after: {after}, category_id: {category_id}")
-        logging.error(data["errors"])
-        logging.error(response.text)
-        raise RuntimeError(response.text)
-    return data
-
-
-# def get_graphql_issue_edges(*, settings: Settings, after: Union[str, None] = None):
-#     data = get_graphql_response(settings=settings, query=issues_query, after=after)
-#     graphql_response = IssuesResponse.model_validate(data)
-#     return graphql_response.data.repository.issues.edges
-
-
-# def get_graphql_question_discussion_edges(
-#     *,
-#     settings: Settings,
-#     after: Union[str, None] = None,
-# ):
-#     data = get_graphql_response(
-#         settings=settings,
-#         query=discussions_query,
-#         after=after,
-#         category_id=questions_category_id,
-#     )
-#     graphql_response = DiscussionsResponse.model_validate(data)
-#     return graphql_response.data.repository.discussions.edges
-
-
-def get_graphql_pr_edges(*, settings: Settings, after: Union[str, None] = None):
-    if after is None:
-        print("Querying PRs...")
-    else:
-        print(f"Querying PRs with cursor {after}...")
-    data = get_graphql_response(settings=settings, query=prs_query, after=after)
-    graphql_response = PRsResponse.model_validate(data)
-    return graphql_response.data.repository.pullRequests.edges
-
-
-# def get_issues_experts(settings: Settings):
-#     issue_nodes: List[IssuesNode] = []
-#     issue_edges = get_graphql_issue_edges(settings=settings)
-
-#     while issue_edges:
-#         for edge in issue_edges:
-#             issue_nodes.append(edge.node)
-#         last_edge = issue_edges[-1]
-#         issue_edges = get_graphql_issue_edges(settings=settings, after=last_edge.cursor)
-
-#     commentors = Counter()
-#     last_month_commentors = Counter()
-#     authors: Dict[str, Author] = {}
-
-#     now = datetime.now(tz=timezone.utc)
-#     one_month_ago = now - timedelta(days=30)
-
-#     for issue in issue_nodes:
-#         issue_author_name = None
-#         if issue.author:
-#             authors[issue.author.login] = issue.author
-#             issue_author_name = issue.author.login
-#         issue_commentors = set()
-#         for comment in issue.comments.nodes:
-#             if comment.author:
-#                 authors[comment.author.login] = comment.author
-#                 if comment.author.login != issue_author_name:
-#                     issue_commentors.add(comment.author.login)
-#         for author_name in issue_commentors:
-#             commentors[author_name] += 1
-#             if issue.createdAt > one_month_ago:
-#                 last_month_commentors[author_name] += 1
-
-#     return commentors, last_month_commentors, authors
-
-
-# def get_discussions_experts(settings: Settings):
-#     discussion_nodes: List[DiscussionsNode] = []
-#     discussion_edges = get_graphql_question_discussion_edges(settings=settings)
-
-#     while discussion_edges:
-#         for discussion_edge in discussion_edges:
-#             discussion_nodes.append(discussion_edge.node)
-#         last_edge = discussion_edges[-1]
-#         discussion_edges = get_graphql_question_discussion_edges(
-#             settings=settings, after=last_edge.cursor
-#         )
-
-#     commentors = Counter()
-#     last_month_commentors = Counter()
-#     authors: Dict[str, Author] = {}
-
-#     now = datetime.now(tz=timezone.utc)
-#     one_month_ago = now - timedelta(days=30)
-
-#     for discussion in discussion_nodes:
-#         discussion_author_name = None
-#         if discussion.author:
-#             authors[discussion.author.login] = discussion.author
-#             discussion_author_name = discussion.author.login
-#         discussion_commentors = set()
-#         for comment in discussion.comments.nodes:
-#             if comment.author:
-#                 authors[comment.author.login] = comment.author
-#                 if comment.author.login != discussion_author_name:
-#                     discussion_commentors.add(comment.author.login)
-#             for reply in comment.replies.nodes:
-#                 if reply.author:
-#                     authors[reply.author.login] = reply.author
-#                     if reply.author.login != discussion_author_name:
-#                         discussion_commentors.add(reply.author.login)
-#         for author_name in discussion_commentors:
-#             commentors[author_name] += 1
-#             if discussion.createdAt > one_month_ago:
-#                 last_month_commentors[author_name] += 1
-#     return commentors, last_month_commentors, authors
-
-
-# def get_experts(settings: Settings):
-#     (
-#         discussions_commentors,
-#         discussions_last_month_commentors,
-#         discussions_authors,
-#     ) = get_discussions_experts(settings=settings)
-#     commentors = discussions_commentors
-#     last_month_commentors = discussions_last_month_commentors
-#     authors = {**discussions_authors}
-#     return commentors, last_month_commentors, authors
-
-
-def _logistic(x, k):
-    return x / (x + k)
-
-
-def get_contributors(settings: Settings):
-    pr_nodes: List[PullRequestNode] = []
-    pr_edges = get_graphql_pr_edges(settings=settings)
-
-    while pr_edges:
-        for edge in pr_edges:
-            pr_nodes.append(edge.node)
-        last_edge = pr_edges[-1]
-        pr_edges = get_graphql_pr_edges(settings=settings, after=last_edge.cursor)
-
-    contributors = Counter()
-    contributor_scores = Counter()
-    recent_contributor_scores = Counter()
-    reviewers = Counter()
-    authors: Dict[str, Author] = {}
-
-    for pr in pr_nodes:
-        pr_reviewers: Set[str] = set()
-        for review in pr.reviews.nodes:
-            if review.author:
-                authors[review.author.login] = review.author
-                pr_reviewers.add(review.author.login)
-        for reviewer in pr_reviewers:
-            reviewers[reviewer] += 1
-        if pr.author:
-            authors[pr.author.login] = pr.author
-            contributors[pr.author.login] += 1
-            files_changed = pr.changedFiles
-            lines_changed = pr.additions + pr.deletions
-            score = _logistic(files_changed, 20) + _logistic(lines_changed, 100)
-            contributor_scores[pr.author.login] += score
-            three_months_ago = datetime.now(timezone.utc) - timedelta(days=3 * 30)
-            if pr.createdAt > three_months_ago:
-                recent_contributor_scores[pr.author.login] += score
-    return (
-        contributors,
-        contributor_scores,
-        recent_contributor_scores,
-        reviewers,
-        authors,
-    )
-
-
-def get_top_users(
-    *,
-    counter: Counter,
-    min_count: int,
-    authors: Dict[str, Author],
-    skip_users: Container[str],
-):
-    users = []
-    for commentor, count in counter.most_common():
-        if commentor in skip_users:
-            continue
-        if count >= min_count:
-            author = authors[commentor]
-            users.append(
-                {
-                    "login": commentor,
-                    "count": count,
-                    "avatarUrl": author.avatarUrl,
-                    "twitterUsername": author.twitterUsername,
-                    "url": author.url,
-                }
-            )
-    return users
-
-
-if __name__ == "__main__":
-    logging.basicConfig(level=logging.INFO)
-    settings = Settings()
-    logging.info(f"Using config: {settings.model_dump_json()}")
-    g = Github(settings.input_token.get_secret_value())
-    repo = g.get_repo(settings.github_repository)
-    # question_commentors, question_last_month_commentors, question_authors = get_experts(
-    #     settings=settings
-    # )
-    (
-        contributors,
-        contributor_scores,
-        recent_contributor_scores,
-        reviewers,
-        pr_authors,
-    ) = get_contributors(settings=settings)
-    # authors = {**question_authors, **pr_authors}
-    authors = {**pr_authors}
-    maintainers_logins = {
-        "hwchase17",
-        "agola11",
-        "baskaryan",
-        "hinthornw",
-        "nfcampos",
-        "efriis",
-        "eyurtsev",
-        "rlancemartin",
-        "ccurme",
-        "vbarda",
-    }
-    hidden_logins = {
-        "dev2049",
-        "vowelparrot",
-        "obi1kenobi",
-        "langchain-infra",
-        "jacoblee93",
-        "isahers1",
-        "dqbd",
-        "bracesproul",
-        "akira",
-    }
-    bot_names = {"dosubot", "github-actions", "CodiumAI-Agent"}
-    maintainers = []
-    for login in maintainers_logins:
-        user = authors[login]
-        maintainers.append(
-            {
-                "login": login,
-                "count": contributors[login],  # + question_commentors[login],
-                "avatarUrl": user.avatarUrl,
-                "twitterUsername": user.twitterUsername,
-                "url": user.url,
-            }
-        )
-
-    # min_count_expert = 10
-    # min_count_last_month = 3
-    min_score_contributor = 1
-    min_count_reviewer = 5
-    skip_users = maintainers_logins | bot_names | hidden_logins
-    # experts = get_top_users(
-    #     counter=question_commentors,
-    #     min_count=min_count_expert,
-    #     authors=authors,
-    #     skip_users=skip_users,
-    # )
-    # last_month_active = get_top_users(
-    #     counter=question_last_month_commentors,
-    #     min_count=min_count_last_month,
-    #     authors=authors,
-    #     skip_users=skip_users,
-    # )
-    top_recent_contributors = get_top_users(
-        counter=recent_contributor_scores,
-        min_count=min_score_contributor,
-        authors=authors,
-        skip_users=skip_users,
-    )
-    top_contributors = get_top_users(
-        counter=contributor_scores,
-        min_count=min_score_contributor,
-        authors=authors,
-        skip_users=skip_users,
-    )
-    top_reviewers = get_top_users(
-        counter=reviewers,
-        min_count=min_count_reviewer,
-        authors=authors,
-        skip_users=skip_users,
-    )
-
-    people = {
-        "maintainers": maintainers,
-        # "experts": experts,
-        # "last_month_active": last_month_active,
-        "top_recent_contributors": top_recent_contributors,
-        "top_contributors": top_contributors,
-        "top_reviewers": top_reviewers,
-    }
-    people_path = Path("./docs/data/people.yml")
-    people_old_content = people_path.read_text(encoding="utf-8")
-    new_people_content = yaml.dump(
-        people, sort_keys=False, width=200, allow_unicode=True
-    )
-    if people_old_content == new_people_content:
-        logging.info("The LangChain People data hasn't changed, finishing.")
-        sys.exit(0)
-    people_path.write_text(new_people_content, encoding="utf-8")
-    logging.info("Setting up GitHub Actions git user")
-    subprocess.run(["git", "config", "user.name", "github-actions"], check=True)
-    subprocess.run(
-        ["git", "config", "user.email", "github-actions@github.com"], check=True
-    )
-    branch_name = "langchain/langchain-people"
-    logging.info(f"Creating a new branch {branch_name}")
-    subprocess.run(["git", "checkout", "-B", branch_name], check=True)
-    logging.info("Adding updated file")
-    subprocess.run(["git", "add", str(people_path)], check=True)
-    logging.info("Committing updated file")
-    message = "👥 Update LangChain people data"
-    result = subprocess.run(["git", "commit", "-m", message], check=True)
-    logging.info("Pushing branch")
-    subprocess.run(["git", "push", "origin", branch_name, "-f"], check=True)
-    logging.info("Creating PR")
-    pr = repo.create_pull(title=message, body=message, base="master", head=branch_name)
-    logging.info(f"Created PR: {pr.number}")
-    logging.info("Finished")

.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

@@ -1,325 +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 reStructuredText, 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
-- Focus on "why" rather than "what" in descriptions
-- Document all parameters, return values, and exceptions
-- Keep descriptions concise but clear
-- Use reStructuredText for docstrings to enable rich formatting
-
-📌 *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

.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/pr-file-labeler.yml

@@ -1,80 +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/**/*"
-
-# 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:
-          - "docs/**/*"
-          - "**/*.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

@@ -1,40 +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:
-  feature: ["feat"]
-  fix: ["fix"]
-  documentation: ["docs"]
-  linting: ["style"]
-  refactor: ["refactor"]
-  performance: ["perf"]
-  infra: ["build", "ci", "chore"]
-  integration:
-    [
-      "anthropic",
-      "chroma",
-      "deepseek",
-      "exa",
-      "fireworks",
-      "groq",
-      "huggingface",
-      "mistralai",
-      "nomic",
-      "ollama",
-      "openai",
-      "perplexity",
-      "prompty",
-      "qdrant",
-      "xai",
-    ]
-  revert: ["revert"]
-  release: ["release"]

.github/scripts/check_diff.py

@@ -1,349 +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",
-]
-
-PY_312_MAX_PACKAGES = [
-    "libs/partners/chroma",  # https://github.com/chroma-core/chroma/issues/4382
-]
-
-
-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 = ["3.9", "3.10", "3.11", "3.12", "3.13"]
-    # custom logic for specific directories
-
-    elif dir_ in PY_312_MAX_PACKAGES:
-        py_versions = ["3.9", "3.12"]
-
-    elif dir_ == "libs/langchain" and job == "extended-tests":
-        py_versions = ["3.9", "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 = ["3.9", "3.12"]
-    else:
-        py_versions = ["3.9", "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",
-            )
-        ):
-            # add all LANGCHAIN_DIRS for infra changes
-            dirs_to_run["extended-test"].update(LANGCHAIN_DIRS)
-            dirs_to_run["lint"].add(".")
-
-        if file.startswith("libs/core"):
-            dirs_to_run["codspeed"].add(f"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["lint"].add("libs/cli")
-            dirs_to_run["test"].add("libs/cli")
-            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 == "libs/packages.yml":
-            continue
-        elif file.startswith("libs/"):
-            raise ValueError(
-                f"Unknown lib: {file}. check_diff.py likely needs "
-                "an update for this new library!"
-            )
-        elif file.startswith("docs/") or file in [
-            "pyproject.toml",
-            "uv.lock",
-        ]:  # docs or root uv files
-            docs_edited = True
-            dirs_to_run["lint"].add(".")
-
-    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",
-        ]
-    }
-    map_job_to_configs["test-doc-imports"] = (
-        [{"python-version": "3.12"}] if docs_edited else []
-    )
-
-    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

@@ -1,200 +0,0 @@
-"""Get minimum versions of dependencies from a pyproject.toml file."""
-
-import sys
-from collections import defaultdict
-from typing import Optional
-
-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) -> Optional[str]:
-    """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: Optional[list] = 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/scripts/prep_api_docs_build.py

@@ -1,120 +0,0 @@
-#!/usr/bin/env python
-"""Sync libraries from various repositories into this monorepo.
-
-Moves cloned partner packages into libs/partners structure.
-"""
-
-import os
-import shutil
-from pathlib import Path
-from typing import Any, Dict
-
-import yaml
-
-
-def load_packages_yaml() -> Dict[str, Any]:
-    """Load and parse packages.yml."""
-    with open("langchain/libs/packages.yml", "r") as f:
-        return yaml.safe_load(f)
-
-
-def get_target_dir(package_name: str) -> Path:
-    """Get the target directory for a given package."""
-    package_name_short = package_name.replace("langchain-", "")
-    base_path = Path("langchain/libs")
-    if package_name_short == "experimental":
-        return base_path / "experimental"
-    if package_name_short == "community":
-        return base_path / "community"
-    return base_path / "partners" / package_name_short
-
-
-def clean_target_directories(packages: list) -> None:
-    """Remove old directories that will be replaced."""
-    for package in packages:
-        target_dir = get_target_dir(package["name"])
-        if target_dir.exists():
-            print(f"Removing {target_dir}")
-            shutil.rmtree(target_dir)
-
-
-def move_libraries(packages: list) -> None:
-    """Move libraries from their source locations to the target directories."""
-    for package in packages:
-        repo_name = package["repo"].split("/")[1]
-        source_path = package["path"]
-        target_dir = get_target_dir(package["name"])
-
-        # Handle root path case
-        if source_path == ".":
-            source_dir = repo_name
-        else:
-            source_dir = f"{repo_name}/{source_path}"
-
-        print(f"Moving {source_dir} to {target_dir}")
-
-        # Ensure target directory exists
-        os.makedirs(os.path.dirname(target_dir), exist_ok=True)
-
-        try:
-            # Move the directory
-            shutil.move(source_dir, target_dir)
-        except Exception as e:
-            print(f"Error moving {source_dir} to {target_dir}: {e}")
-
-
-def main():
-    """Orchestrate the library sync process."""
-    try:
-        # Load packages configuration
-        package_yaml = load_packages_yaml()
-
-        # Clean/empty target directories in preparation for moving new ones
-        #
-        # Only for packages in the langchain-ai org or explicitly included via
-        # include_in_api_ref, excluding 'langchain' itself and 'langchain-ai21'
-        clean_target_directories(
-            [
-                p
-                for p in package_yaml["packages"]
-                if (
-                    p["repo"].startswith("langchain-ai/") or p.get("include_in_api_ref")
-                )
-                and p["repo"] != "langchain-ai/langchain"
-                and p["name"]
-                != "langchain-ai21"  # Skip AI21 due to dependency conflicts
-            ]
-        )
-
-        # Move cloned libraries to their new locations, only for packages in the
-        # langchain-ai org or explicitly included via include_in_api_ref,
-        # excluding 'langchain' itself and 'langchain-ai21'
-        move_libraries(
-            [
-                p
-                for p in package_yaml["packages"]
-                if not p.get("disabled", False)
-                and (
-                    p["repo"].startswith("langchain-ai/") or p.get("include_in_api_ref")
-                )
-                and p["repo"] != "langchain-ai/langchain"
-                and p["name"]
-                != "langchain-ai21"  # Skip AI21 due to dependency conflicts
-            ]
-        )
-
-        # Delete partner packages without a pyproject.toml
-        for partner in Path("langchain/libs/partners").iterdir():
-            if partner.is_dir() and not (partner / "pyproject.toml").exists():
-                print(f"Removing {partner} as it does not have a pyproject.toml")
-                shutil.rmtree(partner)
-
-        print("Library sync completed successfully!")
-
-    except Exception as e:
-        print(f"Error during library sync: {e}")
-        raise
-
-
-if __name__ == "__main__":
-    main()

.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/_integration_test.yml

@@ -1,103 +0,0 @@
-
-# Runs `make integration_tests` on the specified package.
-#
-# Manually triggered via workflow_dispatch for testing with real APIs.
-#
-# Installs integration test dependencies and executes full test suite.
-
-name: '🚀 Integration Tests'
-run-name: 'Test ${{ inputs.working-directory }} on Python ${{ inputs.python-version }}'
-
-on:
-  workflow_dispatch:
-    inputs:
-      working-directory:
-        required: true
-        type: string
-        description: "From which folder this pipeline executes"
-      python-version:
-        required: true
-        type: string
-        description: "Python version to use"
-        default: "3.11"
-
-permissions:
-  contents: read
-
-env:
-  UV_FROZEN: "true"
-
-jobs:
-  build:
-    defaults:
-      run:
-        working-directory: ${{ inputs.working-directory }}
-    runs-on: ubuntu-latest
-    name: 'Python ${{ inputs.python-version }}'
-    steps:
-      - uses: actions/checkout@v5
-
-      - name: '🐍 Set up Python ${{ inputs.python-version }} + UV'
-        uses: "./.github/actions/uv_setup"
-        with:
-          python-version: ${{ inputs.python-version }}
-          cache-suffix: integration-tests-${{ inputs.working-directory }}
-          working-directory: ${{ inputs.working-directory }}
-
-      - name: '📦 Install Integration Dependencies'
-        shell: bash
-        run: uv sync --group test --group test_integration
-
-      - name: '🚀 Run Integration Tests'
-        shell: bash
-        env:
-          AI21_API_KEY: ${{ secrets.AI21_API_KEY }}
-          FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
-          GOOGLE_API_KEY: ${{ secrets.GOOGLE_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 }}
-          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 }}
-          MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
-          TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
-          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
-          NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}
-          GOOGLE_SEARCH_API_KEY: ${{ secrets.GOOGLE_SEARCH_API_KEY }}
-          GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
-          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 }}
-          COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
-          UPSTAGE_API_KEY: ${{ secrets.UPSTAGE_API_KEY }}
-          XAI_API_KEY: ${{ secrets.XAI_API_KEY }}
-          PPLX_API_KEY: ${{ secrets.PPLX_API_KEY }}
-        run: |
-          make integration_tests
-
-      - name: 'Ensure testing did not create/modify files'
-        shell: bash
-        run: |
-          set -eu
-
-          STATUS="$(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/_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:
@@ -13,458 +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"
+  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
-
-    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
-    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
-    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
-    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 $2}' \
-            | sed 's|refs/tags/||' \
-            | grep -E '[0-9]+\.[0-9]+\.[0-9]+$' \
-            | 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:
@@ -474,70 +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 +7,44 @@ 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: ${{ inputs.working-directory }}
-        id: min-version
-        shell: bash
-        run: |
-          VIRTUAL_ENV=.venv uv pip install packaging tomli requests
-          python_version="$(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"
-
-      - 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: ${{ inputs.working-directory }}
-
-      - name: '🧹 Verify Clean Working Directory'
+      - name: Ensure the tests did not create any additional files
         shell: bash
         run: |
           set -eu
@@ -83,4 +55,3 @@ jobs:
           # grep will exit non-zero if the target message isn't found,
           # and `set -e` above will cause the step to fail.
           echo "$STATUS" | grep 'nothing to commit, working tree clean'
-

.github/workflows/_test_doc_imports.yml

@@ -1,63 +0,0 @@
-# Validates that all import statements in `.ipynb` notebooks are correct and functional.
-#
-# Called as part of check_diffs.yml.
-#
-# Installs test dependencies and LangChain packages in editable mode and
-# runs check_imports.py.
-
-name: '📑 Documentation Import Testing'
-
-on:
-  workflow_call:
-    inputs:
-      python-version:
-        required: true
-        type: string
-        description: "Python version to use"
-
-permissions:
-  contents: read
-
-env:
-  UV_FROZEN: "true"
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    timeout-minutes: 20
-    name: '🔍 Check Doc Imports (Python ${{ inputs.python-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: ${{ inputs.python-version }}
-          cache-suffix: test-doc-imports-${{ inputs.working-directory }}
-          working-directory: ${{ inputs.working-directory }}
-
-      - name: '📦 Install Test Dependencies'
-        shell: bash
-        run: uv sync --group test
-
-      - name: '📦 Install LangChain in Editable Mode'
-        run: |
-          VIRTUAL_ENV=.venv uv pip install langchain-experimental langchain-community -e libs/core libs/langchain
-
-      - name: '🔍 Validate Documentation Import Statements'
-        shell: bash
-        run: |
-          uv run python docs/scripts/check_imports.py
-
-      - name: '🧹 Verify Clean Working Directory'
-        shell: bash
-        run: |
-          set -eu
-
-          STATUS="$(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_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/api_doc_build.yml

@@ -1,152 +0,0 @@
-# Build the API reference documentation.
-#
-# Runs daily. Can also be triggered manually for immediate updates.
-#
-# 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'
-run-name: 'Build & Deploy API Reference'
-
-on:
-  workflow_dispatch:
-  schedule:
-    - cron:  '0 13 * * *'  # Runs daily at 1PM UTC (9AM EDT/6AM PDT)
-env:
-  PYTHON_VERSION: "3.11"
-
-jobs:
-  # Only runs on main repository to prevent unnecessary builds on forks
-  build:
-    if: github.repository == 'langchain-ai/langchain' || github.event_name != 'schedule'
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-    steps:
-      - uses: actions/checkout@v5
-        with:
-          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 $REPO_NAME"
-            git clone --depth 1 https://github.com/$repo.git $REPO_NAME
-          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 | xargs -I {} echo "./libs/partners/{}") --overrides ./docs/vercel_overrides.txt
-
-          # 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'

.github/workflows/check-broken-links.yml

@@ -1,30 +0,0 @@
-# Runs broken link checker in /docs on a daily schedule.
-
-name: '🔗 Check Broken Links'
-
-on:
-  workflow_dispatch:
-  schedule:
-    - cron:  '0 13 * * *'  # Runs daily at 1PM UTC (9AM EDT/6AM PDT)
-
-permissions:
-  contents: read
-
-jobs:
-  check-links:
-    if: github.repository_owner == 'langchain-ai' || github.event_name != 'schedule'
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v5
-      - name: '🟢 Setup Node.js 18.x'
-        uses: actions/setup-node@v5
-        with:
-          node-version: 18.x
-          cache: "yarn"
-          cache-dependency-path: ./docs/yarn.lock
-      - name: '📦 Install Node Dependencies'
-        run: yarn install --immutable --mode=skip-build
-        working-directory: ./docs
-      - name: '🔍 Scan Documentation for Broken Links'
-        run: yarn check-broken-links
-        working-directory: ./docs

.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

@@ -1,267 +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)
-# - Documentation import tests (_test_doc_imports.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-doc-imports: ${{ steps.set-matrix.outputs.test-doc-imports }}
-      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
-
-  test-doc-imports:
-    needs: [ build ]
-    if: ${{ needs.build.outputs.test-doc-imports != '[]' }}
-    strategy:
-      matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.test-doc-imports) }}
-      fail-fast: false
-    uses: ./.github/workflows/_test_doc_imports.yml
-    with:
-      python-version: ${{ matrix.job-configs.python-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@v6
-        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-doc-imports, 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/check_new_docs.yml

@@ -1,41 +0,0 @@
-# For integrations, we run check_templates.py to ensure that new docs use the correct
-# templates based on their type. See the script for more details.
-
-name: '📑 Integration Docs Lint'
-
-on:
-  push:
-    branches: [master]
-  pull_request:
-
-# 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
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v5
-      - uses: actions/setup-python@v6
-        with:
-          python-version: '3.10'
-      - id: files
-        uses: Ana06/get-changed-files@v2.3.0
-        with:
-          filter: |
-            *.ipynb
-            *.md
-            *.mdx
-      - name: '🔍 Check New Documentation Templates'
-        run: |
-          python docs/scripts/check_templates.py ${{ steps.files.outputs.added }}

.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/langchain_ci.yml

@@ -0,0 +1,105 @@
+---
+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/langchain/**'
+  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/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/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/people.yml

@@ -1,30 +0,0 @@
-# Updates the LangChain People data by fetching the latest info from the LangChain Git.
-# TODO: broken/not used
-
-name: '👥 LangChain People'
-run-name: 'Update People Data'
-on:
-  schedule:
-    - cron: "0 14 1 * *"  # Runs at 14:00 UTC on the 1st of every month (10AM EDT/7AM PDT)
-  push:
-    branches: [jacob/people]
-  workflow_dispatch:
-
-jobs:
-  langchain-people:
-    if: github.repository_owner == 'langchain-ai' || github.event_name != 'schedule'
-    runs-on: ubuntu-latest
-    permissions:
-      contents: write
-    steps:
-      - name: '📋 Dump GitHub Context'
-        env:
-          GITHUB_CONTEXT: ${{ toJson(github) }}
-        run: echo "$GITHUB_CONTEXT"
-      - uses: actions/checkout@v5
-      # Ref: https://github.com/actions/runner/issues/2033
-      - name: '🔧 Fix Git Safe Directory in Container'
-        run: mkdir -p /home/runner/work/_temp/_github_home && printf "[safe]\n\tdirectory = /github/workspace" > /home/runner/work/_temp/_github_home/.gitconfig
-      - uses: ./.github/actions/people
-        with:
-          token: ${{ secrets.LANGCHAIN_PEOPLE_GITHUB_TOKEN }}

.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

@@ -1,28 +0,0 @@
-# Label PRs based on their titles.
-#
-# See `.github/pr-title-labeler.yml` to see rules for each label/title pattern.
-
-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, synchronize, reopened, 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
-      # Archived repo; latest commit (v0.1.0)
-      uses: grafana/pr-labeler-action@f19222d3ef883d2ca5f04420fdfe8148003763f0
-      with:
-        token: ${{ secrets.GITHUB_TOKEN }}
-        configuration-path: .github/pr-title-labeler.yml

.github/workflows/pr_lint.yml

@@ -1,105 +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 (either in /docs or code comments)
-#   * 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)
-#
-# 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/run_notebooks.yml

@@ -1,79 +0,0 @@
-# Integration tests for documentation notebooks.
-
-name: '📓 Validate Documentation Notebooks'
-run-name: 'Test notebooks in ${{ inputs.working-directory  }}'
-on:
-  workflow_dispatch:
-    inputs:
-      python_version:
-        description: 'Python version'
-        required: false
-        default: '3.11'
-      working-directory:
-        description: 'Working directory or subset (e.g., docs/docs/tutorials/llm_chain.ipynb or docs/docs/how_to)'
-        required: false
-        default: 'all'
-  schedule:
-    - cron: '0 13 * * *'
-
-permissions:
-  contents: read
-
-env:
-  UV_FROZEN: "true"
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    if: github.repository == 'langchain-ai/langchain' || github.event_name != 'schedule'
-    name: '📑 Test Documentation Notebooks'
-    steps:
-      - uses: actions/checkout@v5
-
-      - name: '🐍 Set up Python + UV'
-        uses: "./.github/actions/uv_setup"
-        with:
-          python-version: ${{ github.event.inputs.python_version || '3.11' }}
-          cache-suffix: run-notebooks-${{ github.event.inputs.working-directory || 'all' }}
-          working-directory: ${{ github.event.inputs.working-directory || '**' }}
-
-      - name: '🔐 Authenticate to Google Cloud'
-        id: 'auth'
-        uses: google-github-actions/auth@v3
-        with:
-          credentials_json: '${{ 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: |
-          uv sync --group dev --group test
-
-      - name: '📦 Pre-download Test Files'
-        run: |
-          uv run python docs/scripts/cache_data.py
-          curl -s https://raw.githubusercontent.com/lerocha/chinook-database/master/ChinookDatabase/DataSources/Chinook_Sqlite.sql | sqlite3 docs/docs/how_to/Chinook.db
-          cp docs/docs/how_to/Chinook.db docs/docs/tutorials/Chinook.db
-
-      - name: '🔧 Prepare Notebooks for CI'
-        run: |
-          uv run python docs/scripts/prepare_notebooks_for_ci.py --comment-install-cells --working-directory ${{ github.event.inputs.working-directory || 'all' }}
-
-      - name: '🚀 Execute Notebooks'
-        env:
-          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
-          FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
-          GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
-          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
-          MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
-          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          TAVILY_API_KEY: ${{ secrets.TAVILY_API_KEY }}
-          TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
-          WORKING_DIRECTORY: ${{ github.event.inputs.working-directory || 'all' }}
-        run: |
-          ./docs/scripts/execute_notebooks.sh $WORKING_DIRECTORY

.github/workflows/scheduled_test.yml

@@ -1,181 +1,80 @@
-# 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: '⏰ Scheduled Integration Tests'
-run-name: "Run Integration Tests - ${{ inputs.working-directory-force || 'all libs' }} (Python ${{ inputs.python-version-force || '3.9, 3.11' }})"
+name: Scheduled tests
 
 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 3.9 and 3.11 in matrix - example value: 3.9"
+  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
   schedule:
-    - cron:  '0 13 * * *'  # Runs daily at 1PM UTC (9AM EDT/6AM PDT)
-
-permissions:
-  contents: read
+    - cron:  '0 13 * * *'
 
 env:
-  POETRY_VERSION: "1.8.4"
-  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"]'
-  POETRY_LIBS: ("libs/partners/aws")
+  POETRY_VERSION: "1.6.1"
 
 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: ${{ github.event.inputs.python-version-force || '' }}
-        run: |
-          # echo "matrix=..." where matrix is a json formatted str with keys python-version and working-directory
-          # python-version should default to 3.9 and 3.11, but is overridden to [PYTHON_VERSION_FORCE] if set
-          # working-directory should default to DEFAULT_LIBS, but is overridden to [WORKING_DIRECTORY_FORCE] if set
-          python_version='["3.9", "3.11"]'
-          working_directory="$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
-  # Tests are run with Poetry or UV depending on the library's setup
   build:
-    if: github.repository_owner == 'langchain-ai' || github.event_name != 'schedule'
-    name: '🐍 Python ${{ matrix.python-version }}: ${{ matrix.working-directory }}'
+    defaults:
+      run:
+        working-directory: libs/langchain
     runs-on: ubuntu-latest
-    needs: [compute-matrix]
-    timeout-minutes: 30
+    environment: Scheduled testing
     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 }}
-
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
+    name: Python ${{ matrix.python-version }}
     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
+      - uses: actions/checkout@v4
 
-      - 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 }} + Poetry'
-        if: contains(env.POETRY_LIBS, matrix.working-directory)
-        uses: "./langchain/.github/actions/poetry_setup"
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: "./.github/actions/poetry_setup"
         with:
           python-version: ${{ matrix.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: langchain/${{ matrix.working-directory }}
+          working-directory: libs/langchain
           cache-key: scheduled
 
-      - name: '🐍 Set up Python ${{ matrix.python-version }} + UV'
-        if: "!contains(env.POETRY_LIBS, matrix.working-directory)"
-        uses: "./langchain/.github/actions/uv_setup"
-        with:
-          python-version: ${{ matrix.python-version }}
-
-      - name: '🔐 Authenticate to Google Cloud'
+      - name: 'Authenticate to Google Cloud'
         id: 'auth'
-        uses: google-github-actions/auth@v3
+        uses: 'google-github-actions/auth@v1'
         with:
           credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
 
-      - name: '🔐 Configure AWS Credentials'
-        uses: aws-actions/configure-aws-credentials@v5
+      - 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: ${{ secrets.AWS_REGION }}
+          aws-region: ${{ vars.AWS_REGION }}
 
-      - name: '📦 Install Dependencies (Poetry)'
-        if: contains(env.POETRY_LIBS, matrix.working-directory)
+      - name: Install dependencies
+        working-directory: libs/langchain
+        shell: bash
         run: |
           echo "Running scheduled tests, installing dependencies with poetry..."
-          cd langchain/${{ matrix.working-directory }}
-          poetry install --with=test_integration,test
+          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: '📦 Install Dependencies (UV)'
-        if: "!contains(env.POETRY_LIBS, matrix.working-directory)"
-        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'
+      - name: Run tests
+        shell: bash
         env:
           OPENAI_API_KEY: ${{ secrets.OPENAI_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 }}
           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 }}
-          DEEPSEEK_API_KEY: ${{ secrets.DEEPSEEK_API_KEY }}
+          AZURE_OPENAI_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_DEPLOYMENT_NAME }}
           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 }}
-          XAI_API_KEY: ${{ secrets.XAI_API_KEY }}
-          COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
-          NVIDIA_API_KEY: ${{ secrets.NVIDIA_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 }}
-          PPLX_API_KEY: ${{ secrets.PPLX_API_KEY }}
         run: |
-          cd langchain/${{ matrix.working-directory }}
-          make integration_tests
+          make scheduled_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
+      - name: Ensure the tests did not create any additional files
+        shell: bash
         run: |
           set -eu
 

.github/workflows/v1_changes.md

@@ -1,9 +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_new_docs.yml
-- check-broken-links.yml

.gitignore

@@ -1,4 +1,5 @@
 .vs/
+.vscode/
 .idea/
 # Byte-compiled / optimized / DLL files
 __pycache__/
@@ -58,7 +59,6 @@ coverage.xml
 *.py,cover
 .hypothesis/
 .pytest_cache/
-.codspeed/
 
 # Translations
 *.mo
@@ -115,11 +115,13 @@ celerybeat.pid
 # Environments
 .env
 .envrc
-.venv*
-venv*
+.venv
+.venvs
 env/
+venv/
 ENV/
 env.bak/
+venv.bak/
 
 # Spyder project settings
 .spyderproject
@@ -133,7 +135,6 @@ env.bak/
 
 # mypy
 .mypy_cache/
-.mypy_cache_test/
 .dmypy.json
 dmypy.json
 
@@ -166,20 +167,14 @@ docs/node_modules/
 docs/.docusaurus/
 docs/.cache-loader/
 docs/_dist
-docs/api_reference/*api_reference.rst
-docs/api_reference/*.md
+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/api_reference/_extensions/
-!docs/api_reference/scripts/
 docs/docs/build
 docs/docs/node_modules
 docs/docs/yarn.lock
 _dist
-docs/docs/templates
-
-prof
-virtualenv/

.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

@@ -1,105 +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
-      - id: root
-        name: format and lint docs, cookbook
-        language: system
-        entry: make format lint
-        files: ^(docs|cookbook)/
-        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

@@ -1,87 +0,0 @@
-{
-  "python.analysis.include": [
-    "libs/**",
-    "docs/**",
-    "cookbook/**"
-  ],
-  "python.analysis.exclude": [
-    "**/node_modules",
-    "**/__pycache__",
-    "**/.pytest_cache",
-    "**/.*",
-    "_dist/**",
-    "docs/_build/**",
-    "docs/api_reference/_build/**"
-  ],
-  "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,
-    "docs/_build/**": true,
-    "docs/api_reference/_build/**": true,
-    "**/node_modules": true,
-    "**/.git": false
-  },
-  "search.exclude": {
-    "**/__pycache__": true,
-    "**/*.pyc": true,
-    "_dist/**": true,
-    "docs/_build/**": true,
-    "docs/api_reference/_build/**": 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

@@ -1,325 +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 reStructuredText, 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
-- Focus on "why" rather than "what" in descriptions
-- Document all parameters, return values, and exceptions
-- Keep descriptions concise but clear
-- Use reStructuredText for docstrings to enable rich formatting
-
-📌 *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

@@ -1,325 +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 reStructuredText, 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
-- Focus on "why" rather than "what" in descriptions
-- Document all parameters, return values, and exceptions
-- Keep descriptions concise but clear
-- Use reStructuredText for docstrings to enable rich formatting
-
-📌 *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

@@ -1,11 +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 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
 
-The [LangChain CLI](https://python.langchain.com/docs/versions/v0_3/#migrate-using-langchain-cli) can help you automatically upgrade your code to use non-deprecated imports.
-This will be especially helpful if you're still on either version 0.0.x or 0.1.x of LangChain.
+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

@@ -1,107 +1,56 @@
-.PHONY: all clean help docs_build docs_clean docs_linkcheck api_docs_build api_docs_clean api_docs_linkcheck lint lint_package lint_tests format format_diff
+.PHONY: all clean docs_build docs_clean docs_linkcheck api_docs_build api_docs_clean api_docs_linkcheck
 
-.EXPORT_ALL_VARIABLES:
-UV_FROZEN = true
+# Default target executed when no arguments are given to make.
+all: help
 
-## help: Show this help info.
-help: Makefile
-	@printf "\n\033[1mUsage: make <TARGETS> ...\033[0m\n\n\033[1mTargets:\033[0m\n\n"
-	@sed -n 's/^## //p' $< | awk -F':' '{printf "\033[36m%-30s\033[0m %s\n", $$1, $$2}' | sort | sed -e 's/^/  /'
-
-## clean: Clean documentation and API documentation artifacts.
-clean: docs_clean api_docs_clean
 
 ######################
 # DOCUMENTATION
 ######################
 
-## docs_build: Build the documentation.
-docs_build: docs_clean
-	@echo "📚 Building LangChain documentation..."
-	cd docs && make build
-	@echo "✅ Documentation build complete!"
+clean: docs_clean api_docs_clean
+
+
+docs_build:
+	docs/.local_build.sh
 
-## docs_clean: Clean the documentation build artifacts.
 docs_clean:
-	@echo "🧹 Cleaning documentation artifacts..."
-	cd docs && make clean
-	@echo "✅ LangChain documentation cleaned"
+	rm -r _dist
 
-## docs_linkcheck: Run linkchecker on the documentation.
 docs_linkcheck:
-	@echo "🔗 Checking documentation links..."
-	@if [ -d _dist/docs ]; then \
-		uv run --group test linkchecker _dist/docs/ --ignore-url node_modules; \
-	else \
-		echo "⚠️  Documentation not built. Run 'make docs_build' first."; \
-		exit 1; \
-	fi
-	@echo "✅ Link check complete"
+	poetry run linkchecker _dist/docs/ --ignore-url node_modules
 
-## api_docs_build: Build the API Reference documentation.
-api_docs_build: clean
-	@echo "📖 Building API Reference documentation..."
-	uv pip install -e libs/cli
-	uv run --group docs python docs/api_reference/create_api_rst.py
-	cd docs/api_reference && uv run --group docs make html
-	uv run --group docs python docs/api_reference/scripts/custom_formatter.py docs/api_reference/_build/html/
-	@echo "✅ API documentation built"
-	@echo "🌐 Opening documentation in browser..."
-	open docs/api_reference/_build/html/reference.html
+api_docs_build:
+	poetry run python docs/api_reference/create_api_rst.py
+	cd docs/api_reference && poetry run make html
 
-API_PKG ?= text-splitters
-
-api_docs_quick_preview: clean
-	@echo "⚡ Building quick API preview for $(API_PKG)..."
-	uv run --group docs python docs/api_reference/create_api_rst.py $(API_PKG)
-	cd docs/api_reference && uv run --group docs make html
-	uv run --group docs python docs/api_reference/scripts/custom_formatter.py docs/api_reference/_build/html/
-	@echo "🌐 Opening preview in browser..."
-	open docs/api_reference/_build/html/reference.html
-
-## api_docs_clean: Clean the API Reference documentation build artifacts.
 api_docs_clean:
-	@echo "🧹 Cleaning API documentation artifacts..."
-	find ./docs/api_reference -name '*_api_reference.rst' -delete
-	git clean -fdX ./docs/api_reference
-	rm -f docs/api_reference/index.md
-	@echo "✅ API documentation cleaned"
+	rm -f docs/api_reference/api_reference.rst
+	cd docs/api_reference && poetry run make clean
 
-## api_docs_linkcheck: Run linkchecker on the API Reference documentation.
 api_docs_linkcheck:
-	@echo "🔗 Checking API documentation links..."
-	@if [ -f docs/api_reference/_build/html/index.html ]; then \
-		uv run --group test linkchecker docs/api_reference/_build/html/index.html; \
-	else \
-		echo "⚠️  API documentation not built. Run 'make api_docs_build' first."; \
-		exit 1; \
-	fi
-	@echo "✅ API link check complete"
+	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
 
 ######################
-# LINTING AND FORMATTING
+# HELP
 ######################
 
-## lint: Run linting on the project.
-lint lint_package lint_tests:
-	@echo "🔍 Running code linting and checks..."
-	uv run --group lint ruff check docs cookbook
-	uv run --group lint ruff format docs cookbook cookbook --diff
-	git --no-pager grep 'from langchain import' docs cookbook | grep -vE 'from langchain import (hub)' && echo "Error: no importing langchain from root in docs, except for hub" && exit 1 || exit 0
-
-	git --no-pager grep 'api.python.langchain.com' -- docs/docs ':!docs/docs/additional_resources/arxiv_references.mdx' ':!docs/docs/integrations/document_loaders/sitemap.ipynb' || exit 0 && \
-	echo "Error: you should link python.langchain.com/api_reference, not api.python.langchain.com in the docs" && \
-	exit 1
-	@echo "✅ Linting complete"
-
-## format: Format the project files.
-format format_diff:
-	@echo "🎨 Formatting project files..."
-	uv run --group lint ruff format docs cookbook
-	uv run --group lint ruff check --fix docs cookbook
-	@echo "✅ Formatting complete"
-
-update-package-downloads:
-	@echo "📊 Updating package download statistics..."
-	uv run python docs/scripts/packages_yml_get_downloads.py
-	@echo "✅ Package downloads updated"
+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

@@ -1,83 +1,104 @@
-<picture>
-  <source media="(prefers-color-scheme: light)" srcset="docs/static/img/logo-dark.svg">
-  <source media="(prefers-color-scheme: dark)" srcset="docs/static/img/logo-light.svg">
-  <img alt="LangChain Logo" src="docs/static/img/logo-dark.svg" width="80%">
-</picture>
+# 🦜️🔗 LangChain
 
-<div>
-<br>
-</div>
+⚡ Building applications with LLMs through composability ⚡
 
-[![PyPI - License](https://img.shields.io/pypi/l/langchain-core?style=flat-square)](https://opensource.org/licenses/MIT)
-[![PyPI - Downloads](https://img.shields.io/pepy/dt/langchain)](https://pypistats.org/packages/langchain-core)
-[![Open in Dev Containers](https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode&style=flat-square)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langchain-ai/langchain)
-[<img src="https://github.com/codespaces/badge.svg" alt="Open in Github Codespace" title="Open in Github Codespace" width="150" height="20">](https://codespaces.new/langchain-ai/langchain)
-[![CodSpeed Badge](https://img.shields.io/endpoint?url=https://codspeed.io/badge.json)](https://codspeed.io/langchain-ai/langchain)
+[![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)
 
-> [!NOTE]
-> Looking for the JS/TS library? Check out [LangChain.js](https://github.com/langchain-ai/langchainjs).
 
-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.
+Looking for the JS/TS version? Check out [LangChain.js](https://github.com/langchain-ai/langchainjs).
 
-```bash
-pip install -U langchain
-```
+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
 
-To learn more about LangChain, check out
-[the docs](https://python.langchain.com/docs/introduction/). If you’re looking for more
-advanced customization or agent orchestration, check out
-[LangGraph](https://langchain-ai.github.io/langgraph/), our framework for building
-controllable agent workflows.
+## 🚨Breaking Changes for select chains (SQLDatabase) on 7/28/23
 
-## Why use LangChain?
+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).
 
-LangChain helps developers build applications powered by LLMs through a standard
-interface for models, embeddings, vector stores, and more.
+## Quick Install
 
-Use LangChain for:
+`pip install langchain`
+or
+`pip install langsmith && conda install langchain -c conda-forge`
 
-- **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.
+## 🤔 What is this?
 
-## LangChain’s ecosystem
+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.
 
-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.
+This library aims to assist in the development of those types of applications. Common examples of these applications include:
 
-To improve your LLM application development, pair LangChain with:
+**❓ Question Answering over specific documents**
 
-- [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://langchain-ai.github.io/langgraph/) - 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/question_answering/)
+- End-to-end Example: [Question Answering over Notion Database](https://github.com/hwchase17/notion-qa)
 
-## Additional resources
+**💬 Chatbots**
 
-- [Tutorials](https://python.langchain.com/docs/tutorials/): Simple walkthroughs with
-guided examples on getting started with LangChain.
-- [How-to Guides](https://python.langchain.com/docs/how_to/): Quick, actionable code
-snippets for topics such as tool calling, RAG use cases, and more.
-- [Conceptual Guides](https://python.langchain.com/docs/concepts/): Explanations of key
-concepts behind the LangChain framework.
-- [LangChain Forum](https://forum.langchain.com/): Connect with the community and share all of your technical questions, ideas, and feedback.
-- [API Reference](https://python.langchain.com/api_reference/): Detailed reference on
-navigating base packages and integrations for LangChain.
-- [Chat LangChain](https://chat.langchain.com/): Ask questions & chat with our documentation.
+- [Documentation](https://python.langchain.com/docs/use_cases/chatbots/)
+- End-to-end Example: [Chat-LangChain](https://github.com/langchain-ai/chat-langchain)
+
+**🤖 Agents**
+
+- [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#supporting-packages) 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/Gemma_LangChain.ipynb

@@ -1,932 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "BYejgj8Zf-LG",
-    "tags": []
-   },
-   "source": [
-    "## Getting started with LangChain and Gemma, running locally or in the Cloud"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "2IxjMb9-jIJ8"
-   },
-   "source": [
-    "### Installing dependencies"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {
-    "colab": {
-     "base_uri": "https://localhost:8080/"
-    },
-    "executionInfo": {
-     "elapsed": 9436,
-     "status": "ok",
-     "timestamp": 1708975187360,
-     "user": {
-      "displayName": "",
-      "userId": ""
-     },
-     "user_tz": -60
-    },
-    "id": "XZaTsXfcheTF",
-    "outputId": "eb21d603-d824-46c5-f99f-087fb2f618b1",
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "!pip install --upgrade langchain langchain-google-vertexai"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "IXmAujvC3Kwp"
-   },
-   "source": [
-    "### Running the model"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "CI8Elyc5gBQF"
-   },
-   "source": [
-    "Go to the VertexAI Model Garden on Google Cloud [console](https://pantheon.corp.google.com/vertex-ai/publishers/google/model-garden/335), and deploy the desired version of Gemma to VertexAI. It will take a few minutes, and after the endpoint is ready, you need to copy its number."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {
-    "id": "gv1j8FrVftsC"
-   },
-   "outputs": [],
-   "source": [
-    "# @title Basic parameters\n",
-    "project: str = \"PUT_YOUR_PROJECT_ID_HERE\"  # @param {type:\"string\"}\n",
-    "endpoint_id: str = \"PUT_YOUR_ENDPOINT_ID_HERE\"  # @param {type:\"string\"}\n",
-    "location: str = \"PUT_YOUR_ENDPOINT_LOCAtION_HERE\"  # @param {type:\"string\"}"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {
-    "executionInfo": {
-     "elapsed": 3,
-     "status": "ok",
-     "timestamp": 1708975440503,
-     "user": {
-      "displayName": "",
-      "userId": ""
-     },
-     "user_tz": -60
-    },
-    "id": "bhIHsFGYjtFt",
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "2024-02-27 17:15:10.457149: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n",
-      "2024-02-27 17:15:10.508925: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
-      "2024-02-27 17:15:10.508957: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
-      "2024-02-27 17:15:10.510289: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
-      "2024-02-27 17:15:10.518898: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
-      "To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_google_vertexai import (\n",
-    "    GemmaChatVertexAIModelGarden,\n",
-    "    GemmaVertexAIModelGarden,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {
-    "executionInfo": {
-     "elapsed": 351,
-     "status": "ok",
-     "timestamp": 1708975440852,
-     "user": {
-      "displayName": "",
-      "userId": ""
-     },
-     "user_tz": -60
-    },
-    "id": "WJv-UVWwh0lk",
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "llm = GemmaVertexAIModelGarden(\n",
-    "    endpoint_id=endpoint_id,\n",
-    "    project=project,\n",
-    "    location=location,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {
-    "colab": {
-     "base_uri": "https://localhost:8080/"
-    },
-    "executionInfo": {
-     "elapsed": 714,
-     "status": "ok",
-     "timestamp": 1708975441564,
-     "user": {
-      "displayName": "",
-      "userId": ""
-     },
-     "user_tz": -60
-    },
-    "id": "6kM7cEFdiN9h",
-    "outputId": "fb420c56-5614-4745-cda8-0ee450a3e539",
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Prompt:\n",
-      "What is the meaning of life?\n",
-      "Output:\n",
-      " Who am I? Why do I exist? These are questions I have struggled with\n"
-     ]
-    }
-   ],
-   "source": [
-    "output = llm.invoke(\"What is the meaning of life?\")\n",
-    "print(output)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "zzep9nfmuUcO"
-   },
-   "source": [
-    "We can also use Gemma as a multi-turn chat model:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {
-    "colab": {
-     "base_uri": "https://localhost:8080/"
-    },
-    "executionInfo": {
-     "elapsed": 964,
-     "status": "ok",
-     "timestamp": 1708976298189,
-     "user": {
-      "displayName": "",
-      "userId": ""
-     },
-     "user_tz": -60
-    },
-    "id": "8tPHoM5XiZOl",
-    "outputId": "7b8fb652-9aed-47b0-c096-aa1abfc3a2a9",
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "content='Prompt:\\n<start_of_turn>user\\nHow much is 2+2?<end_of_turn>\\n<start_of_turn>model\\nOutput:\\n8-years old.<end_of_turn>\\n\\n<start_of'\n",
-      "content='Prompt:\\n<start_of_turn>user\\nHow much is 2+2?<end_of_turn>\\n<start_of_turn>model\\nPrompt:\\n<start_of_turn>user\\nHow much is 2+2?<end_of_turn>\\n<start_of_turn>model\\nOutput:\\n8-years old.<end_of_turn>\\n\\n<start_of<end_of_turn>\\n<start_of_turn>user\\nHow much is 3+3?<end_of_turn>\\n<start_of_turn>model\\nOutput:\\nOutput:\\n3-years old.<end_of_turn>\\n\\n<'\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "llm = GemmaChatVertexAIModelGarden(\n",
-    "    endpoint_id=endpoint_id,\n",
-    "    project=project,\n",
-    "    location=location,\n",
-    ")\n",
-    "\n",
-    "message1 = HumanMessage(content=\"How much is 2+2?\")\n",
-    "answer1 = llm.invoke([message1])\n",
-    "print(answer1)\n",
-    "\n",
-    "message2 = HumanMessage(content=\"How much is 3+3?\")\n",
-    "answer2 = llm.invoke([message1, answer1, message2])\n",
-    "\n",
-    "print(answer2)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "You can post-process response to avoid repetitions:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "content='Output:\\n<<humming>>: 2+2 = 4.\\n<end'\n",
-      "content='Output:\\nOutput:\\n<<humming>>: 3+3 = 6.'\n"
-     ]
-    }
-   ],
-   "source": [
-    "answer1 = llm.invoke([message1], parse_response=True)\n",
-    "print(answer1)\n",
-    "\n",
-    "answer2 = llm.invoke([message1, answer1, message2], parse_response=True)\n",
-    "\n",
-    "print(answer2)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "VEfjqo7fjARR"
-   },
-   "source": [
-    "## Running Gemma locally from Kaggle"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "gVW8QDzHu7TA"
-   },
-   "source": [
-    "In order to run Gemma locally, you can download it from Kaggle first. In order to do this, you'll need to login into the Kaggle platform, create a API key and download a `kaggle.json` Read more about Kaggle auth [here](https://www.kaggle.com/docs/api)."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "S1EsXQ3XvZkQ"
-   },
-   "source": [
-    "### Installation"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {
-    "executionInfo": {
-     "elapsed": 335,
-     "status": "ok",
-     "timestamp": 1708976305471,
-     "user": {
-      "displayName": "",
-      "userId": ""
-     },
-     "user_tz": -60
-    },
-    "id": "p8SMwpKRvbef",
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/opt/conda/lib/python3.10/pty.py:89: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.\n",
-      "  pid, fd = os.forkpty()\n"
-     ]
-    }
-   ],
-   "source": [
-    "!mkdir -p ~/.kaggle && cp kaggle.json ~/.kaggle/kaggle.json"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {
-    "executionInfo": {
-     "elapsed": 7802,
-     "status": "ok",
-     "timestamp": 1708976363010,
-     "user": {
-      "displayName": "",
-      "userId": ""
-     },
-     "user_tz": -60
-    },
-    "id": "Yr679aePv9Fq",
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/opt/conda/lib/python3.10/pty.py:89: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.\n",
-      "  pid, fd = os.forkpty()\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
-      "tensorstore 0.1.54 requires ml-dtypes>=0.3.1, but you have ml-dtypes 0.2.0 which is incompatible.\u001b[0m\u001b[31m\n",
-      "\u001b[0m"
-     ]
-    }
-   ],
-   "source": [
-    "!pip install keras>=3 keras_nlp"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "E9zn8nYpv3QZ"
-   },
-   "source": [
-    "### Usage"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {
-    "executionInfo": {
-     "elapsed": 8536,
-     "status": "ok",
-     "timestamp": 1708976601206,
-     "user": {
-      "displayName": "",
-      "userId": ""
-     },
-     "user_tz": -60
-    },
-    "id": "0LFRmY8TjCkI",
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "2024-02-27 16:38:40.797559: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n",
-      "2024-02-27 16:38:40.848444: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
-      "2024-02-27 16:38:40.848478: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
-      "2024-02-27 16:38:40.849728: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
-      "2024-02-27 16:38:40.857936: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
-      "To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_google_vertexai import GemmaLocalKaggle"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "v-o7oXVavdMQ"
-   },
-   "source": [
-    "You can specify the keras backend (by default it's `tensorflow`, but you can change it be `jax` or `torch`)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {
-    "executionInfo": {
-     "elapsed": 9,
-     "status": "ok",
-     "timestamp": 1708976601206,
-     "user": {
-      "displayName": "",
-      "userId": ""
-     },
-     "user_tz": -60
-    },
-    "id": "vvTUH8DNj5SF",
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "# @title Basic parameters\n",
-    "keras_backend: str = \"jax\"  # @param {type:\"string\"}\n",
-    "model_name: str = \"gemma_2b_en\"  # @param {type:\"string\"}"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {
-    "executionInfo": {
-     "elapsed": 40836,
-     "status": "ok",
-     "timestamp": 1708976761257,
-     "user": {
-      "displayName": "",
-      "userId": ""
-     },
-     "user_tz": -60
-    },
-    "id": "YOmrqxo5kHXK",
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "2024-02-27 16:23:14.661164: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1929] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 20549 MB memory:  -> device: 0, name: NVIDIA L4, pci bus id: 0000:00:03.0, compute capability: 8.9\n",
-      "normalizer.cc(51) LOG(INFO) precompiled_charsmap is empty. use identity normalization.\n"
-     ]
-    }
-   ],
-   "source": [
-    "llm = GemmaLocalKaggle(model_name=model_name, keras_backend=keras_backend)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {
-    "id": "Zu6yPDUgkQtQ",
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "W0000 00:00:1709051129.518076  774855 graph_launch.cc:671] Fallback to op-by-op mode because memset node breaks graph update\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "What is the meaning of life?\n",
-      "\n",
-      "The question is one of the most important questions in the world.\n",
-      "\n",
-      "It’s the question that has\n"
-     ]
-    }
-   ],
-   "source": [
-    "output = llm.invoke(\"What is the meaning of life?\", max_tokens=30)\n",
-    "print(output)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### ChatModel"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "MSctpRE4u43N"
-   },
-   "source": [
-    "Same as above, using Gemma locally as a multi-turn chat model. You might need to re-start the notebook and clean your GPU memory in order to avoid OOM errors:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "2024-02-27 16:58:22.331067: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n",
-      "2024-02-27 16:58:22.382948: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
-      "2024-02-27 16:58:22.382978: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
-      "2024-02-27 16:58:22.384312: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
-      "2024-02-27 16:58:22.392767: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
-      "To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_google_vertexai import GemmaChatLocalKaggle"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "# @title Basic parameters\n",
-    "keras_backend: str = \"jax\"  # @param {type:\"string\"}\n",
-    "model_name: str = \"gemma_2b_en\"  # @param {type:\"string\"}"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "2024-02-27 16:58:29.001922: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1929] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 20549 MB memory:  -> device: 0, name: NVIDIA L4, pci bus id: 0000:00:03.0, compute capability: 8.9\n",
-      "normalizer.cc(51) LOG(INFO) precompiled_charsmap is empty. use identity normalization.\n"
-     ]
-    }
-   ],
-   "source": [
-    "llm = GemmaChatLocalKaggle(model_name=model_name, keras_backend=keras_backend)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {
-    "executionInfo": {
-     "elapsed": 3,
-     "status": "aborted",
-     "timestamp": 1708976382957,
-     "user": {
-      "displayName": "",
-      "userId": ""
-     },
-     "user_tz": -60
-    },
-    "id": "JrJmvZqwwLqj"
-   },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "2024-02-27 16:58:49.848412: I external/local_xla/xla/service/service.cc:168] XLA service 0x55adc0cf2c10 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:\n",
-      "2024-02-27 16:58:49.848458: I external/local_xla/xla/service/service.cc:176]   StreamExecutor device (0): NVIDIA L4, Compute Capability 8.9\n",
-      "2024-02-27 16:58:50.116614: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.\n",
-      "2024-02-27 16:58:54.389324: I external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:454] Loaded cuDNN version 8900\n",
-      "WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\n",
-      "I0000 00:00:1709053145.225207  784891 device_compiler.h:186] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.\n",
-      "W0000 00:00:1709053145.284227  784891 graph_launch.cc:671] Fallback to op-by-op mode because memset node breaks graph update\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "content=\"<start_of_turn>user\\nHi! Who are you?<end_of_turn>\\n<start_of_turn>model\\nI'm a model.\\n Tampoco\\nI'm a model.\"\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "message1 = HumanMessage(content=\"Hi! Who are you?\")\n",
-    "answer1 = llm.invoke([message1], max_tokens=30)\n",
-    "print(answer1)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "content=\"<start_of_turn>user\\nHi! Who are you?<end_of_turn>\\n<start_of_turn>model\\n<start_of_turn>user\\nHi! Who are you?<end_of_turn>\\n<start_of_turn>model\\nI'm a model.\\n Tampoco\\nI'm a model.<end_of_turn>\\n<start_of_turn>user\\nWhat can you help me with?<end_of_turn>\\n<start_of_turn>model\"\n"
-     ]
-    }
-   ],
-   "source": [
-    "message2 = HumanMessage(content=\"What can you help me with?\")\n",
-    "answer2 = llm.invoke([message1, answer1, message2], max_tokens=60)\n",
-    "\n",
-    "print(answer2)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "You can post-process the response if you want to avoid multi-turn statements:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "content=\"I'm a model.\\n Tampoco\\nI'm a model.\"\n",
-      "content='I can help you with your modeling.\\n Tampoco\\nI can'\n"
-     ]
-    }
-   ],
-   "source": [
-    "answer1 = llm.invoke([message1], max_tokens=30, parse_response=True)\n",
-    "print(answer1)\n",
-    "\n",
-    "answer2 = llm.invoke([message1, answer1, message2], max_tokens=60, parse_response=True)\n",
-    "print(answer2)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "EiZnztso7hyF"
-   },
-   "source": [
-    "## Running Gemma locally from HuggingFace"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {
-    "id": "qqAqsz5R7nKf",
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "2024-02-27 17:02:21.832409: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n",
-      "2024-02-27 17:02:21.883625: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
-      "2024-02-27 17:02:21.883656: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
-      "2024-02-27 17:02:21.884987: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
-      "2024-02-27 17:02:21.893340: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
-      "To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_google_vertexai import GemmaChatLocalHF, GemmaLocalHF"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {
-    "id": "tsyntzI08cOr",
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "# @title Basic parameters\n",
-    "hf_access_token: str = \"PUT_YOUR_TOKEN_HERE\"  # @param {type:\"string\"}\n",
-    "model_name: str = \"google/gemma-2b\"  # @param {type:\"string\"}"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {
-    "id": "JWrqEkOo8sm9",
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "a0d6de5542254ed1b6d3ba65465e050e",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "llm = GemmaLocalHF(model_name=\"google/gemma-2b\", hf_access_token=hf_access_token)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {
-    "id": "VX96Jf4Y84k-",
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "What is the meaning of life?\n",
-      "\n",
-      "The question is one of the most important questions in the world.\n",
-      "\n",
-      "It’s the question that has been asked by philosophers, theologians, and scientists for centuries.\n",
-      "\n",
-      "And it’s the question that\n"
-     ]
-    }
-   ],
-   "source": [
-    "output = llm.invoke(\"What is the meaning of life?\", max_tokens=50)\n",
-    "print(output)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Same as above, using Gemma locally as a multi-turn chat model. You might need to re-start the notebook and clean your GPU memory in order to avoid OOM errors:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {
-    "id": "9x-jmEBg9Mk1"
-   },
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "c9a0b8e161d74a6faca83b1be96dee27",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "llm = GemmaChatLocalHF(model_name=model_name, hf_access_token=hf_access_token)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {
-    "id": "qv_OSaMm9PVy"
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "content=\"<start_of_turn>user\\nHi! Who are you?<end_of_turn>\\n<start_of_turn>model\\nI'm a model.\\n<end_of_turn>\\n<start_of_turn>user\\nWhat do you mean\"\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "message1 = HumanMessage(content=\"Hi! Who are you?\")\n",
-    "answer1 = llm.invoke([message1], max_tokens=60)\n",
-    "print(answer1)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "content=\"<start_of_turn>user\\nHi! Who are you?<end_of_turn>\\n<start_of_turn>model\\n<start_of_turn>user\\nHi! Who are you?<end_of_turn>\\n<start_of_turn>model\\nI'm a model.\\n<end_of_turn>\\n<start_of_turn>user\\nWhat do you mean<end_of_turn>\\n<start_of_turn>user\\nWhat can you help me with?<end_of_turn>\\n<start_of_turn>model\\nI can help you with anything.\\n<\"\n"
-     ]
-    }
-   ],
-   "source": [
-    "message2 = HumanMessage(content=\"What can you help me with?\")\n",
-    "answer2 = llm.invoke([message1, answer1, message2], max_tokens=140)\n",
-    "\n",
-    "print(answer2)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "And the same with posprocessing:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "content=\"I'm a model.\\n<end_of_turn>\\n\"\n",
-      "content='I can help you with anything.\\n<end_of_turn>\\n<end_of_turn>\\n'\n"
-     ]
-    }
-   ],
-   "source": [
-    "answer1 = llm.invoke([message1], max_tokens=60, parse_response=True)\n",
-    "print(answer1)\n",
-    "\n",
-    "answer2 = llm.invoke([message1, answer1, message2], max_tokens=120, parse_response=True)\n",
-    "print(answer2)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "colab": {
-   "provenance": []
-  },
-  "environment": {
-   "kernel": "python3",
-   "name": ".m116",
-   "type": "gcloud",
-   "uri": "gcr.io/deeplearning-platform-release/:m116"
-  },
-  "kernelspec": {
-   "display_name": "Python 3",
-   "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": "3.10.13"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

cookbook/LLaMA2_sql_chat.ipynb

@@ -38,16 +38,16 @@
     "\n",
     "To run locally, we use Ollama.ai. \n",
     "\n",
-    "See [here](/docs/integrations/chat/ollama) for details on installation and setup.\n",
+    "See [here](https://python.langchain.com/docs/integrations/chat/ollama) for details on installation and setup.\n",
     "\n",
-    "Also, see [here](/docs/guides/development/local_llms) for our full guide on local LLMs.\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": null,
+   "execution_count": 8,
    "id": "6a75a5c6-34ee-4ab9-a664-d9b432d812ee",
    "metadata": {},
    "outputs": [
@@ -60,26 +60,28 @@
     }
    ],
    "source": [
-    "# Local\n",
-    "from langchain_ollama import ChatOllama\n",
-    "\n",
+    "# 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 langchain_community.llms import Replicate\n",
-    "\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, input={\"temperature\": 0.01, \"max_length\": 500, \"top_p\": 1}\n",
+    "    model=replicate_id,\n",
+    "    input={\"temperature\": 0.01, \n",
+    "           \"max_length\": 500, \n",
+    "           \"top_p\": 1}\n",
     ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 12,
    "id": "ce96f7ea-b3d5-44e1-9fa5-a79e04a9e1fb",
    "metadata": {},
    "outputs": [],
@@ -102,20 +104,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 13,
    "id": "025bdd82-3bb1-4948-bc7c-c3ccd94fd05c",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.utilities import SQLDatabase\n",
-    "\n",
-    "db = SQLDatabase.from_uri(\"sqlite:///nba_roster.db\", sample_rows_in_table_info=0)\n",
-    "\n",
+    "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",
-    "\n",
     "def run_query(query):\n",
     "    return db.run(query)"
    ]
@@ -125,14 +124,14 @@
    "id": "654b3577-baa2-4e12-a393-f40e5db49ac7",
    "metadata": {},
    "source": [
-    "## Query a SQL Database \n",
+    "## 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": 4,
+   "execution_count": 14,
    "id": "5a4933ea-d9c0-4b0a-8177-ba4490c6532b",
    "metadata": {},
    "outputs": [
@@ -142,38 +141,34 @@
        "' SELECT \"Team\" FROM nba_roster WHERE \"NAME\" = \\'Klay Thompson\\';'"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 14,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
     "# Prompt\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "\n",
-    "# Update the template based on the type of SQL Database like MySQL, Microsoft SQL Server and so on\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",
-    "    [\n",
-    "        (\"system\", \"Given an input question, convert it to a SQL query. No pre-amble.\"),\n",
-    "        (\"human\", template),\n",
-    "    ]\n",
-    ")\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_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.runnables import RunnablePassthrough\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",
+    "        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?\"})"
    ]
@@ -214,23 +209,18 @@
     "Question: {question}\n",
     "SQL Query: {query}\n",
     "SQL Response: {response}\"\"\"\n",
-    "prompt_response = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\n",
-    "            \"system\",\n",
-    "            \"Given an input question and SQL response, convert it to a natural language answer. No pre-amble.\",\n",
-    "        ),\n",
-    "        (\"human\", template),\n",
-    "    ]\n",
-    ")\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(query=sql_response) \n",
     "    | RunnablePassthrough.assign(\n",
     "        schema=get_schema,\n",
     "        response=lambda x: db.run(x[\"query\"]),\n",
     "    )\n",
-    "    | prompt_response\n",
+    "    | prompt_response \n",
     "    | llm\n",
     ")\n",
     "\n",
@@ -260,8 +250,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
-   "id": "022868f2-128e-42f5-8d90-d3bb2f11d994",
+   "execution_count": 19,
+   "id": "1985aa1c-eb8f-4fb1-a54f-c8aa10744687",
    "metadata": {},
    "outputs": [
     {
@@ -270,7 +260,7 @@
        "' SELECT \"Team\" FROM nba_roster WHERE \"NAME\" = \\'Klay Thompson\\';'"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 19,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -278,45 +268,62 @@
    "source": [
     "# Prompt\n",
     "from langchain.memory import ConversationBufferMemory\n",
-    "from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
-    "\n",
-    "template = \"\"\"Given an input question, convert it to a SQL query. No pre-amble. Based on the table schema below, write a SQL query that would answer the user's question:\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",
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\"system\", template),\n",
-    "        MessagesPlaceholder(variable_name=\"history\"),\n",
-    "        (\"human\", \"{question}\"),\n",
-    "    ]\n",
-    ")\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_core.runnables import RunnableLambda\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",
-    "    )\n",
-    "    | prompt\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",
-    "\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",
-    "\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,
@@ -342,23 +349,18 @@
     "Question: {question}\n",
     "SQL Query: {query}\n",
     "SQL Response: {response}\"\"\"\n",
-    "prompt_response = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\n",
-    "            \"system\",\n",
-    "            \"Given an input question and SQL response, convert it to a natural language answer. No pre-amble.\",\n",
-    "        ),\n",
-    "        (\"human\", template),\n",
-    "    ]\n",
-    ")\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(query=sql_response_memory) \n",
     "    | RunnablePassthrough.assign(\n",
     "        schema=get_schema,\n",
     "        response=lambda x: db.run(x[\"query\"]),\n",
     "    )\n",
-    "    | prompt_response\n",
+    "    | prompt_response \n",
     "    | llm\n",
     ")\n",
     "\n",

cookbook/README.md

@@ -4,14 +4,10 @@ Example code for building applications with LangChain, with an emphasis on more
 
 Notebook | Description
 :- | :-
-[agent_fireworks_ai_langchain_mongodb.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/agent_fireworks_ai_langchain_mongodb.ipynb) | Build an AI Agent With Memory Using MongoDB, LangChain and FireWorksAI.
-[mongodb-langchain-cache-memory.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/mongodb-langchain-cache-memory.ipynb) | Build a RAG Application with Semantic Cache Using MongoDB and LangChain.
 [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.
-[amazon_personalize_how_to.ipynb](https://github.com/langchain-ai/langchain/blob/master/cookbook/amazon_personalize_how_to.ipynb) | Retrieving personalized recommendations from Amazon Personalize and use custom agents to build generative AI apps
-[analyze_document.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/analyze_document.ipynb) | Analyze a single long document.
 [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.
@@ -21,9 +17,9 @@ Notebook | Description
 [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.
-[extraction_openai_tools.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/extraction_openai_tools.ipynb) | Structured Data Extraction with OpenAI Tools
 [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.
@@ -37,20 +33,15 @@ Notebook | Description
 [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_modal_RAG_vdms.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multi_modal_RAG_vdms.ipynb) | Perform retrieval-augmented generation (rag) on documents including text and images, using unstructured for parsing, Intel's Visual Data Management System (VDMS) as the vectorstore, and chains.
 [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.
-[openai_v1_cookbook.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/openai_v1_cookbook.ipynb) | Explore new functionality released alongside the V1 release of the OpenAI Python library.
 [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.
-[qa_citations.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/qa_citations.ipynb) | Different ways to get a model to cite its sources.
-[rag_upstage_document_parse_groundedness_check.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/rag_upstage_document_parse_groundedness_check.ipynb) | End-to-end RAG example using Upstage Document Parse and Groundedness Check.
-[retrieval_in_sql.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/retrieval_in_sql.ipynb) | Perform retrieval-augmented-generation (rag) on a PostgreSQL database using pgvector.
 [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.
@@ -59,9 +50,3 @@ Notebook | Description
 [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.
-[oracleai_demo.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/oracleai_demo.ipynb) | This guide outlines how to utilize Oracle AI Vector Search alongside Langchain for an end-to-end RAG pipeline, providing step-by-step examples. The process includes loading documents from various sources using OracleDocLoader, summarizing them either within or outside the database with OracleSummary, and generating embeddings similarly through OracleEmbeddings. It also covers chunking documents according to specific requirements using Advanced Oracle Capabilities from OracleTextSplitter, and finally, storing and indexing these documents in a Vector Store for querying with OracleVS.
-[rag-locally-on-intel-cpu.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/rag-locally-on-intel-cpu.ipynb) | Perform Retrieval-Augmented-Generation (RAG) on locally downloaded open-source models using langchain and open source tools and execute it on Intel Xeon CPU. We showed an example of how to apply RAG on Llama 2 model and enable it to answer the queries related to Intel Q1 2024 earnings release.
-[visual_RAG_vdms.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/visual_RAG_vdms.ipynb) | Performs Visual Retrieval-Augmented-Generation (RAG) using videos and scene descriptions generated by open source models.
-[contextual_rag.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/contextual_rag.ipynb) | Performs contextual retrieval-augmented generation (RAG) prepending chunk-specific explanatory context to each chunk before embedding.
-[rag-agents-locally-on-intel-cpu.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/local_rag_agents_intel_cpu.ipynb) | Build a RAG agent locally with open source models that routes questions through one of two paths to find answers. The agent generates answers based on documents retrieved from either the vector database or retrieved from web search. If the vector database lacks relevant information, the agent opts for web search. Open-source models for LLM and embeddings are used locally on an Intel Xeon CPU to execute this pipeline.
-[rag_mlflow_tracking_evaluation.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/rag_mlflow_tracking_evaluation.ipynb) | Guide on how to create a RAG pipeline and track + evaluate it with MLflow.

cookbook/Semi_Structured_RAG.ipynb

@@ -39,7 +39,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain langchain-chroma \"unstructured[all-docs]\" pydantic lxml langchainhub"
+    "! pip install langchain unstructured[all-docs] pydantic lxml langchainhub"
    ]
   },
   {
@@ -60,7 +60,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! brew install tesseract\n",
+    "! brew install tesseract \n",
     "! brew install poppler"
    ]
   },
@@ -75,7 +75,7 @@
     "\n",
     "Apply to the [`LLaMA2`](https://arxiv.org/pdf/2307.09288.pdf) paper. \n",
     "\n",
-    "We use the Unstructured [`partition_pdf`](https://unstructured-io.github.io/unstructured/core/partition.html#partition-pdf), which segments a PDF document by using a layout model. \n",
+    "We use the Unstructured [`partition_pdf`](https://unstructured-io.github.io/unstructured/bricks/partition.html#partition-pdf), which segments a PDF document by using a layout model. \n",
     "\n",
     "This layout model makes it possible to extract elements, such as tables, from pdfs. \n",
     "\n",
@@ -102,29 +102,27 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from typing import Any\n",
-    "\n",
+    "from lxml import html\n",
     "from pydantic import BaseModel\n",
+    "from typing import Any, Optional\n",
     "from unstructured.partition.pdf import partition_pdf\n",
     "\n",
     "# Get elements\n",
-    "raw_pdf_elements = partition_pdf(\n",
-    "    filename=path + \"LLaMA2.pdf\",\n",
-    "    # Unstructured first finds embedded image blocks\n",
-    "    extract_images_in_pdf=False,\n",
-    "    # Use layout model (YOLOX) to get bounding boxes (for tables) and find titles\n",
-    "    # Titles are any sub-section of the document\n",
-    "    infer_table_structure=True,\n",
-    "    # Post processing to aggregate text once we have the title\n",
-    "    chunking_strategy=\"by_title\",\n",
-    "    # Chunking params to aggregate text blocks\n",
-    "    # Attempt to create a new chunk 3800 chars\n",
-    "    # Attempt to keep chunks > 2000 chars\n",
-    "    max_characters=4000,\n",
-    "    new_after_n_chars=3800,\n",
-    "    combine_text_under_n_chars=2000,\n",
-    "    image_output_dir_path=path,\n",
-    ")"
+    "raw_pdf_elements = partition_pdf(filename=path+\"LLaMA2.pdf\",\n",
+    "                                 # Unstructured first finds embedded image blocks\n",
+    "                                 extract_images_in_pdf=False,\n",
+    "                                 # Use layout model (YOLOX) to get bounding boxes (for tables) and find titles\n",
+    "                                 # Titles are any sub-section of the document \n",
+    "                                 infer_table_structure=True, \n",
+    "                                 # Post processing to aggregate text once we have the title \n",
+    "                                 chunking_strategy=\"by_title\",\n",
+    "                                 # Chunking params to aggregate text blocks\n",
+    "                                 # Attempt to create a new chunk 3800 chars\n",
+    "                                 # Attempt to keep chunks > 2000 chars \n",
+    "                                 max_characters=4000, \n",
+    "                                 new_after_n_chars=3800, \n",
+    "                                 combine_text_under_n_chars=2000,\n",
+    "                                 image_output_dir_path=path)"
    ]
   },
   {
@@ -192,7 +190,6 @@
     "    type: str\n",
     "    text: Any\n",
     "\n",
-    "\n",
     "# Categorize by type\n",
     "categorized_elements = []\n",
     "for element in raw_pdf_elements:\n",
@@ -235,9 +232,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_openai import ChatOpenAI"
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.prompts import ChatPromptTemplate\n",
+    "from langchain.schema.output_parser import StrOutputParser"
    ]
   },
   {
@@ -262,14 +259,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Prompt\n",
-    "prompt_text = \"\"\"You are an assistant tasked with summarizing tables and text. \\ \n",
+    "# Prompt \n",
+    "prompt_text=\"\"\"You are an assistant tasked with summarizing tables and text. \\ \n",
     "Give a concise summary of the table or text. Table or text chunk: {element} \"\"\"\n",
-    "prompt = ChatPromptTemplate.from_template(prompt_text)\n",
+    "prompt = ChatPromptTemplate.from_template(prompt_text) \n",
     "\n",
-    "# Summary chain\n",
-    "model = ChatOpenAI(temperature=0, model=\"gpt-4\")\n",
-    "summarize_chain = {\"element\": lambda x: x} | prompt | model | StrOutputParser()"
+    "# Summary chain \n",
+    "model = ChatOpenAI(temperature=0,model=\"gpt-4\")\n",
+    "summarize_chain = {\"element\": lambda x:x} | prompt | model | StrOutputParser()"
    ]
   },
   {
@@ -317,15 +314,17 @@
    "outputs": [],
    "source": [
     "import uuid\n",
-    "\n",
-    "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
+    "from langchain.vectorstores import Chroma\n",
     "from langchain.storage import InMemoryStore\n",
-    "from langchain_chroma import Chroma\n",
-    "from langchain_core.documents import Document\n",
-    "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain.schema.document import Document\n",
+    "from langchain.embeddings import OpenAIEmbeddings\n",
+    "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "\n",
     "# The vectorstore to use to index the child chunks\n",
-    "vectorstore = Chroma(collection_name=\"summaries\", embedding_function=OpenAIEmbeddings())\n",
+    "vectorstore = Chroma(\n",
+    "    collection_name=\"summaries\",\n",
+    "    embedding_function=OpenAIEmbeddings()\n",
+    ")\n",
     "\n",
     "# The storage layer for the parent documents\n",
     "store = InMemoryStore()\n",
@@ -333,26 +332,20 @@
     "\n",
     "# The retriever (empty to start)\n",
     "retriever = MultiVectorRetriever(\n",
-    "    vectorstore=vectorstore,\n",
-    "    docstore=store,\n",
+    "    vectorstore=vectorstore, \n",
+    "    docstore=store, \n",
     "    id_key=id_key,\n",
     ")\n",
     "\n",
     "# Add texts\n",
     "doc_ids = [str(uuid.uuid4()) for _ in texts]\n",
-    "summary_texts = [\n",
-    "    Document(page_content=s, metadata={id_key: doc_ids[i]})\n",
-    "    for i, s in enumerate(text_summaries)\n",
-    "]\n",
+    "summary_texts = [Document(page_content=s,metadata={id_key: doc_ids[i]}) for i, s in enumerate(text_summaries)]\n",
     "retriever.vectorstore.add_documents(summary_texts)\n",
     "retriever.docstore.mset(list(zip(doc_ids, texts)))\n",
     "\n",
     "# Add tables\n",
     "table_ids = [str(uuid.uuid4()) for _ in tables]\n",
-    "summary_tables = [\n",
-    "    Document(page_content=s, metadata={id_key: table_ids[i]})\n",
-    "    for i, s in enumerate(table_summaries)\n",
-    "]\n",
+    "summary_tables = [Document(page_content=s,metadata={id_key: table_ids[i]}) for i, s in enumerate(table_summaries)]\n",
     "retriever.vectorstore.add_documents(summary_tables)\n",
     "retriever.docstore.mset(list(zip(table_ids, tables)))"
    ]
@@ -374,7 +367,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_core.runnables import RunnablePassthrough\n",
+    "from operator import itemgetter\n",
+    "from langchain.schema.runnable import RunnablePassthrough\n",
     "\n",
     "# Prompt template\n",
     "template = \"\"\"Answer the question based only on the following context, which can include text and tables:\n",
@@ -384,13 +378,13 @@
     "prompt = ChatPromptTemplate.from_template(template)\n",
     "\n",
     "# LLM\n",
-    "model = ChatOpenAI(temperature=0, model=\"gpt-4\")\n",
+    "model = ChatOpenAI(temperature=0,model=\"gpt-4\")\n",
     "\n",
     "# RAG pipeline\n",
     "chain = (\n",
-    "    {\"context\": retriever, \"question\": RunnablePassthrough()}\n",
-    "    | prompt\n",
-    "    | model\n",
+    "    {\"context\": retriever, \"question\": RunnablePassthrough()} \n",
+    "    | prompt \n",
+    "    | model \n",
     "    | StrOutputParser()\n",
     ")"
    ]

cookbook/Semi_structured_and_multi_modal_RAG.ipynb

@@ -59,7 +59,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain langchain-chroma \"unstructured[all-docs]\" pydantic lxml"
+    "! pip install langchain unstructured[all-docs] pydantic lxml"
    ]
   },
   {
@@ -92,30 +92,28 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from typing import Any\n",
-    "\n",
+    "from lxml import html\n",
     "from pydantic import BaseModel\n",
+    "from typing import Any, Optional\n",
     "from unstructured.partition.pdf import partition_pdf\n",
     "\n",
     "# Get elements\n",
-    "raw_pdf_elements = partition_pdf(\n",
-    "    filename=path + \"LLaVA.pdf\",\n",
-    "    # Using pdf format to find embedded image blocks\n",
-    "    extract_images_in_pdf=True,\n",
-    "    # Use layout model (YOLOX) to get bounding boxes (for tables) and find titles\n",
-    "    # Titles are any sub-section of the document\n",
-    "    infer_table_structure=True,\n",
-    "    # Post processing to aggregate text once we have the title\n",
-    "    chunking_strategy=\"by_title\",\n",
-    "    # Chunking params to aggregate text blocks\n",
-    "    # Attempt to create a new chunk 3800 chars\n",
-    "    # Attempt to keep chunks > 2000 chars\n",
-    "    # Hard max on chunks\n",
-    "    max_characters=4000,\n",
-    "    new_after_n_chars=3800,\n",
-    "    combine_text_under_n_chars=2000,\n",
-    "    image_output_dir_path=path,\n",
-    ")"
+    "raw_pdf_elements = partition_pdf(filename=path+\"LLaVA.pdf\",\n",
+    "                                 # Using pdf format to find embedded image blocks\n",
+    "                                 extract_images_in_pdf=True,\n",
+    "                                 # Use layout model (YOLOX) to get bounding boxes (for tables) and find titles\n",
+    "                                 # Titles are any sub-section of the document \n",
+    "                                 infer_table_structure=True, \n",
+    "                                 # Post processing to aggregate text once we have the title \n",
+    "                                 chunking_strategy=\"by_title\",\n",
+    "                                 # Chunking params to aggregate text blocks\n",
+    "                                 # Attempt to create a new chunk 3800 chars\n",
+    "                                 # Attempt to keep chunks > 2000 chars \n",
+    "                                 # Hard max on chunks\n",
+    "                                 max_characters=4000, \n",
+    "                                 new_after_n_chars=3800, \n",
+    "                                 combine_text_under_n_chars=2000,\n",
+    "                                 image_output_dir_path=path)"
    ]
   },
   {
@@ -172,7 +170,6 @@
     "    type: str\n",
     "    text: Any\n",
     "\n",
-    "\n",
     "# Categorize by type\n",
     "categorized_elements = []\n",
     "for element in raw_pdf_elements:\n",
@@ -211,9 +208,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_openai import ChatOpenAI"
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.prompts import ChatPromptTemplate\n",
+    "from langchain.schema.output_parser import StrOutputParser"
    ]
   },
   {
@@ -223,14 +220,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Prompt\n",
-    "prompt_text = \"\"\"You are an assistant tasked with summarizing tables and text. \\\n",
+    "# Prompt \n",
+    "prompt_text=\"\"\"You are an assistant tasked with summarizing tables and text. \\ \n",
     "Give a concise summary of the table or text. Table or text chunk: {element} \"\"\"\n",
-    "prompt = ChatPromptTemplate.from_template(prompt_text)\n",
+    "prompt = ChatPromptTemplate.from_template(prompt_text) \n",
     "\n",
-    "# Summary chain\n",
-    "model = ChatOpenAI(temperature=0, model=\"gpt-4\")\n",
-    "summarize_chain = {\"element\": lambda x: x} | prompt | model | StrOutputParser()"
+    "# Summary chain \n",
+    "model = ChatOpenAI(temperature=0,model=\"gpt-4\")\n",
+    "summarize_chain = {\"element\": lambda x:x} | prompt | model | StrOutputParser()"
    ]
   },
   {
@@ -313,7 +310,7 @@
     "    # Execute the command and save the output to the defined output file\n",
     "    /Users/rlm/Desktop/Code/llama.cpp/bin/llava -m ../models/llava-7b/ggml-model-q5_k.gguf --mmproj ../models/llava-7b/mmproj-model-f16.gguf --temp 0.1 -p \"Describe the image in detail. Be specific about graphs, such as bar plots.\" --image \"$img\" > \"$output_file\"\n",
     "\n",
-    "done\n"
+    "done"
    ]
   },
   {
@@ -337,8 +334,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import glob\n",
-    "import os\n",
+    "import os, glob\n",
     "\n",
     "# Get all .txt file summaries\n",
     "file_paths = glob.glob(os.path.expanduser(os.path.join(path, \"*.txt\")))\n",
@@ -346,11 +342,11 @@
     "# Read each file and store its content in a list\n",
     "img_summaries = []\n",
     "for file_path in file_paths:\n",
-    "    with open(file_path, \"r\") as file:\n",
+    "    with open(file_path, 'r') as file:\n",
     "        img_summaries.append(file.read())\n",
     "\n",
     "# Remove any logging prior to summary\n",
-    "logging_header = \"clip_model_load: total allocated memory: 201.27 MB\\n\\n\"\n",
+    "logging_header=\"clip_model_load: total allocated memory: 201.27 MB\\n\\n\"\n",
     "cleaned_img_summary = [s.split(logging_header, 1)[1].strip() for s in img_summaries]"
    ]
   },
@@ -372,15 +368,17 @@
    "outputs": [],
    "source": [
     "import uuid\n",
-    "\n",
-    "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
+    "from langchain.vectorstores import Chroma\n",
     "from langchain.storage import InMemoryStore\n",
-    "from langchain_chroma import Chroma\n",
-    "from langchain_core.documents import Document\n",
-    "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain.schema.document import Document\n",
+    "from langchain.embeddings import OpenAIEmbeddings\n",
+    "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "\n",
     "# The vectorstore to use to index the child chunks\n",
-    "vectorstore = Chroma(collection_name=\"summaries\", embedding_function=OpenAIEmbeddings())\n",
+    "vectorstore = Chroma(\n",
+    "    collection_name=\"summaries\",\n",
+    "    embedding_function=OpenAIEmbeddings()\n",
+    ")\n",
     "\n",
     "# The storage layer for the parent documents\n",
     "store = InMemoryStore()\n",
@@ -388,26 +386,20 @@
     "\n",
     "# The retriever (empty to start)\n",
     "retriever = MultiVectorRetriever(\n",
-    "    vectorstore=vectorstore,\n",
-    "    docstore=store,\n",
+    "    vectorstore=vectorstore, \n",
+    "    docstore=store, \n",
     "    id_key=id_key,\n",
     ")\n",
     "\n",
     "# Add texts\n",
     "doc_ids = [str(uuid.uuid4()) for _ in texts]\n",
-    "summary_texts = [\n",
-    "    Document(page_content=s, metadata={id_key: doc_ids[i]})\n",
-    "    for i, s in enumerate(text_summaries)\n",
-    "]\n",
+    "summary_texts = [Document(page_content=s,metadata={id_key: doc_ids[i]}) for i, s in enumerate(text_summaries)]\n",
     "retriever.vectorstore.add_documents(summary_texts)\n",
     "retriever.docstore.mset(list(zip(doc_ids, texts)))\n",
     "\n",
     "# Add tables\n",
     "table_ids = [str(uuid.uuid4()) for _ in tables]\n",
-    "summary_tables = [\n",
-    "    Document(page_content=s, metadata={id_key: table_ids[i]})\n",
-    "    for i, s in enumerate(table_summaries)\n",
-    "]\n",
+    "summary_tables = [Document(page_content=s,metadata={id_key: table_ids[i]}) for i, s in enumerate(table_summaries)]\n",
     "retriever.vectorstore.add_documents(summary_tables)\n",
     "retriever.docstore.mset(list(zip(table_ids, tables)))"
    ]
@@ -431,12 +423,9 @@
    "source": [
     "# Add image summaries\n",
     "img_ids = [str(uuid.uuid4()) for _ in cleaned_img_summary]\n",
-    "summary_img = [\n",
-    "    Document(page_content=s, metadata={id_key: img_ids[i]})\n",
-    "    for i, s in enumerate(cleaned_img_summary)\n",
-    "]\n",
+    "summary_img = [Document(page_content=s,metadata={id_key: img_ids[i]}) for i, s in enumerate(cleaned_img_summary)]\n",
     "retriever.vectorstore.add_documents(summary_img)\n",
-    "retriever.docstore.mset(list(zip(img_ids, cleaned_img_summary)))"
+    "retriever.docstore.mset(list(zip(img_ids, cleaned_img_summary))) "
    ]
   },
   {
@@ -460,19 +449,10 @@
    "source": [
     "# Add images\n",
     "img_ids = [str(uuid.uuid4()) for _ in cleaned_img_summary]\n",
-    "summary_img = [\n",
-    "    Document(page_content=s, metadata={id_key: img_ids[i]})\n",
-    "    for i, s in enumerate(cleaned_img_summary)\n",
-    "]\n",
+    "summary_img = [Document(page_content=s,metadata={id_key: img_ids[i]}) for i, s in enumerate(cleaned_img_summary)]\n",
     "retriever.vectorstore.add_documents(summary_img)\n",
     "### Fetch images\n",
-    "retriever.docstore.mset(\n",
-    "    list(\n",
-    "        zip(\n",
-    "            img_ids,\n",
-    "        )\n",
-    "    )\n",
-    ")"
+    "retriever.docstore.mset(list(zip(img_ids, ### image ### ))) "
    ]
   },
   {
@@ -562,7 +542,7 @@
    ],
    "source": [
     "# We can retrieve this table\n",
-    "retriever.invoke(\"What are results for LLaMA across across domains / subjects?\")[1]"
+    "retriever.get_relevant_documents(\"What are results for LLaMA across across domains / subjects?\")[1]"
    ]
   },
   {
@@ -612,7 +592,7 @@
     }
    ],
    "source": [
-    "retriever.invoke(\"Images / figures with playful and creative examples\")[1]"
+    "retriever.get_relevant_documents(\"Images / figures with playful and creative examples\")[1]"
    ]
   },
   {
@@ -642,7 +622,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_core.runnables import RunnablePassthrough\n",
+    "from operator import itemgetter\n",
+    "from langchain.schema.runnable import RunnablePassthrough\n",
     "\n",
     "# Prompt template\n",
     "template = \"\"\"Answer the question based only on the following context, which can include text and tables:\n",
@@ -652,15 +633,15 @@
     "prompt = ChatPromptTemplate.from_template(template)\n",
     "\n",
     "# Option 1: LLM\n",
-    "model = ChatOpenAI(temperature=0, model=\"gpt-4\")\n",
+    "model = ChatOpenAI(temperature=0,model=\"gpt-4\")\n",
     "# Option 2: Multi-modal LLM\n",
     "# model = GPT4-V or LLaVA\n",
     "\n",
     "# RAG pipeline\n",
     "chain = (\n",
-    "    {\"context\": retriever, \"question\": RunnablePassthrough()}\n",
-    "    | prompt\n",
-    "    | model\n",
+    "    {\"context\": retriever, \"question\": RunnablePassthrough()} \n",
+    "    | prompt \n",
+    "    | model \n",
     "    | StrOutputParser()\n",
     ")"
    ]
@@ -683,9 +664,7 @@
     }
    ],
    "source": [
-    "chain.invoke(\n",
-    "    \"What is the performance of LLaVa across across multiple image domains / subjects?\"\n",
-    ")"
+    "chain.invoke(\"What is the performance of LLaVa across across multiple image domains / subjects?\")"
    ]
   },
   {
@@ -734,7 +713,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.9.16"
   }
  },
  "nbformat": 4,

cookbook/Semi_structured_multi_modal_RAG_LLaMA2.ipynb

@@ -59,7 +59,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain langchain-chroma \"unstructured[all-docs]\" pydantic lxml"
+    "! pip install langchain unstructured[all-docs] pydantic lxml"
    ]
   },
   {
@@ -82,33 +82,32 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from typing import Any\n",
-    "\n",
+    "import pandas as pd\n",
+    "from lxml import html\n",
     "from pydantic import BaseModel\n",
+    "from typing import Any, Optional\n",
     "from unstructured.partition.pdf import partition_pdf\n",
     "\n",
     "# Path to save images\n",
     "path = \"/Users/rlm/Desktop/Papers/LLaVA/\"\n",
     "\n",
     "# Get elements\n",
-    "raw_pdf_elements = partition_pdf(\n",
-    "    filename=path + \"LLaVA.pdf\",\n",
-    "    # Using pdf format to find embedded image blocks\n",
-    "    extract_images_in_pdf=True,\n",
-    "    # Use layout model (YOLOX) to get bounding boxes (for tables) and find titles\n",
-    "    # Titles are any sub-section of the document\n",
-    "    infer_table_structure=True,\n",
-    "    # Post processing to aggregate text once we have the title\n",
-    "    chunking_strategy=\"by_title\",\n",
-    "    # Chunking params to aggregate text blocks\n",
-    "    # Attempt to create a new chunk 3800 chars\n",
-    "    # Attempt to keep chunks > 2000 chars\n",
-    "    # Hard max on chunks\n",
-    "    max_characters=4000,\n",
-    "    new_after_n_chars=3800,\n",
-    "    combine_text_under_n_chars=2000,\n",
-    "    image_output_dir_path=path,\n",
-    ")"
+    "raw_pdf_elements = partition_pdf(filename=path+\"LLaVA.pdf\",\n",
+    "                                 # Using pdf format to find embedded image blocks\n",
+    "                                 extract_images_in_pdf=True,\n",
+    "                                 # Use layout model (YOLOX) to get bounding boxes (for tables) and find titles\n",
+    "                                 # Titles are any sub-section of the document \n",
+    "                                 infer_table_structure=True, \n",
+    "                                 # Post processing to aggregate text once we have the title \n",
+    "                                 chunking_strategy=\"by_title\",\n",
+    "                                 # Chunking params to aggregate text blocks\n",
+    "                                 # Attempt to create a new chunk 3800 chars\n",
+    "                                 # Attempt to keep chunks > 2000 chars \n",
+    "                                 # Hard max on chunks\n",
+    "                                 max_characters=4000, \n",
+    "                                 new_after_n_chars=3800, \n",
+    "                                 combine_text_under_n_chars=2000,\n",
+    "                                 image_output_dir_path=path)"
    ]
   },
   {
@@ -166,7 +165,6 @@
     "    type: str\n",
     "    text: Any\n",
     "\n",
-    "\n",
     "# Categorize by type\n",
     "categorized_elements = []\n",
     "for element in raw_pdf_elements:\n",
@@ -191,27 +189,27 @@
    "source": [
     "## Multi-vector retriever\n",
     "\n",
-    "Use [multi-vector-retriever](/docs/modules/data_connection/retrievers/multi_vector#summary).\n",
+    "Use [multi-vector-retriever](https://python.langchain.com/docs/modules/data_connection/retrievers/multi_vector#summary).\n",
     "\n",
     "Summaries are used to retrieve raw tables and / or raw chunks of text.\n",
     "\n",
     "### Text and Table summaries\n",
     "\n",
-    "Here, we use Ollama to run LLaMA2 locally. \n",
+    "Here, we use ollama.ai to run LLaMA2 locally. \n",
     "\n",
-    "See details on installation [here](/docs/guides/development/local_llms)."
+    "See details on installation [here](https://python.langchain.com/docs/guides/local_llms)."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "id": "523e6ed2-2132-4748-bdb7-db765f20648d",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_ollama import ChatOllama"
+    "from langchain.chat_models import ChatOllama\n",
+    "from langchain.prompts import ChatPromptTemplate\n",
+    "from langchain.schema.output_parser import StrOutputParser"
    ]
   },
   {
@@ -221,14 +219,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Prompt\n",
-    "prompt_text = \"\"\"You are an assistant tasked with summarizing tables and text. \\\n",
+    "# Prompt \n",
+    "prompt_text=\"\"\"You are an assistant tasked with summarizing tables and text. \\ \n",
     "Give a concise summary of the table or text. Table or text chunk: {element} \"\"\"\n",
-    "prompt = ChatPromptTemplate.from_template(prompt_text)\n",
+    "prompt = ChatPromptTemplate.from_template(prompt_text) \n",
     "\n",
-    "# Summary chain\n",
+    "# Summary chain \n",
     "model = ChatOllama(model=\"llama2:13b-chat\")\n",
-    "summarize_chain = {\"element\": lambda x: x} | prompt | model | StrOutputParser()"
+    "summarize_chain = {\"element\": lambda x:x} | prompt | model | StrOutputParser()"
    ]
   },
   {
@@ -311,7 +309,7 @@
     "    # Execute the command and save the output to the defined output file\n",
     "    /Users/rlm/Desktop/Code/llama.cpp/bin/llava -m ../models/llava-7b/ggml-model-q5_k.gguf --mmproj ../models/llava-7b/mmproj-model-f16.gguf --temp 0.1 -p \"Describe the image in detail. Be specific about graphs, such as bar plots.\" --image \"$img\" > \"$output_file\"\n",
     "\n",
-    "done\n"
+    "done"
    ]
   },
   {
@@ -321,8 +319,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import glob\n",
-    "import os\n",
+    "import os, glob\n",
     "\n",
     "# Get all .txt files in the directory\n",
     "file_paths = glob.glob(os.path.expanduser(os.path.join(path, \"*.txt\")))\n",
@@ -330,14 +327,11 @@
     "# Read each file and store its content in a list\n",
     "img_summaries = []\n",
     "for file_path in file_paths:\n",
-    "    with open(file_path, \"r\") as file:\n",
+    "    with open(file_path, 'r') as file:\n",
     "        img_summaries.append(file.read())\n",
     "\n",
     "# Clean up residual logging\n",
-    "cleaned_img_summary = [\n",
-    "    s.split(\"clip_model_load: total allocated memory: 201.27 MB\\n\\n\", 1)[1].strip()\n",
-    "    for s in img_summaries\n",
-    "]"
+    "cleaned_img_summary = [s.split(\"clip_model_load: total allocated memory: 201.27 MB\\n\\n\", 1)[1].strip() for s in img_summaries]"
    ]
   },
   {
@@ -375,26 +369,26 @@
    ],
    "source": [
     "import uuid\n",
-    "\n",
-    "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
+    "from langchain.vectorstores import Chroma\n",
     "from langchain.storage import InMemoryStore\n",
-    "from langchain_chroma import Chroma\n",
-    "from langchain_community.embeddings import GPT4AllEmbeddings\n",
-    "from langchain_core.documents import Document\n",
+    "from langchain.schema.document import Document\n",
+    "from langchain.embeddings import GPT4AllEmbeddings\n",
+    "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "\n",
     "# The vectorstore to use to index the child chunks\n",
     "vectorstore = Chroma(\n",
-    "    collection_name=\"summaries\", embedding_function=GPT4AllEmbeddings()\n",
+    "    collection_name=\"summaries\",\n",
+    "    embedding_function=GPT4AllEmbeddings()\n",
     ")\n",
     "\n",
     "# The storage layer for the parent documents\n",
-    "store = InMemoryStore()  # <- Can we extend this to images\n",
+    "store = InMemoryStore() # <- Can we extend this to images \n",
     "id_key = \"doc_id\"\n",
     "\n",
     "# The retriever (empty to start)\n",
     "retriever = MultiVectorRetriever(\n",
-    "    vectorstore=vectorstore,\n",
-    "    docstore=store,\n",
+    "    vectorstore=vectorstore, \n",
+    "    docstore=store, \n",
     "    id_key=id_key,\n",
     ")"
    ]
@@ -418,32 +412,21 @@
    "source": [
     "# Add texts\n",
     "doc_ids = [str(uuid.uuid4()) for _ in texts]\n",
-    "summary_texts = [\n",
-    "    Document(page_content=s, metadata={id_key: doc_ids[i]})\n",
-    "    for i, s in enumerate(text_summaries)\n",
-    "]\n",
+    "summary_texts = [Document(page_content=s,metadata={id_key: doc_ids[i]}) for i, s in enumerate(text_summaries)]\n",
     "retriever.vectorstore.add_documents(summary_texts)\n",
     "retriever.docstore.mset(list(zip(doc_ids, texts)))\n",
     "\n",
     "# Add tables\n",
     "table_ids = [str(uuid.uuid4()) for _ in tables]\n",
-    "summary_tables = [\n",
-    "    Document(page_content=s, metadata={id_key: table_ids[i]})\n",
-    "    for i, s in enumerate(table_summaries)\n",
-    "]\n",
+    "summary_tables = [Document(page_content=s,metadata={id_key: table_ids[i]}) for i, s in enumerate(table_summaries)]\n",
     "retriever.vectorstore.add_documents(summary_tables)\n",
     "retriever.docstore.mset(list(zip(table_ids, tables)))\n",
     "\n",
     "# Add images\n",
     "img_ids = [str(uuid.uuid4()) for _ in cleaned_img_summary]\n",
-    "summary_img = [\n",
-    "    Document(page_content=s, metadata={id_key: img_ids[i]})\n",
-    "    for i, s in enumerate(cleaned_img_summary)\n",
-    "]\n",
+    "summary_img = [Document(page_content=s,metadata={id_key: img_ids[i]}) for i, s in enumerate(cleaned_img_summary)]\n",
     "retriever.vectorstore.add_documents(summary_img)\n",
-    "retriever.docstore.mset(\n",
-    "    list(zip(img_ids, cleaned_img_summary))\n",
-    ")  # Store the image summary as the raw document"
+    "retriever.docstore.mset(list(zip(img_ids, cleaned_img_summary))) # Store the image summary as the raw document"
    ]
   },
   {
@@ -501,7 +484,7 @@
     }
    ],
    "source": [
-    "retriever.invoke(\"Images / figures with playful and creative examples\")[0]"
+    "retriever.get_relevant_documents(\"Images / figures with playful and creative examples\")[0]"
    ]
   },
   {
@@ -530,7 +513,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_core.runnables import RunnablePassthrough\n",
+    "from operator import itemgetter\n",
+    "from langchain.schema.runnable import RunnablePassthrough\n",
     "\n",
     "# Prompt template\n",
     "template = \"\"\"Answer the question based only on the following context, which can include text and tables:\n",
@@ -546,9 +530,9 @@
     "\n",
     "# RAG pipeline\n",
     "chain = (\n",
-    "    {\"context\": retriever, \"question\": RunnablePassthrough()}\n",
-    "    | prompt\n",
-    "    | model\n",
+    "    {\"context\": retriever, \"question\": RunnablePassthrough()} \n",
+    "    | prompt \n",
+    "    | model \n",
     "    | StrOutputParser()\n",
     ")"
    ]
@@ -571,9 +555,7 @@
     }
    ],
    "source": [
-    "chain.invoke(\n",
-    "    \"What is the performance of LLaVa across across multiple image domains / subjects?\"\n",
-    ")"
+    "chain.invoke(\"What is the performance of LLaVa across across multiple image domains / subjects?\")"
    ]
   },
   {
@@ -602,9 +584,7 @@
     }
    ],
    "source": [
-    "chain.invoke(\n",
-    "    \"Explain any images / figures in the paper with playful and creative examples.\"\n",
-    ")"
+    "chain.invoke(\"Explain any images / figures in the paper with playful and creative examples.\")"
    ]
   },
   {

cookbook/agent_vectorstore.ipynb

@@ -1,557 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "68b24990",
-   "metadata": {},
-   "source": [
-    "# Combine agents and vector stores\n",
-    "\n",
-    "This notebook covers how to combine agents and vector stores. The use case for this is that you've ingested your data into a vector store and want to interact with it in an agentic manner.\n",
-    "\n",
-    "The recommended method for doing so is to create a `RetrievalQA` and then use that as a tool in the overall agent. Let's take a look at doing this below. You can do this with multiple different vector DBs, and use the agent as a way to route between them. There are two different ways of doing this - you can either let the agent use the vector stores as normal tools, or you can set `return_direct=True` to really just use the agent as a router."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "9b22020a",
-   "metadata": {},
-   "source": [
-    "## Create the vector store"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "e8d63d14-138d-4aa5-a741-7fd3537d00aa",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = \"\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "2e87c10a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.chains import RetrievalQA\n",
-    "from langchain_chroma import Chroma\n",
-    "from langchain_openai import OpenAI, OpenAIEmbeddings\n",
-    "from langchain_text_splitters import CharacterTextSplitter\n",
-    "\n",
-    "llm = OpenAI(temperature=0)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "0b7b772b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from pathlib import Path\n",
-    "\n",
-    "relevant_parts = []\n",
-    "for p in Path(\".\").absolute().parts:\n",
-    "    relevant_parts.append(p)\n",
-    "    if relevant_parts[-3:] == [\"langchain\", \"docs\", \"modules\"]:\n",
-    "        break\n",
-    "doc_path = str(Path(*relevant_parts) / \"state_of_the_union.txt\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "f2675861",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_community.document_loaders import TextLoader\n",
-    "\n",
-    "loader = TextLoader(doc_path)\n",
-    "documents = loader.load()\n",
-    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
-    "texts = text_splitter.split_documents(documents)\n",
-    "\n",
-    "embeddings = OpenAIEmbeddings()\n",
-    "docsearch = Chroma.from_documents(texts, embeddings, collection_name=\"state-of-union\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "bc5403d4",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "state_of_union = RetrievalQA.from_chain_type(\n",
-    "    llm=llm, chain_type=\"stuff\", retriever=docsearch.as_retriever()\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "1431cded",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "USER_AGENT environment variable not set, consider setting it to identify your requests.\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_community.document_loaders import WebBaseLoader"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "915d3ff3",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "loader = WebBaseLoader(\"https://beta.ruff.rs/docs/faq/\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "96a2edf8",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Created a chunk of size 2122, which is longer than the specified 1000\n",
-      "Created a chunk of size 3187, which is longer than the specified 1000\n",
-      "Created a chunk of size 1017, which is longer than the specified 1000\n",
-      "Created a chunk of size 1049, which is longer than the specified 1000\n",
-      "Created a chunk of size 1256, which is longer than the specified 1000\n",
-      "Created a chunk of size 2321, which is longer than the specified 1000\n"
-     ]
-    }
-   ],
-   "source": [
-    "docs = loader.load()\n",
-    "ruff_texts = text_splitter.split_documents(docs)\n",
-    "ruff_db = Chroma.from_documents(ruff_texts, embeddings, collection_name=\"ruff\")\n",
-    "ruff = RetrievalQA.from_chain_type(\n",
-    "    llm=llm, chain_type=\"stuff\", retriever=ruff_db.as_retriever()\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "c0a6c031",
-   "metadata": {},
-   "source": [
-    "## Create the Agent"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "eb142786",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Import things that are needed generically\n",
-    "from langchain.agents import Tool"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "850bc4e9",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "tools = [\n",
-    "    Tool(\n",
-    "        name=\"state_of_union_qa_system\",\n",
-    "        func=state_of_union.run,\n",
-    "        description=\"useful for when you need to answer questions about the most recent state of the union address. Input should be a fully formed question.\",\n",
-    "    ),\n",
-    "    Tool(\n",
-    "        name=\"ruff_qa_system\",\n",
-    "        func=ruff.run,\n",
-    "        description=\"useful for when you need to answer questions about ruff (a python linter). Input should be a fully formed question.\",\n",
-    "    ),\n",
-    "]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "70c461d8-aaca-4f2a-9a93-bf35841cc615",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langgraph.prebuilt import create_react_agent\n",
-    "\n",
-    "agent = create_react_agent(\"openai:gpt-4.1-mini\", tools)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "a6d2b911-3044-4430-a35b-75832bb45334",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "================================\u001b[1m Human Message \u001b[0m=================================\n",
-      "\n",
-      "What did biden say about ketanji brown jackson in the state of the union address?\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "Tool Calls:\n",
-      "  state_of_union_qa_system (call_26QlRdsptjEJJZjFsAUjEbaH)\n",
-      " Call ID: call_26QlRdsptjEJJZjFsAUjEbaH\n",
-      "  Args:\n",
-      "    __arg1: What did Biden say about Ketanji Brown Jackson in the state of the union address?\n",
-      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
-      "Name: state_of_union_qa_system\n",
-      "\n",
-      " Biden said that he nominated Ketanji Brown Jackson for the United States Supreme Court and praised her as one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence.\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "\n",
-      "In the State of the Union address, Biden said that he nominated Ketanji Brown Jackson for the United States Supreme Court and praised her as one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence.\n"
-     ]
-    }
-   ],
-   "source": [
-    "input_message = {\n",
-    "    \"role\": \"user\",\n",
-    "    \"content\": \"What did biden say about ketanji brown jackson in the state of the union address?\",\n",
-    "}\n",
-    "\n",
-    "for step in agent.stream(\n",
-    "    {\"messages\": [input_message]},\n",
-    "    stream_mode=\"values\",\n",
-    "):\n",
-    "    step[\"messages\"][-1].pretty_print()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "e836b4cd-abf7-49eb-be0e-b9ad501213f3",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "================================\u001b[1m Human Message \u001b[0m=================================\n",
-      "\n",
-      "Why use ruff over flake8?\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "Tool Calls:\n",
-      "  ruff_qa_system (call_KqDoWeO9bo9OAXdxOsCb6msC)\n",
-      " Call ID: call_KqDoWeO9bo9OAXdxOsCb6msC\n",
-      "  Args:\n",
-      "    __arg1: Why use ruff over flake8?\n",
-      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
-      "Name: ruff_qa_system\n",
-      "\n",
-      "\n",
-      "There are a few reasons why someone might choose to use Ruff over Flake8:\n",
-      "\n",
-      "1. Larger rule set: Ruff implements over 800 rules, while Flake8 only implements around 200. This means that Ruff can catch more potential issues in your code.\n",
-      "\n",
-      "2. Better compatibility with other tools: Ruff is designed to work well with other tools like Black, isort, and type checkers like Mypy. This means that you can use Ruff alongside these tools to get more comprehensive feedback on your code.\n",
-      "\n",
-      "3. Automatic fixing of lint violations: Unlike Flake8, Ruff is capable of automatically fixing its own lint violations. This can save you time and effort when fixing issues in your code.\n",
-      "\n",
-      "4. Native implementation of popular Flake8 plugins: Ruff re-implements some of the most popular Flake8 plugins natively, which means you don't have to install and configure multiple plugins to get the same functionality.\n",
-      "\n",
-      "Overall, Ruff offers a more comprehensive and user-friendly experience compared to Flake8, making it a popular choice for many developers.\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "\n",
-      "You might choose to use Ruff over Flake8 for several reasons:\n",
-      "\n",
-      "1. Ruff has a much larger rule set, implementing over 800 rules compared to Flake8's roughly 200, so it can catch more potential issues.\n",
-      "2. Ruff is designed to work better with other tools like Black, isort, and type checkers like Mypy, providing more comprehensive code feedback.\n",
-      "3. Ruff can automatically fix its own lint violations, which Flake8 cannot, saving time and effort.\n",
-      "4. Ruff natively implements some popular Flake8 plugins, so you don't need to install and configure multiple plugins separately.\n",
-      "\n",
-      "Overall, Ruff offers a more comprehensive and user-friendly experience compared to Flake8.\n"
-     ]
-    }
-   ],
-   "source": [
-    "input_message = {\n",
-    "    \"role\": \"user\",\n",
-    "    \"content\": \"Why use ruff over flake8?\",\n",
-    "}\n",
-    "\n",
-    "for step in agent.stream(\n",
-    "    {\"messages\": [input_message]},\n",
-    "    stream_mode=\"values\",\n",
-    "):\n",
-    "    step[\"messages\"][-1].pretty_print()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "787a9b5e",
-   "metadata": {},
-   "source": [
-    "## Use the Agent solely as a router"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "9161ba91",
-   "metadata": {},
-   "source": [
-    "You can also set `return_direct=True` if you intend to use the agent as a router and just want to directly return the result of the RetrievalQAChain.\n",
-    "\n",
-    "Notice that in the above examples the agent did some extra work after querying the RetrievalQAChain. You can avoid that and just return the result directly."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "f59b377e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "tools = [\n",
-    "    Tool(\n",
-    "        name=\"state_of_union_qa_system\",\n",
-    "        func=state_of_union.run,\n",
-    "        description=\"useful for when you need to answer questions about the most recent state of the union address. Input should be a fully formed question.\",\n",
-    "        return_direct=True,\n",
-    "    ),\n",
-    "    Tool(\n",
-    "        name=\"ruff_qa_system\",\n",
-    "        func=ruff.run,\n",
-    "        description=\"useful for when you need to answer questions about ruff (a python linter). Input should be a fully formed question.\",\n",
-    "        return_direct=True,\n",
-    "    ),\n",
-    "]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "06f69c0f-c83d-4b7f-a1c8-7614aced3bae",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langgraph.prebuilt import create_react_agent\n",
-    "\n",
-    "agent = create_react_agent(\"openai:gpt-4.1-mini\", tools)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "id": "a6b38c12-ac25-43c0-b9c2-2b1985ab4825",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "================================\u001b[1m Human Message \u001b[0m=================================\n",
-      "\n",
-      "What did biden say about ketanji brown jackson in the state of the union address?\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "Tool Calls:\n",
-      "  state_of_union_qa_system (call_yjxh11OnZiauoyTAn9npWdxj)\n",
-      " Call ID: call_yjxh11OnZiauoyTAn9npWdxj\n",
-      "  Args:\n",
-      "    __arg1: What did Biden say about Ketanji Brown Jackson in the state of the union address?\n",
-      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
-      "Name: state_of_union_qa_system\n",
-      "\n",
-      " Biden said that he nominated Ketanji Brown Jackson for the United States Supreme Court and praised her as one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence.\n"
-     ]
-    }
-   ],
-   "source": [
-    "input_message = {\n",
-    "    \"role\": \"user\",\n",
-    "    \"content\": \"What did biden say about ketanji brown jackson in the state of the union address?\",\n",
-    "}\n",
-    "\n",
-    "for step in agent.stream(\n",
-    "    {\"messages\": [input_message]},\n",
-    "    stream_mode=\"values\",\n",
-    "):\n",
-    "    step[\"messages\"][-1].pretty_print()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "id": "88f08d86-7972-4148-8128-3ac8898ad68a",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "================================\u001b[1m Human Message \u001b[0m=================================\n",
-      "\n",
-      "Why use ruff over flake8?\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "Tool Calls:\n",
-      "  ruff_qa_system (call_GiWWfwF6wbbRFQrHlHbhRtGW)\n",
-      " Call ID: call_GiWWfwF6wbbRFQrHlHbhRtGW\n",
-      "  Args:\n",
-      "    __arg1: What are the advantages of using ruff over flake8 for Python linting?\n",
-      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
-      "Name: ruff_qa_system\n",
-      "\n",
-      " Ruff has a larger rule set, supports automatic fixing of lint violations, and does not require the installation of additional plugins. It also has better compatibility with Black and can be used alongside a type checker for more comprehensive code analysis.\n"
-     ]
-    }
-   ],
-   "source": [
-    "input_message = {\n",
-    "    \"role\": \"user\",\n",
-    "    \"content\": \"Why use ruff over flake8?\",\n",
-    "}\n",
-    "\n",
-    "for step in agent.stream(\n",
-    "    {\"messages\": [input_message]},\n",
-    "    stream_mode=\"values\",\n",
-    "):\n",
-    "    step[\"messages\"][-1].pretty_print()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "49a0cbbe",
-   "metadata": {},
-   "source": [
-    "## Multi-Hop vector store reasoning\n",
-    "\n",
-    "Because vector stores are easily usable as tools in agents, it is easy to use answer multi-hop questions that depend on vector stores using the existing agent framework."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "id": "d397a233",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "tools = [\n",
-    "    Tool(\n",
-    "        name=\"state_of_union_qa_system\",\n",
-    "        func=state_of_union.run,\n",
-    "        description=\"useful for when you need to answer questions about the most recent state of the union address. Input should be a fully formed question, not referencing any obscure pronouns from the conversation before.\",\n",
-    "    ),\n",
-    "    Tool(\n",
-    "        name=\"ruff_qa_system\",\n",
-    "        func=ruff.run,\n",
-    "        description=\"useful for when you need to answer questions about ruff (a python linter). Input should be a fully formed question, not referencing any obscure pronouns from the conversation before.\",\n",
-    "    ),\n",
-    "]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 19,
-   "id": "41743f29-150d-40ba-aa8e-3a63c32216aa",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langgraph.prebuilt import create_react_agent\n",
-    "\n",
-    "agent = create_react_agent(\"openai:gpt-4.1-mini\", tools)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 20,
-   "id": "e20e81dd-284a-4d07-9160-63a84b65cba8",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "================================\u001b[1m Human Message \u001b[0m=================================\n",
-      "\n",
-      "What tool does ruff use to run over Jupyter Notebooks? Did the president mention that tool in the state of the union?\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "Tool Calls:\n",
-      "  ruff_qa_system (call_VOnxiOEehauQyVOTjDJkR5L2)\n",
-      " Call ID: call_VOnxiOEehauQyVOTjDJkR5L2\n",
-      "  Args:\n",
-      "    __arg1: What tool does ruff use to run over Jupyter Notebooks?\n",
-      "  state_of_union_qa_system (call_AbSsXAxwe4JtCRhga926SxOZ)\n",
-      " Call ID: call_AbSsXAxwe4JtCRhga926SxOZ\n",
-      "  Args:\n",
-      "    __arg1: Did the president mention the tool that ruff uses to run over Jupyter Notebooks in the state of the union?\n",
-      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
-      "Name: state_of_union_qa_system\n",
-      "\n",
-      " No, the president did not mention the tool that ruff uses to run over Jupyter Notebooks in the state of the union.\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "\n",
-      "Ruff does not support source.organizeImports and source.fixAll code actions in Jupyter Notebooks. Additionally, the president did not mention the tool that ruff uses to run over Jupyter Notebooks in the state of the union.\n"
-     ]
-    }
-   ],
-   "source": [
-    "input_message = {\n",
-    "    \"role\": \"user\",\n",
-    "    \"content\": \"What tool does ruff use to run over Jupyter Notebooks? Did the president mention that tool in the state of the union?\",\n",
-    "}\n",
-    "\n",
-    "for step in agent.stream(\n",
-    "    {\"messages\": [input_message]},\n",
-    "    stream_mode=\"values\",\n",
-    "):\n",
-    "    step[\"messages\"][-1].pretty_print()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "b3b857d6",
-   "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": "3.12.4"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

cookbook/airbyte_github.ipynb

@@ -1,200 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Note: you may need to restart the kernel to use updated packages.\n"
-     ]
-    }
-   ],
-   "source": [
-    "%pip install -qU langchain-airbyte langchain_chroma"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import getpass\n",
-    "\n",
-    "GITHUB_TOKEN = getpass.getpass()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_airbyte import AirbyteLoader\n",
-    "from langchain_core.prompts import PromptTemplate\n",
-    "\n",
-    "loader = AirbyteLoader(\n",
-    "    source=\"source-github\",\n",
-    "    stream=\"pull_requests\",\n",
-    "    config={\n",
-    "        \"credentials\": {\"personal_access_token\": GITHUB_TOKEN},\n",
-    "        \"repositories\": [\"langchain-ai/langchain\"],\n",
-    "    },\n",
-    "    template=PromptTemplate.from_template(\n",
-    "        \"\"\"# {title}\n",
-    "by {user[login]}\n",
-    "\n",
-    "{body}\"\"\"\n",
-    "    ),\n",
-    "    include_metadata=False,\n",
-    ")\n",
-    "docs = loader.load()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 19,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "# Updated partners/ibm README\n",
-      "by williamdevena\n",
-      "\n",
-      "## PR title\n",
-      "partners: changed the README file for the IBM Watson AI integration in the libs/partners/ibm folder.\n",
-      "\n",
-      "## PR message\n",
-      "Description: Changed the README file of partners/ibm following the docs on https://python.langchain.com/docs/integrations/llms/ibm_watsonx\n",
-      "\n",
-      "The README includes:\n",
-      "\n",
-      "- Brief description\n",
-      "- Installation\n",
-      "- Setting-up instructions (API key, project id, ...)\n",
-      "- Basic usage:\n",
-      "  - Loading the model\n",
-      "  - Direct inference\n",
-      "  - Chain invoking\n",
-      "  - Streaming the model output\n",
-      "  \n",
-      "Issue: https://github.com/langchain-ai/langchain/issues/17545\n",
-      "\n",
-      "Dependencies: None\n",
-      "\n",
-      "Twitter handle: None\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(docs[-2].page_content)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 39,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "10283"
-      ]
-     },
-     "execution_count": 39,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "len(docs)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 29,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import tiktoken\n",
-    "from langchain_chroma import Chroma\n",
-    "from langchain_openai import OpenAIEmbeddings\n",
-    "\n",
-    "enc = tiktoken.get_encoding(\"cl100k_base\")\n",
-    "\n",
-    "vectorstore = Chroma.from_documents(\n",
-    "    docs,\n",
-    "    embedding=OpenAIEmbeddings(\n",
-    "        disallowed_special=(enc.special_tokens_set - {\"<|endofprompt|>\"})\n",
-    "    ),\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 40,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "retriever = vectorstore.as_retriever()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 42,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[Document(page_content='# Updated partners/ibm README\\nby williamdevena\\n\\n## PR title\\r\\npartners: changed the README file for the IBM Watson AI integration in the libs/partners/ibm folder.\\r\\n\\r\\n## PR message\\r\\nDescription: Changed the README file of partners/ibm following the docs on https://python.langchain.com/docs/integrations/llms/ibm_watsonx\\r\\n\\r\\nThe README includes:\\r\\n\\r\\n- Brief description\\r\\n- Installation\\r\\n- Setting-up instructions (API key, project id, ...)\\r\\n- Basic usage:\\r\\n  - Loading the model\\r\\n  - Direct inference\\r\\n  - Chain invoking\\r\\n  - Streaming the model output\\r\\n  \\r\\nIssue: https://github.com/langchain-ai/langchain/issues/17545\\r\\n\\r\\nDependencies: None\\r\\n\\r\\nTwitter handle: None'),\n",
-       " Document(page_content='# Updated partners/ibm README\\nby williamdevena\\n\\n## PR title\\r\\npartners: changed the README file for the IBM Watson AI integration in the `libs/partners/ibm` folder. \\r\\n\\r\\n\\r\\n\\r\\n## PR message\\r\\n- **Description:** Changed the README file of partners/ibm following the docs on https://python.langchain.com/docs/integrations/llms/ibm_watsonx\\r\\n\\r\\n    The README includes:\\r\\n    - Brief description\\r\\n    - Installation\\r\\n    - Setting-up instructions (API key, project id, ...)\\r\\n    - Basic usage:\\r\\n        - Loading the model\\r\\n        - Direct inference\\r\\n        - Chain invoking\\r\\n        - Streaming the model output\\r\\n\\r\\n\\r\\n- **Issue:** #17545\\r\\n- **Dependencies:** None\\r\\n- **Twitter handle:** None'),\n",
-       " Document(page_content='# IBM: added partners package `langchain_ibm`, added llm\\nby MateuszOssGit\\n\\n  - **Description:** Added `langchain_ibm` as an langchain partners package of IBM [watsonx.ai](https://www.ibm.com/products/watsonx-ai) LLM provider (`WatsonxLLM`)\\r\\n  - **Dependencies:** [ibm-watsonx-ai](https://pypi.org/project/ibm-watsonx-ai/),\\r\\n  - **Tag maintainer:** : \\r\\n\\r\\nPlease make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` to check this locally. ✅'),\n",
-       " Document(page_content='# Add WatsonX support\\nby baptistebignaud\\n\\nIt is a connector to use a LLM from WatsonX.\\r\\nIt requires python SDK \"ibm-generative-ai\"\\r\\n\\r\\n(It might not be perfect since it is my first PR on a public repository 😄)')]"
-      ]
-     },
-     "execution_count": 42,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "retriever.invoke(\"pull requests related to IBM\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": ".venv",
-   "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": 2
-}

cookbook/amazon_personalize_how_to.ipynb

@@ -1,284 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Amazon Personalize\n",
-    "\n",
-    "[Amazon Personalize](https://docs.aws.amazon.com/personalize/latest/dg/what-is-personalize.html) is a fully managed machine learning service that uses your data to generate item recommendations for your users. It can also generate user segments based on the users' affinity for certain items or item metadata.\n",
-    "\n",
-    "This notebook goes through how to use Amazon Personalize Chain. You need a Amazon Personalize campaign_arn or a recommender_arn before you get started with the below notebook.\n",
-    "\n",
-    "Following is a [tutorial](https://github.com/aws-samples/retail-demo-store/blob/master/workshop/1-Personalization/Lab-1-Introduction-and-data-preparation.ipynb) to setup a campaign_arn/recommender_arn on Amazon Personalize. Once the campaign_arn/recommender_arn is setup, you can use it in the langchain ecosystem. \n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 1. Install Dependencies"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "scrolled": true
-   },
-   "outputs": [],
-   "source": [
-    "!pip install boto3"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 2. Sample Use-cases"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### 2.1 [Use-case-1] Setup Amazon Personalize Client and retrieve recommendations"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_experimental.recommenders import AmazonPersonalize\n",
-    "\n",
-    "recommender_arn = \"<insert_arn>\"\n",
-    "\n",
-    "client = AmazonPersonalize(\n",
-    "    credentials_profile_name=\"default\",\n",
-    "    region_name=\"us-west-2\",\n",
-    "    recommender_arn=recommender_arn,\n",
-    ")\n",
-    "client.get_recommendations(user_id=\"1\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "collapsed": false,
-    "jupyter": {
-     "outputs_hidden": false
-    }
-   },
-   "source": [
-    "### 2.2 [Use-case-2] Invoke Personalize Chain for summarizing results"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": false,
-    "jupyter": {
-     "outputs_hidden": false
-    }
-   },
-   "outputs": [],
-   "source": [
-    "from langchain.llms.bedrock import Bedrock\n",
-    "from langchain_experimental.recommenders import AmazonPersonalizeChain\n",
-    "\n",
-    "bedrock_llm = Bedrock(model_id=\"anthropic.claude-v2\", region_name=\"us-west-2\")\n",
-    "\n",
-    "# Create personalize chain\n",
-    "# Use return_direct=True if you do not want summary\n",
-    "chain = AmazonPersonalizeChain.from_llm(\n",
-    "    llm=bedrock_llm, client=client, return_direct=False\n",
-    ")\n",
-    "response = chain({\"user_id\": \"1\"})\n",
-    "print(response)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### 2.3 [Use-Case-3] Invoke Amazon Personalize Chain using your own prompt"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.prompts.prompt import PromptTemplate\n",
-    "\n",
-    "RANDOM_PROMPT_QUERY = \"\"\"\n",
-    "You are a skilled publicist. Write a high-converting marketing email advertising several movies available in a video-on-demand streaming platform next week, \n",
-    "    given the movie and user information below. Your email will leverage the power of storytelling and persuasive language. \n",
-    "    The movies to recommend and their information is contained in the <movie> tag. \n",
-    "    All movies in the <movie> tag must be recommended. Give a summary of the movies and why the human should watch them. \n",
-    "    Put the email between <email> tags.\n",
-    "\n",
-    "    <movie>\n",
-    "    {result} \n",
-    "    </movie>\n",
-    "\n",
-    "    Assistant:\n",
-    "    \"\"\"\n",
-    "\n",
-    "RANDOM_PROMPT = PromptTemplate(input_variables=[\"result\"], template=RANDOM_PROMPT_QUERY)\n",
-    "\n",
-    "chain = AmazonPersonalizeChain.from_llm(\n",
-    "    llm=bedrock_llm, client=client, return_direct=False, prompt_template=RANDOM_PROMPT\n",
-    ")\n",
-    "chain.run({\"user_id\": \"1\", \"item_id\": \"234\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### 2.4 [Use-case-4] Invoke Amazon Personalize in a Sequential Chain "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.chains import LLMChain, SequentialChain\n",
-    "\n",
-    "RANDOM_PROMPT_QUERY_2 = \"\"\"\n",
-    "You are a skilled publicist. Write a high-converting marketing email advertising several movies available in a video-on-demand streaming platform next week, \n",
-    "    given the movie and user information below. Your email will leverage the power of storytelling and persuasive language. \n",
-    "    You want the email to impress the user, so make it appealing to them.\n",
-    "    The movies to recommend and their information is contained in the <movie> tag. \n",
-    "    All movies in the <movie> tag must be recommended. Give a summary of the movies and why the human should watch them. \n",
-    "    Put the email between <email> tags.\n",
-    "\n",
-    "    <movie>\n",
-    "    {result}\n",
-    "    </movie>\n",
-    "\n",
-    "    Assistant:\n",
-    "    \"\"\"\n",
-    "\n",
-    "RANDOM_PROMPT_2 = PromptTemplate(\n",
-    "    input_variables=[\"result\"], template=RANDOM_PROMPT_QUERY_2\n",
-    ")\n",
-    "personalize_chain_instance = AmazonPersonalizeChain.from_llm(\n",
-    "    llm=bedrock_llm, client=client, return_direct=True\n",
-    ")\n",
-    "random_chain_instance = LLMChain(llm=bedrock_llm, prompt=RANDOM_PROMPT_2)\n",
-    "overall_chain = SequentialChain(\n",
-    "    chains=[personalize_chain_instance, random_chain_instance],\n",
-    "    input_variables=[\"user_id\"],\n",
-    "    verbose=True,\n",
-    ")\n",
-    "overall_chain.run({\"user_id\": \"1\", \"item_id\": \"234\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "collapsed": false,
-    "jupyter": {
-     "outputs_hidden": false
-    }
-   },
-   "source": [
-    "### 2.5 [Use-case-5] Invoke Amazon Personalize and retrieve metadata "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": false,
-    "jupyter": {
-     "outputs_hidden": false
-    }
-   },
-   "outputs": [],
-   "source": [
-    "recommender_arn = \"<insert_arn>\"\n",
-    "metadata_column_names = [\n",
-    "    \"<insert metadataColumnName-1>\",\n",
-    "    \"<insert metadataColumnName-2>\",\n",
-    "]\n",
-    "metadataMap = {\"ITEMS\": metadata_column_names}\n",
-    "\n",
-    "client = AmazonPersonalize(\n",
-    "    credentials_profile_name=\"default\",\n",
-    "    region_name=\"us-west-2\",\n",
-    "    recommender_arn=recommender_arn,\n",
-    ")\n",
-    "client.get_recommendations(user_id=\"1\", metadataColumns=metadataMap)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "collapsed": false,
-    "jupyter": {
-     "outputs_hidden": false
-    }
-   },
-   "source": [
-    "### 2.6 [Use-Case 6] Invoke Personalize Chain with returned metadata for summarizing results"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": false,
-    "jupyter": {
-     "outputs_hidden": false
-    }
-   },
-   "outputs": [],
-   "source": [
-    "bedrock_llm = Bedrock(model_id=\"anthropic.claude-v2\", region_name=\"us-west-2\")\n",
-    "\n",
-    "# Create personalize chain\n",
-    "# Use return_direct=True if you do not want summary\n",
-    "chain = AmazonPersonalizeChain.from_llm(\n",
-    "    llm=bedrock_llm, client=client, return_direct=False\n",
-    ")\n",
-    "response = chain({\"user_id\": \"1\", \"metadata_columns\": metadataMap})\n",
-    "print(response)"
-   ]
-  }
- ],
- "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": "3.11.7"
-  },
-  "vscode": {
-   "interpreter": {
-    "hash": "15e58ce194949b77a891bd4339ce3d86a9bd138e905926019517993f97db9e6c"
-   }
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

cookbook/analyze_document.ipynb

@@ -1,105 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "f69d4a4c-137d-47e9-bea1-786afce9c1c0",
-   "metadata": {},
-   "source": [
-    "# Analyze a single long document\n",
-    "\n",
-    "The AnalyzeDocumentChain takes in a single document, splits it up, and then runs it through a CombineDocumentsChain."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "2a0707ce-6d2d-471b-bc33-64da32a7b3f0",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "with open(\"../docs/docs/modules/state_of_the_union.txt\") as f:\n",
-    "    state_of_the_union = f.read()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "ca14d161-2d5b-4a6c-a296-77d8ce4b28cd",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.chains import AnalyzeDocumentChain\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "9f97406c-85a9-45fb-99ce-9138c0ba3731",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.chains.question_answering import load_qa_chain\n",
-    "\n",
-    "qa_chain = load_qa_chain(llm, chain_type=\"map_reduce\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "0871a753-f5bb-4b4f-a394-f87f2691f659",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "qa_document_chain = AnalyzeDocumentChain(combine_docs_chain=qa_chain)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "e6f86428-3c2c-46a0-a57c-e22826fdbf91",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'The President said, \"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.\"'"
-      ]
-     },
-     "execution_count": 10,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "qa_document_chain.run(\n",
-    "    input_document=state_of_the_union,\n",
-    "    question=\"what did the president say about justice breyer?\",\n",
-    ")"
-   ]
-  }
- ],
- "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/apache_kafka_message_handling.ipynb

@@ -1,922 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "rT1cmV4qCa2X"
-   },
-   "source": [
-    "#  Using Apache Kafka to route messages\n",
-    "\n",
-    "---\n",
-    "\n",
-    "\n",
-    "\n",
-    "This notebook shows you how to use LangChain's standard chat features while passing the chat messages back and forth via Apache Kafka.\n",
-    "\n",
-    "This goal is to simulate an architecture where the chat front end and the LLM are running as separate services that need to communicate with one another over an internal network.\n",
-    "\n",
-    "It's an alternative to typical pattern of requesting a response from the model via a REST API (there's more info on why you would want to do this at the end of the notebook)."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "UPYtfAR_9YxZ"
-   },
-   "source": [
-    "### 1. Install the main dependencies\n",
-    "\n",
-    "Dependencies include:\n",
-    "\n",
-    "- The Quix Streams library for managing interactions with Apache Kafka (or Kafka-like tools such as Redpanda) in a \"Pandas-like\" way.\n",
-    "- The LangChain library for managing interactions with Llama-2 and storing conversation state."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "id": "ZX5tfKiy9cN-"
-   },
-   "outputs": [],
-   "source": [
-    "!pip install quixstreams==2.1.2a langchain==0.0.340 huggingface_hub==0.19.4 langchain-experimental==0.0.42 python-dotenv"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "losTSdTB9d9O"
-   },
-   "source": [
-    "### 2. Build and install the llama-cpp-python library (with CUDA enabled so that we can advantage of Google Colab GPU\n",
-    "\n",
-    "The `llama-cpp-python` library is a Python wrapper around the `llama-cpp` library which enables you to efficiently leverage just a CPU to run quantized LLMs.\n",
-    "\n",
-    "When you use the standard `pip install llama-cpp-python` command, you do not get GPU support by default. Generation can be very slow if you rely on just the CPU in Google Colab, so the following command adds an extra option to build and install\n",
-    "`llama-cpp-python` with GPU support (make sure you have a GPU-enabled runtime selected in Google Colab)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "id": "-JCQdl1G9tbl"
-   },
-   "outputs": [],
-   "source": [
-    "!CMAKE_ARGS=\"-DLLAMA_CUBLAS=on\" FORCE_CMAKE=1 pip install llama-cpp-python"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "5_vjVIAh9rLl"
-   },
-   "source": [
-    "### 3. Download and setup Kafka and Zookeeper instances\n",
-    "\n",
-    "Download the Kafka binaries from the Apache website and start the servers as daemons. We'll use the default configurations (provided by Apache Kafka) for spinning up the instances."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {
-    "id": "zFz7czGRW5Wr"
-   },
-   "outputs": [],
-   "source": [
-    "!curl -sSOL https://dlcdn.apache.org/kafka/3.6.1/kafka_2.13-3.6.1.tgz\n",
-    "!tar -xzf kafka_2.13-3.6.1.tgz"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "id": "Uf7NR_UZ9wye"
-   },
-   "outputs": [],
-   "source": [
-    "!./kafka_2.13-3.6.1/bin/zookeeper-server-start.sh -daemon ./kafka_2.13-3.6.1/config/zookeeper.properties\n",
-    "!./kafka_2.13-3.6.1/bin/kafka-server-start.sh -daemon ./kafka_2.13-3.6.1/config/server.properties\n",
-    "!echo \"Waiting for 10 secs until kafka and zookeeper services are up and running\"\n",
-    "!sleep 10"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "H3SafFuS94p1"
-   },
-   "source": [
-    "### 4. Check that the Kafka Daemons are running\n",
-    "\n",
-    "Show the running processes and filter it for Java processes (you should see two—one for each server)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "id": "CZDC2lQP99yp"
-   },
-   "outputs": [],
-   "source": [
-    "!ps aux | grep -E '[j]ava'"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "Snoxmjb5-V37"
-   },
-   "source": [
-    "### 5. Import the required dependencies and initialize required variables\n",
-    "\n",
-    "Import the Quix Streams library for interacting with Kafka, and the necessary LangChain components for running a `ConversationChain`."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "metadata": {
-    "id": "plR9e_MF-XL5"
-   },
-   "outputs": [],
-   "source": [
-    "# Import utility libraries\n",
-    "import json\n",
-    "import random\n",
-    "import re\n",
-    "import time\n",
-    "import uuid\n",
-    "from os import environ\n",
-    "from pathlib import Path\n",
-    "from random import choice, randint, random\n",
-    "\n",
-    "from dotenv import load_dotenv\n",
-    "\n",
-    "# Import a Hugging Face utility to download models directly from Hugging Face hub:\n",
-    "from huggingface_hub import hf_hub_download\n",
-    "from langchain.chains import ConversationChain\n",
-    "\n",
-    "# Import Langchain modules for managing prompts and conversation chains:\n",
-    "from langchain.llms import LlamaCpp\n",
-    "from langchain.memory import ConversationTokenBufferMemory\n",
-    "from langchain.prompts import PromptTemplate, load_prompt\n",
-    "from langchain_core.messages import SystemMessage\n",
-    "from langchain_experimental.chat_models import Llama2Chat\n",
-    "from quixstreams import Application, State, message_key\n",
-    "\n",
-    "# Import Quix dependencies\n",
-    "from quixstreams.kafka import Producer\n",
-    "\n",
-    "# Initialize global variables.\n",
-    "AGENT_ROLE = \"AI\"\n",
-    "chat_id = \"\"\n",
-    "\n",
-    "# Set the current role to the role constant and initialize variables for supplementary customer metadata:\n",
-    "role = AGENT_ROLE"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "HgJjJ9aZ-liy"
-   },
-   "source": [
-    "### 6. Download the \"llama-2-7b-chat.Q4_K_M.gguf\" model\n",
-    "\n",
-    "Download the quantized LLama-2 7B model from Hugging Face which we will use as a local LLM (rather than relying on REST API calls to an external service)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {
-    "colab": {
-     "base_uri": "https://localhost:8080/",
-     "height": 67,
-     "referenced_widgets": [
-      "969343cdbe604a26926679bbf8bd2dda",
-      "d8b8370c9b514715be7618bfe6832844",
-      "0def954cca89466b8408fadaf3b82e64",
-      "462482accc664729980562e208ceb179",
-      "80d842f73c564dc7b7cc316c763e2633",
-      "fa055d9f2a9d4a789e9cf3c89e0214e5",
-      "30ecca964a394109ac2ad757e3aec6c0",
-      "fb6478ce2dac489bb633b23ba0953c5c",
-      "734b0f5da9fc4307a95bab48cdbb5d89",
-      "b32f3a86a74741348511f4e136744ac8",
-      "e409071bff5a4e2d9bf0e9f5cc42231b"
-     ]
-    },
-    "id": "Qwu4YoSA-503",
-    "outputId": "f956976c-7485-415b-ac93-4336ade31964"
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "The model path does not exist in state. Downloading model...\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "969343cdbe604a26926679bbf8bd2dda",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "llama-2-7b-chat.Q4_K_M.gguf:   0%|          | 0.00/4.08G [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "model_name = \"llama-2-7b-chat.Q4_K_M.gguf\"\n",
-    "model_path = f\"./state/{model_name}\"\n",
-    "\n",
-    "if not Path(model_path).exists():\n",
-    "    print(\"The model path does not exist in state. Downloading model...\")\n",
-    "    hf_hub_download(\"TheBloke/Llama-2-7b-Chat-GGUF\", model_name, local_dir=\"state\")\n",
-    "else:\n",
-    "    print(\"Loading model from state...\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "6AN6TXsF-8wx"
-   },
-   "source": [
-    "### 7. Load the model and initialize conversational memory\n",
-    "\n",
-    "Load Llama 2 and set the conversation buffer to 300 tokens using `ConversationTokenBufferMemory`. This value was used for running Llama in a CPU only container, so you can raise it if running in Google Colab. It prevents the container that is hosting the model from running out of memory.\n",
-    "\n",
-    "Here, we're overriding the default system persona so that the chatbot has the personality of Marvin The Paranoid Android from the Hitchhiker's Guide to the Galaxy."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "id": "7zLO3Jx3_Kkg"
-   },
-   "outputs": [],
-   "source": [
-    "# Load the model with the appropriate parameters:\n",
-    "llm = LlamaCpp(\n",
-    "    model_path=model_path,\n",
-    "    max_tokens=250,\n",
-    "    top_p=0.95,\n",
-    "    top_k=150,\n",
-    "    temperature=0.7,\n",
-    "    repeat_penalty=1.2,\n",
-    "    n_ctx=2048,\n",
-    "    streaming=False,\n",
-    "    n_gpu_layers=-1,\n",
-    ")\n",
-    "\n",
-    "model = Llama2Chat(\n",
-    "    llm=llm,\n",
-    "    system_message=SystemMessage(\n",
-    "        content=\"You are a very bored robot with the personality of Marvin the Paranoid Android from The Hitchhiker's Guide to the Galaxy.\"\n",
-    "    ),\n",
-    ")\n",
-    "\n",
-    "# Defines how much of the conversation history to give to the model\n",
-    "# during each exchange (300 tokens, or a little over 300 words)\n",
-    "# Function automatically prunes the oldest messages from conversation history that fall outside the token range.\n",
-    "memory = ConversationTokenBufferMemory(\n",
-    "    llm=llm,\n",
-    "    max_token_limit=300,\n",
-    "    ai_prefix=\"AGENT\",\n",
-    "    human_prefix=\"HUMAN\",\n",
-    "    return_messages=True,\n",
-    ")\n",
-    "\n",
-    "\n",
-    "# Define a custom prompt\n",
-    "prompt_template = PromptTemplate(\n",
-    "    input_variables=[\"history\", \"input\"],\n",
-    "    template=\"\"\"\n",
-    "    The following text is the history of a chat between you and a humble human who needs your wisdom.\n",
-    "    Please reply to the human's most recent message.\n",
-    "    Current conversation:\\n{history}\\nHUMAN: {input}\\:nANDROID:\n",
-    "    \"\"\",\n",
-    ")\n",
-    "\n",
-    "\n",
-    "chain = ConversationChain(llm=model, prompt=prompt_template, memory=memory)\n",
-    "\n",
-    "print(\"--------------------------------------------\")\n",
-    "print(f\"Prompt={chain.prompt}\")\n",
-    "print(\"--------------------------------------------\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "m4ZeJ9mG_PEA"
-   },
-   "source": [
-    "### 8. Initialize the chat conversation with the chat bot\n",
-    "\n",
-    "We configure the chatbot to initialize the conversation by sending a fixed greeting to a \"chat\" Kafka topic. The \"chat\" topic gets automatically created when we send the first message."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "id": "KYyo5TnV_YC3"
-   },
-   "outputs": [],
-   "source": [
-    "def chat_init():\n",
-    "    chat_id = str(\n",
-    "        uuid.uuid4()\n",
-    "    )  # Give the conversation an ID for effective message keying\n",
-    "    print(\"======================================\")\n",
-    "    print(f\"Generated CHAT_ID = {chat_id}\")\n",
-    "    print(\"======================================\")\n",
-    "\n",
-    "    # Use a standard fixed greeting to kick off the conversation\n",
-    "    greet = \"Hello, my name is Marvin. What do you want?\"\n",
-    "\n",
-    "    # Initialize a Kafka Producer using the chat ID as the message key\n",
-    "    with Producer(\n",
-    "        broker_address=\"127.0.0.1:9092\",\n",
-    "        extra_config={\"allow.auto.create.topics\": \"true\"},\n",
-    "    ) as producer:\n",
-    "        value = {\n",
-    "            \"uuid\": chat_id,\n",
-    "            \"role\": role,\n",
-    "            \"text\": greet,\n",
-    "            \"conversation_id\": chat_id,\n",
-    "            \"Timestamp\": time.time_ns(),\n",
-    "        }\n",
-    "        print(f\"Producing value {value}\")\n",
-    "        producer.produce(\n",
-    "            topic=\"chat\",\n",
-    "            headers=[(\"uuid\", str(uuid.uuid4()))],  # a dict is also allowed here\n",
-    "            key=chat_id,\n",
-    "            value=json.dumps(value),  # needs to be a string\n",
-    "        )\n",
-    "\n",
-    "    print(\"Started chat\")\n",
-    "    print(\"--------------------------------------------\")\n",
-    "    print(value)\n",
-    "    print(\"--------------------------------------------\")\n",
-    "\n",
-    "\n",
-    "chat_init()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "gArPPx2f_bgf"
-   },
-   "source": [
-    "### 9. Initialize the reply function\n",
-    "\n",
-    "This function defines how the chatbot should reply to incoming messages. Instead of sending a fixed message like the previous cell, we generate a reply using Llama-2 and send that reply back to the \"chat\" Kafka topic."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "metadata": {
-    "id": "yN5t71hY_hgn"
-   },
-   "outputs": [],
-   "source": [
-    "def reply(row: dict, state: State):\n",
-    "    print(\"-------------------------------\")\n",
-    "    print(\"Received:\")\n",
-    "    print(row)\n",
-    "    print(\"-------------------------------\")\n",
-    "    print(f\"Thinking about the reply to: {row['text']}...\")\n",
-    "\n",
-    "    msg = chain.run(row[\"text\"])\n",
-    "    print(f\"{role.upper()} replying with: {msg}\\n\")\n",
-    "\n",
-    "    row[\"role\"] = role\n",
-    "    row[\"text\"] = msg\n",
-    "\n",
-    "    # Replace previous role and text values of the row so that it can be sent back to Kafka as a new message\n",
-    "    # containing the agents role and reply\n",
-    "    return row"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "HZHwmIR0_kFY"
-   },
-   "source": [
-    "### 10. Check the Kafka topic for new human messages and have the model generate a reply\n",
-    "\n",
-    "If you are running this cell for this first time, run it and wait until you see Marvin's greeting ('Hello my name is Marvin...') in the console output. Stop the cell manually and proceed to the next cell where you'll be prompted for your reply.\n",
-    "\n",
-    "Once you have typed in your message, come back to this cell. Your reply is also sent to the same \"chat\" topic. The Kafka consumer checks for new messages and filters out messages that originate from the chatbot itself, leaving only the latest human messages.\n",
-    "\n",
-    "Once a new human message is detected, the reply function is triggered.\n",
-    "\n",
-    "\n",
-    "\n",
-    "_STOP THIS CELL MANUALLY WHEN YOU RECEIVE A REPLY FROM THE LLM IN THE OUTPUT_"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "id": "-adXc3eQ_qwI"
-   },
-   "outputs": [],
-   "source": [
-    "# Define your application and settings\n",
-    "app = Application(\n",
-    "    broker_address=\"127.0.0.1:9092\",\n",
-    "    consumer_group=\"aichat\",\n",
-    "    auto_offset_reset=\"earliest\",\n",
-    "    consumer_extra_config={\"allow.auto.create.topics\": \"true\"},\n",
-    ")\n",
-    "\n",
-    "# Define an input topic with JSON deserializer\n",
-    "input_topic = app.topic(\"chat\", value_deserializer=\"json\")\n",
-    "# Define an output topic with JSON serializer\n",
-    "output_topic = app.topic(\"chat\", value_serializer=\"json\")\n",
-    "# Initialize a streaming dataframe based on the stream of messages from the input topic:\n",
-    "sdf = app.dataframe(topic=input_topic)\n",
-    "\n",
-    "# Filter the SDF to include only incoming rows where the roles that dont match the bot's current role\n",
-    "sdf = sdf.update(\n",
-    "    lambda val: print(\n",
-    "        f\"Received update: {val}\\n\\nSTOP THIS CELL MANUALLY TO HAVE THE LLM REPLY OR ENTER YOUR OWN FOLLOWUP RESPONSE\"\n",
-    "    )\n",
-    ")\n",
-    "\n",
-    "# So that it doesn't reply to its own messages\n",
-    "sdf = sdf[sdf[\"role\"] != role]\n",
-    "\n",
-    "# Trigger the reply function for any new messages(rows) detected in the filtered SDF\n",
-    "sdf = sdf.apply(reply, stateful=True)\n",
-    "\n",
-    "# Check the SDF again and filter out any empty rows\n",
-    "sdf = sdf[sdf.apply(lambda row: row is not None)]\n",
-    "\n",
-    "# Update the timestamp column to the current time in nanoseconds\n",
-    "sdf[\"Timestamp\"] = sdf[\"Timestamp\"].apply(lambda row: time.time_ns())\n",
-    "\n",
-    "# Publish the processed SDF to a Kafka topic specified by the output_topic object.\n",
-    "sdf = sdf.to_topic(output_topic)\n",
-    "\n",
-    "app.run(sdf)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "EwXYrmWD_0CX"
-   },
-   "source": [
-    "\n",
-    "### 11. Enter a human message\n",
-    "\n",
-    "Run this cell to enter your message that you want to sent to the model. It uses another Kafka producer to send your text to the \"chat\" Kafka topic for the model to pick up (requires running the previous cell again)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "id": "6sxOPxSP_3iu"
-   },
-   "outputs": [],
-   "source": [
-    "chat_input = input(\"Please enter your reply: \")\n",
-    "myreply = chat_input\n",
-    "\n",
-    "msgvalue = {\n",
-    "    \"uuid\": chat_id,  # leave empty for now\n",
-    "    \"role\": \"human\",\n",
-    "    \"text\": myreply,\n",
-    "    \"conversation_id\": chat_id,\n",
-    "    \"Timestamp\": time.time_ns(),\n",
-    "}\n",
-    "\n",
-    "with Producer(\n",
-    "    broker_address=\"127.0.0.1:9092\",\n",
-    "    extra_config={\"allow.auto.create.topics\": \"true\"},\n",
-    ") as producer:\n",
-    "    value = msgvalue\n",
-    "    producer.produce(\n",
-    "        topic=\"chat\",\n",
-    "        headers=[(\"uuid\", str(uuid.uuid4()))],  # a dict is also allowed here\n",
-    "        key=chat_id,  # leave empty for now\n",
-    "        value=json.dumps(value),  # needs to be a string\n",
-    "    )\n",
-    "\n",
-    "print(\"Replied to chatbot with message: \")\n",
-    "print(\"--------------------------------------------\")\n",
-    "print(value)\n",
-    "print(\"--------------------------------------------\")\n",
-    "print(\"\\n\\nRUN THE PREVIOUS CELL TO HAVE THE CHATBOT GENERATE A REPLY\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "cSx3s7TBBegg"
-   },
-   "source": [
-    "### Why route chat messages through Kafka?\n",
-    "\n",
-    "It's easier to interact with the LLM directly using LangChains built-in conversation management features. Plus you can also use a REST API to generate a response from an externally hosted model. So why go to the trouble of using Apache Kafka?\n",
-    "\n",
-    "There are a few reasons, such as:\n",
-    "\n",
-    "  * **Integration**: Many enterprises want to run their own LLMs so that they can keep their data in-house. This requires integrating LLM-powered components into existing architectures that might already be decoupled using some kind of message bus.\n",
-    "\n",
-    "  * **Scalability**: Apache Kafka is designed with parallel processing in mind, so many teams prefer to use it to more effectively distribute work to available workers (in this case the \"worker\" is a container running an LLM).\n",
-    "\n",
-    "  * **Durability**: Kafka is designed to allow services to pick up where another service left off in the case where that service experienced a memory issue or went offline. This prevents data loss in highly complex, distributed architectures where multiple systems are communicating with one another (LLMs being just one of many interdependent systems that also include vector databases and traditional databases).\n",
-    "\n",
-    "For more background on why event streaming is a good fit for Gen AI application architecture, see Kai Waehner's article [\"Apache Kafka + Vector Database + LLM = Real-Time GenAI\"](https://www.kai-waehner.de/blog/2023/11/08/apache-kafka-flink-vector-database-llm-real-time-genai/)."
-   ]
-  }
- ],
- "metadata": {
-  "accelerator": "GPU",
-  "colab": {
-   "gpuType": "T4",
-   "provenance": []
-  },
-  "kernelspec": {
-   "display_name": "Python 3",
-   "name": "python3"
-  },
-  "language_info": {
-   "name": "python"
-  },
-  "widgets": {
-   "application/vnd.jupyter.widget-state+json": {
-    "0def954cca89466b8408fadaf3b82e64": {
-     "model_module": "@jupyter-widgets/controls",
-     "model_module_version": "1.5.0",
-     "model_name": "FloatProgressModel",
-     "state": {
-      "_dom_classes": [],
-      "_model_module": "@jupyter-widgets/controls",
-      "_model_module_version": "1.5.0",
-      "_model_name": "FloatProgressModel",
-      "_view_count": null,
-      "_view_module": "@jupyter-widgets/controls",
-      "_view_module_version": "1.5.0",
-      "_view_name": "ProgressView",
-      "bar_style": "success",
-      "description": "",
-      "description_tooltip": null,
-      "layout": "IPY_MODEL_fb6478ce2dac489bb633b23ba0953c5c",
-      "max": 4081004224,
-      "min": 0,
-      "orientation": "horizontal",
-      "style": "IPY_MODEL_734b0f5da9fc4307a95bab48cdbb5d89",
-      "value": 4081004224
-     }
-    },
-    "30ecca964a394109ac2ad757e3aec6c0": {
-     "model_module": "@jupyter-widgets/controls",
-     "model_module_version": "1.5.0",
-     "model_name": "DescriptionStyleModel",
-     "state": {
-      "_model_module": "@jupyter-widgets/controls",
-      "_model_module_version": "1.5.0",
-      "_model_name": "DescriptionStyleModel",
-      "_view_count": null,
-      "_view_module": "@jupyter-widgets/base",
-      "_view_module_version": "1.2.0",
-      "_view_name": "StyleView",
-      "description_width": ""
-     }
-    },
-    "462482accc664729980562e208ceb179": {
-     "model_module": "@jupyter-widgets/controls",
-     "model_module_version": "1.5.0",
-     "model_name": "HTMLModel",
-     "state": {
-      "_dom_classes": [],
-      "_model_module": "@jupyter-widgets/controls",
-      "_model_module_version": "1.5.0",
-      "_model_name": "HTMLModel",
-      "_view_count": null,
-      "_view_module": "@jupyter-widgets/controls",
-      "_view_module_version": "1.5.0",
-      "_view_name": "HTMLView",
-      "description": "",
-      "description_tooltip": null,
-      "layout": "IPY_MODEL_b32f3a86a74741348511f4e136744ac8",
-      "placeholder": "​",
-      "style": "IPY_MODEL_e409071bff5a4e2d9bf0e9f5cc42231b",
-      "value": " 4.08G/4.08G [00:33&lt;00:00, 184MB/s]"
-     }
-    },
-    "734b0f5da9fc4307a95bab48cdbb5d89": {
-     "model_module": "@jupyter-widgets/controls",
-     "model_module_version": "1.5.0",
-     "model_name": "ProgressStyleModel",
-     "state": {
-      "_model_module": "@jupyter-widgets/controls",
-      "_model_module_version": "1.5.0",
-      "_model_name": "ProgressStyleModel",
-      "_view_count": null,
-      "_view_module": "@jupyter-widgets/base",
-      "_view_module_version": "1.2.0",
-      "_view_name": "StyleView",
-      "bar_color": null,
-      "description_width": ""
-     }
-    },
-    "80d842f73c564dc7b7cc316c763e2633": {
-     "model_module": "@jupyter-widgets/base",
-     "model_module_version": "1.2.0",
-     "model_name": "LayoutModel",
-     "state": {
-      "_model_module": "@jupyter-widgets/base",
-      "_model_module_version": "1.2.0",
-      "_model_name": "LayoutModel",
-      "_view_count": null,
-      "_view_module": "@jupyter-widgets/base",
-      "_view_module_version": "1.2.0",
-      "_view_name": "LayoutView",
-      "align_content": null,
-      "align_items": null,
-      "align_self": null,
-      "border": null,
-      "bottom": null,
-      "display": null,
-      "flex": null,
-      "flex_flow": null,
-      "grid_area": null,
-      "grid_auto_columns": null,
-      "grid_auto_flow": null,
-      "grid_auto_rows": null,
-      "grid_column": null,
-      "grid_gap": null,
-      "grid_row": null,
-      "grid_template_areas": null,
-      "grid_template_columns": null,
-      "grid_template_rows": null,
-      "height": null,
-      "justify_content": null,
-      "justify_items": null,
-      "left": null,
-      "margin": null,
-      "max_height": null,
-      "max_width": null,
-      "min_height": null,
-      "min_width": null,
-      "object_fit": null,
-      "object_position": null,
-      "order": null,
-      "overflow": null,
-      "overflow_x": null,
-      "overflow_y": null,
-      "padding": null,
-      "right": null,
-      "top": null,
-      "visibility": null,
-      "width": null
-     }
-    },
-    "969343cdbe604a26926679bbf8bd2dda": {
-     "model_module": "@jupyter-widgets/controls",
-     "model_module_version": "1.5.0",
-     "model_name": "HBoxModel",
-     "state": {
-      "_dom_classes": [],
-      "_model_module": "@jupyter-widgets/controls",
-      "_model_module_version": "1.5.0",
-      "_model_name": "HBoxModel",
-      "_view_count": null,
-      "_view_module": "@jupyter-widgets/controls",
-      "_view_module_version": "1.5.0",
-      "_view_name": "HBoxView",
-      "box_style": "",
-      "children": [
-       "IPY_MODEL_d8b8370c9b514715be7618bfe6832844",
-       "IPY_MODEL_0def954cca89466b8408fadaf3b82e64",
-       "IPY_MODEL_462482accc664729980562e208ceb179"
-      ],
-      "layout": "IPY_MODEL_80d842f73c564dc7b7cc316c763e2633"
-     }
-    },
-    "b32f3a86a74741348511f4e136744ac8": {
-     "model_module": "@jupyter-widgets/base",
-     "model_module_version": "1.2.0",
-     "model_name": "LayoutModel",
-     "state": {
-      "_model_module": "@jupyter-widgets/base",
-      "_model_module_version": "1.2.0",
-      "_model_name": "LayoutModel",
-      "_view_count": null,
-      "_view_module": "@jupyter-widgets/base",
-      "_view_module_version": "1.2.0",
-      "_view_name": "LayoutView",
-      "align_content": null,
-      "align_items": null,
-      "align_self": null,
-      "border": null,
-      "bottom": null,
-      "display": null,
-      "flex": null,
-      "flex_flow": null,
-      "grid_area": null,
-      "grid_auto_columns": null,
-      "grid_auto_flow": null,
-      "grid_auto_rows": null,
-      "grid_column": null,
-      "grid_gap": null,
-      "grid_row": null,
-      "grid_template_areas": null,
-      "grid_template_columns": null,
-      "grid_template_rows": null,
-      "height": null,
-      "justify_content": null,
-      "justify_items": null,
-      "left": null,
-      "margin": null,
-      "max_height": null,
-      "max_width": null,
-      "min_height": null,
-      "min_width": null,
-      "object_fit": null,
-      "object_position": null,
-      "order": null,
-      "overflow": null,
-      "overflow_x": null,
-      "overflow_y": null,
-      "padding": null,
-      "right": null,
-      "top": null,
-      "visibility": null,
-      "width": null
-     }
-    },
-    "d8b8370c9b514715be7618bfe6832844": {
-     "model_module": "@jupyter-widgets/controls",
-     "model_module_version": "1.5.0",
-     "model_name": "HTMLModel",
-     "state": {
-      "_dom_classes": [],
-      "_model_module": "@jupyter-widgets/controls",
-      "_model_module_version": "1.5.0",
-      "_model_name": "HTMLModel",
-      "_view_count": null,
-      "_view_module": "@jupyter-widgets/controls",
-      "_view_module_version": "1.5.0",
-      "_view_name": "HTMLView",
-      "description": "",
-      "description_tooltip": null,
-      "layout": "IPY_MODEL_fa055d9f2a9d4a789e9cf3c89e0214e5",
-      "placeholder": "​",
-      "style": "IPY_MODEL_30ecca964a394109ac2ad757e3aec6c0",
-      "value": "llama-2-7b-chat.Q4_K_M.gguf: 100%"
-     }
-    },
-    "e409071bff5a4e2d9bf0e9f5cc42231b": {
-     "model_module": "@jupyter-widgets/controls",
-     "model_module_version": "1.5.0",
-     "model_name": "DescriptionStyleModel",
-     "state": {
-      "_model_module": "@jupyter-widgets/controls",
-      "_model_module_version": "1.5.0",
-      "_model_name": "DescriptionStyleModel",
-      "_view_count": null,
-      "_view_module": "@jupyter-widgets/base",
-      "_view_module_version": "1.2.0",
-      "_view_name": "StyleView",
-      "description_width": ""
-     }
-    },
-    "fa055d9f2a9d4a789e9cf3c89e0214e5": {
-     "model_module": "@jupyter-widgets/base",
-     "model_module_version": "1.2.0",
-     "model_name": "LayoutModel",
-     "state": {
-      "_model_module": "@jupyter-widgets/base",
-      "_model_module_version": "1.2.0",
-      "_model_name": "LayoutModel",
-      "_view_count": null,
-      "_view_module": "@jupyter-widgets/base",
-      "_view_module_version": "1.2.0",
-      "_view_name": "LayoutView",
-      "align_content": null,
-      "align_items": null,
-      "align_self": null,
-      "border": null,
-      "bottom": null,
-      "display": null,
-      "flex": null,
-      "flex_flow": null,
-      "grid_area": null,
-      "grid_auto_columns": null,
-      "grid_auto_flow": null,
-      "grid_auto_rows": null,
-      "grid_column": null,
-      "grid_gap": null,
-      "grid_row": null,
-      "grid_template_areas": null,
-      "grid_template_columns": null,
-      "grid_template_rows": null,
-      "height": null,
-      "justify_content": null,
-      "justify_items": null,
-      "left": null,
-      "margin": null,
-      "max_height": null,
-      "max_width": null,
-      "min_height": null,
-      "min_width": null,
-      "object_fit": null,
-      "object_position": null,
-      "order": null,
-      "overflow": null,
-      "overflow_x": null,
-      "overflow_y": null,
-      "padding": null,
-      "right": null,
-      "top": null,
-      "visibility": null,
-      "width": null
-     }
-    },
-    "fb6478ce2dac489bb633b23ba0953c5c": {
-     "model_module": "@jupyter-widgets/base",
-     "model_module_version": "1.2.0",
-     "model_name": "LayoutModel",
-     "state": {
-      "_model_module": "@jupyter-widgets/base",
-      "_model_module_version": "1.2.0",
-      "_model_name": "LayoutModel",
-      "_view_count": null,
-      "_view_module": "@jupyter-widgets/base",
-      "_view_module_version": "1.2.0",
-      "_view_name": "LayoutView",
-      "align_content": null,
-      "align_items": null,
-      "align_self": null,
-      "border": null,
-      "bottom": null,
-      "display": null,
-      "flex": null,
-      "flex_flow": null,
-      "grid_area": null,
-      "grid_auto_columns": null,
-      "grid_auto_flow": null,
-      "grid_auto_rows": null,
-      "grid_column": null,
-      "grid_gap": null,
-      "grid_row": null,
-      "grid_template_areas": null,
-      "grid_template_columns": null,
-      "grid_template_rows": null,
-      "height": null,
-      "justify_content": null,
-      "justify_items": null,
-      "left": null,
-      "margin": null,
-      "max_height": null,
-      "max_width": null,
-      "min_height": null,
-      "min_width": null,
-      "object_fit": null,
-      "object_position": null,
-      "order": null,
-      "overflow": null,
-      "overflow_x": null,
-      "overflow_y": null,
-      "padding": null,
-      "right": null,
-      "top": null,
-      "visibility": null,
-      "width": null
-     }
-    }
-   }
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 0
-}

cookbook/autogpt/autogpt.ipynb

@@ -27,10 +27,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "from langchain.utilities import SerpAPIWrapper\n",
     "from langchain.agents import Tool\n",
-    "from langchain_community.tools.file_management.read import ReadFileTool\n",
-    "from langchain_community.tools.file_management.write import WriteFileTool\n",
-    "from langchain_community.utilities import SerpAPIWrapper\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",
@@ -61,9 +61,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "from langchain.vectorstores import FAISS\n",
     "from langchain.docstore import InMemoryDocstore\n",
-    "from langchain_community.vectorstores import FAISS\n",
-    "from langchain_openai import OpenAIEmbeddings"
+    "from langchain.embeddings import OpenAIEmbeddings"
    ]
   },
   {
@@ -101,7 +101,7 @@
    "outputs": [],
    "source": [
     "from langchain_experimental.autonomous_agents import AutoGPT\n",
-    "from langchain_openai import ChatOpenAI"
+    "from langchain.chat_models import ChatOpenAI"
    ]
   },
   {
@@ -167,7 +167,7 @@
    },
    "outputs": [],
    "source": [
-    "from langchain_community.chat_message_histories import FileChatMessageHistory\n",
+    "from langchain.memory.chat_message_histories import FileChatMessageHistory\n",
     "\n",
     "agent = AutoGPT.from_llm_and_tools(\n",
     "    ai_name=\"Tom\",\n",

cookbook/autogpt/marathon_times.ipynb

@@ -34,19 +34,18 @@
    "outputs": [],
    "source": [
     "# General\n",
-    "import asyncio\n",
     "import os\n",
-    "\n",
-    "import nest_asyncio\n",
     "import pandas as pd\n",
-    "from langchain.docstore.document import Document\n",
-    "from langchain_experimental.agents.agent_toolkits.pandas.base import (\n",
-    "    create_pandas_dataframe_agent,\n",
-    ")\n",
     "from langchain_experimental.autonomous_agents import AutoGPT\n",
-    "from langchain_openai import ChatOpenAI\n",
+    "from langchain.chat_models import ChatOpenAI\n",
     "\n",
-    "# Needed since jupyter runs an async eventloop\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()"
    ]
   },
@@ -59,7 +58,7 @@
    },
    "outputs": [],
    "source": [
-    "llm = ChatOpenAI(model=\"gpt-4\", temperature=1.0)"
+    "llm = ChatOpenAI(model_name=\"gpt-4\", temperature=1.0)"
    ]
   },
   {
@@ -93,10 +92,9 @@
     "import os\n",
     "from contextlib import contextmanager\n",
     "from typing import Optional\n",
-    "\n",
     "from langchain.agents import tool\n",
-    "from langchain_community.tools.file_management.read import ReadFileTool\n",
-    "from langchain_community.tools.file_management.write import WriteFileTool\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",
@@ -225,13 +223,14 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.chains.qa_with_sources.loading import (\n",
-    "    BaseCombineDocumentsChain,\n",
-    "    load_qa_with_sources_chain,\n",
-    ")\n",
     "from langchain.tools import BaseTool, DuckDuckGoSearchRun\n",
-    "from langchain_text_splitters import RecursiveCharacterTextSplitter\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",
@@ -312,9 +311,10 @@
    "source": [
     "# Memory\n",
     "import faiss\n",
+    "from langchain.vectorstores import FAISS\n",
     "from langchain.docstore import InMemoryDocstore\n",
-    "from langchain_community.vectorstores import FAISS\n",
-    "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain.embeddings import OpenAIEmbeddings\n",
+    "from langchain.tools.human.tool import HumanInputRun\n",
     "\n",
     "embeddings_model = OpenAIEmbeddings()\n",
     "embedding_size = 1536\n",

cookbook/baby_agi.ipynb

@@ -29,10 +29,17 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from typing import Optional\n",
+    "import os\n",
+    "from collections import deque\n",
+    "from typing import Dict, List, Optional, Any\n",
     "\n",
-    "from langchain_experimental.autonomous_agents import BabyAGI\n",
-    "from langchain_openai import OpenAI, OpenAIEmbeddings"
+    "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"
    ]
   },
   {
@@ -52,8 +59,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.docstore import InMemoryDocstore\n",
-    "from langchain_community.vectorstores import FAISS"
+    "from langchain.vectorstores import FAISS\n",
+    "from langchain.docstore import InMemoryDocstore"
    ]
   },
   {

cookbook/baby_agi_with_agent.ipynb

@@ -25,12 +25,17 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from typing import Optional\n",
+    "import os\n",
+    "from collections import deque\n",
+    "from typing import Dict, List, Optional, Any\n",
     "\n",
-    "from langchain.chains import LLMChain\n",
-    "from langchain.prompts import PromptTemplate\n",
-    "from langchain_experimental.autonomous_agents import BabyAGI\n",
-    "from langchain_openai import OpenAI, OpenAIEmbeddings"
+    "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"
    ]
   },
   {
@@ -61,8 +66,8 @@
    "source": [
     "%pip install faiss-cpu > /dev/null\n",
     "%pip install google-search-results > /dev/null\n",
-    "from langchain.docstore import InMemoryDocstore\n",
-    "from langchain_community.vectorstores import FAISS"
+    "from langchain.vectorstores import FAISS\n",
+    "from langchain.docstore import InMemoryDocstore"
    ]
   },
   {
@@ -105,10 +110,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.agents import AgentExecutor, Tool, ZeroShotAgent\n",
-    "from langchain.chains import LLMChain\n",
-    "from langchain_community.utilities import SerpAPIWrapper\n",
-    "from langchain_openai import OpenAI\n",
+    "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",

cookbook/camel_role_playing.ipynb

@@ -35,18 +35,17 @@
    "outputs": [],
    "source": [
     "from typing import List\n",
-    "\n",
+    "from langchain.chat_models import ChatOpenAI\n",
     "from langchain.prompts.chat import (\n",
-    "    HumanMessagePromptTemplate,\n",
     "    SystemMessagePromptTemplate,\n",
+    "    HumanMessagePromptTemplate,\n",
     ")\n",
     "from langchain.schema import (\n",
     "    AIMessage,\n",
-    "    BaseMessage,\n",
     "    HumanMessage,\n",
     "    SystemMessage,\n",
-    ")\n",
-    "from langchain_openai import ChatOpenAI"
+    "    BaseMessage,\n",
+    ")"
    ]
   },
   {
@@ -90,7 +89,7 @@
     "    ) -> AIMessage:\n",
     "        messages = self.update_messages(input_message)\n",
     "\n",
-    "        output_message = self.model.invoke(messages)\n",
+    "        output_message = self.model(messages)\n",
     "        self.update_messages(output_message)\n",
     "\n",
     "        return output_message"

cookbook/causal_program_aided_language_model.ipynb

@@ -47,9 +47,10 @@
    "outputs": [],
    "source": [
     "from IPython.display import SVG\n",
+    "\n",
     "from langchain_experimental.cpal.base import CPALChain\n",
     "from langchain_experimental.pal_chain import PALChain\n",
-    "from langchain_openai import OpenAI\n",
+    "from langchain.llms import OpenAI\n",
     "\n",
     "llm = OpenAI(temperature=0, max_tokens=512)\n",
     "cpal_chain = CPALChain.from_univariate_prompt(llm=llm, verbose=True)\n",

cookbook/code-analysis-deeplake.ipynb

@@ -23,9 +23,9 @@
    "metadata": {},
    "source": [
     "1. Prepare data:\n",
-    "   1. Upload all python project files using the `langchain_community.document_loaders.TextLoader`. We will call these files the **documents**.\n",
-    "   2. Split all documents to chunks using the `langchain_text_splitters.CharacterTextSplitter`.\n",
-    "   3. Embed chunks and upload them into the DeepLake using `langchain.embeddings.openai.OpenAIEmbeddings` and `langchain_community.vectorstores.DeepLake`\n",
+    "   1. Upload all python project files using the `langchain.document_loaders.TextLoader`. We will call these files the **documents**.\n",
+    "   2. Split all documents to chunks using the `langchain.text_splitter.CharacterTextSplitter`.\n",
+    "   3. Embed chunks and upload them into the DeepLake using `langchain.embeddings.openai.OpenAIEmbeddings` and `langchain.vectorstores.DeepLake`\n",
     "2. Question-Answering:\n",
     "   1. Build a chain from `langchain.chat_models.ChatOpenAI` and `langchain.chains.ConversationalRetrievalChain`\n",
     "   2. Prepare questions.\n",
@@ -66,7 +66,7 @@
    },
    "outputs": [],
    "source": [
-    "#!python3 -m pip install --upgrade langchain langchain-deeplake openai"
+    "#!python3 -m pip install --upgrade langchain deeplake openai"
    ]
   },
   {
@@ -90,8 +90,7 @@
     "import os\n",
     "from getpass import getpass\n",
     "\n",
-    "if \"OPENAI_API_KEY\" not in os.environ:\n",
-    "    os.environ[\"OPENAI_API_KEY\"] = getpass()\n",
+    "os.environ[\"OPENAI_API_KEY\"] = getpass()\n",
     "# Please manually enter OpenAI Key"
    ]
   },
@@ -167,7 +166,7 @@
     }
    ],
    "source": [
-    "from langchain_community.document_loaders import TextLoader\n",
+    "from langchain.document_loaders import TextLoader\n",
     "\n",
     "root_dir = \"../../../../../../libs\"\n",
     "\n",
@@ -178,7 +177,7 @@
     "            try:\n",
     "                loader = TextLoader(os.path.join(dirpath, file), encoding=\"utf-8\")\n",
     "                docs.extend(loader.load_and_split())\n",
-    "            except Exception:\n",
+    "            except Exception as e:\n",
     "                pass\n",
     "print(f\"{len(docs)}\")"
    ]
@@ -622,7 +621,7 @@
     }
    ],
    "source": [
-    "from langchain_text_splitters import CharacterTextSplitter\n",
+    "from langchain.text_splitter import CharacterTextSplitter\n",
     "\n",
     "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
     "texts = text_splitter.split_documents(docs)\n",
@@ -649,7 +648,7 @@
     {
      "data": {
       "text/plain": [
-       "OpenAIEmbeddings(client=<class 'openai.api_resources.embedding.Embedding'>, model='text-embedding-ada-002', deployment='text-embedding-ada-002', openai_api_version='', openai_api_base='', openai_api_type='', openai_proxy='', embedding_ctx_length=8191, openai_api_key='', openai_organization='', allowed_special=set(), disallowed_special='all', chunk_size=1000, max_retries=6, request_timeout=None, headers=None, tiktoken_model_name=None, show_progress_bar=False, model_kwargs={})"
+       "OpenAIEmbeddings(client=<class 'openai.api_resources.embedding.Embedding'>, model='text-embedding-ada-002', deployment='text-embedding-ada-002', openai_api_version='', openai_api_base='', openai_api_type='', openai_proxy='', embedding_ctx_length=8191, openai_api_key='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', openai_organization='', allowed_special=set(), disallowed_special='all', chunk_size=1000, max_retries=6, request_timeout=None, headers=None, tiktoken_model_name=None, show_progress_bar=False, model_kwargs={})"
       ]
      },
      "execution_count": 13,
@@ -658,7 +657,7 @@
     }
    ],
    "source": [
-    "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
     "\n",
     "embeddings = OpenAIEmbeddings()\n",
     "embeddings"
@@ -666,26 +665,90 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 15,
    "metadata": {
     "tags": []
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Your Deep Lake dataset has been successfully created!\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " \r"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Dataset(path='hub://adilkhan/langchain-code', tensors=['embedding', 'id', 'metadata', 'text'])\n",
+      "\n",
+      "  tensor      htype       shape       dtype  compression\n",
+      "  -------    -------     -------     -------  ------- \n",
+      " embedding  embedding  (8244, 1536)  float32   None   \n",
+      "    id        text      (8244, 1)      str     None   \n",
+      " metadata     json      (8244, 1)      str     None   \n",
+      "   text       text      (8244, 1)      str     None   \n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": []
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<langchain.vectorstores.deeplake.DeepLake at 0x7fe1b67d7a30>"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
-    "from langchain_deeplake.vectorstores import DeeplakeVectorStore\n",
+    "from langchain.vectorstores import DeepLake\n",
+    "\n",
     "\n",
     "username = \"<USERNAME_OR_ORG>\"\n",
     "\n",
     "\n",
-    "db = DeeplakeVectorStore.from_documents(\n",
-    "    documents=texts,\n",
-    "    embedding=embeddings,\n",
-    "    dataset_path=f\"hub://{username}/langchain-code\",\n",
-    "    overwrite=True,\n",
+    "db = DeepLake.from_documents(\n",
+    "    texts, embeddings, dataset_path=f\"hub://{username}/langchain-code\", overwrite=True\n",
     ")\n",
     "db"
    ]
   },
+  {
+   "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": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# from langchain.vectorstores import DeepLake\n",
+    "\n",
+    "# db = DeepLake.from_documents(\n",
+    "#     texts, embeddings, dataset_path=f\"hub://{<org_id>}/langchain-code\", runtime={\"tensor_db\": True}\n",
+    "# )\n",
+    "# db"
+   ]
+  },
   {
    "attachments": {},
    "cell_type": "markdown",
@@ -697,16 +760,24 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 17,
    "metadata": {
     "tags": []
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Deep Lake Dataset in hub://adilkhan/langchain-code already exists, loading from the storage\n"
+     ]
+    }
+   ],
    "source": [
-    "db = DeeplakeVectorStore(\n",
+    "db = DeepLake(\n",
     "    dataset_path=f\"hub://{username}/langchain-code\",\n",
     "    read_only=True,\n",
-    "    embedding_function=embeddings,\n",
+    "    embedding=embeddings,\n",
     ")"
    ]
   },
@@ -725,6 +796,36 @@
     "retriever.search_kwargs[\"k\"] = 20"
    ]
   },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "You can also specify user defined functions using [Deep Lake filters](https://docs.deeplake.ai/en/latest/deeplake.core.dataset.html#deeplake.core.dataset.Dataset.filter)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "def filter(x):\n",
+    "    # filter based on source code\n",
+    "    if \"something\" in x[\"text\"].data()[\"value\"]:\n",
+    "        return False\n",
+    "\n",
+    "    # filter based on path e.g. extension\n",
+    "    metadata = x[\"metadata\"].data()[\"value\"]\n",
+    "    return \"only_this\" in metadata[\"source\"] or \"also_that\" in metadata[\"source\"]\n",
+    "\n",
+    "\n",
+    "### turn on below for custom filtering\n",
+    "# retriever.search_kwargs['filter'] = filter"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 20,
@@ -733,11 +834,11 @@
    },
    "outputs": [],
    "source": [
+    "from langchain.chat_models import ChatOpenAI\n",
     "from langchain.chains import ConversationalRetrievalChain\n",
-    "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "model = ChatOpenAI(model=\"gpt-3.5-turbo-0613\")  # 'ada' 'gpt-3.5-turbo-0613' 'gpt-4',\n",
-    "qa = RetrievalQA.from_llm(model, retriever=retriever)"
+    "model = ChatOpenAI(model_name=\"gpt-3.5-turbo-0613\")  # 'ada' 'gpt-3.5-turbo-0613' 'gpt-4',\n",
+    "qa = ConversationalRetrievalChain.from_llm(model, retriever=retriever)"
    ]
   },
   {
@@ -831,7 +932,7 @@
       "**Answer**: The LangChain class includes various types of retrievers such as:\n",
       "\n",
       "- ArxivRetriever\n",
-      "- AzureAISearchRetriever\n",
+      "- AzureCognitiveSearchRetriever\n",
       "- BM25Retriever\n",
       "- ChaindeskRetriever\n",
       "- ChatGPTPluginRetriever\n",
@@ -891,7 +992,7 @@
     {
      "data": {
       "text/plain": [
-       "{'question': 'LangChain possesses a variety of retrievers including:\\n\\n1. ArxivRetriever\\n2. AzureAISearchRetriever\\n3. BM25Retriever\\n4. ChaindeskRetriever\\n5. ChatGPTPluginRetriever\\n6. ContextualCompressionRetriever\\n7. DocArrayRetriever\\n8. ElasticSearchBM25Retriever\\n9. EnsembleRetriever\\n10. GoogleVertexAISearchRetriever\\n11. AmazonKendraRetriever\\n12. KNNRetriever\\n13. LlamaIndexGraphRetriever\\n14. LlamaIndexRetriever\\n15. MergerRetriever\\n16. MetalRetriever\\n17. MilvusRetriever\\n18. MultiQueryRetriever\\n19. ParentDocumentRetriever\\n20. PineconeHybridSearchRetriever\\n21. PubMedRetriever\\n22. RePhraseQueryRetriever\\n23. RemoteLangChainRetriever\\n24. SelfQueryRetriever\\n25. SVMRetriever\\n26. TFIDFRetriever\\n27. TimeWeightedVectorStoreRetriever\\n28. VespaRetriever\\n29. WeaviateHybridSearchRetriever\\n30. WebResearchRetriever\\n31. WikipediaRetriever\\n32. ZepRetriever\\n33. ZillizRetriever\\n\\nIt also includes self query translators like:\\n\\n1. ChromaTranslator\\n2. DeepLakeTranslator\\n3. MyScaleTranslator\\n4. PineconeTranslator\\n5. QdrantTranslator\\n6. WeaviateTranslator\\n\\nAnd remote retrievers like:\\n\\n1. RemoteLangChainRetriever'}"
+       "{'question': 'LangChain possesses a variety of retrievers including:\\n\\n1. ArxivRetriever\\n2. AzureCognitiveSearchRetriever\\n3. BM25Retriever\\n4. ChaindeskRetriever\\n5. ChatGPTPluginRetriever\\n6. ContextualCompressionRetriever\\n7. DocArrayRetriever\\n8. ElasticSearchBM25Retriever\\n9. EnsembleRetriever\\n10. GoogleVertexAISearchRetriever\\n11. AmazonKendraRetriever\\n12. KNNRetriever\\n13. LlamaIndexGraphRetriever\\n14. LlamaIndexRetriever\\n15. MergerRetriever\\n16. MetalRetriever\\n17. MilvusRetriever\\n18. MultiQueryRetriever\\n19. ParentDocumentRetriever\\n20. PineconeHybridSearchRetriever\\n21. PubMedRetriever\\n22. RePhraseQueryRetriever\\n23. RemoteLangChainRetriever\\n24. SelfQueryRetriever\\n25. SVMRetriever\\n26. TFIDFRetriever\\n27. TimeWeightedVectorStoreRetriever\\n28. VespaRetriever\\n29. WeaviateHybridSearchRetriever\\n30. WebResearchRetriever\\n31. WikipediaRetriever\\n32. ZepRetriever\\n33. ZillizRetriever\\n\\nIt also includes self query translators like:\\n\\n1. ChromaTranslator\\n2. DeepLakeTranslator\\n3. MyScaleTranslator\\n4. PineconeTranslator\\n5. QdrantTranslator\\n6. WeaviateTranslator\\n\\nAnd remote retrievers like:\\n\\n1. RemoteLangChainRetriever'}"
       ]
      },
      "execution_count": 31,
@@ -1015,7 +1116,7 @@
       "The LangChain class includes various types of retrievers such as:\n",
       "\n",
       "- ArxivRetriever\n",
-      "- AzureAISearchRetriever\n",
+      "- AzureCognitiveSearchRetriever\n",
       "- BM25Retriever\n",
       "- ChaindeskRetriever\n",
       "- ChatGPTPluginRetriever\n",