bump 291 (#10604)

**I recently reviewed the content and identified that there heading
appeared twice on the docs.**

.devcontainer/README.md

@@ -0,0 +1,41 @@
+# Dev container
+
+This project includes a [dev container](https://containers.dev/), which lets you use a container as a full-featured dev environment.
+
+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/hwchase17/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/hwchase17/langchain.
+1. Click on the **Codespaces** tab.
+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 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>
+
+
+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.
+
+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).
+
+2. Open a locally cloned copy of the code:
+
+   - Fork and Clone this repository to your local filesystem.
+   - Press <kbd>F1</kbd> and select the **Dev Containers: Open Folder in Container...** command.
+   - Select the cloned copy of this folder, wait for the container to start, and try things out!
+
+You can learn more in the [Dev Containers documentation](https://code.visualstudio.com/docs/devcontainers/containers).
+
+## 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.

.devcontainer/devcontainer.json

@@ -0,0 +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/${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

@@ -0,0 +1,32 @@
+version: '3'
+services:
+  langchain:
+    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 
+  #   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
+    
+    

.gitattributes

@@ -0,0 +1,3 @@
+* text=auto eol=lf
+*.{cmd,[cC][mM][dD]} text eol=crlf
+*.{bat,[bB][aA][tT]} text eol=crlf

.github/CONTRIBUTING.md

@@ -2,82 +2,94 @@
 
 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 it be in the form of a new feature, improved infra, or better documentation.
+to contributions, whether they be in the form of new features, improved infra, better documentation, or bug fixes.
+
+## 🗺️ Guidelines
+
+### 👩‍💻 Contributing Code
 
 To contribute to this project, please follow a ["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 maintainer.
 
-## 🗺️Contributing Guidelines
+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
+[Common Tasks](#-common-tasks) 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 lives 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're a small, building-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/hwchase17/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. These include:
+with bugs, improvements, and feature requests.
 
-- prompts: related to prompt tooling/infra.
-- llms: related to LLM wrappers/tooling/infra.
-- chains
-- utilities: related to different types of utilities to integrate with (Python, SQL, etc.).
-- agents
-- memory
-- applications: related to example applications to build
+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 the two issues are related, or blocking, please link them rather than keep them as one single one.
+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 develop in this field some may get out of date.
-If you notice this happening, please just let us know.
+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
 
-Although we try to have a developer setup to make it as easy as possible for others to contribute (see below)
-it is possible that some pain point may arise around environment setup, linting, documentation, or other.
-Should that occur, 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.
+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.
+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.
 
-### 🏭Release process
+## 🚀 Quick Start
 
-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/).
+> **Note:** You can run this repository locally (which is described below) or in a [development container](https://containers.dev/) (which is described in the [.devcontainer folder](https://github.com/hwchase17/langchain/tree/master/.devcontainer)).
 
-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).
-
-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 in another manner.
-
-## 🚀Quick Start
-
-This project uses [Poetry](https://python-poetry.org/) as a dependency manager. Check out Poetry's [documentation on how to install it](https://python-poetry.org/docs/#installation) on your system before proceeding.
+This project uses [Poetry](https://python-poetry.org/) v1.5.1 as a dependency manager. Check out Poetry's [documentation on how to install it](https://python-poetry.org/docs/#installation) on your system before proceeding.
 
 ❗Note: If you use `Conda` or `Pyenv` as your environment / package manager, avoid dependency conflicts by doing the following first:
 1. *Before installing Poetry*, create and activate a new Conda env (e.g. `conda create -n langchain python=3.9`)
-2. Install Poetry (see above)
+2. Install Poetry v1.5.1 (see above)
 3. Tell Poetry to use the virtualenv python environment (`poetry config virtualenvs.prefer-active-python true`)
 4. Continue with the following steps.
 
+There are two separate projects in this repository:
+- `langchain`: core langchain code, abstractions, and use cases
+- `langchain.experimental`: more experimental code
+
+Each of these has their OWN development environment.
+In order to run any of the commands below, please move into their respective directories.
+For example, to contribute to `langchain` run `cd libs/langchain` before getting started with the below.
+
 To install requirements:
 
 ```bash
-poetry install -E all
+poetry install --with test
 ```
 
-This will install all requirements for running the package, examples, linting, formatting, tests, and coverage. Note the `-E all` flag will install all optional dependencies necessary for integration testing.
+This will install all requirements for running the package, examples, linting, formatting, tests, and coverage.
 
-❗Note: If you're running Poetry 1.4.1 and receive a `WheelFileValidationError` for `debugpy` during installation, you can try either downgrading to Poetry 1.4.0 or disabling "modern installation" (`poetry config installer.modern-installation false`) and re-install requirements. See [this `debugpy` issue](https://github.com/microsoft/debugpy/issues/1246) for more details.
+❗Note: If during installation you receive a `WheelFileValidationError` for `debugpy`, please make sure you are running Poetry v1.5.1. 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 v1.5.1, 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.
 
-Now, you should be able to run the common tasks in the following section. To double check, run `make test`, all tests should pass. If they don't you may need to pip install additional dependencies, such as `numexpr` and `openapi_schema_pydantic`.
+Now assuming `make` and `pytest` are installed, you should be able to run the common tasks in the following section. To double check, run `make test` under `libs/langchain`, all tests should pass. If they don't, you may need to pip install additional dependencies, such as `numexpr` and `openapi_schema_pydantic`.
 
-## ✅Common Tasks
+## ✅ Common Tasks
 
 Type `make` for a list of common tasks.
 
@@ -91,6 +103,14 @@ To run formatting for this project:
 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/), [isort](https://pycqa.github.io/isort/), [flake8](https://flake8.pycqa.org/en/latest/), and [mypy](http://mypy-lang.org/).
@@ -101,8 +121,42 @@ To run linting for this project:
 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'
+```
+
 ### Coverage
 
 Code coverage (i.e. the amount of code that is covered by unit tests) helps identify areas of the code that are potentially more or less brittle.
@@ -113,8 +167,37 @@ To get a report of current coverage, run the following:
 make coverage
 ```
 
+### 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 that 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.
+
 ### Testing
 
+See section about optional dependencies.
+
+#### Unit Tests
+
 Unit tests cover modular logic that does not require calls to outside APIs.
 
 To run unit tests:
@@ -131,8 +214,20 @@ make docker_tests
 
 If you add new logic, please add a unit test.
 
+
+
+#### Integration Tests
+
 Integration tests cover logic that requires making calls to outside APIs (often integration with other services).
 
+**warning** Almost no tests should be integration tests.
+
+  Tests that require making network connections make it difficult for other
+  developers to test the code.
+
+  Instead favor relying on `responses` library and/or mock.patch to mock
+  requests using small fixtures.
+
 To run integration tests:
 
 ```bash
@@ -161,30 +256,54 @@ When you run `poetry install`, the `langchain` package is installed as editable
 
 ## 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.
+
 ### Contribute Documentation
 
-Docs are largely autogenerated by [sphinx](https://www.sphinx-doc.org/en/master/) from the code.
+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 run the linkchecker to make sure all links are valid:
-
-```bash
-make docs_linkcheck
-```
-
-Finally, you can build the documentation as outlined below:
+Next, you can build the documentation as outlined below:
 
 ```bash
 make docs_build
+make api_docs_build
 ```
+
+Finally, you can run the linkchecker to make sure all links are valid:
+
+```bash
+make docs_linkcheck
+make api_docs_linkcheck
+```
+
+## 🏭 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 in another manner.

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -0,0 +1,106 @@
+name: "\U0001F41B Bug Report"
+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. Before creating a new
+        issue, please make sure to take a few moments to check the issue tracker
+        for existing issues about the bug.
+
+  - type: textarea
+    id: system-info
+    attributes:
+      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: "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: Reproduction
+      description: |
+        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: |
+        Steps to reproduce the behavior:
+
+          1.
+          2.
+          3.
+
+  - type: textarea
+    id: expected-behavior
+    validations:
+      required: true
+    attributes:
+      label: Expected behavior
+      description: "A clear and concise description of what you would expect to happen."

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,6 @@
+blank_issues_enabled: true
+version: 2.1
+contact_links:
+  - 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

@@ -0,0 +1,30 @@
+name: "\U0001F680 Feature request"
+description: Submit a proposal/request for a new LangChain feature
+labels: ["02 Feature Request"]
+body:
+  - type: textarea
+    id: feature-request
+    validations:
+      required: true
+    attributes:
+      label: Feature request
+      description: |
+        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: motivation
+    validations:
+      required: true
+    attributes:
+      label: Motivation
+      description: |
+        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: contribution
+    validations:
+      required: true
+    attributes:
+      label: Your contribution
+      description: |
+        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/hwchase17/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/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,20 @@
+<!-- Thank you for contributing to LangChain!
+
+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!
+
+Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` to check this locally.
+
+See contribution guidelines for more information on how to write/run tests, lint, etc: 
+https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
+
+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.
+
+If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17.
+ -->

.github/actions/poetry_setup/action.yml

@@ -0,0 +1,91 @@
+# An action for setting up poetry install with caching.
+# Using a custom action since the default action does not
+# take poetry install groups into account.
+# Action code from:
+# https://github.com/actions/setup-python/issues/505#issuecomment-1273013236
+name: poetry-install-with-caching
+description: Poetry install with support for caching of dependency groups.
+
+inputs:
+  python-version:
+    description: Python version, supporting MAJOR.MINOR only
+    required: true
+
+  poetry-version:
+    description: Poetry version
+    required: true
+
+  cache-key:
+    description: Cache key to use for manual handling of caching
+    required: true
+
+  working-directory:
+    description: Directory whose poetry.lock file should be cached
+    required: true
+
+runs:
+  using: composite
+  steps:
+    - uses: actions/setup-python@v4
+      name: Setup python ${{ inputs.python-version }}
+      with:
+        python-version: ${{ inputs.python-version }}
+
+    - uses: actions/cache@v3
+      id: cache-bin-poetry
+      name: Cache Poetry binary - Python ${{ inputs.python-version }}
+      env:
+        SEGMENT_DOWNLOAD_TIMEOUT_MIN: "1"
+      with:
+        path: |
+          /opt/pipx/venvs/poetry
+        # This step caches the poetry installation, so make sure it's keyed on the poetry version as well.
+        key: bin-poetry-${{ runner.os }}-${{ runner.arch }}-py-${{ inputs.python-version }}-${{ inputs.poetry-version }}
+
+    - name: Refresh shell hashtable and fixup softlinks
+      if: steps.cache-bin-poetry.outputs.cache-hit == 'true'
+      shell: bash
+      env:
+        POETRY_VERSION: ${{ inputs.poetry-version }}
+        PYTHON_VERSION: ${{ inputs.python-version }}
+      run: |
+        set -eux
+
+        # Refresh the shell hashtable, to ensure correct `which` output.
+        hash -r
+
+        # `actions/cache@v3` doesn't always seem able to correctly unpack softlinks.
+        # Delete and recreate the softlinks pipx expects to have.
+        rm /opt/pipx/venvs/poetry/bin/python
+        cd /opt/pipx/venvs/poetry/bin
+        ln -s "$(which "python$PYTHON_VERSION")" python
+        chmod +x python
+        cd /opt/pipx_bin/
+        ln -s /opt/pipx/venvs/poetry/bin/poetry poetry
+        chmod +x poetry
+
+        # Ensure everything got set up correctly.
+        /opt/pipx/venvs/poetry/bin/python --version
+        /opt/pipx_bin/poetry --version
+
+    - name: Install poetry
+      if: steps.cache-bin-poetry.outputs.cache-hit != 'true'
+      shell: bash
+      env:
+        POETRY_VERSION: ${{ inputs.poetry-version }}
+        PYTHON_VERSION: ${{ inputs.python-version }}
+      run: pipx install "poetry==$POETRY_VERSION" --python "python$PYTHON_VERSION" --verbose
+
+    - name: Restore pip and poetry cached dependencies
+      uses: actions/cache@v3
+      env:
+        SEGMENT_DOWNLOAD_TIMEOUT_MIN: "4"
+        WORKDIR: ${{ inputs.working-directory == '' && '.' || inputs.working-directory }}
+      with:
+        path: |
+          ~/.cache/pip
+          ~/.cache/pypoetry/virtualenvs
+          ~/.cache/pypoetry/cache
+          ~/.cache/pypoetry/artifacts
+          ${{ env.WORKDIR }}/.venv
+        key: py-deps-${{ runner.os }}-${{ runner.arch }}-py-${{ inputs.python-version }}-poetry-${{ inputs.poetry-version }}-${{ inputs.cache-key }}-${{ hashFiles(format('{0}/**/poetry.lock', env.WORKDIR)) }}

.github/tools/git-restore-mtime

@@ -0,0 +1,606 @@
+#!/usr/bin/env python3
+#
+# git-restore-mtime - Change mtime of files based on commit date of last change
+#
+#    Copyright (C) 2012 Rodrigo Silva (MestreLion) <linux@rodrigosilva.com>
+#
+#    This program is free software: you can redistribute it and/or modify
+#    it under the terms of the GNU General Public License as published by
+#    the Free Software Foundation, either version 3 of the License, or
+#    (at your option) any later version.
+#
+#    This program is distributed in the hope that it will be useful,
+#    but WITHOUT ANY WARRANTY; without even the implied warranty of
+#    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+#    GNU General Public License for more details.
+#
+#    You should have received a copy of the GNU General Public License
+#    along with this program. See <http://www.gnu.org/licenses/gpl.html>
+#
+# Source: https://github.com/MestreLion/git-tools
+# Version: July 13, 2023 (commit hash 5f832e72453e035fccae9d63a5056918d64476a2)
+"""
+Change the modification time (mtime) of files in work tree, based on the
+date of the most recent commit that modified the file, including renames.
+
+Ignores untracked files and uncommitted deletions, additions and renames, and
+by default modifications too.
+---
+Useful prior to generating release tarballs, so each file is archived with a
+date that is similar to the date when the file was actually last modified,
+assuming the actual modification date and its commit date are close.
+"""
+
+# TODO:
+# - Add -z on git whatchanged/ls-files, so we don't deal with filename decoding
+# - When Python is bumped to 3.7, use text instead of universal_newlines on subprocess
+# - Update "Statistics for some large projects" with modern hardware and repositories.
+# - Create a README.md for git-restore-mtime alone. It deserves extensive documentation
+#   - Move Statistics there
+# - See git-extras as a good example on project structure and documentation
+
+# FIXME:
+# - When current dir is outside the worktree, e.g. using --work-tree, `git ls-files`
+#   assume any relative pathspecs are to worktree root, not the current dir. As such,
+#   relative pathspecs may not work.
+# - Renames are tricky:
+#   - R100 should not change mtime, but original name is not on filelist. Should
+#     track renames until a valid (A, M) mtime found and then set on current name.
+#   - Should set mtime for both current and original directories.
+#   - Check mode changes with unchanged blobs?
+# - Check file (A, D) for the directory mtime is not sufficient:
+#   - Renames also change dir mtime, unless rename was on a parent dir
+#   - If most recent change of all files in a dir was a Modification (M),
+#     dir might not be touched at all.
+#   - Dirs containing only subdirectories but no direct files will also
+#     not be touched. They're files' [grand]parent dir, but never their dirname().
+#   - Some solutions:
+#     - After files done, perform some dir processing for missing dirs, finding latest
+#       file (A, D, R)
+#     - Simple approach: dir mtime is the most recent child (dir or file) mtime
+#     - Use a virtual concept of "created at most at" to fill missing info, bubble up
+#       to parents and grandparents
+#   - When handling [grand]parent dirs, stay inside <pathspec>
+# - Better handling of merge commits. `-m` is plain *wrong*. `-c/--cc` is perfect, but
+#   painfully slow. First pass without merge commits is not accurate. Maybe add a new
+#   `--accurate` mode for `--cc`?
+
+if __name__ != "__main__":
+    raise ImportError("{} should not be used as a module.".format(__name__))
+
+import argparse
+import datetime
+import logging
+import os.path
+import shlex
+import signal
+import subprocess
+import sys
+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', []))
+
+# Call os.path.normpath() only if not in a POSIX platform (Windows)
+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}
+
+
+# Command-line interface ######################################################
+
+def parse_args():
+    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="""
+        Print additional information for each processed file.
+        Specify twice to further increase verbosity.
+        """)
+
+    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="""
+        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="""
+        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="""
+        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="""
+        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.
+        Including merge commits may lead to fewer commits being evaluated as files
+        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="""
+        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="""
+        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="""
+        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('--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="""
+        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="""
+        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="""
+        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="""
+        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="""
+        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()))
+
+    args_ = parser.parse_args()
+    if args_.verbose:
+        args_.loglevel = max(logging.TRACE, logging.DEBUG // args_.verbose)
+    args_.debug = args_.loglevel <= logging.DEBUG
+    return args_
+
+
+def get_version(version=__version__):
+    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')
+    except Git.Error:
+        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
+    logging.Logger.trace = lambda _, m, *a, **k: _.log(TRACE, m, *a, **k)
+    return logging.getLogger()
+
+
+def normalize(path):
+    r"""Normalize paths from git, handling non-ASCII characters.
+
+    Git stores paths as UTF-8 normalization form C.
+    If path contains non-ASCII or non-printable characters, git outputs the UTF-8
+    in octal-escaped notation, escaping double-quotes and backslashes, and then
+    double-quoting the whole path.
+    https://git-scm.com/docs/git-config#Documentation/git-config.txt-corequotePath
+
+    This function reverts this encoding, so:
+    normalize(r'"Back\\slash_double\"quote_a\303\247a\303\255"') =>
+        r'Back\slash_double"quote_açaí')
+
+    Paths with invalid UTF-8 encoding, such as single 0x80-0xFF bytes (e.g, from
+    Latin1/Windows-1251 encoding) are decoded using surrogate escape, the same
+    method used by Python for filesystem paths. So 0xE6 ("æ" in Latin1, r'\\346'
+    from Git) is decoded as "\udce6". See https://peps.python.org/pep-0383/ and
+    https://vstinner.github.io/painful-history-python-filesystem-encoding.html
+
+    Also see notes on `windows/non-ascii-paths.txt` about path encodings on
+    non-UTF-8 platforms and filesystems.
+    """
+    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
+    if NORMALIZE_PATHS:
+        # Make sure the slash matches the OS; for Windows we need a backslash
+        path = os.path.normpath(path)
+    return path
+
+
+def dummy(*_args, **_kwargs):
+    """No-op function used in dry-run tests"""
+
+
+def touch(path, mtime):
+    """The actual mtime update"""
+    os.utime(path, (mtime, mtime), **UTIME_KWS)
+
+
+def touch_ns(path, mtime_ns):
+    """The actual mtime update, using nanoseconds for unique timestamps"""
+    os.utime(path, None, ns=(mtime_ns, mtime_ns), **UTIME_KWS)
+
+
+def isodate(secs: int):
+    # time.localtime() accepts floats, but discards fractional part
+    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=' ')
+
+
+def get_mtime_ns(secs: int, idx: int):
+    # Time resolution for filesystems and functions:
+    # ext-4 and other POSIX filesystems: 1 nanosecond
+    # NTFS (Windows default): 100 nanoseconds
+    # datetime.datetime() (due to 64-bit float epoch): 1 microsecond
+    us = idx % 1000000  # 10**6
+    return 1000 * (1000000 * secs + us)
+
+
+def get_mtime_path(path):
+    return os.path.getmtime(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.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))
+        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))
+
+    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')))
+
+    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]
+
+    def terminate(self):
+        if self._proc is None:
+            return
+        try:
+            self._proc.terminate()
+        except OSError:
+            # Avoid errors on OpenBSD
+            pass
+
+    def _get_repo_dirs(self):
+        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.extend(paths)
+        popen_args = dict(universal_newlines=True, encoding='utf8')
+        if not self.errors:
+            popen_args['stderr'] = subprocess.DEVNULL
+        log.trace("Executing: %s", ' '.join(cmdlist))
+        if not output:
+            return subprocess.call(cmdlist, **popen_args)
+        if check:
+            try:
+                stdout: str = subprocess.check_output(cmdlist, **popen_args)
+                return stdout.splitlines()
+            except subprocess.CalledProcessError as e:
+                raise self.Error(e.returncode, e.cmd, e.output, e.stderr)
+        self._proc = subprocess.Popen(cmdlist, stdout=subprocess.PIPE, **popen_args)
+        return (_.rstrip() for _ in self._proc.stdout)
+
+    def __del__(self):
+        self.terminate()
+
+    class Error(subprocess.CalledProcessError):
+        """Error from git executable"""
+
+
+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
+    ):
+        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
+            mtime = int(line)
+            if args.unique_times:
+                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')
+
+        # Possible statuses:
+        # M: Modified (content changed)
+        # A: Added (created)
+        # D: Deleted
+        # 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]
+        file = tokens[-1]
+
+        # Handles non-ASCII chars and OS path separator
+        file = normalize(file)
+
+        def do_file():
+            if args.skip_older_than_commit and get_mtime_path(file) <= mtime:
+                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)
+            try:
+                touch(os.path.join(git.workdir, file), mtime)
+                stats['touches'] += 1
+            except Exception as e:
+                log.error("ERROR: %s: %s", e, file)
+                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 '.'))
+            try:
+                touch(os.path.join(git.workdir, dirname), mtime)
+                stats['dirtouches'] += 1
+            except Exception as e:
+                log.error("ERROR: %s: %s", e, dirname)
+                stats['direrrors'] += 1
+
+        if file in filelist:
+            stats['files'] -= 1
+            filelist.remove(file)
+            do_file()
+
+        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']:
+            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')}
+
+    logging.basicConfig(level=args.loglevel, format='%(message)s')
+    log.trace("Arguments: %s", args)
+
+    # First things first: Where and Who are we?
+    if args.cwd:
+        log.debug("Changing directory: %s", args.cwd)
+        try:
+            os.chdir(args.cwd)
+        except OSError as e:
+            log.critical(e)
+            return e.errno
+    # Using both os.chdir() and `git -C` is redundant, but might prevent side effects
+    # `git -C` alone could be enough if we make sure that:
+    # - all paths, including args.pathspec, are processed by git: ls-files, rev-parse
+    # - touch() / os.utime() path argument is always prepended with git.workdir
+    try:
+        git = Git(workdir=args.workdir, gitdir=args.gitdir, cwd=args.cwd)
+    except Git.Error as e:
+        # Not in a git repository, and git already informed user on stderr. So we just...
+        return e.returncode
+
+    # Get the files managed by git and build file list to be processed
+    if UPDATE_SYMLINKS and not args.skip_older_than:
+        filelist = set(git.ls_files(args.pathspec))
+    else:
+        filelist = set()
+        for path in git.ls_files(args.pathspec):
+            fullpath = os.path.join(git.workdir, path)
+
+            # 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)
+                continue
+
+            # skip files which are older than given threshold
+            if (args.skip_older_than
+                    and start - get_mtime_path(fullpath) > args.skip_older_than):
+                continue
+
+            # Always add files relative to worktree root
+            filelist.add(path)
+
+    # If --force, silently ignore uncommitted deletions (not in the filesystem)
+    # and renames / additions (will not be found in log anyway)
+    if args.force:
+        filelist -= set(git.ls_dirty(force=True))
+    # Otherwise, ignore any dirty files
+    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.")
+            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']))
+
+    if not filelist:
+        # Nothing to do. Exit silently and without errors, just like git does
+        return
+
+    # Process the log until all files are 'touched'
+    log.debug("Line #\tLog #\tF.Left\tModification Time\tFile Name")
+    parse_log(filelist, dirlist, stats, git, args.merge, args.pathspec)
+
+    # Missing files
+    if filelist:
+        # Try to find them in merge logs, if not done already
+        # (usually HUGE, thus MUCH slower!)
+        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))
+            for i in range(0, missing, STEPMISSING):
+                parse_log(filelist, dirlist, stats, git,
+                          merge=True, filterlist=filterlist[i:i + STEPMISSING])
+
+        # Still missing some?
+        for file in filelist:
+            log.warning("WARNING: not found in the log: %s", file)
+
+    # 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,)
+        # %-formatting lacks a thousand separator, must pre-render with .format()
+        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'])
+
+    if args.dirs:
+        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'])
+
+    log_info("%d files updated", stats['touches'])
+
+    if args.test:
+        log.info("TEST RUN - No files modified!")
+
+
+# Keep only essential, global assignments here. Any other logic must be in main()
+log = setup_logging()
+args = parse_args()
+
+# Set the actual touch() and other functions based on command-line arguments
+if args.unique_times:
+    touch = touch_ns
+    isodate = isodate_ns
+
+# Make sure this is always set last to ensure --test behaves as intended
+if args.test:
+    touch = dummy
+
+# UI done, it's showtime!
+try:
+    sys.exit(main())
+except KeyboardInterrupt:
+    log.info("\nAborting")
+    signal.signal(signal.SIGINT, signal.SIG_DFL)
+    os.kill(os.getpid(), signal.SIGINT)

.github/workflows/_lint.yml

@@ -0,0 +1,150 @@
+name: lint
+
+on:
+  workflow_call:
+    inputs:
+      working-directory:
+        required: true
+        type: string
+        description: "From which folder this pipeline executes"
+
+env:
+  POETRY_VERSION: "1.5.1"
+  WORKDIR: ${{ inputs.working-directory == '' && '.' || inputs.working-directory }}
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    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:
+      - uses: actions/checkout@v3
+        with:
+          # 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: Check Poetry File
+        shell: bash
+        working-directory: ${{ inputs.working-directory }}
+        run: |
+          poetry check
+
+      - name: Check lock file
+        shell: bash
+        working-directory: ${{ inputs.working-directory }}
+        run: |
+          poetry lock --check
+
+      - 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: |
+          poetry install --with dev,lint,test,typing
+
+      - name: Install langchain editable
+        working-directory: ${{ inputs.working-directory }}
+        if: ${{ inputs.working-directory != 'libs/langchain' }}
+        run: |
+          pip install -e ../langchain
+
+      - name: Restore black cache
+        uses: actions/cache@v3
+        env:
+          CACHE_BASE: black-${{ 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: "1.5.1"
+
+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@v3
+
+      - 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

@@ -0,0 +1,64 @@
+name: release
+
+on:
+  workflow_call:
+    inputs:
+      working-directory:
+        required: true
+        type: string
+        description: "From which folder this pipeline executes"
+
+env:
+  POETRY_VERSION: "1.5.1"
+
+jobs:
+  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:
+      # 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
+
+      # 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@v3
+
+      - 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: Create Release
+        uses: ncipollo/release-action@v1
+        if: ${{ inputs.working-directory == 'libs/langchain' }}
+        with:
+          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

.github/workflows/_test.yml

@@ -0,0 +1,57 @@
+name: test
+
+on:
+  workflow_call:
+    inputs:
+      working-directory:
+        required: true
+        type: string
+        description: "From which folder this pipeline executes"
+
+env:
+  POETRY_VERSION: "1.5.1"
+
+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: Python ${{ matrix.python-version }}
+    steps:
+      - uses: actions/checkout@v3
+
+      - 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: ${{ inputs.working-directory }}
+          cache-key: core
+
+      - name: Install dependencies
+        shell: bash
+        run: poetry install
+
+      - name: Run core tests
+        shell: bash
+        run: make test
+
+      - name: Ensure the tests did not create any additional files
+        shell: bash
+        run: |
+          set -eu
+
+          STATUS="$(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/codespell.yml

@@ -0,0 +1,24 @@
+---
+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@v3
+      - name: Codespell
+        uses: codespell-project/actions-codespell@v2
+        with:
+          skip: guide_imports.json

.github/workflows/langchain_ci.yml

@@ -0,0 +1,97 @@
+---
+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/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: "1.5.1"
+  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
+
+  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@v3
+
+      - 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_experimental_ci.yml

@@ -0,0 +1,129 @@
+---
+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/langchain/**'
+      - '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: "1.5.1"
+  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
+
+  # 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@v3
+
+      - 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@v3
+
+      - 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_release.yml

@@ -0,0 +1,13 @@
+---
+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

.github/workflows/linkcheck.yml

@@ -1,36 +0,0 @@
-name: linkcheck
-
-on:
-  push:
-    branches: [master]
-  pull_request:
-
-env:
-  POETRY_VERSION: "1.3.1"
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version:
-          - "3.11"
-    steps:
-      - uses: actions/checkout@v3
-      - name: Install poetry
-        run: |
-          pipx install poetry==$POETRY_VERSION
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v4
-        with:
-          python-version: ${{ matrix.python-version }}
-          cache: poetry
-      - name: Install dependencies
-        run: |
-          poetry install --with docs
-      - name: Build the docs
-        run: |
-          make docs_build
-      - name: Analyzing the docs with linkcheck
-        run: |
-          make docs_linkcheck

.github/workflows/lint.yml

@@ -1,36 +0,0 @@
-name: lint
-
-on:
-  push:
-    branches: [master]
-  pull_request:
-
-env:
-  POETRY_VERSION: "1.3.1"
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version:
-          - "3.8"
-          - "3.9"
-          - "3.10"
-          - "3.11"
-    steps:
-      - uses: actions/checkout@v3
-      - name: Install poetry
-        run: |
-          pipx install poetry==$POETRY_VERSION
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v4
-        with:
-          python-version: ${{ matrix.python-version }}
-          cache: poetry
-      - name: Install dependencies
-        run: |
-          poetry install
-      - name: Analysing the code with our lint
-        run: |
-          make lint

.github/workflows/release.yml

@@ -1,49 +0,0 @@
-name: release
-
-on:
-  pull_request:
-    types:
-      - closed
-    branches:
-      - master
-    paths:
-      - 'pyproject.toml'
-
-env:
-  POETRY_VERSION: "1.3.1"
-
-jobs:
-  if_release:
-    if: |
-        ${{ github.event.pull_request.merged == true }}
-        && ${{ contains(github.event.pull_request.labels.*.name, 'release') }}
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-      - name: Install poetry
-        run: pipx install poetry==$POETRY_VERSION
-      - name: Set up Python 3.10
-        uses: actions/setup-python@v4
-        with:
-          python-version: "3.10"
-          cache: "poetry"
-      - 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
-        with:
-          artifacts: "dist/*"
-          token: ${{ secrets.GITHUB_TOKEN }}
-          draft: false
-          generateReleaseNotes: true
-          tag: v${{ steps.check-version.outputs.version }}
-          commit: master
-      - name: Publish to PyPI
-        env:
-          POETRY_PYPI_TOKEN_PYPI: ${{ secrets.PYPI_API_TOKEN }}
-        run: | 
-          poetry publish

.github/workflows/scheduled_test.yml

@@ -0,0 +1,61 @@
+name: Scheduled tests
+
+on:
+  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
+  schedule:
+    - cron:  '0 13 * * *'
+
+env:
+  POETRY_VERSION: "1.5.1"
+
+jobs:
+  build:
+    defaults:
+      run:
+        working-directory: libs/langchain
+    runs-on: ubuntu-latest
+    environment: Scheduled testing
+    strategy:
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
+    name: Python ${{ matrix.python-version }}
+    steps:
+      - uses: actions/checkout@v3
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: "./.github/actions/poetry_setup"
+        with:
+          python-version: ${{ matrix.python-version }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: libs/langchain
+          cache-key: scheduled
+
+      - name: Install dependencies
+        working-directory: libs/langchain
+        shell: bash
+        run: |
+          echo "Running scheduled tests, installing dependencies with poetry..."
+          poetry install --with=test_integration
+
+      - name: Run tests
+        shell: bash
+        env:
+          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+        run: |
+          make scheduled_tests
+
+      - name: Ensure the tests did not create any additional files
+        shell: bash
+        run: |
+          set -eu
+
+          STATUS="$(git status)"
+          echo "$STATUS"
+
+          # grep will exit non-zero if the target message isn't found,
+          # and `set -e` above will cause the step to fail.
+          echo "$STATUS" | grep 'nothing to commit, working tree clean'

.github/workflows/test.yml

@@ -1,34 +0,0 @@
-name: test
-
-on:
-  push:
-    branches: [master]
-  pull_request:
-
-env:
-  POETRY_VERSION: "1.3.1"
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version:
-          - "3.8"
-          - "3.9"
-          - "3.10"
-          - "3.11"
-    steps:
-      - uses: actions/checkout@v3
-      - name: Install poetry
-        run: pipx install poetry==$POETRY_VERSION
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v4
-        with:
-          python-version: ${{ matrix.python-version }}
-          cache: "poetry"
-      - name: Install dependencies
-        run: poetry install
-      - name: Run unit tests
-        run: |
-          make test

.gitignore

@@ -1,3 +1,4 @@
+.vs/
 .vscode/
 .idea/
 # Byte-compiled / optimized / DLL files
@@ -72,6 +73,7 @@ instance/
 
 # Sphinx documentation
 docs/_build/
+docs/docs/_build/
 
 # PyBuilder
 target/
@@ -144,4 +146,28 @@ wandb/
 /.ruff_cache/
 
 *.pkl
-*.bin
+*.bin
+
+# integration test artifacts
+data_map*
+\[('_type', 'fake'), ('stop', None)]
+
+# Replit files
+*replit*
+
+node_modules
+docs/.yarn/
+docs/node_modules/
+docs/.docusaurus/
+docs/.cache-loader/
+docs/_dist
+docs/api_reference/api_reference.rst
+docs/api_reference/experimental_api_reference.rst
+docs/api_reference/_build
+docs/api_reference/*/
+!docs/api_reference/_static/
+!docs/api_reference/templates/
+!docs/api_reference/themes/
+docs/docs_skeleton/build
+docs/docs_skeleton/node_modules
+docs/docs_skeleton/yarn.lock

.gitmodules

@@ -0,0 +1,4 @@
+[submodule "docs/_docs_skeleton"]
+	path = docs/_docs_skeleton
+	url = https://github.com/langchain-ai/langchain-shared-docs
+	branch = main

.readthedocs.yaml

@@ -0,0 +1,29 @@
+# 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"
+  jobs:
+    pre_build:
+      - python docs/api_reference/create_api_rst.py
+
+# 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
+   - method: pip
+     path: .

MIGRATE.md

@@ -0,0 +1,61 @@
+# Migrating to `langchain_experimental`
+
+We are moving any experimental components of LangChain, or components with vulnerability issues, into `langchain_experimental`.
+This guide covers how to migrate.
+
+## Installation
+
+Previously:
+
+`pip install -U langchain`
+
+Now (only if you want to access things in experimental):
+
+`pip install -U langchain langchain_experimental`
+
+## Things in `langchain.experimental`
+
+Previously:
+
+`from langchain.experimental import ...`
+
+Now:
+
+`from langchain_experimental import ...`
+
+## PALChain
+
+Previously:
+
+`from langchain.chains import PALChain`
+
+Now:
+
+`from langchain_experimental.pal_chain import PALChain`
+
+## SQLDatabaseChain
+
+Previously:
+
+`from langchain.chains import SQLDatabaseChain`
+
+Now:
+
+`from langchain_experimental.sql import SQLDatabaseChain`
+
+Alternatively, if you are just interested in using the query generation part of the SQL chain, you can check out [`create_sql_query_chain`](https://github.com/langchain-ai/langchain/blob/master/docs/extras/use_cases/tabular/sql_query.ipynb)
+
+`from langchain.chains import create_sql_query_chain`
+
+## `load_prompt` for Python files
+
+Note: this only applies if you want to load Python files as prompts.
+If you want to load json/yaml files, no change is needed.
+
+Previously:
+
+`from langchain.prompts import load_prompt`
+
+Now:
+
+`from langchain_experimental.prompts import load_prompt`

Makefile

@@ -1,62 +1,54 @@
-.PHONY: all clean format lint test tests test_watch integration_tests docker_tests help
+.PHONY: all clean docs_build docs_clean docs_linkcheck api_docs_build api_docs_clean api_docs_linkcheck
 
+# Default target executed when no arguments are given to make.
 all: help
 
-coverage:
-	poetry run pytest --cov \
-		--cov-config=.coveragerc \
-		--cov-report xml \
-		--cov-report term-missing:skip-covered
 
-clean: docs_clean
+######################
+# DOCUMENTATION
+######################
+
+clean: docs_clean api_docs_clean
+
 
 docs_build:
-	cd docs && poetry run make html
+	docs/.local_build.sh
 
 docs_clean:
-	cd docs && poetry run make clean
+	rm -r docs/_dist
 
 docs_linkcheck:
-	poetry run linkchecker docs/_build/html/index.html
+	poetry run linkchecker docs/_dist/docs_skeleton/ --ignore-url node_modules
 
-format:
-	poetry run black .
-	poetry run ruff --select I --fix .
+api_docs_build:
+	poetry run python docs/api_reference/create_api_rst.py
+	cd docs/api_reference && poetry run make html
 
-PYTHON_FILES=.
-lint: PYTHON_FILES=.
-lint_diff: PYTHON_FILES=$(shell git diff --name-only --diff-filter=d master | grep -E '\.py$$')
+api_docs_clean:
+	rm -f docs/api_reference/api_reference.rst
+	cd docs/api_reference && poetry run make clean
 
-lint lint_diff:
-	poetry run mypy $(PYTHON_FILES)
-	poetry run black $(PYTHON_FILES) --check
-	poetry run ruff .
+api_docs_linkcheck:
+	poetry run linkchecker docs/api_reference/_build/html/index.html
 
-test:
-	poetry run pytest tests/unit_tests
+spell_check:
+	poetry run codespell --toml pyproject.toml
 
-tests:
-	poetry run pytest tests/unit_tests
+spell_fix:
+	poetry run codespell --toml pyproject.toml -w
 
-test_watch:
-	poetry run ptw --now . -- tests/unit_tests
-
-integration_tests:
-	poetry run pytest tests/integration_tests
-
-docker_tests:
-	docker build -t my-langchain-image:test .
-	docker run --rm my-langchain-image:test
+######################
+# HELP
+######################
 
 help:
 	@echo '----'
-	@echo 'coverage            - run unit tests and generate coverage report'
-	@echo 'docs_build          - build the documentation'
-	@echo 'docs_clean          - clean the documentation build artifacts'
-	@echo 'docs_linkcheck      - run linkchecker on the documentation'
-	@echo 'format              - run code formatters'
-	@echo 'lint                - run linters'
-	@echo 'test                - run unit tests'
-	@echo 'test_watch          - run unit tests in watch mode'
-	@echo 'integration_tests   - run integration tests'
-	@echo 'docker_tests        - run unit tests in docker'
+	@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'

README.md

@@ -2,44 +2,63 @@
 
 ⚡ Building applications with LLMs through composability ⚡
 
-[![lint](https://github.com/hwchase17/langchain/actions/workflows/lint.yml/badge.svg)](https://github.com/hwchase17/langchain/actions/workflows/lint.yml) [![test](https://github.com/hwchase17/langchain/actions/workflows/test.yml/badge.svg)](https://github.com/hwchase17/langchain/actions/workflows/test.yml) [![linkcheck](https://github.com/hwchase17/langchain/actions/workflows/linkcheck.yml/badge.svg)](https://github.com/hwchase17/langchain/actions/workflows/linkcheck.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)
+[![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)
 
-**Production Support:** As you move your LangChains into production, we'd love to offer more comprehensive support.
-Please fill out [this form](https://forms.gle/57d8AmXBYp8PP8tZA) and we'll set up a dedicated support Slack channel.
+
+Looking for the JS/TS version? Check out [LangChain.js](https://github.com/hwchase17/langchainjs).
+
+**Production Support:** As you move your LangChains into production, we'd love to offer more hands-on support.
+Fill out [this form](https://airtable.com/appwQzlErAS2qiP0L/shrGtGaVBVAz7NcV2) to share more about what you're building, and our team will get in touch.
+
+## 🚨Breaking Changes for select chains (SQLDatabase) on 7/28/23
+
+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/hwchase17/langchain/discussions/8043).
+Read how to migrate your code [here](MIGRATE.md).
 
 ## Quick Install
 
 `pip install langchain`
 or
-`conda install langchain -c conda-forge`
+`pip install langsmith && conda install langchain -c conda-forge`
 
 ## 🤔 What is this?
 
-Large language models (LLMs) are emerging as a transformative technology, enabling
-developers to build applications that they previously could not.
-But using these LLMs in isolation is often not enough to
-create a truly powerful app - the real power comes when you can combine them with other sources of computation or knowledge.
+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.
 
-This library is aimed at assisting in the development of those types of applications. Common examples of these types of applications include:
+This library aims to assist in the development of those types of applications. Common examples of these applications include:
 
 **❓ Question Answering over specific documents**
 
-- [Documentation](https://langchain.readthedocs.io/en/latest/use_cases/question_answering.html)
+- [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)
 
 **💬 Chatbots**
 
-- [Documentation](https://langchain.readthedocs.io/en/latest/use_cases/chatbots.html)
+- [Documentation](https://python.langchain.com/docs/use_cases/chatbots/)
 - End-to-end Example: [Chat-LangChain](https://github.com/hwchase17/chat-langchain)
 
 **🤖 Agents**
 
-- [Documentation](https://langchain.readthedocs.io/en/latest/modules/agents.html)
+- [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://langchain.readthedocs.io/en/latest/?) for full documentation on:
+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)
@@ -53,32 +72,32 @@ These are, in increasing order of complexity:
 
 **📃 LLMs and Prompts:**
 
-This includes prompt management, prompt optimization, generic interface for all LLMs, and common utilities for working with LLMs.
+This includes prompt management, prompt optimization, a generic interface for all LLMs, and common utilities for working with LLMs.
 
 **🔗 Chains:**
 
-Chains go beyond just a single LLM call, and are 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.
+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 datasource to fetch data to use in the generation step. Examples of this include summarization of long pieces of text and question/answering over specific data sources.
+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.
+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 is the concept of 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.
+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 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://langchain.readthedocs.io/en/latest/).
+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 infra, or better documentation.
+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

@@ -0,0 +1,6 @@
+# Security Policy
+
+## Reporting a Vulnerability
+
+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.

docs/.local_build.sh

@@ -0,0 +1,18 @@
+#!/usr/bin/env bash
+
+set -o errexit
+set -o nounset
+set -o pipefail
+set -o xtrace
+
+SCRIPT_DIR="$(cd "$(dirname "$0")"; pwd)"
+cd "${SCRIPT_DIR}"
+
+mkdir -p _dist/docs_skeleton
+cp -r {docs_skeleton,snippets} _dist
+cp -r extras/* _dist/docs_skeleton/docs
+cd _dist/docs_skeleton
+poetry run nbdoc_build
+poetry run python generate_api_reference_links.py
+yarn install
+yarn start

docs/_static/css/custom.css

@@ -1,17 +0,0 @@
-pre {
-  white-space: break-spaces;
-}
-
-@media (min-width: 1200px) {
-  .container,
-  .container-lg,
-  .container-md,
-  .container-sm,
-  .container-xl {
-    max-width: 2560px !important;
-  }
-}
-
-#my-component-root *, #headlessui-portal-root * {
-  z-index: 1000000000000;
-}

docs/api_reference/_static/css/custom.css

@@ -0,0 +1,17 @@
+pre {
+  white-space: break-spaces;
+}
+
+@media (min-width: 1200px) {
+  .container,
+  .container-lg,
+  .container-md,
+  .container-sm,
+  .container-xl {
+    max-width: 2560px !important;
+  }
+}
+
+#my-component-root *, #headlessui-portal-root * {
+  z-index: 10000;
+}

docs/api_reference/conf.py

@@ -0,0 +1,168 @@
+"""Configuration file for the Sphinx documentation builder."""
+# Configuration file for the Sphinx documentation builder.
+#
+# This file only contains a selection of the most common options. For a full
+# list see the documentation:
+# https://www.sphinx-doc.org/en/master/usage/configuration.html
+
+# -- Path setup --------------------------------------------------------------
+
+import json
+import os
+import sys
+from pathlib import Path
+
+import toml
+from docutils import nodes
+from sphinx.util.docutils import SphinxDirective
+
+# If extensions (or modules to document with autodoc) are in another directory,
+# add these directories to sys.path here. If the directory is relative to the
+# documentation root, use os.path.abspath to make it absolute, like shown here.
+
+_DIR = Path(__file__).parent.absolute()
+sys.path.insert(0, os.path.abspath("."))
+sys.path.insert(0, os.path.abspath("../../libs/langchain"))
+sys.path.insert(0, os.path.abspath("../../libs/experimental"))
+
+with (_DIR.parents[1] / "libs" / "langchain" / "pyproject.toml").open("r") as f:
+    data = toml.load(f)
+with (_DIR / "guide_imports.json").open("r") as f:
+    imported_classes = json.load(f)
+
+
+class ExampleLinksDirective(SphinxDirective):
+    """Directive to generate a list of links to examples.
+
+    We have a script that extracts links to API reference docs
+    from our notebook examples. This directive uses that information
+    to backlink to the examples from the API reference docs."""
+
+    has_content = False
+    required_arguments = 1
+
+    def run(self):
+        """Run the directive.
+
+        Called any time :example_links:`ClassName` is used
+        in the template *.rst files."""
+        class_or_func_name = self.arguments[0]
+        links = imported_classes.get(class_or_func_name, {})
+        list_node = nodes.bullet_list()
+        for doc_name, link in links.items():
+            item_node = nodes.list_item()
+            para_node = nodes.paragraph()
+            link_node = nodes.reference()
+            link_node["refuri"] = link
+            link_node.append(nodes.Text(doc_name))
+            para_node.append(link_node)
+            item_node.append(para_node)
+            list_node.append(item_node)
+        if list_node.children:
+            title_node = nodes.title()
+            title_node.append(nodes.Text(f"Examples using {class_or_func_name}"))
+            return [title_node, list_node]
+        return [list_node]
+
+
+def setup(app):
+    app.add_directive("example_links", ExampleLinksDirective)
+
+
+# -- Project information -----------------------------------------------------
+
+project = "🦜🔗 LangChain"
+copyright = "2023, Harrison Chase"
+author = "Harrison Chase"
+
+version = data["tool"]["poetry"]["version"]
+release = version
+
+html_title = project + " " + version
+html_last_updated_fmt = "%b %d, %Y"
+
+
+# -- General configuration ---------------------------------------------------
+
+# Add any Sphinx extension module names here, as strings. They can be
+# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
+# ones.
+extensions = [
+    "sphinx.ext.autodoc",
+    "sphinx.ext.autodoc.typehints",
+    "sphinx.ext.autosummary",
+    "sphinx.ext.napoleon",
+    "sphinx.ext.viewcode",
+    "sphinxcontrib.autodoc_pydantic",
+    "sphinx_copybutton",
+    "sphinx_panels",
+    "IPython.sphinxext.ipython_console_highlighting",
+]
+source_suffix = [".rst"]
+
+# some autodoc pydantic options are repeated in the actual template.
+# potentially user error, but there may be bugs in the sphinx extension
+# with options not being passed through correctly (from either the location in the code)
+autodoc_pydantic_model_show_json = False
+autodoc_pydantic_field_list_validators = False
+autodoc_pydantic_config_members = False
+autodoc_pydantic_model_show_config_summary = False
+autodoc_pydantic_model_show_validator_members = False
+autodoc_pydantic_model_show_validator_summary = False
+autodoc_pydantic_model_signature_prefix = "class"
+autodoc_pydantic_field_signature_prefix = "param"
+autodoc_member_order = "groupwise"
+autoclass_content = "both"
+autodoc_typehints_format = "short"
+
+# autodoc_typehints = "description"
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ["templates"]
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+# This pattern also affects html_static_path and html_extra_path.
+exclude_patterns = ["_build", "Thumbs.db", ".DS_Store"]
+
+
+# -- Options for HTML output -------------------------------------------------
+
+# The theme to use for HTML and HTML Help pages.  See the documentation for
+# a list of builtin themes.
+#
+html_theme = "scikit-learn-modern"
+html_theme_path = ["themes"]
+
+# redirects dictionary maps from old links to new links
+html_additional_pages = {}
+redirects = {
+    "index": "api_reference",
+}
+for old_link in redirects:
+    html_additional_pages[old_link] = "redirects.html"
+
+html_context = {
+    "display_github": True,  # Integrate GitHub
+    "github_user": "hwchase17",  # Username
+    "github_repo": "langchain",  # Repo name
+    "github_version": "master",  # Version
+    "conf_py_path": "/docs/api_reference",  # Path in the checkout to the docs root
+    "redirects": redirects,
+}
+
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+html_static_path = ["_static"]
+
+# These paths are either relative to html_static_path
+# or fully qualified paths (e.g. https://...)
+html_css_files = [
+    "css/custom.css",
+]
+html_use_index = False
+
+myst_enable_extensions = ["colon_fence"]
+
+# generate autosummary even if no references
+autosummary_generate = True

docs/api_reference/create_api_rst.py

@@ -0,0 +1,284 @@
+"""Script for auto-generating api_reference.rst."""
+import importlib
+import inspect
+import typing
+from pathlib import Path
+from typing import TypedDict, Sequence, List, Dict, Literal, Union
+from enum import Enum
+
+from pydantic import BaseModel
+
+ROOT_DIR = Path(__file__).parents[2].absolute()
+HERE = Path(__file__).parent
+
+PKG_DIR = ROOT_DIR / "libs" / "langchain" / "langchain"
+EXP_DIR = ROOT_DIR / "libs" / "experimental" / "langchain_experimental"
+WRITE_FILE = HERE / "api_reference.rst"
+EXP_WRITE_FILE = HERE / "experimental_api_reference.rst"
+
+
+ClassKind = Literal["TypedDict", "Regular", "Pydantic", "enum"]
+
+
+class ClassInfo(TypedDict):
+    """Information about a class."""
+
+    name: str
+    """The name of the class."""
+    qualified_name: str
+    """The fully qualified name of the class."""
+    kind: ClassKind
+    """The kind of the class."""
+    is_public: bool
+    """Whether the class is public or not."""
+
+
+class FunctionInfo(TypedDict):
+    """Information about a function."""
+
+    name: str
+    """The name of the function."""
+    qualified_name: str
+    """The fully qualified name of the function."""
+    is_public: bool
+    """Whether the function is public or not."""
+
+
+class ModuleMembers(TypedDict):
+    """A dictionary of module members."""
+
+    classes_: Sequence[ClassInfo]
+    functions: Sequence[FunctionInfo]
+
+
+def _load_module_members(module_path: str, namespace: str) -> ModuleMembers:
+    """Load all members of a module.
+
+    Args:
+        module_path: Path to the module.
+        namespace: the namespace of the module.
+
+    Returns:
+        list: A list of loaded module objects.
+    """
+    classes_: List[ClassInfo] = []
+    functions: List[FunctionInfo] = []
+    module = importlib.import_module(module_path)
+    for name, type_ in inspect.getmembers(module):
+        if not hasattr(type_, "__module__"):
+            continue
+        if type_.__module__ != module_path:
+            continue
+
+        if inspect.isclass(type_):
+            if type(type_) == typing._TypedDictMeta:  # type: ignore
+                kind: ClassKind = "TypedDict"
+            elif issubclass(type_, Enum):
+                kind = "enum"
+            elif issubclass(type_, BaseModel):
+                kind = "Pydantic"
+            else:
+                kind = "Regular"
+
+            classes_.append(
+                ClassInfo(
+                    name=name,
+                    qualified_name=f"{namespace}.{name}",
+                    kind=kind,
+                    is_public=not name.startswith("_"),
+                )
+            )
+        elif inspect.isfunction(type_):
+            functions.append(
+                FunctionInfo(
+                    name=name,
+                    qualified_name=f"{namespace}.{name}",
+                    is_public=not name.startswith("_"),
+                )
+            )
+        else:
+            continue
+
+    return ModuleMembers(
+        classes_=classes_,
+        functions=functions,
+    )
+
+
+def _merge_module_members(
+    module_members: Sequence[ModuleMembers],
+) -> ModuleMembers:
+    """Merge module members."""
+    classes_: List[ClassInfo] = []
+    functions: List[FunctionInfo] = []
+    for module in module_members:
+        classes_.extend(module["classes_"])
+        functions.extend(module["functions"])
+
+    return ModuleMembers(
+        classes_=classes_,
+        functions=functions,
+    )
+
+
+def _load_package_modules(
+    package_directory: Union[str, Path]
+) -> Dict[str, ModuleMembers]:
+    """Recursively load modules of a package based on the file system.
+
+    Traversal based on the file system makes it easy to determine which
+    of the modules/packages are part of the package vs. 3rd party or built-in.
+
+    Parameters:
+        package_directory: Path to the package directory.
+
+    Returns:
+        list: A list of loaded module objects.
+    """
+    package_path = (
+        Path(package_directory)
+        if isinstance(package_directory, str)
+        else package_directory
+    )
+    modules_by_namespace = {}
+
+    package_name = package_path.name
+
+    for file_path in package_path.rglob("*.py"):
+        if file_path.name.startswith("_"):
+            continue
+
+        relative_module_name = file_path.relative_to(package_path)
+
+        # Skip if any module part starts with an underscore
+        if any(part.startswith("_") for part in relative_module_name.parts):
+            continue
+
+        # Get the full namespace of the module
+        namespace = str(relative_module_name).replace(".py", "").replace("/", ".")
+        # Keep only the top level namespace
+        top_namespace = namespace.split(".")[0]
+
+        try:
+            module_members = _load_module_members(
+                f"{package_name}.{namespace}", namespace
+            )
+            # Merge module members if the namespace already exists
+            if top_namespace in modules_by_namespace:
+                existing_module_members = modules_by_namespace[top_namespace]
+                _module_members = _merge_module_members(
+                    [existing_module_members, module_members]
+                )
+            else:
+                _module_members = module_members
+
+            modules_by_namespace[top_namespace] = _module_members
+
+        except ImportError as e:
+            print(f"Error: Unable to import module '{namespace}' with error: {e}")
+
+    return modules_by_namespace
+
+
+def _construct_doc(pkg: str, members_by_namespace: Dict[str, ModuleMembers]) -> str:
+    """Construct the contents of the reference.rst file for the given package.
+
+    Args:
+        pkg: The package name
+        members_by_namespace: The members of the package, dict organized by top level
+                              module contains a list of classes and functions
+                              inside of the top level namespace.
+
+    Returns:
+        The contents of the reference.rst file.
+    """
+    full_doc = f"""\
+=======================
+``{pkg}`` API Reference
+=======================
+
+"""
+    namespaces = sorted(members_by_namespace)
+
+    for module in namespaces:
+        _members = members_by_namespace[module]
+        classes = _members["classes_"]
+        functions = _members["functions"]
+        if not (classes or functions):
+            continue
+        section = f":mod:`{pkg}.{module}`"
+        underline = "=" * (len(section) + 1)
+        full_doc += f"""\
+{section}
+{underline}
+
+.. automodule:: {pkg}.{module}
+    :no-members:
+    :no-inherited-members:
+
+"""
+
+        if classes:
+            full_doc += f"""\
+Classes
+--------------
+.. currentmodule:: {pkg}
+
+.. autosummary::
+    :toctree: {module}
+"""
+
+            for class_ in sorted(classes, key=lambda c: c["qualified_name"]):
+                if not class_["is_public"]:
+                    continue
+
+                if class_["kind"] == "TypedDict":
+                    template = "typeddict.rst"
+                elif class_["kind"] == "enum":
+                    template = "enum.rst"
+                elif class_["kind"] == "Pydantic":
+                    template = "pydantic.rst"
+                else:
+                    template = "class.rst"
+
+                full_doc += f"""\
+    :template: {template}
+    
+    {class_["qualified_name"]}
+    
+"""
+
+        if functions:
+            _functions = [f["qualified_name"] for f in functions if f["is_public"]]
+            fstring = "\n    ".join(sorted(_functions))
+            full_doc += f"""\
+Functions
+--------------
+.. currentmodule:: {pkg}
+
+.. autosummary::
+    :toctree: {module}
+    :template: function.rst
+
+    {fstring}
+
+"""
+    return full_doc
+
+
+def main() -> None:
+    """Generate the reference.rst file for each package."""
+    lc_members = _load_package_modules(PKG_DIR)
+    lc_doc = ".. _api_reference:\n\n" + _construct_doc("langchain", lc_members)
+    with open(WRITE_FILE, "w") as f:
+        f.write(lc_doc)
+    exp_members = _load_package_modules(EXP_DIR)
+    exp_doc = ".. _experimental_api_reference:\n\n" + _construct_doc(
+        "langchain_experimental", exp_members
+    )
+    with open(EXP_WRITE_FILE, "w") as f:
+        f.write(exp_doc)
+
+
+if __name__ == "__main__":
+    main()

docs/api_reference/index.rst

@@ -0,0 +1,8 @@
+=============
+LangChain API
+=============
+
+.. toctree::
+    :maxdepth: 2
+
+    api_reference.rst

docs/api_reference/requirements.txt

@@ -1,9 +1,11 @@
+-e libs/langchain
+-e libs/experimental
+pydantic<2
 autodoc_pydantic==1.8.0
 myst_parser
 nbsphinx==0.8.9
 sphinx==4.5.0
 sphinx-autobuild==2021.3.14
-sphinx_book_theme
 sphinx_rtd_theme==1.0.0
 sphinx-typlog-theme==0.8.0
 sphinx-panels

docs/api_reference/templates/COPYRIGHT.txt

@@ -0,0 +1,27 @@
+Copyright (c) 2007-2023 The scikit-learn developers.
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+* Redistributions of source code must retain the above copyright notice, this
+  list of conditions and the following disclaimer.
+
+* Redistributions in binary form must reproduce the above copyright notice,
+  this list of conditions and the following disclaimer in the documentation
+  and/or other materials provided with the distribution.
+
+* Neither the name of the copyright holder nor the names of its
+  contributors may be used to endorse or promote products derived from
+  this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

docs/api_reference/templates/class.rst

@@ -0,0 +1,36 @@
+:mod:`{{module}}`.{{objname}}
+{{ underline }}==============
+
+.. currentmodule:: {{ module }}
+
+.. autoclass:: {{ objname }}
+
+   {% block attributes %}
+   {% if attributes %}
+   .. rubric:: {{ _('Attributes') }}
+
+   .. autosummary::
+   {% for item in attributes %}
+      ~{{ name }}.{{ item }}
+   {%- endfor %}
+   {% endif %}
+   {% endblock %}
+
+   {% block methods %}
+   {% if methods %}
+   .. rubric:: {{ _('Methods') }}
+
+   .. autosummary::
+   {% for item in methods %}
+      ~{{ name }}.{{ item }}
+   {%- endfor %}
+
+   {% for item in methods %}
+   .. automethod:: {{ name }}.{{ item }}
+   {%- endfor %}
+
+   {% endif %}
+   {% endblock %}
+
+
+.. example_links:: {{ objname }}

docs/api_reference/templates/enum.rst

@@ -0,0 +1,14 @@
+:mod:`{{module}}`.{{objname}}
+{{ underline }}==============
+
+.. currentmodule:: {{ module }}
+
+.. autoclass:: {{ objname }}
+
+    {% block attributes %}
+    {% for item in attributes %}
+    .. autoattribute:: {{ item }}
+    {% endfor %}
+    {% endblock %}
+
+.. example_links:: {{ objname }}

docs/api_reference/templates/function.rst

@@ -0,0 +1,8 @@
+:mod:`{{module}}`.{{objname}}
+{{ underline }}==============
+
+.. currentmodule:: {{ module }}
+
+.. autofunction:: {{ objname }}
+
+.. example_links:: {{ objname }}

docs/api_reference/templates/pydantic.rst

@@ -0,0 +1,22 @@
+:mod:`{{module}}`.{{objname}}
+{{ underline }}==============
+
+.. currentmodule:: {{ module }}
+
+.. autopydantic_model:: {{ objname }}
+    :model-show-json: False
+    :model-show-config-summary: False
+    :model-show-validator-members: False
+    :model-show-field-summary: False
+    :field-signature-prefix: param
+    :members:
+    :undoc-members:
+    :inherited-members:
+    :member-order: groupwise
+    :show-inheritance: True
+    :special-members: __call__
+
+    {% block attributes %}
+    {% endblock %}
+
+.. example_links:: {{ objname }}

docs/api_reference/templates/redirects.html

@@ -0,0 +1,16 @@
+{% set redirect = pathto(redirects[pagename]) %}
+<!DOCTYPE html>
+<html>
+  <head>
+    <meta charset="utf-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <meta http-equiv="Refresh" content="0; url={{ redirect }}" />
+    <meta name="robots" content="follow, index">
+    <meta name="Description" content="Python API reference for LangChain.">
+    <link rel="canonical" href="{{ redirect }}" />
+    <title>LangChain Python API Reference Documentation.</title>
+  </head>
+  <body>
+    <p>You will be automatically redirected to the <a href="{{ redirect }}">new location of this page</a>.</p>
+  </body>
+</html>

docs/api_reference/templates/typeddict.rst

@@ -0,0 +1,14 @@
+:mod:`{{module}}`.{{objname}}
+{{ underline }}==============
+
+.. currentmodule:: {{ module }}
+
+.. autoclass:: {{ objname }}
+
+    {% block attributes %}
+   {% for item in attributes %}
+  .. autoattribute:: {{ item }}
+   {% endfor %}
+   {% endblock %}
+
+.. example_links:: {{ objname }}

docs/api_reference/themes/COPYRIGHT.txt

@@ -0,0 +1,27 @@
+Copyright (c) 2007-2023 The scikit-learn developers.
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+* Redistributions of source code must retain the above copyright notice, this
+  list of conditions and the following disclaimer.
+
+* Redistributions in binary form must reproduce the above copyright notice,
+  this list of conditions and the following disclaimer in the documentation
+  and/or other materials provided with the distribution.
+
+* Neither the name of the copyright holder nor the names of its
+  contributors may be used to endorse or promote products derived from
+  this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

docs/api_reference/themes/scikit-learn-modern/javascript.html

@@ -0,0 +1,67 @@
+<script>
+$(document).ready(function() {
+    /* Add a [>>>] button on the top-right corner of code samples to hide
+     * the >>> and ... prompts and the output and thus make the code
+     * copyable. */
+    var div = $('.highlight-python .highlight,' +
+                '.highlight-python3 .highlight,' +
+                '.highlight-pycon .highlight,' +
+		'.highlight-default .highlight')
+    var pre = div.find('pre');
+
+    // get the styles from the current theme
+    pre.parent().parent().css('position', 'relative');
+    var hide_text = 'Hide prompts and outputs';
+    var show_text = 'Show prompts and outputs';
+
+    // create and add the button to all the code blocks that contain >>>
+    div.each(function(index) {
+        var jthis = $(this);
+        if (jthis.find('.gp').length > 0) {
+            var button = $('<span class="copybutton">&gt;&gt;&gt;</span>');
+            button.attr('title', hide_text);
+            button.data('hidden', 'false');
+            jthis.prepend(button);
+        }
+        // tracebacks (.gt) contain bare text elements that need to be
+        // wrapped in a span to work with .nextUntil() (see later)
+        jthis.find('pre:has(.gt)').contents().filter(function() {
+            return ((this.nodeType == 3) && (this.data.trim().length > 0));
+        }).wrap('<span>');
+    });
+
+    // define the behavior of the button when it's clicked
+    $('.copybutton').click(function(e){
+        e.preventDefault();
+        var button = $(this);
+        if (button.data('hidden') === 'false') {
+            // hide the code output
+            button.parent().find('.go, .gp, .gt').hide();
+            button.next('pre').find('.gt').nextUntil('.gp, .go').css('visibility', 'hidden');
+            button.css('text-decoration', 'line-through');
+            button.attr('title', show_text);
+            button.data('hidden', 'true');
+        } else {
+            // show the code output
+            button.parent().find('.go, .gp, .gt').show();
+            button.next('pre').find('.gt').nextUntil('.gp, .go').css('visibility', 'visible');
+            button.css('text-decoration', 'none');
+            button.attr('title', hide_text);
+            button.data('hidden', 'false');
+        }
+    });
+
+	/*** Add permalink buttons next to glossary terms ***/
+	$('dl.glossary > dt[id]').append(function() {
+		return ('<a class="headerlink" href="#' +
+			    this.getAttribute('id') +
+			    '" title="Permalink to this term">¶</a>');
+	});
+});
+
+</script>
+{%- if pagename != 'index' and pagename != 'documentation' %}
+    {% if theme_mathjax_path %}
+<script id="MathJax-script" async src="{{ theme_mathjax_path }}"></script>
+    {% endif %}
+{%- endif %}

docs/api_reference/themes/scikit-learn-modern/layout.html

@@ -0,0 +1,142 @@
+{# TEMPLATE VAR SETTINGS #}
+{%- set url_root = pathto('', 1) %}
+{%- if url_root == '#' %}{% set url_root = '' %}{% endif %}
+{%- if not embedded and docstitle %}
+  {%- set titlesuffix = " — "|safe + docstitle|e %}
+{%- else %}
+  {%- set titlesuffix = "" %}
+{%- endif %}
+{%- set lang_attr = 'en' %}
+
+<!DOCTYPE html>
+<!--[if IE 8]><html class="no-js lt-ie9" lang="{{ lang_attr }}" > <![endif]-->
+<!--[if gt IE 8]><!--> <html class="no-js" lang="{{ lang_attr }}" > <!--<![endif]-->
+<head>
+  <meta charset="utf-8">
+  {{ metatags }}
+  <meta name="viewport" content="width=device-width, initial-scale=1.0">
+
+  {% block htmltitle %}
+  <title>{{ title|striptags|e }}{{ titlesuffix }}</title>
+  {% endblock %}
+  <link rel="canonical" href="https://api.python.langchain.com/en/latest/{{pagename}}.html" />
+
+  {% if favicon_url %}
+  <link rel="shortcut icon" href="{{ favicon_url|e }}"/>
+  {% endif %}
+
+  <link rel="stylesheet" href="{{ pathto('_static/css/vendor/bootstrap.min.css', 1) }}" type="text/css" />
+  {%- for css in css_files %}
+    {%- if css|attr("rel") %}
+  <link rel="{{ css.rel }}" href="{{ pathto(css.filename, 1) }}" type="text/css"{% if css.title is not none %} title="{{ css.title }}"{% endif %} />
+    {%- else %}
+  <link rel="stylesheet" href="{{ pathto(css, 1) }}" type="text/css" />
+    {%- endif %}
+  {%- endfor %}
+  <link rel="stylesheet" href="{{ pathto('_static/' + style, 1) }}" type="text/css" />
+<script id="documentation_options" data-url_root="{{ pathto('', 1) }}" src="{{ pathto('_static/documentation_options.js', 1) }}"></script>
+<script src="{{ pathto('_static/jquery.js', 1) }}"></script>
+{%- block extrahead %} {% endblock %}
+</head>
+<body>
+{% include "nav.html" %}
+{%- block content %}
+<div class="d-flex" id="sk-doc-wrapper">
+    <input type="checkbox" name="sk-toggle-checkbox" id="sk-toggle-checkbox">
+    <label id="sk-sidemenu-toggle" class="sk-btn-toggle-toc btn sk-btn-primary" for="sk-toggle-checkbox">Toggle Menu</label>
+    <div id="sk-sidebar-wrapper" class="border-right">
+      <div class="sk-sidebar-toc-wrapper">
+        <div class="btn-group w-100 mb-2" role="group" aria-label="rellinks">
+          {%- if prev %}
+            <a href="{{ prev.link|e }}" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="{{ prev.title|striptags }}">Prev</a>
+          {%- else %}
+            <a href="#" role="button" class="btn sk-btn-rellink py-1 disabled"">Prev</a>
+          {%- endif %}
+          {%- if parents -%}
+            <a href="{{ parents[-1].link|e }}" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="{{ parents[-1].title|striptags }}">Up</a>
+          {%- else %}
+            <a href="#" role="button" class="btn sk-btn-rellink disabled py-1">Up</a>
+          {%- endif %}
+          {%- if next %}
+            <a href="{{ next.link|e }}" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="{{ next.title|striptags }}">Next</a>
+          {%- else %}
+            <a href="#" role="button" class="btn sk-btn-rellink py-1 disabled"">Next</a>
+          {%- endif %}
+        </div>
+        {%- if pagename != "install" %}
+        <div class="alert alert-warning p-1 mb-2" role="alert">
+          <p class="text-center mb-0">
+          <strong>LangChain {{ release }}</strong><br/>
+          </p>
+        </div>
+        {%- endif %}
+            {%- if meta and meta['parenttoc']|tobool %}
+            <div class="sk-sidebar-toc">
+            {% set nav = get_nav_object(maxdepth=3, collapse=True, numbered=True) %}
+              <ul>
+              {% for main_nav_item in nav %}
+              {% if main_nav_item.active %}
+              <li>
+                <a href="{{ main_nav_item.url }}" class="sk-toc-active">{{ main_nav_item.title }}</a>
+              </li>
+              <ul>
+              {% for nav_item in main_nav_item.children %}
+                <li>
+                  <a href="{{ nav_item.url }}" class="{% if nav_item.active %}sk-toc-active{% endif %}">{{ nav_item.title }}</a>
+                  {% if nav_item.children %}
+                  <ul>
+                    {% for inner_child in nav_item.children %}
+                      <li class="sk-toctree-l3">
+                        <a href="{{ inner_child.url }}">{{ inner_child.title }}</a>
+                      </li>
+                    {% endfor %}
+                  </ul>
+                  {% endif %}
+                </li>
+              {% endfor %}
+              </ul>
+              {% endif %}
+              {% endfor %}
+              </ul>
+            </div>
+            {%- elif meta and meta['globalsidebartoc']|tobool %}
+            <div class="sk-sidebar-toc sk-sidebar-global-toc">
+              {{ toctree(maxdepth=2, titles_only=True) }}
+            </div>
+            {%- else %}
+            <div class="sk-sidebar-toc">
+              {{ toc }}
+            </div>
+            {%- endif %}
+      </div>
+    </div>
+    <div id="sk-page-content-wrapper">
+      <div class="sk-page-content container-fluid body px-md-3" role="main">
+        {% block body %}{% endblock %}
+      </div>
+    <div class="container">
+      <footer class="sk-content-footer">
+        {%- if pagename != 'index' %}
+        {%- if show_copyright %}
+          {%- if hasdoc('copyright') %}
+            {% trans path=pathto('copyright'), copyright=copyright|e %}&copy; {{ copyright }}.{% endtrans %}
+          {%- else %}
+            {% trans copyright=copyright|e %}&copy; {{ copyright }}.{% endtrans %}
+          {%- endif %}
+        {%- endif %}
+        {%- if last_updated %}
+          {% trans last_updated=last_updated|e %}Last updated on {{ last_updated }}.{% endtrans %}
+        {%- endif %}
+        {%- if show_source and has_source and sourcename %}
+          <a href="{{ pathto('_sources/' + sourcename, true)|e }}" rel="nofollow">{{ _('Show this page source') }}</a>
+        {%- endif %}
+        {%- endif %}
+      </footer>
+    </div>
+  </div>
+</div>
+{%- endblock %}
+<script src="{{ pathto('_static/js/vendor/bootstrap.min.js', 1) }}"></script>
+{% include "javascript.html" %}
+</body>
+</html>

docs/api_reference/themes/scikit-learn-modern/nav.html

@@ -0,0 +1,61 @@
+{%- if pagename != 'index' and pagename != 'documentation' %}
+  {%- set nav_bar_class = "sk-docs-navbar" %}
+  {%- set top_container_cls = "sk-docs-container" %}
+{%- else %}
+  {%- set nav_bar_class = "sk-landing-navbar" %}
+  {%- set top_container_cls = "sk-landing-container" %}
+{%- endif %}
+
+<nav id="navbar" class="{{ nav_bar_class }} navbar navbar-expand-md navbar-light bg-light py-0">
+  <div class="container-fluid {{ top_container_cls }} px-0">
+    {%- if logo_url %}
+      <a class="navbar-brand py-0" href="{{ pathto('index') }}">
+        <img
+          class="sk-brand-img"
+          src="{{ logo_url|e }}"
+          alt="logo"/>
+      </a>
+    {%- endif %}
+    <button
+      id="sk-navbar-toggler"
+      class="navbar-toggler"
+      type="button"
+      data-toggle="collapse"
+      data-target="#navbarSupportedContent"
+      aria-controls="navbarSupportedContent"
+      aria-expanded="false"
+      aria-label="Toggle navigation"
+    >
+      <span class="navbar-toggler-icon"></span>
+    </button>
+
+    <div class="sk-navbar-collapse collapse navbar-collapse" id="navbarSupportedContent">
+      <ul class="navbar-nav mr-auto">
+        <li class="nav-item">
+          <a class="sk-nav-link nav-link" href="{{ pathto('api_reference') }}">API</a>
+        </li>
+        <li class="nav-item">
+          <a class="sk-nav-link nav-link" href="{{ pathto('experimental_api_reference') }}">Experimental</a>
+        </li>
+        <li class="nav-item">
+          <a class="sk-nav-link nav-link" target="_blank" rel="noopener noreferrer" href="https://python.langchain.com/">Python Docs</a>
+        </li>
+        {%- for title, link, link_attrs in drop_down_navigation %}
+        <li class="nav-item">
+          <a class="sk-nav-link nav-link nav-more-item-mobile-items" href="{{ link }}" {{ link_attrs }}>{{ title }}</a>
+        </li>
+        {%- endfor %}
+      </ul>
+      {%- if pagename != "search"%}
+      <div id="searchbox" role="search">
+          <div class="searchformwrapper">
+          <form class="search" action="{{ pathto('search') }}" method="get">
+            <input class="sk-search-text-input" type="text" name="q" aria-labelledby="searchlabel" />
+            <input class="sk-search-text-btn" type="submit" value="{{ _('Go') }}" />
+          </form>
+          </div>
+      </div>
+      {%- endif %}
+    </div>
+  </div>
+</nav>

docs/api_reference/themes/scikit-learn-modern/search.html

@@ -0,0 +1,16 @@
+{%- extends "basic/search.html" %}
+{% block extrahead %}
+  <script type="text/javascript" src="{{ pathto('_static/underscore.js', 1) }}"></script>
+  <script type="text/javascript" src="{{ pathto('searchindex.js', 1) }}" defer></script>
+  <script type="text/javascript" src="{{ pathto('_static/doctools.js', 1) }}"></script>
+  <script type="text/javascript" src="{{ pathto('_static/language_data.js', 1) }}"></script>
+  <script type="text/javascript" src="{{ pathto('_static/searchtools.js', 1) }}"></script>
+  <!-- <script type="text/javascript" src="{{ pathto('_static/sphinx_highlight.js', 1) }}"></script> -->
+  <script type="text/javascript">
+    $(document).ready(function() {
+      if (!Search.out) {
+        Search.init();
+      }
+    });
+  </script>
+{% endblock %}

docs/api_reference/themes/scikit-learn-modern/theme.conf

@@ -0,0 +1,8 @@
+[theme]
+inherit = basic
+pygments_style = default
+stylesheet = css/theme.css
+
+[options]
+link_to_live_contributing_page = false
+mathjax_path =

docs/conf.py

@@ -1,112 +0,0 @@
-"""Configuration file for the Sphinx documentation builder."""
-# Configuration file for the Sphinx documentation builder.
-#
-# This file only contains a selection of the most common options. For a full
-# list see the documentation:
-# https://www.sphinx-doc.org/en/master/usage/configuration.html
-
-# -- Path setup --------------------------------------------------------------
-
-# If extensions (or modules to document with autodoc) are in another directory,
-# add these directories to sys.path here. If the directory is relative to the
-# documentation root, use os.path.abspath to make it absolute, like shown here.
-#
-# import os
-# import sys
-# sys.path.insert(0, os.path.abspath('.'))
-
-import toml
-
-with open("../pyproject.toml") as f:
-    data = toml.load(f)
-
-# -- Project information -----------------------------------------------------
-
-project = "🦜🔗 LangChain"
-copyright = "2023, Harrison Chase"
-author = "Harrison Chase"
-
-version = data["tool"]["poetry"]["version"]
-release = version
-
-html_title = project + " " + version
-html_last_updated_fmt = "%b %d, %Y"
-
-
-# -- General configuration ---------------------------------------------------
-
-# Add any Sphinx extension module names here, as strings. They can be
-# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
-# ones.
-extensions = [
-    "sphinx.ext.autodoc",
-    "sphinx.ext.autodoc.typehints",
-    "sphinx.ext.autosummary",
-    "sphinx.ext.napoleon",
-    "sphinx.ext.viewcode",
-    "sphinxcontrib.autodoc_pydantic",
-    "myst_nb",
-    "sphinx_copybutton",
-    "sphinx_panels",
-    "IPython.sphinxext.ipython_console_highlighting",
-]
-source_suffix = [".ipynb", ".html", ".md", ".rst"]
-
-autodoc_pydantic_model_show_json = False
-autodoc_pydantic_field_list_validators = False
-autodoc_pydantic_config_members = False
-autodoc_pydantic_model_show_config_summary = False
-autodoc_pydantic_model_show_validator_members = False
-autodoc_pydantic_model_show_field_summary = False
-autodoc_pydantic_model_members = False
-autodoc_pydantic_model_undoc_members = False
-# autodoc_typehints = "signature"
-# autodoc_typehints = "description"
-
-# Add any paths that contain templates here, relative to this directory.
-templates_path = ["_templates"]
-
-# List of patterns, relative to source directory, that match files and
-# directories to ignore when looking for source files.
-# This pattern also affects html_static_path and html_extra_path.
-exclude_patterns = ["_build", "Thumbs.db", ".DS_Store"]
-
-
-# -- Options for HTML output -------------------------------------------------
-
-# The theme to use for HTML and HTML Help pages.  See the documentation for
-# a list of builtin themes.
-#
-html_theme = "sphinx_book_theme"
-
-html_theme_options = {
-    "path_to_docs": "docs",
-    "repository_url": "https://github.com/hwchase17/langchain",
-    "use_repository_button": True,
-}
-
-html_context = {
-    "display_github": True,  # Integrate GitHub
-    "github_user": "hwchase17",  # Username
-    "github_repo": "langchain",  # Repo name
-    "github_version": "master",  # Version
-    "conf_py_path": "/docs/",  # Path in the checkout to the docs root
-}
-
-# Add any paths that contain custom static files (such as style sheets) here,
-# relative to this directory. They are copied after the builtin static files,
-# so a file named "default.css" will overwrite the builtin "default.css".
-html_static_path = ["_static"]
-
-# These paths are either relative to html_static_path
-# or fully qualified paths (eg. https://...)
-html_css_files = [
-    "css/custom.css",
-]
-
-html_js_files = [
-    "js/mendablesearch.js",
-]
-
-nb_execution_mode = "off"
-myst_enable_extensions = ["colon_fence"]

docs/deployments.md

@@ -1,51 +0,0 @@
-# Deployments
-
-So you've made a really cool chain - now what? How do you deploy it and make it easily sharable with the world?
-
-This section covers several options for that.
-Note that these are meant as quick deployment options for prototypes and demos, and not for production systems.
-If you are looking for help with deployment of a production system, please contact us directly.
-
-What follows is a list of template GitHub repositories aimed that are intended to be
-very easy to fork and modify to use your chain.
-This is far from an exhaustive list of options, and we are EXTREMELY open to contributions here.
-
-## [Streamlit](https://github.com/hwchase17/langchain-streamlit-template)
-
-This repo serves as a template for how to deploy a LangChain with Streamlit.
-It implements a chatbot interface.
-It also contains instructions for how to deploy this app on the Streamlit platform.
-
-## [Gradio (on Hugging Face)](https://github.com/hwchase17/langchain-gradio-template)
-
-This repo serves as a template for how deploy a LangChain with Gradio.
-It implements a chatbot interface, with a "Bring-Your-Own-Token" approach (nice for not wracking up big bills).
-It also contains instructions for how to deploy this app on the Hugging Face platform.
-This is heavily influenced by James Weaver's [excellent examples](https://huggingface.co/JavaFXpert).
-
-## [Beam](https://github.com/slai-labs/get-beam/tree/main/examples/langchain-question-answering)
-
-This repo serves as a template for how deploy a LangChain with [Beam](https://beam.cloud).
-
-It implements a Question Answering app and contains instructions for deploying the app as a serverless REST API.
-
-## [Vercel](https://github.com/homanp/vercel-langchain)
-
-A minimal example on how to run LangChain on Vercel using Flask.
-
-## [Digitalocean App Platform](https://github.com/homanp/digitalocean-langchain)
-
-A minimal example on how to deploy LangChain to DigitalOcean App Platform.
-
-## [SteamShip](https://github.com/steamship-core/steamship-langchain/)
-
-This repository contains LangChain adapters for Steamship, enabling LangChain developers to rapidly deploy their apps on Steamship.
-This includes: production ready endpoints, horizontal scaling across dependencies, persistant storage of app state, multi-tenancy support, etc.
-
-## [Langchain-serve](https://github.com/jina-ai/langchain-serve)
-
-This repository allows users to serve local chains and agents as RESTful, gRPC, or Websocket APIs thanks to [Jina](https://docs.jina.ai/). Deploy your chains & agents with ease and enjoy independent scaling, serverless and autoscaling APIs, as well as a Streamlit playground on Jina AI Cloud.
-
-## [BentoML](https://github.com/ssheng/BentoChain)
-
-This repository provides an example of how to deploy a LangChain application with [BentoML](https://github.com/bentoml/BentoML). BentoML is a framework that enables the containerization of machine learning applications as standard OCI images. BentoML also allows for the automatic generation of OpenAPI and gRPC endpoints. With BentoML, you can integrate models from all popular ML frameworks and deploy them as microservices running on the most optimal hardware and scaling independently.

docs/docs_skeleton/.gitignore

@@ -0,0 +1,7 @@
+.yarn/
+
+node_modules/
+
+.docusaurus
+.cache-loader
+docs/api

docs/docs_skeleton/README.md

@@ -0,0 +1,49 @@
+# Website
+
+This website is built using [Docusaurus 2](https://docusaurus.io/), a modern static website generator.
+
+### Installation
+
+```
+$ yarn
+```
+
+### Local Development
+
+```
+$ yarn start
+```
+
+This command starts a local development server and opens up a browser window. Most changes are reflected live without having to restart the server.
+
+### Build
+
+```
+$ yarn build
+```
+
+This command generates static content into the `build` directory and can be served using any static contents hosting service.
+
+### Deployment
+
+Using SSH:
+
+```
+$ USE_SSH=true yarn deploy
+```
+
+Not using SSH:
+
+```
+$ GIT_USER=<Your GitHub username> yarn deploy
+```
+
+If you are using GitHub pages for hosting, this command is a convenient way to build the website and push to the `gh-pages` branch.
+
+### Continuous Integration
+
+Some common defaults for linting/formatting have been set for you. If you integrate your project with an open source Continuous Integration system (e.g. Travis CI, CircleCI), you may check for issues using the following command.
+
+```
+$ yarn ci
+```

docs/docs_skeleton/babel.config.js

@@ -0,0 +1,12 @@
+/**
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
+ *
+ * This source code is licensed under the MIT license found in the
+ * LICENSE file in the root directory of this source tree.
+ *
+ * @format
+ */
+
+module.exports = {
+  presets: [require.resolve("@docusaurus/core/lib/babel/preset")],
+};

docs/docs_skeleton/code-block-loader.js

@@ -0,0 +1,76 @@
+/* eslint-disable prefer-template */
+/* eslint-disable no-param-reassign */
+// eslint-disable-next-line import/no-extraneous-dependencies
+const babel = require("@babel/core");
+const path = require("path");
+const fs = require("fs");
+
+/**
+ *
+ * @param {string|Buffer} content Content of the resource file
+ * @param {object} [map] SourceMap data consumable by https://github.com/mozilla/source-map
+ * @param {any} [meta] Meta data, could be anything
+ */
+async function webpackLoader(content, map, meta) {
+  const cb = this.async();
+
+  if (!this.resourcePath.endsWith(".ts")) {
+    cb(null, JSON.stringify({ content, imports: [] }), map, meta);
+    return;
+  }
+
+  try {
+    const result = await babel.parseAsync(content, {
+      sourceType: "module",
+      filename: this.resourcePath,
+    });
+
+    const imports = [];
+
+    result.program.body.forEach((node) => {
+      if (node.type === "ImportDeclaration") {
+        const source = node.source.value;
+
+        if (!source.startsWith("langchain")) {
+          return;
+        }
+
+        node.specifiers.forEach((specifier) => {
+          if (specifier.type === "ImportSpecifier") {
+            const local = specifier.local.name;
+            const imported = specifier.imported.name;
+            imports.push({ local, imported, source });
+          } else {
+            throw new Error("Unsupported import type");
+          }
+        });
+      }
+    });
+
+    imports.forEach((imp) => {
+      const { imported, source } = imp;
+      const moduleName = source.split("/").slice(1).join("_");
+      const docsPath = path.resolve(__dirname, "docs", "api", moduleName);
+      const available = fs.readdirSync(docsPath, { withFileTypes: true });
+      const found = available.find(
+        (dirent) =>
+          dirent.isDirectory() &&
+          fs.existsSync(path.resolve(docsPath, dirent.name, imported + ".md"))
+      );
+      if (found) {
+        imp.docs =
+          "/" + path.join("docs", "api", moduleName, found.name, imported);
+      } else {
+        throw new Error(
+          `Could not find docs for ${source}.${imported} in docs/api/`
+        );
+      }
+    });
+
+    cb(null, JSON.stringify({ content, imports }), map, meta);
+  } catch (err) {
+    cb(err);
+  }
+}
+
+module.exports = webpackLoader;

docs/docs_skeleton/docs/_static/css/custom.css

@@ -0,0 +1,21 @@
+pre {
+  white-space: break-spaces;
+}
+
+@media (min-width: 1200px) {
+  .container,
+  .container-lg,
+  .container-md,
+  .container-sm,
+  .container-xl {
+    max-width: 2560px !important;
+  }
+}
+
+#my-component-root *, #headlessui-portal-root * {
+  z-index: 10000;
+}
+
+.content-container p {
+    margin: revert;
+}

docs/docs_skeleton/docs/_static/js/mendablesearch.js

@@ -30,10 +30,7 @@ document.addEventListener('DOMContentLoaded', () => {
     const icon = React.createElement('p', {
       style: { color: '#ffffff', fontSize: '22px',width: '48px', height: '48px', margin: '0px', padding: '0px', display: 'flex', alignItems: 'center', justifyContent: 'center', textAlign: 'center' },
     }, [iconSpan1, iconSpan2]);
-
     
-    
-
     const mendableFloatingButton = React.createElement(
       MendableFloatingButton,
       {
@@ -42,6 +39,7 @@ document.addEventListener('DOMContentLoaded', () => {
         anon_key: '82842b36-3ea6-49b2-9fb8-52cfc4bde6bf', // Mendable Search Public ANON key, ok to be public
         messageSettings: {
           openSourcesInNewTab: false,
+          prettySources: true // Prettify the sources displayed now
         },
         icon: icon,
       }
@@ -52,7 +50,7 @@ document.addEventListener('DOMContentLoaded', () => {
 
   loadScript('https://unpkg.com/react@17/umd/react.production.min.js', () => {
     loadScript('https://unpkg.com/react-dom@17/umd/react-dom.production.min.js', () => {
-      loadScript('https://unpkg.com/@mendable/search@0.0.83/dist/umd/mendable.min.js', initializeMendable);
+      loadScript('https://unpkg.com/@mendable/search@0.0.102/dist/umd/mendable.min.js', initializeMendable);
     });
   });
 });

docs/docs_skeleton/docs/community.md

@@ -0,0 +1,54 @@
+# Community navigator
+
+Hi! Thanks for being here. We’re lucky to have a community of so many passionate developers building with LangChain–we have so much to teach and learn from each other. Community members contribute code, host meetups, write blog posts, amplify each other’s work, become each other's customers and collaborators, and so much more.
+
+Whether you’re new to LangChain, looking to go deeper, or just want to get more exposure to the world of building with LLMs, this page can point you in the right direction. 
+
+- **🦜 Contribute to LangChain**
+
+- **🌍 Meetups, Events, and Hackathons**
+
+- **📣 Help Us Amplify Your Work**
+
+- **💬 Stay in the loop**
+
+
+# 🦜 Contribute to LangChain
+
+LangChain is the product of over 5,000+ contributions by 1,500+ contributors, and there is ******still****** so much to do together. Here are some ways to get involved:
+
+- **[Open a pull request](https://github.com/langchain-ai/langchain/issues):** we’d appreciate all forms of contributions–new features, infrastructure improvements, better documentation, bug fixes, etc. If you have an improvement or an idea, we’d love to work on it with you.
+- **[Read our contributor guidelines:](https://github.com/langchain-ai/langchain/blob/bbd22b9b761389a5e40fc45b0570e1830aabb707/.github/CONTRIBUTING.md)** We ask contributors to follow a ["fork and pull request"](https://docs.github.com/en/get-started/quickstart/contributing-to-projects) workflow, run a few local checks for formatting, linting, and testing before submitting, and follow certain documentation and testing conventions.
+    - **First time contributor?** [Try one of these PRs with the “good first issue” tag](https://github.com/langchain-ai/langchain/contribute).
+- **Become an expert:** our experts help the community by answering product questions in Discord. If that’s a role you’d like to play, we’d be so grateful! (And we have some special experts-only goodies/perks we can tell you more about). Send us an email to introduce yourself at hello@langchain.dev and we’ll take it from there!
+- **Integrate with LangChain:** if your product integrates with LangChain–or aspires to–we want to help make sure the experience is as smooth as possible for you and end users. Send us an email at hello@langchain.dev and tell us what you’re working on.
+    - **Become an Integration Maintainer:** Partner with our team to ensure your integration stays up-to-date and talk directly with users (and answer their inquiries) in our Discord. Introduce yourself at hello@langchain.dev if you’d like to explore this role.
+
+
+# 🌍 Meetups, Events, and Hackathons
+
+One of our favorite things about working in AI is how much enthusiasm there is for building together. We want to help make that as easy and impactful for you as possible! 
+- **Find a meetup, hackathon, or webinar:** you can find the one for you on our [global events calendar](https://mirror-feeling-d80.notion.site/0bc81da76a184297b86ca8fc782ee9a3?v=0d80342540df465396546976a50cfb3f).  
+    - **Submit an event to our calendar:** email us at events@langchain.dev with a link to your event page! We can also help you spread the word with our local communities.
+- **Host a meetup:** If you want to bring a group of builders together, we want to help! We can publicize your event on our event calendar/Twitter, share with our local communities in Discord, send swag, or potentially hook you up with a sponsor. Email us at events@langchain.dev to tell us about your event!
+- **Become a meetup sponsor:** we often hear from groups of builders that want to get together, but are blocked or limited on some dimension (space to host, budget for snacks, prizes to distribute, etc.). If you’d like to help, send us an email to events@langchain.dev we can share more about how it works!
+- **Speak at an event:** meetup hosts are always looking for great speakers, presenters, and panelists. If you’d like to do that at an event, send us an email to hello@langchain.dev with more information about yourself, what you want to talk about, and what city you’re based in and we’ll try to match you with an upcoming event!
+- **Tell us about your LLM community:** If you host or participate in a community that would welcome support from LangChain and/or our team, send us an email at hello@langchain.dev and let us know how we can help.
+
+# 📣 Help Us Amplify Your Work
+
+If you’re working on something you’re proud of, and think the LangChain community would benefit from knowing about it, we want to help you show it off.
+
+- **Post about your work and mention us:** we love hanging out on Twitter to see what people in the space are talking about and working on. If you tag [@langchainai](https://twitter.com/LangChainAI), we’ll almost certainly see it and can show you some love.
+- **Publish something on our blog:** if you’re writing about your experience building with LangChain, we’d love to post (or crosspost) it on our blog! E-mail hello@langchain.dev with a draft of your post! Or even an idea for something you want to write about.
+- **Get your product onto our [integrations hub](https://integrations.langchain.com/):** Many developers take advantage of our seamless integrations with other products, and come to our integrations hub to find out who those are. If you want to get your product up there, tell us about it (and how it works with LangChain) at hello@langchain.dev.
+
+# ☀️ Stay in the loop
+
+Here’s where our team hangs out, talks shop, spotlights cool work, and shares what we’re up to. We’d love to see you there too.
+
+- **[Twitter](https://twitter.com/LangChainAI):** we post about what we’re working on and what cool things we’re seeing in the space. If you tag @langchainai in your post, we’ll almost certainly see it, and can show you some love!
+- **[Discord](https://discord.gg/6adMQxSpJS):** connect with >30k developers who are building with LangChain
+- **[GitHub](https://github.com/langchain-ai/langchain):** open pull requests, contribute to a discussion, and/or contribute
+- **[Subscribe to our bi-weekly Release Notes](https://6w1pwbss0py.typeform.com/to/KjZB1auB):** a twice/month email roundup of the coolest things going on in our orbit
+- **Slack:** if you’re building an application in production at your company, we’d love to get into a Slack channel together. Fill out [this form](https://airtable.com/appwQzlErAS2qiP0L/shrGtGaVBVAz7NcV2) and we’ll get in touch about setting one up.

docs/docs_skeleton/docs/expression_language/index.mdx

@@ -0,0 +1,14 @@
+---
+sidebar_class_name: hidden
+---
+
+# LangChain Expression Language (LCEL)
+
+LangChain Expression Language or LCEL is a declarative way to easily compose chains together.
+Any chain constructed this way will automatically have full sync, async, and streaming support.
+
+#### [Interface](/docs/expression_language/interface)
+The base interface shared by all LCEL objects
+
+#### [Cookbook](/docs/expression_language/cookbook)
+Examples of common LCEL usage patterns

docs/docs_skeleton/docs/get_started/installation.mdx

@@ -0,0 +1,5 @@
+# Installation
+
+import Installation from "@snippets/get_started/installation.mdx"
+
+<Installation/>

docs/docs_skeleton/docs/get_started/introduction.mdx

@@ -0,0 +1,64 @@
+---
+sidebar_position: 0
+---
+
+# Introduction
+
+**LangChain** is a framework for developing applications powered by language models. It enables applications that are:
+- **Data-aware**: connect a language model to other sources of data
+- **Agentic**: allow a language model to interact with its environment
+
+The main value props of LangChain are:
+1. **Components**: abstractions for working with language models, along with a collection of implementations for each abstraction. Components are modular and easy-to-use, whether you are using the rest of the LangChain framework or not
+2. **Off-the-shelf chains**: a structured assembly of components for accomplishing specific higher-level tasks
+
+Off-the-shelf chains make it easy to get started. For more complex applications and nuanced use-cases, components make it easy to customize existing chains or build new ones.
+
+## Get started
+
+[Here’s](/docs/get_started/installation.html) how to install LangChain, set up your environment, and start building.
+
+We recommend following our [Quickstart](/docs/get_started/quickstart.html) guide to familiarize yourself with the framework by building your first LangChain application.
+
+_**Note**: These docs are for the LangChain [Python package](https://github.com/hwchase17/langchain). For documentation on [LangChain.js](https://github.com/hwchase17/langchainjs), the JS/TS version, [head here](https://js.langchain.com/docs)._
+
+## Modules
+
+LangChain provides standard, extendable interfaces and external integrations for the following modules, listed from least to most complex:
+
+#### [Model I/O](/docs/modules/model_io/)
+Interface with language models
+#### [Retrieval](/docs/modules/data_connection/)
+Interface with application-specific data
+#### [Chains](/docs/modules/chains/)
+Construct sequences of calls
+#### [Agents](/docs/modules/agents/)
+Let chains choose which tools to use given high-level directives
+#### [Memory](/docs/modules/memory/)
+Persist application state between runs of a chain
+#### [Callbacks](/docs/modules/callbacks/)
+Log and stream intermediate steps of any chain
+
+## Examples, ecosystem, and resources
+### [Use cases](/docs/use_cases/)
+Walkthroughs and best-practices for common end-to-end use cases, like:
+- [Chatbots](/docs/use_cases/chatbots)
+- [Answering questions using sources](/docs/use_cases/question_answering/)
+- [Analyzing structured data](/docs/use_cases/sql)
+- and much more...
+
+### [Guides](/docs/guides/)
+Learn best practices for developing with LangChain.
+
+### [Ecosystem](/docs/ecosystem/)
+LangChain is part of a rich ecosystem of tools that integrate with our framework and build on top of it. Check out our growing list of [integrations](/docs/integrations/) and [dependent repos](/docs/additional_resources/dependents).
+
+### [Additional resources](/docs/additional_resources/)
+Our community is full of prolific developers, creative builders, and fantastic teachers. Check out [YouTube tutorials](/docs/additional_resources/youtube.html) for great tutorials from folks in the community, and [Gallery](https://github.com/kyrolabs/awesome-langchain) for a list of awesome LangChain projects, compiled by the folks at [KyroLabs](https://kyrolabs.com).
+
+### [Community](/docs/community)
+Head to the [Community navigator](/docs/community) to find places to ask questions, share feedback, meet other developers, and dream about the future of LLM’s.
+
+## API reference
+
+Head to the [reference](https://api.python.langchain.com) section for full documentation of all classes and methods in the LangChain Python package.

docs/docs_skeleton/docs/get_started/quickstart.mdx

@@ -0,0 +1,162 @@
+# Quickstart
+
+## Installation
+
+To install LangChain run:
+
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+import Install from "@snippets/get_started/quickstart/installation.mdx"
+
+<Install/>
+
+For more details, see our [Installation guide](/docs/get_started/installation.html).
+
+## Environment setup
+
+Using LangChain will usually require integrations with one or more model providers, data stores, APIs, etc. For this example, we'll use OpenAI's model APIs.
+
+import OpenAISetup from "@snippets/get_started/quickstart/openai_setup.mdx"
+
+<OpenAISetup/>
+
+## Building an application
+
+Now we can start building our language model application. LangChain provides many modules that can be used to build language model applications.
+Modules can be used as stand-alones in simple applications and they can be combined for more complex use cases.
+
+The core building block of LangChain applications is the LLMChain.
+This combines three things:
+- LLM: The language model is the core reasoning engine here. In order to work with LangChain, you need to understand the different types of language models and how to work with them.
+- Prompt Templates: This provides instructions to the language model. This controls what the language model outputs, so understanding how to construct prompts and different prompting strategies is crucial.
+- Output Parsers: These translate the raw response from the LLM to a more workable format, making it easy to use the output downstream.
+
+In this getting started guide we will cover those three components by themselves, and then cover the LLMChain which combines all of them.
+Understanding these concepts will set you up well for being able to use and customize LangChain applications.
+Most LangChain applications allow you to configure the LLM and/or the prompt used, so knowing how to take advantage of this will be a big enabler.
+
+## LLMs
+
+There are two types of language models, which in LangChain are called:
+
+- LLMs: this is a language model which takes a string as input and returns a string
+- ChatModels: this is a language model which takes a list of messages as input and returns a message
+
+The input/output for LLMs is simple and easy to understand - a string.
+But what about ChatModels? The input there is a list of `ChatMessage`s, and the output is a single `ChatMessage`.
+A `ChatMessage` has two required components:
+
+- `content`: This is the content of the message.
+- `role`: This is the role of the entity from which the `ChatMessage` is coming from.
+
+LangChain provides several objects to easily distinguish between different roles:
+
+- `HumanMessage`: A `ChatMessage` coming from a human/user.
+- `AIMessage`: A `ChatMessage` coming from an AI/assistant.
+- `SystemMessage`: A `ChatMessage` coming from the system.
+- `FunctionMessage`: A `ChatMessage` coming from a function call.
+
+If none of those roles sound right, there is also a `ChatMessage` class where you can specify the role manually.
+For more information on how to use these different messages most effectively, see our prompting guide.
+
+LangChain provides a standard interface for both, but it's useful to understand this difference in order to construct prompts for a given language model.
+The standard interface that LangChain provides has two methods:
+- `predict`: Takes in a string, returns a string
+- `predict_messages`: Takes in a list of messages, returns a message.
+
+Let's see how to work with these different types of models and these different types of inputs.
+First, let's import an LLM and a ChatModel.
+
+import ImportLLMs from "@snippets/get_started/quickstart/import_llms.mdx"
+
+<ImportLLMs/>
+
+The `OpenAI` and `ChatOpenAI` objects are basically just configuration objects.
+You can initialize them with parameters like `temperature` and others, and pass them around.
+
+Next, let's use the `predict` method to run over a string input.
+
+import InputString from "@snippets/get_started/quickstart/input_string.mdx"
+
+<InputString/>
+
+Finally, let's use the `predict_messages` method to run over a list of messages.
+
+import InputMessages from "@snippets/get_started/quickstart/input_messages.mdx"
+
+<InputMessages/>
+
+For both these methods, you can also pass in parameters as key word arguments.
+For example, you could pass in `temperature=0` to adjust the temperature that is used from what the object was configured with.
+Whatever values are passed in during run time will always override what the object was configured with.
+
+
+## Prompt templates
+
+Most LLM applications do not pass user input directly into an LLM. Usually they will add the user input to a larger piece of text, called a prompt template, that provides additional context on the specific task at hand.
+
+In the previous example, the text we passed to the model contained instructions to generate a company name. For our application, it'd be great if the user only had to provide the description of a company/product, without having to worry about giving the model instructions.
+
+PromptTemplates help with exactly this!
+They bundle up all the logic for going from user input into a fully formatted prompt.
+This can start off very simple - for example, a prompt to produce the above string would just be:
+
+import PromptTemplateLLM from "@snippets/get_started/quickstart/prompt_templates_llms.mdx"
+import PromptTemplateChatModel from "@snippets/get_started/quickstart/prompt_templates_chat_models.mdx"
+
+<PromptTemplateLLM/>
+
+However, the advantages of using these over raw string formatting are several.
+You can "partial" out variables - e.g. you can format only some of the variables at a time.
+You can compose them together, easily combining different templates into a single prompt.
+For explanations of these functionalities, see the [section on prompts](/docs/modules/model_io/prompts) for more detail.
+
+PromptTemplates can also be used to produce a list of messages.
+In this case, the prompt not only contains information about the content, but also each message (its role, its position in the list, etc)
+Here, what happens most often is a ChatPromptTemplate is a list of ChatMessageTemplates.
+Each ChatMessageTemplate contains instructions for how to format that ChatMessage - its role, and then also its content.
+Let's take a look at this below:
+
+<PromptTemplateChatModel/>
+
+ChatPromptTemplates can also include other things besides ChatMessageTemplates - see the [section on prompts](/docs/modules/model_io/prompts) for more detail.
+
+## Output parsers
+
+OutputParsers convert the raw output of an LLM into a format that can be used downstream.
+There are few main type of OutputParsers, including:
+
+- Convert text from LLM -> structured information (e.g. JSON)
+- Convert a ChatMessage into just a string
+- Convert the extra information returned from a call besides the message (like OpenAI function invocation) into a string.
+
+For full information on this, see the [section on output parsers](/docs/modules/model_io/output_parsers)
+
+In this getting started guide, we will write our own output parser - one that converts a comma separated list into a list.
+
+import OutputParser from "@snippets/get_started/quickstart/output_parser.mdx"
+
+<OutputParser/>
+
+## LLMChain
+
+We can now combine all these into one chain.
+This chain will take input variables, pass those to a prompt template to create a prompt, pass the prompt to an LLM, and then pass the output through an (optional) output parser.
+This is a convenient way to bundle up a modular piece of logic.
+Let's see it in action!
+
+import LLMChain from "@snippets/get_started/quickstart/llm_chain.mdx"
+
+<LLMChain/>
+
+## Next steps
+
+This is it!
+We've now gone over how to create the core building block of LangChain applications - the LLMChains.
+There is a lot more nuance in all these components (LLMs, prompts, output parsers) and a lot more different components to learn about as well.
+To continue on your journey:
+
+- [Dive deeper](/docs/modules/model_io) into LLMs, prompts, and output parsers
+- Learn the other [key components](/docs/modules)
+- Check out our [helpful guides](/docs/guides) for detailed walkthroughs on particular topics
+- Explore [end-to-end use cases](/docs/use_cases)

docs/docs_skeleton/docs/guides/evaluation/comparison/index.mdx

@@ -0,0 +1,24 @@
+---
+sidebar_position: 3 
+---
+# Comparison Evaluators
+
+Comparison evaluators in LangChain help measure two different chains or LLM outputs. These evaluators are helpful for comparative analyses, such as A/B testing between two language models, or comparing different versions of the same model. They can also be useful for things like generating preference scores for ai-assisted reinforcement learning.
+
+These evaluators inherit from the `PairwiseStringEvaluator` class, providing a comparison interface for two strings - typically, the outputs from two different prompts or models, or two versions of the same model. In essence, a comparison evaluator performs an evaluation on a pair of strings and returns a dictionary containing the evaluation score and other relevant details.
+
+To create a custom comparison evaluator, inherit from the `PairwiseStringEvaluator` class and overwrite the `_evaluate_string_pairs` method. If you require asynchronous evaluation, also overwrite the `_aevaluate_string_pairs` method.
+
+Here's a summary of the key methods and properties of a comparison evaluator:
+
+- `evaluate_string_pairs`: Evaluate the output string pairs. This function should be overwritten when creating custom evaluators.
+- `aevaluate_string_pairs`: Asynchronously evaluate the output string pairs. This function should be overwritten for asynchronous evaluation.
+- `requires_input`: This property indicates whether this evaluator requires an input string.
+- `requires_reference`: This property specifies whether this evaluator requires a reference label.
+
+Detailed information about creating custom evaluators and the available built-in comparison evaluators is provided in the following sections.
+
+import DocCardList from "@theme/DocCardList";
+
+<DocCardList />
+

docs/docs_skeleton/docs/guides/evaluation/examples/index.mdx

@@ -0,0 +1,12 @@
+---
+sidebar_position: 5
+---
+# Examples
+
+🚧 _Docs under construction_ 🚧
+
+Below are some examples for inspecting and checking different chains.
+
+import DocCardList from "@theme/DocCardList";
+
+<DocCardList />

docs/docs_skeleton/docs/guides/evaluation/index.mdx

@@ -0,0 +1,27 @@
+import DocCardList from "@theme/DocCardList";
+
+# Evaluation
+
+Building applications with language models involves many moving parts. One of the most critical components is ensuring that the outcomes produced by your models are reliable and useful across a broad array of inputs, and that they work well with your application's other software components. Ensuring reliability usually boils down to some combination of application design, testing & evaluation, and runtime checks. 
+
+The guides in this section review the APIs and functionality LangChain provides to help you better evaluate your applications. Evaluation and testing are both critical when thinking about deploying LLM applications, since production environments require repeatable and useful outcomes.
+
+LangChain offers various types of evaluators to help you measure performance and integrity on diverse data, and we hope to encourage the community to create and share other useful evaluators so everyone can improve. These docs will introduce the evaluator types, how to use them, and provide some examples of their use in real-world scenarios.
+
+Each evaluator type in LangChain comes with ready-to-use implementations and an extensible API that allows for customization according to your unique requirements. Here are some of the types of evaluators we offer:
+
+- [String Evaluators](/docs/guides/evaluation/string/): These evaluators assess the predicted string for a given input, usually comparing it against a reference string.
+- [Trajectory Evaluators](/docs/guides/evaluation/trajectory/): These are used to evaluate the entire trajectory of agent actions.
+- [Comparison Evaluators](/docs/guides/evaluation/comparison/): These evaluators are designed to compare predictions from two runs on a common input.
+
+These evaluators can be used across various scenarios and can be applied to different chain and LLM implementations in the LangChain library.
+
+We also are working to share guides and cookbooks that demonstrate how to use these evaluators in real-world scenarios, such as:
+
+- [Chain Comparisons](/docs/guides/evaluation/examples/comparisons): This example uses a comparison evaluator to predict the preferred output. It reviews ways to measure confidence intervals to select statistically significant differences in aggregate preference scores across different models or prompts.
+
+## Reference Docs
+
+For detailed information on the available evaluators, including how to instantiate, configure, and customize them, check out the [reference documentation](https://api.python.langchain.com/en/latest/api_reference.html#module-langchain.evaluation) directly.
+
+<DocCardList />

docs/docs_skeleton/docs/guides/evaluation/string/index.mdx

@@ -0,0 +1,27 @@
+---
+sidebar_position: 2 
+---
+# String Evaluators
+
+A string evaluator is a component within LangChain designed to assess the performance of a language model by comparing its generated outputs (predictions) to a reference string or an input. This comparison is a crucial step in the evaluation of language models, providing a measure of the accuracy or quality of the generated text.
+
+In practice, string evaluators are typically used to evaluate a predicted string against a given input, such as a question or a prompt. Often, a reference label or context string is provided to define what a correct or ideal response would look like. These evaluators can be customized to tailor the evaluation process to fit your application's specific requirements.
+
+To create a custom string evaluator, inherit from the `StringEvaluator` class and implement the `_evaluate_strings` method. If you require asynchronous support, also implement the `_aevaluate_strings` method.
+
+Here's a summary of the key attributes and methods associated with a string evaluator:
+
+- `evaluation_name`: Specifies the name of the evaluation.
+- `requires_input`: Boolean attribute that indicates whether the evaluator requires an input string. If True, the evaluator will raise an error when the input isn't provided. If False, a warning will be logged if an input _is_ provided, indicating that it will not be considered in the evaluation.
+- `requires_reference`: Boolean attribute specifying whether the evaluator requires a reference label. If True, the evaluator will raise an error when the reference isn't provided. If False, a warning will be logged if a reference _is_ provided, indicating that it will not be considered in the evaluation.
+
+String evaluators also implement the following methods:
+
+- `aevaluate_strings`: Asynchronously evaluates the output of the Chain or Language Model, with support for optional input and label.
+- `evaluate_strings`: Synchronously evaluates the output of the Chain or Language Model, with support for optional input and label.
+
+The following sections provide detailed information on available string evaluator implementations as well as how to create a custom string evaluator.
+
+import DocCardList from "@theme/DocCardList";
+
+<DocCardList />

docs/docs_skeleton/docs/guides/evaluation/trajectory/index.mdx

@@ -0,0 +1,28 @@
+---
+sidebar_position: 4
+---
+# Trajectory Evaluators
+
+Trajectory Evaluators in LangChain provide a more holistic approach to evaluating an agent. These evaluators assess the full sequence of actions taken by an agent and their corresponding responses, which we refer to as the "trajectory". This allows you to better measure an agent's effectiveness and capabilities.
+
+A Trajectory Evaluator implements the `AgentTrajectoryEvaluator` interface, which requires two main methods:
+
+- `evaluate_agent_trajectory`: This method synchronously evaluates an agent's trajectory.
+- `aevaluate_agent_trajectory`: This asynchronous counterpart allows evaluations to be run in parallel for efficiency.
+
+Both methods accept three main parameters:
+
+- `input`: The initial input given to the agent.
+- `prediction`: The final predicted response from the agent.
+- `agent_trajectory`: The intermediate steps taken by the agent, given as a list of tuples.
+
+These methods return a dictionary. It is recommended that custom implementations return a `score` (a float indicating the effectiveness of the agent) and `reasoning` (a string explaining the reasoning behind the score).
+
+You can capture an agent's trajectory by initializing the agent with the `return_intermediate_steps=True` parameter. This lets you collect all intermediate steps without relying on special callbacks.
+
+For a deeper dive into the implementation and use of Trajectory Evaluators, refer to the sections below.
+
+import DocCardList from "@theme/DocCardList";
+
+<DocCardList />
+

docs/docs_skeleton/docs/guides/langsmith/index.md

@@ -0,0 +1,22 @@
+# LangSmith
+
+import DocCardList from "@theme/DocCardList";
+
+[LangSmith](https://smith.langchain.com) helps you trace and evaluate your language model applications and intelligent agents to help you
+move from prototype to production.
+
+Check out the [interactive walkthrough](/docs/guides/langsmith/walkthrough) below to get started.
+
+For more information, please refer to the [LangSmith documentation](https://docs.smith.langchain.com/).
+
+For tutorials and other end-to-end examples demonstrating ways to integrate LangSmith in your workflow,
+check out the [LangSmith Cookbook](https://github.com/langchain-ai/langsmith-cookbook). Some of the guides therein include:
+
+- Leveraging user feedback in your JS application ([link](https://github.com/langchain-ai/langsmith-cookbook/blob/main/feedback-examples/nextjs/README.md)).
+- Building an automated feedback pipeline ([link](https://github.com/langchain-ai/langsmith-cookbook/blob/main/feedback-examples/algorithmic-feedback/algorithmic_feedback.ipynb)).
+- How to evaluate and audit your RAG workflows ([link](https://github.com/langchain-ai/langsmith-cookbook/tree/main/testing-examples/qa-correctness)).
+- How to fine-tune a LLM on real usage data ([link](https://github.com/langchain-ai/langsmith-cookbook/blob/main/fine-tuning-examples/export-to-openai/fine-tuning-on-chat-runs.ipynb)).
+- How to use the [LangChain Hub](https://smith.langchain.com/hub) to version your prompts ([link](https://github.com/langchain-ai/langsmith-cookbook/blob/main/hub-examples/retrieval-qa-chain/retrieval-qa.ipynb))
+
+
+<DocCardList />

docs/docs_skeleton/docs/guides/safety/constitutional_chain.mdx

@@ -0,0 +1,7 @@
+# Self-critique chain with constitutional AI
+The ConstitutionalChain is a chain that ensures the output of a language model adheres to a predefined set of constitutional principles. By incorporating specific rules and guidelines, the ConstitutionalChain filters and modifies the generated content to align with these principles, thus providing more controlled, ethical, and contextually appropriate responses. This mechanism helps maintain the integrity of the output while minimizing the risk of generating content that may violate guidelines, be offensive, or deviate from the desired context.
+
+
+import Example from "@snippets/modules/chains/additional/constitutional_chain.mdx"
+
+<Example/>

docs/docs_skeleton/docs/guides/safety/index.mdx

@@ -0,0 +1,8 @@
+# Moderation
+
+One of the key concerns with using LLMs is that they may generate harmful or unethical text. This is an area of active research in the field. Here we present some built-in chains inspired by this research, which are intended to make the outputs of LLMs safer.
+
+- [Moderation chain](/docs/guides/safety/moderation): Explicitly check if any output text is harmful and flag it.
+- [Constitutional chain](/docs/guides/safety/constitutional_chain): Prompt the model with a set of principles which should guide it's behavior.
+- [Logical Fallacy chain](/docs/guides/safety/logical_fallacy_chain): Checks the model output against logical fallacies to correct any deviation.
+- [Amazon Comprehend moderation chain](/docs/guides/safety/amazon_comprehend_chain): Use [Amazon Comprehend](https://aws.amazon.com/comprehend/) to detect and handle PII and toxicity.

docs/docs_skeleton/docs/guides/safety/logical_fallacy_chain.mdx

@@ -0,0 +1,85 @@
+# Removing logical fallacies from model output
+Logical fallacies are flawed reasoning or false arguments that can undermine the validity of a model's outputs. Examples include circular reasoning, false
+dichotomies, ad hominem attacks, etc.  Machine learning models are optimized to perform well on specific metrics like accuracy, perplexity, or loss. However, 
+optimizing for metrics alone does not guarantee logically sound reasoning.
+
+Language models can learn to exploit flaws in reasoning to generate plausible-sounding but logically invalid arguments.  When models rely on fallacies, their outputs become unreliable and untrustworthy, even if they achieve high scores on metrics. Users cannot depend on such outputs. Propagating logical fallacies can spread misinformation, confuse users, and lead to harmful real-world consequences when models are deployed in products or services.
+
+Monitoring and testing specifically for logical flaws is challenging unlike other quality issues. It requires reasoning about arguments rather than pattern matching.
+
+Therefore, it is crucial that model developers proactively address logical fallacies after optimizing metrics. Specialized techniques like causal modeling, robustness testing, and bias mitigation can help avoid flawed reasoning.  Overall, allowing logical flaws to persist makes models less safe and ethical. Eliminating fallacies ensures model outputs remain logically valid and aligned with human reasoning. This maintains user trust and mitigates risks.
+
+
+
+```python
+# Imports
+from langchain.llms import OpenAI
+from langchain.prompts import PromptTemplate
+from langchain.chains.llm import LLMChain
+from langchain_experimental.fallacy_removal.base import FallacyChain
+```
+
+```python
+# Example of a model output being returned with a logical fallacy
+misleading_prompt = PromptTemplate(
+    template="""You have to respond by using only logical fallacies inherent in your answer explanations.
+
+Question: {question}
+
+Bad answer:""",
+    input_variables=["question"],
+)
+
+llm = OpenAI(temperature=0)
+
+misleading_chain = LLMChain(llm=llm, prompt=misleading_prompt)
+
+misleading_chain.run(question="How do I know the earth is round?")
+```
+
+<CodeOutputBlock lang="python">
+
+```
+    'The earth is round because my professor said it is, and everyone believes my professor'
+```
+
+</CodeOutputBlock>
+
+
+```python
+fallacies = FallacyChain.get_fallacies(["correction"])
+fallacy_chain = FallacyChain.from_llm(
+    chain=misleading_chain,
+    logical_fallacies=fallacies,
+    llm=llm,
+    verbose=True,
+)
+
+fallacy_chain.run(question="How do I know the earth is round?")
+```
+
+<CodeOutputBlock lang="python">
+
+```
+
+
+    > Entering new FallacyChain chain...
+    Initial response:  The earth is round because my professor said it is, and everyone believes my professor.
+
+    Applying correction...
+
+    Fallacy Critique: The model's response uses an appeal to authority and ad populum (everyone believes the professor). Fallacy Critique Needed.
+
+    Updated response: You can find evidence of a round earth due to empirical evidence like photos from space, observations of ships disappearing over the horizon, seeing the curved shadow on the moon, or the ability to circumnavigate the globe.
+
+
+    > Finished chain.
+
+
+
+
+
+    'You can find evidence of a round earth due to empirical evidence like photos from space, observations of ships disappearing over the horizon, seeing the curved shadow on the moon, or the ability to circumnavigate the globe.'
+```
+
+</CodeOutputBlock>

docs/docs_skeleton/docs/guides/safety/moderation.mdx

@@ -0,0 +1,8 @@
+# Moderation
+This notebook walks through examples of how to use a moderation chain, and several common ways for doing so. Moderation chains are useful for detecting text that could be hateful, violent, etc. This can be useful to apply on both user input, but also on the output of a Language Model. Some API providers, like OpenAI, [specifically prohibit](https://beta.openai.com/docs/usage-policies/use-case-policy) you, or your end users, from generating some types of harmful content. To comply with this (and to just generally prevent your application from being harmful) you may often want to append a moderation chain to any LLMChains, in order to make sure any output the LLM generates is not harmful.
+
+If the content passed into the moderation chain is harmful, there is not one best way to handle it, it probably depends on your application. Sometimes you may want to throw an error in the Chain (and have your application handle that). Other times, you may want to return something to the user explaining that the text was harmful. There could even be other ways to handle it! We will cover all these ways in this walkthrough.
+
+import Example from "@snippets/modules/chains/additional/moderation.mdx"
+
+<Example/>

docs/docs_skeleton/docs/modules/agents/agent_types/chat_conversation_agent.mdx

@@ -0,0 +1,13 @@
+# Conversational
+
+This walkthrough demonstrates how to use an agent optimized for conversation. Other agents are often optimized for using tools to figure out the best response, which is not ideal in a conversational setting where you may want the agent to be able to chat with the user as well.
+
+import Example from "@snippets/modules/agents/agent_types/conversational_agent.mdx"
+
+<Example/>
+
+import ChatExample from "@snippets/modules/agents/agent_types/chat_conversation_agent.mdx"
+
+## Using a chat model
+
+<ChatExample/>