x

.devcontainer/README.md

@@ -5,31 +5,26 @@ This project includes a [dev container](https://containers.dev/), which lets you
 You can use the dev container configuration in this folder to build and run the app without needing to install any of its tools locally! You can use it in [GitHub Codespaces](https://github.com/features/codespaces) or the [VS Code Dev Containers extension](https://marketplace.visualstudio.com/items?itemName=ms-vscode-remote.remote-containers).
 
 ## GitHub Codespaces
-
 [![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/langchain-ai/langchain)
 
 You may use the button above, or follow these steps to open this repo in a Codespace:
-
-1. Click the **Code** drop-down menu at the top of <https://github.com/langchain-ai/langchain>.
+1. Click the **Code** drop-down menu at the top of https://github.com/langchain-ai/langchain.
 1. Click on the **Codespaces** tab.
-1. Click **Create codespace on master**.
+1. Click **Create codespace on master** .
 
 For more info, check out the [GitHub documentation](https://docs.github.com/en/free-pro-team@latest/github/developing-online-with-codespaces/creating-a-codespace#creating-a-codespace).
-
+  
 ## VS Code Dev Containers
-
 [![Open in Dev Containers](https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langchain-ai/langchain)
 
-> [!NOTE]
-> If you click the link above you will open the main repo (`langchain-ai/langchain`) and *not* your local cloned repo. This is fine if you only want to run and test the library, but if you want to contribute you can use the link below and replace with your username and cloned repo name:
-
-```txt
-https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/&lt;YOUR_USERNAME&gt;/&lt;YOUR_CLONED_REPO_NAME&gt;
+Note: If you click the link above you will open the main repo (langchain-ai/langchain) and not your local cloned repo. This is fine if you only want to run and test the library, but if you want to contribute you can use the  link below and replace with your username and cloned repo name: 
 ```
+https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/<yourusername>/<yourclonedreponame>
 
+```
 Then you will have a local cloned repo where you can contribute and then create pull requests.
 
-If you already have VS Code and Docker installed, you can use the button above to get started. This will use VSCode to automatically install the Dev Containers extension if needed, clone the source code into a container volume, and spin up a dev container for use.
+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.
 
 Alternatively you can also follow these steps to open this repo in a container using the VS Code Dev Containers extension:
 
@@ -45,5 +40,5 @@ You can learn more in the [Dev Containers documentation](https://code.visualstud
 
 ## Tips and tricks
 
-- If you are working with the same repository folder in a container and Windows, you'll want consistent line endings (otherwise you may see hundreds of changes in the SCM view). The `.gitattributes` file in the root of this repo will disable line ending conversion and should prevent this. See [tips and tricks](https://code.visualstudio.com/docs/devcontainers/tips-and-tricks#_resolving-git-line-ending-issues-in-containers-resulting-in-many-modified-files) for more info.
-- If you'd like to review the contents of the image used in this dev container, you can check it out in the [devcontainers/images](https://github.com/devcontainers/images/tree/main/src/python) repo.
+* If you are working with the same repository folder in a container and Windows, you'll want consistent line endings (otherwise you may see hundreds of changes in the SCM view). The `.gitattributes` file in the root of this repo will disable line ending conversion and should prevent this. See [tips and tricks](https://code.visualstudio.com/docs/devcontainers/tips-and-tricks#_resolving-git-line-ending-issues-in-containers-resulting-in-many-modified-files) for more info.
+* If you'd like to review the contents of the image used in this dev container, you can check it out in the [devcontainers/images](https://github.com/devcontainers/images/tree/main/src/python) repo.

.devcontainer/devcontainer.json

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

.devcontainer/docker-compose.yaml

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

.editorconfig

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

.github/CODEOWNERS

@@ -1,3 +0,0 @@
-/.github/   @baskaryan @ccurme @eyurtsev
-/libs/core/ @eyurtsev
-/libs/packages.yml   @ccurme

.github/CODE_OF_CONDUCT.md

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

.github/CONTRIBUTING.md

@@ -3,4 +3,4 @@
 Hi there! Thank you for even being interested in contributing to LangChain.
 As an open-source project in a rapidly developing field, we are extremely open to contributions, whether they involve new features, improved infrastructure, better documentation, or bug fixes.
 
-To learn how to contribute to LangChain, please follow the [contribution guide here](https://docs.langchain.com/oss/python/contributing).
+To learn how to contribute to LangChain, please follow the [contribution guide here](https://python.langchain.com/docs/contributing/).

.github/DISCUSSION_TEMPLATE/ideas.yml

@@ -0,0 +1,38 @@
+labels: [idea]
+body:
+  - type: checkboxes
+    id: checks
+    attributes:
+      label: Checked
+      description: Please confirm and check all the following options.
+      options:
+        - label: I searched existing ideas and did not find a similar one
+          required: true
+        - label: I added a very descriptive title
+          required: true
+        - label: I've clearly described the feature request and motivation for it
+          required: true
+  - 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: proposal
+    validations:
+      required: false
+    attributes:
+      label: Proposal (If applicable)
+      description: |
+        If you would like to propose a solution, please describe it here. 

.github/DISCUSSION_TEMPLATE/q-a.yml

@@ -0,0 +1,122 @@
+labels: [Question]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for your interest in LangChain 🦜️🔗!
+
+        Please follow these instructions, fill every question, and do every step. 🙏
+        
+        We're asking for this because answering questions and solving problems in GitHub takes a lot of time --
+        this is time that we cannot spend on adding new features, fixing bugs, writing documentation or reviewing pull requests.
+
+        By asking questions in a structured way (following this) it will be much easier for us to help you.
+
+        There's a high chance that by following this process, you'll find the solution on your own, eliminating the need to submit a question and wait for an answer. 😎
+
+        As there are many questions submitted every day, we will **DISCARD** and close the incomplete ones. 
+        
+        That will allow us (and others) to focus on helping people like you that follow the whole process. 🤓
+        
+        Relevant links to check before opening a question to see if your question has already been answered, fixed or
+        if there's another way to solve your problem:
+        
+        [LangChain documentation with the integrated search](https://python.langchain.com/docs/get_started/introduction),
+        [API Reference](https://api.python.langchain.com/en/stable/),
+        [GitHub search](https://github.com/langchain-ai/langchain),
+        [LangChain Github Discussions](https://github.com/langchain-ai/langchain/discussions),
+        [LangChain Github Issues](https://github.com/langchain-ai/langchain/issues?q=is%3Aissue),
+        [LangChain ChatBot](https://chat.langchain.com/)
+  - type: checkboxes
+    id: checks
+    attributes:
+      label: Checked other resources
+      description: Please confirm and check all the following options.
+      options:
+        - label: I added a very descriptive title to this question.
+          required: true
+        - label: I searched the LangChain documentation with the integrated search.
+          required: true
+        - label: I used the GitHub search to find a similar question and didn't find it.
+          required: true
+  - type: checkboxes
+    id: help
+    attributes:
+      label: Commit to Help
+      description: |
+        After submitting this, I commit to one of:
+
+          * Read open questions until I find 2 where I can help someone and add a comment to help there.
+          * I already hit the "watch" button in this repository to receive notifications and I commit to help at least 2 people that ask questions in the future.
+          * Once my question is answered, I will mark the answer as "accepted".
+      options:
+        - label: I commit to help with one of those options 👆
+          required: true
+  - type: textarea
+    id: example
+    attributes:
+      label: Example Code
+      description: |
+        Please add a self-contained, [minimal, reproducible, example](https://stackoverflow.com/help/minimal-reproducible-example) with your use case.
+        
+        If a maintainer can copy it, run it, and see it right away, there's a much higher chance that you'll be able to get help.
+        
+        **Important!** 
+        
+        * Use code tags (e.g., ```python ... ```) to correctly [format your code](https://help.github.com/en/github/writing-on-github/creating-and-highlighting-code-blocks#syntax-highlighting).
+        * INCLUDE the language label (e.g. `python`) after the first three backticks to enable syntax highlighting. (e.g., ```python rather than ```).
+        * Reduce your code to the minimum required to reproduce the issue if possible. This makes it much easier for others to help you.
+        * Avoid screenshots when possible, as they are hard to read and (more importantly) don't allow others to copy-and-paste your code.
+
+      placeholder: |
+        from langchain_core.runnables import RunnableLambda
+
+        def bad_code(inputs) -> int:
+          raise NotImplementedError('For demo purpose')
+        
+          chain = RunnableLambda(bad_code)
+          chain.invoke('Hello!')
+      render: python
+    validations:
+      required: true
+  - type: textarea
+    id: description
+    attributes:
+      label: Description
+      description: |
+        What is the problem, question, or error?
+
+        Write a short description explaining what you are doing, what you expect to happen, and what is currently happening.
+      placeholder: |
+        * I'm trying to use the `langchain` library to do X.
+        * I expect to see Y.
+        * Instead, it does Z.
+    validations:
+      required: true
+  - type: textarea
+    id: system-info
+    attributes:
+      label: System Info
+      description: |
+        Please share your system info with us. 
+        
+        "pip freeze | grep langchain" 
+        platform (windows / linux / mac)
+        python version
+        
+        OR if you're on a recent version of langchain-core you can paste the output of:
+        
+        python -m langchain_core.sys_info
+      placeholder: |
+        "pip freeze | grep langchain"
+        platform
+        python version
+        
+        Alternatively, if you're on a recent version of langchain-core you can paste the output of:
+        
+        python -m langchain_core.sys_info
+        
+        These will only surface LangChain packages, don't forget to include any other relevant
+        packages you're using (if you're not sure what's relevant, you can paste the entire output of `pip freeze`).
+    validations:
+      required: true

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -1,32 +1,35 @@
 name: "\U0001F41B Bug Report"
-description: Report a bug in LangChain. To report a security issue, please instead use the security option below. For questions, please use the LangChain forum.
-labels: ["bug"]
-type: bug
+description: Report a bug in LangChain. To report a security issue, please instead use the security option below. For questions, please use the GitHub Discussions.
+labels: ["02 Bug Report"]
 body:
   - type: markdown
     attributes:
-      value: |
-        Thank you for taking the time to file a bug report.
-
-        Use this to report BUGS in LangChain. For usage questions, feature requests and general design questions, please use the [LangChain Forum](https://forum.langchain.com/).
-
+      value: >
+        Thank you for taking the time to file a bug report. 
+        
+        Use this to report bugs in LangChain. 
+        
+        If you're not certain that your issue is due to a bug in LangChain, please use [GitHub Discussions](https://github.com/langchain-ai/langchain/discussions)
+        to ask for help with your issue.
+        
         Relevant links to check before filing a bug report to see if your issue has already been reported, fixed or
         if there's another way to solve your problem:
-
-        * [LangChain Forum](https://forum.langchain.com/),
-        * [LangChain documentation with the integrated search](https://docs.langchain.com/oss/python/langchain/overview),
-        * [API Reference](https://python.langchain.com/api_reference/),
-        * [LangChain ChatBot](https://chat.langchain.com/)
-        * [GitHub search](https://github.com/langchain-ai/langchain),
+        
+        [LangChain documentation with the integrated search](https://python.langchain.com/docs/get_started/introduction),
+        [API Reference](https://api.python.langchain.com/en/stable/),
+        [GitHub search](https://github.com/langchain-ai/langchain),
+        [LangChain Github Discussions](https://github.com/langchain-ai/langchain/discussions),
+        [LangChain Github Issues](https://github.com/langchain-ai/langchain/issues?q=is%3Aissue),
+        [LangChain ChatBot](https://chat.langchain.com/)
   - type: checkboxes
     id: checks
     attributes:
       label: Checked other resources
       description: Please confirm and check all the following options.
       options:
-        - label: This is a bug, not a usage question.
+        - label: I added a very descriptive title to this issue.
           required: true
-        - label: I added a clear and descriptive title that summarizes this issue.
+        - label: I searched the LangChain documentation with the integrated search.
           required: true
         - label: I used the GitHub search to find a similar question and didn't find it.
           required: true
@@ -34,12 +37,6 @@ body:
           required: true
         - label: The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).
           required: true
-        - label: This is not related to the langchain-community package.
-          required: true
-        - label: I read what a minimal reproducible example is (https://stackoverflow.com/help/minimal-reproducible-example).
-          required: true
-        - label: I posted a self-contained, minimal, reproducible example. A maintainer can copy it and run it AS IS.
-          required: true
   - type: textarea
     id: reproduction
     validations:
@@ -48,25 +45,25 @@ body:
       label: Example Code
       description: |
         Please add a self-contained, [minimal, reproducible, example](https://stackoverflow.com/help/minimal-reproducible-example) with your use case.
-
+        
         If a maintainer can copy it, run it, and see it right away, there's a much higher chance that you'll be able to get help.
-
-        **Important!**
-
-        * Avoid screenshots when possible, as they are hard to read and (more importantly) don't allow others to copy-and-paste your code.
-        * Reduce your code to the minimum required to reproduce the issue if possible. This makes it much easier for others to help you.
+        
+        **Important!** 
+        
         * Use code tags (e.g., ```python ... ```) to correctly [format your code](https://help.github.com/en/github/writing-on-github/creating-and-highlighting-code-blocks#syntax-highlighting).
         * INCLUDE the language label (e.g. `python`) after the first three backticks to enable syntax highlighting. (e.g., ```python rather than ```).
+        * Reduce your code to the minimum required to reproduce the issue if possible. This makes it much easier for others to help you.
+        * Avoid screenshots when possible, as they are hard to read and (more importantly) don't allow others to copy-and-paste your code.
 
       placeholder: |
-        The following code:
-
+        The following code: 
+        
         ```python
         from langchain_core.runnables import RunnableLambda
 
         def bad_code(inputs) -> int:
           raise NotImplementedError('For demo purpose')
-
+          
           chain = RunnableLambda(bad_code)
           chain.invoke('Hello!')
         ```
@@ -99,27 +96,25 @@ body:
     attributes:
       label: System Info
       description: |
-        Please share your system info with us. Do NOT skip this step and please don't trim
-        the output. Most users don't include enough information here and it makes it harder
-        for us to help you.
-
-        Run the following command in your terminal and paste the output here:
-
-        `python -m langchain_core.sys_info`
-
-        or if you have an existing python interpreter running:
-
-        ```python
-        from langchain_core import sys_info
-        sys_info.print_sys_info()
-        ```
-
-        alternatively, put the entire output of `pip freeze` here.
-      placeholder: |
+        Please share your system info with us. 
+        
+        "pip freeze | grep langchain" 
+        platform (windows / linux / mac)
+        python version
+        
+        OR if you're on a recent version of langchain-core you can paste the output of:
+        
         python -m langchain_core.sys_info
+      placeholder: |
+        "pip freeze | grep langchain"
+        platform
+        python version
+        
+        Alternatively, if you're on a recent version of langchain-core you can paste the output of:
+        
+        python -m langchain_core.sys_info
+        
+        These will only surface LangChain packages, don't forget to include any other relevant
+        packages you're using (if you're not sure what's relevant, you can paste the entire output of `pip freeze`).
     validations:
       required: true
-
-
-
-

.github/ISSUE_TEMPLATE/config.yml

@@ -1,9 +1,15 @@
 blank_issues_enabled: false
 version: 2.1
 contact_links:
-  - name: 📚 Documentation
-    url: https://github.com/langchain-ai/docs/issues/new?template=langchain.yml
-    about: Report an issue related to the LangChain documentation
-  - name: 💬 LangChain Forum
-    url:  https://forum.langchain.com/
-    about: General community discussions and support
+  - name: 🤔 Question or Problem
+    about: Ask a question or ask about a problem in GitHub Discussions.
+    url: https://www.github.com/langchain-ai/langchain/discussions/categories/q-a
+  - name: Discord
+    url: https://discord.gg/6adMQxSpJS
+    about: General community discussions
+  - name: Feature Request
+    url: https://www.github.com/langchain-ai/langchain/discussions/categories/ideas
+    about: Suggest a feature or an idea
+  - name: Show and tell
+    about: Show what you built with LangChain
+    url: https://www.github.com/langchain-ai/langchain/discussions/categories/show-and-tell

.github/ISSUE_TEMPLATE/documentation.yml

@@ -0,0 +1,51 @@
+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: markdown
+  attributes:
+    value: >
+      Thank you for taking the time to report an issue in the documentation.
+      
+      Only report issues with documentation here, explain if there are
+      any missing topics or if you found a mistake in the documentation.
+      
+      Do **NOT** use this to ask usage questions or reporting issues with your code.
+      
+      If you have usage questions or need help solving some problem, 
+      please use [GitHub Discussions](https://github.com/langchain-ai/langchain/discussions).
+      
+      If you're in the wrong place, here are some helpful links to find a better
+      place to ask your question:
+      
+      [LangChain documentation with the integrated search](https://python.langchain.com/docs/get_started/introduction),
+      [API Reference](https://api.python.langchain.com/en/stable/),
+      [GitHub search](https://github.com/langchain-ai/langchain),
+      [LangChain Github Discussions](https://github.com/langchain-ai/langchain/discussions),
+      [LangChain Github Issues](https://github.com/langchain-ai/langchain/issues?q=is%3Aissue),
+      [LangChain ChatBot](https://chat.langchain.com/)
+- type: checkboxes
+  id: checks
+  attributes:
+    label: Checklist
+    description: Please confirm and check all the following options.
+    options:
+      - label: I added a very descriptive title to this issue.
+        required: true
+      - label: I included a link to the documentation page I am referring to (if applicable).
+        required: true
+- type: textarea
+  attributes: 
+    label: "Issue with current documentation:"
+    description: >
+      Please make sure to leave a reference to the document/code you're
+      referring to. Feel free to include names of classes, functions, methods
+      or concepts you'd like to see documented more.
+- type: textarea
+  attributes:
+    label: "Idea or request for content:"
+    description: >
+      Please describe as clearly as possible what topics you think are missing
+      from the current documentation.

.github/ISSUE_TEMPLATE/feature-request.yml

@@ -1,118 +0,0 @@
-name: "✨ Feature Request"
-description: Request a new feature or enhancement for LangChain. For questions, please use the LangChain forum.
-labels: ["feature request"]
-type: feature
-body:
-  - type: markdown
-    attributes:
-      value: |
-        Thank you for taking the time to request a new feature.
-
-        Use this to request NEW FEATURES or ENHANCEMENTS in LangChain. For bug reports, please use the bug report template. For usage questions and general design questions, please use the [LangChain Forum](https://forum.langchain.com/).
-
-        Relevant links to check before filing a feature request to see if your request has already been made or
-        if there's another way to achieve what you want:
-
-        * [LangChain Forum](https://forum.langchain.com/),
-        * [LangChain documentation with the integrated search](https://docs.langchain.com/oss/python/langchain/overview),
-        * [API Reference](https://python.langchain.com/api_reference/),
-        * [LangChain ChatBot](https://chat.langchain.com/)
-        * [GitHub search](https://github.com/langchain-ai/langchain),
-  - type: checkboxes
-    id: checks
-    attributes:
-      label: Checked other resources
-      description: Please confirm and check all the following options.
-      options:
-        - label: This is a feature request, not a bug report or usage question.
-          required: true
-        - label: I added a clear and descriptive title that summarizes the feature request.
-          required: true
-        - label: I used the GitHub search to find a similar feature request and didn't find it.
-          required: true
-        - label: I checked the LangChain documentation and API reference to see if this feature already exists.
-          required: true
-        - label: This is not related to the langchain-community package.
-          required: true
-  - type: textarea
-    id: feature-description
-    validations:
-      required: true
-    attributes:
-      label: Feature Description
-      description: |
-        Please provide a clear and concise description of the feature you would like to see added to LangChain.
-        
-        What specific functionality are you requesting? Be as detailed as possible.
-      placeholder: |
-        I would like LangChain to support...
-        
-        This feature would allow users to...
-  - type: textarea
-    id: use-case
-    validations:
-      required: true
-    attributes:
-      label: Use Case
-      description: |
-        Describe the specific use case or problem this feature would solve.
-        
-        Why do you need this feature? What problem does it solve for you or other users?
-      placeholder: |
-        I'm trying to build an application that...
-        
-        Currently, I have to work around this by...
-        
-        This feature would help me/users to...
-  - type: textarea
-    id: proposed-solution
-    validations:
-      required: false
-    attributes:
-      label: Proposed Solution
-      description: |
-        If you have ideas about how this feature could be implemented, please describe them here.
-        
-        This is optional but can be helpful for maintainers to understand your vision.
-      placeholder: |
-        I think this could be implemented by...
-        
-        The API could look like...
-        
-        ```python
-        # Example of how the feature might work
-        ```
-  - type: textarea
-    id: alternatives
-    validations:
-      required: false
-    attributes:
-      label: Alternatives Considered
-      description: |
-        Have you considered any alternative solutions or workarounds?
-        
-        What other approaches have you tried or considered?
-      placeholder: |
-        I've tried using...
-        
-        Alternative approaches I considered:
-        1. ...
-        2. ...
-        
-        But these don't work because...
-  - type: textarea
-    id: additional-context
-    validations:
-      required: false
-    attributes:
-      label: Additional Context
-      description: |
-        Add any other context, screenshots, examples, or references that would help explain your feature request.
-      placeholder: |
-        Related issues: #...
-        
-        Similar features in other libraries:
-        - ...
-        
-        Additional context or examples:
-        - ...

.github/ISSUE_TEMPLATE/privileged.yml

@@ -4,7 +4,12 @@ body:
   - type: markdown
     attributes:
       value: |
-        If you are not a LangChain maintainer, employee, or were not asked directly by a maintainer to create an issue, then please start the conversation on the [LangChain Forum](https://forum.langchain.com/) instead.
+        Thanks for your interest in LangChain! 🚀
+        
+        If you are not a LangChain maintainer or were not asked directly by a maintainer to create an issue, then please start the conversation in a [Question in GitHub Discussions](https://github.com/langchain-ai/langchain/discussions/categories/q-a) instead.
+        
+        You are a LangChain maintainer if you maintain any of the packages inside of the LangChain repository 
+        or are a regular contributor to LangChain with previous merged pull requests.
   - type: checkboxes
     id: privileged
     attributes:

.github/ISSUE_TEMPLATE/task.yml

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

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,33 +1,29 @@
-(Replace this entire block of text)
+Thank you for contributing to LangChain!
 
-Thank you for contributing to LangChain! Follow these steps to mark your pull request as ready for review. **If any of these steps are not completed, your PR will not be considered for review.**
+- [ ] **PR title**: "package: description"
+  - Where "package" is whichever of langchain, community, core, experimental, etc. is being modified. Use "docs: ..." for purely docs changes, "templates: ..." for template changes, "infra: ..." for CI changes.
+  - Example: "community: add foobar LLM"
 
-- [ ] **PR title**: Follows the format: {TYPE}({SCOPE}): {DESCRIPTION}
-  - Examples:
-    - feat(core): add multi-tenant support
-    - fix(cli): resolve flag parsing error
-    - docs(openai): update API usage examples
-  - Allowed `{TYPE}` values:
-    - feat, fix, docs, style, refactor, perf, test, build, ci, chore, revert, release
-  - Allowed `{SCOPE}` values (optional):
-    - core, cli, langchain, standard-tests, docs, anthropic, chroma, deepseek, exa, fireworks, groq, huggingface, mistralai, nomic, ollama, openai, perplexity, prompty, qdrant, xai
-  - *Note:* the `{DESCRIPTION}` must not start with an uppercase letter.
-  - Once you've written the title, please delete this checklist item; do not include it in the PR.
 
 - [ ] **PR message**: ***Delete this entire checklist*** and replace with
-  - **Description:** a description of the change. Include a [closing keyword](https://docs.github.com/en/issues/tracking-your-work-with-issues/using-issues/linking-a-pull-request-to-an-issue#linking-a-pull-request-to-an-issue-using-a-keyword) if applicable to a relevant issue.
-  - **Issue:** the issue # it fixes, if applicable (e.g. Fixes #123)
-  - **Dependencies:** any dependencies required for this change
+    - **Description:** a description of the change
+    - **Issue:** the issue # it fixes, if applicable
+    - **Dependencies:** any dependencies required for this change
+    - **Twitter handle:** if your PR gets announced, and you'd like a mention, we'll gladly shout you out!
 
-- [ ] **Add tests and docs**: If you're adding a new integration, you must include:
-  1. A test for the integration, preferably unit tests that do not rely on network access,
-  2. An example notebook showing its use. It lives in `docs/docs/integrations` directory.
 
-- [ ] **Lint and test**: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. **We will not consider a PR unless these three are passing in CI.** See [contribution guidelines](https://python.langchain.com/docs/contributing/) for more.
+- [ ] **Add tests and docs**: 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/docs/integrations` directory.
+
+
+- [ ] **Lint and test**: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. See contribution guidelines for more: https://python.langchain.com/docs/contributing/
 
 Additional guidelines:
-
-- Most PRs should not touch more than one package.
-- Please do not add dependencies to `pyproject.toml` files (even optional ones) unless they are **required** for unit tests.
-- Changes should be backwards compatible.
 - Make sure optional dependencies are imported within a function.
+- Please do not add dependencies to pyproject.toml files (even optional ones) unless they are required for unit tests.
+- Most PRs should not touch more than one package.
+- Changes should be backwards compatible.
+- If you are adding something to community, do not re-import it in langchain.
+
+If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, hwchase17.

.github/actions/people/Dockerfile

@@ -4,4 +4,4 @@ RUN pip install httpx PyGithub "pydantic==2.0.2" pydantic-settings "pyyaml>=5.3.
 
 COPY ./app /app
 
-CMD ["python", "/app/main.py"]
+CMD ["python", "/app/main.py"]

.github/actions/people/action.yml

@@ -1,13 +1,11 @@
 # Adapted from https://github.com/tiangolo/fastapi/blob/master/.github/actions/people/action.yml
-# TODO: fix this, migrate to new docs repo?
-
 name: "Generate LangChain People"
 description: "Generate the data for the LangChain People page"
 author: "Jacob Lee <jacob@langchain.dev>"
 inputs:
   token:
-    description: "User token, to read the GitHub API. Can be passed in using {{ secrets.LANGCHAIN_PEOPLE_GITHUB_TOKEN }}"
+    description: 'User token, to read the GitHub API. Can be passed in using {{ secrets.LANGCHAIN_PEOPLE_GITHUB_TOKEN }}'
     required: true
 runs:
-  using: "docker"
-  image: "Dockerfile"
+  using: 'docker'
+  image: 'Dockerfile'

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

@@ -350,7 +350,11 @@ def get_graphql_pr_edges(*, settings: Settings, after: Union[str, None] = None):
         print("Querying PRs...")
     else:
         print(f"Querying PRs with cursor {after}...")
-    data = get_graphql_response(settings=settings, query=prs_query, after=after)
+    data = get_graphql_response(
+        settings=settings,
+        query=prs_query,
+        after=after
+    )
     graphql_response = PRsResponse.model_validate(data)
     return graphql_response.data.repository.pullRequests.edges
 
@@ -480,16 +484,10 @@ def get_contributors(settings: Settings):
             lines_changed = pr.additions + pr.deletions
             score = _logistic(files_changed, 20) + _logistic(lines_changed, 100)
             contributor_scores[pr.author.login] += score
-            three_months_ago = datetime.now(timezone.utc) - timedelta(days=3 * 30)
+            three_months_ago = (datetime.now(timezone.utc) - timedelta(days=3*30))
             if pr.createdAt > three_months_ago:
                 recent_contributor_scores[pr.author.login] += score
-    return (
-        contributors,
-        contributor_scores,
-        recent_contributor_scores,
-        reviewers,
-        authors,
-    )
+    return contributors, contributor_scores, recent_contributor_scores, reviewers, authors
 
 
 def get_top_users(
@@ -526,13 +524,9 @@ if __name__ == "__main__":
     # question_commentors, question_last_month_commentors, question_authors = get_experts(
     #     settings=settings
     # )
-    (
-        contributors,
-        contributor_scores,
-        recent_contributor_scores,
-        reviewers,
-        pr_authors,
-    ) = get_contributors(settings=settings)
+    contributors, contributor_scores, recent_contributor_scores, reviewers, pr_authors = get_contributors(
+        settings=settings
+    )
     # authors = {**question_authors, **pr_authors}
     authors = {**pr_authors}
     maintainers_logins = {
@@ -543,9 +537,7 @@ if __name__ == "__main__":
         "nfcampos",
         "efriis",
         "eyurtsev",
-        "rlancemartin",
-        "ccurme",
-        "vbarda",
+        "rlancemartin"
     }
     hidden_logins = {
         "dev2049",
@@ -553,7 +545,6 @@ if __name__ == "__main__":
         "obi1kenobi",
         "langchain-infra",
         "jacoblee93",
-        "isahers1",
         "dqbd",
         "bracesproul",
         "akira",
@@ -565,7 +556,7 @@ if __name__ == "__main__":
         maintainers.append(
             {
                 "login": login,
-                "count": contributors[login],  # + question_commentors[login],
+                "count": contributors[login], #+ question_commentors[login],
                 "avatarUrl": user.avatarUrl,
                 "twitterUsername": user.twitterUsername,
                 "url": user.url,
@@ -621,7 +612,9 @@ if __name__ == "__main__":
     new_people_content = yaml.dump(
         people, sort_keys=False, width=200, allow_unicode=True
     )
-    if people_old_content == new_people_content:
+    if (
+        people_old_content == new_people_content
+    ):
         logging.info("The LangChain People data hasn't changed, finishing.")
         sys.exit(0)
     people_path.write_text(new_people_content, encoding="utf-8")
@@ -634,7 +627,9 @@ if __name__ == "__main__":
     logging.info(f"Creating a new branch {branch_name}")
     subprocess.run(["git", "checkout", "-B", branch_name], check=True)
     logging.info("Adding updated file")
-    subprocess.run(["git", "add", str(people_path)], check=True)
+    subprocess.run(
+        ["git", "add", str(people_path)], check=True
+    )
     logging.info("Committing updated file")
     message = "👥 Update LangChain people data"
     result = subprocess.run(["git", "commit", "-m", message], check=True)
@@ -643,4 +638,4 @@ if __name__ == "__main__":
     logging.info("Creating PR")
     pr = repo.create_pull(title=message, body=message, base="master", head=branch_name)
     logging.info(f"Created PR: {pr.number}")
-    logging.info("Finished")
+    logging.info("Finished")

.github/actions/uv_setup/action.yml

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

.github/copilot-instructions.md

@@ -1,325 +0,0 @@
-# Global Development Guidelines for LangChain Projects
-
-## Core Development Principles
-
-### 1. Maintain Stable Public Interfaces ⚠️ CRITICAL
-
-**Always attempt to preserve function signatures, argument positions, and names for exported/public methods.**
-
-❌ **Bad - Breaking Change:**
-
-```python
-def get_user(id, verbose=False):  # Changed from `user_id`
-    pass
-```
-
-✅ **Good - Stable Interface:**
-
-```python
-def get_user(user_id: str, verbose: bool = False) -> User:
-    """Retrieve user by ID with optional verbose output."""
-    pass
-```
-
-**Before making ANY changes to public APIs:**
-
-- Check if the function/class is exported in `__init__.py`
-- Look for existing usage patterns in tests and examples
-- Use keyword-only arguments for new parameters: `*, new_param: str = "default"`
-- Mark experimental features clearly with docstring warnings (using reStructuredText, like `.. warning::`)
-
-🧠 *Ask yourself:* "Would this change break someone's code if they used it last week?"
-
-### 2. Code Quality Standards
-
-**All Python code MUST include type hints and return types.**
-
-❌ **Bad:**
-
-```python
-def p(u, d):
-    return [x for x in u if x not in d]
-```
-
-✅ **Good:**
-
-```python
-def filter_unknown_users(users: list[str], known_users: set[str]) -> list[str]:
-    """Filter out users that are not in the known users set.
-
-    Args:
-        users: List of user identifiers to filter.
-        known_users: Set of known/valid user identifiers.
-
-    Returns:
-        List of users that are not in the known_users set.
-    """
-    return [user for user in users if user not in known_users]
-```
-
-**Style Requirements:**
-
-- Use descriptive, **self-explanatory variable names**. Avoid overly short or cryptic identifiers.
-- Attempt to break up complex functions (>20 lines) into smaller, focused functions where it makes sense
-- Avoid unnecessary abstraction or premature optimization
-- Follow existing patterns in the codebase you're modifying
-
-### 3. Testing Requirements
-
-**Every new feature or bugfix MUST be covered by unit tests.**
-
-**Test Organization:**
-
-- Unit tests: `tests/unit_tests/` (no network calls allowed)
-- Integration tests: `tests/integration_tests/` (network calls permitted)
-- Use `pytest` as the testing framework
-
-**Test Quality Checklist:**
-
-- [ ] Tests fail when your new logic is broken
-- [ ] Happy path is covered
-- [ ] Edge cases and error conditions are tested
-- [ ] Use fixtures/mocks for external dependencies
-- [ ] Tests are deterministic (no flaky tests)
-
-Checklist questions:
-
-- [ ] Does the test suite fail if your new logic is broken?
-- [ ] Are all expected behaviors exercised (happy path, invalid input, etc)?
-- [ ] Do tests use fixtures or mocks where needed?
-
-```python
-def test_filter_unknown_users():
-    """Test filtering unknown users from a list."""
-    users = ["alice", "bob", "charlie"]
-    known_users = {"alice", "bob"}
-
-    result = filter_unknown_users(users, known_users)
-
-    assert result == ["charlie"]
-    assert len(result) == 1
-```
-
-### 4. Security and Risk Assessment
-
-**Security Checklist:**
-
-- No `eval()`, `exec()`, or `pickle` on user-controlled input
-- Proper exception handling (no bare `except:`) and use a `msg` variable for error messages
-- Remove unreachable/commented code before committing
-- Race conditions or resource leaks (file handles, sockets, threads).
-- Ensure proper resource cleanup (file handles, connections)
-
-❌ **Bad:**
-
-```python
-def load_config(path):
-    with open(path) as f:
-        return eval(f.read())  # ⚠️ Never eval config
-```
-
-✅ **Good:**
-
-```python
-import json
-
-def load_config(path: str) -> dict:
-    with open(path) as f:
-        return json.load(f)
-```
-
-### 5. Documentation Standards
-
-**Use Google-style docstrings with Args section for all public functions.**
-
-❌ **Insufficient Documentation:**
-
-```python
-def send_email(to, msg):
-    """Send an email to a recipient."""
-```
-
-✅ **Complete Documentation:**
-
-```python
-def send_email(to: str, msg: str, *, priority: str = "normal") -> bool:
-    """
-    Send an email to a recipient with specified priority.
-
-    Args:
-        to: The email address of the recipient.
-        msg: The message body to send.
-        priority: Email priority level (``'low'``, ``'normal'``, ``'high'``).
-
-    Returns:
-        True if email was sent successfully, False otherwise.
-
-    Raises:
-        InvalidEmailError: If the email address format is invalid.
-        SMTPConnectionError: If unable to connect to email server.
-    """
-```
-
-**Documentation Guidelines:**
-
-- Types go in function signatures, NOT in docstrings
-- Focus on "why" rather than "what" in descriptions
-- Document all parameters, return values, and exceptions
-- Keep descriptions concise but clear
-- Use reStructuredText for docstrings to enable rich formatting
-
-📌 *Tip:* Keep descriptions concise but clear. Only document return values if non-obvious.
-
-### 6. Architectural Improvements
-
-**When you encounter code that could be improved, suggest better designs:**
-
-❌ **Poor Design:**
-
-```python
-def process_data(data, db_conn, email_client, logger):
-    # Function doing too many things
-    validated = validate_data(data)
-    result = db_conn.save(validated)
-    email_client.send_notification(result)
-    logger.log(f"Processed {len(data)} items")
-    return result
-```
-
-✅ **Better Design:**
-
-```python
-@dataclass
-class ProcessingResult:
-    """Result of data processing operation."""
-    items_processed: int
-    success: bool
-    errors: List[str] = field(default_factory=list)
-
-class DataProcessor:
-    """Handles data validation, storage, and notification."""
-
-    def __init__(self, db_conn: Database, email_client: EmailClient):
-        self.db = db_conn
-        self.email = email_client
-
-    def process(self, data: List[dict]) -> ProcessingResult:
-        """Process and store data with notifications."""
-        validated = self._validate_data(data)
-        result = self.db.save(validated)
-        self._notify_completion(result)
-        return result
-```
-
-**Design Improvement Areas:**
-
-If there's a **cleaner**, **more scalable**, or **simpler** design, highlight it and suggest improvements that would:
-
-- Reduce code duplication through shared utilities
-- Make unit testing easier
-- Improve separation of concerns (single responsibility)
-- Make unit testing easier through dependency injection
-- Add clarity without adding complexity
-- Prefer dataclasses for structured data
-
-## Development Tools & Commands
-
-### Package Management
-
-```bash
-# Add package
-uv add package-name
-
-# Sync project dependencies
-uv sync
-uv lock
-```
-
-### Testing
-
-```bash
-# Run unit tests (no network)
-make test
-
-# Don't run integration tests, as API keys must be set
-
-# Run specific test file
-uv run --group test pytest tests/unit_tests/test_specific.py
-```
-
-### Code Quality
-
-```bash
-# Lint code
-make lint
-
-# Format code
-make format
-
-# Type checking
-uv run --group lint mypy .
-```
-
-### Dependency Management Patterns
-
-**Local Development Dependencies:**
-
-```toml
-[tool.uv.sources]
-langchain-core = { path = "../core", editable = true }
-langchain-tests = { path = "../standard-tests", editable = true }
-```
-
-**For tools, use the `@tool` decorator from `langchain_core.tools`:**
-
-```python
-from langchain_core.tools import tool
-
-@tool
-def search_database(query: str) -> str:
-    """Search the database for relevant information.
-
-    Args:
-        query: The search query string.
-    """
-    # Implementation here
-    return results
-```
-
-## Commit Standards
-
-**Use Conventional Commits format for PR titles:**
-
-- `feat(core): add multi-tenant support`
-- `fix(cli): resolve flag parsing error`
-- `docs: update API usage examples`
-- `docs(openai): update API usage examples`
-
-## Framework-Specific Guidelines
-
-- Follow the existing patterns in `langchain-core` for base abstractions
-- Use `langchain_core.callbacks` for execution tracking
-- Implement proper streaming support where applicable
-- Avoid deprecated components like legacy `LLMChain`
-
-### Partner Integrations
-
-- Follow the established patterns in existing partner libraries
-- Implement standard interfaces (`BaseChatModel`, `BaseEmbeddings`, etc.)
-- Include comprehensive integration tests
-- Document API key requirements and authentication
-
----
-
-## Quick Reference Checklist
-
-Before submitting code changes:
-
-- [ ] **Breaking Changes**: Verified no public API changes
-- [ ] **Type Hints**: All functions have complete type annotations
-- [ ] **Tests**: New functionality is fully tested
-- [ ] **Security**: No dangerous patterns (eval, silent failures, etc.)
-- [ ] **Documentation**: Google-style docstrings for public functions
-- [ ] **Code Quality**: `make lint` and `make format` pass
-- [ ] **Architecture**: Suggested improvements where applicable
-- [ ] **Commit Message**: Follows Conventional Commits format

.github/dependabot.yml

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

.github/pr-file-labeler.yml

@@ -1,80 +0,0 @@
-# Label PRs (config)
-# Automatically applies labels based on changed files and branch patterns
-
-# Core packages
-core:
-  - changed-files:
-      - any-glob-to-any-file:
-          - "libs/core/**/*"
-
-langchain:
-  - changed-files:
-      - any-glob-to-any-file:
-          - "libs/langchain/**/*"
-          - "libs/langchain_v1/**/*"
-
-v1:
-  - changed-files:
-      - any-glob-to-any-file:
-          - "libs/langchain_v1/**/*"
-
-cli:
-  - changed-files:
-      - any-glob-to-any-file:
-          - "libs/cli/**/*"
-
-standard-tests:
-  - changed-files:
-      - any-glob-to-any-file:
-          - "libs/standard-tests/**/*"
-
-# Partner integrations
-integration:
-  - changed-files:
-      - any-glob-to-any-file:
-          - "libs/partners/**/*"
-
-# Infrastructure and DevOps
-infra:
-  - changed-files:
-      - any-glob-to-any-file:
-          - ".github/**/*"
-          - "Makefile"
-          - ".pre-commit-config.yaml"
-          - "scripts/**/*"
-          - "docker/**/*"
-          - "Dockerfile*"
-
-github_actions:
-  - changed-files:
-      - any-glob-to-any-file:
-          - ".github/workflows/**/*"
-          - ".github/actions/**/*"
-
-dependencies:
-  - changed-files:
-      - any-glob-to-any-file:
-          - "**/pyproject.toml"
-          - "uv.lock"
-          - "**/requirements*.txt"
-          - "**/poetry.lock"
-
-# Documentation
-documentation:
-  - changed-files:
-      - any-glob-to-any-file:
-          - "docs/**/*"
-          - "**/*.md"
-          - "**/*.rst"
-          - "**/README*"
-
-# Security related changes
-security:
-  - changed-files:
-      - any-glob-to-any-file:
-          - "**/*security*"
-          - "**/*auth*"
-          - "**/*credential*"
-          - "**/*secret*"
-          - "**/*token*"
-          - ".github/workflows/security*"

.github/pr-title-labeler.yml

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

.github/scripts/check_diff.py

@@ -1,242 +1,16 @@
-"""Analyze git diffs to determine which directories need to be tested.
-
-Intelligently determines which LangChain packages and directories need to be tested,
-linted, or built based on the changes. Handles dependency relationships between
-packages, maps file changes to appropriate CI job configurations, and outputs JSON
-configurations for GitHub Actions.
-
-- Maps changed files to affected package directories (libs/core, libs/partners/*, etc.)
-- Builds dependency graph to include dependent packages when core components change
-- Generates test matrix configurations with appropriate Python versions
-- Handles special cases for Pydantic version testing and performance benchmarks
-
-Used as part of the check_diffs workflow.
-"""
-
-import glob
 import json
-import os
 import sys
-from collections import defaultdict
-from pathlib import Path
-from typing import Dict, List, Set
-
-import tomllib
-from get_min_versions import get_min_version_from_toml
-from packaging.requirements import Requirement
+import os
+from typing import Dict
 
 LANGCHAIN_DIRS = [
     "libs/core",
     "libs/text-splitters",
+    "libs/community",
     "libs/langchain",
-    "libs/langchain_v1",
+    "libs/experimental",
 ]
 
-# When set to True, we are ignoring core dependents
-# in order to be able to get CI to pass for each individual
-# package that depends on core
-# e.g. if you touch core, we don't then add textsplitters/etc to CI
-IGNORE_CORE_DEPENDENTS = False
-
-# ignored partners are removed from dependents
-# but still run if directly edited
-IGNORED_PARTNERS = [
-    # remove huggingface from dependents because of CI instability
-    # specifically in huggingface jobs
-    # https://github.com/langchain-ai/langchain/issues/25558
-    "huggingface",
-    # prompty exhibiting issues with numpy for Python 3.13
-    # https://github.com/langchain-ai/langchain/actions/runs/12651104685/job/35251034969?pr=29065
-    "prompty",
-]
-
-PY_312_MAX_PACKAGES = [
-    "libs/partners/chroma",  # https://github.com/chroma-core/chroma/issues/4382
-]
-
-
-def all_package_dirs() -> Set[str]:
-    return {
-        "/".join(path.split("/")[:-1]).lstrip("./")
-        for path in glob.glob("./libs/**/pyproject.toml", recursive=True)
-        if "libs/cli" not in path and "libs/standard-tests" not in path
-    }
-
-
-def dependents_graph() -> dict:
-    """Construct a mapping of package -> dependents
-
-    Done such that we can run tests on all dependents of a package when a change is made.
-    """
-    dependents = defaultdict(set)
-
-    for path in glob.glob("./libs/**/pyproject.toml", recursive=True):
-        if "template" in path:
-            continue
-
-        # load regular and test deps from pyproject.toml
-        with open(path, "rb") as f:
-            pyproject = tomllib.load(f)
-
-        pkg_dir = "libs" + "/".join(path.split("libs")[1].split("/")[:-1])
-        for dep in [
-            *pyproject["project"]["dependencies"],
-            *pyproject["dependency-groups"]["test"],
-        ]:
-            requirement = Requirement(dep)
-            package_name = requirement.name
-            if "langchain" in dep:
-                dependents[package_name].add(pkg_dir)
-                continue
-
-        # load extended deps from extended_testing_deps.txt
-        package_path = Path(path).parent
-        extended_requirement_path = package_path / "extended_testing_deps.txt"
-        if extended_requirement_path.exists():
-            with open(extended_requirement_path, "r") as f:
-                extended_deps = f.read().splitlines()
-                for depline in extended_deps:
-                    if depline.startswith("-e "):
-                        # editable dependency
-                        assert depline.startswith("-e ../partners/"), (
-                            "Extended test deps should only editable install partner packages"
-                        )
-                        partner = depline.split("partners/")[1]
-                        dep = f"langchain-{partner}"
-                    else:
-                        dep = depline.split("==")[0]
-
-                    if "langchain" in dep:
-                        dependents[dep].add(pkg_dir)
-
-    for k in dependents:
-        for partner in IGNORED_PARTNERS:
-            if f"libs/partners/{partner}" in dependents[k]:
-                dependents[k].remove(f"libs/partners/{partner}")
-    return dependents
-
-
-def add_dependents(dirs_to_eval: Set[str], dependents: dict) -> List[str]:
-    updated = set()
-    for dir_ in dirs_to_eval:
-        # handle core manually because it has so many dependents
-        if "core" in dir_:
-            updated.add(dir_)
-            continue
-        pkg = "langchain-" + dir_.split("/")[-1]
-        updated.update(dependents[pkg])
-        updated.add(dir_)
-    return list(updated)
-
-
-def _get_configs_for_single_dir(job: str, dir_: str) -> List[Dict[str, str]]:
-    if job == "test-pydantic":
-        return _get_pydantic_test_configs(dir_)
-
-    if job == "codspeed":
-        py_versions = ["3.12"]  # 3.13 is not yet supported
-    elif dir_ == "libs/core":
-        py_versions = ["3.9", "3.10", "3.11", "3.12", "3.13"]
-    # custom logic for specific directories
-
-    elif dir_ in PY_312_MAX_PACKAGES:
-        py_versions = ["3.9", "3.12"]
-
-    elif dir_ == "libs/langchain" and job == "extended-tests":
-        py_versions = ["3.9", "3.13"]
-    elif dir_ == "libs/langchain_v1":
-        py_versions = ["3.10", "3.13"]
-    elif dir_ in {"libs/cli"}:
-        py_versions = ["3.10", "3.13"]
-
-    elif dir_ == ".":
-        # unable to install with 3.13 because tokenizers doesn't support 3.13 yet
-        py_versions = ["3.9", "3.12"]
-    else:
-        py_versions = ["3.9", "3.13"]
-
-    return [{"working-directory": dir_, "python-version": py_v} for py_v in py_versions]
-
-
-def _get_pydantic_test_configs(
-    dir_: str, *, python_version: str = "3.11"
-) -> List[Dict[str, str]]:
-    with open("./libs/core/uv.lock", "rb") as f:
-        core_uv_lock_data = tomllib.load(f)
-    for package in core_uv_lock_data["package"]:
-        if package["name"] == "pydantic":
-            core_max_pydantic_minor = package["version"].split(".")[1]
-            break
-
-    with open(f"./{dir_}/uv.lock", "rb") as f:
-        dir_uv_lock_data = tomllib.load(f)
-
-    for package in dir_uv_lock_data["package"]:
-        if package["name"] == "pydantic":
-            dir_max_pydantic_minor = package["version"].split(".")[1]
-            break
-
-    core_min_pydantic_version = get_min_version_from_toml(
-        "./libs/core/pyproject.toml", "release", python_version, include=["pydantic"]
-    )["pydantic"]
-    core_min_pydantic_minor = (
-        core_min_pydantic_version.split(".")[1]
-        if "." in core_min_pydantic_version
-        else "0"
-    )
-    dir_min_pydantic_version = get_min_version_from_toml(
-        f"./{dir_}/pyproject.toml", "release", python_version, include=["pydantic"]
-    ).get("pydantic", "0.0.0")
-    dir_min_pydantic_minor = (
-        dir_min_pydantic_version.split(".")[1]
-        if "." in dir_min_pydantic_version
-        else "0"
-    )
-
-    max_pydantic_minor = min(
-        int(dir_max_pydantic_minor),
-        int(core_max_pydantic_minor),
-    )
-    min_pydantic_minor = max(
-        int(dir_min_pydantic_minor),
-        int(core_min_pydantic_minor),
-    )
-
-    configs = [
-        {
-            "working-directory": dir_,
-            "pydantic-version": f"2.{v}.0",
-            "python-version": python_version,
-        }
-        for v in range(min_pydantic_minor, max_pydantic_minor + 1)
-    ]
-    return configs
-
-
-def _get_configs_for_multi_dirs(
-    job: str, dirs_to_run: Dict[str, Set[str]], dependents: dict
-) -> List[Dict[str, str]]:
-    if job == "lint":
-        dirs = add_dependents(
-            dirs_to_run["lint"] | dirs_to_run["test"] | dirs_to_run["extended-test"],
-            dependents,
-        )
-    elif job in ["test", "compile-integration-tests", "dependencies", "test-pydantic"]:
-        dirs = add_dependents(
-            dirs_to_run["test"] | dirs_to_run["extended-test"], dependents
-        )
-    elif job == "extended-tests":
-        dirs = list(dirs_to_run["extended-test"])
-    elif job == "codspeed":
-        dirs = list(dirs_to_run["codspeed"])
-    else:
-        raise ValueError(f"Unknown job: {job}")
-
-    return [
-        config for dir_ in dirs for config in _get_configs_for_single_dir(job, dir_)
-    ]
-
-
 if __name__ == "__main__":
     files = sys.argv[1:]
 
@@ -244,15 +18,11 @@ if __name__ == "__main__":
         "lint": set(),
         "test": set(),
         "extended-test": set(),
-        "codspeed": set(),
     }
-    docs_edited = False
 
-    if len(files) >= 300:
+    if len(files) == 300:
         # max diff length is 300 files - there are likely files missing
-        dirs_to_run["lint"] = all_package_dirs()
-        dirs_to_run["test"] = all_package_dirs()
-        dirs_to_run["extended-test"] = set(LANGCHAIN_DIRS)
+        raise ValueError("Max diff reached. Please manually run CI on changed libs.")
 
     for file in files:
         if any(
@@ -268,38 +38,18 @@ if __name__ == "__main__":
             dirs_to_run["extended-test"].update(LANGCHAIN_DIRS)
             dirs_to_run["lint"].add(".")
 
-        if file.startswith("libs/core"):
-            dirs_to_run["codspeed"].add(f"libs/core")
         if any(file.startswith(dir_) for dir_ in LANGCHAIN_DIRS):
             # add that dir and all dirs after in LANGCHAIN_DIRS
             # for extended testing
-
             found = False
             for dir_ in LANGCHAIN_DIRS:
-                if dir_ == "libs/core" and IGNORE_CORE_DEPENDENTS:
-                    dirs_to_run["extended-test"].add(dir_)
-                    continue
                 if file.startswith(dir_):
                     found = True
                 if found:
                     dirs_to_run["extended-test"].add(dir_)
-        elif file.startswith("libs/standard-tests"):
-            # TODO: update to include all packages that rely on standard-tests (all partner packages)
-            # Note: won't run on external repo partners
-            dirs_to_run["lint"].add("libs/standard-tests")
-            dirs_to_run["test"].add("libs/standard-tests")
-            dirs_to_run["lint"].add("libs/cli")
-            dirs_to_run["test"].add("libs/cli")
-            dirs_to_run["test"].add("libs/partners/mistralai")
-            dirs_to_run["test"].add("libs/partners/openai")
-            dirs_to_run["test"].add("libs/partners/anthropic")
-            dirs_to_run["test"].add("libs/partners/fireworks")
-            dirs_to_run["test"].add("libs/partners/groq")
-
         elif file.startswith("libs/cli"):
-            dirs_to_run["lint"].add("libs/cli")
-            dirs_to_run["test"].add("libs/cli")
-
+            # todo: add cli makefile
+            pass
         elif file.startswith("libs/partners"):
             partner_dir = file.split("/")[2]
             if os.path.isdir(f"libs/partners/{partner_dir}") and [
@@ -308,42 +58,22 @@ if __name__ == "__main__":
                 if not filename.startswith(".")
             ] != ["README.md"]:
                 dirs_to_run["test"].add(f"libs/partners/{partner_dir}")
-                dirs_to_run["codspeed"].add(f"libs/partners/{partner_dir}")
             # Skip if the directory was deleted or is just a tombstone readme
-        elif file == "libs/packages.yml":
-            continue
         elif file.startswith("libs/"):
             raise ValueError(
                 f"Unknown lib: {file}. check_diff.py likely needs "
                 "an update for this new library!"
             )
-        elif file.startswith("docs/") or file in [
-            "pyproject.toml",
-            "uv.lock",
-        ]:  # docs or root uv files
-            docs_edited = True
+        elif any(file.startswith(p) for p in ["docs/", "templates/", "cookbook/"]):
             dirs_to_run["lint"].add(".")
 
-    dependents = dependents_graph()
-
-    # we now have dirs_by_job
-    # todo: clean this up
-    map_job_to_configs = {
-        job: _get_configs_for_multi_dirs(job, dirs_to_run, dependents)
-        for job in [
-            "lint",
-            "test",
-            "extended-tests",
-            "compile-integration-tests",
-            "dependencies",
-            "test-pydantic",
-            "codspeed",
-        ]
+    outputs = {
+        "dirs-to-lint": list(
+            dirs_to_run["lint"] | dirs_to_run["test"] | dirs_to_run["extended-test"]
+        ),
+        "dirs-to-test": list(dirs_to_run["test"] | dirs_to_run["extended-test"]),
+        "dirs-to-extended-test": list(dirs_to_run["extended-test"]),
     }
-    map_job_to_configs["test-doc-imports"] = (
-        [{"python-version": "3.12"}] if docs_edited else []
-    )
-
-    for key, value in map_job_to_configs.items():
+    for key, value in outputs.items():
         json_output = json.dumps(value)
-        print(f"{key}={json_output}")
+        print(f"{key}={json_output}")  # noqa: T201

.github/scripts/check_prerelease_dependencies.py

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

.github/scripts/get_min_versions.py

@@ -1,151 +1,54 @@
-"""Get minimum versions of dependencies from a pyproject.toml file."""
-
 import sys
-from collections import defaultdict
-from typing import Optional
-
-if sys.version_info >= (3, 11):
-    import tomllib
-else:
-    # For Python 3.10 and below, which doesnt have stdlib tomllib
-    import tomli as tomllib
 
+import tomllib
+from packaging.version import parse as parse_version
 import re
-from typing import List
 
-import requests
-from packaging.requirements import Requirement
-from packaging.specifiers import SpecifierSet
-from packaging.version import Version, parse
-
-MIN_VERSION_LIBS = [
-    "langchain-core",
-    "langchain",
-    "langchain-text-splitters",
-    "numpy",
-    "SQLAlchemy",
-]
-
-# some libs only get checked on release because of simultaneous changes in
-# multiple libs
-SKIP_IF_PULL_REQUEST = [
-    "langchain-core",
-    "langchain-text-splitters",
-    "langchain",
-]
+MIN_VERSION_LIBS = ["langchain-core", "langchain-community", "langchain", "langchain-text-splitters"]
 
 
-def get_pypi_versions(package_name: str) -> List[str]:
-    """Fetch all available versions for a package from PyPI.
+def get_min_version(version: str) -> str:
+    # case ^x.x.x
+    _match = re.match(r"^\^(\d+(?:\.\d+){0,2})$", version)
+    if _match:
+        return _match.group(1)
 
-    Args:
-        package_name: Name of the package
+    # case >=x.x.x,<y.y.y
+    _match = re.match(r"^>=(\d+(?:\.\d+){0,2}),<(\d+(?:\.\d+){0,2})$", version)
+    if _match:
+        _min = _match.group(1)
+        _max = _match.group(2)
+        assert parse_version(_min) < parse_version(_max)
+        return _min
 
-    Returns:
-        List of all available versions
+    # case x.x.x
+    _match = re.match(r"^(\d+(?:\.\d+){0,2})$", version)
+    if _match:
+        return _match.group(1)
 
-    Raises:
-        requests.exceptions.RequestException: If PyPI API request fails
-        KeyError: If package not found or response format unexpected
-    """
-    pypi_url = f"https://pypi.org/pypi/{package_name}/json"
-    response = requests.get(pypi_url)
-    response.raise_for_status()
-    return list(response.json()["releases"].keys())
+    raise ValueError(f"Unrecognized version format: {version}")
 
 
-def get_minimum_version(package_name: str, spec_string: str) -> Optional[str]:
-    """Find the minimum published version that satisfies the given constraints.
-
-    Args:
-        package_name: Name of the package
-        spec_string: Version specification string (e.g., ">=0.2.43,<0.4.0,!=0.3.0")
-
-    Returns:
-        Minimum compatible version or None if no compatible version found
-    """
-    # Rewrite occurrences of ^0.0.z to 0.0.z (can be anywhere in constraint string)
-    spec_string = re.sub(r"\^0\.0\.(\d+)", r"0.0.\1", spec_string)
-    # Rewrite occurrences of ^0.y.z to >=0.y.z,<0.y+1 (can be anywhere in constraint string)
-    for y in range(1, 10):
-        spec_string = re.sub(
-            rf"\^0\.{y}\.(\d+)", rf">=0.{y}.\1,<0.{y + 1}", spec_string
-        )
-    # Rewrite occurrences of ^x.y.z to >=x.y.z,<x+1.0.0 (can be anywhere in constraint string)
-    for x in range(1, 10):
-        spec_string = re.sub(
-            rf"\^{x}\.(\d+)\.(\d+)", rf">={x}.\1.\2,<{x + 1}", spec_string
-        )
-
-    spec_set = SpecifierSet(spec_string)
-    all_versions = get_pypi_versions(package_name)
-
-    valid_versions = []
-    for version_str in all_versions:
-        try:
-            version = parse(version_str)
-            if spec_set.contains(version):
-                valid_versions.append(version)
-        except ValueError:
-            continue
-
-    return str(min(valid_versions)) if valid_versions else None
-
-
-def _check_python_version_from_requirement(
-    requirement: Requirement, python_version: str
-) -> bool:
-    if not requirement.marker:
-        return True
-    else:
-        marker_str = str(requirement.marker)
-        if "python_version" or "python_full_version" in marker_str:
-            python_version_str = "".join(
-                char
-                for char in marker_str
-                if char.isdigit() or char in (".", "<", ">", "=", ",")
-            )
-            return check_python_version(python_version, python_version_str)
-        return True
-
-
-def get_min_version_from_toml(
-    toml_path: str,
-    versions_for: str,
-    python_version: str,
-    *,
-    include: Optional[list] = None,
-):
+def get_min_version_from_toml(toml_path: str):
     # Parse the TOML file
     with open(toml_path, "rb") as file:
         toml_data = tomllib.load(file)
 
-    dependencies = defaultdict(list)
-    for dep in toml_data["project"]["dependencies"]:
-        requirement = Requirement(dep)
-        dependencies[requirement.name].append(requirement)
+    # Get the dependencies from tool.poetry.dependencies
+    dependencies = toml_data["tool"]["poetry"]["dependencies"]
 
     # Initialize a dictionary to store the minimum versions
     min_versions = {}
 
     # Iterate over the libs in MIN_VERSION_LIBS
-    for lib in set(MIN_VERSION_LIBS + (include or [])):
-        if versions_for == "pull_request" and lib in SKIP_IF_PULL_REQUEST:
-            # some libs only get checked on release because of simultaneous
-            # changes in multiple libs
-            continue
+    for lib in MIN_VERSION_LIBS:
         # Check if the lib is present in the dependencies
         if lib in dependencies:
-            if include and lib not in include:
-                continue
-            requirements = dependencies[lib]
-            for requirement in requirements:
-                if _check_python_version_from_requirement(requirement, python_version):
-                    version_string = str(requirement.specifier)
-                    break
+            # Get the version string
+            version_string = dependencies[lib]
 
             # Use parse_version to get the minimum supported version from version_string
-            min_version = get_minimum_version(lib, version_string)
+            min_version = get_min_version(version_string)
 
             # Store the minimum version in the min_versions dictionary
             min_versions[lib] = min_version
@@ -153,48 +56,12 @@ def get_min_version_from_toml(
     return min_versions
 
 
-def check_python_version(version_string, constraint_string):
-    """Check if the given Python version matches the given constraints.
+# Get the TOML file path from the command line argument
+toml_file = sys.argv[1]
 
-    Args:
-        version_string: A string representing the Python version (e.g. "3.8.5").
-        constraint_string: A string representing the package's Python version
-            constraints (e.g. ">=3.6, <4.0").
+# Call the function to get the minimum versions
+min_versions = get_min_version_from_toml(toml_file)
 
-    Returns:
-        True if the version matches the constraints
-    """
-
-    # Rewrite occurrences of ^0.0.z to 0.0.z (can be anywhere in constraint string)
-    constraint_string = re.sub(r"\^0\.0\.(\d+)", r"0.0.\1", constraint_string)
-    # Rewrite occurrences of ^0.y.z to >=0.y.z,<0.y+1.0 (can be anywhere in constraint string)
-    for y in range(1, 10):
-        constraint_string = re.sub(
-            rf"\^0\.{y}\.(\d+)", rf">=0.{y}.\1,<0.{y + 1}.0", constraint_string
-        )
-    # Rewrite occurrences of ^x.y.z to >=x.y.z,<x+1.0.0 (can be anywhere in constraint string)
-    for x in range(1, 10):
-        constraint_string = re.sub(
-            rf"\^{x}\.0\.(\d+)", rf">={x}.0.\1,<{x + 1}.0.0", constraint_string
-        )
-
-    try:
-        version = Version(version_string)
-        constraints = SpecifierSet(constraint_string)
-        return version in constraints
-    except Exception as e:
-        print(f"Error: {e}")
-        return False
-
-
-if __name__ == "__main__":
-    # Get the TOML file path from the command line argument
-    toml_file = sys.argv[1]
-    versions_for = sys.argv[2]
-    python_version = sys.argv[3]
-    assert versions_for in ["release", "pull_request"]
-
-    # Call the function to get the minimum versions
-    min_versions = get_min_version_from_toml(toml_file, versions_for, python_version)
-
-    print(" ".join([f"{lib}=={version}" for lib, version in min_versions.items()]))
+print(
+    " ".join([f"{lib}=={version}" for lib, version in min_versions.items()])
+)  # noqa: T201

.github/scripts/prep_api_docs_build.py

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

.github/tools/git-restore-mtime

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

.github/workflows/_compile_integration_test.yml

@@ -1,12 +1,4 @@
-# Validates that a package's integration tests compile without syntax or import errors.
-#
-# (If an integration test fails to compile, it won't run.)
-#
-# Called as part of check_diffs.yml workflow
-#
-# Runs pytest with compile marker to check syntax/imports.
-
-name: '🔗 Compile Integration Tests'
+name: compile-integration-test
 
 on:
   workflow_call:
@@ -15,16 +7,9 @@ on:
         required: true
         type: string
         description: "From which folder this pipeline executes"
-      python-version:
-        required: true
-        type: string
-        description: "Python version to use"
-
-permissions:
-  contents: read
 
 env:
-  UV_FROZEN: "true"
+  POETRY_VERSION: "1.7.1"
 
 jobs:
   build:
@@ -32,27 +17,34 @@ jobs:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
-    timeout-minutes: 20
-    name: 'Python ${{ inputs.python-version }}'
+    strategy:
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
+    name: "poetry run pytest -m compile tests/integration_tests #${{ matrix.python-version }}"
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v4
 
-      - name: '🐍 Set up Python ${{ inputs.python-version }} + UV'
-        uses: "./.github/actions/uv_setup"
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ inputs.python-version }}
-          cache-suffix: compile-integration-tests-${{ inputs.working-directory }}
+          python-version: ${{ matrix.python-version }}
+          poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
+          cache-key: compile-integration
 
-      - name: '📦 Install Integration Dependencies'
+      - name: Install integration dependencies
         shell: bash
-        run: uv sync --group test --group test_integration
+        run: poetry install --with=test_integration,test
 
-      - name: '🔗 Check Integration Tests Compile'
+      - name: Check integration tests compile
         shell: bash
-        run: uv run pytest -m compile tests/integration_tests
+        run: poetry run pytest -m compile tests/integration_tests
 
-      - name: '🧹 Verify Clean Working Directory'
+      - name: Ensure the tests did not create any additional files
         shell: bash
         run: |
           set -eu

.github/workflows/_dependencies.yml

@@ -0,0 +1,146 @@
+# The dependencies action runs unit tests with different versions of the package
+# dependencies.
+# This is our current solution for setting up a test matrix primarily for
+# testing compatibility with different versions of pydantic.
+# This code has some duplication with the _test action due to the need to
+# do extra logic if pydantic version 2 is installed; i.e., maybe run
+# with LC_PYDANTIC_V2_EXPERIMENTAL=True
+# The extra logic may not be worth refactoring as it'll be deleted once
+# migration to pydantic v2 proper is complete.
+name: dependencies
+
+on:
+  workflow_call:
+    inputs:
+      working-directory:
+        required: true
+        type: string
+        description: "From which folder this pipeline executes"
+      langchain-location:
+        required: false
+        type: string
+        description: "Relative path to the langchain library folder"
+
+env:
+  POETRY_VERSION: "1.7.1"
+
+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: dependency checks ${{ matrix.python-version }}
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
+        with:
+          python-version: ${{ matrix.python-version }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: ${{ inputs.working-directory }}
+          cache-key: pydantic-cross-compat
+
+      - name: Install dependencies
+        shell: bash
+        run: poetry install
+
+      - name: Check imports with base dependencies
+        shell: bash
+        run: poetry run make check_imports
+
+      - name: Install test dependencies
+        shell: bash
+        run: poetry install --with test
+
+      - name: Install langchain editable
+        working-directory: ${{ inputs.working-directory }}
+        if: ${{ inputs.langchain-location }}
+        env:
+          LANGCHAIN_LOCATION: ${{ inputs.langchain-location }}
+        run: |
+          poetry run pip install -e "$LANGCHAIN_LOCATION"
+
+      - name: Install the opposite major version of pydantic
+        # If normal tests use pydantic v1, here we'll use v2, and vice versa.
+        shell: bash
+        # airbyte currently doesn't support pydantic v2
+        if: ${{ !startsWith(inputs.working-directory, 'libs/partners/airbyte') }}
+        run: |
+          # Determine the major part of pydantic version
+          REGULAR_VERSION=$(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
+        # airbyte currently doesn't support pydantic v2
+        if: ${{ !startsWith(inputs.working-directory, 'libs/partners/airbyte') }}
+        shell: bash
+        run: make test
+      - name: Maybe run unit tests with LC_PYDANTIC_V2_EXPERIMENTAL=True
+        # This step will run unit tests if pydantic>=2.0.0 is installed
+        # It will run unit tests with the environment variable LC_PYDANTIC_V2_EXPERIMENTAL=True
+        # libraries that support the flag, will attempt to run unit tests
+        # using pydantic proper rather than via the pydantic.v1 namespace.
+        # TODO: Refactor how code is tested with LC_PYDANTIC_V2_EXPERIMENTAL=True
+        # We should probably have a JSON file that lists which code paths
+        # that support the flag
+        if: ${{ !startsWith(inputs.working-directory, 'libs/core/') }}
+        shell: bash
+        run: |
+          # Determine the major part of pydantic version
+          REGULAR_VERSION=$(poetry run python -c "import pydantic; print(pydantic.__version__)" | cut -d. -f1)
+          # If version 2 then we run tests with LC_PYDANTIC_V2_EXPERIMENTAL=True
+          # Otherwise echo that there's nothing to do since the version is 1
+          if [[ "$REGULAR_VERSION" == "2" ]]; then
+            LC_PYDANTIC_V2_EXPERIMENTAL=True make test 
+            echo "Finished running unit tests with LC_PYDANTIC_V2_EXPERIMENTAL=True"
+          else
+            echo "No running tests with LC_PYDANTIC_V2_EXPERIMENTAL=True since pydantic version is 1"
+          fi
+      - name: Ensure the tests did not create any additional files
+        shell: bash
+        run: |
+          set -eu
+
+          STATUS="$(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/_integration_test.yml

@@ -1,12 +1,4 @@
-
-# Runs `make integration_tests` on the specified package.
-#
-# Manually triggered via workflow_dispatch for testing with real APIs.
-#
-# Installs integration test dependencies and executes full test suite.
-
-name: '🚀 Integration Tests'
-run-name: 'Test ${{ inputs.working-directory }} on Python ${{ inputs.python-version }}'
+name: Integration tests
 
 on:
   workflow_dispatch:
@@ -14,83 +6,79 @@ on:
       working-directory:
         required: true
         type: string
-        description: "From which folder this pipeline executes"
-      python-version:
-        required: true
-        type: string
-        description: "Python version to use"
-        default: "3.11"
-
-permissions:
-  contents: read
 
 env:
-  UV_FROZEN: "true"
+  POETRY_VERSION: "1.7.1"
 
 jobs:
   build:
+    environment: Scheduled testing
     defaults:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
-    name: 'Python ${{ inputs.python-version }}'
+    strategy:
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.11"
+    name: Python ${{ matrix.python-version }}
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v4
 
-      - name: '🐍 Set up Python ${{ inputs.python-version }} + UV'
-        uses: "./.github/actions/uv_setup"
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ inputs.python-version }}
-          cache-suffix: integration-tests-${{ inputs.working-directory }}
+          python-version: ${{ matrix.python-version }}
+          poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
+          cache-key: core
 
-      - name: '📦 Install Integration Dependencies'
+      - name: Install dependencies
         shell: bash
-        run: uv sync --group test --group test_integration
+        run: poetry install --with test,test_integration
 
-      - name: '🚀 Run Integration Tests'
+      - name: Install deps outside pyproject
+        if: ${{ startsWith(inputs.working-directory, 'libs/community/') }}
+        shell: bash
+        run: poetry run pip install "boto3<2" "google-cloud-aiplatform<2"
+
+      - name: 'Authenticate to Google Cloud'
+        id: 'auth'
+        uses: google-github-actions/auth@v2
+        with:
+          credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
+
+      - name: Run integration tests
         shell: bash
         env:
           AI21_API_KEY: ${{ secrets.AI21_API_KEY }}
-          FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
           GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
           ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
-          ANTHROPIC_FILES_API_IMAGE_ID: ${{ secrets.ANTHROPIC_FILES_API_IMAGE_ID }}
-          ANTHROPIC_FILES_API_PDF_ID: ${{ secrets.ANTHROPIC_FILES_API_PDF_ID }}
-          AZURE_OPENAI_API_VERSION: ${{ secrets.AZURE_OPENAI_API_VERSION }}
-          AZURE_OPENAI_API_BASE: ${{ secrets.AZURE_OPENAI_API_BASE }}
-          AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
-          AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_CHAT_DEPLOYMENT_NAME }}
-          AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME }}
-          AZURE_OPENAI_LLM_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LLM_DEPLOYMENT_NAME }}
-          AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME }}
           MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
           TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
           NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}
           GOOGLE_SEARCH_API_KEY: ${{ secrets.GOOGLE_SEARCH_API_KEY }}
           GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
-          HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
           EXA_API_KEY: ${{ secrets.EXA_API_KEY }}
           NOMIC_API_KEY: ${{ secrets.NOMIC_API_KEY }}
           WATSONX_APIKEY: ${{ secrets.WATSONX_APIKEY }}
           WATSONX_PROJECT_ID: ${{ secrets.WATSONX_PROJECT_ID }}
+          PINECONE_API_KEY: ${{ secrets.PINECONE_API_KEY }}
+          PINECONE_ENVIRONMENT: ${{ secrets.PINECONE_ENVIRONMENT }}
           ASTRA_DB_API_ENDPOINT: ${{ secrets.ASTRA_DB_API_ENDPOINT }}
           ASTRA_DB_APPLICATION_TOKEN: ${{ secrets.ASTRA_DB_APPLICATION_TOKEN }}
           ASTRA_DB_KEYSPACE: ${{ secrets.ASTRA_DB_KEYSPACE }}
           ES_URL: ${{ secrets.ES_URL }}
           ES_CLOUD_ID: ${{ secrets.ES_CLOUD_ID }}
           ES_API_KEY: ${{ secrets.ES_API_KEY }}
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} # for airbyte
           MONGODB_ATLAS_URI: ${{ secrets.MONGODB_ATLAS_URI }}
-          COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
-          UPSTAGE_API_KEY: ${{ secrets.UPSTAGE_API_KEY }}
-          XAI_API_KEY: ${{ secrets.XAI_API_KEY }}
-          PPLX_API_KEY: ${{ secrets.PPLX_API_KEY }}
         run: |
           make integration_tests
 
-      - name: 'Ensure testing did not create/modify files'
+      - name: Ensure the tests did not create any additional files
         shell: bash
         run: |
           set -eu

.github/workflows/_lint.yml

@@ -1,11 +1,4 @@
-# Runs linting.
-#
-# Uses the package's Makefile to run the checks, specifically the
-# `lint_package` and `lint_tests` targets.
-#
-# Called as part of check_diffs.yml workflow.
-
-name: '🧹 Linting'
+name: lint
 
 on:
   workflow_call:
@@ -14,62 +7,122 @@ on:
         required: true
         type: string
         description: "From which folder this pipeline executes"
-      python-version:
-        required: true
+      langchain-location:
+        required: false
         type: string
-        description: "Python version to use"
-
-permissions:
-  contents: read
+        description: "Relative path to the langchain library folder"
 
 env:
+  POETRY_VERSION: "1.7.1"
   WORKDIR: ${{ inputs.working-directory == '' && '.' || inputs.working-directory }}
 
   # This env var allows us to get inline annotations when ruff has complaints.
   RUFF_OUTPUT_FORMAT: github
 
-  UV_FROZEN: "true"
-
 jobs:
-  # Linting job - runs quality checks on package and test code
   build:
-    name: 'Python ${{ inputs.python-version }}'
+    name: "make lint #${{ matrix.python-version }}"
     runs-on: ubuntu-latest
-    timeout-minutes: 20
+    strategy:
+      matrix:
+        # Only lint on the min and max supported Python versions.
+        # It's extremely unlikely that there's a lint issue on any version in between
+        # that doesn't show up on the min or max versions.
+        #
+        # GitHub rate-limits how many jobs can be running at any one time.
+        # Starting new jobs is also relatively slow,
+        # so linting on fewer versions makes CI faster.
+        python-version:
+          - "3.8"
+          - "3.11"
     steps:
-      - name: '📋 Checkout Code'
-        uses: actions/checkout@v5
+      - uses: actions/checkout@v4
 
-      - name: '🐍 Set up Python ${{ inputs.python-version }} + UV'
-        uses: "./.github/actions/uv_setup"
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ inputs.python-version }}
-          cache-suffix: lint-${{ inputs.working-directory }}
+          python-version: ${{ matrix.python-version }}
+          poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
+          cache-key: lint-with-extras
 
-      - name: '📦 Install Lint & Typing Dependencies'
+      - name: Check Poetry File
+        shell: bash
         working-directory: ${{ inputs.working-directory }}
         run: |
-          uv sync --group lint --group typing
+          poetry check
 
-      - name: '🔍 Analyze Package Code with Linters'
+      - name: Check lock file
+        shell: bash
+        working-directory: ${{ inputs.working-directory }}
+        run: |
+          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 lint,typing
+
+      - name: Install langchain editable
+        working-directory: ${{ inputs.working-directory }}
+        if: ${{ inputs.langchain-location }}
+        env:
+          LANGCHAIN_LOCATION: ${{ inputs.langchain-location }}
+        run: |
+          poetry run pip install -e "$LANGCHAIN_LOCATION"
+
+      - name: Get .mypy_cache to speed up mypy
+        uses: actions/cache@v4
+        env:
+          SEGMENT_DOWNLOAD_TIMEOUT_MIN: "2"
+        with:
+          path: |
+            ${{ env.WORKDIR }}/.mypy_cache
+          key: mypy-lint-${{ runner.os }}-${{ runner.arch }}-py${{ matrix.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}
+
+
+      - name: Analysing the code with our lint
         working-directory: ${{ inputs.working-directory }}
         run: |
           make lint_package
 
-      - name: '📦 Install Test Dependencies (non-partners)'
-        # (For directories NOT starting with libs/partners/)
+      - name: Install unit test 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.
         if: ${{ ! startsWith(inputs.working-directory, 'libs/partners/') }}
         working-directory: ${{ inputs.working-directory }}
         run: |
-          uv sync --inexact --group test
-      - name: '📦 Install Test Dependencies'
+          poetry install --with test
+      - name: Install unit+integration test dependencies
         if: ${{ startsWith(inputs.working-directory, 'libs/partners/') }}
         working-directory: ${{ inputs.working-directory }}
         run: |
-          uv sync --inexact --group test --group test_integration
+          poetry install --with test,test_integration
 
-      - name: '🔍 Analyze Test Code with Linters'
+      - name: Get .mypy_cache_test to speed up mypy
+        uses: actions/cache@v4
+        env:
+          SEGMENT_DOWNLOAD_TIMEOUT_MIN: "2"
+        with:
+          path: |
+            ${{ env.WORKDIR }}/.mypy_cache_test
+          key: mypy-test-${{ runner.os }}-${{ runner.arch }}-py${{ matrix.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}
+
+      - name: Analysing the code with our lint
         working-directory: ${{ inputs.working-directory }}
         run: |
           make lint_tests

.github/workflows/_release.yml

@@ -1,11 +1,5 @@
-# Builds and publishes LangChain packages to PyPI.
-#
-# Manually triggered, though can be used as a reusable workflow (workflow_call).
-#
-# Handles version bumping, building, and publishing to PyPI with authentication.
-
-name: '🚀 Package Release'
-run-name: 'Release ${{ inputs.working-directory }} ${{ inputs.release-version }}'
+name: release
+run-name: Release ${{ inputs.working-directory }} by @${{ github.actor }}
 on:
   workflow_call:
     inputs:
@@ -18,29 +12,15 @@ on:
       working-directory:
         required: true
         type: string
-        description: "From which folder this pipeline executes"
         default: 'libs/langchain'
-      release-version:
-        required: true
-        type: string
-        default: '0.1.0'
-        description: "New version of package being released"
-      dangerous-nonmaster-release:
-        required: false
-        type: boolean
-        default: false
-        description: "Release from a non-master branch (danger!) - Only use for hotfixes"
 
 env:
   PYTHON_VERSION: "3.11"
-  UV_FROZEN: "true"
-  UV_NO_SYNC: "true"
+  POETRY_VERSION: "1.7.1"
 
 jobs:
-  # Build the distribution package and extract version info
-  # Runs in isolated environment with minimal permissions for security
   build:
-    if: github.ref == 'refs/heads/master' || inputs.dangerous-nonmaster-release
+    if: github.ref == 'refs/heads/master'
     environment: Scheduled testing
     runs-on: ubuntu-latest
 
@@ -49,17 +29,20 @@ jobs:
       version: ${{ steps.check-version.outputs.version }}
 
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v4
 
-      - name: Set up Python + uv
-        uses: "./.github/actions/uv_setup"
+      - name: Set up Python + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
         with:
           python-version: ${{ env.PYTHON_VERSION }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: ${{ inputs.working-directory }}
+          cache-key: release
 
       # We want to keep this build stage *separate* from the release stage,
       # so that there's no sharing of permissions between them.
-      # (Release stage has trusted publishing and GitHub repo contents write access,
-      #
+      # The release stage has trusted publishing and GitHub repo contents write access,
+      # and we want to keep the scope of that access limited just to the release job.
       # Otherwise, a malicious `build` step (e.g. via a compromised dependency)
       # could get access to our GitHub or PyPI credentials.
       #
@@ -68,7 +51,7 @@ jobs:
       # > from the publish job.
       # https://github.com/pypa/gh-action-pypi-publish#non-goals
       - name: Build project for distribution
-        run: uv build
+        run: poetry build
         working-directory: ${{ inputs.working-directory }}
 
       - name: Upload build
@@ -77,158 +60,30 @@ jobs:
           name: dist
           path: ${{ inputs.working-directory }}/dist/
 
-      - name: Check version
+      - name: Check Version
         id: check-version
-        shell: python
+        shell: bash
         working-directory: ${{ inputs.working-directory }}
         run: |
-          import os
-          import tomllib
-          with open("pyproject.toml", "rb") as f:
-              data = tomllib.load(f)
-          pkg_name = data["project"]["name"]
-          version = data["project"]["version"]
-          with open(os.environ["GITHUB_OUTPUT"], "a") as f:
-              f.write(f"pkg-name={pkg_name}\n")
-              f.write(f"version={version}\n")
-  release-notes:
-    needs:
-      - build
-    runs-on: ubuntu-latest
-    outputs:
-      release-body: ${{ steps.generate-release-body.outputs.release-body }}
-    steps:
-      - uses: actions/checkout@v5
-        with:
-          repository: langchain-ai/langchain
-          path: langchain
-          sparse-checkout: | # this only grabs files for relevant dir
-            ${{ inputs.working-directory }}
-          ref: ${{ github.ref }} # this scopes to just ref'd branch
-          fetch-depth: 0 # this fetches entire commit history
-      - name: Check tags
-        id: check-tags
-        shell: bash
-        working-directory: langchain/${{ inputs.working-directory }}
-        env:
-          PKG_NAME: ${{ needs.build.outputs.pkg-name }}
-          VERSION: ${{ needs.build.outputs.version }}
-        run: |
-          # Handle regular versions and pre-release versions differently
-          if [[ "$VERSION" == *"-"* ]]; then
-            # This is a pre-release version (contains a hyphen)
-            # Extract the base version without the pre-release suffix
-            BASE_VERSION=${VERSION%%-*}
-            # Look for the latest release of the same base version
-            REGEX="^$PKG_NAME==$BASE_VERSION\$"
-            PREV_TAG=$(git tag --sort=-creatordate | (grep -P "$REGEX" || true) | head -1)
-
-            # If no exact base version match, look for the latest release of any kind
-            if [ -z "$PREV_TAG" ]; then
-              REGEX="^$PKG_NAME==\\d+\\.\\d+\\.\\d+\$"
-              PREV_TAG=$(git tag --sort=-creatordate | (grep -P "$REGEX" || true) | head -1)
-            fi
-          else
-            # Regular version handling
-            PREV_TAG="$PKG_NAME==${VERSION%.*}.$(( ${VERSION##*.} - 1 ))"; [[ "${VERSION##*.}" -eq 0 ]] && PREV_TAG=""
-
-            # backup case if releasing e.g. 0.3.0, looks up last release
-            # note if last release (chronologically) was e.g. 0.1.47 it will get
-            # that instead of the last 0.2 release
-            if [ -z "$PREV_TAG" ]; then
-              REGEX="^$PKG_NAME==\\d+\\.\\d+\\.\\d+\$"
-              echo $REGEX
-              PREV_TAG=$(git tag --sort=-creatordate | (grep -P $REGEX || true) | head -1)
-            fi
-          fi
-
-          # if PREV_TAG is empty, let it be empty
-          if [ -z "$PREV_TAG" ]; then
-            echo "No previous tag found - first release"
-          else
-            # confirm prev-tag actually exists in git repo with git tag
-            GIT_TAG_RESULT=$(git tag -l "$PREV_TAG")
-            if [ -z "$GIT_TAG_RESULT" ]; then
-              echo "Previous tag $PREV_TAG not found in git repo"
-              exit 1
-            fi
-          fi
-
-
-          TAG="${PKG_NAME}==${VERSION}"
-          if [ "$TAG" == "$PREV_TAG" ]; then
-            echo "No new version to release"
-            exit 1
-          fi
-          echo tag="$TAG" >> $GITHUB_OUTPUT
-          echo prev-tag="$PREV_TAG" >> $GITHUB_OUTPUT
-      - name: Generate release body
-        id: generate-release-body
-        working-directory: langchain
-        env:
-          WORKING_DIR: ${{ inputs.working-directory }}
-          PKG_NAME: ${{ needs.build.outputs.pkg-name }}
-          TAG: ${{ steps.check-tags.outputs.tag }}
-          PREV_TAG: ${{ steps.check-tags.outputs.prev-tag }}
-        run: |
-          PREAMBLE="Changes since $PREV_TAG"
-          # if PREV_TAG is empty, then we are releasing the first version
-          if [ -z "$PREV_TAG" ]; then
-            PREAMBLE="Initial release"
-            PREV_TAG=$(git rev-list --max-parents=0 HEAD)
-          fi
-          {
-            echo 'release-body<<EOF'
-            echo $PREAMBLE
-            echo
-            git log --format="%s" "$PREV_TAG"..HEAD -- $WORKING_DIR
-            echo EOF
-          } >> "$GITHUB_OUTPUT"
+          echo pkg-name="$(poetry version | cut -d ' ' -f 1)" >> $GITHUB_OUTPUT
+          echo version="$(poetry version --short)" >> $GITHUB_OUTPUT
 
   test-pypi-publish:
     needs:
       - build
-      - release-notes
-    runs-on: ubuntu-latest
-    permissions:
-      # This permission is used for trusted publishing:
-      # https://blog.pypi.org/posts/2023-04-20-introducing-trusted-publishers/
-      #
-      # Trusted publishing has to also be configured on PyPI for each package:
-      # https://docs.pypi.org/trusted-publishers/adding-a-publisher/
-      id-token: write
-
-    steps:
-      - uses: actions/checkout@v5
-
-      - uses: actions/download-artifact@v5
-        with:
-          name: dist
-          path: ${{ inputs.working-directory }}/dist/
-
-      - name: Publish to test PyPI
-        uses: pypa/gh-action-pypi-publish@release/v1
-        with:
-          packages-dir: ${{ inputs.working-directory }}/dist/
-          verbose: true
-          print-hash: true
-          repository-url: https://test.pypi.org/legacy/
-          # We overwrite any existing distributions with the same name and version.
-          # This is *only for CI use* and is *extremely dangerous* otherwise!
-          # https://github.com/pypa/gh-action-pypi-publish#tolerating-release-package-file-duplicates
-          skip-existing: true
-          # Temp workaround since attestations are on by default as of gh-action-pypi-publish v1.11.0
-          attestations: false
+    uses:
+      ./.github/workflows/_test_release.yml
+    with:
+      working-directory: ${{ inputs.working-directory }}
+    secrets: inherit
 
   pre-release-checks:
     needs:
       - build
-      - release-notes
       - test-pypi-publish
     runs-on: ubuntu-latest
-    timeout-minutes: 20
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v4
 
       # We explicitly *don't* set up caching here. This ensures our tests are
       # maximally sensitive to catching breakage.
@@ -243,25 +98,21 @@ jobs:
       # - The package is published, and it breaks on the missing dependency when
       #   used in the real world.
 
-      - name: Set up Python + uv
-        uses: "./.github/actions/uv_setup"
-        id: setup-python
+      - name: Set up Python + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
         with:
           python-version: ${{ env.PYTHON_VERSION }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: ${{ inputs.working-directory }}
 
-      - uses: actions/download-artifact@v5
-        with:
-          name: dist
-          path: ${{ inputs.working-directory }}/dist/
-
-      - name: Import dist package
+      - name: Import published package
         shell: bash
         working-directory: ${{ inputs.working-directory }}
         env:
           PKG_NAME: ${{ needs.build.outputs.pkg-name }}
           VERSION: ${{ needs.build.outputs.version }}
         # Here we use:
-        # - The default regular PyPI index as the *primary* index, meaning
+        # - The default regular PyPI index as the *primary* index, meaning 
         #   that it takes priority (https://pypi.org/simple)
         # - The test PyPI index as an extra index, so that any dependencies that
         #   are not found on test PyPI can be resolved and installed anyway.
@@ -270,21 +121,27 @@ jobs:
         # - attempt install again after 5 seconds if it fails because there is
         #   sometimes a delay in availability on test pypi
         run: |
-          uv venv
-          VIRTUAL_ENV=.venv uv pip install dist/*.whl
+          poetry run pip install \
+            --extra-index-url https://test.pypi.org/simple/ \
+            "$PKG_NAME==$VERSION" || \
+          ( \
+            sleep 5 && \
+            poetry run pip install \
+              --extra-index-url https://test.pypi.org/simple/ \
+              "$PKG_NAME==$VERSION" \
+          )
 
           # Replace all dashes in the package name with underscores,
           # since that's how Python imports packages with dashes in the name.
-          # also remove _official suffix
-          IMPORT_NAME="$(echo "$PKG_NAME" | sed s/-/_/g | sed s/_official//g)"
+          IMPORT_NAME="$(echo "$PKG_NAME" | sed s/-/_/g)"
 
-          uv run python -c "import $IMPORT_NAME; print(dir($IMPORT_NAME))"
+          poetry run python -c "import $IMPORT_NAME; print(dir($IMPORT_NAME))"
 
       - name: Import test dependencies
-        run: uv sync --group test
+        run: poetry install --with test,test_integration
         working-directory: ${{ inputs.working-directory }}
 
-      # Overwrite the local version of the package with the built version
+      # Overwrite the local version of the package with the test PyPI version.
       - name: Import published package (again)
         working-directory: ${{ inputs.working-directory }}
         shell: bash
@@ -292,46 +149,21 @@ jobs:
           PKG_NAME: ${{ needs.build.outputs.pkg-name }}
           VERSION: ${{ needs.build.outputs.version }}
         run: |
-          VIRTUAL_ENV=.venv uv pip install dist/*.whl
-
-      - name: Check for prerelease versions
-        # Block release if any dependencies allow prerelease versions
-        # (unless this is itself a prerelease version)
-        working-directory: ${{ inputs.working-directory }}
-        run: |
-          uv run python $GITHUB_WORKSPACE/.github/scripts/check_prerelease_dependencies.py pyproject.toml
+          poetry run pip install \
+            --extra-index-url https://test.pypi.org/simple/ \
+            "$PKG_NAME==$VERSION"
 
       - name: Run unit tests
         run: make tests
         working-directory: ${{ inputs.working-directory }}
 
-      - name: Get minimum versions
-        # Find the minimum published versions that satisfies the given constraints
-        working-directory: ${{ inputs.working-directory }}
-        id: min-version
-        run: |
-          VIRTUAL_ENV=.venv uv pip install packaging requests
-          python_version="$(uv run python --version | awk '{print $2}')"
-          min_versions="$(uv run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml release $python_version)"
-          echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"
-          echo "min-versions=$min_versions"
-
-      - name: Run unit tests with minimum dependency versions
-        if: ${{ steps.min-version.outputs.min-versions != '' }}
-        env:
-          MIN_VERSIONS: ${{ steps.min-version.outputs.min-versions }}
-        run: |
-          VIRTUAL_ENV=.venv uv pip install --force-reinstall --editable .
-          VIRTUAL_ENV=.venv uv pip install --force-reinstall $MIN_VERSIONS
-          make tests
-        working-directory: ${{ inputs.working-directory }}
-
-      - name: Import integration test dependencies
-        run: uv sync --group test --group test_integration
-        working-directory: ${{ inputs.working-directory }}
+      - name: 'Authenticate to Google Cloud'
+        id: 'auth'
+        uses: google-github-actions/auth@v2
+        with:
+          credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
 
       - name: Run integration tests
-        # Uses the Makefile's `integration_tests` target for the specified package
         if: ${{ startsWith(inputs.working-directory, 'libs/partners/') }}
         env:
           AI21_API_KEY: ${{ secrets.AI21_API_KEY }}
@@ -344,127 +176,52 @@ jobs:
           AZURE_OPENAI_API_BASE: ${{ secrets.AZURE_OPENAI_API_BASE }}
           AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
           AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_CHAT_DEPLOYMENT_NAME }}
-          AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME }}
           AZURE_OPENAI_LLM_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LLM_DEPLOYMENT_NAME }}
           AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME }}
           NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}
           GOOGLE_SEARCH_API_KEY: ${{ secrets.GOOGLE_SEARCH_API_KEY }}
           GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
           GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
-          HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
           EXA_API_KEY: ${{ secrets.EXA_API_KEY }}
           NOMIC_API_KEY: ${{ secrets.NOMIC_API_KEY }}
           WATSONX_APIKEY: ${{ secrets.WATSONX_APIKEY }}
           WATSONX_PROJECT_ID: ${{ secrets.WATSONX_PROJECT_ID }}
+          PINECONE_API_KEY: ${{ secrets.PINECONE_API_KEY }}
+          PINECONE_ENVIRONMENT: ${{ secrets.PINECONE_ENVIRONMENT }}
           ASTRA_DB_API_ENDPOINT: ${{ secrets.ASTRA_DB_API_ENDPOINT }}
           ASTRA_DB_APPLICATION_TOKEN: ${{ secrets.ASTRA_DB_APPLICATION_TOKEN }}
           ASTRA_DB_KEYSPACE: ${{ secrets.ASTRA_DB_KEYSPACE }}
           ES_URL: ${{ secrets.ES_URL }}
           ES_CLOUD_ID: ${{ secrets.ES_CLOUD_ID }}
           ES_API_KEY: ${{ secrets.ES_API_KEY }}
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} # for airbyte
           MONGODB_ATLAS_URI: ${{ secrets.MONGODB_ATLAS_URI }}
-          UPSTAGE_API_KEY: ${{ secrets.UPSTAGE_API_KEY }}
-          FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
-          XAI_API_KEY: ${{ secrets.XAI_API_KEY }}
-          DEEPSEEK_API_KEY: ${{ secrets.DEEPSEEK_API_KEY }}
-          PPLX_API_KEY: ${{ secrets.PPLX_API_KEY }}
         run: make integration_tests
         working-directory: ${{ inputs.working-directory }}
 
-  # Test select published packages against new core
-  # Done when code changes are made to langchain-core
-  test-prior-published-packages-against-new-core:
-    # Installs the new core with old partners: Installs the new unreleased core
-    # alongside the previously published partner packages and runs integration tests
-    needs:
-      - build
-      - release-notes
-      - test-pypi-publish
-      - pre-release-checks
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        partner: [openai, anthropic]
-      fail-fast: false  # Continue testing other partners if one fails
-    env:
-      ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
-      ANTHROPIC_FILES_API_IMAGE_ID: ${{ secrets.ANTHROPIC_FILES_API_IMAGE_ID }}
-      ANTHROPIC_FILES_API_PDF_ID: ${{ secrets.ANTHROPIC_FILES_API_PDF_ID }}
-      OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-      AZURE_OPENAI_API_VERSION: ${{ secrets.AZURE_OPENAI_API_VERSION }}
-      AZURE_OPENAI_API_BASE: ${{ secrets.AZURE_OPENAI_API_BASE }}
-      AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
-      AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_CHAT_DEPLOYMENT_NAME }}
-      AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME }}
-      AZURE_OPENAI_LLM_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LLM_DEPLOYMENT_NAME }}
-      AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME }}
-    steps:
-      - uses: actions/checkout@v5
-
-      # We implement this conditional as Github Actions does not have good support
-      # for conditionally needing steps. https://github.com/actions/runner/issues/491
-      # TODO: this seems to be resolved upstream, so we can probably remove this workaround
-      - name: Check if libs/core
+      - name: Get minimum versions
+        working-directory: ${{ inputs.working-directory }}
+        id: min-version
         run: |
-          if [ "${{ startsWith(inputs.working-directory, 'libs/core') }}" != "true" ]; then
-            echo "Not in libs/core. Exiting successfully."
-            exit 0
-          fi
+          poetry run pip install packaging
+          min_versions="$(poetry run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml)"
+          echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"
+          echo "min-versions=$min_versions"
 
-      - name: Set up Python + uv
-        if: startsWith(inputs.working-directory, 'libs/core')
-        uses: "./.github/actions/uv_setup"
-        with:
-          python-version: ${{ env.PYTHON_VERSION }}
-
-      - uses: actions/download-artifact@v5
-        if: startsWith(inputs.working-directory, 'libs/core')
-        with:
-          name: dist
-          path: ${{ inputs.working-directory }}/dist/
-
-      - name: Test against ${{ matrix.partner }}
-        if: startsWith(inputs.working-directory, 'libs/core')
+      - name: Run unit tests with minimum dependency versions
+        if: ${{ steps.min-version.outputs.min-versions != '' }}
+        env:
+          MIN_VERSIONS: ${{ steps.min-version.outputs.min-versions }}
         run: |
-          # Identify latest tag, excluding pre-releases
-          LATEST_PACKAGE_TAG="$(
-            git ls-remote --tags origin "langchain-${{ matrix.partner }}*" \
-            | awk '{print $2}' \
-            | sed 's|refs/tags/||' \
-            | grep -E '[0-9]+\.[0-9]+\.[0-9]+$' \
-            | sort -Vr \
-            | head -n 1
-          )"
-          echo "Latest package tag: $LATEST_PACKAGE_TAG"
-
-          # Shallow-fetch just that single tag
-          git fetch --depth=1 origin tag "$LATEST_PACKAGE_TAG"
-
-          # Checkout the latest package files
-          rm -rf $GITHUB_WORKSPACE/libs/partners/${{ matrix.partner }}/*
-          rm -rf $GITHUB_WORKSPACE/libs/standard-tests/*
-          cd $GITHUB_WORKSPACE/libs/
-          git checkout "$LATEST_PACKAGE_TAG" -- standard-tests/
-          git checkout "$LATEST_PACKAGE_TAG" -- partners/${{ matrix.partner }}/
-          cd partners/${{ matrix.partner }}
-
-          # Print as a sanity check
-          echo "Version number from pyproject.toml: "
-          cat pyproject.toml | grep "version = "
-
-          # Run tests
-          uv sync --group test --group test_integration
-          uv pip install ../../core/dist/*.whl
-          make integration_tests
+          poetry run pip install $MIN_VERSIONS
+          make tests
+        working-directory: ${{ inputs.working-directory }}
 
   publish:
-    # Publishes the package to PyPI
     needs:
       - build
-      - release-notes
       - test-pypi-publish
       - pre-release-checks
-      - test-prior-published-packages-against-new-core
     runs-on: ubuntu-latest
     permissions:
       # This permission is used for trusted publishing:
@@ -479,14 +236,17 @@ jobs:
         working-directory: ${{ inputs.working-directory }}
 
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v4
 
-      - name: Set up Python + uv
-        uses: "./.github/actions/uv_setup"
+      - name: Set up Python + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
         with:
           python-version: ${{ env.PYTHON_VERSION }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: ${{ inputs.working-directory }}
+          cache-key: release
 
-      - uses: actions/download-artifact@v5
+      - uses: actions/download-artifact@v4
         with:
           name: dist
           path: ${{ inputs.working-directory }}/dist/
@@ -497,21 +257,17 @@ jobs:
           packages-dir: ${{ inputs.working-directory }}/dist/
           verbose: true
           print-hash: true
-          # Temp workaround since attestations are on by default as of gh-action-pypi-publish v1.11.0
-          attestations: false
 
   mark-release:
-    # Marks the GitHub release with the new version tag
     needs:
       - build
-      - release-notes
       - test-pypi-publish
       - pre-release-checks
       - publish
     runs-on: ubuntu-latest
     permissions:
       # This permission is needed by `ncipollo/release-action` to
-      # create the GitHub release/tag
+      # create the GitHub release.
       contents: write
 
     defaults:
@@ -519,25 +275,28 @@ jobs:
         working-directory: ${{ inputs.working-directory }}
 
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v4
 
-      - name: Set up Python + uv
-        uses: "./.github/actions/uv_setup"
+      - name: Set up Python + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
         with:
           python-version: ${{ env.PYTHON_VERSION }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: ${{ inputs.working-directory }}
+          cache-key: release
 
-      - uses: actions/download-artifact@v5
+      - uses: actions/download-artifact@v4
         with:
           name: dist
           path: ${{ inputs.working-directory }}/dist/
 
-      - name: Create Tag
+      - name: Create Release
         uses: ncipollo/release-action@v1
+        if: ${{ inputs.working-directory == 'libs/langchain' }}
         with:
           artifacts: "dist/*"
           token: ${{ secrets.GITHUB_TOKEN }}
-          generateReleaseNotes: false
-          tag: ${{needs.build.outputs.pkg-name}}==${{ needs.build.outputs.version }}
-          body: ${{ needs.release-notes.outputs.release-body }}
-          commit: ${{ github.sha }}
-          makeLatest: ${{ needs.build.outputs.pkg-name == 'langchain-core'}}
+          draft: false
+          generateReleaseNotes: true
+          tag: v${{ needs.build.outputs.version }}
+          commit: master

.github/workflows/_release_docker.yml

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

.github/workflows/_test.yml

@@ -1,7 +1,4 @@
-# Runs unit tests with both current and minimum supported dependency versions
-# to ensure compatibility across the supported range.
-
-name: '🧪 Unit Testing'
+name: test
 
 on:
   workflow_call:
@@ -10,69 +7,78 @@ on:
         required: true
         type: string
         description: "From which folder this pipeline executes"
-      python-version:
-        required: true
+      langchain-location:
+        required: false
         type: string
-        description: "Python version to use"
-
-permissions:
-  contents: read
+        description: "Relative path to the langchain library folder"
 
 env:
-  UV_FROZEN: "true"
-  UV_NO_SYNC: "true"
+  POETRY_VERSION: "1.7.1"
 
 jobs:
-  # Main test job - runs unit tests with current deps, then retests with minimum versions
   build:
     defaults:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
-    timeout-minutes: 20
-    name: 'Python ${{ inputs.python-version }}'
+    strategy:
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
+    name: "make test #${{ matrix.python-version }}"
     steps:
-      - name: '📋 Checkout Code'
-        uses: actions/checkout@v5
+      - uses: actions/checkout@v4
 
-      - name: '🐍 Set up Python ${{ inputs.python-version }} + UV'
-        uses: "./.github/actions/uv_setup"
-        id: setup-python
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ inputs.python-version }}
-          cache-suffix: test-${{ inputs.working-directory }}
+          python-version: ${{ matrix.python-version }}
+          poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
+          cache-key: core
 
-      - name: '📦 Install Test Dependencies'
+      - name: Install dependencies
         shell: bash
-        run: uv sync --group test --dev
+        run: poetry install --with test
 
-      - name: '🧪 Run Core Unit Tests'
+      - name: Install langchain editable
+        working-directory: ${{ inputs.working-directory }}
+        if: ${{ inputs.langchain-location }}
+        env:
+          LANGCHAIN_LOCATION: ${{ inputs.langchain-location }}
+        run: |
+          poetry run pip install -e "$LANGCHAIN_LOCATION"
+
+      - name: Run core tests
         shell: bash
         run: |
           make test
 
-      - name: '🔍 Calculate Minimum Dependency Versions'
-        working-directory: ${{ inputs.working-directory }}
-        id: min-version
+      - name: Maybe run unit tests with LC_PYDANTIC_V2_EXPERIMENTAL=True
+        # This step will run unit tests if pydantic>=2.0.0 is installed
+        # It will run unit tests with the environment variable LC_PYDANTIC_V2_EXPERIMENTAL=True
+        # libraries that support the flag, will attempt to run unit tests
+        # using pydantic proper rather than via the pydantic.v1 namespace.
+        # TODO: Refactor how code is tested with LC_PYDANTIC_V2_EXPERIMENTAL=True
+        # We should probably have a JSON file that lists which code paths
+        # that support the flag
+        if: ${{ !startsWith(inputs.working-directory, 'libs/core/') }}
         shell: bash
         run: |
-          VIRTUAL_ENV=.venv uv pip install packaging tomli requests
-          python_version="$(uv run python --version | awk '{print $2}')"
-          min_versions="$(uv run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml pull_request $python_version)"
-          echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"
-          echo "min-versions=$min_versions"
-
-      - name: '🧪 Run Tests with Minimum Dependencies'
-        if: ${{ steps.min-version.outputs.min-versions != '' }}
-        env:
-          MIN_VERSIONS: ${{ steps.min-version.outputs.min-versions }}
-        run: |
-          VIRTUAL_ENV=.venv uv pip install $MIN_VERSIONS
-          make tests
-        working-directory: ${{ inputs.working-directory }}
-
-      - name: '🧹 Verify Clean Working Directory'
+          # Determine the major part of pydantic version
+          REGULAR_VERSION=$(poetry run python -c "import pydantic; print(pydantic.__version__)" | cut -d. -f1)
+          # If version 2 then we run tests with LC_PYDANTIC_V2_EXPERIMENTAL=True
+          # Otherwise echo that there's nothing to do since the version is 1
+          if [[ "$REGULAR_VERSION" == "2" ]]; then
+            LC_PYDANTIC_V2_EXPERIMENTAL=True make test 
+            echo "Finished running unit tests with LC_PYDANTIC_V2_EXPERIMENTAL=True"
+          else
+            echo "No running tests with LC_PYDANTIC_V2_EXPERIMENTAL=True since pydantic version is 1"
+          fi
+      - name: Ensure the tests did not create any additional files
         shell: bash
         run: |
           set -eu
@@ -83,4 +89,3 @@ jobs:
           # grep will exit non-zero if the target message isn't found,
           # and `set -e` above will cause the step to fail.
           echo "$STATUS" | grep 'nothing to commit, working tree clean'
-

.github/workflows/_test_doc_imports.yml

@@ -1,63 +0,0 @@
-# Validates that all import statements in `.ipynb` notebooks are correct and functional.
-#
-# Called as part of check_diffs.yml.
-#
-# Installs test dependencies and LangChain packages in editable mode and
-# runs check_imports.py.
-
-name: '📑 Documentation Import Testing'
-
-on:
-  workflow_call:
-    inputs:
-      python-version:
-        required: true
-        type: string
-        description: "Python version to use"
-
-permissions:
-  contents: read
-
-env:
-  UV_FROZEN: "true"
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    timeout-minutes: 20
-    name: '🔍 Check Doc Imports (Python ${{ inputs.python-version }})'
-    steps:
-      - name: '📋 Checkout Code'
-        uses: actions/checkout@v5
-
-      - name: '🐍 Set up Python ${{ inputs.python-version }} + UV'
-        uses: "./.github/actions/uv_setup"
-        with:
-          python-version: ${{ inputs.python-version }}
-          cache-suffix: test-doc-imports-${{ inputs.working-directory }}
-          working-directory: ${{ inputs.working-directory }}
-
-      - name: '📦 Install Test Dependencies'
-        shell: bash
-        run: uv sync --group test
-
-      - name: '📦 Install LangChain in Editable Mode'
-        run: |
-          VIRTUAL_ENV=.venv uv pip install langchain-experimental langchain-community -e libs/core libs/langchain
-
-      - name: '🔍 Validate Documentation Import Statements'
-        shell: bash
-        run: |
-          uv run python docs/scripts/check_imports.py
-
-      - name: '🧹 Verify Clean Working Directory'
-        shell: bash
-        run: |
-          set -eu
-
-          STATUS="$(git status)"
-          echo "$STATUS"
-
-          # grep will exit non-zero if the target message isn't found,
-          # and `set -e` above will cause the step to fail.
-          echo "$STATUS" | grep 'nothing to commit, working tree clean'

.github/workflows/_test_pydantic.yml

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

.github/workflows/_test_release.yml

@@ -0,0 +1,95 @@
+name: test-release
+
+on:
+  workflow_call:
+    inputs:
+      working-directory:
+        required: true
+        type: string
+        description: "From which folder this pipeline executes"
+
+env:
+  POETRY_VERSION: "1.7.1"
+  PYTHON_VERSION: "3.10"
+
+jobs:
+  build:
+    if: github.ref == 'refs/heads/master'
+    runs-on: ubuntu-latest
+
+    outputs:
+      pkg-name: ${{ steps.check-version.outputs.pkg-name }}
+      version: ${{ steps.check-version.outputs.version }}
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
+        with:
+          python-version: ${{ env.PYTHON_VERSION }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: ${{ inputs.working-directory }}
+          cache-key: release
+
+      # We want to keep this build stage *separate* from the release stage,
+      # so that there's no sharing of permissions between them.
+      # The release stage has trusted publishing and GitHub repo contents write access,
+      # and we want to keep the scope of that access limited just to the release job.
+      # Otherwise, a malicious `build` step (e.g. via a compromised dependency)
+      # could get access to our GitHub or PyPI credentials.
+      #
+      # Per the trusted publishing GitHub Action:
+      # > It is strongly advised to separate jobs for building [...]
+      # > from the publish job.
+      # https://github.com/pypa/gh-action-pypi-publish#non-goals
+      - name: Build project for distribution
+        run: poetry build
+        working-directory: ${{ inputs.working-directory }}
+
+      - name: Upload build
+        uses: actions/upload-artifact@v4
+        with:
+          name: test-dist
+          path: ${{ inputs.working-directory }}/dist/
+
+      - name: Check Version
+        id: check-version
+        shell: bash
+        working-directory: ${{ inputs.working-directory }}
+        run: |
+          echo pkg-name="$(poetry version | cut -d ' ' -f 1)" >> $GITHUB_OUTPUT
+          echo version="$(poetry version --short)" >> $GITHUB_OUTPUT
+
+  publish:
+    needs:
+      - build
+    runs-on: ubuntu-latest
+    permissions:
+      # This permission is used for trusted publishing:
+      # https://blog.pypi.org/posts/2023-04-20-introducing-trusted-publishers/
+      #
+      # Trusted publishing has to also be configured on PyPI for each package:
+      # https://docs.pypi.org/trusted-publishers/adding-a-publisher/
+      id-token: write
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/download-artifact@v4
+        with:
+          name: test-dist
+          path: ${{ inputs.working-directory }}/dist/
+
+      - name: Publish to test PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          packages-dir: ${{ inputs.working-directory }}/dist/
+          verbose: true
+          print-hash: true
+          repository-url: https://test.pypi.org/legacy/
+
+          # We overwrite any existing distributions with the same name and version.
+          # This is *only for CI use* and is *extremely dangerous* otherwise!
+          # https://github.com/pypa/gh-action-pypi-publish#tolerating-release-package-file-duplicates
+          skip-existing: true

.github/workflows/api_doc_build.yml

@@ -1,152 +0,0 @@
-# Build the API reference documentation.
-#
-# Runs daily. Can also be triggered manually for immediate updates.
-#
-# Built HTML pushed to langchain-ai/langchain-api-docs-html.
-#
-# Looks for langchain-ai org repos in packages.yml and checks them out.
-# Calls prep_api_docs_build.py.
-
-name: '📚 API Docs'
-run-name: 'Build & Deploy API Reference'
-
-on:
-  workflow_dispatch:
-  schedule:
-    - cron:  '0 13 * * *'  # Runs daily at 1PM UTC (9AM EDT/6AM PDT)
-env:
-  PYTHON_VERSION: "3.11"
-
-jobs:
-  # Only runs on main repository to prevent unnecessary builds on forks
-  build:
-    if: github.repository == 'langchain-ai/langchain' || github.event_name != 'schedule'
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-    steps:
-      - uses: actions/checkout@v5
-        with:
-          path: langchain
-      - uses: actions/checkout@v5
-        with:
-          repository: langchain-ai/langchain-api-docs-html
-          path: langchain-api-docs-html
-          token: ${{ secrets.TOKEN_GITHUB_API_DOCS_HTML }}
-
-      - name: '📋 Extract Repository List with yq'
-        id: get-unsorted-repos
-        uses: mikefarah/yq@master
-        with:
-          cmd: |
-            # Extract repos from packages.yml that are in the langchain-ai org
-            # (excluding 'langchain' itself)
-            yq '
-              .packages[]
-              | select(
-                  (
-                    (.repo | test("^langchain-ai/"))
-                    and
-                    (.repo != "langchain-ai/langchain")
-                  )
-                  or
-                  (.include_in_api_ref // false)
-                )
-              | .repo
-            ' langchain/libs/packages.yml
-
-      - name: '📋 Parse YAML & Checkout Repositories'
-        env:
-          REPOS_UNSORTED: ${{ steps.get-unsorted-repos.outputs.result }}
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: |
-          # Get unique repositories
-          REPOS=$(echo "$REPOS_UNSORTED" | sort -u)
-          # Checkout each unique repository
-          for repo in $REPOS; do
-            # Validate repository format (allow any org with proper format)
-            if [[ ! "$repo" =~ ^[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+$ ]]; then
-              echo "Error: Invalid repository format: $repo"
-              exit 1
-            fi
-
-            REPO_NAME=$(echo $repo | cut -d'/' -f2)
-
-            # Additional validation for repo name
-            if [[ ! "$REPO_NAME" =~ ^[a-zA-Z0-9_.-]+$ ]]; then
-              echo "Error: Invalid repository name: $REPO_NAME"
-              exit 1
-            fi
-            echo "Checking out $repo to $REPO_NAME"
-            git clone --depth 1 https://github.com/$repo.git $REPO_NAME
-          done
-
-      - name: '🐍 Setup Python ${{ env.PYTHON_VERSION }}'
-        uses: actions/setup-python@v6
-        id: setup-python
-        with:
-          python-version: ${{ env.PYTHON_VERSION }}
-
-      - name: '📦 Install Initial Python Dependencies using uv'
-        working-directory: langchain
-        run: |
-          python -m pip install -U uv
-          python -m uv pip install --upgrade --no-cache-dir pip setuptools pyyaml
-
-      - name: '📦 Organize Library Directories'
-        # Places cloned partner packages into libs/partners structure
-        run: python langchain/.github/scripts/prep_api_docs_build.py
-
-      - name: '🧹 Clear Prior Build'
-        run:
-          # Remove artifacts from prior docs build
-          rm -rf langchain-api-docs-html/api_reference_build/html
-
-      - name: '📦 Install Documentation Dependencies using uv'
-        working-directory: langchain
-        run: |
-          # Install all partner packages in editable mode with overrides
-          python -m uv pip install $(ls ./libs/partners | xargs -I {} echo "./libs/partners/{}") --overrides ./docs/vercel_overrides.txt
-
-          # Install core langchain and other main packages
-          python -m uv pip install libs/core libs/langchain libs/text-splitters libs/community libs/experimental libs/standard-tests
-
-          # Install Sphinx and related packages for building docs
-          python -m uv pip install -r docs/api_reference/requirements.txt
-
-      - name: '🔧 Configure Git Settings'
-        working-directory: langchain
-        run: |
-          git config --local user.email "actions@github.com"
-          git config --local user.name "Github Actions"
-
-      - name: '📚 Build API Documentation'
-        working-directory: langchain
-        run: |
-          # Generate the API reference RST files
-          python docs/api_reference/create_api_rst.py
-
-          # Build the HTML documentation using Sphinx
-          # -T: show full traceback on exception
-          # -E: don't use cached environment (force rebuild, ignore cached doctrees)
-          # -b html: build HTML docs (vs PDS, etc.)
-          # -d: path for the cached environment (parsed document trees / doctrees)
-          #     - Separate from output dir for faster incremental builds
-          # -c: path to conf.py
-          # -j auto: parallel build using all available CPU cores
-          python -m sphinx -T -E -b html -d ../langchain-api-docs-html/_build/doctrees -c docs/api_reference docs/api_reference ../langchain-api-docs-html/api_reference_build/html -j auto
-
-          # Post-process the generated HTML
-          python docs/api_reference/scripts/custom_formatter.py ../langchain-api-docs-html/api_reference_build/html
-
-          # Default index page is blank so we copy in the actual home page.
-          cp ../langchain-api-docs-html/api_reference_build/html/{reference,index}.html
-
-          # Removes Sphinx's intermediate build artifacts after the build is complete.
-          rm -rf ../langchain-api-docs-html/_build/
-
-      # Commit and push changes to langchain-api-docs-html repo
-      - uses: EndBug/add-and-commit@v9
-        with:
-          cwd: langchain-api-docs-html
-          message: 'Update API docs build'

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

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

.github/workflows/check_core_versions.yml

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

.github/workflows/check_diffs.yml

@@ -1,179 +1,127 @@
-# Primary CI workflow.
-#
-# Only runs against packages that have changed files.
-#
-# Runs:
-# - Linting (_lint.yml)
-# - Unit Tests (_test.yml)
-# - Pydantic compatibility tests (_test_pydantic.yml)
-# - Documentation import tests (_test_doc_imports.yml)
-# - Integration test compilation checks (_compile_integration_test.yml)
-# - Extended test suites that require additional dependencies
-# - Codspeed benchmarks (if not labeled 'codspeed-ignore')
-#
-# Reports status to GitHub checks and PR status.
-
-name: '🔧 CI'
+---
+name: CI
 
 on:
   push:
     branches: [master]
   pull_request:
-  merge_group:
 
-# Optimizes CI performance by canceling redundant workflow runs
 # If another push to the same PR or branch happens while this workflow is still running,
 # cancel the earlier run in favor of the next run.
 #
 # There's no point in testing an outdated version of the code. GitHub only allows
-# a limited number of job runners to be active at the same time, so it's better to
-# cancel pointless jobs early so that more useful jobs can run sooner.
+# a limited number of job runners to be active at the same time, so it's better to cancel
+# pointless jobs early so that more useful jobs can run sooner.
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
   cancel-in-progress: true
 
-permissions:
-  contents: read
-
 env:
-  UV_FROZEN: "true"
-  UV_NO_SYNC: "true"
+  POETRY_VERSION: "1.7.1"
 
 jobs:
-  # This job analyzes which files changed and creates a dynamic test matrix
-  # to only run tests/lints for the affected packages, improving CI efficiency
   build:
-    name: 'Detect Changes & Set Matrix'
     runs-on: ubuntu-latest
-    if: ${{ !contains(github.event.pull_request.labels.*.name, 'ci-ignore') }}
     steps:
-      - name: '📋 Checkout Code'
-        uses: actions/checkout@v5
-      - name: '🐍 Setup Python 3.11'
-        uses: actions/setup-python@v6
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
         with:
-          python-version: '3.11'
-      - name: '📂 Get Changed Files'
-        id: files
-        uses: Ana06/get-changed-files@v2.3.0
-      - name: '🔍 Analyze Changed Files & Generate Build Matrix'
-        id: set-matrix
+          python-version: '3.10'
+      - id: files
+        uses: Ana06/get-changed-files@v2.2.0
+      - id: set-matrix
         run: |
-          python -m pip install packaging requests
           python .github/scripts/check_diff.py ${{ steps.files.outputs.all }} >> $GITHUB_OUTPUT
     outputs:
-      lint: ${{ steps.set-matrix.outputs.lint }}
-      test: ${{ steps.set-matrix.outputs.test }}
-      extended-tests: ${{ steps.set-matrix.outputs.extended-tests }}
-      compile-integration-tests: ${{ steps.set-matrix.outputs.compile-integration-tests }}
-      dependencies: ${{ steps.set-matrix.outputs.dependencies }}
-      test-doc-imports: ${{ steps.set-matrix.outputs.test-doc-imports }}
-      test-pydantic: ${{ steps.set-matrix.outputs.test-pydantic }}
-      codspeed: ${{ steps.set-matrix.outputs.codspeed }}
-  # Run linting only on packages that have changed files
+      dirs-to-lint: ${{ steps.set-matrix.outputs.dirs-to-lint }}
+      dirs-to-test: ${{ steps.set-matrix.outputs.dirs-to-test }}
+      dirs-to-extended-test: ${{ steps.set-matrix.outputs.dirs-to-extended-test }}
   lint:
+    name: cd ${{ matrix.working-directory }}
     needs: [ build ]
-    if: ${{ needs.build.outputs.lint != '[]' }}
+    if: ${{ needs.build.outputs.dirs-to-lint != '[]' }}
     strategy:
       matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.lint) }}
-      fail-fast: false
+        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-lint) }}
     uses: ./.github/workflows/_lint.yml
     with:
-      working-directory: ${{ matrix.job-configs.working-directory }}
-      python-version: ${{ matrix.job-configs.python-version }}
+      working-directory: ${{ matrix.working-directory }}
     secrets: inherit
 
-  # Run unit tests only on packages that have changed files
   test:
+    name: cd ${{ matrix.working-directory }}
     needs: [ build ]
-    if: ${{ needs.build.outputs.test != '[]' }}
+    if: ${{ needs.build.outputs.dirs-to-test != '[]' }}
     strategy:
       matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.test) }}
-      fail-fast: false
+        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-test) }}
     uses: ./.github/workflows/_test.yml
     with:
-      working-directory: ${{ matrix.job-configs.working-directory }}
-      python-version: ${{ matrix.job-configs.python-version }}
+      working-directory: ${{ matrix.working-directory }}
     secrets: inherit
 
-  # Test compatibility with different Pydantic versions for affected packages
-  test-pydantic:
-    needs: [ build ]
-    if: ${{ needs.build.outputs.test-pydantic != '[]' }}
-    strategy:
-      matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.test-pydantic) }}
-      fail-fast: false
-    uses: ./.github/workflows/_test_pydantic.yml
-    with:
-      working-directory: ${{ matrix.job-configs.working-directory }}
-      pydantic-version: ${{ matrix.job-configs.pydantic-version }}
-    secrets: inherit
-
-  test-doc-imports:
-    needs: [ build ]
-    if: ${{ needs.build.outputs.test-doc-imports != '[]' }}
-    strategy:
-      matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.test-doc-imports) }}
-      fail-fast: false
-    uses: ./.github/workflows/_test_doc_imports.yml
-    with:
-      python-version: ${{ matrix.job-configs.python-version }}
-    secrets: inherit
-
-  # Verify integration tests compile without actually running them (faster feedback)
   compile-integration-tests:
-    name: 'Compile Integration Tests'
+    name: cd ${{ matrix.working-directory }}
     needs: [ build ]
-    if: ${{ needs.build.outputs.compile-integration-tests != '[]' }}
+    if: ${{ needs.build.outputs.dirs-to-test != '[]' }}
     strategy:
       matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.compile-integration-tests) }}
-      fail-fast: false
+        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-test) }}
     uses: ./.github/workflows/_compile_integration_test.yml
     with:
-      working-directory: ${{ matrix.job-configs.working-directory }}
-      python-version: ${{ matrix.job-configs.python-version }}
+      working-directory: ${{ matrix.working-directory }}
     secrets: inherit
 
-  # Run extended test suites that require additional dependencies
-  extended-tests:
-    name: 'Extended Tests'
+  dependencies:
+    name: cd ${{ matrix.working-directory }}
     needs: [ build ]
-    if: ${{ needs.build.outputs.extended-tests != '[]' }}
+    if: ${{ needs.build.outputs.dirs-to-test != '[]' }}
+    strategy:
+      matrix:
+        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-test) }}
+    uses: ./.github/workflows/_dependencies.yml
+    with:
+      working-directory: ${{ matrix.working-directory }}
+    secrets: inherit
+
+  extended-tests:
+    name: "cd ${{ matrix.working-directory }} / make extended_tests #${{ matrix.python-version }}"
+    needs: [ build ]
+    if: ${{ needs.build.outputs.dirs-to-extended-test != '[]' }}
     strategy:
       matrix:
         # note different variable for extended test dirs
-        job-configs: ${{ fromJson(needs.build.outputs.extended-tests) }}
-      fail-fast: false
+        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-extended-test) }}
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
     runs-on: ubuntu-latest
-    timeout-minutes: 20
     defaults:
       run:
-        working-directory: ${{ matrix.job-configs.working-directory }}
+        working-directory: ${{ matrix.working-directory }}
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v4
 
-      - name: '🐍 Set up Python ${{ matrix.job-configs.python-version }} + UV'
-        uses: "./.github/actions/uv_setup"
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ matrix.job-configs.python-version }}
-          cache-suffix: extended-tests-${{ matrix.job-configs.working-directory }}
-          working-directory: ${{ matrix.job-configs.working-directory }}
+          python-version: ${{ matrix.python-version }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: ${{ matrix.working-directory }}
+          cache-key: extended
 
-      - name: '📦 Install Dependencies & Run Extended Tests'
+      - name: Install dependencies
         shell: bash
         run: |
-          echo "Running extended tests, installing dependencies with uv..."
-          uv venv
-          uv sync --group test
-          VIRTUAL_ENV=.venv uv pip install -r extended_testing_deps.txt
-          VIRTUAL_ENV=.venv make extended_tests
+          echo "Running extended tests, installing dependencies with poetry..."
+          poetry install -E extended_testing --with test
 
-      - name: '🧹 Verify Clean Working Directory'
+      - name: Run extended tests
+        run: make extended_tests
+
+      - name: Ensure the tests did not create any additional files
         shell: bash
         run: |
           set -eu
@@ -184,73 +132,9 @@ jobs:
           # grep will exit non-zero if the target message isn't found,
           # and `set -e` above will cause the step to fail.
           echo "$STATUS" | grep 'nothing to commit, working tree clean'
-
-  # Run codspeed benchmarks only on packages that have changed files
-  codspeed:
-    name: '⚡ CodSpeed Benchmarks'
-    needs: [ build ]
-    if: ${{ needs.build.outputs.codspeed != '[]' && !contains(github.event.pull_request.labels.*.name, 'codspeed-ignore') }}
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.codspeed) }}
-      fail-fast: false
-    steps:
-      - uses: actions/checkout@v5
-
-      # We have to use 3.12 as 3.13 is not yet supported
-      - name: '📦 Install UV Package Manager'
-        uses: astral-sh/setup-uv@v6
-        with:
-          python-version: "3.12"
-
-      - uses: actions/setup-python@v6
-        with:
-          python-version: "3.12"
-
-      - name: '📦 Install Test Dependencies'
-        run: uv sync --group test
-        working-directory: ${{ matrix.job-configs.working-directory }}
-
-      - name: '⚡ Run Benchmarks: ${{ matrix.job-configs.working-directory }}'
-        uses: CodSpeedHQ/action@v4
-        env:
-          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
-          ANTHROPIC_FILES_API_IMAGE_ID: ${{ secrets.ANTHROPIC_FILES_API_IMAGE_ID }}
-          ANTHROPIC_FILES_API_PDF_ID: ${{ secrets.ANTHROPIC_FILES_API_PDF_ID }}
-          AZURE_OPENAI_API_VERSION: ${{ secrets.AZURE_OPENAI_API_VERSION }}
-          AZURE_OPENAI_API_BASE: ${{ secrets.AZURE_OPENAI_API_BASE }}
-          AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
-          AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_CHAT_DEPLOYMENT_NAME }}
-          AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME }}
-          AZURE_OPENAI_LLM_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LLM_DEPLOYMENT_NAME }}
-          AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME }}
-          COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
-          DEEPSEEK_API_KEY: ${{ secrets.DEEPSEEK_API_KEY }}
-          EXA_API_KEY: ${{ secrets.EXA_API_KEY }}
-          FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
-          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
-          HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
-          MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
-          NOMIC_API_KEY: ${{ secrets.NOMIC_API_KEY }}
-          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          PPLX_API_KEY: ${{ secrets.PPLX_API_KEY }}
-          XAI_API_KEY: ${{ secrets.XAI_API_KEY }}
-        with:
-          token: ${{ secrets.CODSPEED_TOKEN }}
-          run: |
-            cd ${{ matrix.job-configs.working-directory }}
-            if [ "${{ matrix.job-configs.working-directory }}" = "libs/core" ]; then
-              uv run --no-sync pytest ./tests/benchmarks --codspeed
-            else
-              uv run --no-sync pytest ./tests/ --codspeed
-            fi
-          mode: ${{ matrix.job-configs.working-directory == 'libs/core' && 'walltime' || 'instrumentation' }}
-
-  # Final status check - ensures all required jobs passed before allowing merge
   ci_success:
-    name: '✅ CI Success'
-    needs: [build, lint, test, compile-integration-tests, extended-tests, test-doc-imports, test-pydantic, codspeed]
+    name: "CI Success"
+    needs: [build, lint, test, compile-integration-tests, dependencies, extended-tests]
     if: |
       always()
     runs-on: ubuntu-latest
@@ -259,7 +143,7 @@ jobs:
       RESULTS_JSON: ${{ toJSON(needs.*.result) }}
       EXIT_CODE: ${{!contains(needs.*.result, 'failure') && !contains(needs.*.result, 'cancelled') && '0' || '1'}}
     steps:
-      - name: '🎉 All Checks Passed'
+      - name: "CI Success"
         run: |
           echo $JOBS_JSON
           echo $RESULTS_JSON

.github/workflows/check_new_docs.yml

@@ -1,41 +0,0 @@
-# For integrations, we run check_templates.py to ensure that new docs use the correct
-# templates based on their type. See the script for more details.
-
-name: '📑 Integration Docs Lint'
-
-on:
-  push:
-    branches: [master]
-  pull_request:
-
-# If another push to the same PR or branch happens while this workflow is still running,
-# cancel the earlier run in favor of the next run.
-#
-# There's no point in testing an outdated version of the code. GitHub only allows
-# a limited number of job runners to be active at the same time, so it's better to cancel
-# pointless jobs early so that more useful jobs can run sooner.
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-permissions:
-  contents: read
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v5
-      - uses: actions/setup-python@v6
-        with:
-          python-version: '3.10'
-      - id: files
-        uses: Ana06/get-changed-files@v2.3.0
-        with:
-          filter: |
-            *.ipynb
-            *.md
-            *.mdx
-      - name: '🔍 Check New Documentation Templates'
-        run: |
-          python docs/scripts/check_templates.py ${{ steps.files.outputs.added }}

.github/workflows/codespell.yml

@@ -0,0 +1,37 @@
+---
+name: CI / cd . / make spell_check
+
+on:
+  push:
+    branches: [master]
+  pull_request:
+    branches: [master]
+
+permissions:
+  contents: read
+
+jobs:
+  codespell:
+    name: (Check for spelling errors)
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Install Dependencies
+        run: |
+          pip install toml
+
+      - name: Extract Ignore Words List
+        run: |
+          # Use a Python script to extract the ignore words list from pyproject.toml
+          python .github/workflows/extract_ignored_words_list.py
+        id: extract_ignore_words
+
+      - name: Codespell
+        uses: codespell-project/actions-codespell@v2
+        with:
+          skip: guide_imports.json,*.ambr,./cookbook/data/imdb_top_1000.csv,*.lock
+          ignore_words_list: ${{ steps.extract_ignore_words.outputs.ignore_words_list }}
+          exclude_file: libs/community/langchain_community/llms/yuan2.py

.github/workflows/extract_ignored_words_list.py

@@ -0,0 +1,10 @@
+import toml
+
+pyproject_toml = toml.load("pyproject.toml")
+
+# Extract the ignore words list (adjust the key as per your TOML structure)
+ignore_words_list = (
+    pyproject_toml.get("tool", {}).get("codespell", {}).get("ignore-words-list")
+)
+
+print(f"::set-output name=ignore_words_list::{ignore_words_list}")  # noqa: T201

.github/workflows/langchain_release_docker.yml

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

.github/workflows/people.yml

@@ -1,30 +1,36 @@
-# Updates the LangChain People data by fetching the latest info from the LangChain Git.
-# TODO: broken/not used
+name: LangChain People
 
-name: '👥 LangChain People'
-run-name: 'Update People Data'
 on:
   schedule:
-    - cron: "0 14 1 * *"  # Runs at 14:00 UTC on the 1st of every month (10AM EDT/7AM PDT)
+    - cron: "0 14 1 * *"
   push:
     branches: [jacob/people]
   workflow_dispatch:
+    inputs:
+      debug_enabled:
+        description: 'Run the build with tmate debugging enabled (https://github.com/marketplace/actions/debugging-with-tmate)'
+        required: false
+        default: 'false'
 
 jobs:
   langchain-people:
-    if: github.repository_owner == 'langchain-ai' || github.event_name != 'schedule'
+    if: github.repository_owner == 'langchain-ai'
     runs-on: ubuntu-latest
-    permissions:
-      contents: write
     steps:
-      - name: '📋 Dump GitHub Context'
+      - name: Dump GitHub context
         env:
           GITHUB_CONTEXT: ${{ toJson(github) }}
         run: echo "$GITHUB_CONTEXT"
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v4
       # Ref: https://github.com/actions/runner/issues/2033
-      - name: '🔧 Fix Git Safe Directory in Container'
+      - name: Fix git safe.directory in container
         run: mkdir -p /home/runner/work/_temp/_github_home && printf "[safe]\n\tdirectory = /github/workspace" > /home/runner/work/_temp/_github_home/.gitconfig
+      # Allow debugging with tmate
+      - name: Setup tmate session
+        uses: mxschmitt/action-tmate@v3
+        if: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.debug_enabled == 'true' }}
+        with:
+          limit-access-to-actor: true
       - uses: ./.github/actions/people
         with:
-          token: ${{ secrets.LANGCHAIN_PEOPLE_GITHUB_TOKEN }}
+          token: ${{ secrets.LANGCHAIN_PEOPLE_GITHUB_TOKEN }}

.github/workflows/pr_labeler_file.yml

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

.github/workflows/pr_labeler_title.yml

@@ -1,28 +0,0 @@
-# Label PRs based on their titles.
-#
-# See `.github/pr-title-labeler.yml` to see rules for each label/title pattern.
-
-name: "🏷️ PR Title Labeler"
-
-on:
-  # Safe since we're not checking out or running the PR's code
-  # Never check out the PR's head in a pull_request_target job
-  pull_request_target:
-    types: [opened, synchronize, reopened, edited]
-
-jobs:
-  pr-title-labeler:
-    name: 'label'
-    permissions:
-      contents: read
-      pull-requests: write
-      issues: write
-    runs-on: ubuntu-latest
-
-    steps:
-    - name: Label PR based on title
-      # Archived repo; latest commit (v0.1.0)
-      uses: grafana/pr-labeler-action@f19222d3ef883d2ca5f04420fdfe8148003763f0
-      with:
-        token: ${{ secrets.GITHUB_TOKEN }}
-        configuration-path: .github/pr-title-labeler.yml

.github/workflows/pr_lint.yml

@@ -1,105 +0,0 @@
-# PR title linting.
-#
-# FORMAT (Conventional Commits 1.0.0):
-#
-#   <type>[optional scope]: <description>
-#   [optional body]
-#   [optional footer(s)]
-#
-# Examples:
-#     feat(core): add multi‐tenant support
-#     fix(cli): resolve flag parsing error
-#     docs: update API usage examples
-#     docs(openai): update API usage examples
-#
-# Allowed Types:
-#   * feat       — a new feature (MINOR)
-#   * fix        — a bug fix (PATCH)
-#   * docs       — documentation only changes (either in /docs or code comments)
-#   * style      — formatting, linting, etc.; no code change or typing refactors
-#   * refactor   — code change that neither fixes a bug nor adds a feature
-#   * perf       — code change that improves performance
-#   * test       — adding tests or correcting existing
-#   * build      — changes that affect the build system/external dependencies
-#   * ci         — continuous integration/configuration changes
-#   * chore      — other changes that don't modify source or test files
-#   * revert     — reverts a previous commit
-#   * release    — prepare a new release
-#
-# Allowed Scopes (optional):
-#   core, cli, langchain, langchain_v1, langchain_legacy, standard-tests,
-#   text-splitters, docs, anthropic, chroma, deepseek, exa, fireworks, groq,
-#   huggingface, mistralai, nomic, ollama, openai, perplexity, prompty, qdrant,
-#   xai, infra
-#
-# Rules:
-#   1. The 'Type' must start with a lowercase letter.
-#   2. Breaking changes: append "!" after type/scope (e.g., feat!: drop x support)
-#
-# Enforces Conventional Commits format for pull request titles to maintain a clear and
-# machine-readable change history.
-
-name: '🏷️ PR Title Lint'
-
-permissions:
-  pull-requests: read
-
-on:
-  pull_request:
-    types: [opened, edited, synchronize]
-
-jobs:
-  # Validates that PR title follows Conventional Commits 1.0.0 specification
-  lint-pr-title:
-    name: 'validate format'
-    runs-on: ubuntu-latest
-    steps:
-      - name: '✅ Validate Conventional Commits Format'
-        uses: amannn/action-semantic-pull-request@v6
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        with:
-          types: |
-            feat
-            fix
-            docs
-            style
-            refactor
-            perf
-            test
-            build
-            ci
-            chore
-            revert
-            release
-          scopes: |
-            core
-            cli
-            langchain
-            langchain_v1
-            langchain_legacy
-            standard-tests
-            text-splitters
-            docs
-            anthropic
-            chroma
-            deepseek
-            exa
-            fireworks
-            groq
-            huggingface
-            mistralai
-            nomic
-            ollama
-            openai
-            perplexity
-            prompty
-            qdrant
-            xai
-            infra
-          requireScope: false
-          disallowScopes: |
-            release
-            [A-Z]+
-          ignoreLabels: |
-            ignore-lint-pr-title

.github/workflows/run_notebooks.yml

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

.github/workflows/scheduled_test.yml

@@ -1,181 +1,81 @@
-# Routine integration tests against partner libraries with live API credentials.
-#
-# Uses `make integration_tests` for each library in the matrix.
-#
-# Runs daily. Can also be triggered manually for immediate updates.
-
-name: '⏰ Scheduled Integration Tests'
-run-name: "Run Integration Tests - ${{ inputs.working-directory-force || 'all libs' }} (Python ${{ inputs.python-version-force || '3.9, 3.11' }})"
+name: Scheduled tests
 
 on:
-  workflow_dispatch:
-    inputs:
-      working-directory-force:
-        type: string
-        description: "From which folder this pipeline executes - defaults to all in matrix - example value: libs/partners/anthropic"
-      python-version-force:
-        type: string
-        description: "Python version to use - defaults to 3.9 and 3.11 in matrix - example value: 3.9"
+  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
   schedule:
-    - cron:  '0 13 * * *'  # Runs daily at 1PM UTC (9AM EDT/6AM PDT)
-
-permissions:
-  contents: read
+    - cron:  '0 13 * * *'
 
 env:
-  POETRY_VERSION: "1.8.4"
-  UV_FROZEN: "true"
-  DEFAULT_LIBS: '["libs/partners/openai", "libs/partners/anthropic", "libs/partners/fireworks", "libs/partners/groq", "libs/partners/mistralai", "libs/partners/xai", "libs/partners/google-vertexai", "libs/partners/google-genai", "libs/partners/aws"]'
-  POETRY_LIBS: ("libs/partners/aws")
+  POETRY_VERSION: "1.7.1"
 
 jobs:
-  # Generate dynamic test matrix based on input parameters or defaults
-  # Only runs on the main repo (for scheduled runs) or when manually triggered
-  compute-matrix:
-    if: github.repository_owner == 'langchain-ai' || github.event_name != 'schedule'
-    runs-on: ubuntu-latest
-    name: '📋 Compute Test Matrix'
-    outputs:
-      matrix: ${{ steps.set-matrix.outputs.matrix }}
-    steps:
-      - name: '🔢 Generate Python & Library Matrix'
-        id: set-matrix
-        env:
-          DEFAULT_LIBS: ${{ env.DEFAULT_LIBS }}
-          WORKING_DIRECTORY_FORCE: ${{ github.event.inputs.working-directory-force || '' }}
-          PYTHON_VERSION_FORCE: ${{ github.event.inputs.python-version-force || '' }}
-        run: |
-          # echo "matrix=..." where matrix is a json formatted str with keys python-version and working-directory
-          # python-version should default to 3.9 and 3.11, but is overridden to [PYTHON_VERSION_FORCE] if set
-          # working-directory should default to DEFAULT_LIBS, but is overridden to [WORKING_DIRECTORY_FORCE] if set
-          python_version='["3.9", "3.11"]'
-          working_directory="$DEFAULT_LIBS"
-          if [ -n "$PYTHON_VERSION_FORCE" ]; then
-            python_version="[\"$PYTHON_VERSION_FORCE\"]"
-          fi
-          if [ -n "$WORKING_DIRECTORY_FORCE" ]; then
-            working_directory="[\"$WORKING_DIRECTORY_FORCE\"]"
-          fi
-          matrix="{\"python-version\": $python_version, \"working-directory\": $working_directory}"
-          echo $matrix
-          echo "matrix=$matrix" >> $GITHUB_OUTPUT
-  # Run integration tests against partner libraries with live API credentials
-  # Tests are run with Poetry or UV depending on the library's setup
   build:
-    if: github.repository_owner == 'langchain-ai' || github.event_name != 'schedule'
-    name: '🐍 Python ${{ matrix.python-version }}: ${{ matrix.working-directory }}'
+    defaults:
+      run:
+        working-directory: libs/langchain
     runs-on: ubuntu-latest
-    needs: [compute-matrix]
-    timeout-minutes: 30
+    environment: Scheduled testing
     strategy:
-      fail-fast: false
       matrix:
-        python-version: ${{ fromJSON(needs.compute-matrix.outputs.matrix).python-version }}
-        working-directory: ${{ fromJSON(needs.compute-matrix.outputs.matrix).working-directory }}
-
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
+    name: Python ${{ matrix.python-version }}
     steps:
-      - uses: actions/checkout@v5
-        with:
-          path: langchain
-      - uses: actions/checkout@v5
-        with:
-          repository: langchain-ai/langchain-google
-          path: langchain-google
-      - uses: actions/checkout@v5
-        with:
-          repository: langchain-ai/langchain-aws
-          path: langchain-aws
+      - uses: actions/checkout@v4
 
-      - name: '📦 Organize External Libraries'
-        run: |
-          rm -rf \
-            langchain/libs/partners/google-genai \
-            langchain/libs/partners/google-vertexai
-          mv langchain-google/libs/genai langchain/libs/partners/google-genai
-          mv langchain-google/libs/vertexai langchain/libs/partners/google-vertexai
-          mv langchain-aws/libs/aws langchain/libs/partners/aws
-
-      - name: '🐍 Set up Python ${{ matrix.python-version }} + Poetry'
-        if: contains(env.POETRY_LIBS, matrix.working-directory)
-        uses: "./langchain/.github/actions/poetry_setup"
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: "./.github/actions/poetry_setup"
         with:
           python-version: ${{ matrix.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: langchain/${{ matrix.working-directory }}
+          working-directory: libs/langchain
           cache-key: scheduled
 
-      - name: '🐍 Set up Python ${{ matrix.python-version }} + UV'
-        if: "!contains(env.POETRY_LIBS, matrix.working-directory)"
-        uses: "./langchain/.github/actions/uv_setup"
-        with:
-          python-version: ${{ matrix.python-version }}
-
-      - name: '🔐 Authenticate to Google Cloud'
+      - name: 'Authenticate to Google Cloud'
         id: 'auth'
-        uses: google-github-actions/auth@v3
+        uses: google-github-actions/auth@v2
         with:
           credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
 
-      - name: '🔐 Configure AWS Credentials'
-        uses: aws-actions/configure-aws-credentials@v5
+      - name: Configure AWS Credentials
+        uses: aws-actions/configure-aws-credentials@v4
         with:
           aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
           aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
-          aws-region: ${{ secrets.AWS_REGION }}
+          aws-region: ${{ vars.AWS_REGION }}
 
-      - name: '📦 Install Dependencies (Poetry)'
-        if: contains(env.POETRY_LIBS, matrix.working-directory)
+      - name: Install dependencies
+        working-directory: libs/langchain
+        shell: bash
         run: |
           echo "Running scheduled tests, installing dependencies with poetry..."
-          cd langchain/${{ matrix.working-directory }}
           poetry install --with=test_integration,test
 
-      - name: '📦 Install Dependencies (UV)'
-        if: "!contains(env.POETRY_LIBS, matrix.working-directory)"
-        run: |
-          echo "Running scheduled tests, installing dependencies with uv..."
-          cd langchain/${{ matrix.working-directory }}
-          uv sync --group test --group test_integration
+      - name: Install deps outside pyproject
+        if: ${{ startsWith(inputs.working-directory, 'libs/community/') }}
+        shell: bash
+        run: poetry run pip install "boto3<2" "google-cloud-aiplatform<2"
 
-      - name: '🚀 Run Integration Tests'
+      - name: Run tests
+        shell: bash
         env:
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
           ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
-          ANTHROPIC_FILES_API_IMAGE_ID: ${{ secrets.ANTHROPIC_FILES_API_IMAGE_ID }}
-          ANTHROPIC_FILES_API_PDF_ID: ${{ secrets.ANTHROPIC_FILES_API_PDF_ID }}
           AZURE_OPENAI_API_VERSION: ${{ secrets.AZURE_OPENAI_API_VERSION }}
           AZURE_OPENAI_API_BASE: ${{ secrets.AZURE_OPENAI_API_BASE }}
           AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
           AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_CHAT_DEPLOYMENT_NAME }}
-          AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME }}
           AZURE_OPENAI_LLM_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LLM_DEPLOYMENT_NAME }}
           AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME }}
-          DEEPSEEK_API_KEY: ${{ secrets.DEEPSEEK_API_KEY }}
           FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
-          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
-          HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
-          MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
-          XAI_API_KEY: ${{ secrets.XAI_API_KEY }}
-          COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
-          NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}
-          GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
-          GOOGLE_SEARCH_API_KEY: ${{ secrets.GOOGLE_SEARCH_API_KEY }}
-          GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
-          PPLX_API_KEY: ${{ secrets.PPLX_API_KEY }}
         run: |
-          cd langchain/${{ matrix.working-directory }}
-          make integration_tests
+          make scheduled_tests
 
-      - name: '🧹 Clean up External Libraries'
-        # Clean up external libraries to avoid affecting the following git status check
-        run: |
-          rm -rf \
-            langchain/libs/partners/google-genai \
-            langchain/libs/partners/google-vertexai \
-            langchain/libs/partners/aws
-
-      - name: '🧹 Verify Clean Working Directory'
-        working-directory: langchain
+      - name: Ensure the tests did not create any additional files
+        shell: bash
         run: |
           set -eu
 

.github/workflows/v1_changes.md

@@ -1,9 +0,0 @@
-With the deprecation of v0 docs, the following files will need to be migrated/supported
-in the new docs repo:
-
-- run_notebooks.yml: New repo should run Integration tests on code snippets?
-- people.yml: Need to fix and somehow display on the new docs site
-  - Subsequently, `.github/actions/people/`
-- _test_doc_imports.yml
-- check_new_docs.yml
-- check-broken-links.yml

.gitignore

@@ -1,4 +1,5 @@
 .vs/
+.vscode/
 .idea/
 # Byte-compiled / optimized / DLL files
 __pycache__/
@@ -58,7 +59,6 @@ coverage.xml
 *.py,cover
 .hypothesis/
 .pytest_cache/
-.codspeed/
 
 # Translations
 *.mo
@@ -116,7 +116,6 @@ celerybeat.pid
 .env
 .envrc
 .venv*
-venv*
 env/
 ENV/
 env.bak/
@@ -133,7 +132,6 @@ env.bak/
 
 # mypy
 .mypy_cache/
-.mypy_cache_test/
 .dmypy.json
 dmypy.json
 
@@ -167,14 +165,11 @@ docs/.docusaurus/
 docs/.cache-loader/
 docs/_dist
 docs/api_reference/*api_reference.rst
-docs/api_reference/*.md
 docs/api_reference/_build
 docs/api_reference/*/
 !docs/api_reference/_static/
 !docs/api_reference/templates/
 !docs/api_reference/themes/
-!docs/api_reference/_extensions/
-!docs/api_reference/scripts/
 docs/docs/build
 docs/docs/node_modules
 docs/docs/yarn.lock
@@ -182,4 +177,3 @@ _dist
 docs/docs/templates
 
 prof
-virtualenv/

.markdownlint.json

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

.pre-commit-config.yaml

@@ -1,105 +0,0 @@
-repos:
-  - repo: local
-    hooks:
-      - id: core
-        name: format and lint core
-        language: system
-        entry: make -C libs/core format lint
-        files: ^libs/core/
-        pass_filenames: false
-      - id: langchain
-        name: format and lint langchain
-        language: system
-        entry: make -C libs/langchain format lint
-        files: ^libs/langchain/
-        pass_filenames: false
-      - id: standard-tests
-        name: format and lint standard-tests
-        language: system
-        entry: make -C libs/standard-tests format lint
-        files: ^libs/standard-tests/
-        pass_filenames: false
-      - id: text-splitters
-        name: format and lint text-splitters
-        language: system
-        entry: make -C libs/text-splitters format lint
-        files: ^libs/text-splitters/
-        pass_filenames: false
-      - id: anthropic
-        name: format and lint partners/anthropic
-        language: system
-        entry: make -C libs/partners/anthropic format lint
-        files: ^libs/partners/anthropic/
-        pass_filenames: false
-      - id: chroma
-        name: format and lint partners/chroma
-        language: system
-        entry: make -C libs/partners/chroma format lint
-        files: ^libs/partners/chroma/
-        pass_filenames: false
-      - id: exa
-        name: format and lint partners/exa
-        language: system
-        entry: make -C libs/partners/exa format lint
-        files: ^libs/partners/exa/
-        pass_filenames: false
-      - id: fireworks
-        name: format and lint partners/fireworks
-        language: system
-        entry: make -C libs/partners/fireworks format lint
-        files: ^libs/partners/fireworks/
-        pass_filenames: false
-      - id: groq
-        name: format and lint partners/groq
-        language: system
-        entry: make -C libs/partners/groq format lint
-        files: ^libs/partners/groq/
-        pass_filenames: false
-      - id: huggingface
-        name: format and lint partners/huggingface
-        language: system
-        entry: make -C libs/partners/huggingface format lint
-        files: ^libs/partners/huggingface/
-        pass_filenames: false
-      - id: mistralai
-        name: format and lint partners/mistralai
-        language: system
-        entry: make -C libs/partners/mistralai format lint
-        files: ^libs/partners/mistralai/
-        pass_filenames: false
-      - id: nomic
-        name: format and lint partners/nomic
-        language: system
-        entry: make -C libs/partners/nomic format lint
-        files: ^libs/partners/nomic/
-        pass_filenames: false
-      - id: ollama
-        name: format and lint partners/ollama
-        language: system
-        entry: make -C libs/partners/ollama format lint
-        files: ^libs/partners/ollama/
-        pass_filenames: false
-      - id: openai
-        name: format and lint partners/openai
-        language: system
-        entry: make -C libs/partners/openai format lint
-        files: ^libs/partners/openai/
-        pass_filenames: false
-      - id: prompty
-        name: format and lint partners/prompty
-        language: system
-        entry: make -C libs/partners/prompty format lint
-        files: ^libs/partners/prompty/
-        pass_filenames: false
-      - id: qdrant
-        name: format and lint partners/qdrant
-        language: system
-        entry: make -C libs/partners/qdrant format lint
-        files: ^libs/partners/qdrant/
-        pass_filenames: false
-      - id: root
-        name: format and lint docs, cookbook
-        language: system
-        entry: make format lint
-        files: ^(docs|cookbook)/
-        pass_filenames: false

.readthedocs.yaml

@@ -0,0 +1,29 @@
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+formats:
+  - pdf
+
+# Set the version of Python and other tools you might need
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.11"
+  commands:
+    - mkdir -p $READTHEDOCS_OUTPUT
+    - cp -r api_reference_build/* $READTHEDOCS_OUTPUT
+# Build documentation in the docs/ directory with Sphinx
+sphinx:
+   configuration: docs/api_reference/conf.py
+
+# If using Sphinx, optionally build your docs in additional formats such as PDF
+# formats:
+#    - pdf
+
+# Optionally declare the Python requirements required to build your docs
+python:
+   install:
+   - requirements: docs/api_reference/requirements.txt

.vscode/extensions.json

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

.vscode/settings.json

@@ -1,87 +0,0 @@
-{
-  "python.analysis.include": [
-    "libs/**",
-    "docs/**",
-    "cookbook/**"
-  ],
-  "python.analysis.exclude": [
-    "**/node_modules",
-    "**/__pycache__",
-    "**/.pytest_cache",
-    "**/.*",
-    "_dist/**",
-    "docs/_build/**",
-    "docs/api_reference/_build/**"
-  ],
-  "python.analysis.autoImportCompletions": true,
-  "python.analysis.typeCheckingMode": "basic",
-  "python.testing.cwd": "${workspaceFolder}",
-  "python.linting.enabled": true,
-  "python.linting.ruffEnabled": true,
-  "[python]": {
-    "editor.formatOnSave": true,
-    "editor.codeActionsOnSave": {
-      "source.organizeImports.ruff": "explicit",
-      "source.fixAll": "explicit"
-    },
-    "editor.defaultFormatter": "charliermarsh.ruff"
-  },
-  "editor.rulers": [
-    88
-  ],
-  "editor.tabSize": 4,
-  "editor.insertSpaces": true,
-  "editor.trimAutoWhitespace": true,
-  "files.trimTrailingWhitespace": true,
-  "files.insertFinalNewline": true,
-  "files.exclude": {
-    "**/__pycache__": true,
-    "**/.pytest_cache": true,
-    "**/*.pyc": true,
-    "**/.mypy_cache": true,
-    "**/.ruff_cache": true,
-    "_dist/**": true,
-    "docs/_build/**": true,
-    "docs/api_reference/_build/**": true,
-    "**/node_modules": true,
-    "**/.git": false
-  },
-  "search.exclude": {
-    "**/__pycache__": true,
-    "**/*.pyc": true,
-    "_dist/**": true,
-    "docs/_build/**": true,
-    "docs/api_reference/_build/**": true,
-    "**/node_modules": true,
-    "**/.git": true,
-    "uv.lock": true,
-    "yarn.lock": true
-  },
-  "git.autofetch": true,
-  "git.enableSmartCommit": true,
-  "jupyter.askForKernelRestart": false,
-  "jupyter.interactiveWindow.textEditor.executeSelection": true,
-  "[markdown]": {
-    "editor.wordWrap": "on",
-    "editor.quickSuggestions": {
-      "comments": "off",
-      "strings": "off",
-      "other": "off"
-    }
-  },
-  "[yaml]": {
-    "editor.tabSize": 2,
-    "editor.insertSpaces": true
-  },
-  "[json]": {
-    "editor.tabSize": 2,
-    "editor.insertSpaces": true
-  },
-  "python.terminal.activateEnvironment": false,
-  "python.defaultInterpreterPath": "./.venv/bin/python",
-  "github.copilot.chat.commitMessageGeneration.instructions": [
-    {
-      "file": ".github/workflows/pr_lint.yml"
-    }
-  ]
-}

AGENTS.md

@@ -1,325 +0,0 @@
-# Global Development Guidelines for LangChain Projects
-
-## Core Development Principles
-
-### 1. Maintain Stable Public Interfaces ⚠️ CRITICAL
-
-**Always attempt to preserve function signatures, argument positions, and names for exported/public methods.**
-
-❌ **Bad - Breaking Change:**
-
-```python
-def get_user(id, verbose=False):  # Changed from `user_id`
-    pass
-```
-
-✅ **Good - Stable Interface:**
-
-```python
-def get_user(user_id: str, verbose: bool = False) -> User:
-    """Retrieve user by ID with optional verbose output."""
-    pass
-```
-
-**Before making ANY changes to public APIs:**
-
-- Check if the function/class is exported in `__init__.py`
-- Look for existing usage patterns in tests and examples
-- Use keyword-only arguments for new parameters: `*, new_param: str = "default"`
-- Mark experimental features clearly with docstring warnings (using reStructuredText, like `.. warning::`)
-
-🧠 *Ask yourself:* "Would this change break someone's code if they used it last week?"
-
-### 2. Code Quality Standards
-
-**All Python code MUST include type hints and return types.**
-
-❌ **Bad:**
-
-```python
-def p(u, d):
-    return [x for x in u if x not in d]
-```
-
-✅ **Good:**
-
-```python
-def filter_unknown_users(users: list[str], known_users: set[str]) -> list[str]:
-    """Filter out users that are not in the known users set.
-
-    Args:
-        users: List of user identifiers to filter.
-        known_users: Set of known/valid user identifiers.
-
-    Returns:
-        List of users that are not in the known_users set.
-    """
-    return [user for user in users if user not in known_users]
-```
-
-**Style Requirements:**
-
-- Use descriptive, **self-explanatory variable names**. Avoid overly short or cryptic identifiers.
-- Attempt to break up complex functions (>20 lines) into smaller, focused functions where it makes sense
-- Avoid unnecessary abstraction or premature optimization
-- Follow existing patterns in the codebase you're modifying
-
-### 3. Testing Requirements
-
-**Every new feature or bugfix MUST be covered by unit tests.**
-
-**Test Organization:**
-
-- Unit tests: `tests/unit_tests/` (no network calls allowed)
-- Integration tests: `tests/integration_tests/` (network calls permitted)
-- Use `pytest` as the testing framework
-
-**Test Quality Checklist:**
-
-- [ ] Tests fail when your new logic is broken
-- [ ] Happy path is covered
-- [ ] Edge cases and error conditions are tested
-- [ ] Use fixtures/mocks for external dependencies
-- [ ] Tests are deterministic (no flaky tests)
-
-Checklist questions:
-
-- [ ] Does the test suite fail if your new logic is broken?
-- [ ] Are all expected behaviors exercised (happy path, invalid input, etc)?
-- [ ] Do tests use fixtures or mocks where needed?
-
-```python
-def test_filter_unknown_users():
-    """Test filtering unknown users from a list."""
-    users = ["alice", "bob", "charlie"]
-    known_users = {"alice", "bob"}
-
-    result = filter_unknown_users(users, known_users)
-
-    assert result == ["charlie"]
-    assert len(result) == 1
-```
-
-### 4. Security and Risk Assessment
-
-**Security Checklist:**
-
-- No `eval()`, `exec()`, or `pickle` on user-controlled input
-- Proper exception handling (no bare `except:`) and use a `msg` variable for error messages
-- Remove unreachable/commented code before committing
-- Race conditions or resource leaks (file handles, sockets, threads).
-- Ensure proper resource cleanup (file handles, connections)
-
-❌ **Bad:**
-
-```python
-def load_config(path):
-    with open(path) as f:
-        return eval(f.read())  # ⚠️ Never eval config
-```
-
-✅ **Good:**
-
-```python
-import json
-
-def load_config(path: str) -> dict:
-    with open(path) as f:
-        return json.load(f)
-```
-
-### 5. Documentation Standards
-
-**Use Google-style docstrings with Args section for all public functions.**
-
-❌ **Insufficient Documentation:**
-
-```python
-def send_email(to, msg):
-    """Send an email to a recipient."""
-```
-
-✅ **Complete Documentation:**
-
-```python
-def send_email(to: str, msg: str, *, priority: str = "normal") -> bool:
-    """
-    Send an email to a recipient with specified priority.
-
-    Args:
-        to: The email address of the recipient.
-        msg: The message body to send.
-        priority: Email priority level (``'low'``, ``'normal'``, ``'high'``).
-
-    Returns:
-        True if email was sent successfully, False otherwise.
-
-    Raises:
-        InvalidEmailError: If the email address format is invalid.
-        SMTPConnectionError: If unable to connect to email server.
-    """
-```
-
-**Documentation Guidelines:**
-
-- Types go in function signatures, NOT in docstrings
-- Focus on "why" rather than "what" in descriptions
-- Document all parameters, return values, and exceptions
-- Keep descriptions concise but clear
-- Use reStructuredText for docstrings to enable rich formatting
-
-📌 *Tip:* Keep descriptions concise but clear. Only document return values if non-obvious.
-
-### 6. Architectural Improvements
-
-**When you encounter code that could be improved, suggest better designs:**
-
-❌ **Poor Design:**
-
-```python
-def process_data(data, db_conn, email_client, logger):
-    # Function doing too many things
-    validated = validate_data(data)
-    result = db_conn.save(validated)
-    email_client.send_notification(result)
-    logger.log(f"Processed {len(data)} items")
-    return result
-```
-
-✅ **Better Design:**
-
-```python
-@dataclass
-class ProcessingResult:
-    """Result of data processing operation."""
-    items_processed: int
-    success: bool
-    errors: List[str] = field(default_factory=list)
-
-class DataProcessor:
-    """Handles data validation, storage, and notification."""
-
-    def __init__(self, db_conn: Database, email_client: EmailClient):
-        self.db = db_conn
-        self.email = email_client
-
-    def process(self, data: List[dict]) -> ProcessingResult:
-        """Process and store data with notifications."""
-        validated = self._validate_data(data)
-        result = self.db.save(validated)
-        self._notify_completion(result)
-        return result
-```
-
-**Design Improvement Areas:**
-
-If there's a **cleaner**, **more scalable**, or **simpler** design, highlight it and suggest improvements that would:
-
-- Reduce code duplication through shared utilities
-- Make unit testing easier
-- Improve separation of concerns (single responsibility)
-- Make unit testing easier through dependency injection
-- Add clarity without adding complexity
-- Prefer dataclasses for structured data
-
-## Development Tools & Commands
-
-### Package Management
-
-```bash
-# Add package
-uv add package-name
-
-# Sync project dependencies
-uv sync
-uv lock
-```
-
-### Testing
-
-```bash
-# Run unit tests (no network)
-make test
-
-# Don't run integration tests, as API keys must be set
-
-# Run specific test file
-uv run --group test pytest tests/unit_tests/test_specific.py
-```
-
-### Code Quality
-
-```bash
-# Lint code
-make lint
-
-# Format code
-make format
-
-# Type checking
-uv run --group lint mypy .
-```
-
-### Dependency Management Patterns
-
-**Local Development Dependencies:**
-
-```toml
-[tool.uv.sources]
-langchain-core = { path = "../core", editable = true }
-langchain-tests = { path = "../standard-tests", editable = true }
-```
-
-**For tools, use the `@tool` decorator from `langchain_core.tools`:**
-
-```python
-from langchain_core.tools import tool
-
-@tool
-def search_database(query: str) -> str:
-    """Search the database for relevant information.
-
-    Args:
-        query: The search query string.
-    """
-    # Implementation here
-    return results
-```
-
-## Commit Standards
-
-**Use Conventional Commits format for PR titles:**
-
-- `feat(core): add multi-tenant support`
-- `fix(cli): resolve flag parsing error`
-- `docs: update API usage examples`
-- `docs(openai): update API usage examples`
-
-## Framework-Specific Guidelines
-
-- Follow the existing patterns in `langchain-core` for base abstractions
-- Use `langchain_core.callbacks` for execution tracking
-- Implement proper streaming support where applicable
-- Avoid deprecated components like legacy `LLMChain`
-
-### Partner Integrations
-
-- Follow the established patterns in existing partner libraries
-- Implement standard interfaces (`BaseChatModel`, `BaseEmbeddings`, etc.)
-- Include comprehensive integration tests
-- Document API key requirements and authentication
-
----
-
-## Quick Reference Checklist
-
-Before submitting code changes:
-
-- [ ] **Breaking Changes**: Verified no public API changes
-- [ ] **Type Hints**: All functions have complete type annotations
-- [ ] **Tests**: New functionality is fully tested
-- [ ] **Security**: No dangerous patterns (eval, silent failures, etc.)
-- [ ] **Documentation**: Google-style docstrings for public functions
-- [ ] **Code Quality**: `make lint` and `make format` pass
-- [ ] **Architecture**: Suggested improvements where applicable
-- [ ] **Commit Message**: Follows Conventional Commits format

CLAUDE.md

@@ -1,325 +0,0 @@
-# Global Development Guidelines for LangChain Projects
-
-## Core Development Principles
-
-### 1. Maintain Stable Public Interfaces ⚠️ CRITICAL
-
-**Always attempt to preserve function signatures, argument positions, and names for exported/public methods.**
-
-❌ **Bad - Breaking Change:**
-
-```python
-def get_user(id, verbose=False):  # Changed from `user_id`
-    pass
-```
-
-✅ **Good - Stable Interface:**
-
-```python
-def get_user(user_id: str, verbose: bool = False) -> User:
-    """Retrieve user by ID with optional verbose output."""
-    pass
-```
-
-**Before making ANY changes to public APIs:**
-
-- Check if the function/class is exported in `__init__.py`
-- Look for existing usage patterns in tests and examples
-- Use keyword-only arguments for new parameters: `*, new_param: str = "default"`
-- Mark experimental features clearly with docstring warnings (using reStructuredText, like `.. warning::`)
-
-🧠 *Ask yourself:* "Would this change break someone's code if they used it last week?"
-
-### 2. Code Quality Standards
-
-**All Python code MUST include type hints and return types.**
-
-❌ **Bad:**
-
-```python
-def p(u, d):
-    return [x for x in u if x not in d]
-```
-
-✅ **Good:**
-
-```python
-def filter_unknown_users(users: list[str], known_users: set[str]) -> list[str]:
-    """Filter out users that are not in the known users set.
-
-    Args:
-        users: List of user identifiers to filter.
-        known_users: Set of known/valid user identifiers.
-
-    Returns:
-        List of users that are not in the known_users set.
-    """
-    return [user for user in users if user not in known_users]
-```
-
-**Style Requirements:**
-
-- Use descriptive, **self-explanatory variable names**. Avoid overly short or cryptic identifiers.
-- Attempt to break up complex functions (>20 lines) into smaller, focused functions where it makes sense
-- Avoid unnecessary abstraction or premature optimization
-- Follow existing patterns in the codebase you're modifying
-
-### 3. Testing Requirements
-
-**Every new feature or bugfix MUST be covered by unit tests.**
-
-**Test Organization:**
-
-- Unit tests: `tests/unit_tests/` (no network calls allowed)
-- Integration tests: `tests/integration_tests/` (network calls permitted)
-- Use `pytest` as the testing framework
-
-**Test Quality Checklist:**
-
-- [ ] Tests fail when your new logic is broken
-- [ ] Happy path is covered
-- [ ] Edge cases and error conditions are tested
-- [ ] Use fixtures/mocks for external dependencies
-- [ ] Tests are deterministic (no flaky tests)
-
-Checklist questions:
-
-- [ ] Does the test suite fail if your new logic is broken?
-- [ ] Are all expected behaviors exercised (happy path, invalid input, etc)?
-- [ ] Do tests use fixtures or mocks where needed?
-
-```python
-def test_filter_unknown_users():
-    """Test filtering unknown users from a list."""
-    users = ["alice", "bob", "charlie"]
-    known_users = {"alice", "bob"}
-
-    result = filter_unknown_users(users, known_users)
-
-    assert result == ["charlie"]
-    assert len(result) == 1
-```
-
-### 4. Security and Risk Assessment
-
-**Security Checklist:**
-
-- No `eval()`, `exec()`, or `pickle` on user-controlled input
-- Proper exception handling (no bare `except:`) and use a `msg` variable for error messages
-- Remove unreachable/commented code before committing
-- Race conditions or resource leaks (file handles, sockets, threads).
-- Ensure proper resource cleanup (file handles, connections)
-
-❌ **Bad:**
-
-```python
-def load_config(path):
-    with open(path) as f:
-        return eval(f.read())  # ⚠️ Never eval config
-```
-
-✅ **Good:**
-
-```python
-import json
-
-def load_config(path: str) -> dict:
-    with open(path) as f:
-        return json.load(f)
-```
-
-### 5. Documentation Standards
-
-**Use Google-style docstrings with Args section for all public functions.**
-
-❌ **Insufficient Documentation:**
-
-```python
-def send_email(to, msg):
-    """Send an email to a recipient."""
-```
-
-✅ **Complete Documentation:**
-
-```python
-def send_email(to: str, msg: str, *, priority: str = "normal") -> bool:
-    """
-    Send an email to a recipient with specified priority.
-
-    Args:
-        to: The email address of the recipient.
-        msg: The message body to send.
-        priority: Email priority level (``'low'``, ``'normal'``, ``'high'``).
-
-    Returns:
-        True if email was sent successfully, False otherwise.
-
-    Raises:
-        InvalidEmailError: If the email address format is invalid.
-        SMTPConnectionError: If unable to connect to email server.
-    """
-```
-
-**Documentation Guidelines:**
-
-- Types go in function signatures, NOT in docstrings
-- Focus on "why" rather than "what" in descriptions
-- Document all parameters, return values, and exceptions
-- Keep descriptions concise but clear
-- Use reStructuredText for docstrings to enable rich formatting
-
-📌 *Tip:* Keep descriptions concise but clear. Only document return values if non-obvious.
-
-### 6. Architectural Improvements
-
-**When you encounter code that could be improved, suggest better designs:**
-
-❌ **Poor Design:**
-
-```python
-def process_data(data, db_conn, email_client, logger):
-    # Function doing too many things
-    validated = validate_data(data)
-    result = db_conn.save(validated)
-    email_client.send_notification(result)
-    logger.log(f"Processed {len(data)} items")
-    return result
-```
-
-✅ **Better Design:**
-
-```python
-@dataclass
-class ProcessingResult:
-    """Result of data processing operation."""
-    items_processed: int
-    success: bool
-    errors: List[str] = field(default_factory=list)
-
-class DataProcessor:
-    """Handles data validation, storage, and notification."""
-
-    def __init__(self, db_conn: Database, email_client: EmailClient):
-        self.db = db_conn
-        self.email = email_client
-
-    def process(self, data: List[dict]) -> ProcessingResult:
-        """Process and store data with notifications."""
-        validated = self._validate_data(data)
-        result = self.db.save(validated)
-        self._notify_completion(result)
-        return result
-```
-
-**Design Improvement Areas:**
-
-If there's a **cleaner**, **more scalable**, or **simpler** design, highlight it and suggest improvements that would:
-
-- Reduce code duplication through shared utilities
-- Make unit testing easier
-- Improve separation of concerns (single responsibility)
-- Make unit testing easier through dependency injection
-- Add clarity without adding complexity
-- Prefer dataclasses for structured data
-
-## Development Tools & Commands
-
-### Package Management
-
-```bash
-# Add package
-uv add package-name
-
-# Sync project dependencies
-uv sync
-uv lock
-```
-
-### Testing
-
-```bash
-# Run unit tests (no network)
-make test
-
-# Don't run integration tests, as API keys must be set
-
-# Run specific test file
-uv run --group test pytest tests/unit_tests/test_specific.py
-```
-
-### Code Quality
-
-```bash
-# Lint code
-make lint
-
-# Format code
-make format
-
-# Type checking
-uv run --group lint mypy .
-```
-
-### Dependency Management Patterns
-
-**Local Development Dependencies:**
-
-```toml
-[tool.uv.sources]
-langchain-core = { path = "../core", editable = true }
-langchain-tests = { path = "../standard-tests", editable = true }
-```
-
-**For tools, use the `@tool` decorator from `langchain_core.tools`:**
-
-```python
-from langchain_core.tools import tool
-
-@tool
-def search_database(query: str) -> str:
-    """Search the database for relevant information.
-
-    Args:
-        query: The search query string.
-    """
-    # Implementation here
-    return results
-```
-
-## Commit Standards
-
-**Use Conventional Commits format for PR titles:**
-
-- `feat(core): add multi-tenant support`
-- `fix(cli): resolve flag parsing error`
-- `docs: update API usage examples`
-- `docs(openai): update API usage examples`
-
-## Framework-Specific Guidelines
-
-- Follow the existing patterns in `langchain-core` for base abstractions
-- Use `langchain_core.callbacks` for execution tracking
-- Implement proper streaming support where applicable
-- Avoid deprecated components like legacy `LLMChain`
-
-### Partner Integrations
-
-- Follow the established patterns in existing partner libraries
-- Implement standard interfaces (`BaseChatModel`, `BaseEmbeddings`, etc.)
-- Include comprehensive integration tests
-- Document API key requirements and authentication
-
----
-
-## Quick Reference Checklist
-
-Before submitting code changes:
-
-- [ ] **Breaking Changes**: Verified no public API changes
-- [ ] **Type Hints**: All functions have complete type annotations
-- [ ] **Tests**: New functionality is fully tested
-- [ ] **Security**: No dangerous patterns (eval, silent failures, etc.)
-- [ ] **Documentation**: Google-style docstrings for public functions
-- [ ] **Code Quality**: `make lint` and `make format` pass
-- [ ] **Architecture**: Suggested improvements where applicable
-- [ ] **Commit Message**: Follows Conventional Commits format

MIGRATE.md

@@ -1,11 +1,70 @@
 # Migrating
 
-Please see the following guides for migrating LangChain code:
+## 🚨Breaking Changes for select chains (SQLDatabase) on 7/28/23
 
-* Migrate to [LangChain v0.3](https://python.langchain.com/docs/versions/v0_3/)
-* Migrate to [LangChain v0.2](https://python.langchain.com/docs/versions/v0_2/)
-* Migrating from [LangChain 0.0.x Chains](https://python.langchain.com/docs/versions/migrating_chains/)
-* Upgrade to [LangGraph Memory](https://python.langchain.com/docs/versions/migrating_memory/)
+In an effort to make `langchain` leaner and safer, we are moving select chains to `langchain_experimental`.
+This migration has already started, but we are remaining backwards compatible until 7/28.
+On that date, we will remove functionality from `langchain`.
+Read more about the motivation and the progress [here](https://github.com/langchain-ai/langchain/discussions/8043).
 
-The [LangChain CLI](https://python.langchain.com/docs/versions/v0_3/#migrate-using-langchain-cli) can help you automatically upgrade your code to use non-deprecated imports.
-This will be especially helpful if you're still on either version 0.0.x or 0.1.x of LangChain.
+### 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

@@ -1,107 +1,76 @@
-.PHONY: all clean help docs_build docs_clean docs_linkcheck api_docs_build api_docs_clean api_docs_linkcheck lint lint_package lint_tests format format_diff
+.PHONY: all clean docs_build docs_clean docs_linkcheck api_docs_build api_docs_clean api_docs_linkcheck
 
-.EXPORT_ALL_VARIABLES:
-UV_FROZEN = true
+# Default target executed when no arguments are given to make.
+all: help
 
-## help: Show this help info.
-help: Makefile
-	@printf "\n\033[1mUsage: make <TARGETS> ...\033[0m\n\n\033[1mTargets:\033[0m\n\n"
-	@sed -n 's/^## //p' $< | awk -F':' '{printf "\033[36m%-30s\033[0m %s\n", $$1, $$2}' | sort | sed -e 's/^/  /'
-
-## clean: Clean documentation and API documentation artifacts.
-clean: docs_clean api_docs_clean
 
 ######################
 # DOCUMENTATION
 ######################
 
-## docs_build: Build the documentation.
-docs_build: docs_clean
-	@echo "📚 Building LangChain documentation..."
-	cd docs && make build
-	@echo "✅ Documentation build complete!"
+clean: docs_clean api_docs_clean
+
+
+docs_build:
+	docs/.local_build.sh
 
-## docs_clean: Clean the documentation build artifacts.
 docs_clean:
-	@echo "🧹 Cleaning documentation artifacts..."
-	cd docs && make clean
-	@echo "✅ LangChain documentation cleaned"
+	@if [ -d _dist ]; then \
+			rm -r _dist; \
+			echo "Directory _dist has been cleaned."; \
+	else \
+			echo "Nothing to clean."; \
+	fi
 
-## docs_linkcheck: Run linkchecker on the documentation.
 docs_linkcheck:
-	@echo "🔗 Checking documentation links..."
-	@if [ -d _dist/docs ]; then \
-		uv run --group test linkchecker _dist/docs/ --ignore-url node_modules; \
-	else \
-		echo "⚠️  Documentation not built. Run 'make docs_build' first."; \
-		exit 1; \
-	fi
-	@echo "✅ Link check complete"
+	poetry run linkchecker _dist/docs/ --ignore-url node_modules
 
-## api_docs_build: Build the API Reference documentation.
-api_docs_build: clean
-	@echo "📖 Building API Reference documentation..."
-	uv pip install -e libs/cli
-	uv run --group docs python docs/api_reference/create_api_rst.py
-	cd docs/api_reference && uv run --group docs make html
-	uv run --group docs python docs/api_reference/scripts/custom_formatter.py docs/api_reference/_build/html/
-	@echo "✅ API documentation built"
-	@echo "🌐 Opening documentation in browser..."
-	open docs/api_reference/_build/html/reference.html
+api_docs_build:
+	poetry run python docs/api_reference/create_api_rst.py
+	cd docs/api_reference && poetry run make html
 
-API_PKG ?= text-splitters
-
-api_docs_quick_preview: clean
-	@echo "⚡ Building quick API preview for $(API_PKG)..."
-	uv run --group docs python docs/api_reference/create_api_rst.py $(API_PKG)
-	cd docs/api_reference && uv run --group docs make html
-	uv run --group docs python docs/api_reference/scripts/custom_formatter.py docs/api_reference/_build/html/
-	@echo "🌐 Opening preview in browser..."
-	open docs/api_reference/_build/html/reference.html
-
-## api_docs_clean: Clean the API Reference documentation build artifacts.
 api_docs_clean:
-	@echo "🧹 Cleaning API documentation artifacts..."
-	find ./docs/api_reference -name '*_api_reference.rst' -delete
-	git clean -fdX ./docs/api_reference
-	rm -f docs/api_reference/index.md
-	@echo "✅ API documentation cleaned"
+	rm -f docs/api_reference/api_reference.rst
+	cd docs/api_reference && poetry run make clean
 
-## api_docs_linkcheck: Run linkchecker on the API Reference documentation.
 api_docs_linkcheck:
-	@echo "🔗 Checking API documentation links..."
-	@if [ -f docs/api_reference/_build/html/index.html ]; then \
-		uv run --group test linkchecker docs/api_reference/_build/html/index.html; \
-	else \
-		echo "⚠️  API documentation not built. Run 'make api_docs_build' first."; \
-		exit 1; \
-	fi
-	@echo "✅ API link check complete"
+	poetry run linkchecker docs/api_reference/_build/html/index.html
+
+spell_check:
+	poetry run codespell --toml pyproject.toml
+
+spell_fix:
+	poetry run codespell --toml pyproject.toml -w
 
 ######################
 # LINTING AND FORMATTING
 ######################
 
-## lint: Run linting on the project.
 lint lint_package lint_tests:
-	@echo "🔍 Running code linting and checks..."
-	uv run --group lint ruff check docs cookbook
-	uv run --group lint ruff format docs cookbook cookbook --diff
-	git --no-pager grep 'from langchain import' docs cookbook | grep -vE 'from langchain import (hub)' && echo "Error: no importing langchain from root in docs, except for hub" && exit 1 || exit 0
+	poetry run ruff docs templates cookbook
+	poetry run ruff format docs templates cookbook --diff
+	poetry run ruff --select I docs templates cookbook
+	git grep 'from langchain import' docs/docs templates cookbook | grep -vE 'from langchain import (hub)' && exit 1 || exit 0
 
-	git --no-pager grep 'api.python.langchain.com' -- docs/docs ':!docs/docs/additional_resources/arxiv_references.mdx' ':!docs/docs/integrations/document_loaders/sitemap.ipynb' || exit 0 && \
-	echo "Error: you should link python.langchain.com/api_reference, not api.python.langchain.com in the docs" && \
-	exit 1
-	@echo "✅ Linting complete"
-
-## format: Format the project files.
 format format_diff:
-	@echo "🎨 Formatting project files..."
-	uv run --group lint ruff format docs cookbook
-	uv run --group lint ruff check --fix docs cookbook
-	@echo "✅ Formatting complete"
+	poetry run ruff format docs templates cookbook
+	poetry run ruff --select I --fix docs templates cookbook
 
-update-package-downloads:
-	@echo "📊 Updating package download statistics..."
-	uv run python docs/scripts/packages_yml_get_downloads.py
-	@echo "✅ Package downloads updated"
+
+######################
+# HELP
+######################
+
+help:
+	@echo '===================='
+	@echo '-- DOCUMENTATION --'
+	@echo 'clean                        - run docs_clean and api_docs_clean'
+	@echo 'docs_build                   - build the documentation'
+	@echo 'docs_clean                   - clean the documentation build artifacts'
+	@echo 'docs_linkcheck               - run linkchecker on the documentation'
+	@echo 'api_docs_build               - build the API Reference documentation'
+	@echo 'api_docs_clean               - clean the API Reference documentation build artifacts'
+	@echo 'api_docs_linkcheck           - run linkchecker on the API Reference documentation'
+	@echo 'spell_check               	- run codespell on the project'
+	@echo 'spell_fix               		- run codespell on the project and fix the errors'
+	@echo '-- TEST and LINT tasks are within libs/*/ per-package --'

README.md

@@ -1,83 +1,113 @@
-<picture>
-  <source media="(prefers-color-scheme: light)" srcset="docs/static/img/logo-dark.svg">
-  <source media="(prefers-color-scheme: dark)" srcset="docs/static/img/logo-light.svg">
-  <img alt="LangChain Logo" src="docs/static/img/logo-dark.svg" width="80%">
-</picture>
+# 🦜️🔗 LangChain
 
-<div>
-<br>
-</div>
+⚡ Build context-aware reasoning applications ⚡
 
-[![PyPI - License](https://img.shields.io/pypi/l/langchain-core?style=flat-square)](https://opensource.org/licenses/MIT)
-[![PyPI - Downloads](https://img.shields.io/pepy/dt/langchain)](https://pypistats.org/packages/langchain-core)
-[![Open in Dev Containers](https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode&style=flat-square)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langchain-ai/langchain)
-[<img src="https://github.com/codespaces/badge.svg" alt="Open in Github Codespace" title="Open in Github Codespace" width="150" height="20">](https://codespaces.new/langchain-ai/langchain)
-[![CodSpeed Badge](https://img.shields.io/endpoint?url=https://codspeed.io/badge.json)](https://codspeed.io/langchain-ai/langchain)
+[![Release Notes](https://img.shields.io/github/release/langchain-ai/langchain)](https://github.com/langchain-ai/langchain/releases)
+[![CI](https://github.com/langchain-ai/langchain/actions/workflows/check_diffs.yml/badge.svg)](https://github.com/langchain-ai/langchain/actions/workflows/check_diffs.yml)
+[![Downloads](https://static.pepy.tech/badge/langchain/month)](https://pepy.tech/project/langchain)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 [![Twitter](https://img.shields.io/twitter/url/https/twitter.com/langchainai.svg?style=social&label=Follow%20%40LangChainAI)](https://twitter.com/langchainai)
+[![](https://dcbadge.vercel.app/api/server/6adMQxSpJS?compact=true&style=flat)](https://discord.gg/6adMQxSpJS)
+[![Open in Dev Containers](https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langchain-ai/langchain)
+[![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/langchain-ai/langchain)
+[![GitHub star chart](https://img.shields.io/github/stars/langchain-ai/langchain?style=social)](https://star-history.com/#langchain-ai/langchain)
+[![Dependency Status](https://img.shields.io/librariesio/github/langchain-ai/langchain)](https://libraries.io/github/langchain-ai/langchain)
+[![Open Issues](https://img.shields.io/github/issues-raw/langchain-ai/langchain)](https://github.com/langchain-ai/langchain/issues)
 
-> [!NOTE]
-> Looking for the JS/TS library? Check out [LangChain.js](https://github.com/langchain-ai/langchainjs).
+Looking for the JS/TS library? Check out [LangChain.js](https://github.com/langchain-ai/langchainjs).
 
-LangChain is a framework for building LLM-powered applications. It helps you chain
-together interoperable components and third-party integrations to simplify AI
-application development —  all while future-proofing decisions as the underlying
-technology evolves.
+To help you ship LangChain apps to production faster, check out [LangSmith](https://smith.langchain.com). 
+[LangSmith](https://smith.langchain.com) is a unified developer platform for building, testing, and monitoring LLM applications. 
+Fill out [this form](https://www.langchain.com/contact-sales) to speak with our sales team.
 
+## Quick Install
+
+With pip:
 ```bash
-pip install -U langchain
+pip install langchain
 ```
 
-To learn more about LangChain, check out
-[the docs](https://python.langchain.com/docs/introduction/). If you’re looking for more
-advanced customization or agent orchestration, check out
-[LangGraph](https://langchain-ai.github.io/langgraph/), our framework for building
-controllable agent workflows.
+With conda:
+```bash
+conda install langchain -c conda-forge
+```
 
-## Why use LangChain?
+## 🤔 What is LangChain?
 
-LangChain helps developers build applications powered by LLMs through a standard
-interface for models, embeddings, vector stores, and more.
+**LangChain** is a framework for developing applications powered by language models. It enables applications that:
+- **Are context-aware**: connect a language model to sources of context (prompt instructions, few shot examples, content to ground its response in, etc.)
+- **Reason**: rely on a language model to reason (about how to answer based on provided context, what actions to take, etc.)
 
-Use LangChain for:
+This framework consists of several parts.
+- **LangChain Libraries**: The Python and JavaScript libraries. Contains interfaces and integrations for a myriad of components, a basic run time for combining these components into chains and agents, and off-the-shelf implementations of chains and agents.
+- **[LangChain Templates](templates)**: A collection of easily deployable reference architectures for a wide variety of tasks.
+- **[LangServe](https://github.com/langchain-ai/langserve)**: A library for deploying LangChain chains as a REST API.
+- **[LangSmith](https://smith.langchain.com)**: A developer platform that lets you debug, test, evaluate, and monitor chains built on any LLM framework and seamlessly integrates with LangChain.
+- **[LangGraph](https://python.langchain.com/docs/langgraph)**: LangGraph is a library for building stateful, multi-actor applications with LLMs, built on top of (and intended to be used with) LangChain. It extends the LangChain Expression Language with the ability to coordinate multiple chains (or actors) across multiple steps of computation in a cyclic manner. 
 
-- **Real-time data augmentation**. Easily connect LLMs to diverse data sources and
-external/internal systems, drawing from LangChain’s vast library of integrations with
-model providers, tools, vector stores, retrievers, and more.
-- **Model interoperability**. Swap models in and out as your engineering team
-experiments to find the best choice for your application’s needs. As the industry
-frontier evolves, adapt quickly — LangChain’s abstractions keep you moving without
-losing momentum.
+The LangChain libraries themselves are made up of several different packages.
+- **[`langchain-core`](libs/core)**: Base abstractions and LangChain Expression Language.
+- **[`langchain-community`](libs/community)**: Third party integrations.
+- **[`langchain`](libs/langchain)**: Chains, agents, and retrieval strategies that make up an application's cognitive architecture.
 
-## LangChain’s ecosystem
+![Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers.](docs/static/svg/langchain_stack.svg "LangChain Architecture Overview")
 
-While the LangChain framework can be used standalone, it also integrates seamlessly
-with any LangChain product, giving developers a full suite of tools when building LLM
-applications.
+## 🧱 What can you build with LangChain?
+**❓ Retrieval augmented generation**
 
-To improve your LLM application development, pair LangChain with:
+- [Documentation](https://python.langchain.com/docs/use_cases/question_answering/)
+- End-to-end Example: [Chat LangChain](https://chat.langchain.com) and [repo](https://github.com/langchain-ai/chat-langchain)
 
-- [LangSmith](https://www.langchain.com/langsmith) - Helpful for agent evals and
-observability. Debug poor-performing LLM app runs, evaluate agent trajectories, gain
-visibility in production, and improve performance over time.
-- [LangGraph](https://langchain-ai.github.io/langgraph/) - Build agents that can
-reliably handle complex tasks with LangGraph, our low-level agent orchestration
-framework. LangGraph offers customizable architecture, long-term memory, and
-human-in-the-loop workflows — and is trusted in production by companies like LinkedIn,
-Uber, Klarna, and GitLab.
-- [LangGraph Platform](https://docs.langchain.com/langgraph-platform) - Deploy
-and scale agents effortlessly with a purpose-built deployment platform for long-running, stateful workflows. Discover, reuse, configure, and share agents across
-teams — and iterate quickly with visual prototyping in
-[LangGraph Studio](https://langchain-ai.github.io/langgraph/concepts/langgraph_studio/).
+**💬 Analyzing structured data**
 
-## Additional resources
+- [Documentation](https://python.langchain.com/docs/use_cases/qa_structured/sql)
+- End-to-end Example: [SQL Llama2 Template](https://github.com/langchain-ai/langchain/tree/master/templates/sql-llama2)
 
-- [Tutorials](https://python.langchain.com/docs/tutorials/): Simple walkthroughs with
-guided examples on getting started with LangChain.
-- [How-to Guides](https://python.langchain.com/docs/how_to/): Quick, actionable code
-snippets for topics such as tool calling, RAG use cases, and more.
-- [Conceptual Guides](https://python.langchain.com/docs/concepts/): Explanations of key
-concepts behind the LangChain framework.
-- [LangChain Forum](https://forum.langchain.com/): Connect with the community and share all of your technical questions, ideas, and feedback.
-- [API Reference](https://python.langchain.com/api_reference/): Detailed reference on
-navigating base packages and integrations for LangChain.
-- [Chat LangChain](https://chat.langchain.com/): Ask questions & chat with our documentation.
+**🤖 Chatbots**
+
+- [Documentation](https://python.langchain.com/docs/use_cases/chatbots)
+- End-to-end Example: [Web LangChain (web researcher chatbot)](https://weblangchain.vercel.app) and [repo](https://github.com/langchain-ai/weblangchain)
+
+And much more! Head to the [Use cases](https://python.langchain.com/docs/use_cases/) section of the docs for more.
+
+## 🚀 How does LangChain help?
+The main value props of the LangChain libraries are:
+1. **Components**: composable tools and integrations for working with language models. Components are modular and easy-to-use, whether you are using the rest of the LangChain framework or not
+2. **Off-the-shelf chains**: built-in assemblages of components for accomplishing higher-level tasks
+
+Off-the-shelf chains make it easy to get started. Components make it easy to customize existing chains and build new ones. 
+
+Components fall into the following **modules**:
+
+**📃 Model I/O:**
+
+This includes prompt management, prompt optimization, a generic interface for all LLMs, and common utilities for working with LLMs.
+
+**📚 Retrieval:**
+
+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.
+
+## 📖 Documentation
+
+Please see [here](https://python.langchain.com) for full documentation, which includes:
+
+- [Getting started](https://python.langchain.com/docs/get_started/introduction): installation, setting up the environment, simple examples
+- Overview of the [interfaces](https://python.langchain.com/docs/expression_language/), [modules](https://python.langchain.com/docs/modules/), and [integrations](https://python.langchain.com/docs/integrations/providers)
+- [Use case](https://python.langchain.com/docs/use_cases/qa_structured/sql) walkthroughs and best practice [guides](https://python.langchain.com/docs/guides/adapters/openai)
+- [LangSmith](https://python.langchain.com/docs/langsmith/), [LangServe](https://python.langchain.com/docs/langserve), and [LangChain Template](https://python.langchain.com/docs/templates/) overviews
+- [Reference](https://api.python.langchain.com): full API docs
+
+
+## 💁 Contributing
+
+As an open-source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of a new feature, improved infrastructure, or better documentation.
+
+For detailed information on how to contribute, see [here](https://python.langchain.com/docs/contributing/).
+
+## 🌟 Contributors
+
+[![langchain contributors](https://contrib.rocks/image?repo=langchain-ai/langchain&max=2000)](https://github.com/langchain-ai/langchain/graphs/contributors)

SECURITY.md

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

cookbook/Gemma_LangChain.ipynb

@@ -60,7 +60,7 @@
     "id": "CI8Elyc5gBQF"
    },
    "source": [
-    "Go to the VertexAI Model Garden on Google Cloud [console](https://pantheon.corp.google.com/vertex-ai/publishers/google/model-garden/335), and deploy the desired version of Gemma to VertexAI. It will take a few minutes, and after the endpoint is ready, you need to copy its number."
+    "Go to the VertexAI Model Garden on Google Cloud [console](https://pantheon.corp.google.com/vertex-ai/publishers/google/model-garden/335), and deploy the desired version of Gemma to VertexAI. It will take a few minutes, and after the endpoint it ready, you need to copy its number."
    ]
   },
   {

cookbook/LLaMA2_sql_chat.ipynb

@@ -38,16 +38,16 @@
     "\n",
     "To run locally, we use Ollama.ai. \n",
     "\n",
-    "See [here](/docs/integrations/chat/ollama) for details on installation and setup.\n",
+    "See [here](https://python.langchain.com/docs/integrations/chat/ollama) for details on installation and setup.\n",
     "\n",
-    "Also, see [here](/docs/guides/development/local_llms) for our full guide on local LLMs.\n",
+    "Also, see [here](https://python.langchain.com/docs/guides/local_llms) for our full guide on local LLMs.\n",
     " \n",
     "To use an external API, which is not private, we can use Replicate."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "id": "6a75a5c6-34ee-4ab9-a664-d9b432d812ee",
    "metadata": {},
    "outputs": [
@@ -61,7 +61,7 @@
    ],
    "source": [
     "# Local\n",
-    "from langchain_ollama import ChatOllama\n",
+    "from langchain_community.chat_models import ChatOllama\n",
     "\n",
     "llama2_chat = ChatOllama(model=\"llama2:13b-chat\")\n",
     "llama2_code = ChatOllama(model=\"codellama:7b-instruct\")\n",

cookbook/Multi_modal_RAG.ipynb

@@ -64,7 +64,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install -U langchain openai langchain-chroma langchain-experimental # (newest versions required for multi-modal)"
+    "! pip install -U langchain openai chromadb langchain-experimental # (newest versions required for multi-modal)"
    ]
   },
   {
@@ -355,7 +355,7 @@
     "\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryStore\n",
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_core.documents import Document\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
@@ -464,8 +464,8 @@
     "    Check if the base64 data is an image by looking at the start of the data\n",
     "    \"\"\"\n",
     "    image_signatures = {\n",
-    "        b\"\\xff\\xd8\\xff\": \"jpg\",\n",
-    "        b\"\\x89\\x50\\x4e\\x47\\x0d\\x0a\\x1a\\x0a\": \"png\",\n",
+    "        b\"\\xFF\\xD8\\xFF\": \"jpg\",\n",
+    "        b\"\\x89\\x50\\x4E\\x47\\x0D\\x0A\\x1A\\x0A\": \"png\",\n",
     "        b\"\\x47\\x49\\x46\\x38\": \"gif\",\n",
     "        b\"\\x52\\x49\\x46\\x46\": \"webp\",\n",
     "    }\n",
@@ -604,7 +604,7 @@
    "source": [
     "# Check retrieval\n",
     "query = \"Give me company names that are interesting investments based on EV / NTM and NTM rev growth. Consider EV / NTM multiples vs historical?\"\n",
-    "docs = retriever_multi_vector_img.invoke(query, limit=6)\n",
+    "docs = retriever_multi_vector_img.get_relevant_documents(query, limit=6)\n",
     "\n",
     "# We get 4 docs\n",
     "len(docs)"
@@ -630,7 +630,7 @@
    "source": [
     "# Check retrieval\n",
     "query = \"What are the EV / NTM and NTM rev growth for MongoDB, Cloudflare, and Datadog?\"\n",
-    "docs = retriever_multi_vector_img.invoke(query, limit=6)\n",
+    "docs = retriever_multi_vector_img.get_relevant_documents(query, limit=6)\n",
     "\n",
     "# We get 4 docs\n",
     "len(docs)"

cookbook/Multi_modal_RAG_google.ipynb

@@ -37,7 +37,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install -U --quiet langchain langchain-chroma langchain-community openai langchain-experimental\n",
+    "%pip install -U --quiet langchain langchain_community openai chromadb langchain-experimental\n",
     "%pip install --quiet \"unstructured[all-docs]\" pypdf pillow pydantic lxml pillow matplotlib chromadb tiktoken"
    ]
   },
@@ -144,7 +144,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "id": "kWDWfSDBMPl8",
    "metadata": {},
    "outputs": [
@@ -185,7 +185,7 @@
     "    )\n",
     "    # Text summary chain\n",
     "    model = VertexAI(\n",
-    "        temperature=0, model_name=\"gemini-2.5-flash\", max_tokens=1024\n",
+    "        temperature=0, model_name=\"gemini-pro\", max_output_tokens=1024\n",
     "    ).with_fallbacks([empty_response])\n",
     "    summarize_chain = {\"element\": lambda x: x} | prompt | model | StrOutputParser()\n",
     "\n",
@@ -235,7 +235,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "id": "PeK9bzXv3olF",
    "metadata": {},
    "outputs": [],
@@ -254,9 +254,9 @@
     "\n",
     "def image_summarize(img_base64, prompt):\n",
     "    \"\"\"Make image summary\"\"\"\n",
-    "    model = ChatVertexAI(model=\"gemini-2.5-flash\", max_tokens=1024)\n",
+    "    model = ChatVertexAI(model_name=\"gemini-pro-vision\", max_output_tokens=1024)\n",
     "\n",
-    "    msg = model.invoke(\n",
+    "    msg = model(\n",
     "        [\n",
     "            HumanMessage(\n",
     "                content=[\n",
@@ -344,8 +344,8 @@
     "\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryStore\n",
-    "from langchain_chroma import Chroma\n",
     "from langchain_community.embeddings import VertexAIEmbeddings\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_core.documents import Document\n",
     "\n",
     "\n",
@@ -394,7 +394,7 @@
     "# The vectorstore to use to index the summaries\n",
     "vectorstore = Chroma(\n",
     "    collection_name=\"mm_rag_cj_blog\",\n",
-    "    embedding_function=VertexAIEmbeddings(model_name=\"text-embedding-005\"),\n",
+    "    embedding_function=VertexAIEmbeddings(model_name=\"textembedding-gecko@latest\"),\n",
     ")\n",
     "\n",
     "# Create retriever\n",
@@ -431,7 +431,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 9,
    "id": "GlwCErBaCKQW",
    "metadata": {},
    "outputs": [],
@@ -445,7 +445,7 @@
     "\n",
     "\n",
     "def plt_img_base64(img_base64):\n",
-    "    \"\"\"Display base64 encoded string as image\"\"\"\n",
+    "    \"\"\"Disply base64 encoded string as image\"\"\"\n",
     "    # Create an HTML img tag with the base64 string as the source\n",
     "    image_html = f'<img src=\"data:image/jpeg;base64,{img_base64}\" />'\n",
     "    # Display the image by rendering the HTML\n",
@@ -462,8 +462,8 @@
     "    Check if the base64 data is an image by looking at the start of the data\n",
     "    \"\"\"\n",
     "    image_signatures = {\n",
-    "        b\"\\xff\\xd8\\xff\": \"jpg\",\n",
-    "        b\"\\x89\\x50\\x4e\\x47\\x0d\\x0a\\x1a\\x0a\": \"png\",\n",
+    "        b\"\\xFF\\xD8\\xFF\": \"jpg\",\n",
+    "        b\"\\x89\\x50\\x4E\\x47\\x0D\\x0A\\x1A\\x0A\": \"png\",\n",
     "        b\"\\x47\\x49\\x46\\x38\": \"gif\",\n",
     "        b\"\\x52\\x49\\x46\\x46\": \"webp\",\n",
     "    }\n",
@@ -553,7 +553,9 @@
     "    \"\"\"\n",
     "\n",
     "    # Multi-modal LLM\n",
-    "    model = ChatVertexAI(temperature=0, model_name=\"gemini-2.5-flash\", max_tokens=1024)\n",
+    "    model = ChatVertexAI(\n",
+    "        temperature=0, model_name=\"gemini-pro-vision\", max_output_tokens=1024\n",
+    "    )\n",
     "\n",
     "    # RAG pipeline\n",
     "    chain = (\n",
@@ -602,7 +604,7 @@
    ],
    "source": [
     "query = \"What are the EV / NTM and NTM rev growth for MongoDB, Cloudflare, and Datadog?\"\n",
-    "docs = retriever_multi_vector_img.invoke(query, limit=1)\n",
+    "docs = retriever_multi_vector_img.get_relevant_documents(query, limit=1)\n",
     "\n",
     "# We get 2 docs\n",
     "len(docs)"

cookbook/RAPTOR.ipynb

@@ -7,7 +7,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "pip install -U langchain umap-learn scikit-learn langchain_community tiktoken langchain-openai langchainhub langchain-chroma langchain-anthropic"
+    "pip install -U langchain umap-learn scikit-learn langchain_community tiktoken langchain-openai langchainhub chromadb langchain-anthropic"
    ]
   },
   {
@@ -535,9 +535,9 @@
     "    print(f\"--Generated {len(all_clusters)} clusters--\")\n",
     "\n",
     "    # Summarization\n",
-    "    template = \"\"\"Here is a sub-set of LangChain Expression Language doc. \n",
+    "    template = \"\"\"Here is a sub-set of LangChain Expression Langauge doc. \n",
     "    \n",
-    "    LangChain Expression Language provides a way to compose chain in LangChain.\n",
+    "    LangChain Expression Langauge provides a way to compose chain in LangChain.\n",
     "    \n",
     "    Give a detailed summary of the documentation provided.\n",
     "    \n",
@@ -645,7 +645,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "\n",
     "# Initialize all_texts with leaf_texts\n",
     "all_texts = leaf_texts.copy()\n",

cookbook/README.md

@@ -4,8 +4,6 @@ Example code for building applications with LangChain, with an emphasis on more
 
 Notebook | Description
 :- | :-
-[agent_fireworks_ai_langchain_mongodb.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/agent_fireworks_ai_langchain_mongodb.ipynb) | Build an AI Agent With Memory Using MongoDB, LangChain and FireWorksAI.
-[mongodb-langchain-cache-memory.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/mongodb-langchain-cache-memory.ipynb) | Build a RAG Application with Semantic Cache Using MongoDB and LangChain.
 [LLaMA2_sql_chat.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/LLaMA2_sql_chat.ipynb) | Build a chat application that interacts with a SQL database using an open source llm (llama2), specifically demonstrated on an SQLite database containing rosters.
 [Semi_Structured_RAG.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/Semi_Structured_RAG.ipynb) | Perform retrieval-augmented generation (rag) on documents with semi-structured data, including text and tables, using unstructured for parsing, multi-vector retriever for storing, and lcel for implementing chains.
 [Semi_structured_and_multi_moda...](https://github.com/langchain-ai/langchain/tree/master/cookbook/Semi_structured_and_multi_modal_RAG.ipynb) | Perform retrieval-augmented generation (rag) on documents with semi-structured data and images, using unstructured for parsing, multi-vector retriever for storage and retrieval, and lcel for implementing chains.
@@ -21,6 +19,7 @@ Notebook | Description
 [code-analysis-deeplake.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/code-analysis-deeplake.ipynb) | Analyze its own code base with the help of gpt and activeloop's deep lake.
 [custom_agent_with_plugin_retri...](https://github.com/langchain-ai/langchain/tree/master/cookbook/custom_agent_with_plugin_retrieval.ipynb) | Build a custom agent that can interact with ai plugins by retrieving tools and creating natural language wrappers around openapi endpoints.
 [custom_agent_with_plugin_retri...](https://github.com/langchain-ai/langchain/tree/master/cookbook/custom_agent_with_plugin_retrieval_using_plugnplai.ipynb) | Build a custom agent with plugin retrieval functionality, utilizing ai plugins from the `plugnplai` directory.
+[databricks_sql_db.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/databricks_sql_db.ipynb) | Connect to databricks runtimes and databricks sql.
 [deeplake_semantic_search_over_...](https://github.com/langchain-ai/langchain/tree/master/cookbook/deeplake_semantic_search_over_chat.ipynb) | Perform semantic search and question-answering over a group chat using activeloop's deep lake with gpt4.
 [elasticsearch_db_qa.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/elasticsearch_db_qa.ipynb) | Interact with elasticsearch analytics databases in natural language and build search queries via the elasticsearch dsl API.
 [extraction_openai_tools.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/extraction_openai_tools.ipynb) | Structured Data Extraction with OpenAI Tools
@@ -37,7 +36,6 @@ Notebook | Description
 [llm_symbolic_math.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/llm_symbolic_math.ipynb) | Solve algebraic equations with the help of llms (language learning models) and sympy, a python library for symbolic mathematics.
 [meta_prompt.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/meta_prompt.ipynb) | Implement the meta-prompt concept, which is a method for building self-improving agents that reflect on their own performance and modify their instructions accordingly.
 [multi_modal_output_agent.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multi_modal_output_agent.ipynb) | Generate multi-modal outputs, specifically images and text.
-[multi_modal_RAG_vdms.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multi_modal_RAG_vdms.ipynb) | Perform retrieval-augmented generation (rag) on documents including text and images, using unstructured for parsing, Intel's Visual Data Management System (VDMS) as the vectorstore, and chains.
 [multi_player_dnd.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multi_player_dnd.ipynb) | Simulate multi-player dungeons & dragons games, with a custom function determining the speaking schedule of the agents.
 [multiagent_authoritarian.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multiagent_authoritarian.ipynb) | Implement a multi-agent simulation where a privileged agent controls the conversation, including deciding who speaks and when the conversation ends, in the context of a simulated news network.
 [multiagent_bidding.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multiagent_bidding.ipynb) | Implement a multi-agent simulation where agents bid to speak, with the highest bidder speaking next, demonstrated through a fictitious presidential debate example.
@@ -49,7 +47,6 @@ Notebook | Description
 [press_releases.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/press_releases.ipynb) | Retrieve and query company press release data powered by [Kay.ai](https://kay.ai).
 [program_aided_language_model.i...](https://github.com/langchain-ai/langchain/tree/master/cookbook/program_aided_language_model.ipynb) | Implement program-aided language models as described in the provided research paper.
 [qa_citations.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/qa_citations.ipynb) | Different ways to get a model to cite its sources.
-[rag_upstage_document_parse_groundedness_check.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/rag_upstage_document_parse_groundedness_check.ipynb) | End-to-end RAG example using Upstage Document Parse and Groundedness Check.
 [retrieval_in_sql.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/retrieval_in_sql.ipynb) | Perform retrieval-augmented-generation (rag) on a PostgreSQL database using pgvector.
 [sales_agent_with_context.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/sales_agent_with_context.ipynb) | Implement a context-aware ai sales agent, salesgpt, that can have natural sales conversations, interact with other systems, and use a product knowledge base to discuss a company's offerings.
 [self_query_hotel_search.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/self_query_hotel_search.ipynb) | Build a hotel room search feature with self-querying retrieval, using a specific hotel recommendation dataset.
@@ -59,9 +56,3 @@ Notebook | Description
 [two_agent_debate_tools.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/two_agent_debate_tools.ipynb) | Simulate multi-agent dialogues where the agents can utilize various tools.
 [two_player_dnd.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/two_player_dnd.ipynb) | Simulate a two-player dungeons & dragons game, where a dialogue simulator class is used to coordinate the dialogue between the protagonist and the dungeon master.
 [wikibase_agent.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/wikibase_agent.ipynb) | Create a simple wikibase agent that utilizes sparql generation, with testing done on http://wikidata.org.
-[oracleai_demo.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/oracleai_demo.ipynb) | This guide outlines how to utilize Oracle AI Vector Search alongside Langchain for an end-to-end RAG pipeline, providing step-by-step examples. The process includes loading documents from various sources using OracleDocLoader, summarizing them either within or outside the database with OracleSummary, and generating embeddings similarly through OracleEmbeddings. It also covers chunking documents according to specific requirements using Advanced Oracle Capabilities from OracleTextSplitter, and finally, storing and indexing these documents in a Vector Store for querying with OracleVS.
-[rag-locally-on-intel-cpu.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/rag-locally-on-intel-cpu.ipynb) | Perform Retrieval-Augmented-Generation (RAG) on locally downloaded open-source models using langchain and open source tools and execute it on Intel Xeon CPU. We showed an example of how to apply RAG on Llama 2 model and enable it to answer the queries related to Intel Q1 2024 earnings release.
-[visual_RAG_vdms.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/visual_RAG_vdms.ipynb) | Performs Visual Retrieval-Augmented-Generation (RAG) using videos and scene descriptions generated by open source models.
-[contextual_rag.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/contextual_rag.ipynb) | Performs contextual retrieval-augmented generation (RAG) prepending chunk-specific explanatory context to each chunk before embedding.
-[rag-agents-locally-on-intel-cpu.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/local_rag_agents_intel_cpu.ipynb) | Build a RAG agent locally with open source models that routes questions through one of two paths to find answers. The agent generates answers based on documents retrieved from either the vector database or retrieved from web search. If the vector database lacks relevant information, the agent opts for web search. Open-source models for LLM and embeddings are used locally on an Intel Xeon CPU to execute this pipeline.
-[rag_mlflow_tracking_evaluation.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/rag_mlflow_tracking_evaluation.ipynb) | Guide on how to create a RAG pipeline and track + evaluate it with MLflow.

cookbook/Semi_Structured_RAG.ipynb

@@ -39,7 +39,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain langchain-chroma \"unstructured[all-docs]\" pydantic lxml langchainhub"
+    "! pip install langchain unstructured[all-docs] pydantic lxml langchainhub"
    ]
   },
   {
@@ -75,7 +75,7 @@
     "\n",
     "Apply to the [`LLaMA2`](https://arxiv.org/pdf/2307.09288.pdf) paper. \n",
     "\n",
-    "We use the Unstructured [`partition_pdf`](https://unstructured-io.github.io/unstructured/core/partition.html#partition-pdf), which segments a PDF document by using a layout model. \n",
+    "We use the Unstructured [`partition_pdf`](https://unstructured-io.github.io/unstructured/bricks/partition.html#partition-pdf), which segments a PDF document by using a layout model. \n",
     "\n",
     "This layout model makes it possible to extract elements, such as tables, from pdfs. \n",
     "\n",
@@ -320,7 +320,7 @@
     "\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryStore\n",
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_core.documents import Document\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",

cookbook/Semi_structured_and_multi_modal_RAG.ipynb

@@ -59,7 +59,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain langchain-chroma \"unstructured[all-docs]\" pydantic lxml"
+    "! pip install langchain unstructured[all-docs] pydantic lxml"
    ]
   },
   {
@@ -375,7 +375,7 @@
     "\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryStore\n",
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_core.documents import Document\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
@@ -562,7 +562,9 @@
    ],
    "source": [
     "# We can retrieve this table\n",
-    "retriever.invoke(\"What are results for LLaMA across across domains / subjects?\")[1]"
+    "retriever.get_relevant_documents(\n",
+    "    \"What are results for LLaMA across across domains / subjects?\"\n",
+    ")[1]"
    ]
   },
   {
@@ -612,7 +614,9 @@
     }
    ],
    "source": [
-    "retriever.invoke(\"Images / figures with playful and creative examples\")[1]"
+    "retriever.get_relevant_documents(\"Images / figures with playful and creative examples\")[\n",
+    "    1\n",
+    "]"
    ]
   },
   {

cookbook/Semi_structured_multi_modal_RAG_LLaMA2.ipynb

@@ -59,7 +59,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain langchain-chroma \"unstructured[all-docs]\" pydantic lxml"
+    "! pip install langchain unstructured[all-docs] pydantic lxml"
    ]
   },
   {
@@ -191,27 +191,27 @@
    "source": [
     "## Multi-vector retriever\n",
     "\n",
-    "Use [multi-vector-retriever](/docs/modules/data_connection/retrievers/multi_vector#summary).\n",
+    "Use [multi-vector-retriever](https://python.langchain.com/docs/modules/data_connection/retrievers/multi_vector#summary).\n",
     "\n",
     "Summaries are used to retrieve raw tables and / or raw chunks of text.\n",
     "\n",
     "### Text and Table summaries\n",
     "\n",
-    "Here, we use Ollama to run LLaMA2 locally. \n",
+    "Here, we use ollama.ai to run LLaMA2 locally. \n",
     "\n",
-    "See details on installation [here](/docs/guides/development/local_llms)."
+    "See details on installation [here](https://python.langchain.com/docs/guides/local_llms)."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "id": "523e6ed2-2132-4748-bdb7-db765f20648d",
    "metadata": {},
    "outputs": [],
    "source": [
+    "from langchain_community.chat_models import ChatOllama\n",
     "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_ollama import ChatOllama"
+    "from langchain_core.prompts import ChatPromptTemplate"
    ]
   },
   {
@@ -378,8 +378,8 @@
     "\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryStore\n",
-    "from langchain_chroma import Chroma\n",
     "from langchain_community.embeddings import GPT4AllEmbeddings\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_core.documents import Document\n",
     "\n",
     "# The vectorstore to use to index the child chunks\n",
@@ -501,7 +501,9 @@
     }
    ],
    "source": [
-    "retriever.invoke(\"Images / figures with playful and creative examples\")[0]"
+    "retriever.get_relevant_documents(\"Images / figures with playful and creative examples\")[\n",
+    "    0\n",
+    "]"
    ]
   },
   {

cookbook/advanced_rag_eval.ipynb

@@ -19,7 +19,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install -U langchain openai langchain_chroma langchain-experimental # (newest versions required for multi-modal)"
+    "! pip install -U langchain openai chromadb langchain-experimental # (newest versions required for multi-modal)"
    ]
   },
   {
@@ -30,7 +30,7 @@
    "outputs": [],
    "source": [
     "# lock to 0.10.19 due to a persistent bug in more recent versions\n",
-    "! pip install \"unstructured[all-docs]==0.10.19\" pillow pydantic lxml matplotlib tiktoken open_clip_torch torch"
+    "! pip install \"unstructured[all-docs]==0.10.19\" pillow pydantic lxml pillow matplotlib tiktoken open_clip_torch torch"
    ]
   },
   {
@@ -132,7 +132,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
     "baseline = Chroma.from_texts(\n",
@@ -342,7 +342,7 @@
     "# Testing on retrieval\n",
     "query = \"What percentage of CPI is dedicated to Housing, and how does it compare to the combined percentage of Medical Care, Apparel, and Other Goods and Services?\"\n",
     "suffix_for_images = \" Include any pie charts, graphs, or tables.\"\n",
-    "docs = retriever_multi_vector_img.invoke(query + suffix_for_images)"
+    "docs = retriever_multi_vector_img.get_relevant_documents(query + suffix_for_images)"
    ]
   },
   {
@@ -409,7 +409,7 @@
     "    table_summaries,\n",
     "    tables,\n",
     "    image_summaries,\n",
-    "    img_base64_list,\n",
+    "    image_summaries,\n",
     ")"
    ]
   },
@@ -532,8 +532,8 @@
     "def is_image_data(b64data):\n",
     "    \"\"\"Check if the base64 data is an image by looking at the start of the data.\"\"\"\n",
     "    image_signatures = {\n",
-    "        b\"\\xff\\xd8\\xff\": \"jpg\",\n",
-    "        b\"\\x89\\x50\\x4e\\x47\\x0d\\x0a\\x1a\\x0a\": \"png\",\n",
+    "        b\"\\xFF\\xD8\\xFF\": \"jpg\",\n",
+    "        b\"\\x89\\x50\\x4E\\x47\\x0D\\x0A\\x1A\\x0A\": \"png\",\n",
     "        b\"\\x47\\x49\\x46\\x38\": \"gif\",\n",
     "        b\"\\x52\\x49\\x46\\x46\": \"webp\",\n",
     "    }\n",

cookbook/agent_vectorstore.ipynb

@@ -22,25 +22,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
-   "id": "e8d63d14-138d-4aa5-a741-7fd3537d00aa",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = \"\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 16,
    "id": "2e87c10a",
    "metadata": {},
    "outputs": [],
    "source": [
     "from langchain.chains import RetrievalQA\n",
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_openai import OpenAI, OpenAIEmbeddings\n",
     "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
@@ -49,7 +37,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 17,
    "id": "0b7b772b",
    "metadata": {},
    "outputs": [],
@@ -66,10 +54,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 18,
    "id": "f2675861",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running Chroma using direct local API.\n",
+      "Using DuckDB in-memory for database. Data will be transient.\n"
+     ]
+    }
+   ],
    "source": [
     "from langchain_community.document_loaders import TextLoader\n",
     "\n",
@@ -84,7 +81,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "id": "bc5403d4",
    "metadata": {},
    "outputs": [],
@@ -96,25 +93,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 5,
    "id": "1431cded",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "USER_AGENT environment variable not set, consider setting it to identify your requests.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "from langchain_community.document_loaders import WebBaseLoader"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 6,
    "id": "915d3ff3",
    "metadata": {},
    "outputs": [],
@@ -124,20 +113,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 7,
    "id": "96a2edf8",
    "metadata": {},
    "outputs": [
     {
-     "name": "stderr",
+     "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Created a chunk of size 2122, which is longer than the specified 1000\n",
-      "Created a chunk of size 3187, which is longer than the specified 1000\n",
-      "Created a chunk of size 1017, which is longer than the specified 1000\n",
-      "Created a chunk of size 1049, which is longer than the specified 1000\n",
-      "Created a chunk of size 1256, which is longer than the specified 1000\n",
-      "Created a chunk of size 2321, which is longer than the specified 1000\n"
+      "Running Chroma using direct local API.\n",
+      "Using DuckDB in-memory for database. Data will be transient.\n"
      ]
     }
    ],
@@ -150,6 +135,14 @@
     ")"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "71ecef90",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
   {
    "cell_type": "markdown",
    "id": "c0a6c031",
@@ -160,30 +153,31 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 43,
    "id": "eb142786",
    "metadata": {},
    "outputs": [],
    "source": [
     "# Import things that are needed generically\n",
-    "from langchain.agents import Tool"
+    "from langchain.agents import AgentType, Tool, initialize_agent\n",
+    "from langchain_openai import OpenAI"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 44,
    "id": "850bc4e9",
    "metadata": {},
    "outputs": [],
    "source": [
     "tools = [\n",
     "    Tool(\n",
-    "        name=\"state_of_union_qa_system\",\n",
+    "        name=\"State of Union QA System\",\n",
     "        func=state_of_union.run,\n",
     "        description=\"useful for when you need to answer questions about the most recent state of the union address. Input should be a fully formed question.\",\n",
     "    ),\n",
     "    Tool(\n",
-    "        name=\"ruff_qa_system\",\n",
+    "        name=\"Ruff QA System\",\n",
     "        func=ruff.run,\n",
     "        description=\"useful for when you need to answer questions about ruff (a python linter). Input should be a fully formed question.\",\n",
     "    ),\n",
@@ -192,116 +186,94 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
-   "id": "70c461d8-aaca-4f2a-9a93-bf35841cc615",
+   "execution_count": 45,
+   "id": "fc47f230",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langgraph.prebuilt import create_react_agent\n",
-    "\n",
-    "agent = create_react_agent(\"openai:gpt-4.1-mini\", tools)"
+    "# Construct the agent. We will use the default agent type here.\n",
+    "# See documentation for a full list of options.\n",
+    "agent = initialize_agent(\n",
+    "    tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
+    ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
-   "id": "a6d2b911-3044-4430-a35b-75832bb45334",
+   "execution_count": 46,
+   "id": "10ca2db8",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "================================\u001b[1m Human Message \u001b[0m=================================\n",
       "\n",
-      "What did biden say about ketanji brown jackson in the state of the union address?\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "Tool Calls:\n",
-      "  state_of_union_qa_system (call_26QlRdsptjEJJZjFsAUjEbaH)\n",
-      " Call ID: call_26QlRdsptjEJJZjFsAUjEbaH\n",
-      "  Args:\n",
-      "    __arg1: What did Biden say about Ketanji Brown Jackson in the state of the union address?\n",
-      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
-      "Name: state_of_union_qa_system\n",
       "\n",
-      " Biden said that he nominated Ketanji Brown Jackson for the United States Supreme Court and praised her as one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence.\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m I need to find out what Biden said about Ketanji Brown Jackson in the State of the Union address.\n",
+      "Action: State of Union QA System\n",
+      "Action Input: What did Biden say about Ketanji Brown Jackson in the State of the Union address?\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3m Biden said that Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: Biden said that Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
       "\n",
-      "In the State of the Union address, Biden said that he nominated Ketanji Brown Jackson for the United States Supreme Court and praised her as one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence.\n"
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\"Biden said that Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\""
+      ]
+     },
+     "execution_count": 46,
+     "metadata": {},
+     "output_type": "execute_result"
     }
    ],
    "source": [
-    "input_message = {\n",
-    "    \"role\": \"user\",\n",
-    "    \"content\": \"What did biden say about ketanji brown jackson in the state of the union address?\",\n",
-    "}\n",
-    "\n",
-    "for step in agent.stream(\n",
-    "    {\"messages\": [input_message]},\n",
-    "    stream_mode=\"values\",\n",
-    "):\n",
-    "    step[\"messages\"][-1].pretty_print()"
+    "agent.run(\n",
+    "    \"What did biden say about ketanji brown jackson in the state of the union address?\"\n",
+    ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
-   "id": "e836b4cd-abf7-49eb-be0e-b9ad501213f3",
+   "execution_count": 47,
+   "id": "4e91b811",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "================================\u001b[1m Human Message \u001b[0m=================================\n",
-      "\n",
-      "Why use ruff over flake8?\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "Tool Calls:\n",
-      "  ruff_qa_system (call_KqDoWeO9bo9OAXdxOsCb6msC)\n",
-      " Call ID: call_KqDoWeO9bo9OAXdxOsCb6msC\n",
-      "  Args:\n",
-      "    __arg1: Why use ruff over flake8?\n",
-      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
-      "Name: ruff_qa_system\n",
       "\n",
       "\n",
-      "There are a few reasons why someone might choose to use Ruff over Flake8:\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m I need to find out the advantages of using ruff over flake8\n",
+      "Action: Ruff QA System\n",
+      "Action Input: What are the advantages of using ruff over flake8?\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3m Ruff can be used as a drop-in replacement for Flake8 when used (1) without or with a small number of plugins, (2) alongside Black, and (3) on Python 3 code. It also re-implements some of the most popular Flake8 plugins and related code quality tools natively, including isort, yesqa, eradicate, and most of the rules implemented in pyupgrade. Ruff also supports automatically fixing its own lint violations, which Flake8 does not.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: Ruff can be used as a drop-in replacement for Flake8 when used (1) without or with a small number of plugins, (2) alongside Black, and (3) on Python 3 code. It also re-implements some of the most popular Flake8 plugins and related code quality tools natively, including isort, yesqa, eradicate, and most of the rules implemented in pyupgrade. Ruff also supports automatically fixing its own lint violations, which Flake8 does not.\u001b[0m\n",
       "\n",
-      "1. Larger rule set: Ruff implements over 800 rules, while Flake8 only implements around 200. This means that Ruff can catch more potential issues in your code.\n",
-      "\n",
-      "2. Better compatibility with other tools: Ruff is designed to work well with other tools like Black, isort, and type checkers like Mypy. This means that you can use Ruff alongside these tools to get more comprehensive feedback on your code.\n",
-      "\n",
-      "3. Automatic fixing of lint violations: Unlike Flake8, Ruff is capable of automatically fixing its own lint violations. This can save you time and effort when fixing issues in your code.\n",
-      "\n",
-      "4. Native implementation of popular Flake8 plugins: Ruff re-implements some of the most popular Flake8 plugins natively, which means you don't have to install and configure multiple plugins to get the same functionality.\n",
-      "\n",
-      "Overall, Ruff offers a more comprehensive and user-friendly experience compared to Flake8, making it a popular choice for many developers.\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "\n",
-      "You might choose to use Ruff over Flake8 for several reasons:\n",
-      "\n",
-      "1. Ruff has a much larger rule set, implementing over 800 rules compared to Flake8's roughly 200, so it can catch more potential issues.\n",
-      "2. Ruff is designed to work better with other tools like Black, isort, and type checkers like Mypy, providing more comprehensive code feedback.\n",
-      "3. Ruff can automatically fix its own lint violations, which Flake8 cannot, saving time and effort.\n",
-      "4. Ruff natively implements some popular Flake8 plugins, so you don't need to install and configure multiple plugins separately.\n",
-      "\n",
-      "Overall, Ruff offers a more comprehensive and user-friendly experience compared to Flake8.\n"
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'Ruff can be used as a drop-in replacement for Flake8 when used (1) without or with a small number of plugins, (2) alongside Black, and (3) on Python 3 code. It also re-implements some of the most popular Flake8 plugins and related code quality tools natively, including isort, yesqa, eradicate, and most of the rules implemented in pyupgrade. Ruff also supports automatically fixing its own lint violations, which Flake8 does not.'"
+      ]
+     },
+     "execution_count": 47,
+     "metadata": {},
+     "output_type": "execute_result"
     }
    ],
    "source": [
-    "input_message = {\n",
-    "    \"role\": \"user\",\n",
-    "    \"content\": \"Why use ruff over flake8?\",\n",
-    "}\n",
-    "\n",
-    "for step in agent.stream(\n",
-    "    {\"messages\": [input_message]},\n",
-    "    stream_mode=\"values\",\n",
-    "):\n",
-    "    step[\"messages\"][-1].pretty_print()"
+    "agent.run(\"Why use ruff over flake8?\")"
    ]
   },
   {
@@ -324,20 +296,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 48,
    "id": "f59b377e",
    "metadata": {},
    "outputs": [],
    "source": [
     "tools = [\n",
     "    Tool(\n",
-    "        name=\"state_of_union_qa_system\",\n",
+    "        name=\"State of Union QA System\",\n",
     "        func=state_of_union.run,\n",
     "        description=\"useful for when you need to answer questions about the most recent state of the union address. Input should be a fully formed question.\",\n",
     "        return_direct=True,\n",
     "    ),\n",
     "    Tool(\n",
-    "        name=\"ruff_qa_system\",\n",
+    "        name=\"Ruff QA System\",\n",
     "        func=ruff.run,\n",
     "        description=\"useful for when you need to answer questions about ruff (a python linter). Input should be a fully formed question.\",\n",
     "        return_direct=True,\n",
@@ -347,92 +319,90 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
-   "id": "06f69c0f-c83d-4b7f-a1c8-7614aced3bae",
+   "execution_count": 49,
+   "id": "8615707a",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langgraph.prebuilt import create_react_agent\n",
-    "\n",
-    "agent = create_react_agent(\"openai:gpt-4.1-mini\", tools)"
+    "agent = initialize_agent(\n",
+    "    tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
+    ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
-   "id": "a6b38c12-ac25-43c0-b9c2-2b1985ab4825",
+   "execution_count": 50,
+   "id": "36e718a9",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "================================\u001b[1m Human Message \u001b[0m=================================\n",
       "\n",
-      "What did biden say about ketanji brown jackson in the state of the union address?\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "Tool Calls:\n",
-      "  state_of_union_qa_system (call_yjxh11OnZiauoyTAn9npWdxj)\n",
-      " Call ID: call_yjxh11OnZiauoyTAn9npWdxj\n",
-      "  Args:\n",
-      "    __arg1: What did Biden say about Ketanji Brown Jackson in the state of the union address?\n",
-      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
-      "Name: state_of_union_qa_system\n",
       "\n",
-      " Biden said that he nominated Ketanji Brown Jackson for the United States Supreme Court and praised her as one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence.\n"
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m I need to find out what Biden said about Ketanji Brown Jackson in the State of the Union address.\n",
+      "Action: State of Union QA System\n",
+      "Action Input: What did Biden say about Ketanji Brown Jackson in the State of the Union address?\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3m Biden said that Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\" Biden said that Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\""
+      ]
+     },
+     "execution_count": 50,
+     "metadata": {},
+     "output_type": "execute_result"
     }
    ],
    "source": [
-    "input_message = {\n",
-    "    \"role\": \"user\",\n",
-    "    \"content\": \"What did biden say about ketanji brown jackson in the state of the union address?\",\n",
-    "}\n",
-    "\n",
-    "for step in agent.stream(\n",
-    "    {\"messages\": [input_message]},\n",
-    "    stream_mode=\"values\",\n",
-    "):\n",
-    "    step[\"messages\"][-1].pretty_print()"
+    "agent.run(\n",
+    "    \"What did biden say about ketanji brown jackson in the state of the union address?\"\n",
+    ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
-   "id": "88f08d86-7972-4148-8128-3ac8898ad68a",
+   "execution_count": 51,
+   "id": "edfd0a1a",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "================================\u001b[1m Human Message \u001b[0m=================================\n",
       "\n",
-      "Why use ruff over flake8?\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "Tool Calls:\n",
-      "  ruff_qa_system (call_GiWWfwF6wbbRFQrHlHbhRtGW)\n",
-      " Call ID: call_GiWWfwF6wbbRFQrHlHbhRtGW\n",
-      "  Args:\n",
-      "    __arg1: What are the advantages of using ruff over flake8 for Python linting?\n",
-      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
-      "Name: ruff_qa_system\n",
       "\n",
-      " Ruff has a larger rule set, supports automatic fixing of lint violations, and does not require the installation of additional plugins. It also has better compatibility with Black and can be used alongside a type checker for more comprehensive code analysis.\n"
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m I need to find out the advantages of using ruff over flake8\n",
+      "Action: Ruff QA System\n",
+      "Action Input: What are the advantages of using ruff over flake8?\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3m Ruff can be used as a drop-in replacement for Flake8 when used (1) without or with a small number of plugins, (2) alongside Black, and (3) on Python 3 code. It also re-implements some of the most popular Flake8 plugins and related code quality tools natively, including isort, yesqa, eradicate, and most of the rules implemented in pyupgrade. Ruff also supports automatically fixing its own lint violations, which Flake8 does not.\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "' Ruff can be used as a drop-in replacement for Flake8 when used (1) without or with a small number of plugins, (2) alongside Black, and (3) on Python 3 code. It also re-implements some of the most popular Flake8 plugins and related code quality tools natively, including isort, yesqa, eradicate, and most of the rules implemented in pyupgrade. Ruff also supports automatically fixing its own lint violations, which Flake8 does not.'"
+      ]
+     },
+     "execution_count": 51,
+     "metadata": {},
+     "output_type": "execute_result"
     }
    ],
    "source": [
-    "input_message = {\n",
-    "    \"role\": \"user\",\n",
-    "    \"content\": \"Why use ruff over flake8?\",\n",
-    "}\n",
-    "\n",
-    "for step in agent.stream(\n",
-    "    {\"messages\": [input_message]},\n",
-    "    stream_mode=\"values\",\n",
-    "):\n",
-    "    step[\"messages\"][-1].pretty_print()"
+    "agent.run(\"Why use ruff over flake8?\")"
    ]
   },
   {
@@ -447,19 +417,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 57,
    "id": "d397a233",
    "metadata": {},
    "outputs": [],
    "source": [
     "tools = [\n",
     "    Tool(\n",
-    "        name=\"state_of_union_qa_system\",\n",
+    "        name=\"State of Union QA System\",\n",
     "        func=state_of_union.run,\n",
     "        description=\"useful for when you need to answer questions about the most recent state of the union address. Input should be a fully formed question, not referencing any obscure pronouns from the conversation before.\",\n",
     "    ),\n",
     "    Tool(\n",
-    "        name=\"ruff_qa_system\",\n",
+    "        name=\"Ruff QA System\",\n",
     "        func=ruff.run,\n",
     "        description=\"useful for when you need to answer questions about ruff (a python linter). Input should be a fully formed question, not referencing any obscure pronouns from the conversation before.\",\n",
     "    ),\n",
@@ -468,60 +438,60 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
-   "id": "41743f29-150d-40ba-aa8e-3a63c32216aa",
+   "execution_count": 58,
+   "id": "06157240",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langgraph.prebuilt import create_react_agent\n",
-    "\n",
-    "agent = create_react_agent(\"openai:gpt-4.1-mini\", tools)"
+    "# Construct the agent. We will use the default agent type here.\n",
+    "# See documentation for a full list of options.\n",
+    "agent = initialize_agent(\n",
+    "    tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
+    ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
-   "id": "e20e81dd-284a-4d07-9160-63a84b65cba8",
+   "execution_count": 59,
+   "id": "b492b520",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "================================\u001b[1m Human Message \u001b[0m=================================\n",
       "\n",
-      "What tool does ruff use to run over Jupyter Notebooks? Did the president mention that tool in the state of the union?\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "Tool Calls:\n",
-      "  ruff_qa_system (call_VOnxiOEehauQyVOTjDJkR5L2)\n",
-      " Call ID: call_VOnxiOEehauQyVOTjDJkR5L2\n",
-      "  Args:\n",
-      "    __arg1: What tool does ruff use to run over Jupyter Notebooks?\n",
-      "  state_of_union_qa_system (call_AbSsXAxwe4JtCRhga926SxOZ)\n",
-      " Call ID: call_AbSsXAxwe4JtCRhga926SxOZ\n",
-      "  Args:\n",
-      "    __arg1: Did the president mention the tool that ruff uses to run over Jupyter Notebooks in the state of the union?\n",
-      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
-      "Name: state_of_union_qa_system\n",
       "\n",
-      " No, the president did not mention the tool that ruff uses to run over Jupyter Notebooks in the state of the union.\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m I need to find out what tool ruff uses to run over Jupyter Notebooks, and if the president mentioned it in the state of the union.\n",
+      "Action: Ruff QA System\n",
+      "Action Input: What tool does ruff use to run over Jupyter Notebooks?\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3m Ruff is integrated into nbQA, a tool for running linters and code formatters over Jupyter Notebooks. After installing ruff and nbqa, you can run Ruff over a notebook like so: > nbqa ruff Untitled.html\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now need to find out if the president mentioned this tool in the state of the union.\n",
+      "Action: State of Union QA System\n",
+      "Action Input: Did the president mention nbQA in the state of the union?\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3m No, the president did not mention nbQA in the state of the union.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
+      "Final Answer: No, the president did not mention nbQA in the state of the union.\u001b[0m\n",
       "\n",
-      "Ruff does not support source.organizeImports and source.fixAll code actions in Jupyter Notebooks. Additionally, the president did not mention the tool that ruff uses to run over Jupyter Notebooks in the state of the union.\n"
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'No, the president did not mention nbQA in the state of the union.'"
+      ]
+     },
+     "execution_count": 59,
+     "metadata": {},
+     "output_type": "execute_result"
     }
    ],
    "source": [
-    "input_message = {\n",
-    "    \"role\": \"user\",\n",
-    "    \"content\": \"What tool does ruff use to run over Jupyter Notebooks? Did the president mention that tool in the state of the union?\",\n",
-    "}\n",
-    "\n",
-    "for step in agent.stream(\n",
-    "    {\"messages\": [input_message]},\n",
-    "    stream_mode=\"values\",\n",
-    "):\n",
-    "    step[\"messages\"][-1].pretty_print()"
+    "agent.run(\n",
+    "    \"What tool does ruff use to run over Jupyter Notebooks? Did the president mention that tool in the state of the union?\"\n",
+    ")"
    ]
   },
   {
@@ -549,7 +519,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.4"
+   "version": "3.10.1"
   }
  },
  "nbformat": 4,

cookbook/airbyte_github.ipynb

@@ -14,7 +14,7 @@
     }
    ],
    "source": [
-    "%pip install -qU langchain-airbyte langchain_chroma"
+    "%pip install -qU langchain-airbyte"
    ]
   },
   {
@@ -123,7 +123,7 @@
    "outputs": [],
    "source": [
     "import tiktoken\n",
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
     "enc = tiktoken.get_encoding(\"cl100k_base\")\n",

cookbook/autogpt/marathon_times.ipynb

@@ -40,13 +40,11 @@
     "import nest_asyncio\n",
     "import pandas as pd\n",
     "from langchain.docstore.document import Document\n",
-    "from langchain_experimental.agents.agent_toolkits.pandas.base import (\n",
-    "    create_pandas_dataframe_agent,\n",
-    ")\n",
+    "from langchain_community.agent_toolkits.pandas.base import create_pandas_dataframe_agent\n",
     "from langchain_experimental.autonomous_agents import AutoGPT\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "# Needed since jupyter runs an async eventloop\n",
+    "# Needed synce jupyter runs an async eventloop\n",
     "nest_asyncio.apply()"
    ]
   },
@@ -59,7 +57,7 @@
    },
    "outputs": [],
    "source": [
-    "llm = ChatOpenAI(model=\"gpt-4\", temperature=1.0)"
+    "llm = ChatOpenAI(model_name=\"gpt-4\", temperature=1.0)"
    ]
   },
   {

cookbook/camel_role_playing.ipynb

@@ -90,7 +90,7 @@
     "    ) -> AIMessage:\n",
     "        messages = self.update_messages(input_message)\n",
     "\n",
-    "        output_message = self.model.invoke(messages)\n",
+    "        output_message = self.model(messages)\n",
     "        self.update_messages(output_message)\n",
     "\n",
     "        return output_message"

cookbook/code-analysis-deeplake.ipynb

@@ -66,7 +66,7 @@
    },
    "outputs": [],
    "source": [
-    "#!python3 -m pip install --upgrade langchain langchain-deeplake openai"
+    "#!python3 -m pip install --upgrade langchain deeplake openai"
    ]
   },
   {
@@ -90,8 +90,7 @@
     "import os\n",
     "from getpass import getpass\n",
     "\n",
-    "if \"OPENAI_API_KEY\" not in os.environ:\n",
-    "    os.environ[\"OPENAI_API_KEY\"] = getpass()\n",
+    "os.environ[\"OPENAI_API_KEY\"] = getpass()\n",
     "# Please manually enter OpenAI Key"
    ]
   },
@@ -666,26 +665,89 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 15,
    "metadata": {
     "tags": []
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Your Deep Lake dataset has been successfully created!\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " \r"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Dataset(path='hub://adilkhan/langchain-code', tensors=['embedding', 'id', 'metadata', 'text'])\n",
+      "\n",
+      "  tensor      htype       shape       dtype  compression\n",
+      "  -------    -------     -------     -------  ------- \n",
+      " embedding  embedding  (8244, 1536)  float32   None   \n",
+      "    id        text      (8244, 1)      str     None   \n",
+      " metadata     json      (8244, 1)      str     None   \n",
+      "   text       text      (8244, 1)      str     None   \n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": []
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<langchain_community.vectorstores.deeplake.DeepLake at 0x7fe1b67d7a30>"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
-    "from langchain_deeplake.vectorstores import DeeplakeVectorStore\n",
+    "from langchain_community.vectorstores import DeepLake\n",
     "\n",
     "username = \"<USERNAME_OR_ORG>\"\n",
     "\n",
     "\n",
-    "db = DeeplakeVectorStore.from_documents(\n",
-    "    documents=texts,\n",
-    "    embedding=embeddings,\n",
-    "    dataset_path=f\"hub://{username}/langchain-code\",\n",
-    "    overwrite=True,\n",
+    "db = DeepLake.from_documents(\n",
+    "    texts, embeddings, dataset_path=f\"hub://{username}/langchain-code\", overwrite=True\n",
     ")\n",
     "db"
    ]
   },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "`Optional`: You can also use Deep Lake's Managed Tensor Database as a hosting service and run queries there. In order to do so, it is necessary to specify the runtime parameter as {'tensor_db': True} during the creation of the vector store. This configuration enables the execution of queries on the Managed Tensor Database, rather than on the client side. It should be noted that this functionality is not applicable to datasets stored locally or in-memory. In the event that a vector store has already been created outside of the Managed Tensor Database, it is possible to transfer it to the Managed Tensor Database by following the prescribed steps."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# from langchain_community.vectorstores import DeepLake\n",
+    "\n",
+    "# db = DeepLake.from_documents(\n",
+    "#     texts, embeddings, dataset_path=f\"hub://{<org_id>}/langchain-code\", runtime={\"tensor_db\": True}\n",
+    "# )\n",
+    "# db"
+   ]
+  },
   {
    "attachments": {},
    "cell_type": "markdown",
@@ -697,16 +759,24 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 17,
    "metadata": {
     "tags": []
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Deep Lake Dataset in hub://adilkhan/langchain-code already exists, loading from the storage\n"
+     ]
+    }
+   ],
    "source": [
-    "db = DeeplakeVectorStore(\n",
+    "db = DeepLake(\n",
     "    dataset_path=f\"hub://{username}/langchain-code\",\n",
     "    read_only=True,\n",
-    "    embedding_function=embeddings,\n",
+    "    embedding=embeddings,\n",
     ")"
    ]
   },
@@ -725,6 +795,36 @@
     "retriever.search_kwargs[\"k\"] = 20"
    ]
   },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "You can also specify user defined functions using [Deep Lake filters](https://docs.deeplake.ai/en/latest/deeplake.core.dataset.html#deeplake.core.dataset.Dataset.filter)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "def filter(x):\n",
+    "    # filter based on source code\n",
+    "    if \"something\" in x[\"text\"].data()[\"value\"]:\n",
+    "        return False\n",
+    "\n",
+    "    # filter based on path e.g. extension\n",
+    "    metadata = x[\"metadata\"].data()[\"value\"]\n",
+    "    return \"only_this\" in metadata[\"source\"] or \"also_that\" in metadata[\"source\"]\n",
+    "\n",
+    "\n",
+    "### turn on below for custom filtering\n",
+    "# retriever.search_kwargs['filter'] = filter"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 20,
@@ -736,8 +836,10 @@
     "from langchain.chains import ConversationalRetrievalChain\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "model = ChatOpenAI(model=\"gpt-3.5-turbo-0613\")  # 'ada' 'gpt-3.5-turbo-0613' 'gpt-4',\n",
-    "qa = RetrievalQA.from_llm(model, retriever=retriever)"
+    "model = ChatOpenAI(\n",
+    "    model_name=\"gpt-3.5-turbo-0613\"\n",
+    ")  # 'ada' 'gpt-3.5-turbo-0613' 'gpt-4',\n",
+    "qa = ConversationalRetrievalChain.from_llm(model, retriever=retriever)"
    ]
   },
   {
@@ -831,7 +933,7 @@
       "**Answer**: The LangChain class includes various types of retrievers such as:\n",
       "\n",
       "- ArxivRetriever\n",
-      "- AzureAISearchRetriever\n",
+      "- AzureCognitiveSearchRetriever\n",
       "- BM25Retriever\n",
       "- ChaindeskRetriever\n",
       "- ChatGPTPluginRetriever\n",
@@ -891,7 +993,7 @@
     {
      "data": {
       "text/plain": [
-       "{'question': 'LangChain possesses a variety of retrievers including:\\n\\n1. ArxivRetriever\\n2. AzureAISearchRetriever\\n3. BM25Retriever\\n4. ChaindeskRetriever\\n5. ChatGPTPluginRetriever\\n6. ContextualCompressionRetriever\\n7. DocArrayRetriever\\n8. ElasticSearchBM25Retriever\\n9. EnsembleRetriever\\n10. GoogleVertexAISearchRetriever\\n11. AmazonKendraRetriever\\n12. KNNRetriever\\n13. LlamaIndexGraphRetriever\\n14. LlamaIndexRetriever\\n15. MergerRetriever\\n16. MetalRetriever\\n17. MilvusRetriever\\n18. MultiQueryRetriever\\n19. ParentDocumentRetriever\\n20. PineconeHybridSearchRetriever\\n21. PubMedRetriever\\n22. RePhraseQueryRetriever\\n23. RemoteLangChainRetriever\\n24. SelfQueryRetriever\\n25. SVMRetriever\\n26. TFIDFRetriever\\n27. TimeWeightedVectorStoreRetriever\\n28. VespaRetriever\\n29. WeaviateHybridSearchRetriever\\n30. WebResearchRetriever\\n31. WikipediaRetriever\\n32. ZepRetriever\\n33. ZillizRetriever\\n\\nIt also includes self query translators like:\\n\\n1. ChromaTranslator\\n2. DeepLakeTranslator\\n3. MyScaleTranslator\\n4. PineconeTranslator\\n5. QdrantTranslator\\n6. WeaviateTranslator\\n\\nAnd remote retrievers like:\\n\\n1. RemoteLangChainRetriever'}"
+       "{'question': 'LangChain possesses a variety of retrievers including:\\n\\n1. ArxivRetriever\\n2. AzureCognitiveSearchRetriever\\n3. BM25Retriever\\n4. ChaindeskRetriever\\n5. ChatGPTPluginRetriever\\n6. ContextualCompressionRetriever\\n7. DocArrayRetriever\\n8. ElasticSearchBM25Retriever\\n9. EnsembleRetriever\\n10. GoogleVertexAISearchRetriever\\n11. AmazonKendraRetriever\\n12. KNNRetriever\\n13. LlamaIndexGraphRetriever\\n14. LlamaIndexRetriever\\n15. MergerRetriever\\n16. MetalRetriever\\n17. MilvusRetriever\\n18. MultiQueryRetriever\\n19. ParentDocumentRetriever\\n20. PineconeHybridSearchRetriever\\n21. PubMedRetriever\\n22. RePhraseQueryRetriever\\n23. RemoteLangChainRetriever\\n24. SelfQueryRetriever\\n25. SVMRetriever\\n26. TFIDFRetriever\\n27. TimeWeightedVectorStoreRetriever\\n28. VespaRetriever\\n29. WeaviateHybridSearchRetriever\\n30. WebResearchRetriever\\n31. WikipediaRetriever\\n32. ZepRetriever\\n33. ZillizRetriever\\n\\nIt also includes self query translators like:\\n\\n1. ChromaTranslator\\n2. DeepLakeTranslator\\n3. MyScaleTranslator\\n4. PineconeTranslator\\n5. QdrantTranslator\\n6. WeaviateTranslator\\n\\nAnd remote retrievers like:\\n\\n1. RemoteLangChainRetriever'}"
       ]
      },
      "execution_count": 31,
@@ -1015,7 +1117,7 @@
       "The LangChain class includes various types of retrievers such as:\n",
       "\n",
       "- ArxivRetriever\n",
-      "- AzureAISearchRetriever\n",
+      "- AzureCognitiveSearchRetriever\n",
       "- BM25Retriever\n",
       "- ChaindeskRetriever\n",
       "- ChatGPTPluginRetriever\n",

cookbook/cql_agent.ipynb

@@ -1,557 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Setup Environment"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Python Modules"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Install the following Python modules:\n",
-    "\n",
-    "```bash\n",
-    "pip install ipykernel python-dotenv cassio pandas langchain_openai langchain langchain-community langchainhub langchain_experimental openai-multi-tool-use-parallel-patch\n",
-    "```"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Load the `.env` File"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Connection is via `cassio` using `auto=True` parameter, and the notebook uses OpenAI. You should create a `.env` file accordingly.\n",
-    "\n",
-    "For Cassandra, set:\n",
-    "```bash\n",
-    "CASSANDRA_CONTACT_POINTS\n",
-    "CASSANDRA_USERNAME\n",
-    "CASSANDRA_PASSWORD\n",
-    "CASSANDRA_KEYSPACE\n",
-    "```\n",
-    "\n",
-    "For Astra, set:\n",
-    "```bash\n",
-    "ASTRA_DB_APPLICATION_TOKEN\n",
-    "ASTRA_DB_DATABASE_ID\n",
-    "ASTRA_DB_KEYSPACE\n",
-    "```\n",
-    "\n",
-    "For example:\n",
-    "\n",
-    "```bash\n",
-    "# Connection to Astra:\n",
-    "ASTRA_DB_DATABASE_ID=a1b2c3d4-...\n",
-    "ASTRA_DB_APPLICATION_TOKEN=AstraCS:...\n",
-    "ASTRA_DB_KEYSPACE=notebooks\n",
-    "\n",
-    "# Also set \n",
-    "OPENAI_API_KEY=sk-....\n",
-    "```\n",
-    "\n",
-    "(You may also modify the below code to directly connect with `cassio`.)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from dotenv import load_dotenv\n",
-    "\n",
-    "load_dotenv(override=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Connect to Cassandra"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "\n",
-    "import cassio\n",
-    "\n",
-    "cassio.init(auto=True)\n",
-    "session = cassio.config.resolve_session()\n",
-    "if not session:\n",
-    "    raise Exception(\n",
-    "        \"Check environment configuration or manually configure cassio connection parameters\"\n",
-    "    )\n",
-    "\n",
-    "keyspace = os.environ.get(\n",
-    "    \"ASTRA_DB_KEYSPACE\", os.environ.get(\"CASSANDRA_KEYSPACE\", None)\n",
-    ")\n",
-    "if not keyspace:\n",
-    "    raise ValueError(\"a KEYSPACE environment variable must be set\")\n",
-    "\n",
-    "session.set_keyspace(keyspace)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Setup Database"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "This needs to be done one time only!"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Download Data"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The dataset used is from Kaggle, the [Environmental Sensor Telemetry Data](https://www.kaggle.com/datasets/garystafford/environmental-sensor-data-132k?select=iot_telemetry_data.csv). The next cell will download and unzip the data into a Pandas dataframe. The following cell is instructions to download manually. \n",
-    "\n",
-    "The net result of this section is you should have a Pandas dataframe variable `df`."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Download Automatically"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from io import BytesIO\n",
-    "from zipfile import ZipFile\n",
-    "\n",
-    "import pandas as pd\n",
-    "import requests\n",
-    "\n",
-    "datasetURL = \"https://storage.googleapis.com/kaggle-data-sets/788816/1355729/bundle/archive.zip?X-Goog-Algorithm=GOOG4-RSA-SHA256&X-Goog-Credential=gcp-kaggle-com%40kaggle-161607.iam.gserviceaccount.com%2F20240404%2Fauto%2Fstorage%2Fgoog4_request&X-Goog-Date=20240404T115828Z&X-Goog-Expires=259200&X-Goog-SignedHeaders=host&X-Goog-Signature=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\"\n",
-    "\n",
-    "response = requests.get(datasetURL)\n",
-    "if response.status_code == 200:\n",
-    "    zip_file = ZipFile(BytesIO(response.content))\n",
-    "    csv_file_name = zip_file.namelist()[0]\n",
-    "else:\n",
-    "    print(\"Failed to download the file\")\n",
-    "\n",
-    "with zip_file.open(csv_file_name) as csv_file:\n",
-    "    df = pd.read_csv(csv_file)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Download Manually"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "You can download the `.zip` file and unpack the `.csv` contained within. Comment in the next line, and adjust the path to this `.csv` file appropriately."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# df = pd.read_csv(\"/path/to/iot_telemetry_data.csv\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Load Data into Cassandra"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "This section assumes the existence of a dataframe `df`, the following cell validates its structure. The Download section above creates this object."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "assert df is not None, \"Dataframe 'df' must be set\"\n",
-    "expected_columns = [\n",
-    "    \"ts\",\n",
-    "    \"device\",\n",
-    "    \"co\",\n",
-    "    \"humidity\",\n",
-    "    \"light\",\n",
-    "    \"lpg\",\n",
-    "    \"motion\",\n",
-    "    \"smoke\",\n",
-    "    \"temp\",\n",
-    "]\n",
-    "assert all([column in df.columns for column in expected_columns]), (\n",
-    "    \"DataFrame does not have the expected columns\"\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Create and load tables:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from datetime import UTC, datetime\n",
-    "\n",
-    "from cassandra.query import BatchStatement\n",
-    "\n",
-    "# Create sensors table\n",
-    "table_query = \"\"\"\n",
-    "CREATE TABLE IF NOT EXISTS iot_sensors (\n",
-    "    device text,\n",
-    "    conditions text,\n",
-    "    room text,\n",
-    "    PRIMARY KEY (device)\n",
-    ")\n",
-    "WITH COMMENT = 'Environmental IoT room sensor metadata.';\n",
-    "\"\"\"\n",
-    "session.execute(table_query)\n",
-    "\n",
-    "pstmt = session.prepare(\n",
-    "    \"\"\"\n",
-    "INSERT INTO iot_sensors (device, conditions, room)\n",
-    "VALUES (?, ?, ?)\n",
-    "\"\"\"\n",
-    ")\n",
-    "\n",
-    "devices = [\n",
-    "    (\"00:0f:00:70:91:0a\", \"stable conditions, cooler and more humid\", \"room 1\"),\n",
-    "    (\"1c:bf:ce:15:ec:4d\", \"highly variable temperature and humidity\", \"room 2\"),\n",
-    "    (\"b8:27:eb:bf:9d:51\", \"stable conditions, warmer and dryer\", \"room 3\"),\n",
-    "]\n",
-    "\n",
-    "for device, conditions, room in devices:\n",
-    "    session.execute(pstmt, (device, conditions, room))\n",
-    "\n",
-    "print(\"Sensors inserted successfully.\")\n",
-    "\n",
-    "# Create data table\n",
-    "table_query = \"\"\"\n",
-    "CREATE TABLE IF NOT EXISTS iot_data (\n",
-    "    day text,\n",
-    "    device text,\n",
-    "    ts timestamp,\n",
-    "    co double,\n",
-    "    humidity double,\n",
-    "    light boolean,\n",
-    "    lpg double,\n",
-    "    motion boolean,\n",
-    "    smoke double,\n",
-    "    temp double,\n",
-    "    PRIMARY KEY ((day, device), ts)\n",
-    ")\n",
-    "WITH COMMENT = 'Data from environmental IoT room sensors. Columns include device identifier, timestamp (ts) of the data collection, carbon monoxide level (co), relative humidity, light presence, LPG concentration, motion detection, smoke concentration, and temperature (temp). Data is partitioned by day and device.';\n",
-    "\"\"\"\n",
-    "session.execute(table_query)\n",
-    "\n",
-    "pstmt = session.prepare(\n",
-    "    \"\"\"\n",
-    "INSERT INTO iot_data (day, device, ts, co, humidity, light, lpg, motion, smoke, temp)\n",
-    "VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)\n",
-    "\"\"\"\n",
-    ")\n",
-    "\n",
-    "\n",
-    "def insert_data_batch(name, group):\n",
-    "    batch = BatchStatement()\n",
-    "    day, device = name\n",
-    "    print(f\"Inserting batch for day: {day}, device: {device}\")\n",
-    "\n",
-    "    for _, row in group.iterrows():\n",
-    "        timestamp = datetime.fromtimestamp(row[\"ts\"], UTC)\n",
-    "        batch.add(\n",
-    "            pstmt,\n",
-    "            (\n",
-    "                day,\n",
-    "                row[\"device\"],\n",
-    "                timestamp,\n",
-    "                row[\"co\"],\n",
-    "                row[\"humidity\"],\n",
-    "                row[\"light\"],\n",
-    "                row[\"lpg\"],\n",
-    "                row[\"motion\"],\n",
-    "                row[\"smoke\"],\n",
-    "                row[\"temp\"],\n",
-    "            ),\n",
-    "        )\n",
-    "\n",
-    "    session.execute(batch)\n",
-    "\n",
-    "\n",
-    "# Convert columns to appropriate types\n",
-    "df[\"light\"] = df[\"light\"] == \"true\"\n",
-    "df[\"motion\"] = df[\"motion\"] == \"true\"\n",
-    "df[\"ts\"] = df[\"ts\"].astype(float)\n",
-    "df[\"day\"] = df[\"ts\"].apply(\n",
-    "    lambda x: datetime.fromtimestamp(x, UTC).strftime(\"%Y-%m-%d\")\n",
-    ")\n",
-    "\n",
-    "grouped_df = df.groupby([\"day\", \"device\"])\n",
-    "\n",
-    "for name, group in grouped_df:\n",
-    "    insert_data_batch(name, group)\n",
-    "\n",
-    "print(\"Data load complete\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "print(session.keyspace)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Load the Tools"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Python `import` statements for the demo:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.agents import AgentExecutor, create_openai_tools_agent\n",
-    "from langchain_community.agent_toolkits.cassandra_database.toolkit import (\n",
-    "    CassandraDatabaseToolkit,\n",
-    ")\n",
-    "from langchain_community.tools.cassandra_database.prompt import QUERY_PATH_PROMPT\n",
-    "from langchain_community.tools.cassandra_database.tool import (\n",
-    "    GetSchemaCassandraDatabaseTool,\n",
-    "    GetTableDataCassandraDatabaseTool,\n",
-    "    QueryCassandraDatabaseTool,\n",
-    ")\n",
-    "from langchain_community.utilities.cassandra_database import CassandraDatabase\n",
-    "from langchain_openai import ChatOpenAI"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The `CassandraDatabase` object is loaded from `cassio`, though it does accept a `Session`-type parameter as an alternative."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Create a CassandraDatabase instance\n",
-    "db = CassandraDatabase(include_tables=[\"iot_sensors\", \"iot_data\"])\n",
-    "\n",
-    "# Create the Cassandra Database tools\n",
-    "query_tool = QueryCassandraDatabaseTool(db=db)\n",
-    "schema_tool = GetSchemaCassandraDatabaseTool(db=db)\n",
-    "select_data_tool = GetTableDataCassandraDatabaseTool(db=db)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The tools can be invoked directly:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Test the tools\n",
-    "print(\"Executing a CQL query:\")\n",
-    "query = \"SELECT * FROM iot_sensors LIMIT 5;\"\n",
-    "result = query_tool.run({\"query\": query})\n",
-    "print(result)\n",
-    "\n",
-    "print(\"\\nGetting the schema for a keyspace:\")\n",
-    "schema = schema_tool.run({\"keyspace\": keyspace})\n",
-    "print(schema)\n",
-    "\n",
-    "print(\"\\nGetting data from a table:\")\n",
-    "table = \"iot_data\"\n",
-    "predicate = \"day = '2020-07-14' and device = 'b8:27:eb:bf:9d:51'\"\n",
-    "data = select_data_tool.run(\n",
-    "    {\"keyspace\": keyspace, \"table\": table, \"predicate\": predicate, \"limit\": 5}\n",
-    ")\n",
-    "print(data)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Agent Configuration"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.agents import Tool\n",
-    "from langchain_experimental.utilities import PythonREPL\n",
-    "\n",
-    "python_repl = PythonREPL()\n",
-    "\n",
-    "repl_tool = Tool(\n",
-    "    name=\"python_repl\",\n",
-    "    description=\"A Python shell. Use this to execute python commands. Input should be a valid python command. If you want to see the output of a value, you should print it out with `print(...)`.\",\n",
-    "    func=python_repl.run,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain import hub\n",
-    "\n",
-    "llm = ChatOpenAI(temperature=0, model=\"gpt-4-1106-preview\")\n",
-    "toolkit = CassandraDatabaseToolkit(db=db)\n",
-    "\n",
-    "# context = toolkit.get_context()\n",
-    "# tools = toolkit.get_tools()\n",
-    "tools = [schema_tool, select_data_tool, repl_tool]\n",
-    "\n",
-    "input = (\n",
-    "    QUERY_PATH_PROMPT\n",
-    "    + f\"\"\"\n",
-    "\n",
-    "Here is your task: In the {keyspace} keyspace, find the total number of times the temperature of each device has exceeded 23 degrees on July 14, 2020.\n",
-    " Create a summary report including the name of the room. Use Pandas if helpful.\n",
-    "\"\"\"\n",
-    ")\n",
-    "\n",
-    "prompt = hub.pull(\"hwchase17/openai-tools-agent\")\n",
-    "\n",
-    "# messages = [\n",
-    "#     HumanMessagePromptTemplate.from_template(input),\n",
-    "#     AIMessage(content=QUERY_PATH_PROMPT),\n",
-    "#     MessagesPlaceholder(variable_name=\"agent_scratchpad\"),\n",
-    "# ]\n",
-    "\n",
-    "# prompt = ChatPromptTemplate.from_messages(messages)\n",
-    "# print(prompt)\n",
-    "\n",
-    "# Choose the LLM that will drive the agent\n",
-    "# Only certain models support this\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-1106\", temperature=0)\n",
-    "\n",
-    "# Construct the OpenAI Tools agent\n",
-    "agent = create_openai_tools_agent(llm, tools, prompt)\n",
-    "\n",
-    "print(\"Available tools:\")\n",
-    "for tool in tools:\n",
-    "    print(\"\\t\" + tool.name + \" - \" + tool.description + \" - \" + str(tool))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)\n",
-    "\n",
-    "response = agent_executor.invoke({\"input\": input})\n",
-    "\n",
-    "print(response[\"output\"])"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.9.1"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

cookbook/custom_agent_with_plugin_retrieval.ipynb

@@ -169,7 +169,7 @@
     "\n",
     "def get_tools(query):\n",
     "    # Get documents, which contain the Plugins to use\n",
-    "    docs = retriever.invoke(query)\n",
+    "    docs = retriever.get_relevant_documents(query)\n",
     "    # Get the toolkits, one for each plugin\n",
     "    tool_kits = [toolkits_dict[d.metadata[\"plugin_name\"]] for d in docs]\n",
     "    # Get the tools: a separate NLAChain for each endpoint\n",

cookbook/custom_agent_with_plugin_retrieval_using_plugnplai.ipynb

@@ -193,7 +193,7 @@
     "\n",
     "def get_tools(query):\n",
     "    # Get documents, which contain the Plugins to use\n",
-    "    docs = retriever.invoke(query)\n",
+    "    docs = retriever.get_relevant_documents(query)\n",
     "    # Get the toolkits, one for each plugin\n",
     "    tool_kits = [toolkits_dict[d.metadata[\"plugin_name\"]] for d in docs]\n",
     "    # Get the tools: a separate NLAChain for each endpoint\n",

cookbook/custom_agent_with_tool_retrieval.ipynb

@@ -142,7 +142,7 @@
     "\n",
     "\n",
     "def get_tools(query):\n",
-    "    docs = retriever.invoke(query)\n",
+    "    docs = retriever.get_relevant_documents(query)\n",
     "    return [ALL_TOOLS[d.metadata[\"index\"]] for d in docs]"
    ]
   },

cookbook/databricks_sql_db.ipynb

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

cookbook/docugami_xml_kg_rag.ipynb

@@ -39,7 +39,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain docugami==0.0.8 dgml-utils==0.3.0 pydantic langchainhub langchain-chroma hnswlib --upgrade --quiet"
+    "! pip install langchain docugami==0.0.8 dgml-utils==0.3.0 pydantic langchainhub chromadb hnswlib --upgrade --quiet"
    ]
   },
   {
@@ -547,7 +547,7 @@
     "\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryStore\n",
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores.chroma import Chroma\n",
     "from langchain_core.documents import Document\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",

cookbook/elasticsearch_db_qa.ipynb

@@ -84,7 +84,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "llm = ChatOpenAI(model=\"gpt-4\", temperature=0)\n",
+    "llm = ChatOpenAI(model_name=\"gpt-4\", temperature=0)\n",
     "chain = ElasticsearchDatabaseChain.from_llm(llm=llm, database=db, verbose=True)"
    ]
   },
@@ -115,7 +115,7 @@
     "\n",
     "PROMPT_TEMPLATE = \"\"\"Given an input question, create a syntactically correct Elasticsearch query to run. Unless the user specifies in their question a specific number of examples they wish to obtain, always limit your query to at most {top_k} results. You can order the results by a relevant column to return the most interesting examples in the database.\n",
     "\n",
-    "Unless told to do not query for all the columns from a specific index, only ask for a few relevant columns given the question.\n",
+    "Unless told to do not query for all the columns from a specific index, only ask for a the few relevant columns given the question.\n",
     "\n",
     "Pay attention to use only the column names that you can see in the mapping description. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which index. Return the query as valid json.\n",
     "\n",

cookbook/fake_llm.ipynb

@@ -100,7 +100,7 @@
     }
    ],
    "source": [
-    "agent.invoke(\"whats 2 + 2\")"
+    "agent.run(\"whats 2 + 2\")"
    ]
   },
   {

cookbook/fireworks_rag.ipynb

@@ -84,7 +84,7 @@
     }
    ],
    "source": [
-    "%pip install --quiet pypdf langchain-chroma tiktoken openai \n",
+    "%pip install --quiet pypdf chromadb tiktoken openai \n",
     "%pip uninstall -y langchain-fireworks\n",
     "%pip install --editable /mnt/disks/data/langchain/libs/partners/fireworks"
    ]
@@ -138,7 +138,7 @@
     "all_splits = text_splitter.split_documents(data)\n",
     "\n",
     "# Add to vectorDB\n",
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_fireworks.embeddings import FireworksEmbeddings\n",
     "\n",
     "vectorstore = Chroma.from_documents(\n",

cookbook/forward_looking_retrieval_augmented_generation.ipynb

@@ -362,7 +362,7 @@
    ],
    "source": [
     "llm = OpenAI()\n",
-    "llm.invoke(query)"
+    "llm(query)"
    ]
   },
   {

cookbook/generative_agents_interactive_simulacra_of_human_behavior.ipynb

@@ -487,7 +487,7 @@
     "        print(\"*\" * 40)\n",
     "        print(\n",
     "            colored(\n",
-    "                f\"After {i + 1} observations, Tommie's summary is:\\n{tommie.get_summary(force_refresh=True)}\",\n",
+    "                f\"After {i+1} observations, Tommie's summary is:\\n{tommie.get_summary(force_refresh=True)}\",\n",
     "                \"blue\",\n",
     "            )\n",
     "        )\n",

cookbook/gymnasium_agent_simulation.ipynb

@@ -108,7 +108,7 @@
     "        return obs_message\n",
     "\n",
     "    def _act(self):\n",
-    "        act_message = self.model.invoke(self.message_history)\n",
+    "        act_message = self.model(self.message_history)\n",
     "        self.message_history.append(act_message)\n",
     "        action = int(self.action_parser.parse(act_message.content)[\"action\"])\n",
     "        return action\n",

cookbook/hypothetical_document_embeddings.ipynb

@@ -170,7 +170,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "with open(\"../../state_of_the_union.txt\") as f:\n",