update

`langchain_pinecone.Pinecone` is deprecated in favor of
`PineconeVectorStore`, and is currently a subclass of
`PineconeVectorStore`.
```python
@deprecated(since="0.0.3", removal="0.2.0", alternative="PineconeVectorStore")
class Pinecone(PineconeVectorStore):
    """Deprecated. Use PineconeVectorStore instead."""

    pass
```

.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": "cd libs/langchain_v1 && 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": "libs/langchain_v1/.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
+    
+    

.dockerignore

@@ -1,34 +0,0 @@
-# Git
-.git
-.github
-
-# Python
-__pycache__
-*.pyc
-*.pyo
-.venv
-.mypy_cache
-.pytest_cache
-.ruff_cache
-*.egg-info
-.tox
-
-# IDE
-.idea
-.vscode
-
-# Worktree
-worktree
-
-# Test artifacts
-.coverage
-htmlcov
-coverage.xml
-
-# Build artifacts
-dist
-build
-
-# Misc
-*.log
-.DS_Store

.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/   @ccurme @eyurtsev @mdrxy
-/libs/core/ @eyurtsev
-/libs/partners/ @ccurme @mdrxy

.github/CODE_OF_CONDUCT.md

@@ -0,0 +1,132 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, caste, color, religion, or sexual
+identity and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the overall
+  community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or advances of
+  any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email address,
+  without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official e-mail address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the community leaders responsible for enforcement at
+conduct@langchain.dev.
+All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series of
+actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or permanent
+ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior, harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within the
+community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.1, available at
+[https://www.contributor-covenant.org/version/2/1/code_of_conduct.html][v2.1].
+
+Community Impact Guidelines were inspired by
+[Mozilla's code of conduct enforcement ladder][Mozilla CoC].
+
+For answers to common questions about this code of conduct, see the FAQ at
+[https://www.contributor-covenant.org/faq][FAQ]. Translations are available at
+[https://www.contributor-covenant.org/translations][translations].
+
+[homepage]: https://www.contributor-covenant.org
+[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

.github/CONTRIBUTING.md

@@ -0,0 +1,6 @@
+# Contributing to LangChain
+
+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://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

@@ -1,33 +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 (below).
-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: |
-        > **All contributions must be in English.** See the [language policy](https://docs.langchain.com/oss/python/contributing/overview#language-policy).
-
-        Thank you for taking the time to file a bug report.
-
-        For usage questions, feature requests and general design questions, please use the [LangChain Forum](https://forum.langchain.com/).
-
-        Check these before submitting to see if your issue has already been reported, fixed or if there's another way to solve your problem:
-
-        * [Documentation](https://docs.langchain.com/oss/python/langchain/overview),
-        * [API Reference Documentation](https://reference.langchain.com/python/),
-        * [LangChain ChatBot](https://chat.langchain.com/)
-        * [GitHub search](https://github.com/langchain-ai/langchain),
-        * [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 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: Submission checklist
+      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
@@ -35,87 +37,46 @@ 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 posted a self-contained, minimal, reproducible example. A maintainer can copy it and run it AS IS.
-          required: true
-  - type: checkboxes
-    id: package
-    attributes:
-      label: Package (Required)
-      description: |
-        Which `langchain` package(s) is this bug related to? Select at least one.
-
-        Note that if the package you are reporting for is not listed here, it is not in this repository (e.g. `langchain-google-genai` is in [`langchain-ai/langchain-google`](https://github.com/langchain-ai/langchain-google/)).
-
-        Please report issues for other packages to their respective repositories.
-      options:
-        - label: langchain
-        - label: langchain-openai
-        - label: langchain-anthropic
-        - label: langchain-classic
-        - label: langchain-core
-        - label: langchain-model-profiles
-        - label: langchain-tests
-        - label: langchain-text-splitters
-        - label: langchain-chroma
-        - label: langchain-deepseek
-        - label: langchain-exa
-        - label: langchain-fireworks
-        - label: langchain-groq
-        - label: langchain-huggingface
-        - label: langchain-mistralai
-        - label: langchain-nomic
-        - label: langchain-ollama
-        - label: langchain-openrouter
-        - label: langchain-perplexity
-        - label: langchain-qdrant
-        - label: langchain-xai
-        - label: Other / not sure / general
-  - type: textarea
-    id: related
-    validations:
-      required: false
-    attributes:
-      label: Related Issues / PRs
-      description: |
-        If this bug is related to any existing issues or pull requests, please link them here.
-      placeholder: |
-        * e.g. #123, #456
   - type: textarea
     id: reproduction
     validations:
       required: true
     attributes:
-      label: Reproduction Steps / Example Code (Python)
+      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.
 
-        **Important!**
-
-        * Avoid screenshots, 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 will be automatically formatted into code, so no need for backticks.)
-      render: python
       placeholder: |
+        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!')
+        ```
   - type: textarea
+    id: error
+    validations:
+      required: false
     attributes:
       label: Error Message and Stack Trace (if applicable)
       description: |
-        If you are reporting an error, please copy and paste the full error message and
-        stack trace.
-        (This will be automatically formatted into code, so no need for backticks.)
-      render: shell
+        If you are reporting an error, please include the full error message and stack trace.
+      placeholder: |
+        Exception + full stack trace
   - type: textarea
     id: description
     attributes:
@@ -135,19 +96,25 @@ body:
     attributes:
       label: System Info
       description: |
-        Please share your system info with us.
-
-        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()
-        ```
-      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

@@ -1,15 +1,15 @@
 blank_issues_enabled: false
 version: 2.1
 contact_links:
-  - name: 💬 LangChain Forum
-    url:  https://forum.langchain.com/
-    about: General community discussions and support
-  - name: 📚 LangChain Documentation
-    url: https://docs.langchain.com/oss/python/langchain/overview
-    about: View the official LangChain documentation
-  - name: 📚 API Reference Documentation
-    url: https://reference.langchain.com/python/
-    about: View the official LangChain API reference documentation
-  - name: 📚 Documentation issue
-    url: https://github.com/langchain-ai/docs/issues/new?template=01-langchain.yml
-    about: Report an issue related to the LangChain documentation
+  - 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

@@ -1,155 +0,0 @@
-name: "✨ Feature Request"
-description: Request a new feature or enhancement for LangChain. For questions, please use the LangChain forum (below).
-labels: ["feature request"]
-type: feature
-body:
-  - type: markdown
-    attributes:
-      value: |
-        > **All contributions must be in English.** See the [language policy](https://docs.langchain.com/oss/python/contributing/overview#language-policy).
-
-        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:
-
-        * [Documentation](https://docs.langchain.com/oss/python/langchain/overview),
-        * [API Reference Documentation](https://reference.langchain.com/python/),
-        * [LangChain ChatBot](https://chat.langchain.com/)
-        * [GitHub search](https://github.com/langchain-ai/langchain),
-        * [LangChain Forum](https://forum.langchain.com/),
-
-        **Note:** Do not begin work on a PR unless explicitly assigned to this issue by a maintainer.
-  - type: checkboxes
-    id: checks
-    attributes:
-      label: Submission checklist
-      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: checkboxes
-    id: package
-    attributes:
-      label: Package (Required)
-      description: |
-        Which `langchain` package(s) is this request related to? Select at least one.
-
-        Note that if the package you are requesting for is not listed here, it is not in this repository (e.g. `langchain-google-genai` is in `langchain-ai/langchain`).
-
-        Please submit feature requests for other packages to their respective repositories.
-      options:
-        - label: langchain
-        - label: langchain-openai
-        - label: langchain-anthropic
-        - label: langchain-classic
-        - label: langchain-core
-        - label: langchain-model-profiles
-        - label: langchain-tests
-        - label: langchain-text-splitters
-        - label: langchain-chroma
-        - label: langchain-deepseek
-        - label: langchain-exa
-        - label: langchain-fireworks
-        - label: langchain-groq
-        - label: langchain-huggingface
-        - label: langchain-mistralai
-        - label: langchain-nomic
-        - label: langchain-ollama
-        - label: langchain-openrouter
-        - label: langchain-perplexity
-        - label: langchain-qdrant
-        - label: langchain-xai
-        - label: Other / not sure / general
-  - 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:
@@ -18,32 +23,3 @@ body:
     attributes:
       label: Issue Content
       description: Add the content of the issue here.
-  - type: checkboxes
-    id: package
-    attributes:
-      label: Package (Required)
-      description: |
-        Please select package(s) that this issue is related to.
-      options:
-        - label: langchain
-        - label: langchain-openai
-        - label: langchain-anthropic
-        - label: langchain-classic
-        - label: langchain-core
-        - label: langchain-model-profiles
-        - label: langchain-tests
-        - label: langchain-text-splitters
-        - label: langchain-chroma
-        - label: langchain-deepseek
-        - label: langchain-exa
-        - label: langchain-fireworks
-        - label: langchain-groq
-        - label: langchain-huggingface
-        - label: langchain-mistralai
-        - label: langchain-nomic
-        - label: langchain-ollama
-        - label: langchain-openrouter
-        - label: langchain-perplexity
-        - label: langchain-qdrant
-        - label: langchain-xai
-        - label: Other / not sure / general

.github/ISSUE_TEMPLATE/task.yml

@@ -1,120 +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
-  - type: checkboxes
-    id: package
-    attributes:
-      label: Package (Required)
-      description: |
-        Please select package(s) that this task is related to.
-      options:
-        - label: langchain
-        - label: langchain-openai
-        - label: langchain-anthropic
-        - label: langchain-classic
-        - label: langchain-core
-        - label: langchain-model-profiles
-        - label: langchain-tests
-        - label: langchain-text-splitters
-        - label: langchain-chroma
-        - label: langchain-deepseek
-        - label: langchain-exa
-        - label: langchain-fireworks
-        - label: langchain-groq
-        - label: langchain-huggingface
-        - label: langchain-mistralai
-        - label: langchain-nomic
-        - label: langchain-ollama
-        - label: langchain-openrouter
-        - label: langchain-perplexity
-        - label: langchain-qdrant
-        - label: langchain-xai
-        - label: Other / not sure / general

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,43 +1,29 @@
-Fixes #
+Thank you for contributing to LangChain!
 
-<!-- Replace everything above this line with a 1-2 sentence description of your change. Keep the "Fixes #xx" keyword and update the issue number. -->
+- [ ] **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"
 
-Read the full contributing guidelines: https://docs.langchain.com/oss/python/contributing/overview
 
-> **All contributions must be in English.** See the [language policy](https://docs.langchain.com/oss/python/contributing/overview#language-policy).
+- [ ] **PR message**: ***Delete this entire checklist*** and replace with
+    - **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!
 
-If you paste a large clearly AI generated description here your PR may be IGNORED or CLOSED!
 
-Thank you for contributing to LangChain! Follow these steps to have your pull request considered as ready for review.
+- [ ] **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.
 
-1. PR title: Should follow the format: TYPE(SCOPE): DESCRIPTION
 
-  - Examples:
-    - fix(anthropic): resolve flag parsing error
-    - feat(core): add multi-tenant support
-    - test(openai): update API usage tests
-  - Allowed TYPE and SCOPE values: https://github.com/langchain-ai/langchain/blob/master/.github/workflows/pr_lint.yml#L15-L33
-
-2. PR description:
-
-  - Write 1-2 sentences summarizing the change.
-  - The `Fixes #xx` line at the top is **required** for external contributions — update the issue number and keep the keyword. This links your PR to the approved issue and auto-closes it on merge.
-  - If there are any breaking changes, please clearly describe them.
-  - If this PR depends on another PR being merged first, please include "Depends on #PR_NUMBER" in the description.
-
-3. 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.
-
-4. How did you verify your code works?
+- [ ] **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:
+- 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.
 
-  - All external PRs must link to an issue or discussion where a solution has been approved by a maintainer, and you must be assigned to that issue. PRs without prior approval will be closed.
-  - PRs should not touch more than one package unless absolutely necessary.
-  - Do not update the `uv.lock` files or add dependencies to `pyproject.toml` files (even optional ones) unless you have explicit permission to do so by a maintainer.
-
-## Social handles (optional)
-<!-- If you'd like a shoutout on release, add your socials below -->
-Twitter: @
-LinkedIn: https://linkedin.com/in/
+If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, hwchase17.

.github/actions/people/Dockerfile

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

.github/actions/people/action.yml

@@ -0,0 +1,11 @@
+# Adapted from https://github.com/tiangolo/fastapi/blob/master/.github/actions/people/action.yml
+name: "Generate LangChain People"
+description: "Generate the data for the LangChain People page"
+author: "Jacob Lee <jacob@langchain.dev>"
+inputs:
+  token:
+    description: 'User token, to read the GitHub API. Can be passed in using {{ secrets.LANGCHAIN_PEOPLE_GITHUB_TOKEN }}'
+    required: true
+runs:
+  using: 'docker'
+  image: 'Dockerfile'

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

@@ -0,0 +1,641 @@
+# Adapted from https://github.com/tiangolo/fastapi/blob/master/.github/actions/people/app/main.py
+
+import logging
+import subprocess
+import sys
+from collections import Counter
+from datetime import datetime, timedelta, timezone
+from pathlib import Path
+from typing import Any, Container, Dict, List, Set, Union
+
+import httpx
+import yaml
+from github import Github
+from pydantic import BaseModel, SecretStr
+from pydantic_settings import BaseSettings
+
+github_graphql_url = "https://api.github.com/graphql"
+questions_category_id = "DIC_kwDOIPDwls4CS6Ve"
+
+# discussions_query = """
+# query Q($after: String, $category_id: ID) {
+#   repository(name: "langchain", owner: "langchain-ai") {
+#     discussions(first: 100, after: $after, categoryId: $category_id) {
+#       edges {
+#         cursor
+#         node {
+#           number
+#           author {
+#             login
+#             avatarUrl
+#             url
+#           }
+#           title
+#           createdAt
+#           comments(first: 100) {
+#             nodes {
+#               createdAt
+#               author {
+#                 login
+#                 avatarUrl
+#                 url
+#               }
+#               isAnswer
+#               replies(first: 10) {
+#                 nodes {
+#                   createdAt
+#                   author {
+#                     login
+#                     avatarUrl
+#                     url
+#                   }
+#                 }
+#               }
+#             }
+#           }
+#         }
+#       }
+#     }
+#   }
+# }
+# """
+
+# issues_query = """
+# query Q($after: String) {
+#   repository(name: "langchain", owner: "langchain-ai") {
+#     issues(first: 100, after: $after) {
+#       edges {
+#         cursor
+#         node {
+#           number
+#           author {
+#             login
+#             avatarUrl
+#             url
+#           }
+#           title
+#           createdAt
+#           state
+#           comments(first: 100) {
+#             nodes {
+#               createdAt
+#               author {
+#                 login
+#                 avatarUrl
+#                 url
+#               }
+#             }
+#           }
+#         }
+#       }
+#     }
+#   }
+# }
+# """
+
+prs_query = """
+query Q($after: String) {
+  repository(name: "langchain", owner: "langchain-ai") {
+    pullRequests(first: 100, after: $after, states: MERGED) {
+      edges {
+        cursor
+        node {
+          changedFiles
+          additions
+          deletions
+          number
+          labels(first: 100) {
+            nodes {
+              name
+            }
+          }
+          author {
+            login
+            avatarUrl
+            url
+            ... on User {
+              twitterUsername
+            }
+          }
+          title
+          createdAt
+          state
+          reviews(first:100) {
+            nodes {
+              author {
+                login
+                avatarUrl
+                url
+                ... on User {
+                  twitterUsername
+                }
+              }
+              state
+            }
+          }
+        }
+      }
+    }
+  }
+}
+"""
+
+
+class Author(BaseModel):
+    login: str
+    avatarUrl: str
+    url: str
+    twitterUsername: Union[str, None] = None
+
+
+# Issues and Discussions
+
+
+class CommentsNode(BaseModel):
+    createdAt: datetime
+    author: Union[Author, None] = None
+
+
+class Replies(BaseModel):
+    nodes: List[CommentsNode]
+
+
+class DiscussionsCommentsNode(CommentsNode):
+    replies: Replies
+
+
+class Comments(BaseModel):
+    nodes: List[CommentsNode]
+
+
+class DiscussionsComments(BaseModel):
+    nodes: List[DiscussionsCommentsNode]
+
+
+class IssuesNode(BaseModel):
+    number: int
+    author: Union[Author, None] = None
+    title: str
+    createdAt: datetime
+    state: str
+    comments: Comments
+
+
+class DiscussionsNode(BaseModel):
+    number: int
+    author: Union[Author, None] = None
+    title: str
+    createdAt: datetime
+    comments: DiscussionsComments
+
+
+class IssuesEdge(BaseModel):
+    cursor: str
+    node: IssuesNode
+
+
+class DiscussionsEdge(BaseModel):
+    cursor: str
+    node: DiscussionsNode
+
+
+class Issues(BaseModel):
+    edges: List[IssuesEdge]
+
+
+class Discussions(BaseModel):
+    edges: List[DiscussionsEdge]
+
+
+class IssuesRepository(BaseModel):
+    issues: Issues
+
+
+class DiscussionsRepository(BaseModel):
+    discussions: Discussions
+
+
+class IssuesResponseData(BaseModel):
+    repository: IssuesRepository
+
+
+class DiscussionsResponseData(BaseModel):
+    repository: DiscussionsRepository
+
+
+class IssuesResponse(BaseModel):
+    data: IssuesResponseData
+
+
+class DiscussionsResponse(BaseModel):
+    data: DiscussionsResponseData
+
+
+# PRs
+
+
+class LabelNode(BaseModel):
+    name: str
+
+
+class Labels(BaseModel):
+    nodes: List[LabelNode]
+
+
+class ReviewNode(BaseModel):
+    author: Union[Author, None] = None
+    state: str
+
+
+class Reviews(BaseModel):
+    nodes: List[ReviewNode]
+
+
+class PullRequestNode(BaseModel):
+    number: int
+    labels: Labels
+    author: Union[Author, None] = None
+    changedFiles: int
+    additions: int
+    deletions: int
+    title: str
+    createdAt: datetime
+    state: str
+    reviews: Reviews
+    # comments: Comments
+
+
+class PullRequestEdge(BaseModel):
+    cursor: str
+    node: PullRequestNode
+
+
+class PullRequests(BaseModel):
+    edges: List[PullRequestEdge]
+
+
+class PRsRepository(BaseModel):
+    pullRequests: PullRequests
+
+
+class PRsResponseData(BaseModel):
+    repository: PRsRepository
+
+
+class PRsResponse(BaseModel):
+    data: PRsResponseData
+
+
+class Settings(BaseSettings):
+    input_token: SecretStr
+    github_repository: str
+    httpx_timeout: int = 30
+
+
+def get_graphql_response(
+    *,
+    settings: Settings,
+    query: str,
+    after: Union[str, None] = None,
+    category_id: Union[str, None] = None,
+) -> Dict[str, Any]:
+    headers = {"Authorization": f"token {settings.input_token.get_secret_value()}"}
+    # category_id is only used by one query, but GraphQL allows unused variables, so
+    # keep it here for simplicity
+    variables = {"after": after, "category_id": category_id}
+    response = httpx.post(
+        github_graphql_url,
+        headers=headers,
+        timeout=settings.httpx_timeout,
+        json={"query": query, "variables": variables, "operationName": "Q"},
+    )
+    if response.status_code != 200:
+        logging.error(
+            f"Response was not 200, after: {after}, category_id: {category_id}"
+        )
+        logging.error(response.text)
+        raise RuntimeError(response.text)
+    data = response.json()
+    if "errors" in data:
+        logging.error(f"Errors in response, after: {after}, category_id: {category_id}")
+        logging.error(data["errors"])
+        logging.error(response.text)
+        raise RuntimeError(response.text)
+    return data
+
+
+# def get_graphql_issue_edges(*, settings: Settings, after: Union[str, None] = None):
+#     data = get_graphql_response(settings=settings, query=issues_query, after=after)
+#     graphql_response = IssuesResponse.model_validate(data)
+#     return graphql_response.data.repository.issues.edges
+
+
+# def get_graphql_question_discussion_edges(
+#     *,
+#     settings: Settings,
+#     after: Union[str, None] = None,
+# ):
+#     data = get_graphql_response(
+#         settings=settings,
+#         query=discussions_query,
+#         after=after,
+#         category_id=questions_category_id,
+#     )
+#     graphql_response = DiscussionsResponse.model_validate(data)
+#     return graphql_response.data.repository.discussions.edges
+
+
+def get_graphql_pr_edges(*, settings: Settings, after: Union[str, None] = None):
+    if after is None:
+        print("Querying PRs...")
+    else:
+        print(f"Querying PRs with cursor {after}...")
+    data = get_graphql_response(
+        settings=settings,
+        query=prs_query,
+        after=after
+    )
+    graphql_response = PRsResponse.model_validate(data)
+    return graphql_response.data.repository.pullRequests.edges
+
+
+# def get_issues_experts(settings: Settings):
+#     issue_nodes: List[IssuesNode] = []
+#     issue_edges = get_graphql_issue_edges(settings=settings)
+
+#     while issue_edges:
+#         for edge in issue_edges:
+#             issue_nodes.append(edge.node)
+#         last_edge = issue_edges[-1]
+#         issue_edges = get_graphql_issue_edges(settings=settings, after=last_edge.cursor)
+
+#     commentors = Counter()
+#     last_month_commentors = Counter()
+#     authors: Dict[str, Author] = {}
+
+#     now = datetime.now(tz=timezone.utc)
+#     one_month_ago = now - timedelta(days=30)
+
+#     for issue in issue_nodes:
+#         issue_author_name = None
+#         if issue.author:
+#             authors[issue.author.login] = issue.author
+#             issue_author_name = issue.author.login
+#         issue_commentors = set()
+#         for comment in issue.comments.nodes:
+#             if comment.author:
+#                 authors[comment.author.login] = comment.author
+#                 if comment.author.login != issue_author_name:
+#                     issue_commentors.add(comment.author.login)
+#         for author_name in issue_commentors:
+#             commentors[author_name] += 1
+#             if issue.createdAt > one_month_ago:
+#                 last_month_commentors[author_name] += 1
+
+#     return commentors, last_month_commentors, authors
+
+
+# def get_discussions_experts(settings: Settings):
+#     discussion_nodes: List[DiscussionsNode] = []
+#     discussion_edges = get_graphql_question_discussion_edges(settings=settings)
+
+#     while discussion_edges:
+#         for discussion_edge in discussion_edges:
+#             discussion_nodes.append(discussion_edge.node)
+#         last_edge = discussion_edges[-1]
+#         discussion_edges = get_graphql_question_discussion_edges(
+#             settings=settings, after=last_edge.cursor
+#         )
+
+#     commentors = Counter()
+#     last_month_commentors = Counter()
+#     authors: Dict[str, Author] = {}
+
+#     now = datetime.now(tz=timezone.utc)
+#     one_month_ago = now - timedelta(days=30)
+
+#     for discussion in discussion_nodes:
+#         discussion_author_name = None
+#         if discussion.author:
+#             authors[discussion.author.login] = discussion.author
+#             discussion_author_name = discussion.author.login
+#         discussion_commentors = set()
+#         for comment in discussion.comments.nodes:
+#             if comment.author:
+#                 authors[comment.author.login] = comment.author
+#                 if comment.author.login != discussion_author_name:
+#                     discussion_commentors.add(comment.author.login)
+#             for reply in comment.replies.nodes:
+#                 if reply.author:
+#                     authors[reply.author.login] = reply.author
+#                     if reply.author.login != discussion_author_name:
+#                         discussion_commentors.add(reply.author.login)
+#         for author_name in discussion_commentors:
+#             commentors[author_name] += 1
+#             if discussion.createdAt > one_month_ago:
+#                 last_month_commentors[author_name] += 1
+#     return commentors, last_month_commentors, authors
+
+
+# def get_experts(settings: Settings):
+#     (
+#         discussions_commentors,
+#         discussions_last_month_commentors,
+#         discussions_authors,
+#     ) = get_discussions_experts(settings=settings)
+#     commentors = discussions_commentors
+#     last_month_commentors = discussions_last_month_commentors
+#     authors = {**discussions_authors}
+#     return commentors, last_month_commentors, authors
+
+
+def _logistic(x, k):
+    return x / (x + k)
+
+
+def get_contributors(settings: Settings):
+    pr_nodes: List[PullRequestNode] = []
+    pr_edges = get_graphql_pr_edges(settings=settings)
+
+    while pr_edges:
+        for edge in pr_edges:
+            pr_nodes.append(edge.node)
+        last_edge = pr_edges[-1]
+        pr_edges = get_graphql_pr_edges(settings=settings, after=last_edge.cursor)
+
+    contributors = Counter()
+    contributor_scores = Counter()
+    recent_contributor_scores = Counter()
+    reviewers = Counter()
+    authors: Dict[str, Author] = {}
+
+    for pr in pr_nodes:
+        pr_reviewers: Set[str] = set()
+        for review in pr.reviews.nodes:
+            if review.author:
+                authors[review.author.login] = review.author
+                pr_reviewers.add(review.author.login)
+        for reviewer in pr_reviewers:
+            reviewers[reviewer] += 1
+        if pr.author:
+            authors[pr.author.login] = pr.author
+            contributors[pr.author.login] += 1
+            files_changed = pr.changedFiles
+            lines_changed = pr.additions + pr.deletions
+            score = _logistic(files_changed, 20) + _logistic(lines_changed, 100)
+            contributor_scores[pr.author.login] += score
+            three_months_ago = (datetime.now(timezone.utc) - timedelta(days=3*30))
+            if pr.createdAt > three_months_ago:
+                recent_contributor_scores[pr.author.login] += score
+    return contributors, contributor_scores, recent_contributor_scores, reviewers, authors
+
+
+def get_top_users(
+    *,
+    counter: Counter,
+    min_count: int,
+    authors: Dict[str, Author],
+    skip_users: Container[str],
+):
+    users = []
+    for commentor, count in counter.most_common():
+        if commentor in skip_users:
+            continue
+        if count >= min_count:
+            author = authors[commentor]
+            users.append(
+                {
+                    "login": commentor,
+                    "count": count,
+                    "avatarUrl": author.avatarUrl,
+                    "twitterUsername": author.twitterUsername,
+                    "url": author.url,
+                }
+            )
+    return users
+
+
+if __name__ == "__main__":
+    logging.basicConfig(level=logging.INFO)
+    settings = Settings()
+    logging.info(f"Using config: {settings.model_dump_json()}")
+    g = Github(settings.input_token.get_secret_value())
+    repo = g.get_repo(settings.github_repository)
+    # question_commentors, question_last_month_commentors, question_authors = get_experts(
+    #     settings=settings
+    # )
+    contributors, contributor_scores, recent_contributor_scores, reviewers, pr_authors = get_contributors(
+        settings=settings
+    )
+    # authors = {**question_authors, **pr_authors}
+    authors = {**pr_authors}
+    maintainers_logins = {
+        "hwchase17",
+        "agola11",
+        "baskaryan",
+        "hinthornw",
+        "nfcampos",
+        "efriis",
+        "eyurtsev",
+        "rlancemartin"
+    }
+    hidden_logins = {
+        "dev2049",
+        "vowelparrot",
+        "obi1kenobi",
+        "langchain-infra",
+        "jacoblee93",
+        "dqbd",
+        "bracesproul",
+        "akira",
+    }
+    bot_names = {"dosubot", "github-actions", "CodiumAI-Agent"}
+    maintainers = []
+    for login in maintainers_logins:
+        user = authors[login]
+        maintainers.append(
+            {
+                "login": login,
+                "count": contributors[login], #+ question_commentors[login],
+                "avatarUrl": user.avatarUrl,
+                "twitterUsername": user.twitterUsername,
+                "url": user.url,
+            }
+        )
+
+    # min_count_expert = 10
+    # min_count_last_month = 3
+    min_score_contributor = 1
+    min_count_reviewer = 5
+    skip_users = maintainers_logins | bot_names | hidden_logins
+    # experts = get_top_users(
+    #     counter=question_commentors,
+    #     min_count=min_count_expert,
+    #     authors=authors,
+    #     skip_users=skip_users,
+    # )
+    # last_month_active = get_top_users(
+    #     counter=question_last_month_commentors,
+    #     min_count=min_count_last_month,
+    #     authors=authors,
+    #     skip_users=skip_users,
+    # )
+    top_recent_contributors = get_top_users(
+        counter=recent_contributor_scores,
+        min_count=min_score_contributor,
+        authors=authors,
+        skip_users=skip_users,
+    )
+    top_contributors = get_top_users(
+        counter=contributor_scores,
+        min_count=min_score_contributor,
+        authors=authors,
+        skip_users=skip_users,
+    )
+    top_reviewers = get_top_users(
+        counter=reviewers,
+        min_count=min_count_reviewer,
+        authors=authors,
+        skip_users=skip_users,
+    )
+
+    people = {
+        "maintainers": maintainers,
+        # "experts": experts,
+        # "last_month_active": last_month_active,
+        "top_recent_contributors": top_recent_contributors,
+        "top_contributors": top_contributors,
+        "top_reviewers": top_reviewers,
+    }
+    people_path = Path("./docs/data/people.yml")
+    people_old_content = people_path.read_text(encoding="utf-8")
+    new_people_content = yaml.dump(
+        people, sort_keys=False, width=200, allow_unicode=True
+    )
+    if (
+        people_old_content == new_people_content
+    ):
+        logging.info("The LangChain People data hasn't changed, finishing.")
+        sys.exit(0)
+    people_path.write_text(new_people_content, encoding="utf-8")
+    logging.info("Setting up GitHub Actions git user")
+    subprocess.run(["git", "config", "user.name", "github-actions"], check=True)
+    subprocess.run(
+        ["git", "config", "user.email", "github-actions@github.com"], check=True
+    )
+    branch_name = "langchain/langchain-people"
+    logging.info(f"Creating a new branch {branch_name}")
+    subprocess.run(["git", "checkout", "-B", branch_name], check=True)
+    logging.info("Adding updated file")
+    subprocess.run(
+        ["git", "add", str(people_path)], check=True
+    )
+    logging.info("Committing updated file")
+    message = "👥 Update LangChain people data"
+    result = subprocess.run(["git", "commit", "-m", message], check=True)
+    logging.info("Pushing branch")
+    subprocess.run(["git", "push", "origin", branch_name, "-f"], check=True)
+    logging.info("Creating PR")
+    pr = repo.create_pull(title=message, body=message, base="master", head=branch_name)
+    logging.info(f"Created PR: {pr.number}")
+    logging.info("Finished")

.github/actions/poetry_setup/action.yml

@@ -0,0 +1,93 @@
+# An action for setting up poetry install with caching.
+# Using a custom action since the default action does not
+# take poetry install groups into account.
+# Action code from:
+# https://github.com/actions/setup-python/issues/505#issuecomment-1273013236
+name: poetry-install-with-caching
+description: Poetry install with support for caching of dependency groups.
+
+inputs:
+  python-version:
+    description: Python version, supporting MAJOR.MINOR only
+    required: true
+
+  poetry-version:
+    description: Poetry version
+    required: true
+
+  cache-key:
+    description: Cache key to use for manual handling of caching
+    required: true
+
+  working-directory:
+    description: Directory whose poetry.lock file should be cached
+    required: true
+
+runs:
+  using: composite
+  steps:
+    - uses: actions/setup-python@v5
+      name: Setup python ${{ inputs.python-version }}
+      id: setup-python
+      with:
+        python-version: ${{ inputs.python-version }}
+
+    - uses: actions/cache@v4
+      id: cache-bin-poetry
+      name: Cache Poetry binary - Python ${{ inputs.python-version }}
+      env:
+        SEGMENT_DOWNLOAD_TIMEOUT_MIN: "1"
+      with:
+        path: |
+          /opt/pipx/venvs/poetry
+        # This step caches the poetry installation, so make sure it's keyed on the poetry version as well.
+        key: bin-poetry-${{ runner.os }}-${{ runner.arch }}-py-${{ inputs.python-version }}-${{ inputs.poetry-version }}
+
+    - name: Refresh shell hashtable and fixup softlinks
+      if: steps.cache-bin-poetry.outputs.cache-hit == 'true'
+      shell: bash
+      env:
+        POETRY_VERSION: ${{ inputs.poetry-version }}
+        PYTHON_VERSION: ${{ inputs.python-version }}
+      run: |
+        set -eux
+
+        # Refresh the shell hashtable, to ensure correct `which` output.
+        hash -r
+
+        # `actions/cache@v3` doesn't always seem able to correctly unpack softlinks.
+        # Delete and recreate the softlinks pipx expects to have.
+        rm /opt/pipx/venvs/poetry/bin/python
+        cd /opt/pipx/venvs/poetry/bin
+        ln -s "$(which "python$PYTHON_VERSION")" python
+        chmod +x python
+        cd /opt/pipx_bin/
+        ln -s /opt/pipx/venvs/poetry/bin/poetry poetry
+        chmod +x poetry
+
+        # Ensure everything got set up correctly.
+        /opt/pipx/venvs/poetry/bin/python --version
+        /opt/pipx_bin/poetry --version
+
+    - name: Install poetry
+      if: steps.cache-bin-poetry.outputs.cache-hit != 'true'
+      shell: bash
+      env:
+        POETRY_VERSION: ${{ inputs.poetry-version }}
+        PYTHON_VERSION: ${{ inputs.python-version }}
+      # Install poetry using the python version installed by setup-python step.
+      run: pipx install "poetry==$POETRY_VERSION" --python '${{ steps.setup-python.outputs.python-path }}' --verbose
+
+    - name: Restore pip and poetry cached dependencies
+      uses: actions/cache@v4
+      env:
+        SEGMENT_DOWNLOAD_TIMEOUT_MIN: "4"
+        WORKDIR: ${{ inputs.working-directory == '' && '.' || inputs.working-directory }}
+      with:
+        path: |
+          ~/.cache/pip
+          ~/.cache/pypoetry/virtualenvs
+          ~/.cache/pypoetry/cache
+          ~/.cache/pypoetry/artifacts
+          ${{ env.WORKDIR }}/.venv
+        key: py-deps-${{ runner.os }}-${{ runner.arch }}-py-${{ inputs.python-version }}-poetry-${{ inputs.poetry-version }}-${{ inputs.cache-key }}-${{ hashFiles(format('{0}/**/poetry.lock', env.WORKDIR)) }}

.github/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@0ca8f610542aa7f4acaf39e65cf4eb3c35091883 # v7
-      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/dependabot.yml

@@ -1,95 +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: "monthly"
-    groups:
-      minor-and-patch:
-        patterns:
-          - "*"
-        update-types:
-          - "minor"
-          - "patch"
-      major:
-        patterns:
-          - "*"
-        update-types:
-          - "major"
-
-  - package-ecosystem: "uv"
-    directories:
-      - "/libs/core/"
-      - "/libs/langchain/"
-      - "/libs/langchain_v1/"
-    schedule:
-      interval: "monthly"
-    groups:
-      minor-and-patch:
-        patterns:
-          - "*"
-        update-types:
-          - "minor"
-          - "patch"
-      major:
-        patterns:
-          - "*"
-        update-types:
-          - "major"
-
-  - package-ecosystem: "uv"
-    directories:
-      - "/libs/partners/anthropic/"
-      - "/libs/partners/chroma/"
-      - "/libs/partners/deepseek/"
-      - "/libs/partners/exa/"
-      - "/libs/partners/fireworks/"
-      - "/libs/partners/groq/"
-      - "/libs/partners/huggingface/"
-      - "/libs/partners/mistralai/"
-      - "/libs/partners/nomic/"
-      - "/libs/partners/ollama/"
-      - "/libs/partners/openai/"
-      - "/libs/partners/openrouter/"
-      - "/libs/partners/perplexity/"
-      - "/libs/partners/qdrant/"
-      - "/libs/partners/xai/"
-    schedule:
-      interval: "monthly"
-    groups:
-      minor-and-patch:
-        patterns:
-          - "*"
-        update-types:
-          - "minor"
-          - "patch"
-      major:
-        patterns:
-          - "*"
-        update-types:
-          - "major"
-
-  - package-ecosystem: "uv"
-    directories:
-      - "/libs/text-splitters/"
-      - "/libs/standard-tests/"
-      - "/libs/model-profiles/"
-    schedule:
-      interval: "monthly"
-    groups:
-      minor-and-patch:
-        patterns:
-          - "*"
-        update-types:
-          - "minor"
-          - "patch"
-      major:
-        patterns:
-          - "*"
-        update-types:
-          - "major"

.github/images/logo-dark.svg

@@ -1,6 +0,0 @@
-<svg width="472" height="100" viewBox="0 0 472 100" fill="none" xmlns="http://www.w3.org/2000/svg">
-<rect width="100" height="100" rx="20" fill="#161F34"/>
-<path d="M54.2612 54.2583L63.1942 45.3253C67.8979 40.6215 67.8979 32.9952 63.1942 28.2914C58.4904 23.5877 50.8641 23.5877 46.1603 28.2914L37.2273 37.2244" stroke="#7FC8FF" stroke-width="12.0389"/>
-<path d="M45.7427 45.7412L36.8098 54.6742C32.106 59.3779 32.106 67.0042 36.8098 71.708C41.5135 76.4118 49.1398 76.4118 53.8436 71.708L62.7766 62.775" stroke="#7FC8FF" stroke-width="12.0389"/>
-<path d="M142.427 70.248V65.748H153.227V32.748H142.427V28.248H158.147V65.748H168.947V70.248H142.427ZM189.174 70.608C182.454 70.608 177.894 67.248 177.894 61.668C177.894 55.548 182.154 52.128 190.194 52.128H199.194V50.028C199.194 46.068 196.374 43.668 191.574 43.668C187.254 43.668 184.374 45.708 183.774 48.828H178.854C179.574 42.828 184.434 39.288 191.814 39.288C199.614 39.288 204.114 43.188 204.114 50.328V63.708C204.114 65.328 204.714 65.748 206.094 65.748H207.654V70.248H204.954C200.874 70.248 199.494 68.508 199.434 65.508C197.514 68.268 194.454 70.608 189.174 70.608ZM189.534 66.408C195.654 66.408 199.194 62.868 199.194 57.768V56.268H189.714C185.334 56.268 182.874 57.888 182.874 61.368C182.874 64.368 185.454 66.408 189.534 66.408ZM216.601 70.248V39.648H220.861L221.521 43.788C223.321 41.448 226.321 39.288 231.121 39.288C237.601 39.288 243.001 42.948 243.001 52.848V70.248H238.081V53.148C238.081 47.028 235.201 43.788 230.281 43.788C224.941 43.788 221.521 47.928 221.521 53.988V70.248H216.601ZM266.348 82.608C258.548 82.608 253.088 78.948 252.308 72.228H257.348C258.188 76.068 261.608 78.228 266.708 78.228C273.128 78.228 276.608 75.228 276.608 68.568V64.968C274.568 68.448 271.268 70.608 266.108 70.608C257.648 70.608 251.408 64.908 251.408 54.948C251.408 45.588 257.648 39.288 266.108 39.288C271.268 39.288 274.688 41.508 276.608 44.928L277.268 39.648H281.528V68.748C281.528 77.568 276.848 82.608 266.348 82.608ZM266.588 66.228C272.588 66.228 276.668 61.608 276.668 55.068C276.668 48.348 272.588 43.668 266.588 43.668C260.528 43.668 256.448 48.288 256.448 54.948C256.448 61.608 260.528 66.228 266.588 66.228ZM304.875 70.608C295.935 70.608 290.055 64.548 290.055 55.008C290.055 45.648 296.115 39.288 304.995 39.288C312.495 39.288 317.235 43.488 318.495 50.208H313.335C312.435 46.128 309.435 43.668 304.935 43.668C299.055 43.668 295.095 48.348 295.095 55.008C295.095 61.668 299.055 66.228 304.935 66.228C309.315 66.228 312.315 63.708 313.275 59.808H318.495C317.295 66.408 312.315 70.608 304.875 70.608ZM328.042 70.248V28.248H332.962V43.788C335.242 40.968 338.782 39.288 342.742 39.288C350.422 39.288 354.802 44.388 354.802 53.208V70.248H349.882V53.508C349.882 47.268 347.002 43.788 341.902 43.788C336.442 43.788 332.962 48.108 332.962 54.948V70.248H328.042ZM375.209 70.608C368.489 70.608 363.929 67.248 363.929 61.668C363.929 55.548 368.189 52.128 376.229 52.128H385.229V50.028C385.229 46.068 382.409 43.668 377.609 43.668C373.289 43.668 370.409 45.708 369.809 48.828H364.889C365.609 42.828 370.469 39.288 377.849 39.288C385.649 39.288 390.149 43.188 390.149 50.328V63.708C390.149 65.328 390.749 65.748 392.129 65.748H393.689V70.248H390.989C386.909 70.248 385.529 68.508 385.469 65.508C383.549 68.268 380.489 70.608 375.209 70.608ZM375.569 66.408C381.689 66.408 385.229 62.868 385.229 57.768V56.268H375.749C371.369 56.268 368.909 57.888 368.909 61.368C368.909 64.368 371.489 66.408 375.569 66.408ZM403.476 70.248V65.748H414.276V44.148H403.476V39.648H419.196V65.748H429.996V70.248H403.476ZM416.796 34.248C414.576 34.248 412.836 32.568 412.836 30.288C412.836 28.068 414.576 26.388 416.796 26.388C419.016 26.388 420.756 28.068 420.756 30.288C420.756 32.568 419.016 34.248 416.796 34.248ZM439.843 70.248V39.648H444.103L444.763 43.788C446.563 41.448 449.563 39.288 454.363 39.288C460.843 39.288 466.243 42.948 466.243 52.848V70.248H461.323V53.148C461.323 47.028 458.443 43.788 453.523 43.788C448.183 43.788 444.763 47.928 444.763 53.988V70.248H439.843Z" fill="white"/>
-</svg>

.github/images/logo-light.svg

@@ -1,6 +0,0 @@
-<svg width="472" height="100" viewBox="0 0 472 100" fill="none" xmlns="http://www.w3.org/2000/svg">
-<rect width="100" height="100" rx="20" fill="#161F34"/>
-<path d="M54.2612 54.2583L63.1942 45.3253C67.8979 40.6215 67.8979 32.9952 63.1942 28.2914C58.4904 23.5877 50.8641 23.5877 46.1603 28.2914L37.2273 37.2244" stroke="#7FC8FF" stroke-width="12.0389"/>
-<path d="M45.7427 45.7411L36.8098 54.6741C32.106 59.3779 32.106 67.0042 36.8098 71.7079C41.5135 76.4117 49.1398 76.4117 53.8436 71.7079L62.7766 62.775" stroke="#7FC8FF" stroke-width="12.0389"/>
-<path d="M142.427 70.248V65.748H153.227V32.748H142.427V28.248H158.147V65.748H168.947V70.248H142.427ZM189.174 70.608C182.454 70.608 177.894 67.248 177.894 61.668C177.894 55.548 182.154 52.128 190.194 52.128H199.194V50.028C199.194 46.068 196.374 43.668 191.574 43.668C187.254 43.668 184.374 45.708 183.774 48.828H178.854C179.574 42.828 184.434 39.288 191.814 39.288C199.614 39.288 204.114 43.188 204.114 50.328V63.708C204.114 65.328 204.714 65.748 206.094 65.748H207.654V70.248H204.954C200.874 70.248 199.494 68.508 199.434 65.508C197.514 68.268 194.454 70.608 189.174 70.608ZM189.534 66.408C195.654 66.408 199.194 62.868 199.194 57.768V56.268H189.714C185.334 56.268 182.874 57.888 182.874 61.368C182.874 64.368 185.454 66.408 189.534 66.408ZM216.601 70.248V39.648H220.861L221.521 43.788C223.321 41.448 226.321 39.288 231.121 39.288C237.601 39.288 243.001 42.948 243.001 52.848V70.248H238.081V53.148C238.081 47.028 235.201 43.788 230.281 43.788C224.941 43.788 221.521 47.928 221.521 53.988V70.248H216.601ZM266.348 82.608C258.548 82.608 253.088 78.948 252.308 72.228H257.348C258.188 76.068 261.608 78.228 266.708 78.228C273.128 78.228 276.608 75.228 276.608 68.568V64.968C274.568 68.448 271.268 70.608 266.108 70.608C257.648 70.608 251.408 64.908 251.408 54.948C251.408 45.588 257.648 39.288 266.108 39.288C271.268 39.288 274.688 41.508 276.608 44.928L277.268 39.648H281.528V68.748C281.528 77.568 276.848 82.608 266.348 82.608ZM266.588 66.228C272.588 66.228 276.668 61.608 276.668 55.068C276.668 48.348 272.588 43.668 266.588 43.668C260.528 43.668 256.448 48.288 256.448 54.948C256.448 61.608 260.528 66.228 266.588 66.228ZM304.875 70.608C295.935 70.608 290.055 64.548 290.055 55.008C290.055 45.648 296.115 39.288 304.995 39.288C312.495 39.288 317.235 43.488 318.495 50.208H313.335C312.435 46.128 309.435 43.668 304.935 43.668C299.055 43.668 295.095 48.348 295.095 55.008C295.095 61.668 299.055 66.228 304.935 66.228C309.315 66.228 312.315 63.708 313.275 59.808H318.495C317.295 66.408 312.315 70.608 304.875 70.608ZM328.042 70.248V28.248H332.962V43.788C335.242 40.968 338.782 39.288 342.742 39.288C350.422 39.288 354.802 44.388 354.802 53.208V70.248H349.882V53.508C349.882 47.268 347.002 43.788 341.902 43.788C336.442 43.788 332.962 48.108 332.962 54.948V70.248H328.042ZM375.209 70.608C368.489 70.608 363.929 67.248 363.929 61.668C363.929 55.548 368.189 52.128 376.229 52.128H385.229V50.028C385.229 46.068 382.409 43.668 377.609 43.668C373.289 43.668 370.409 45.708 369.809 48.828H364.889C365.609 42.828 370.469 39.288 377.849 39.288C385.649 39.288 390.149 43.188 390.149 50.328V63.708C390.149 65.328 390.749 65.748 392.129 65.748H393.689V70.248H390.989C386.909 70.248 385.529 68.508 385.469 65.508C383.549 68.268 380.489 70.608 375.209 70.608ZM375.569 66.408C381.689 66.408 385.229 62.868 385.229 57.768V56.268H375.749C371.369 56.268 368.909 57.888 368.909 61.368C368.909 64.368 371.489 66.408 375.569 66.408ZM403.476 70.248V65.748H414.276V44.148H403.476V39.648H419.196V65.748H429.996V70.248H403.476ZM416.796 34.248C414.576 34.248 412.836 32.568 412.836 30.288C412.836 28.068 414.576 26.388 416.796 26.388C419.016 26.388 420.756 28.068 420.756 30.288C420.756 32.568 419.016 34.248 416.796 34.248ZM439.843 70.248V39.648H444.103L444.763 43.788C446.563 41.448 449.563 39.288 454.363 39.288C460.843 39.288 466.243 42.948 466.243 52.848V70.248H461.323V53.148C461.323 47.028 458.443 43.788 453.523 43.788C448.183 43.788 444.763 47.928 444.763 53.988V70.248H439.843Z" fill="#161F34"/>
-</svg>

.github/scripts/check_diff.py

@@ -1,247 +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/model-profiles",
+    "libs/experimental",
 ]
 
-# Packages with VCR cassette-backed integration tests.
-# These get a playback-only CI check to catch stale cassettes.
-VCR_PACKAGES = {
-    "libs/partners/openai",
-}
-
-# 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
-    "huggingface",
-]
-
-
-def all_package_dirs() -> Set[str]:
-    return {
-        "/".join(path.split("/")[:-1]).lstrip("./")
-        for path in glob.glob("./libs/**/pyproject.toml", recursive=True)
-        if "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":
-        # CPU simulation (<1% variance, Valgrind-based) is the default.
-        # Partners with heavy SDK inits use walltime instead to keep CI fast.
-        CODSPEED_WALLTIME_DIRS = {
-            "libs/core",
-            "libs/partners/fireworks",  # ~328s under simulation
-            "libs/partners/openai",  # 6 benchmarks, ~6 min under simulation
-        }
-        mode = "walltime" if dir_ in CODSPEED_WALLTIME_DIRS else "simulation"
-        return [
-            {
-                "working-directory": dir_,
-                "python-version": "3.13",
-                "codspeed-mode": mode,
-            }
-        ]
-    if dir_ == "libs/core":
-        py_versions = ["3.10", "3.11", "3.12", "3.13", "3.14"]
-    else:
-        py_versions = ["3.10", "3.14"]
-
-    return [{"working-directory": dir_, "python-version": py_v} for py_v in py_versions]
-
-
-def _get_pydantic_test_configs(
-    dir_: str, *, python_version: str = "3.12"
-) -> 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"])
-    elif job == "vcr-tests":
-        # Only run VCR tests for packages that have cassettes and are affected
-        all_affected = set(
-            add_dependents(
-                dirs_to_run["test"] | dirs_to_run["extended-test"], dependents
-            )
-        )
-        dirs = [d for d in VCR_PACKAGES if d in all_affected]
-    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:]
 
@@ -249,15 +18,12 @@ 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(
@@ -269,45 +35,33 @@ if __name__ == "__main__":
                 ".github/scripts/check_diff.py",
             )
         ):
-            # Infrastructure changes (workflows, actions, CI scripts) trigger tests on
-            # all core packages as a safety measure. This ensures that changes to CI/CD
-            # infrastructure don't inadvertently break package testing, even if the change
-            # appears unrelated (e.g., documentation build workflows). This is intentionally
-            # conservative to catch unexpected side effects from workflow modifications.
-            #
-            # Example: A PR modifying .github/workflows/api_doc_build.yml will trigger
-            # lint/test jobs for libs/core, libs/text-splitters, libs/langchain, and
-            # libs/langchain_v1, even though the workflow may only affect documentation.
+            # add all LANGCHAIN_DIRS for infra changes
             dirs_to_run["extended-test"].update(LANGCHAIN_DIRS)
+            dirs_to_run["lint"].add(".")
 
-        if file.startswith("libs/core"):
-            dirs_to_run["codspeed"].add("libs/core")
-        if file.startswith("libs/langchain_v1"):
-            dirs_to_run["codspeed"].add("libs/langchain_v1")
         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
+            # note: won't run on external repo partners
             dirs_to_run["lint"].add("libs/standard-tests")
-            dirs_to_run["test"].add("libs/standard-tests")
             dirs_to_run["test"].add("libs/partners/mistralai")
             dirs_to_run["test"].add("libs/partners/openai")
             dirs_to_run["test"].add("libs/partners/anthropic")
+            dirs_to_run["test"].add("libs/partners/ai21")
             dirs_to_run["test"].add("libs/partners/fireworks")
             dirs_to_run["test"].add("libs/partners/groq")
 
+        elif file.startswith("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 [
@@ -316,49 +70,25 @@ if __name__ == "__main__":
                 if not filename.startswith(".")
             ] != ["README.md"]:
                 dirs_to_run["test"].add(f"libs/partners/{partner_dir}")
-                # Only add to codspeed if the partner has benchmarks and is not ignored
-                if (
-                    partner_dir not in IGNORED_PARTNERS
-                    and os.path.isdir(
-                        f"libs/partners/{partner_dir}/tests/benchmarks"
-                    )
-                ):
-                    dirs_to_run["codspeed"].add(f"libs/partners/{partner_dir}")
             # Skip if the directory was deleted or is just a tombstone readme
         elif file.startswith("libs/"):
-            # Check if this is a root-level file in libs/ (e.g., libs/README.md)
-            file_parts = file.split("/")
-            if len(file_parts) == 2:
-                # Root-level file in libs/, skip it (no tests needed)
-                continue
             raise ValueError(
                 f"Unknown lib: {file}. check_diff.py likely needs "
                 "an update for this new library!"
             )
-        elif file in [
-            "pyproject.toml",
-            "uv.lock",
-        ]:  # root uv files
-            docs_edited = True
+        elif any(file.startswith(p) for p in ["docs/", "templates/", "cookbook/"]):
+            if file.startswith("docs/"):
+                docs_edited = True
+            dirs_to_run["lint"].add(".")
 
-    dependents = dependents_graph()
-
-    # we now have dirs_by_job
-    # todo: clean this up
-    map_job_to_configs = {
-        job: _get_configs_for_multi_dirs(job, dirs_to_run, dependents)
-        for job in [
-            "lint",
-            "test",
-            "extended-tests",
-            "compile-integration-tests",
-            "dependencies",
-            "test-pydantic",
-            "codspeed",
-            "vcr-tests",
-        ]
+    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"]),
+        "docs-edited": "true" 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

@@ -1,150 +1,65 @@
-"""Get minimum versions of dependencies from a pyproject.toml file."""
-
 import sys
-from collections import defaultdict
-
-if sys.version_info >= (3, 11):
-    import tomllib
-else:
-    # For Python 3.10 and below, which doesnt have stdlib tomllib
-    import tomli as tomllib
 
+import 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-community",
     "langchain",
     "langchain-text-splitters",
-    "numpy",
-    "SQLAlchemy",
-]
-
-# some libs only get checked on release because of simultaneous changes in
-# multiple libs
-SKIP_IF_PULL_REQUEST = [
-    "langchain-core",
-    "langchain-text-splitters",
-    "langchain",
 ]
 
 
-def get_pypi_versions(package_name: str) -> List[str]:
-    """Fetch all available versions for a package from PyPI.
+def get_min_version(version: str) -> str:
+    # base regex for x.x.x with cases for rc/post/etc
+    # valid strings: https://peps.python.org/pep-0440/#public-version-identifiers
+    vstring = r"\d+(?:\.\d+){0,2}(?:(?:a|b|rc|\.post|\.dev)\d+)?"
+    # case ^x.x.x
+    _match = re.match(f"^\\^({vstring})$", version)
+    if _match:
+        return _match.group(1)
 
-    Args:
-        package_name: Name of the package
+    # case >=x.x.x,<y.y.y
+    _match = re.match(f"^>=({vstring}),<({vstring})$", 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(f"^({vstring})$", 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, timeout=10.0)
-    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) -> str | None:
-    """Find the minimum published version that satisfies the given constraints.
-
-    Args:
-        package_name: Name of the package
-        spec_string: Version specification string (e.g., ">=0.2.43,<0.4.0,!=0.3.0")
-
-    Returns:
-        Minimum compatible version or None if no compatible version found
-    """
-    # Rewrite occurrences of ^0.0.z to 0.0.z (can be anywhere in constraint string)
-    spec_string = re.sub(r"\^0\.0\.(\d+)", r"0.0.\1", spec_string)
-    # Rewrite occurrences of ^0.y.z to >=0.y.z,<0.y+1 (can be anywhere in constraint string)
-    for y in range(1, 10):
-        spec_string = re.sub(
-            rf"\^0\.{y}\.(\d+)", rf">=0.{y}.\1,<0.{y + 1}", spec_string
-        )
-    # Rewrite occurrences of ^x.y.z to >=x.y.z,<x+1.0.0 (can be anywhere in constraint string)
-    for x in range(1, 10):
-        spec_string = re.sub(
-            rf"\^{x}\.(\d+)\.(\d+)", rf">={x}.\1.\2,<{x + 1}", spec_string
-        )
-
-    spec_set = SpecifierSet(spec_string)
-    all_versions = get_pypi_versions(package_name)
-
-    valid_versions = []
-    for version_str in all_versions:
-        try:
-            version = parse(version_str)
-            if spec_set.contains(version):
-                valid_versions.append(version)
-        except ValueError:
-            continue
-
-    return str(min(valid_versions)) if valid_versions else None
-
-
-def _check_python_version_from_requirement(
-    requirement: Requirement, python_version: str
-) -> bool:
-    if not requirement.marker:
-        return True
-    else:
-        marker_str = str(requirement.marker)
-        if "python_version" in marker_str or "python_full_version" in marker_str:
-            python_version_str = "".join(
-                char
-                for char in marker_str
-                if char.isdigit() or char in (".", "<", ">", "=", ",")
-            )
-            return check_python_version(python_version, python_version_str)
-        return True
-
-
-def get_min_version_from_toml(
-    toml_path: str,
-    versions_for: str,
-    python_version: str,
-    *,
-    include: list | None = None,
-):
+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]
+
+            if isinstance(version_string, dict):
+                version_string = version_string["version"]
 
             # 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
@@ -152,48 +67,13 @@ 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.
-
-    Args:
-        version_string: A string representing the Python version (e.g. "3.8.5").
-        constraint_string: A string representing the package's Python version
-            constraints (e.g. ">=3.6, <4.0").
-
-    Returns:
-        True if the version matches the constraints
-    """
-
-    # Rewrite occurrences of ^0.0.z to 0.0.z (can be anywhere in constraint string)
-    constraint_string = re.sub(r"\^0\.0\.(\d+)", r"0.0.\1", constraint_string)
-    # Rewrite occurrences of ^0.y.z to >=0.y.z,<0.y+1.0 (can be anywhere in constraint string)
-    for y in range(1, 10):
-        constraint_string = re.sub(
-            rf"\^0\.{y}\.(\d+)", rf">=0.{y}.\1,<0.{y + 1}.0", constraint_string
-        )
-    # Rewrite occurrences of ^x.y.z to >=x.y.z,<x+1.0.0 (can be anywhere in constraint string)
-    for x in range(1, 10):
-        constraint_string = re.sub(
-            rf"\^{x}\.0\.(\d+)", rf">={x}.0.\1,<{x + 1}.0.0", constraint_string
-        )
-
-    try:
-        version = Version(version_string)
-        constraints = SpecifierSet(constraint_string)
-        return version in constraints
-    except Exception as e:
-        print(f"Error: {e}")
-        return False
-
-
 if __name__ == "__main__":
     # Get the TOML file path from the command line argument
     toml_file = sys.argv[1]
-    versions_for = sys.argv[2]
-    python_version = sys.argv[3]
-    assert versions_for in ["release", "pull_request"]
 
     # Call the function to get the minimum versions
-    min_versions = get_min_version_from_toml(toml_file, versions_for, python_version)
+    min_versions = get_min_version_from_toml(toml_file)
 
-    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/pr-labeler-config.json

@@ -1,84 +0,0 @@
-{
-  "trustedThreshold": 5,
-  "labelColor": "b76e79",
-  "sizeThresholds": [
-    { "label": "size: XS", "max": 50 },
-    { "label": "size: S", "max": 200 },
-    { "label": "size: M", "max": 500 },
-    { "label": "size: L", "max": 1000 },
-    { "label": "size: XL" }
-  ],
-  "excludedFiles": ["uv.lock"],
-  "excludedPaths": ["docs/"],
-  "typeToLabel": {
-    "feat": "feature",
-    "fix": "fix",
-    "docs": "documentation",
-    "style": "linting",
-    "refactor": "refactor",
-    "perf": "performance",
-    "test": "tests",
-    "build": "infra",
-    "ci": "infra",
-    "chore": "infra",
-    "revert": "revert",
-    "release": "release",
-    "hotfix": "hotfix",
-    "breaking": "breaking"
-  },
-  "scopeToLabel": {
-    "core": "core",
-    "langchain": "langchain",
-    "langchain-classic": "langchain-classic",
-    "model-profiles": "model-profiles",
-    "standard-tests": "standard-tests",
-    "text-splitters": "text-splitters",
-    "anthropic": "anthropic",
-    "chroma": "chroma",
-    "deepseek": "deepseek",
-    "exa": "exa",
-    "fireworks": "fireworks",
-    "groq": "groq",
-    "huggingface": "huggingface",
-    "mistralai": "mistralai",
-    "nomic": "nomic",
-    "ollama": "ollama",
-    "openai": "openai",
-    "openrouter": "openrouter",
-    "perplexity": "perplexity",
-    "qdrant": "qdrant",
-    "xai": "xai",
-    "deps": "dependencies",
-    "docs": "documentation",
-    "infra": "infra"
-  },
-  "fileRules": [
-    { "label": "core", "prefix": "libs/core/", "skipExcludedFiles": true },
-    { "label": "langchain-classic", "prefix": "libs/langchain/", "skipExcludedFiles": true },
-    { "label": "langchain", "prefix": "libs/langchain_v1/", "skipExcludedFiles": true },
-    { "label": "standard-tests", "prefix": "libs/standard-tests/", "skipExcludedFiles": true },
-    { "label": "model-profiles", "prefix": "libs/model-profiles/", "skipExcludedFiles": true },
-    { "label": "text-splitters", "prefix": "libs/text-splitters/", "skipExcludedFiles": true },
-    { "label": "integration", "prefix": "libs/partners/", "skipExcludedFiles": true },
-    { "label": "anthropic", "prefix": "libs/partners/anthropic/", "skipExcludedFiles": true },
-    { "label": "chroma", "prefix": "libs/partners/chroma/", "skipExcludedFiles": true },
-    { "label": "deepseek", "prefix": "libs/partners/deepseek/", "skipExcludedFiles": true },
-    { "label": "exa", "prefix": "libs/partners/exa/", "skipExcludedFiles": true },
-    { "label": "fireworks", "prefix": "libs/partners/fireworks/", "skipExcludedFiles": true },
-    { "label": "groq", "prefix": "libs/partners/groq/", "skipExcludedFiles": true },
-    { "label": "huggingface", "prefix": "libs/partners/huggingface/", "skipExcludedFiles": true },
-    { "label": "mistralai", "prefix": "libs/partners/mistralai/", "skipExcludedFiles": true },
-    { "label": "nomic", "prefix": "libs/partners/nomic/", "skipExcludedFiles": true },
-    { "label": "ollama", "prefix": "libs/partners/ollama/", "skipExcludedFiles": true },
-    { "label": "openai", "prefix": "libs/partners/openai/", "skipExcludedFiles": true },
-    { "label": "openrouter", "prefix": "libs/partners/openrouter/", "skipExcludedFiles": true },
-    { "label": "perplexity", "prefix": "libs/partners/perplexity/", "skipExcludedFiles": true },
-    { "label": "qdrant", "prefix": "libs/partners/qdrant/", "skipExcludedFiles": true },
-    { "label": "xai", "prefix": "libs/partners/xai/", "skipExcludedFiles": true },
-    { "label": "github_actions", "prefix": ".github/workflows/" },
-    { "label": "github_actions", "prefix": ".github/actions/" },
-    { "label": "dependencies", "suffix": "pyproject.toml" },
-    { "label": "dependencies", "exact": "uv.lock" },
-    { "label": "dependencies", "pattern": "(?:^|/)requirements[^/]*\\.txt$" }
-  ]
-}

.github/scripts/pr-labeler.js

@@ -1,278 +0,0 @@
-// Shared helpers for pr_labeler.yml and tag-external-issues.yml.
-//
-// Usage from actions/github-script (requires actions/checkout first):
-//   const { h } = require('./.github/scripts/pr-labeler.js').loadAndInit(github, owner, repo, core);
-
-const fs = require('fs');
-const path = require('path');
-
-function loadConfig() {
-  const configPath = path.join(__dirname, 'pr-labeler-config.json');
-  let raw;
-  try {
-    raw = fs.readFileSync(configPath, 'utf8');
-  } catch (e) {
-    throw new Error(`Failed to read ${configPath}: ${e.message}`);
-  }
-  let config;
-  try {
-    config = JSON.parse(raw);
-  } catch (e) {
-    throw new Error(`Failed to parse pr-labeler-config.json: ${e.message}`);
-  }
-  const required = [
-    'labelColor', 'sizeThresholds', 'fileRules',
-    'typeToLabel', 'scopeToLabel', 'trustedThreshold',
-    'excludedFiles', 'excludedPaths',
-  ];
-  const missing = required.filter(k => !(k in config));
-  if (missing.length > 0) {
-    throw new Error(`pr-labeler-config.json missing required keys: ${missing.join(', ')}`);
-  }
-  return config;
-}
-
-function init(github, owner, repo, config, core) {
-  if (!core) {
-    throw new Error('init() requires a `core` parameter (e.g., from actions/github-script)');
-  }
-  const {
-    trustedThreshold,
-    labelColor,
-    sizeThresholds,
-    scopeToLabel,
-    typeToLabel,
-    fileRules: fileRulesDef,
-    excludedFiles,
-    excludedPaths,
-  } = config;
-
-  const sizeLabels = sizeThresholds.map(t => t.label);
-  const allTypeLabels = [...new Set(Object.values(typeToLabel))];
-  const tierLabels = ['new-contributor', 'trusted-contributor'];
-
-  // ── Label management ──────────────────────────────────────────────
-
-  async function ensureLabel(name, color = labelColor) {
-    try {
-      await github.rest.issues.getLabel({ owner, repo, name });
-    } catch (e) {
-      if (e.status !== 404) throw e;
-      try {
-        await github.rest.issues.createLabel({ owner, repo, name, color });
-      } catch (createErr) {
-        // 422 = label created by a concurrent run between our get and create
-        if (createErr.status !== 422) throw createErr;
-        core.info(`Label "${name}" creation returned 422 (likely already exists)`);
-      }
-    }
-  }
-
-  // ── Size calculation ──────────────────────────────────────────────
-
-  function getSizeLabel(totalChanged) {
-    for (const t of sizeThresholds) {
-      if (t.max != null && totalChanged < t.max) return t.label;
-    }
-    // Last entry has no max — it's the catch-all
-    return sizeThresholds[sizeThresholds.length - 1].label;
-  }
-
-  function computeSize(files) {
-    const excluded = new Set(excludedFiles);
-    const totalChanged = files.reduce((sum, f) => {
-      const p = f.filename ?? '';
-      const base = p.split('/').pop();
-      if (excluded.has(base)) return sum;
-      for (const prefix of excludedPaths) {
-        if (p.startsWith(prefix)) return sum;
-      }
-      return sum + (f.additions ?? 0) + (f.deletions ?? 0);
-    }, 0);
-    return { totalChanged, sizeLabel: getSizeLabel(totalChanged) };
-  }
-
-  // ── File-based labels ─────────────────────────────────────────────
-
-  function buildFileRules() {
-    return fileRulesDef.map((rule, i) => {
-      let test;
-      if (rule.prefix) test = p => p.startsWith(rule.prefix);
-      else if (rule.suffix) test = p => p.endsWith(rule.suffix);
-      else if (rule.exact) test = p => p === rule.exact;
-      else if (rule.pattern) {
-        const re = new RegExp(rule.pattern);
-        test = p => re.test(p);
-      } else {
-        throw new Error(
-          `fileRules[${i}] (label: "${rule.label}") has no recognized matcher ` +
-          `(expected one of: prefix, suffix, exact, pattern)`
-        );
-      }
-      return { label: rule.label, test, skipExcluded: !!rule.skipExcludedFiles };
-    });
-  }
-
-  function matchFileLabels(files, fileRules) {
-    const rules = fileRules || buildFileRules();
-    const excluded = new Set(excludedFiles);
-    const labels = new Set();
-    for (const rule of rules) {
-      // skipExcluded: ignore files whose basename is in the top-level
-      // "excludedFiles" list (e.g. uv.lock) so lockfile-only changes
-      // don't trigger package labels.
-      const candidates = rule.skipExcluded
-        ? files.filter(f => !excluded.has((f.filename ?? '').split('/').pop()))
-        : files;
-      if (candidates.some(f => rule.test(f.filename ?? ''))) {
-        labels.add(rule.label);
-      }
-    }
-    return labels;
-  }
-
-  // ── Title-based labels ────────────────────────────────────────────
-
-  function matchTitleLabels(title) {
-    const labels = new Set();
-    const m = (title ?? '').match(/^(\w+)(?:\(([^)]+)\))?(!)?:/);
-    if (!m) return { labels, type: null, typeLabel: null, scopes: [], breaking: false };
-
-    const type = m[1].toLowerCase();
-    const scopeStr = m[2] ?? '';
-    const breaking = !!m[3];
-
-    const typeLabel = typeToLabel[type] || null;
-    if (typeLabel) labels.add(typeLabel);
-    if (breaking) labels.add('breaking');
-
-    const scopes = scopeStr.split(',').map(s => s.trim()).filter(Boolean);
-    for (const scope of scopes) {
-      const sl = scopeToLabel[scope];
-      if (sl) labels.add(sl);
-    }
-
-    return { labels, type, typeLabel, scopes, breaking };
-  }
-
-  // ── Org membership ────────────────────────────────────────────────
-
-  async function checkMembership(author, userType) {
-    if (userType === 'Bot') {
-      console.log(`${author} is a Bot — treating as internal`);
-      return { isExternal: false };
-    }
-
-    try {
-      const membership = await github.rest.orgs.getMembershipForUser({
-        org: 'langchain-ai',
-        username: author,
-      });
-      const isExternal = membership.data.state !== 'active';
-      console.log(
-        isExternal
-          ? `${author} has pending membership — treating as external`
-          : `${author} is an active member of langchain-ai`,
-      );
-      return { isExternal };
-    } catch (e) {
-      if (e.status === 404) {
-        console.log(`${author} is not a member of langchain-ai`);
-        return { isExternal: true };
-      }
-      // Non-404 errors (rate limit, auth failure, server error) must not
-      // silently default to external — rethrow to fail the step.
-      throw new Error(
-        `Membership check failed for ${author} (${e.status}): ${e.message}`,
-      );
-    }
-  }
-
-  // ── Contributor analysis ──────────────────────────────────────────
-
-  async function getContributorInfo(contributorCache, author, userType) {
-    if (contributorCache.has(author)) return contributorCache.get(author);
-
-    const { isExternal } = await checkMembership(author, userType);
-
-    let mergedCount = null;
-    if (isExternal) {
-      try {
-        const result = await github.rest.search.issuesAndPullRequests({
-          q: `repo:${owner}/${repo} is:pr is:merged author:"${author}"`,
-          per_page: 1,
-        });
-        mergedCount = result?.data?.total_count ?? null;
-      } catch (e) {
-        if (e?.status !== 422) throw e;
-        core.warning(`Search failed for ${author}; skipping tier.`);
-      }
-    }
-
-    const info = { isExternal, mergedCount };
-    contributorCache.set(author, info);
-    return info;
-  }
-
-  // ── Tier label resolution ───────────────────────────────────────────
-
-  async function applyTierLabel(issueNumber, author, { skipNewContributor = false } = {}) {
-    let mergedCount;
-    try {
-      const result = await github.rest.search.issuesAndPullRequests({
-        q: `repo:${owner}/${repo} is:pr is:merged author:"${author}"`,
-        per_page: 1,
-      });
-      mergedCount = result?.data?.total_count;
-    } catch (error) {
-      if (error?.status !== 422) throw error;
-      core.warning(`Search failed for ${author}; skipping tier label.`);
-      return;
-    }
-
-    if (mergedCount == null) {
-      core.warning(`Search response missing total_count for ${author}; skipping tier label.`);
-      return;
-    }
-
-    let tierLabel = null;
-    if (mergedCount >= trustedThreshold) tierLabel = 'trusted-contributor';
-    else if (mergedCount === 0 && !skipNewContributor) tierLabel = 'new-contributor';
-
-    if (tierLabel) {
-      await ensureLabel(tierLabel);
-      await github.rest.issues.addLabels({
-        owner, repo, issue_number: issueNumber, labels: [tierLabel],
-      });
-      console.log(`Applied '${tierLabel}' to #${issueNumber} (${mergedCount} merged PRs)`);
-    } else {
-      console.log(`No tier label for ${author} (${mergedCount} merged PRs)`);
-    }
-
-    return tierLabel;
-  }
-
-  return {
-    ensureLabel,
-    getSizeLabel,
-    computeSize,
-    buildFileRules,
-    matchFileLabels,
-    matchTitleLabels,
-    allTypeLabels,
-    checkMembership,
-    getContributorInfo,
-    applyTierLabel,
-    sizeLabels,
-    tierLabels,
-    trustedThreshold,
-    labelColor,
-  };
-}
-
-function loadAndInit(github, owner, repo, core) {
-  const config = loadConfig();
-  return { config, h: init(github, owner, repo, config, core) };
-}
-
-module.exports = { loadConfig, init, loadAndInit };

.github/scripts/test_release_options.py

@@ -1,48 +0,0 @@
-"""Verify _release.yml dropdown options match actual package directories."""
-
-from pathlib import Path
-
-import yaml
-
-REPO_ROOT = Path(__file__).resolve().parents[2]
-
-
-def _get_release_options() -> list[str]:
-    workflow = REPO_ROOT / ".github" / "workflows" / "_release.yml"
-    with open(workflow) as f:
-        data = yaml.safe_load(f)
-    try:
-        # PyYAML (YAML 1.1) parses the bare key `on` as boolean True
-        return data[True]["workflow_dispatch"]["inputs"]["working-directory"]["options"]
-    except (KeyError, TypeError) as e:
-        msg = f"Could not find workflow_dispatch options in {workflow}: {e}"
-        raise AssertionError(msg) from e
-
-
-def _get_package_dirs() -> set[str]:
-    libs = REPO_ROOT / "libs"
-    dirs: set[str] = set()
-    # Top-level packages (libs/core, libs/langchain, etc.)
-    for p in libs.iterdir():
-        if p.is_dir() and (p / "pyproject.toml").exists():
-            dirs.add(f"libs/{p.name}")
-    # Partner packages (libs/partners/*)
-    partners = libs / "partners"
-    if partners.exists():
-        for p in partners.iterdir():
-            if p.is_dir() and (p / "pyproject.toml").exists():
-                dirs.add(f"libs/partners/{p.name}")
-    return dirs
-
-
-def test_release_options_match_packages() -> None:
-    options = set(_get_release_options())
-    packages = _get_package_dirs()
-    missing_from_dropdown = packages - options
-    extra_in_dropdown = options - packages
-    assert not missing_from_dropdown, (
-        f"Packages on disk missing from _release.yml dropdown: {missing_from_dropdown}"
-    )
-    assert not extra_in_dropdown, (
-        f"Dropdown options with no matching package directory: {extra_in_dropdown}"
-    )

.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@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+      - 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 +1,117 @@
+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: ${{ !startsWith(inputs.working-directory, 'libs/partners/airbyte') }}
+        shell: bash
+        run: make test
+
+      - name: Ensure the tests did not create any additional files
+        shell: bash
+        run: |
+          set -eu
+
+          STATUS="$(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

@@ -0,0 +1,95 @@
+name: Integration tests
+
+on:
+  workflow_dispatch:
+    inputs:
+      working-directory:
+        required: true
+        type: string
+
+env:
+  POETRY_VERSION: "1.7.1"
+
+jobs:
+  build:
+    environment: Scheduled testing
+    defaults:
+      run:
+        working-directory: ${{ inputs.working-directory }}
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.11"
+    name: Python ${{ matrix.python-version }}
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
+        with:
+          python-version: ${{ matrix.python-version }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: ${{ inputs.working-directory }}
+          cache-key: core
+
+      - name: Install dependencies
+        shell: bash
+        run: poetry install --with test,test_integration
+
+      - name: Install deps outside pyproject
+        if: ${{ startsWith(inputs.working-directory, 'libs/community/') }}
+        shell: bash
+        run: poetry run pip install "boto3<2" "google-cloud-aiplatform<2"
+
+      - name: 'Authenticate to Google Cloud'
+        id: 'auth'
+        uses: google-github-actions/auth@v2
+        with:
+          credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
+
+      - name: Run integration tests
+        shell: bash
+        env:
+          AI21_API_KEY: ${{ secrets.AI21_API_KEY }}
+          GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
+          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+          MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
+          TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
+          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+          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 }}
+          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 }}
+          VOYAGE_API_KEY: ${{ secrets.VOYAGE_API_KEY }}
+          COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
+          UPSTAGE_API_KEY: ${{ secrets.UPSTAGE_API_KEY }}
+        run: |
+          make integration_tests
+
+      - name: Ensure the tests did not create any additional files
+        shell: bash
+        run: |
+          set -eu
+
+          STATUS="$(git status)"
+          echo "$STATUS"
+
+          # grep will exit non-zero if the target message isn't found,
+          # and `set -e` above will cause the step to fail.
+          echo "$STATUS" | grep 'nothing to commit, working tree clean'

.github/workflows/_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:
@@ -14,68 +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@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+      - 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: "🔒 Verify Lockfile is Up-to-Date"
-      #   working-directory: ${{ inputs.working-directory }}
-      #   run: |
-      #     unset UV_FROZEN
-      #     uv lock --check
-
-      - 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/_refresh_model_profiles.yml

@@ -1,202 +0,0 @@
-# Reusable workflow: refreshes model profile data for any repo that uses the
-# `langchain-profiles` CLI. Creates (or updates) a pull request with the
-# resulting changes.
-#
-# Callers MUST set `permissions: { contents: write, pull-requests: write }` —
-# reusable workflows cannot escalate the caller's token permissions.
-#
-# ── Example: external repo (langchain-google) ──────────────────────────
-#
-#   jobs:
-#     refresh-profiles:
-#       uses: langchain-ai/langchain/.github/workflows/_refresh_model_profiles.yml@master
-#       with:
-#         providers: >-
-#           [
-#             {"provider":"google",        "data_dir":"libs/genai/langchain_google_genai/data"},
-#           ]
-#       secrets:
-#         MODEL_PROFILE_BOT_APP_ID:      ${{ secrets.MODEL_PROFILE_BOT_APP_ID }}
-#         MODEL_PROFILE_BOT_PRIVATE_KEY: ${{ secrets.MODEL_PROFILE_BOT_PRIVATE_KEY }}
-
-name: "Refresh Model Profiles (reusable)"
-
-on:
-  workflow_call:
-    inputs:
-      providers:
-        description: >-
-          JSON array of objects, each with `provider` (models.dev provider ID)
-          and `data_dir` (path relative to repo root where `_profiles.py` and
-          `profile_augmentations.toml` live).
-        required: true
-        type: string
-      cli-path:
-        description: >-
-          Path (relative to workspace) to an existing `libs/model-profiles`
-          checkout.  When set the workflow skips cloning the langchain repo and
-          uses this directory for the CLI instead.  Useful when the caller IS
-          the langchain monorepo.
-        required: false
-        type: string
-        default: ""
-      cli-ref:
-        description: >-
-          Git ref of langchain-ai/langchain to checkout for the CLI.
-          Ignored when `cli-path` is set.
-        required: false
-        type: string
-        default: master
-      add-paths:
-        description: "Glob for files to stage in the PR commit."
-        required: false
-        type: string
-        default: "**/_profiles.py"
-      pr-branch:
-        description: "Branch name for the auto-created PR."
-        required: false
-        type: string
-        default: bot/refresh-model-profiles
-      pr-title:
-        description: "PR / commit title."
-        required: false
-        type: string
-        default: "chore(model-profiles): refresh model profile data"
-      pr-body:
-        description: "PR body."
-        required: false
-        type: string
-        default: |
-          Automated refresh of model profile data via `langchain-profiles refresh`.
-
-          🤖 Generated by the `refresh_model_profiles` workflow.
-      pr-labels:
-        description: "Comma-separated labels to apply to the PR."
-        required: false
-        type: string
-        default: bot
-    secrets:
-      MODEL_PROFILE_BOT_APP_ID:
-        required: true
-      MODEL_PROFILE_BOT_PRIVATE_KEY:
-        required: true
-
-permissions:
-  contents: write
-  pull-requests: write
-
-jobs:
-  refresh-profiles:
-    name: refresh model profiles
-    runs-on: ubuntu-latest
-    steps:
-      - name: "📋 Checkout"
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-
-      - name: "📋 Checkout langchain-profiles CLI"
-        if: inputs.cli-path == ''
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-        with:
-          repository: langchain-ai/langchain
-          ref: ${{ inputs.cli-ref }}
-          sparse-checkout: libs/model-profiles
-          path: _langchain-cli
-
-      - name: "🔧 Resolve CLI directory"
-        id: cli
-        env:
-          CLI_PATH: ${{ inputs.cli-path }}
-        run: |
-          if [ -n "${CLI_PATH}" ]; then
-            resolved="${GITHUB_WORKSPACE}/${CLI_PATH}"
-            if [ ! -d "${resolved}" ]; then
-              echo "::error::cli-path '${CLI_PATH}' does not exist at ${resolved}"
-              exit 1
-            fi
-            echo "dir=${CLI_PATH}" >> "$GITHUB_OUTPUT"
-          else
-            echo "dir=_langchain-cli/libs/model-profiles" >> "$GITHUB_OUTPUT"
-          fi
-
-      - name: "🐍 Set up Python + uv"
-        uses: astral-sh/setup-uv@0ca8f610542aa7f4acaf39e65cf4eb3c35091883 # v7
-        with:
-          version: "0.5.25"
-          python-version: "3.12"
-          enable-cache: true
-          cache-dependency-glob: "**/model-profiles/uv.lock"
-
-      - name: "📦 Install langchain-profiles CLI"
-        working-directory: ${{ steps.cli.outputs.dir }}
-        run: uv sync --frozen --no-group test --no-group dev --no-group lint
-
-      - name: "✅ Validate providers input"
-        env:
-          PROVIDERS_JSON: ${{ inputs.providers }}
-        run: |
-          echo "${PROVIDERS_JSON}" | jq -e 'type == "array" and length > 0' > /dev/null || {
-            echo "::error::providers input must be a non-empty JSON array"
-            exit 1
-          }
-          echo "${PROVIDERS_JSON}" | jq -e 'all(has("provider") and has("data_dir"))' > /dev/null || {
-            echo "::error::every entry in providers must have 'provider' and 'data_dir' keys"
-            exit 1
-          }
-
-      - name: "🔄 Refresh profiles"
-        env:
-          PROVIDERS_JSON: ${{ inputs.providers }}
-        run: |
-          cli_dir="${GITHUB_WORKSPACE}/${{ steps.cli.outputs.dir }}"
-          failed=""
-          mapfile -t rows < <(echo "${PROVIDERS_JSON}" | jq -c '.[]')
-          for row in "${rows[@]}"; do
-            provider=$(echo "${row}" | jq -r '.provider')
-            data_dir=$(echo "${row}" | jq -r '.data_dir')
-            echo "--- Refreshing ${provider} -> ${data_dir} ---"
-            if ! echo y | uv run --frozen --project "${cli_dir}" \
-              langchain-profiles refresh \
-              --provider "${provider}" \
-              --data-dir "${GITHUB_WORKSPACE}/${data_dir}"; then
-              echo "::error::Failed to refresh provider: ${provider}"
-              failed="${failed} ${provider}"
-            fi
-          done
-          if [ -n "${failed}" ]; then
-            echo "::error::The following providers failed:${failed}"
-            exit 1
-          fi
-
-      - name: "🔑 Generate GitHub App token"
-        id: app-token
-        uses: actions/create-github-app-token@f8d387b68d61c58ab83c6c016672934102569859 # v3
-        with:
-          app-id: ${{ secrets.MODEL_PROFILE_BOT_APP_ID }}
-          private-key: ${{ secrets.MODEL_PROFILE_BOT_PRIVATE_KEY }}
-
-      - name: "🔀 Create pull request"
-        id: create-pr
-        uses: peter-evans/create-pull-request@c0f553fe549906ede9cf27b5156039d195d2ece0 # v8
-        with:
-          token: ${{ steps.app-token.outputs.token }}
-          branch: ${{ inputs.pr-branch }}
-          commit-message: ${{ inputs.pr-title }}
-          title: ${{ inputs.pr-title }}
-          body: ${{ inputs.pr-body }}
-          labels: ${{ inputs.pr-labels }}
-          add-paths: ${{ inputs.add-paths }}
-
-      - name: "📝 Summary"
-        if: always()
-        env:
-          PR_OP: ${{ steps.create-pr.outputs.pull-request-operation }}
-          PR_URL: ${{ steps.create-pr.outputs.pull-request-url }}
-          JOB_STATUS: ${{ job.status }}
-        run: |
-          if [ "${PR_OP}" = "created" ] || [ "${PR_OP}" = "updated" ]; then
-            echo "### ✅ PR ${PR_OP}: ${PR_URL}" >> "$GITHUB_STEP_SUMMARY"
-          elif [ -z "${PR_OP}" ] && [ "${JOB_STATUS}" = "success" ]; then
-            echo "### ⏭️ Skipped: profiles already up to date" >> "$GITHUB_STEP_SUMMARY"
-          elif [ "${JOB_STATUS}" = "failure" ]; then
-            echo "### ❌ Job failed — check step logs for details" >> "$GITHUB_STEP_SUMMARY"
-          fi

.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-override || inputs.working-directory }} ${{ inputs.release-version }}"
+name: release
+run-name: Release ${{ inputs.working-directory }} by @${{ github.actor }}
 on:
   workflow_call:
     inputs:
@@ -17,82 +11,38 @@ on:
     inputs:
       working-directory:
         required: true
-        type: choice
-        description: "From which folder this pipeline executes"
-        default: "libs/langchain_v1"
-        options:
-          - libs/core
-          - libs/langchain
-          - libs/langchain_v1
-          - libs/text-splitters
-          - libs/standard-tests
-          - libs/model-profiles
-          - libs/partners/anthropic
-          - libs/partners/chroma
-          - libs/partners/deepseek
-          - libs/partners/exa
-          - libs/partners/fireworks
-          - libs/partners/groq
-          - libs/partners/huggingface
-          - libs/partners/mistralai
-          - libs/partners/nomic
-          - libs/partners/ollama
-          - libs/partners/openai
-          - libs/partners/openrouter
-          - libs/partners/perplexity
-          - libs/partners/qdrant
-          - libs/partners/xai
-      working-directory-override:
-        required: false
         type: string
-        description: "Manual override — takes precedence over dropdown (e.g. libs/partners/partner-xyz)"
-      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"
+        default: 'libs/langchain'
 
 env:
   PYTHON_VERSION: "3.11"
-  UV_FROZEN: "true"
-  UV_NO_SYNC: "true"
-  EFFECTIVE_WORKING_DIR: ${{ inputs.working-directory-override || inputs.working-directory }}
-
-permissions:
-  contents: read # Job-level overrides grant write only where needed (mark-release)
+  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
-    permissions:
-      contents: read
 
     outputs:
       pkg-name: ${{ steps.check-version.outputs.pkg-name }}
       version: ${{ steps.check-version.outputs.version }}
 
     steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+      - 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,
-      # which the build stage must not have access to.)
-      #
+      # 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.
       #
@@ -101,175 +51,39 @@ jobs:
       # > from the publish job.
       # https://github.com/pypa/gh-action-pypi-publish#non-goals
       - name: Build project for distribution
-        run: uv build
-        working-directory: ${{ env.EFFECTIVE_WORKING_DIR }}
+        run: poetry build
+        working-directory: ${{ inputs.working-directory }}
 
       - name: Upload build
-        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7
+        uses: actions/upload-artifact@v4
         with:
           name: dist
-          path: ${{ env.EFFECTIVE_WORKING_DIR }}/dist/
+          path: ${{ inputs.working-directory }}/dist/
 
-      - name: Check version
+      - name: Check Version
         id: check-version
-        shell: python
-        working-directory: ${{ env.EFFECTIVE_WORKING_DIR }}
-        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:
-    # release-notes must run before publishing because its check-tags step
-    # validates version/tag state — do not remove this dependency.
-    needs:
-      - build
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-    outputs:
-      release-body: ${{ steps.generate-release-body.outputs.release-body }}
-    steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-        with:
-          repository: langchain-ai/langchain
-          path: langchain
-          sparse-checkout: | # this only grabs files for relevant dir
-            ${{ env.EFFECTIVE_WORKING_DIR }}
-          ref: ${{ github.ref }} # this scopes to just ref'd branch
-          fetch-depth: 0 # this fetches entire commit history
-      - name: Check tags
-        id: check-tags
         shell: bash
-        working-directory: langchain/${{ env.EFFECTIVE_WORKING_DIR }}
-        env:
-          PKG_NAME: ${{ needs.build.outputs.pkg-name }}
-          VERSION: ${{ needs.build.outputs.version }}
+        working-directory: ${{ inputs.working-directory }}
         run: |
-          # Handle regular versions and pre-release versions differently
-          if [[ "$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 $REGEX || true) | head -1)
-            fi
-          fi
-
-          # if PREV_TAG is empty or came out to 0.0.0, let it be empty
-          if [ -z "$PREV_TAG" ] || [ "$PREV_TAG" = "$PKG_NAME==0.0.0" ]; 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: ${{ env.EFFECTIVE_WORKING_DIR }}
-          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 $PREV_TAG"
-          # if PREV_TAG is empty or 0.0.0, then we are releasing the first version
-          if [ -z "$PREV_TAG" ] || [ "$PREV_TAG" = "$PKG_NAME==0.0.0" ]; 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:
-    # release-notes must run before publishing because its check-tags step
-    # validates version/tag state — do not remove this dependency.
     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@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-
-      - uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
-        with:
-          name: dist
-          path: ${{ env.EFFECTIVE_WORKING_DIR }}/dist/
-
-      - name: Publish to test PyPI
-        uses: pypa/gh-action-pypi-publish@ed0c53931b1dc9bd32cbe73a98c7f6766f8a527e # release/v1
-        with:
-          packages-dir: ${{ env.EFFECTIVE_WORKING_DIR }}/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
-    permissions:
-      contents: read
-    timeout-minutes: 20
     steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+      - uses: actions/checkout@v4
 
       # We explicitly *don't* set up caching here. This ensures our tests are
       # maximally sensitive to catching breakage.
@@ -284,68 +98,71 @@ 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@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
-        with:
-          name: dist
-          path: ${{ env.EFFECTIVE_WORKING_DIR }}/dist/
-
-      - name: Import dist package
+      - name: Import published package
         shell: bash
-        working-directory: ${{ env.EFFECTIVE_WORKING_DIR }}
+        working-directory: ${{ inputs.working-directory }}
         env:
           PKG_NAME: ${{ needs.build.outputs.pkg-name }}
           VERSION: ${{ needs.build.outputs.version }}
-        # Install directly from the locally-built wheel (no index resolution needed)
+        # Here we use:
+        # - The default regular PyPI index as the *primary* index, meaning
+        #   that it takes priority (https://pypi.org/simple)
+        # - The test PyPI index as an extra index, so that any dependencies that
+        #   are not found on test PyPI can be resolved and installed anyway.
+        #   (https://test.pypi.org/simple). This will include the PKG_NAME==VERSION
+        #   package because VERSION will not have been uploaded to regular PyPI yet.
+        # - attempt install again after 5 seconds if it fails because there is
+        #   sometimes a delay in availability on test pypi
         run: |
-          uv venv
-          VIRTUAL_ENV=.venv uv pip install dist/*.whl
+          poetry run pip install \
+            --extra-index-url https://test.pypi.org/simple/ \
+            "$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
-        working-directory: ${{ env.EFFECTIVE_WORKING_DIR }}
+        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: ${{ env.EFFECTIVE_WORKING_DIR }}
+        working-directory: ${{ inputs.working-directory }}
         shell: bash
         env:
           PKG_NAME: ${{ needs.build.outputs.pkg-name }}
           VERSION: ${{ needs.build.outputs.version }}
         run: |
-          VIRTUAL_ENV=.venv uv pip install dist/*.whl
-
-      - name: Check for prerelease versions
-        # Block release if any dependencies allow prerelease versions
-        # (unless this is itself a prerelease version)
-        working-directory: ${{ env.EFFECTIVE_WORKING_DIR }}
-        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: ${{ env.EFFECTIVE_WORKING_DIR }}
+        working-directory: ${{ inputs.working-directory }}
 
       - name: Get minimum versions
-        # Find the minimum published versions that satisfies the given constraints
-        working-directory: ${{ env.EFFECTIVE_WORKING_DIR }}
+        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 $python_version)"
+          poetry run pip install packaging
+          min_versions="$(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"
 
@@ -354,18 +171,18 @@ jobs:
         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 PYTEST_EXTRA="-q -k 'not test_serdes'"
-        working-directory: ${{ env.EFFECTIVE_WORKING_DIR }}
+          poetry run pip install $MIN_VERSIONS
+          make tests
+        working-directory: ${{ inputs.working-directory }}
 
-      - name: Import integration test dependencies
-        run: uv sync --group test --group test_integration
-        working-directory: ${{ env.EFFECTIVE_WORKING_DIR }}
+      - name: 'Authenticate to Google Cloud'
+        id: 'auth'
+        uses: google-github-actions/auth@v2
+        with:
+          credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
 
       - name: Run integration tests
-        # Uses the Makefile's `integration_tests` target for the specified package
-        if: ${{ startsWith(env.EFFECTIVE_WORKING_DIR, 'libs/partners/') }}
+        if: ${{ startsWith(inputs.working-directory, 'libs/partners/') }}
         env:
           AI21_API_KEY: ${{ secrets.AI21_API_KEY }}
           GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
@@ -377,201 +194,36 @@ 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 }}
+          VOYAGE_API_KEY: ${{ secrets.VOYAGE_API_KEY }}
           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 }}
-          OLLAMA_API_KEY: ${{ secrets.OLLAMA_API_KEY }}
-          OPENROUTER_API_KEY: ${{ secrets.OPENROUTER_API_KEY }}
-          LANGCHAIN_TESTS_USER_AGENT: ${{ secrets.LANGCHAIN_TESTS_USER_AGENT }}
         run: make integration_tests
-        working-directory: ${{ env.EFFECTIVE_WORKING_DIR }}
-
-  # Test select published packages against new core
-  # Done when code changes are made to langchain-core
-  test-prior-published-packages-against-new-core:
-    # Installs the new core with old partners: Installs the new unreleased core
-    # alongside the previously published partner packages and runs integration tests
-    needs:
-      - build
-      - release-notes
-      - test-pypi-publish
-      - pre-release-checks
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-    if: false # temporarily skip
-    strategy:
-      matrix:
-        partner: [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 }}
-      LANGCHAIN_TESTS_USER_AGENT: ${{ secrets.LANGCHAIN_TESTS_USER_AGENT }}
-    steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-
-      # We implement this conditional as Github Actions does not have good support
-      # for conditionally needing steps. https://github.com/actions/runner/issues/491
-      # TODO: this seems to be resolved upstream, so we can probably remove this workaround
-      - name: Check if libs/core
-        run: |
-          if [ "${{ startsWith(env.EFFECTIVE_WORKING_DIR, 'libs/core') }}" != "true" ]; then
-            echo "Not in libs/core. Exiting successfully."
-            exit 0
-          fi
-
-      - name: Set up Python + uv
-        if: startsWith(env.EFFECTIVE_WORKING_DIR, 'libs/core')
-        uses: "./.github/actions/uv_setup"
-        with:
-          python-version: ${{ env.PYTHON_VERSION }}
-
-      - uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
-        if: startsWith(env.EFFECTIVE_WORKING_DIR, 'libs/core')
-        with:
-          name: dist
-          path: ${{ env.EFFECTIVE_WORKING_DIR }}/dist/
-
-      - name: Test against ${{ matrix.partner }}
-        if: startsWith(env.EFFECTIVE_WORKING_DIR, 'libs/core')
-        run: |
-          # Identify latest tag, excluding pre-releases
-          LATEST_PACKAGE_TAG="$(
-            git ls-remote --tags origin "langchain-${{ matrix.partner }}*" \
-            | awk '{print $2}' \
-            | sed 's|refs/tags/||' \
-            | grep -E '[0-9]+\.[0-9]+\.[0-9]+$' \
-            | sort -Vr \
-            | head -n 1
-          )"
-          echo "Latest package tag: $LATEST_PACKAGE_TAG"
-
-          # Shallow-fetch just that single tag
-          git fetch --depth=1 origin tag "$LATEST_PACKAGE_TAG"
-
-          # Checkout the latest package files
-          rm -rf $GITHUB_WORKSPACE/libs/partners/${{ matrix.partner }}/*
-          rm -rf $GITHUB_WORKSPACE/libs/standard-tests/*
-          cd $GITHUB_WORKSPACE/libs/
-          git checkout "$LATEST_PACKAGE_TAG" -- standard-tests/
-          git checkout "$LATEST_PACKAGE_TAG" -- partners/${{ matrix.partner }}/
-          cd partners/${{ matrix.partner }}
-
-          # Print as a sanity check
-          echo "Version number from pyproject.toml: "
-          cat pyproject.toml | grep "version = "
-
-          # Run tests
-          uv sync --group test --group test_integration
-          uv pip install ../../core/dist/*.whl
-          make integration_tests
-
-  # Test external packages that depend on langchain-core/langchain against the new release
-  # Only runs for core and langchain_v1 releases to catch breaking changes before publish
-  test-dependents:
-    name: "🐍 Python ${{ matrix.python-version }}: ${{ matrix.package.path }}"
-    needs:
-      - build
-      - release-notes
-      - test-pypi-publish
-      - pre-release-checks
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-    # Only run for core or langchain_v1 releases.
-    # Job-level 'if' does not support env context; must use inputs directly.
-    if: >-
-      startsWith(inputs.working-directory-override || inputs.working-directory, 'libs/core')
-      || startsWith(inputs.working-directory-override || inputs.working-directory, 'libs/langchain_v1')
-    strategy:
-      fail-fast: false
-      matrix:
-        python-version: ["3.11", "3.13"]
-        package:
-          - name: deepagents
-            repo: langchain-ai/deepagents
-            path: libs/deepagents
-    # No API keys needed for now - deepagents `make test` only runs unit tests
-
-    steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-        with:
-          path: langchain
-
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-        with:
-          repository: ${{ matrix.package.repo }}
-          path: ${{ matrix.package.name }}
-
-      - name: Set up Python + uv
-        uses: "./langchain/.github/actions/uv_setup"
-        with:
-          python-version: ${{ matrix.python-version }}
-
-      - uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
-        with:
-          name: dist
-          path: dist/
-
-      - name: Install ${{ matrix.package.name }} with local packages
-        # External dependents don't have [tool.uv.sources] pointing to this repo,
-        # so we install the package normally then override with the built wheel.
-        run: |
-          cd ${{ matrix.package.name }}/${{ matrix.package.path }}
-
-          # Install the package with test dependencies
-          uv sync --group test
-
-          # Override with the built wheel from this release
-          uv pip install $GITHUB_WORKSPACE/dist/*.whl
-
-      - name: Run ${{ matrix.package.name }} tests
-        run: |
-          cd ${{ matrix.package.name }}/${{ matrix.package.path }}
-          make test
+        working-directory: ${{ inputs.working-directory }}
 
   publish:
-    # Publishes the package to PyPI
     needs:
       - build
-      - release-notes
       - test-pypi-publish
       - pre-release-checks
-      - test-dependents
-      # - test-prior-published-packages-against-new-core
-    # Run if all needed jobs succeeded or were skipped (test-dependents only runs for core/langchain_v1)
-    if: ${{ !cancelled() && !failure() }}
     runs-on: ubuntu-latest
     permissions:
       # This permission is used for trusted publishing:
@@ -583,70 +235,70 @@ jobs:
 
     defaults:
       run:
-        working-directory: ${{ env.EFFECTIVE_WORKING_DIR }}
+        working-directory: ${{ inputs.working-directory }}
 
     steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+      - 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@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
+      - uses: actions/download-artifact@v4
         with:
           name: dist
-          path: ${{ env.EFFECTIVE_WORKING_DIR }}/dist/
+          path: ${{ inputs.working-directory }}/dist/
 
       - name: Publish package distributions to PyPI
-        uses: pypa/gh-action-pypi-publish@ed0c53931b1dc9bd32cbe73a98c7f6766f8a527e # release/v1
+        uses: pypa/gh-action-pypi-publish@release/v1
         with:
-          packages-dir: ${{ env.EFFECTIVE_WORKING_DIR }}/dist/
+          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
-    # Run if all needed jobs succeeded or were skipped
-    if: ${{ !cancelled() && !failure() }}
     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:
       run:
-        working-directory: ${{ env.EFFECTIVE_WORKING_DIR }}
+        working-directory: ${{ inputs.working-directory }}
 
     steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+      - 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@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
+      - uses: actions/download-artifact@v4
         with:
           name: dist
-          path: ${{ env.EFFECTIVE_WORKING_DIR }}/dist/
+          path: ${{ inputs.working-directory }}/dist/
 
-      - name: Create Tag
-        uses: ncipollo/release-action@339a81892b84b4eeb0f6e744e4574d79d0d9b8dd # v1
+      - 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 +7,57 @@ 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@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+      - 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"
-        shell: bash
-        run: |
-          make test PYTEST_EXTRA=-q
-
-      - name: "🔍 Calculate Minimum Dependency Versions"
+      - name: Install langchain editable
         working-directory: ${{ inputs.working-directory }}
-        id: min-version
-        shell: bash
-        run: |
-          VIRTUAL_ENV=.venv uv pip install packaging tomli requests
-          python_version="$(uv run python --version | awk '{print $2}')"
-          min_versions="$(uv run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml pull_request $python_version)"
-          echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"
-          echo "min-versions=$min_versions"
-
-      - name: "🧪 Run Tests with Minimum Dependencies"
-        if: ${{ steps.min-version.outputs.min-versions != '' }}
+        if: ${{ inputs.langchain-location }}
         env:
-          MIN_VERSIONS: ${{ steps.min-version.outputs.min-versions }}
+          LANGCHAIN_LOCATION: ${{ inputs.langchain-location }}
         run: |
-          VIRTUAL_ENV=.venv uv pip install $MIN_VERSIONS
-          make tests PYTEST_EXTRA=-q
-        working-directory: ${{ inputs.working-directory }}
+          poetry run pip install -e "$LANGCHAIN_LOCATION"
 
-      - name: "🧹 Verify Clean Working Directory"
+      - name: Run core tests
+        shell: bash
+        run: |
+          make test
+
+      - name: Ensure the tests did not create any additional files
         shell: bash
         run: |
           set -eu

.github/workflows/_test_doc_imports.yml

@@ -0,0 +1,50 @@
+name: test_doc_imports
+
+on:
+  workflow_call:
+
+env:
+  POETRY_VERSION: "1.7.1"
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version:
+          - "3.11"
+    name: "check doc imports #${{ 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: ${{ env.POETRY_VERSION }}
+          cache-key: core
+
+      - name: Install dependencies
+        shell: bash
+        run: poetry install --with test
+
+      - name: Install langchain editable
+        run: |
+          poetry run pip install -e libs/core libs/langchain libs/community libs/experimental
+
+      - name: Check doc imports
+        shell: bash
+        run: |
+          poetry run python docs/scripts/check_imports.py
+
+      - name: Ensure the test did not create any additional files
+        shell: bash
+        run: |
+          set -eu
+
+          STATUS="$(git status)"
+          echo "$STATUS"
+
+          # grep will exit non-zero if the target message isn't found,
+          # and `set -e` above will cause the step to fail.
+          echo "$STATUS" | grep 'nothing to commit, working tree clean'

.github/workflows/_test_pydantic.yml

@@ -1,73 +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: "3.12"
-      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@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-
-      - 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
-        env:
-          PYDANTIC_VERSION: ${{ inputs.pydantic-version }}
-        run: VIRTUAL_ENV=.venv uv pip install "pydantic~=$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/_test_vcr.yml

@@ -1,66 +0,0 @@
-# Runs VCR cassette-backed integration tests in playback-only mode.
-#
-# No API keys needed — catches stale cassettes caused by test input
-# changes without re-recording.
-#
-# Called as part of check_diffs.yml workflow.
-
-name: "📼 VCR Cassette Tests"
-
-on:
-  workflow_call:
-    inputs:
-      working-directory:
-        required: true
-        type: string
-        description: "From which folder this pipeline executes"
-      python-version:
-        required: true
-        type: string
-        description: "Python version to use"
-
-permissions:
-  contents: read
-
-env:
-  UV_FROZEN: "true"
-
-jobs:
-  build:
-    defaults:
-      run:
-        working-directory: ${{ inputs.working-directory }}
-    runs-on: ubuntu-latest
-    timeout-minutes: 20
-    name: "Python ${{ inputs.python-version }}"
-    steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-
-      - name: "🐍 Set up Python ${{ inputs.python-version }} + UV"
-        uses: "./.github/actions/uv_setup"
-        with:
-          python-version: ${{ inputs.python-version }}
-          cache-suffix: test-vcr-${{ inputs.working-directory }}
-          working-directory: ${{ inputs.working-directory }}
-
-      - name: "📦 Install Test Dependencies"
-        shell: bash
-        run: uv sync --group test
-
-      - name: "📼 Run VCR Cassette Tests (playback-only)"
-        shell: bash
-        env:
-          OPENAI_API_KEY: sk-fake
-        run: make test_vcr
-
-      - name: "🧹 Verify Clean Working Directory"
-        shell: bash
-        run: |
-          set -eu
-
-          STATUS="$(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/auto-label-by-package.yml

@@ -1,115 +0,0 @@
-name: Auto Label Issues by Package
-
-on:
-  issues:
-    types: [opened, edited]
-
-permissions:
-  contents: read
-
-jobs:
-  label-by-package:
-    permissions:
-      issues: write
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Sync package labels
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
-        with:
-          script: |
-            const body = context.payload.issue.body || "";
-
-            // Extract text under "## Package" or "### Package" (handles " (Required)" suffix and being last section)
-            const match = body.match(/#{2,3} Package[^\n]*\n([\s\S]*?)(?:\n#{2,3} |$)/i);
-            if (!match) {
-              core.setFailed(
-                `Could not find "## Package" section in issue #${context.issue.number} body. ` +
-                `The issue template may have changed — update the regex in this workflow.`
-              );
-              return;
-            }
-
-            const packageSection = match[1].trim();
-
-            // Mapping table for package names to labels
-            const mapping = {
-              "langchain": "langchain",
-              "langchain-openai": "openai",
-              "langchain-anthropic": "anthropic",
-              "langchain-classic": "langchain-classic",
-              "langchain-core": "core",
-              "langchain-model-profiles": "model-profiles",
-              "langchain-tests": "standard-tests",
-              "langchain-text-splitters": "text-splitters",
-              "langchain-chroma": "chroma",
-              "langchain-deepseek": "deepseek",
-              "langchain-exa": "exa",
-              "langchain-fireworks": "fireworks",
-              "langchain-groq": "groq",
-              "langchain-huggingface": "huggingface",
-              "langchain-mistralai": "mistralai",
-              "langchain-nomic": "nomic",
-              "langchain-ollama": "ollama",
-              "langchain-openrouter": "openrouter",
-              "langchain-perplexity": "perplexity",
-              "langchain-qdrant": "qdrant",
-              "langchain-xai": "xai",
-            };
-
-            // All possible package labels we manage
-            const allPackageLabels = Object.values(mapping);
-            const selectedLabels = [];
-
-            // Check if this is checkbox format (multiple selection)
-            const checkboxMatches = packageSection.match(/- \[x\]\s+([^\n\r]+)/gi);
-            if (checkboxMatches) {
-              // Handle checkbox format
-              for (const match of checkboxMatches) {
-                const packageName = match.replace(/- \[x\]\s+/i, '').trim();
-                const label = mapping[packageName];
-                if (label && !selectedLabels.includes(label)) {
-                  selectedLabels.push(label);
-                }
-              }
-            } else {
-              // Handle dropdown format (single selection)
-              const label = mapping[packageSection];
-              if (label) {
-                selectedLabels.push(label);
-              }
-            }
-
-            // Get current issue labels
-            const issue = await github.rest.issues.get({
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              issue_number: context.issue.number
-            });
-
-            const currentLabels = issue.data.labels.map(label => label.name);
-            const currentPackageLabels = currentLabels.filter(label => allPackageLabels.includes(label));
-
-            // Determine labels to add and remove
-            const labelsToAdd = selectedLabels.filter(label => !currentPackageLabels.includes(label));
-            const labelsToRemove = currentPackageLabels.filter(label => !selectedLabels.includes(label));
-
-            // Add new labels
-            if (labelsToAdd.length > 0) {
-              await github.rest.issues.addLabels({
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                issue_number: context.issue.number,
-                labels: labelsToAdd
-              });
-            }
-
-            // Remove old labels
-            for (const label of labelsToRemove) {
-              await github.rest.issues.removeLabel({
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                issue_number: context.issue.number,
-                name: label
-              });
-            }

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

@@ -0,0 +1,24 @@
+name: Check Broken Links
+
+on:
+  workflow_dispatch:
+  schedule:
+    - cron:  '0 13 * * *'
+
+jobs:
+  check-links:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Use Node.js 18.x
+        uses: actions/setup-node@v3
+        with:
+          node-version: 18.x
+          cache: "yarn"
+          cache-dependency-path: ./docs/yarn.lock
+      - name: Install dependencies
+        run: yarn install --immutable --mode=skip-build
+        working-directory: ./docs
+      - name: Check broken links
+        run: yarn check-broken-links
+        working-directory: ./docs

.github/workflows/check_agents_sync.yml

@@ -1,42 +0,0 @@
-# Ensures CLAUDE.md and AGENTS.md stay synchronized.
-#
-# These files contain the same development guidelines but are named differently
-# for compatibility with different AI coding assistants (Claude Code uses CLAUDE.md,
-# other tools may use AGENTS.md).
-
-name: "🔄 Check CLAUDE.md / AGENTS.md Sync"
-
-on:
-  push:
-    branches: [master]
-    paths:
-      - "CLAUDE.md"
-      - "AGENTS.md"
-  pull_request:
-    paths:
-      - "CLAUDE.md"
-      - "AGENTS.md"
-
-permissions:
-  contents: read
-
-jobs:
-  check-sync:
-    name: "verify files are identical"
-    runs-on: ubuntu-latest
-    steps:
-      - name: "📋 Checkout Code"
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-
-      - name: "🔍 Check CLAUDE.md and AGENTS.md are in sync"
-        run: |
-          if ! diff -q CLAUDE.md AGENTS.md > /dev/null 2>&1; then
-            echo "❌ CLAUDE.md and AGENTS.md are out of sync!"
-            echo ""
-            echo "These files must contain identical content."
-            echo "Differences:"
-            echo ""
-            diff --color=always CLAUDE.md AGENTS.md || true
-            exit 1
-          fi
-          echo "✅ CLAUDE.md and AGENTS.md are in sync"

.github/workflows/check_core_versions.yml

@@ -1,67 +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"
-      - "libs/partners/anthropic/pyproject.toml"
-      - "libs/partners/anthropic/langchain_anthropic/_version.py"
-
-permissions:
-  contents: read
-
-jobs:
-  check_version_equality:
-    runs-on: ubuntu-latest
-
-    steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-
-      - 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: $LANGCHAIN_PYPROJECT_VERSION"
-          fi
-
-          # Check langchain-anthropic versions
-          ANTHROPIC_PYPROJECT_VERSION=$(grep -Po '(?<=^version = ")[^"]*' libs/partners/anthropic/pyproject.toml)
-          ANTHROPIC_VERSION_PY_VERSION=$(grep -Po '(?<=^__version__ = ")[^"]*' libs/partners/anthropic/langchain_anthropic/_version.py)
-
-          # Compare langchain-anthropic versions
-          if [ "$ANTHROPIC_PYPROJECT_VERSION" != "$ANTHROPIC_VERSION_PY_VERSION" ]; then
-            echo "langchain-anthropic versions in pyproject.toml and _version.py do not match!"
-            echo "pyproject.toml version: $ANTHROPIC_PYPROJECT_VERSION"
-            echo "_version.py version: $ANTHROPIC_VERSION_PY_VERSION"
-            exit 1
-          else
-            echo "Langchain-anthropic versions match: $ANTHROPIC_PYPROJECT_VERSION"
-          fi

.github/workflows/check_diffs.yml

@@ -1,179 +1,134 @@
-# Primary CI workflow.
-#
-# Only runs against packages that have changed files.
-#
-# Runs:
-# - Linting (_lint.yml)
-# - Unit Tests (_test.yml)
-# - Pydantic compatibility tests (_test_pydantic.yml)
-# - Integration test compilation checks (_compile_integration_test.yml)
-# - Extended test suites that require additional dependencies
-#
-# 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@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-      - name: "🐍 Setup Python 3.11"
-        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # 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@25f79e676e7ea1868813e21465014798211fad8c # 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-pydantic: ${{ steps.set-matrix.outputs.test-pydantic }}
-      vcr-tests: ${{ steps.set-matrix.outputs.vcr-tests }}
-  # 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 }}
+      docs-edited: ${{ steps.set-matrix.outputs.docs-edited }}
   lint:
-    needs: [build]
-    if: ${{ needs.build.outputs.lint != '[]' }}
+    name: cd ${{ matrix.working-directory }}
+    needs: [ build ]
+    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:
-    needs: [build]
-    if: ${{ needs.build.outputs.test != '[]' }}
+    name: cd ${{ matrix.working-directory }}
+    needs: [ build ]
+    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 }}
+  test-doc-imports:
+    needs: [ build ]
+    if: ${{ needs.build.outputs.dirs-to-test != '[]' || needs.build.outputs.docs-edited }}
+    uses: ./.github/workflows/_test_doc_imports.yml
     secrets: inherit
 
-  # Verify integration tests compile without actually running them (faster feedback)
   compile-integration-tests:
-    name: "Compile Integration Tests"
-    needs: [build]
-    if: ${{ needs.build.outputs.compile-integration-tests != '[]' }}
+    name: cd ${{ matrix.working-directory }}
+    needs: [ build ]
+    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 VCR cassette-backed integration tests in playback-only mode (no API keys)
-  vcr-tests:
-    name: "VCR Cassette Tests"
-    needs: [build]
-    if: ${{ needs.build.outputs.vcr-tests != '[]' }}
+  dependencies:
+    name: cd ${{ matrix.working-directory }}
+    needs: [ build ]
+    if: ${{ needs.build.outputs.dirs-to-test != '[]' }}
     strategy:
       matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.vcr-tests) }}
-      fail-fast: false
-    uses: ./.github/workflows/_test_vcr.yml
+        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-test) }}
+    uses: ./.github/workflows/_dependencies.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"
-    needs: [build]
-    if: ${{ needs.build.outputs.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@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+      - 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
@@ -184,36 +139,9 @@ 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'
-
-  # Verify _release.yml dropdown options stay in sync with package directories
-  check-release-options:
-    name: "Validate Release Options"
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-      - name: "🐍 Setup Python 3.11"
-        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6
-        with:
-          python-version: "3.11"
-      - name: "📦 Install Dependencies"
-        run: python -m pip install pyyaml pytest
-      - name: "🔍 Check release dropdown matches packages"
-        run: python -m pytest .github/scripts/test_release_options.py -v
-
-  # Final status check - ensures all required jobs passed before allowing merge
   ci_success:
-    name: "✅ CI Success"
-    needs:
-      [
-        build,
-        lint,
-        test,
-        compile-integration-tests,
-        vcr-tests,
-        extended-tests,
-        test-pydantic,
-        check-release-options,
-      ]
+    name: "CI Success"
+    needs: [build, lint, test, compile-integration-tests, dependencies, extended-tests, test-doc-imports]
     if: |
       always()
     runs-on: ubuntu-latest
@@ -222,7 +150,7 @@ 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/close_unchecked_issues.yml

@@ -1,196 +0,0 @@
-# Auto-close issues that bypass or ignore the issue template checkboxes.
-#
-# GitHub issue forms enforce `required: true` checkboxes in the web UI,
-# but the API bypasses form validation entirely — bots/scripts can open
-# issues with every box unchecked or skip the template altogether.
-#
-# Rules:
-#   0. No issue type -> close unless author is an org member
-#   1. No checkboxes at all -> close unless author is an org member or bot
-#   2. Checkboxes present but none checked -> close
-#   3. "Submission checklist" section incomplete -> close
-#   4. "Package (Required)" section has no selection -> close
-#
-# Org membership check reuses the shared helper from pr-labeler.js and
-# the same GitHub App used by tag-external-issues.yml.
-
-name: Close Unchecked Issues
-
-on:
-  issues:
-    types: [opened]
-
-permissions:
-  contents: read
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.issue.number }}
-  cancel-in-progress: true
-
-jobs:
-  check-boxes:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      issues: write
-
-    steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-
-      - name: Generate GitHub App token
-        id: app-token
-        uses: actions/create-github-app-token@f8d387b68d61c58ab83c6c016672934102569859 # v3
-        with:
-          app-id: ${{ secrets.ORG_MEMBERSHIP_APP_ID }}
-          private-key: ${{ secrets.ORG_MEMBERSHIP_APP_PRIVATE_KEY }}
-
-      - name: Validate issue checkboxes
-        if: steps.app-token.outcome == 'success'
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
-        with:
-          github-token: ${{ steps.app-token.outputs.token }}
-          script: |
-            const { owner, repo } = context.repo;
-            const issue_number = context.payload.issue.number;
-            const body = context.payload.issue.body ?? '';
-            const allChecked = (body.match(/- \[x\]/gi) || []).length;
-            const allUnchecked = (body.match(/- \[ \]/g) || []).length;
-            const total = allChecked + allUnchecked;
-
-            // ── Helpers ─────────────────────────────────────────────────
-            // Extract checkboxes under a markdown H2/H3 heading.
-            // Returns { checked, unchecked } counts, or null if the
-            // section heading is not found in the body.
-            function parseSection(heading) {
-              const escaped = heading.replace(/[.*+?^${}()|[\]\\]/g, '\\$&');
-              // Find the heading line
-              const headingRe = new RegExp(`^#{2,3}\\s+${escaped}\\s*$`, 'm');
-              const headingMatch = headingRe.exec(body);
-              if (!headingMatch) return null;
-              // Slice from after the heading to the next heading or end
-              const rest = body.slice(headingMatch.index + headingMatch[0].length);
-              const nextHeading = rest.search(/\n#{2,3}\s/);
-              const block = nextHeading === -1 ? rest : rest.slice(0, nextHeading);
-              return {
-                checked: (block.match(/- \[x\]/gi) || []).length,
-                unchecked: (block.match(/- \[ \]/g) || []).length,
-              };
-            }
-
-            let _cachedMember;
-            async function isOrgMember() {
-              if (_cachedMember) return _cachedMember;
-              const { h } = require('./.github/scripts/pr-labeler.js')
-                .loadAndInit(github, owner, repo, core);
-              const author = context.payload.sender.login;
-              const { isExternal } = await h.checkMembership(
-                author, context.payload.sender.type,
-              );
-              _cachedMember = { internal: !isExternal, author };
-              return _cachedMember;
-            }
-
-            async function closeWithComment(lines) {
-              const templateUrl = `https://github.com/${owner}/${repo}/issues/new/choose`;
-              lines.push(
-                '',
-                `Please use one of the [issue templates](${templateUrl}).`,
-              );
-
-              // Post comment first so the author sees the reason even if
-              // the subsequent close call fails.
-              await github.rest.issues.createComment({
-                owner, repo, issue_number,
-                body: lines.join('\n'),
-              });
-
-              await github.rest.issues.update({
-                owner, repo, issue_number,
-                state: 'closed',
-                state_reason: 'not_planned',
-              });
-            }
-
-            // ── Rule 0: no issue type (API/CLI bypass) ──────────────────
-            // Issue types are set automatically when using web UI templates.
-            // External users cannot set issue types via the API (requires
-            // write/triage permissions), so a missing type reliably indicates
-            // programmatic submission.
-            if (!context.payload.issue.type) {
-              let membership;
-              try {
-                membership = await isOrgMember();
-              } catch (e) {
-                // Org membership check failed — skip Rule 0 and let
-                // Rules 1-4 handle validation via checkboxes.
-                core.warning(`Rule 0: org membership check failed, skipping: ${e.message}`);
-              }
-              if (membership?.internal) {
-                console.log(`No issue type, but ${membership.author} is internal — OK`);
-              } else if (membership) {
-                console.log(`No issue type and ${membership.author} is external — closing`);
-                await closeWithComment([
-                  'This issue was automatically closed because it appears to have been submitted programmatically — issue types are automatically set when using the GitHub web interface, and this issue has none.',
-                  '',
-                  'We do not allow automated issue submission at this time.',
-                ]);
-                return;
-              }
-            }
-
-            // ── Rule 1: no checkboxes at all ────────────────────────────
-            if (total === 0) {
-              const { internal, author } = await isOrgMember();
-              if (internal) {
-                console.log(`No checkboxes, but ${author} is internal — OK`);
-                return;
-              }
-              console.log(`No checkboxes and ${author} is external — closing`);
-              await closeWithComment([
-                'This issue was automatically closed because no issue template was used.',
-              ]);
-              return;
-            }
-
-            // ── Rule 2: checkboxes present but none checked ─────────────
-            if (allChecked === 0) {
-              console.log(`${allUnchecked} checkbox(es) present, none checked — closing`);
-              await closeWithComment([
-                'This issue was automatically closed because none of the required checkboxes were checked. Please re-file using an issue template and complete the checklist.',
-              ]);
-              return;
-            }
-
-            // ── Rules 3–4: parse sections for targeted feedback ─────────
-            const checklist = parseSection('Submission checklist');
-            const pkg = parseSection('Package (Required)');
-            console.log(`Section parse — checklist: ${JSON.stringify(checklist)}, pkg: ${JSON.stringify(pkg)}`);
-
-            const problems = [];
-
-            if (checklist && checklist.unchecked > 0) {
-              problems.push(
-                'the submission checklist is incomplete — please confirm you searched for duplicates, included a reproduction, etc.'
-              );
-            }
-            if (pkg !== null && pkg.checked === 0) {
-              problems.push(
-                'no package was selected (e.g. langchain-core, langchain, langgraph) — this helps us route the issue to the right team'
-              );
-            } else if (pkg === null) {
-              problems.push(
-                'the package selection is missing (e.g. langchain-core, langchain, langgraph) — this helps us route the issue to the right team'
-              );
-            }
-
-            if (problems.length === 0) {
-              console.log(`All section checks passed (${allChecked} checked) — OK`);
-              return;
-            }
-
-            console.log(`Closing — problems: ${problems.join('; ')}`);
-            await closeWithComment([
-              'Thanks for opening an issue! It was automatically closed because:',
-              '',
-              ...problems.map(p => `- ${p}`),
-            ]);

.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/codspeed.yml

@@ -1,81 +0,0 @@
-# CodSpeed performance benchmarks.
-#
-# Runs benchmarks on changed packages and uploads results to CodSpeed.
-# Separated from the main CI workflow so that push-to-master baseline runs
-# are never cancelled by subsequent merges (cancel-in-progress is only
-# enabled for pull_request events).
-
-name: "⚡ CodSpeed"
-
-on:
-  push:
-    branches: [master]
-  pull_request:
-
-# On PRs, cancel stale runs when new commits are pushed.
-# On push-to-master, never cancel — these runs populate CodSpeed baselines.
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event_name == 'push' && github.sha || github.ref }}
-  cancel-in-progress: ${{ github.event_name == 'pull_request' }}
-
-permissions:
-  contents: read
-
-env:
-  UV_FROZEN: "true"
-  UV_NO_SYNC: "true"
-
-jobs:
-  build:
-    name: "Detect Changes"
-    runs-on: ubuntu-latest
-    if: ${{ !contains(github.event.pull_request.labels.*.name, 'codspeed-ignore') }}
-    steps:
-      - name: "📋 Checkout Code"
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-      - name: "🐍 Setup Python 3.11"
-        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6
-        with:
-          python-version: "3.11"
-      - name: "📂 Get Changed Files"
-        id: files
-        uses: Ana06/get-changed-files@25f79e676e7ea1868813e21465014798211fad8c # v2.3.0
-      - name: "🔍 Analyze Changed Files"
-        id: set-matrix
-        run: |
-          python -m pip install packaging requests
-          python .github/scripts/check_diff.py ${{ steps.files.outputs.all }} >> $GITHUB_OUTPUT
-    outputs:
-      codspeed: ${{ steps.set-matrix.outputs.codspeed }}
-
-  benchmarks:
-    name: "⚡ CodSpeed Benchmarks"
-    needs: [build]
-    if: ${{ needs.build.outputs.codspeed != '[]' }}
-    runs-on: codspeed-macro
-    strategy:
-      matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.codspeed) }}
-      fail-fast: false
-    steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-
-      - name: "📦 Install UV Package Manager"
-        uses: astral-sh/setup-uv@0ca8f610542aa7f4acaf39e65cf4eb3c35091883 # v7
-        with:
-          # Pinned to 3.13.11 to work around CodSpeed walltime segfault on 3.13.12+
-          # See: https://github.com/CodSpeedHQ/pytest-codspeed/issues/106
-          python-version: "3.13.11"
-
-      - 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@a50965600eafa04edcd6717761f55b77e52aafbd # v4
-        with:
-          token: ${{ secrets.CODSPEED_TOKEN }}
-          run: |
-            cd ${{ matrix.job-configs.working-directory }}
-            uv run --no-sync pytest ./tests/benchmarks --codspeed
-          mode: ${{ matrix.job-configs.codspeed-mode }}

.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/integration_tests.yml

@@ -1,301 +0,0 @@
-# Routine integration tests against partner libraries with live API credentials.
-#
-# Uses `make integration_tests` within each library being tested.
-#
-# Runs daily with the option to trigger manually.
-
-name: "⏰ Integration Tests"
-run-name: "Run Integration Tests - ${{ inputs.working-directory-override || (inputs.working-directory != 'all' && inputs.working-directory) || 'all libs' }} (Python ${{ inputs.python-version-override || '3.10, 3.13' }})"
-
-on:
-  workflow_dispatch:
-    inputs:
-      working-directory:
-        type: choice
-        description: "Library to test (select from dropdown)"
-        default: "all"
-        options:
-          - "all"
-          - "libs/core"
-          - "libs/langchain"
-          - "libs/langchain_v1"
-          - "libs/text-splitters"
-          - "libs/standard-tests"
-          - "libs/model-profiles"
-          - "libs/partners/anthropic"
-          - "libs/partners/chroma"
-          - "libs/partners/deepseek"
-          - "libs/partners/exa"
-          - "libs/partners/fireworks"
-          - "libs/partners/groq"
-          - "libs/partners/huggingface"
-          - "libs/partners/mistralai"
-          - "libs/partners/nomic"
-          - "libs/partners/ollama"
-          - "libs/partners/openai"
-          - "libs/partners/openrouter"
-          - "libs/partners/perplexity"
-          - "libs/partners/qdrant"
-          - "libs/partners/xai"
-      working-directory-override:
-        type: string
-        description: "Manual override — takes precedence over dropdown (e.g. libs/partners/partner-xyz)"
-      python-version-override:
-        type: string
-        description: "Python version override — defaults to 3.10 and 3.13 in matrix (e.g. 3.11)"
-  schedule:
-    - cron: "0 13 * * *" # Runs daily at 1PM UTC (9AM EDT/6AM PDT)
-
-permissions:
-  contents: read
-
-env:
-  UV_FROZEN: "true"
-  DEFAULT_LIBS: >-
-    ["libs/partners/openai",
-    "libs/partners/anthropic",
-    "libs/partners/fireworks",
-    "libs/partners/groq",
-    "libs/partners/mistralai",
-    "libs/partners/xai",
-    "libs/partners/google-vertexai",
-    "libs/partners/google-genai",
-    "libs/partners/aws"]
-
-jobs:
-  # Generate dynamic test matrix based on input parameters or defaults
-  # Only runs on the main repo (for scheduled runs) or when manually triggered
-  compute-matrix:
-    # Defend against forks running scheduled jobs, but allow manual runs from forks
-    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 }}
-      python-version-min-3-11: ${{ steps.set-matrix.outputs.python-version-min-3-11 }}
-    steps:
-      - name: "🔢 Generate Python & Library Matrix"
-        id: set-matrix
-        env:
-          DEFAULT_LIBS: ${{ env.DEFAULT_LIBS }}
-          WORKING_DIRECTORY_OVERRIDE: ${{ github.event.inputs.working-directory-override || '' }}
-          WORKING_DIRECTORY_CHOICE: ${{ github.event.inputs.working-directory || 'all' }}
-          PYTHON_VERSION_OVERRIDE: ${{ github.event.inputs.python-version-override || '' }}
-        run: |
-          # echo "matrix=..." where matrix is a json formatted str with keys python-version and working-directory
-          # python-version defaults to 3.10 and 3.13, overridden to [PYTHON_VERSION_OVERRIDE] if set
-          # working-directory priority: override string > dropdown choice > DEFAULT_LIBS
-          python_version='["3.10", "3.13"]'
-          python_version_min_3_11='["3.11", "3.13"]'
-          working_directory="$DEFAULT_LIBS"
-          if [ -n "$PYTHON_VERSION_OVERRIDE" ]; then
-            python_version="[\"$PYTHON_VERSION_OVERRIDE\"]"
-            # Bound override version to >= 3.11 for packages requiring it
-            if [ "$(echo "$PYTHON_VERSION_OVERRIDE >= 3.11" | bc -l)" -eq 1 ]; then
-              python_version_min_3_11="[\"$PYTHON_VERSION_OVERRIDE\"]"
-            else
-              python_version_min_3_11='["3.11"]'
-            fi
-          fi
-          if [ -n "$WORKING_DIRECTORY_OVERRIDE" ]; then
-            working_directory="[\"$WORKING_DIRECTORY_OVERRIDE\"]"
-          elif [ "$WORKING_DIRECTORY_CHOICE" != "all" ]; then
-            working_directory="[\"$WORKING_DIRECTORY_CHOICE\"]"
-          fi
-          matrix="{\"python-version\": $python_version, \"working-directory\": $working_directory}"
-          echo "$matrix"
-          echo "matrix=$matrix" >> $GITHUB_OUTPUT
-          echo "python-version-min-3-11=$python_version_min_3_11" >> $GITHUB_OUTPUT
-
-  # Run integration tests against partner libraries with live API credentials
-  integration-tests:
-    if: github.repository_owner == 'langchain-ai' || github.event_name != 'schedule'
-    name: "🐍 Python ${{ matrix.python-version }}: ${{ matrix.working-directory }}"
-    runs-on: ubuntu-latest
-    needs: [compute-matrix]
-    timeout-minutes: 30
-    strategy:
-      fail-fast: false
-      matrix:
-        python-version: ${{ fromJSON(needs.compute-matrix.outputs.matrix).python-version }}
-        working-directory: ${{ fromJSON(needs.compute-matrix.outputs.matrix).working-directory }}
-
-    steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-        with:
-          path: langchain
-
-      # These libraries exist outside of the monorepo and need to be checked out separately
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-        with:
-          repository: langchain-ai/langchain-google
-          path: langchain-google
-      - name: "🔐 Authenticate to Google Cloud"
-        id: "auth"
-        uses: google-github-actions/auth@7c6bc770dae815cd3e89ee6cdf493a5fab2cc093 # v3
-        with:
-          credentials_json: "${{ secrets.GOOGLE_CREDENTIALS }}"
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-        with:
-          repository: langchain-ai/langchain-aws
-          path: langchain-aws
-      - name: "🔐 Configure AWS Credentials"
-        uses: aws-actions/configure-aws-credentials@8df5847569e6427dd6c4fb1cf565c83acfa8afa7 # v6
-        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: "📦 Organize External Libraries"
-        run: |
-          rm -rf \
-            langchain/libs/partners/google-genai \
-            langchain/libs/partners/google-vertexai
-          mv langchain-google/libs/genai langchain/libs/partners/google-genai
-          mv langchain-google/libs/vertexai langchain/libs/partners/google-vertexai
-          mv langchain-aws/libs/aws langchain/libs/partners/aws
-
-      - name: "🐍 Set up Python ${{ matrix.python-version }} + UV"
-        uses: "./langchain/.github/actions/uv_setup"
-        with:
-          python-version: ${{ matrix.python-version }}
-
-      - name: "📦 Install Dependencies"
-        # Partner packages use [tool.uv.sources] in their pyproject.toml to resolve
-        # langchain-core/langchain to local editable installs, so `uv sync` automatically
-        # tests against the versions from the current branch (not published releases).
-
-        # TODO: external google/aws don't have local resolution since they live in
-        # separate repos, so they pull `core`/`langchain_v1` from PyPI. We should update
-        # their dev groups to use git source dependencies pointing to the current
-        # branch's latest commit SHA to fully test against local langchain changes.
-        run: |
-          echo "Running scheduled tests, installing dependencies with uv..."
-          cd langchain/${{ matrix.working-directory }}
-          uv sync --group test --group test_integration
-
-      - name: "🚀 Run Integration Tests"
-        # WARNING: All secrets below are available to every matrix job regardless of
-        # which package is being tested. This is intentional for simplicity, but means
-        # any test file could technically access any key. Only use for trusted code.
-        env:
-          LANGCHAIN_TESTS_USER_AGENT: ${{ secrets.LANGCHAIN_TESTS_USER_AGENT }}
-
-          AI21_API_KEY: ${{ secrets.AI21_API_KEY }}
-          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
-          ANTHROPIC_FILES_API_IMAGE_ID: ${{ secrets.ANTHROPIC_FILES_API_IMAGE_ID }}
-          ANTHROPIC_FILES_API_PDF_ID: ${{ secrets.ANTHROPIC_FILES_API_PDF_ID }}
-          ASTRA_DB_API_ENDPOINT: ${{ secrets.ASTRA_DB_API_ENDPOINT }}
-          ASTRA_DB_APPLICATION_TOKEN: ${{ secrets.ASTRA_DB_APPLICATION_TOKEN }}
-          ASTRA_DB_KEYSPACE: ${{ secrets.ASTRA_DB_KEYSPACE }}
-          AZURE_OPENAI_API_VERSION: ${{ secrets.AZURE_OPENAI_API_VERSION }}
-          AZURE_OPENAI_API_BASE: ${{ secrets.AZURE_OPENAI_API_BASE }}
-          AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
-          AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_CHAT_DEPLOYMENT_NAME }}
-          AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME }}
-          AZURE_OPENAI_LLM_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LLM_DEPLOYMENT_NAME }}
-          AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME }}
-          COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
-          DEEPSEEK_API_KEY: ${{ secrets.DEEPSEEK_API_KEY }}
-          ES_URL: ${{ secrets.ES_URL }}
-          ES_CLOUD_ID: ${{ secrets.ES_CLOUD_ID }}
-          ES_API_KEY: ${{ secrets.ES_API_KEY }}
-          EXA_API_KEY: ${{ secrets.EXA_API_KEY }}
-          FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
-          GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
-          GOOGLE_SEARCH_API_KEY: ${{ secrets.GOOGLE_SEARCH_API_KEY }}
-          GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
-          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
-          HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
-          MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
-          MONGODB_ATLAS_URI: ${{ secrets.MONGODB_ATLAS_URI }}
-          NOMIC_API_KEY: ${{ secrets.NOMIC_API_KEY }}
-          NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}
-          OLLAMA_API_KEY: ${{ secrets.OLLAMA_API_KEY }}
-          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          OPENROUTER_API_KEY: ${{ secrets.OPENROUTER_API_KEY }}
-          PPLX_API_KEY: ${{ secrets.PPLX_API_KEY }}
-          TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
-          UPSTAGE_API_KEY: ${{ secrets.UPSTAGE_API_KEY }}
-          WATSONX_APIKEY: ${{ secrets.WATSONX_APIKEY }}
-          WATSONX_PROJECT_ID: ${{ secrets.WATSONX_PROJECT_ID }}
-          XAI_API_KEY: ${{ secrets.XAI_API_KEY }}
-        run: |
-          cd langchain/${{ matrix.working-directory }}
-          make integration_tests
-
-      - name: "🧹 Clean up External Libraries"
-        # Clean up external libraries to avoid affecting the following git status check
-        run: |
-          rm -rf \
-            langchain/libs/partners/google-genai \
-            langchain/libs/partners/google-vertexai \
-            langchain/libs/partners/aws
-
-      - name: "🧹 Verify Clean Working Directory"
-        working-directory: langchain
-        run: |
-          set -eu
-
-          STATUS="$(git status)"
-          echo "$STATUS"
-
-          # grep will exit non-zero if the target message isn't found,
-          # and `set -e` above will cause the step to fail.
-          echo "$STATUS" | grep 'nothing to commit, working tree clean'
-
-  # Test dependent packages against local packages to catch breaking changes
-  test-dependents:
-    # Defend against forks running scheduled jobs, but allow manual runs from forks
-    if: github.repository_owner == 'langchain-ai' || github.event_name != 'schedule'
-
-    name: "🐍 Python ${{ matrix.python-version }}: ${{ matrix.package.path }}"
-    runs-on: ubuntu-latest
-    needs: [compute-matrix]
-    timeout-minutes: 30
-    strategy:
-      fail-fast: false
-      matrix:
-        # deepagents requires Python >= 3.11, use bounded version from compute-matrix
-        python-version: ${{ fromJSON(needs.compute-matrix.outputs.python-version-min-3-11) }}
-        package:
-          - name: deepagents
-            repo: langchain-ai/deepagents
-            path: libs/deepagents
-
-    steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-        with:
-          path: langchain
-
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-        with:
-          repository: ${{ matrix.package.repo }}
-          path: ${{ matrix.package.name }}
-
-      - name: "🐍 Set up Python ${{ matrix.python-version }} + UV"
-        uses: "./langchain/.github/actions/uv_setup"
-        with:
-          python-version: ${{ matrix.python-version }}
-
-      - name: "📦 Install ${{ matrix.package.name }} with Local"
-        # Unlike partner packages (which use [tool.uv.sources] for local resolution),
-        # external dependents live in separate repos and need explicit overrides to
-        # test against the langchain versions from the current branch, as their
-        # pyproject.toml files point to released versions.
-        run: |
-          cd ${{ matrix.package.name }}/${{ matrix.package.path }}
-
-          # Install the package with test dependencies
-          uv sync --group test
-
-          # Override langchain packages with local versions
-          uv pip install \
-            -e $GITHUB_WORKSPACE/langchain/libs/core \
-            -e $GITHUB_WORKSPACE/langchain/libs/langchain_v1
-
-      # No API keys needed for now - deepagents `make test` only runs unit tests
-      - name: "🚀 Run ${{ matrix.package.name }} Tests"
-        run: |
-          cd ${{ matrix.package.name }}/${{ matrix.package.path }}
-          make test

.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

@@ -0,0 +1,36 @@
+name: LangChain People
+
+on:
+  schedule:
+    - 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'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Dump GitHub context
+        env:
+          GITHUB_CONTEXT: ${{ toJson(github) }}
+        run: echo "$GITHUB_CONTEXT"
+      - uses: actions/checkout@v4
+      # Ref: https://github.com/actions/runner/issues/2033
+      - name: Fix git safe.directory in container
+        run: mkdir -p /home/runner/work/_temp/_github_home && printf "[safe]\n\tdirectory = /github/workspace" > /home/runner/work/_temp/_github_home/.gitconfig
+      # 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 }}

.github/workflows/pr_labeler.yml

@@ -1,213 +0,0 @@
-# Unified PR labeler — applies size, file-based, title-based, and
-# contributor classification labels in a single sequential workflow.
-#
-# Consolidates pr_labeler_file.yml, pr_labeler_title.yml,
-# pr_size_labeler.yml, and PR-handling from tag-external-contributions.yml
-# into one workflow to eliminate race conditions from concurrent label
-# mutations. tag-external-issues.yml remains active for issue-only
-# labeling. Backfill lives in pr_labeler_backfill.yml.
-#
-# Config and shared logic live in .github/scripts/pr-labeler-config.json
-# and .github/scripts/pr-labeler.js — update those when adding partners.
-#
-# Setup Requirements:
-# 1. Create a GitHub App with permissions:
-#    - Repository: Pull requests (write)
-#    - Repository: Issues (write)
-#    - Organization: Members (read)
-# 2. Install the app on your organization and this repository
-# 3. Add these repository secrets:
-#    - ORG_MEMBERSHIP_APP_ID: Your app's ID
-#    - ORG_MEMBERSHIP_APP_PRIVATE_KEY: Your app's private key
-#
-# The GitHub App token is required to check private organization membership
-# and to propagate label events to downstream workflows.
-
-name: "🏷️ PR Labeler"
-
-on:
-  # Safe since we're not checking out or running the PR's code.
-  # NEVER CHECK OUT UNTRUSTED CODE FROM A PR's HEAD IN A pull_request_target JOB.
-  # Doing so would allow attackers to execute arbitrary code in the context of your repository.
-  pull_request_target:
-    types: [opened, synchronize, reopened, edited]
-
-permissions:
-  contents: read
-
-concurrency:
-  # Separate opened events so external/tier labels are never lost to cancellation
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.run_id }}-${{ github.event.action == 'opened' && 'opened' || 'update' }}
-  cancel-in-progress: ${{ github.event.action != 'opened' }}
-
-jobs:
-  label:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      pull-requests: write
-      issues: write
-
-    steps:
-      # Checks out the BASE branch (safe for pull_request_target — never
-      # the PR head). Needed to load .github/scripts/pr-labeler*.
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-
-      - name: Generate GitHub App token
-        if: github.event.action == 'opened'
-        id: app-token
-        uses: actions/create-github-app-token@f8d387b68d61c58ab83c6c016672934102569859 # v3
-        with:
-          app-id: ${{ secrets.ORG_MEMBERSHIP_APP_ID }}
-          private-key: ${{ secrets.ORG_MEMBERSHIP_APP_PRIVATE_KEY }}
-
-      - name: Verify App token
-        if: github.event.action == 'opened'
-        run: |
-          if [ -z "${{ steps.app-token.outputs.token }}" ]; then
-            echo "::error::GitHub App token generation failed — cannot classify contributor"
-            exit 1
-          fi
-
-      - name: Check org membership
-        if: github.event.action == 'opened'
-        id: check-membership
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
-        with:
-          github-token: ${{ steps.app-token.outputs.token }}
-          script: |
-            const { owner, repo } = context.repo;
-            const { h } = require('./.github/scripts/pr-labeler.js').loadAndInit(github, owner, repo, core);
-
-            const author = context.payload.sender.login;
-            const { isExternal } = await h.checkMembership(
-              author, context.payload.sender.type,
-            );
-            core.setOutput('is-external', isExternal ? 'true' : 'false');
-
-      - name: Apply PR labels
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
-        env:
-          IS_EXTERNAL: ${{ steps.check-membership.outputs.is-external }}
-        with:
-          github-token: ${{ secrets.GITHUB_TOKEN }}
-          script: |
-            const { owner, repo } = context.repo;
-            const { h } = require('./.github/scripts/pr-labeler.js').loadAndInit(github, owner, repo, core);
-
-            const pr = context.payload.pull_request;
-            if (!pr) return;
-            const prNumber = pr.number;
-            const action = context.payload.action;
-
-            const toAdd = new Set();
-            const toRemove = new Set();
-
-            const currentLabels = (await github.paginate(
-              github.rest.issues.listLabelsOnIssue,
-              { owner, repo, issue_number: prNumber, per_page: 100 },
-            )).map(l => l.name ?? '');
-
-            // ── Size + file labels (skip on 'edited' — files unchanged) ──
-            if (action !== 'edited') {
-              for (const sl of h.sizeLabels) await h.ensureLabel(sl);
-
-              const files = await github.paginate(github.rest.pulls.listFiles, {
-                owner, repo, pull_number: prNumber, per_page: 100,
-              });
-
-              const { totalChanged, sizeLabel } = h.computeSize(files);
-              toAdd.add(sizeLabel);
-              for (const sl of h.sizeLabels) {
-                if (currentLabels.includes(sl) && sl !== sizeLabel) toRemove.add(sl);
-              }
-              console.log(`Size: ${totalChanged} changed lines → ${sizeLabel}`);
-
-              for (const label of h.matchFileLabels(files)) {
-                toAdd.add(label);
-              }
-            }
-
-            // ── Title-based labels ──
-            const { labels: titleLabels, typeLabel } = h.matchTitleLabels(pr.title || '');
-            for (const label of titleLabels) toAdd.add(label);
-
-            // Remove stale type labels only when a type was detected
-            if (typeLabel) {
-              for (const tl of h.allTypeLabels) {
-                if (currentLabels.includes(tl) && !titleLabels.has(tl)) toRemove.add(tl);
-              }
-            }
-
-            // ── Internal label (only on open, non-external contributors) ──
-            // IS_EXTERNAL is empty string on non-opened events (step didn't
-            // run), so this guard is only true for opened + internal.
-            if (action === 'opened' && process.env.IS_EXTERNAL === 'false') {
-              toAdd.add('internal');
-            }
-
-            // ── Apply changes ──
-            // Ensure all labels we're about to add exist (addLabels returns
-            // 422 if any label in the batch is missing, which would prevent
-            // ALL labels from being applied).
-            for (const name of toAdd) {
-              await h.ensureLabel(name);
-            }
-
-            for (const name of toRemove) {
-              if (toAdd.has(name)) continue;
-              try {
-                await github.rest.issues.removeLabel({
-                  owner, repo, issue_number: prNumber, name,
-                });
-              } catch (e) {
-                if (e.status !== 404) throw e;
-              }
-            }
-
-            const addList = [...toAdd];
-            if (addList.length > 0) {
-              await github.rest.issues.addLabels({
-                owner, repo, issue_number: prNumber, labels: addList,
-              });
-            }
-
-            const removed = [...toRemove].filter(r => !toAdd.has(r));
-            console.log(`PR #${prNumber}: +[${addList.join(', ')}] -[${removed.join(', ')}]`);
-
-      # Apply tier label BEFORE the external label so that
-      # "trusted-contributor" is already present when the "external" labeled
-      # event fires and triggers require_issue_link.yml.
-      - name: Apply contributor tier label
-        if: github.event.action == 'opened' && steps.check-membership.outputs.is-external == 'true'
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
-        with:
-          github-token: ${{ steps.app-token.outputs.token }}
-          script: |
-            const { owner, repo } = context.repo;
-            const { h } = require('./.github/scripts/pr-labeler.js').loadAndInit(github, owner, repo, core);
-
-            const pr = context.payload.pull_request;
-            await h.applyTierLabel(pr.number, pr.user.login);
-
-      - name: Add external label
-        if: github.event.action == 'opened' && steps.check-membership.outputs.is-external == 'true'
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
-        with:
-          # Use App token so the "labeled" event propagates to downstream
-          # workflows (e.g. require_issue_link.yml). Events created by the
-          # default GITHUB_TOKEN do not trigger additional workflow runs.
-          github-token: ${{ steps.app-token.outputs.token }}
-          script: |
-            const { owner, repo } = context.repo;
-            const prNumber = context.payload.pull_request.number;
-
-            const { h } = require('./.github/scripts/pr-labeler.js').loadAndInit(github, owner, repo, core);
-
-            await h.ensureLabel('external');
-            await github.rest.issues.addLabels({
-              owner, repo,
-              issue_number: prNumber,
-              labels: ['external'],
-            });
-            console.log(`Added 'external' label to PR #${prNumber}`);

.github/workflows/pr_labeler_backfill.yml

@@ -1,130 +0,0 @@
-# Backfill PR labels on all open PRs.
-#
-# Manual-only workflow that applies the same labels as pr_labeler.yml
-# (size, file, title, contributor classification) to existing open PRs.
-# Reuses shared logic from .github/scripts/pr-labeler.js.
-
-name: "🏷️ PR Labeler Backfill"
-
-on:
-  workflow_dispatch:
-    inputs:
-      max_items:
-        description: "Maximum number of open PRs to process"
-        default: "100"
-        type: string
-
-permissions:
-  contents: read
-
-jobs:
-  backfill:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      pull-requests: write
-      issues: write
-
-    steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-
-      - name: Generate GitHub App token
-        id: app-token
-        uses: actions/create-github-app-token@f8d387b68d61c58ab83c6c016672934102569859 # v3
-        with:
-          app-id: ${{ secrets.ORG_MEMBERSHIP_APP_ID }}
-          private-key: ${{ secrets.ORG_MEMBERSHIP_APP_PRIVATE_KEY }}
-
-      - name: Backfill labels on open PRs
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
-        with:
-          github-token: ${{ steps.app-token.outputs.token }}
-          script: |
-            const { owner, repo } = context.repo;
-            const rawMax = '${{ inputs.max_items }}';
-            const maxItems = parseInt(rawMax, 10);
-            if (isNaN(maxItems) || maxItems <= 0) {
-              core.setFailed(`Invalid max_items: "${rawMax}" — must be a positive integer`);
-              return;
-            }
-
-            const { h } = require('./.github/scripts/pr-labeler.js').loadAndInit(github, owner, repo, core);
-
-            for (const name of [...h.sizeLabels, ...h.tierLabels]) {
-              await h.ensureLabel(name);
-            }
-
-            const contributorCache = new Map();
-            const fileRules = h.buildFileRules();
-
-            const prs = await github.paginate(github.rest.pulls.list, {
-              owner, repo, state: 'open', per_page: 100,
-            });
-
-            let processed = 0;
-            let failures = 0;
-            for (const pr of prs) {
-              if (processed >= maxItems) break;
-              try {
-                const author = pr.user.login;
-                const info = await h.getContributorInfo(contributorCache, author, pr.user.type);
-                const labels = new Set();
-
-                labels.add(info.isExternal ? 'external' : 'internal');
-                if (info.isExternal && info.mergedCount != null && info.mergedCount >= h.trustedThreshold) {
-                  labels.add('trusted-contributor');
-                } else if (info.isExternal && info.mergedCount === 0) {
-                  labels.add('new-contributor');
-                }
-
-                // Size + file labels
-                const files = await github.paginate(github.rest.pulls.listFiles, {
-                  owner, repo, pull_number: pr.number, per_page: 100,
-                });
-                const { sizeLabel } = h.computeSize(files);
-                labels.add(sizeLabel);
-
-                for (const label of h.matchFileLabels(files, fileRules)) {
-                  labels.add(label);
-                }
-
-                // Title labels
-                const { labels: titleLabels } = h.matchTitleLabels(pr.title ?? '');
-                for (const tl of titleLabels) labels.add(tl);
-
-                // Ensure all labels exist before batch add
-                for (const name of labels) {
-                  await h.ensureLabel(name);
-                }
-
-                // Remove stale managed labels
-                const currentLabels = (await github.paginate(
-                  github.rest.issues.listLabelsOnIssue,
-                  { owner, repo, issue_number: pr.number, per_page: 100 },
-                )).map(l => l.name ?? '');
-
-                const managed = [...h.sizeLabels, ...h.tierLabels, ...h.allTypeLabels];
-                for (const name of currentLabels) {
-                  if (managed.includes(name) && !labels.has(name)) {
-                    try {
-                      await github.rest.issues.removeLabel({
-                        owner, repo, issue_number: pr.number, name,
-                      });
-                    } catch (e) {
-                      if (e.status !== 404) throw e;
-                    }
-                  }
-                }
-
-                await github.rest.issues.addLabels({
-                  owner, repo, issue_number: pr.number, labels: [...labels],
-                });
-                console.log(`PR #${pr.number} (${author}): ${[...labels].join(', ')}`);
-                processed++;
-              } catch (e) {
-                failures++;
-                core.warning(`Failed to process PR #${pr.number}: ${e.message}`);
-              }
-            }
-
-            console.log(`\nBackfill complete. Processed ${processed} PRs, ${failures} failures. ${contributorCache.size} unique authors.`);

.github/workflows/pr_lint.yml

@@ -1,128 +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(langchain): resolve error
-#     docs: update API usage examples
-#     docs(openai): update API usage examples
-#
-# Allowed Types:
-#   * feat       — a new feature (MINOR)
-#   * fix        — a bug fix (PATCH)
-#   * docs       — documentation only changes
-#   * style      — formatting, linting, etc.; no code change or typing refactors
-#   * refactor   — code change that neither fixes a bug nor adds a feature
-#   * perf       — code change that improves performance
-#   * test       — adding tests or correcting existing
-#   * build      — changes that affect the build system/external dependencies
-#   * ci         — continuous integration/configuration changes
-#   * chore      — other changes that don't modify source or test files
-#   * revert     — reverts a previous commit
-#   * release    — prepare a new release
-#   * hotfix     — urgent fix
-#
-# Allowed Scope(s) (optional):
-#   core, langchain, langchain-classic, model-profiles,
-#   standard-tests, text-splitters, docs, anthropic, chroma, deepseek, exa,
-#   fireworks, groq, huggingface, mistralai, nomic, ollama, openai,
-#   perplexity, qdrant, xai, infra, deps, partners
-#
-# Multiple scopes can be used by separating them with a comma. For example:
-#
-#   feat(core,langchain): add multi‐tenant support to core and langchain
-#
-# Note: PRs touching the langchain package should use the 'langchain' scope. It is not
-#   acceptable to omit the scope for changes to the langchain package, despite it being
-#   the main package & name of the repo.
-#
-# Rules:
-#   1. The 'Type' must start with a lowercase letter.
-#   2. Breaking changes: append "!" after type/scope (e.g., feat!: drop x support)
-#   3. When releasing (updating the pyproject.toml and uv.lock), the commit message
-#      should be: `release(scope): x.y.z` (e.g., `release(core): 1.2.0` with no
-#      body, footer, or preceeding/proceeding text).
-#
-# Enforces Conventional Commits format for pull request titles to maintain a clear and
-# machine-readable change history.
-
-name: "🏷️ PR Title Lint"
-
-permissions:
-  pull-requests: read
-
-on:
-  pull_request:
-    types: [opened, edited, synchronize]
-
-jobs:
-  # Validates that PR title follows Conventional Commits 1.0.0 specification
-  lint-pr-title:
-    name: "validate format"
-    runs-on: ubuntu-latest
-    steps:
-      - name: "🚫 Reject empty scope"
-        env:
-          PR_TITLE: ${{ github.event.pull_request.title }}
-        run: |
-          if [[ "$PR_TITLE" =~ ^[a-z]+\(\)[!]?: ]]; then
-            echo "::error::PR title has empty scope parentheses: '$PR_TITLE'"
-            echo "Either remove the parentheses or provide a scope (e.g., 'fix(core): ...')."
-            exit 1
-          fi
-      - name: "✅ Validate Conventional Commits Format"
-        uses: amannn/action-semantic-pull-request@48f256284bd46cdaab1048c3721360e808335d50 # v6
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        with:
-          types: |
-            feat
-            fix
-            docs
-            style
-            refactor
-            perf
-            test
-            build
-            ci
-            chore
-            revert
-            release
-            hotfix
-          scopes: |
-            core
-            langchain
-            langchain-classic
-            model-profiles
-            standard-tests
-            text-splitters
-            docs
-            anthropic
-            chroma
-            deepseek
-            exa
-            fireworks
-            groq
-            huggingface
-            mistralai
-            nomic
-            ollama
-            openai
-            openrouter
-            perplexity
-            qdrant
-            xai
-            infra
-            deps
-            partners
-          requireScope: false
-          disallowScopes: |
-            release
-            [A-Z]+
-          ignoreLabels: |
-            ignore-lint-pr-title

.github/workflows/refresh_model_profiles.yml

@@ -1,45 +0,0 @@
-# Refreshes model profile data for all in-monorepo partner integrations by
-# pulling the latest metadata from models.dev via the `langchain-profiles` CLI.
-#
-# Creates a pull request with any changes. Runs daily and can be triggered
-# manually from the Actions UI. Uses a fixed branch so each run supersedes
-# any stale PR from a previous run.
-
-name: "🔄 Refresh Model Profiles"
-
-on:
-  schedule:
-    - cron: "0 8 * * *" # daily at 08:00 UTC
-  workflow_dispatch:
-
-permissions:
-  contents: write
-  pull-requests: write
-
-jobs:
-  refresh-profiles:
-    uses: ./.github/workflows/_refresh_model_profiles.yml
-    with:
-      providers: >-
-        [
-          {"provider":"anthropic",    "data_dir":"libs/partners/anthropic/langchain_anthropic/data"},
-          {"provider":"deepseek",     "data_dir":"libs/partners/deepseek/langchain_deepseek/data"},
-          {"provider":"fireworks-ai", "data_dir":"libs/partners/fireworks/langchain_fireworks/data"},
-          {"provider":"groq",         "data_dir":"libs/partners/groq/langchain_groq/data"},
-          {"provider":"huggingface",  "data_dir":"libs/partners/huggingface/langchain_huggingface/data"},
-          {"provider":"mistral",      "data_dir":"libs/partners/mistralai/langchain_mistralai/data"},
-          {"provider":"openai",       "data_dir":"libs/partners/openai/langchain_openai/data"},
-          {"provider":"openrouter",   "data_dir":"libs/partners/openrouter/langchain_openrouter/data"},
-          {"provider":"perplexity",   "data_dir":"libs/partners/perplexity/langchain_perplexity/data"},
-          {"provider":"xai",          "data_dir":"libs/partners/xai/langchain_xai/data"}
-        ]
-      cli-path: libs/model-profiles
-      add-paths: libs/partners/**/data/_profiles.py
-      pr-body: |
-        Automated refresh of model profile data for all in-monorepo partner
-        integrations via `langchain-profiles refresh`.
-
-        🤖 Generated by the `refresh_model_profiles` workflow.
-    secrets:
-      MODEL_PROFILE_BOT_APP_ID: ${{ secrets.MODEL_PROFILE_BOT_APP_ID }}
-      MODEL_PROFILE_BOT_PRIVATE_KEY: ${{ secrets.MODEL_PROFILE_BOT_PRIVATE_KEY }}

.github/workflows/reopen_on_assignment.yml

@@ -1,195 +0,0 @@
-# Reopen PRs that were auto-closed by require_issue_link.yml when the
-# contributor was not assigned to the linked issue. When a maintainer
-# assigns the contributor to the issue, this workflow finds matching
-# closed PRs, verifies the issue link, and reopens them.
-#
-# Uses the default GITHUB_TOKEN (not a PAT or app token) so that the
-# reopen and label-removal events do NOT re-trigger other workflows.
-# GitHub suppresses events created by the default GITHUB_TOKEN within
-# workflow runs to prevent infinite loops.
-
-name: Reopen PR on Issue Assignment
-
-on:
-  issues:
-    types: [assigned]
-
-permissions:
-  contents: read
-
-jobs:
-  reopen-linked-prs:
-    runs-on: ubuntu-latest
-    permissions:
-      actions: write
-      pull-requests: write
-
-    steps:
-      - name: Find and reopen matching PRs
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
-        with:
-          script: |
-            const { owner, repo } = context.repo;
-            const issueNumber = context.payload.issue.number;
-            const assignee = context.payload.assignee.login;
-
-            console.log(
-              `Issue #${issueNumber} assigned to ${assignee} — searching for closed PRs to reopen`,
-            );
-
-            const q = [
-              `is:pr`,
-              `is:closed`,
-              `author:${assignee}`,
-              `label:missing-issue-link`,
-              `repo:${owner}/${repo}`,
-            ].join(' ');
-
-            let data;
-            try {
-              ({ data } = await github.rest.search.issuesAndPullRequests({
-                q,
-                per_page: 30,
-              }));
-            } catch (e) {
-              throw new Error(
-                `Failed to search for closed PRs to reopen after assigning ${assignee} ` +
-                `to #${issueNumber} (HTTP ${e.status ?? 'unknown'}): ${e.message}`,
-              );
-            }
-
-            if (data.total_count === 0) {
-              console.log('No matching closed PRs found');
-              return;
-            }
-
-            console.log(`Found ${data.total_count} candidate PR(s)`);
-
-            // Must stay in sync with the identical pattern in require_issue_link.yml
-            const pattern = /(?:close[sd]?|fix(?:e[sd])?|resolve[sd]?)\s*#(\d+)/gi;
-
-            for (const item of data.items) {
-              const prNumber = item.number;
-              const body = item.body || '';
-              const matches = [...body.matchAll(pattern)];
-              const referencedIssues = matches.map(m => parseInt(m[1], 10));
-
-              if (!referencedIssues.includes(issueNumber)) {
-                console.log(`PR #${prNumber} does not reference #${issueNumber} — skipping`);
-                continue;
-              }
-
-              // Skip if already bypassed
-              const labels = item.labels.map(l => l.name);
-              if (labels.includes('bypass-issue-check')) {
-                console.log(`PR #${prNumber} already has bypass-issue-check — skipping`);
-                continue;
-              }
-
-              // Reopen first, remove label second — a closed PR that still has
-              // missing-issue-link is recoverable; a closed PR with the label
-              // stripped is invisible to both workflows.
-              try {
-                await github.rest.pulls.update({
-                  owner,
-                  repo,
-                  pull_number: prNumber,
-                  state: 'open',
-                });
-                console.log(`Reopened PR #${prNumber}`);
-              } catch (e) {
-                if (e.status === 422) {
-                  // Head branch deleted — PR is unrecoverable. Notify the
-                  // contributor so they know to open a new PR.
-                  core.warning(`Cannot reopen PR #${prNumber}: head branch was likely deleted`);
-                  try {
-                    await github.rest.issues.createComment({
-                      owner,
-                      repo,
-                      issue_number: prNumber,
-                      body:
-                        `You have been assigned to #${issueNumber}, but this PR could not be ` +
-                        `reopened because the head branch has been deleted. Please open a new ` +
-                        `PR referencing the issue.`,
-                    });
-                  } catch (commentErr) {
-                    core.warning(
-                      `Also failed to post comment on PR #${prNumber}: ${commentErr.message}`,
-                    );
-                  }
-                  continue;
-                }
-                // Transient errors (rate limit, 5xx) should fail the job so
-                // the label is NOT removed and the run can be retried.
-                throw e;
-              }
-
-              // Remove missing-issue-link label only after successful reopen
-              try {
-                await github.rest.issues.removeLabel({
-                  owner,
-                  repo,
-                  issue_number: prNumber,
-                  name: 'missing-issue-link',
-                });
-                console.log(`Removed missing-issue-link from PR #${prNumber}`);
-              } catch (e) {
-                if (e.status !== 404) throw e;
-              }
-
-              // Minimize stale enforcement comment (best-effort;
-              // sync w/ require_issue_link.yml minimize blocks)
-              try {
-                const marker = '<!-- require-issue-link -->';
-                const comments = await github.paginate(
-                  github.rest.issues.listComments,
-                  { owner, repo, issue_number: prNumber, per_page: 100 },
-                );
-                const stale = comments.find(c => c.body && c.body.includes(marker));
-                if (stale) {
-                  await github.graphql(`
-                    mutation($id: ID!) {
-                      minimizeComment(input: {subjectId: $id, classifier: OUTDATED}) {
-                        minimizedComment { isMinimized }
-                      }
-                    }
-                  `, { id: stale.node_id });
-                  console.log(`Minimized stale enforcement comment ${stale.id} as outdated`);
-                }
-              } catch (e) {
-                core.warning(`Could not minimize stale comment on PR #${prNumber}: ${e.message}`);
-              }
-
-              // Re-run the failed require_issue_link check so it picks up the
-              // new assignment.  The re-run uses the original event payload but
-              // fetches live issue data, so the assignment check will pass.
-              //
-              // Limitation: we look up runs by the PR's current head SHA.  If the
-              // contributor pushed new commits while the PR was closed, head.sha
-              // won't match the SHA of the original failed run and the query will
-              // return 0 results.  This is acceptable because any push after reopen
-              // triggers a fresh require_issue_link run against the new SHA.
-              try {
-                const { data: pr } = await github.rest.pulls.get({
-                  owner, repo, pull_number: prNumber,
-                });
-                const { data: runs } = await github.rest.actions.listWorkflowRuns({
-                  owner, repo,
-                  workflow_id: 'require_issue_link.yml',
-                  head_sha: pr.head.sha,
-                  status: 'failure',
-                  per_page: 1,
-                });
-                if (runs.workflow_runs.length > 0) {
-                  await github.rest.actions.reRunWorkflowFailedJobs({
-                    owner, repo,
-                    run_id: runs.workflow_runs[0].id,
-                  });
-                  console.log(`Re-ran failed require_issue_link run ${runs.workflow_runs[0].id} for PR #${prNumber}`);
-                } else {
-                  console.log(`No failed require_issue_link runs found for PR #${prNumber} — skipping re-run`);
-                }
-              } catch (e) {
-                core.warning(`Could not re-run require_issue_link check for PR #${prNumber} (HTTP ${e.status ?? 'unknown'}): ${e.message}`);
-              }
-            }

.github/workflows/require_issue_link.yml

@@ -1,467 +0,0 @@
-# Require external PRs to reference an approved issue (e.g. Fixes #NNN) and
-# the PR author to be assigned to that issue. On failure the PR is
-# labeled "missing-issue-link", commented on, and closed.
-#
-# Maintainer override: an org member can reopen the PR or remove
-# "missing-issue-link" — both add "bypass-issue-check" and reopen.
-#
-# Dependency: pr_labeler.yml must apply the "external" label first. This
-# workflow does NOT trigger on "opened" (new PRs have no labels yet, so the
-# gate would always skip).
-
-name: Require Issue Link
-
-on:
-  pull_request_target:
-    # NEVER CHECK OUT UNTRUSTED CODE FROM A PR's HEAD IN A pull_request_target JOB.
-    # Doing so would allow attackers to execute arbitrary code in the context of your repository.
-    types: [edited, reopened, labeled, unlabeled]
-
-# ──────────────────────────────────────────────────────────────────────────────
-# Enforcement gate: set to 'true' to activate the issue link requirement.
-# When 'false', the workflow still runs the check logic (useful for dry-run
-# visibility) but will NOT label, comment, close, or fail PRs.
-# ──────────────────────────────────────────────────────────────────────────────
-env:
-  ENFORCE_ISSUE_LINK: "true"
-
-permissions:
-  contents: read
-
-jobs:
-  check-issue-link:
-    # Run when the "external" label is added, on edit/reopen if already labeled,
-    # or when "missing-issue-link" is removed (triggers maintainer override check).
-    # Skip entirely when the PR already carries "trusted-contributor" or
-    # "bypass-issue-check".
-    if: >-
-      !contains(github.event.pull_request.labels.*.name, 'trusted-contributor') &&
-      !contains(github.event.pull_request.labels.*.name, 'bypass-issue-check') &&
-      (
-        (github.event.action == 'labeled' && github.event.label.name == 'external') ||
-        (github.event.action == 'unlabeled' && github.event.label.name == 'missing-issue-link' && contains(github.event.pull_request.labels.*.name, 'external')) ||
-        (github.event.action != 'labeled' && github.event.action != 'unlabeled' && contains(github.event.pull_request.labels.*.name, 'external'))
-      )
-    runs-on: ubuntu-latest
-    permissions:
-      actions: write
-      pull-requests: write
-
-    steps:
-      - name: Check for issue link and assignee
-        id: check-link
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
-        with:
-          script: |
-            const { owner, repo } = context.repo;
-            const prNumber = context.payload.pull_request.number;
-            const action = context.payload.action;
-
-            // ── Helper: ensure a label exists, then add it to the PR ────────
-            async function ensureAndAddLabel(labelName, color) {
-              try {
-                await github.rest.issues.getLabel({ owner, repo, name: labelName });
-              } catch (e) {
-                if (e.status !== 404) throw e;
-                try {
-                  await github.rest.issues.createLabel({ owner, repo, name: labelName, color });
-                } catch (createErr) {
-                  // 422 = label was created by a concurrent run between our
-                  // GET and POST — safe to ignore.
-                  if (createErr.status !== 422) throw createErr;
-                }
-              }
-              await github.rest.issues.addLabels({
-                owner, repo, issue_number: prNumber, labels: [labelName],
-              });
-            }
-
-            // ── Helper: check if the user who triggered this event (reopened
-            // the PR / removed the label) has write+ access on the repo ───
-            // Uses the repo collaborator permission endpoint instead of the
-            // org membership endpoint. The org endpoint requires the caller
-            // to be an org member, which GITHUB_TOKEN (an app installation
-            // token) never is — so it always returns 403.
-            async function senderIsOrgMember() {
-              const sender = context.payload.sender?.login;
-              if (!sender) {
-                throw new Error('Event has no sender — cannot check permissions');
-              }
-              try {
-                const { data } = await github.rest.repos.getCollaboratorPermissionLevel({
-                  owner, repo, username: sender,
-                });
-                const perm = data.permission;
-                if (['admin', 'maintain', 'write'].includes(perm)) {
-                  console.log(`${sender} has ${perm} permission — treating as maintainer`);
-                  return { isMember: true, login: sender };
-                }
-                console.log(`${sender} has ${perm} permission — not a maintainer`);
-                return { isMember: false, login: sender };
-              } catch (e) {
-                if (e.status === 404) {
-                  console.log(`Cannot check permissions for ${sender} — treating as non-maintainer`);
-                  return { isMember: false, login: sender };
-                }
-                const status = e.status ?? 'unknown';
-                throw new Error(
-                  `Permission check failed for ${sender} (HTTP ${status}): ${e.message}`,
-                );
-              }
-            }
-
-            // ── Helper: apply maintainer bypass (shared by both override paths) ──
-            async function applyMaintainerBypass(reason) {
-              console.log(reason);
-
-              // Remove missing-issue-link if present
-              try {
-                await github.rest.issues.removeLabel({
-                  owner, repo, issue_number: prNumber, name: 'missing-issue-link',
-                });
-              } catch (e) {
-                if (e.status !== 404) throw e;
-              }
-
-              // Reopen before adding bypass label — a failed reopen is more
-              // actionable than a closed PR with a bypass label stuck on it.
-              if (context.payload.pull_request.state === 'closed') {
-                try {
-                  await github.rest.pulls.update({
-                    owner, repo, pull_number: prNumber, state: 'open',
-                  });
-                  console.log(`Reopened PR #${prNumber}`);
-                } catch (e) {
-                  // 422 if head branch deleted; 403 if permissions insufficient.
-                  // Bypass labels still apply — maintainer can reopen manually.
-                  core.warning(
-                    `Could not reopen PR #${prNumber} (HTTP ${e.status ?? 'unknown'}): ${e.message}. ` +
-                    `Bypass labels were applied — a maintainer may need to reopen manually.`,
-                  );
-                }
-              }
-
-              // Add bypass-issue-check so future triggers skip enforcement
-              await ensureAndAddLabel('bypass-issue-check', '0e8a16');
-
-              // Minimize stale enforcement comment (best-effort; must not
-              // abort bypass — sync w/ reopen_on_assignment.yml & step below)
-              try {
-                const marker = '<!-- require-issue-link -->';
-                const comments = await github.paginate(
-                  github.rest.issues.listComments,
-                  { owner, repo, issue_number: prNumber, per_page: 100 },
-                );
-                const stale = comments.find(c => c.body && c.body.includes(marker));
-                if (stale) {
-                  await github.graphql(`
-                    mutation($id: ID!) {
-                      minimizeComment(input: {subjectId: $id, classifier: OUTDATED}) {
-                        minimizedComment { isMinimized }
-                      }
-                    }
-                  `, { id: stale.node_id });
-                  console.log(`Minimized stale enforcement comment ${stale.id} as outdated`);
-                }
-              } catch (e) {
-                core.warning(`Could not minimize stale comment on PR #${prNumber}: ${e.message}`);
-              }
-
-              core.setOutput('has-link', 'true');
-              core.setOutput('is-assigned', 'true');
-            }
-
-            // ── Maintainer override: removed "missing-issue-link" label ─────
-            if (action === 'unlabeled') {
-              const { isMember, login } = await senderIsOrgMember();
-              if (isMember) {
-                await applyMaintainerBypass(
-                  `Maintainer ${login} removed missing-issue-link from PR #${prNumber} — bypassing enforcement`,
-                );
-                return;
-              }
-              // Non-member removed the label — re-add it defensively and
-              // set failure outputs so downstream steps (comment, close) fire.
-              // NOTE: addLabels fires a "labeled" event, but the job-level gate
-              // only matches labeled events for "external", so no re-trigger.
-              console.log(`Non-member ${login} removed missing-issue-link — re-adding`);
-              try {
-                await ensureAndAddLabel('missing-issue-link', 'b76e79');
-              } catch (e) {
-                core.warning(
-                  `Failed to re-add missing-issue-link (HTTP ${e.status ?? 'unknown'}): ${e.message}. ` +
-                  `Downstream step will retry.`,
-                );
-              }
-              core.setOutput('has-link', 'false');
-              core.setOutput('is-assigned', 'false');
-              return;
-            }
-
-            // ── Maintainer override: reopened PR with "missing-issue-link" ──
-            const prLabels = context.payload.pull_request.labels.map(l => l.name);
-            if (action === 'reopened' && prLabels.includes('missing-issue-link')) {
-              const { isMember, login } = await senderIsOrgMember();
-              if (isMember) {
-                await applyMaintainerBypass(
-                  `Maintainer ${login} reopened PR #${prNumber} — bypassing enforcement`,
-                );
-                return;
-              }
-              console.log(`Non-member ${login} reopened PR — proceeding with check`);
-            }
-
-            // ── Fetch live labels (race guard) ──────────────────────────────
-            const { data: liveLabels } = await github.rest.issues.listLabelsOnIssue({
-              owner, repo, issue_number: prNumber,
-            });
-            const liveNames = liveLabels.map(l => l.name);
-            if (liveNames.includes('trusted-contributor') || liveNames.includes('bypass-issue-check')) {
-              console.log('PR has trusted-contributor or bypass-issue-check label — bypassing');
-              core.setOutput('has-link', 'true');
-              core.setOutput('is-assigned', 'true');
-              return;
-            }
-
-            const body = context.payload.pull_request.body || '';
-            const pattern = /(?:close[sd]?|fix(?:e[sd])?|resolve[sd]?)\s*#(\d+)/gi;
-            const matches = [...body.matchAll(pattern)];
-
-            if (matches.length === 0) {
-              console.log('No issue link found in PR body');
-              core.setOutput('has-link', 'false');
-              core.setOutput('is-assigned', 'false');
-              return;
-            }
-
-            const issues = matches.map(m => `#${m[1]}`).join(', ');
-            console.log(`Found issue link(s): ${issues}`);
-            core.setOutput('has-link', 'true');
-
-            // Check whether the PR author is assigned to at least one linked issue
-            const prAuthor = context.payload.pull_request.user.login;
-            const MAX_ISSUES = 5;
-            const allIssueNumbers = [...new Set(matches.map(m => parseInt(m[1], 10)))];
-            const issueNumbers = allIssueNumbers.slice(0, MAX_ISSUES);
-            if (allIssueNumbers.length > MAX_ISSUES) {
-              core.warning(
-                `PR references ${allIssueNumbers.length} issues — only checking the first ${MAX_ISSUES}`,
-              );
-            }
-
-            let assignedToAny = false;
-            for (const num of issueNumbers) {
-              try {
-                const { data: issue } = await github.rest.issues.get({
-                  owner, repo, issue_number: num,
-                });
-                const assignees = issue.assignees.map(a => a.login.toLowerCase());
-                if (assignees.includes(prAuthor.toLowerCase())) {
-                  console.log(`PR author "${prAuthor}" is assigned to #${num}`);
-                  assignedToAny = true;
-                  break;
-                } else {
-                  console.log(`PR author "${prAuthor}" is NOT assigned to #${num} (assignees: ${assignees.join(', ') || 'none'})`);
-                }
-              } catch (error) {
-                if (error.status === 404) {
-                  console.log(`Issue #${num} not found — skipping`);
-                } else {
-                  // Non-404 errors (rate limit, server error) must not be
-                  // silently skipped — they could cause false enforcement
-                  // (closing a legitimate PR whose assignment can't be verified).
-                  throw new Error(
-                    `Cannot verify assignee for issue #${num} (${error.status}): ${error.message}`,
-                  );
-                }
-              }
-            }
-
-            core.setOutput('is-assigned', assignedToAny ? 'true' : 'false');
-
-      - name: Add missing-issue-link label
-        if: >-
-          env.ENFORCE_ISSUE_LINK == 'true' &&
-          (steps.check-link.outputs.has-link != 'true' || steps.check-link.outputs.is-assigned != 'true')
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
-        with:
-          script: |
-            const { owner, repo } = context.repo;
-            const prNumber = context.payload.pull_request.number;
-            const labelName = 'missing-issue-link';
-
-            // Ensure the label exists (no checkout/shared helper available)
-            try {
-              await github.rest.issues.getLabel({ owner, repo, name: labelName });
-            } catch (e) {
-              if (e.status !== 404) throw e;
-              try {
-                await github.rest.issues.createLabel({
-                  owner, repo, name: labelName, color: 'b76e79',
-                });
-              } catch (createErr) {
-                if (createErr.status !== 422) throw createErr;
-              }
-            }
-
-            await github.rest.issues.addLabels({
-              owner, repo, issue_number: prNumber, labels: [labelName],
-            });
-
-      - name: Remove missing-issue-link label and reopen PR
-        if: >-
-          env.ENFORCE_ISSUE_LINK == 'true' &&
-          steps.check-link.outputs.has-link == 'true' && steps.check-link.outputs.is-assigned == 'true'
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
-        with:
-          script: |
-            const { owner, repo } = context.repo;
-            const prNumber = context.payload.pull_request.number;
-            try {
-              await github.rest.issues.removeLabel({
-                owner, repo, issue_number: prNumber, name: 'missing-issue-link',
-              });
-            } catch (error) {
-              if (error.status !== 404) throw error;
-            }
-
-            // Reopen if this workflow previously closed the PR. We check the
-            // event payload labels (not live labels) because we already removed
-            // missing-issue-link above; the payload still reflects pre-step state.
-            const labels = context.payload.pull_request.labels.map(l => l.name);
-            if (context.payload.pull_request.state === 'closed' && labels.includes('missing-issue-link')) {
-              await github.rest.pulls.update({
-                owner,
-                repo,
-                pull_number: prNumber,
-                state: 'open',
-              });
-              console.log(`Reopened PR #${prNumber}`);
-            }
-
-            // Minimize stale enforcement comment (best-effort;
-            // sync w/ applyMaintainerBypass above & reopen_on_assignment.yml)
-            try {
-              const marker = '<!-- require-issue-link -->';
-              const comments = await github.paginate(
-                github.rest.issues.listComments,
-                { owner, repo, issue_number: prNumber, per_page: 100 },
-              );
-              const stale = comments.find(c => c.body && c.body.includes(marker));
-              if (stale) {
-                await github.graphql(`
-                  mutation($id: ID!) {
-                    minimizeComment(input: {subjectId: $id, classifier: OUTDATED}) {
-                      minimizedComment { isMinimized }
-                    }
-                  }
-                `, { id: stale.node_id });
-                console.log(`Minimized stale enforcement comment ${stale.id} as outdated`);
-              }
-            } catch (e) {
-              core.warning(`Could not minimize stale comment on PR #${prNumber}: ${e.message}`);
-            }
-
-      - name: Post comment, close PR, and fail
-        if: >-
-          env.ENFORCE_ISSUE_LINK == 'true' &&
-          (steps.check-link.outputs.has-link != 'true' || steps.check-link.outputs.is-assigned != 'true')
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
-        with:
-          script: |
-            const { owner, repo } = context.repo;
-            const prNumber = context.payload.pull_request.number;
-            const hasLink = '${{ steps.check-link.outputs.has-link }}' === 'true';
-            const isAssigned = '${{ steps.check-link.outputs.is-assigned }}' === 'true';
-            const marker = '<!-- require-issue-link -->';
-
-            let lines;
-            if (!hasLink) {
-              lines = [
-                marker,
-                '**This PR has been automatically closed** because it does not link to an approved issue.',
-                '',
-                'All external contributions must reference an approved issue or discussion. Please:',
-                '1. Find or [open an issue](https://github.com/' + owner + '/' + repo + '/issues/new/choose) describing the change',
-                '2. Wait for a maintainer to approve and assign you',
-                '3. Add `Fixes #<issue_number>`, `Closes #<issue_number>`, or `Resolves #<issue_number>` to your PR description and the PR will be reopened automatically',
-                '',
-                '*Maintainers: reopen this PR or remove the `missing-issue-link` label to bypass this check.*',
-              ];
-            } else {
-              lines = [
-                marker,
-                '**This PR has been automatically closed** because you are not assigned to the linked issue.',
-                '',
-                'External contributors must be assigned to an issue before opening a PR for it. Please:',
-                '1. Comment on the linked issue to request assignment from a maintainer',
-                '2. Once assigned, your PR will be reopened automatically',
-                '',
-                '*Maintainers: reopen this PR or remove the `missing-issue-link` label to bypass this check.*',
-              ];
-            }
-
-            const body = lines.join('\n');
-
-            // Deduplicate: check for existing comment with the marker
-            const comments = await github.paginate(
-              github.rest.issues.listComments,
-              { owner, repo, issue_number: prNumber, per_page: 100 },
-            );
-            const existing = comments.find(c => c.body && c.body.includes(marker));
-
-            if (!existing) {
-              await github.rest.issues.createComment({
-                owner,
-                repo,
-                issue_number: prNumber,
-                body,
-              });
-              console.log('Posted requirement comment');
-            } else if (existing.body !== body) {
-              await github.rest.issues.updateComment({
-                owner,
-                repo,
-                comment_id: existing.id,
-                body,
-              });
-              console.log('Updated existing comment with new message');
-            } else {
-              console.log('Comment already exists — skipping');
-            }
-
-            // Close the PR
-            if (context.payload.pull_request.state === 'open') {
-              await github.rest.pulls.update({
-                owner,
-                repo,
-                pull_number: prNumber,
-                state: 'closed',
-              });
-              console.log(`Closed PR #${prNumber}`);
-            }
-
-            // Cancel all other in-progress and queued workflow runs for this PR
-            const headSha = context.payload.pull_request.head.sha;
-            for (const status of ['in_progress', 'queued']) {
-              const runs = await github.paginate(
-                github.rest.actions.listWorkflowRunsForRepo,
-                { owner, repo, head_sha: headSha, status, per_page: 100 },
-              );
-              for (const run of runs) {
-                if (run.id === context.runId) continue;
-                try {
-                  await github.rest.actions.cancelWorkflowRun({
-                    owner, repo, run_id: run.id,
-                  });
-                  console.log(`Cancelled ${status} run ${run.id} (${run.name})`);
-                } catch (err) {
-                  console.log(`Could not cancel run ${run.id}: ${err.message}`);
-                }
-              }
-            }
-
-            const reason = !hasLink
-              ? 'PR must reference an issue using auto-close keywords (e.g., "Fixes #123").'
-              : 'PR author must be assigned to the linked issue.';
-            core.setFailed(reason);

.github/workflows/scheduled_test.yml

@@ -0,0 +1,83 @@
+name: Scheduled tests
+
+on:
+  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
+  schedule:
+    - cron:  '0 13 * * *'
+
+env:
+  POETRY_VERSION: "1.7.1"
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.11"
+        working-directory:
+          - "libs/partners/openai"
+          - "libs/partners/anthropic"
+          - "libs/partners/ai21"
+          - "libs/partners/fireworks"
+          - "libs/partners/groq"
+          - "libs/partners/mistralai"
+          - "libs/partners/together"
+    name: Python ${{ matrix.python-version }} - ${{ matrix.working-directory }}
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: "./.github/actions/poetry_setup"
+        with:
+          python-version: ${{ matrix.python-version }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: ${{ matrix.working-directory }}
+          cache-key: scheduled
+
+      - name: 'Authenticate to Google Cloud'
+        id: 'auth'
+        uses: google-github-actions/auth@v2
+        with:
+          credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
+
+      - name: Install dependencies
+        working-directory: ${{ matrix.working-directory }}
+        shell: bash
+        run: |
+          echo "Running scheduled tests, installing dependencies with poetry..."
+          poetry install --with=test_integration,test
+
+      - name: Run integration tests
+        working-directory: ${{ matrix.working-directory }}
+        shell: bash
+        env:
+          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+          AZURE_OPENAI_API_VERSION: ${{ secrets.AZURE_OPENAI_API_VERSION }}
+          AZURE_OPENAI_API_BASE: ${{ secrets.AZURE_OPENAI_API_BASE }}
+          AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
+          AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_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 }}
+          AI21_API_KEY: ${{ secrets.AI21_API_KEY }}
+          FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
+          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
+          MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
+          TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
+        run: |
+          make integration_test
+
+      - name: Ensure the tests did not create any additional files
+        working-directory: ${{ matrix.working-directory }}
+        shell: bash
+        run: |
+          set -eu
+
+          STATUS="$(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/tag-external-issues.yml

@@ -1,205 +0,0 @@
-# Automatically tag issues as "external" or "internal" based on whether
-# the author is a member of the langchain-ai GitHub organization, and
-# apply contributor tier labels to external contributors based on their
-# merged PR history.
-#
-# NOTE: PR labeling (including external/internal, tier, size, file, and
-# title labels) is handled by pr_labeler.yml. This workflow handles
-# issues only.
-#
-# Config (trustedThreshold, labelColor) is read from
-# .github/scripts/pr-labeler-config.json to stay in sync with
-# pr_labeler.yml.
-#
-# Setup Requirements:
-# 1. Create a GitHub App with permissions:
-#    - Repository: Issues (write)
-#    - Organization: Members (read)
-# 2. Install the app on your organization and this repository
-# 3. Add these repository secrets:
-#    - ORG_MEMBERSHIP_APP_ID: Your app's ID
-#    - ORG_MEMBERSHIP_APP_PRIVATE_KEY: Your app's private key
-#
-# The GitHub App token is required to check private organization membership.
-# Without it, the workflow will fail.
-
-name: Tag External Issues
-
-on:
-  issues:
-    types: [opened]
-  workflow_dispatch:
-    inputs:
-      max_items:
-        description: "Maximum number of open issues to process"
-        default: "100"
-        type: string
-
-permissions:
-  contents: read
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.issue.number || github.run_id }}
-  cancel-in-progress: true
-
-jobs:
-  tag-external:
-    if: github.event_name != 'workflow_dispatch'
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      issues: write
-
-    steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-
-      - name: Generate GitHub App token
-        id: app-token
-        uses: actions/create-github-app-token@f8d387b68d61c58ab83c6c016672934102569859 # v3
-        with:
-          app-id: ${{ secrets.ORG_MEMBERSHIP_APP_ID }}
-          private-key: ${{ secrets.ORG_MEMBERSHIP_APP_PRIVATE_KEY }}
-
-      - name: Check if contributor is external
-        if: steps.app-token.outcome == 'success'
-        id: check-membership
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
-        with:
-          github-token: ${{ steps.app-token.outputs.token }}
-          script: |
-            const { owner, repo } = context.repo;
-            const { h } = require('./.github/scripts/pr-labeler.js').loadAndInit(github, owner, repo, core);
-
-            const author = context.payload.sender.login;
-            const { isExternal } = await h.checkMembership(
-              author, context.payload.sender.type,
-            );
-            core.setOutput('is-external', isExternal ? 'true' : 'false');
-
-      - name: Apply contributor tier label
-        if: steps.check-membership.outputs.is-external == 'true'
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
-        with:
-          # GITHUB_TOKEN is fine here — no downstream workflow chains
-          # off tier labels on issues (unlike PRs where App token is
-          # needed for require_issue_link.yml).
-          github-token: ${{ secrets.GITHUB_TOKEN }}
-          script: |
-            const { owner, repo } = context.repo;
-            const { h } = require('./.github/scripts/pr-labeler.js').loadAndInit(github, owner, repo, core);
-
-            const issue = context.payload.issue;
-            // new-contributor is only meaningful on PRs, not issues
-            await h.applyTierLabel(issue.number, issue.user.login, { skipNewContributor: true });
-
-      - name: Add external/internal label
-        if: steps.check-membership.outputs.is-external != ''
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
-        with:
-          github-token: ${{ secrets.GITHUB_TOKEN }}
-          script: |
-            const { owner, repo } = context.repo;
-            const issue_number = context.payload.issue.number;
-
-            const { h } = require('./.github/scripts/pr-labeler.js').loadAndInit(github, owner, repo, core);
-
-            const label = '${{ steps.check-membership.outputs.is-external }}' === 'true'
-              ? 'external' : 'internal';
-            await h.ensureLabel(label);
-            await github.rest.issues.addLabels({
-              owner, repo, issue_number, labels: [label],
-            });
-            console.log(`Added '${label}' label to issue #${issue_number}`);
-
-  backfill:
-    if: github.event_name == 'workflow_dispatch'
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      issues: write
-
-    steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-
-      - name: Generate GitHub App token
-        id: app-token
-        uses: actions/create-github-app-token@f8d387b68d61c58ab83c6c016672934102569859 # v3
-        with:
-          app-id: ${{ secrets.ORG_MEMBERSHIP_APP_ID }}
-          private-key: ${{ secrets.ORG_MEMBERSHIP_APP_PRIVATE_KEY }}
-
-      - name: Backfill labels on open issues
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
-        with:
-          github-token: ${{ steps.app-token.outputs.token }}
-          script: |
-            const { owner, repo } = context.repo;
-            const rawMax = '${{ inputs.max_items }}';
-            const maxItems = parseInt(rawMax, 10);
-            if (isNaN(maxItems) || maxItems <= 0) {
-              core.setFailed(`Invalid max_items: "${rawMax}" — must be a positive integer`);
-              return;
-            }
-
-            const { h } = require('./.github/scripts/pr-labeler.js').loadAndInit(github, owner, repo, core);
-
-            const tierLabels = ['trusted-contributor'];
-            for (const name of tierLabels) {
-              await h.ensureLabel(name);
-            }
-
-            const contributorCache = new Map();
-
-            const issues = await github.paginate(github.rest.issues.listForRepo, {
-              owner, repo, state: 'open', per_page: 100,
-            });
-
-            let processed = 0;
-            let failures = 0;
-            for (const issue of issues) {
-              if (processed >= maxItems) break;
-              if (issue.pull_request) continue;
-
-              try {
-                const author = issue.user.login;
-                const info = await h.getContributorInfo(contributorCache, author, issue.user.type);
-
-                const labels = [info.isExternal ? 'external' : 'internal'];
-                if (info.isExternal && info.mergedCount != null && info.mergedCount >= h.trustedThreshold) {
-                  labels.push('trusted-contributor');
-                }
-
-                // Ensure all labels exist before batch add
-                for (const name of labels) {
-                  await h.ensureLabel(name);
-                }
-
-                // Remove stale tier labels
-                const currentLabels = (await github.paginate(
-                  github.rest.issues.listLabelsOnIssue,
-                  { owner, repo, issue_number: issue.number, per_page: 100 },
-                )).map(l => l.name ?? '');
-                for (const name of currentLabels) {
-                  if (tierLabels.includes(name) && !labels.includes(name)) {
-                    try {
-                      await github.rest.issues.removeLabel({
-                        owner, repo, issue_number: issue.number, name,
-                      });
-                    } catch (e) {
-                      if (e.status !== 404) throw e;
-                    }
-                  }
-                }
-
-                await github.rest.issues.addLabels({
-                  owner, repo, issue_number: issue.number, labels,
-                });
-                console.log(`Issue #${issue.number} (${author}): ${labels.join(', ')}`);
-                processed++;
-              } catch (e) {
-                failures++;
-                core.warning(`Failed to process issue #${issue.number}: ${e.message}`);
-              }
-            }
-
-            console.log(`\nBackfill complete. Processed ${processed} issues, ${failures} failures. ${contributorCache.size} unique authors.`);

.github/workflows/v03_api_doc_build.yml

@@ -1,167 +0,0 @@
-# Build the API reference documentation for v0.3 branch.
-#
-# Manual trigger only.
-#
-# Built HTML pushed to langchain-ai/langchain-api-docs-html.
-#
-# Looks for langchain-ai org repos in packages.yml and checks them out.
-# Calls prep_api_docs_build.py.
-
-name: "📚 API Docs (v0.3)"
-run-name: "Build & Deploy API Reference (v0.3)"
-
-on:
-  workflow_dispatch:
-
-permissions:
-  contents: read
-
-env:
-  PYTHON_VERSION: "3.11"
-
-jobs:
-  build:
-    if: github.repository == 'langchain-ai/langchain' || github.event_name != 'schedule'
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-    steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-        with:
-          ref: v0.3
-          path: langchain
-
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-        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@17f66dc6c6a177fafd8b71a6abea6d6340aa1e16 # master
-        with:
-          cmd: |
-            # Extract repos from packages.yml that are in the langchain-ai org
-            # (excluding 'langchain' itself)
-            yq '
-              .packages[]
-              | select(
-                  (
-                    (.repo | test("^langchain-ai/"))
-                    and
-                    (.repo != "langchain-ai/langchain")
-                  )
-                  or
-                  (.include_in_api_ref // false)
-                )
-              | .repo
-            ' langchain/libs/packages.yml
-
-      - name: "📋 Parse YAML & Checkout Repositories"
-        env:
-          REPOS_UNSORTED: ${{ steps.get-unsorted-repos.outputs.result }}
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: |
-          # Get unique repositories
-          REPOS=$(echo "$REPOS_UNSORTED" | sort -u)
-          # Checkout each unique repository
-          for repo in $REPOS; do
-            # Validate repository format (allow any org with proper format)
-            if [[ ! "$repo" =~ ^[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+$ ]]; then
-              echo "Error: Invalid repository format: $repo"
-              exit 1
-            fi
-
-            REPO_NAME=$(echo $repo | cut -d'/' -f2)
-
-            # Additional validation for repo name
-            if [[ ! "$REPO_NAME" =~ ^[a-zA-Z0-9_.-]+$ ]]; then
-              echo "Error: Invalid repository name: $REPO_NAME"
-              exit 1
-            fi
-            echo "Checking out $repo to $REPO_NAME"
-
-            # Special handling for langchain-tavily: checkout by commit hash
-            if [[ "$REPO_NAME" == "langchain-tavily" ]]; then
-              git clone https://github.com/$repo.git $REPO_NAME
-              cd $REPO_NAME
-              git checkout f3515654724a9e87bdfe2c2f509d6cdde646e563
-              cd ..
-            else
-              git clone --depth 1 --branch v0.3 https://github.com/$repo.git $REPO_NAME
-            fi
-          done
-
-      - name: "🐍 Setup Python ${{ env.PYTHON_VERSION }}"
-        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6
-        id: setup-python
-        with:
-          python-version: ${{ env.PYTHON_VERSION }}
-
-      - name: "📦 Install Initial Python Dependencies using uv"
-        working-directory: langchain
-        run: |
-          python -m pip install -U uv
-          python -m uv pip install --upgrade --no-cache-dir pip setuptools pyyaml
-
-      - name: "📦 Organize Library Directories"
-        # Places cloned partner packages into libs/partners structure
-        run: python langchain/.github/scripts/prep_api_docs_build.py
-
-      - name: "🧹 Clear Prior Build"
-        run:
-          # Remove artifacts from prior docs build
-          rm -rf langchain-api-docs-html/api_reference_build/html
-
-      - name: "📦 Install Documentation Dependencies using uv"
-        working-directory: langchain
-        run: |
-          # Install all partner packages in editable mode with overrides
-          python -m uv pip install $(ls ./libs/partners | grep -v azure-ai | xargs -I {} echo "./libs/partners/{}") --overrides ./docs/vercel_overrides.txt --prerelease=allow
-
-          # Install langchain-azure-ai with tools extra
-          python -m uv pip install "./libs/partners/azure-ai[tools]" --overrides ./docs/vercel_overrides.txt --prerelease=allow
-
-          # Install core langchain and other main packages
-          python -m uv pip install libs/core libs/langchain libs/text-splitters libs/community libs/experimental libs/standard-tests
-
-          # Install Sphinx and related packages for building docs
-          python -m uv pip install -r docs/api_reference/requirements.txt
-
-      - name: "🔧 Configure Git Settings"
-        working-directory: langchain
-        run: |
-          git config --local user.email "actions@github.com"
-          git config --local user.name "Github Actions"
-
-      - name: "📚 Build API Documentation"
-        working-directory: langchain
-        run: |
-          # Generate the API reference RST files
-          python docs/api_reference/create_api_rst.py
-
-          # Build the HTML documentation using Sphinx
-          # -T: show full traceback on exception
-          # -E: don't use cached environment (force rebuild, ignore cached doctrees)
-          # -b html: build HTML docs (vs PDS, etc.)
-          # -d: path for the cached environment (parsed document trees / doctrees)
-          #     - Separate from output dir for faster incremental builds
-          # -c: path to conf.py
-          # -j auto: parallel build using all available CPU cores
-          python -m sphinx -T -E -b html -d ../langchain-api-docs-html/_build/doctrees -c docs/api_reference docs/api_reference ../langchain-api-docs-html/api_reference_build/html -j auto
-
-          # Post-process the generated HTML
-          python docs/api_reference/scripts/custom_formatter.py ../langchain-api-docs-html/api_reference_build/html
-
-          # Default index page is blank so we copy in the actual home page.
-          cp ../langchain-api-docs-html/api_reference_build/html/{reference,index}.html
-
-          # Removes Sphinx's intermediate build artifacts after the build is complete.
-          rm -rf ../langchain-api-docs-html/_build/
-
-      # Commit and push changes to langchain-api-docs-html repo
-      - uses: EndBug/add-and-commit@290ea2c423ad77ca9c62ae0f5b224379612c0321 # v10.0.0
-        with:
-          cwd: langchain-api-docs-html
-          message: "Update API docs build from v0.3 branch"

.gitignore

@@ -1,8 +1,6 @@
 .vs/
-.claude/
+.vscode/
 .idea/
-#Emacs backup
-*~
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]
@@ -61,7 +59,6 @@ coverage.xml
 *.py,cover
 .hypothesis/
 .pytest_cache/
-.codspeed/
 
 # Translations
 *.mo
@@ -80,6 +77,10 @@ instance/
 # Scrapy stuff:
 .scrapy
 
+# Sphinx documentation
+docs/_build/
+docs/docs/_build/
+
 # PyBuilder
 target/
 
@@ -132,7 +133,6 @@ env.bak/
 
 # mypy
 .mypy_cache/
-.mypy_cache_test/
 .dmypy.json
 dmypy.json
 
@@ -160,9 +160,21 @@ data_map*
 *replit*
 
 node_modules
+docs/.yarn/
+docs/node_modules/
+docs/.docusaurus/
+docs/.cache-loader/
+docs/_dist
+docs/api_reference/*api_reference.rst
+docs/api_reference/_build
+docs/api_reference/*/
+!docs/api_reference/_static/
+!docs/api_reference/templates/
+!docs/api_reference/themes/
+docs/docs/build
+docs/docs/node_modules
+docs/docs/yarn.lock
+_dist
+docs/docs/templates
 
 prof
-virtualenv/
-scratch/
-
-.langgraph_api/

.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"
-  }
-}

.mcp.json

@@ -1,12 +0,0 @@
-{
-  "mcpServers": {
-    "docs-langchain": {
-      "type": "http",
-      "url": "https://docs.langchain.com/mcp"
-    },
-    "reference-langchain": {
-      "type": "http",
-      "url": "https://reference.langchain.com/mcp"
-    }
-  }
-}

.pre-commit-config.yaml

@@ -1,125 +0,0 @@
-repos:
-  - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.3.0
-    hooks:
-      - id: no-commit-to-branch # prevent direct commits to protected branches
-        args: ["--branch", "master"]
-      - id: check-yaml # validate YAML syntax
-        args: ["--unsafe"] # allow custom tags
-      - id: check-toml # validate TOML syntax
-      - id: end-of-file-fixer # ensure files end with a newline
-      - id: trailing-whitespace # remove trailing whitespace from lines
-        exclude: \.ambr$
-
-  # Text normalization hooks for consistent formatting
-  - repo: https://github.com/sirosen/texthooks
-    rev: 0.6.8
-    hooks:
-      - id: fix-smartquotes # replace curly quotes with straight quotes
-      - id: fix-spaces # replace non-standard spaces (e.g., non-breaking) with regular spaces
-
-  # Per-package format and lint hooks for the monorepo
-  - 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: 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: core-version
-        name: check core version consistency
-        language: system
-        entry: make -C libs/core check_version
-        files: ^libs/core/(pyproject\.toml|langchain_core/version\.py)$
-        pass_filenames: false
-      - id: langchain-v1-version
-        name: check langchain version consistency
-        language: system
-        entry: make -C libs/langchain_v1 check_version
-        files: ^libs/langchain_v1/(pyproject\.toml|langchain/__init__\.py)$
-        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

@@ -1,19 +0,0 @@
-{
-  "recommendations": [
-    "ms-python.python",
-    "charliermarsh.ruff",
-    "ms-python.mypy-type-checker",
-    "ms-toolsai.jupyter",
-    "ms-toolsai.jupyter-keymap",
-    "ms-toolsai.jupyter-renderers",
-    "yzhang.markdown-all-in-one",
-    "davidanson.vscode-markdownlint",
-    "bierner.markdown-mermaid",
-    "bierner.markdown-preview-github-styles",
-    "eamodio.gitlens",
-    "github.vscode-pull-request-github",
-    "github.vscode-github-actions",
-    "redhat.vscode-yaml",
-    "editorconfig.editorconfig",
-  ],
-}

.vscode/settings.json

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

AGENTS.md

@@ -1,267 +0,0 @@
-# Global development guidelines for the LangChain monorepo
-
-This document provides context to understand the LangChain Python project and assist with development.
-
-## Project architecture and context
-
-### Monorepo structure
-
-This is a Python monorepo with multiple independently versioned packages that use `uv`.
-
-```txt
-langchain/
-├── libs/
-│   ├── core/             # `langchain-core` primitives and base abstractions
-│   ├── langchain/        # `langchain-classic` (legacy, no new features)
-│   ├── langchain_v1/     # Actively maintained `langchain` package
-│   ├── partners/         # Third-party integrations
-│   │   ├── openai/       # OpenAI models and embeddings
-│   │   ├── anthropic/    # Anthropic (Claude) integration
-│   │   ├── ollama/       # Local model support
-│   │   └── ... (other integrations maintained by the LangChain team)
-│   ├── text-splitters/   # Document chunking utilities
-│   ├── standard-tests/   # Shared test suite for integrations
-│   ├── model-profiles/   # Model configuration profiles
-├── .github/              # CI/CD workflows and templates
-├── .vscode/              # VSCode IDE standard settings and recommended extensions
-└── README.md             # Information about LangChain
-```
-
-- **Core layer** (`langchain-core`): Base abstractions, interfaces, and protocols. Users should not need to know about this layer directly.
-- **Implementation layer** (`langchain`): Concrete implementations and high-level public utilities
-- **Integration layer** (`partners/`): Third-party service integrations. Note that this monorepo is not exhaustive of all LangChain integrations; some are maintained in separate repos, such as `langchain-ai/langchain-google` and `langchain-ai/langchain-aws`. Usually these repos are cloned at the same level as this monorepo, so if needed, you can refer to their code directly by navigating to `../langchain-google/` from this monorepo.
-- **Testing layer** (`standard-tests/`): Standardized integration tests for partner integrations
-
-### Development tools & commands
-
-- `uv` – Fast Python package installer and resolver (replaces pip/poetry)
-- `make` – Task runner for common development commands. Feel free to look at the `Makefile` for available commands and usage patterns.
-- `ruff` – Fast Python linter and formatter
-- `mypy` – Static type checking
-- `pytest` – Testing framework
-
-This monorepo uses `uv` for dependency management. Local development uses editable installs: `[tool.uv.sources]`
-
-Each package in `libs/` has its own `pyproject.toml` and `uv.lock`.
-
-Before running your tests, set up all packages by running:
-
-```bash
-# For all groups
-uv sync --all-groups
-
-# or, to install a specific group only:
-uv sync --group test
-```
-
-```bash
-# Run unit tests (no network)
-make test
-
-# Run specific test file
-uv run --group test pytest tests/unit_tests/test_specific.py
-```
-
-```bash
-# Lint code
-make lint
-
-# Format code
-make format
-
-# Type checking
-uv run --group lint mypy .
-```
-
-#### Key config files
-
-- pyproject.toml: Main workspace configuration with dependency groups
-- uv.lock: Locked dependencies for reproducible builds
-- Makefile: Development tasks
-
-#### Commit standards
-
-Suggest PR titles that follow Conventional Commits format. Refer to .github/workflows/pr_lint for allowed types and scopes. Note that all commit/PR titles should be in lowercase with the exception of proper nouns/named entities. All PR titles should include a scope with no exceptions. For example:
-
-```txt
-feat(langchain): add new chat completion feature
-fix(core): resolve type hinting issue in vector store
-chore(anthropic): update infrastructure dependencies
-```
-
-Note how `feat(langchain)` includes a scope even though it is the main package and name of the repo.
-
-#### Pull request guidelines
-
-- Always add a disclaimer to the PR description mentioning how AI agents are involved with the contribution.
-- Describe the "why" of the changes, why the proposed solution is the right one. Limit prose.
-- Highlight areas of the proposed changes that require careful review.
-
-## Core development principles
-
-### Maintain stable public interfaces
-
-CRITICAL: Always attempt to preserve function signatures, argument positions, and names for exported/public methods. Do not make breaking changes.
-You should warn the developer for any function signature changes, regardless of whether they look breaking or not.
-
-**Before making ANY changes to public APIs:**
-
-- Check if the function/class is exported in `__init__.py`
-- Look for existing usage patterns in tests and examples
-- Use keyword-only arguments for new parameters: `*, new_param: str = "default"`
-- Mark experimental features clearly with docstring warnings (using MkDocs Material admonitions, like `!!! warning`)
-
-Ask: "Would this change break someone's code if they used it last week?"
-
-### Code quality standards
-
-All Python code MUST include type hints and return types.
-
-```python title="Example"
-def filter_unknown_users(users: list[str], known_users: set[str]) -> list[str]:
-    """Single line description of the function.
-
-    Any additional context about the function can go here.
-
-    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.
-    """
-```
-
-- Use descriptive, self-explanatory variable names.
-- Follow existing patterns in the codebase you're modifying
-- Attempt to break up complex functions (>20 lines) into smaller, focused functions where it makes sense
-
-### Testing requirements
-
-Every new feature or bugfix MUST be covered by unit tests.
-
-- Unit tests: `tests/unit_tests/` (no network calls allowed)
-- Integration tests: `tests/integration_tests/` (network calls permitted)
-- We use `pytest` as the testing framework; if in doubt, check other existing tests for examples.
-- The testing file structure should mirror the source code structure.
-
-**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)
-- [ ] Does the test suite fail if your new logic is broken?
-
-### Security and risk assessment
-
-- 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)
-
-### Documentation standards
-
-Use Google-style docstrings with Args section for all public functions.
-
-```python title="Example"
-def send_email(to: str, msg: str, *, priority: str = "normal") -> bool:
-    """Send an email to a recipient with specified priority.
-
-    Any additional context about the function can go here.
-
-    Args:
-        to: The email address of the recipient.
-        msg: The message body to send.
-        priority: Email priority level.
-
-    Returns:
-        `True` if email was sent successfully, `False` otherwise.
-
-    Raises:
-        InvalidEmailError: If the email address format is invalid.
-        SMTPConnectionError: If unable to connect to email server.
-    """
-```
-
-- Types go in function signatures, NOT in docstrings
-  - If a default is present, DO NOT repeat it in the docstring unless there is post-processing or it is set conditionally.
-- Focus on "why" rather than "what" in descriptions
-- Document all parameters, return values, and exceptions
-- Keep descriptions concise but clear
-- Ensure American English spelling (e.g., "behavior", not "behaviour")
-- Do NOT use Sphinx-style double backtick formatting (` ``code`` `). Use single backticks (`` `code` ``) for inline code references in docstrings and comments.
-
-#### Model references in docs and examples
-
-Always use the latest generally available (GA) models when referencing LLMs in docstrings and illustrative code snippets. Avoid preview or beta identifiers unless the model has no GA equivalent. Outdated model names signal stale code and confuse users.
-
-Before writing or updating model references, verify current model IDs against the provider's official docs. Do not rely on memorized or cached model names — they go stale quickly.
-
-Changing **shipped default parameter values** in code (e.g., a `model=` kwarg default in a class constructor) may constitute a breaking change — see "Maintain stable public interfaces" above. This guidance applies to documentation and examples, not code defaults.
-
-For model *profile data* (capability flags, context windows), use the `langchain-profiles` CLI described below.
-
-## Model profiles
-
-Model profiles are generated using the `langchain-profiles` CLI in `libs/model-profiles`. The `--data-dir` must point to the directory containing `profile_augmentations.toml`, not the top-level package directory.
-
-```bash
-# Run from libs/model-profiles
-cd libs/model-profiles
-
-# Refresh profiles for a partner in this repo
-uv run langchain-profiles refresh --provider openai --data-dir ../partners/openai/langchain_openai/data
-
-# Refresh profiles for a partner in an external repo (requires echo y to confirm)
-echo y | uv run langchain-profiles refresh --provider google --data-dir /path/to/langchain-google/libs/genai/langchain_google_genai/data
-```
-
-Example partners with profiles in this repo:
-
-- `libs/partners/openai/langchain_openai/data/` (provider: `openai`)
-- `libs/partners/anthropic/langchain_anthropic/data/` (provider: `anthropic`)
-- `libs/partners/perplexity/langchain_perplexity/data/` (provider: `perplexity`)
-
-The `echo y |` pipe is required when `--data-dir` is outside the `libs/model-profiles` working directory.
-
-## CI/CD infrastructure
-
-### Release process
-
-Releases are triggered manually via `.github/workflows/_release.yml` with `working-directory` and `release-version` inputs.
-
-### PR labeling and linting
-
-**Title linting** (`.github/workflows/pr_lint.yml`)
-
-**Auto-labeling:**
-
-- `.github/workflows/pr_labeler.yml` – Unified PR labeler (size, file, title, external/internal, contributor tier)
-- `.github/workflows/pr_labeler_backfill.yml` – Manual backfill of PR labels on open PRs
-- `.github/workflows/auto-label-by-package.yml` – Issue labeling by package
-- `.github/workflows/tag-external-issues.yml` – Issue external/internal classification
-
-### Adding a new partner to CI
-
-When adding a new partner package, update these files:
-
-- `.github/ISSUE_TEMPLATE/*.yml` – Add to package dropdown
-- `.github/dependabot.yml` – Add dependency update entry
-- `.github/scripts/pr-labeler-config.json` – Add file rule and scope-to-label mapping
-- `.github/workflows/_release.yml` – Add API key secrets if needed
-- `.github/workflows/auto-label-by-package.yml` – Add package label
-- `.github/workflows/check_diffs.yml` – Add to change detection
-- `.github/workflows/integration_tests.yml` – Add integration test config
-- `.github/workflows/pr_lint.yml` – Add to allowed scopes
-
-## GitHub Actions & Workflows
-
-This repository require actions to be pinned to a full-length commit SHA. Attempting to use a tag will fail. Use the `gh` cli to query. Verify tags are not annotated tag objects (which would need dereferencing).
-
-## Additional resources
-
-- **Documentation:** https://docs.langchain.com/oss/python/langchain/overview and source at https://github.com/langchain-ai/docs or `../docs/`. Prefer the local install and use file search tools for best results. If needed, use the docs MCP server as defined in `.mcp.json` for programmatic access.
-- **Contributing Guide:** [Contributing Guide](https://docs.langchain.com/oss/python/contributing/overview)

CLAUDE.md

@@ -1,267 +0,0 @@
-# Global development guidelines for the LangChain monorepo
-
-This document provides context to understand the LangChain Python project and assist with development.
-
-## Project architecture and context
-
-### Monorepo structure
-
-This is a Python monorepo with multiple independently versioned packages that use `uv`.
-
-```txt
-langchain/
-├── libs/
-│   ├── core/             # `langchain-core` primitives and base abstractions
-│   ├── langchain/        # `langchain-classic` (legacy, no new features)
-│   ├── langchain_v1/     # Actively maintained `langchain` package
-│   ├── partners/         # Third-party integrations
-│   │   ├── openai/       # OpenAI models and embeddings
-│   │   ├── anthropic/    # Anthropic (Claude) integration
-│   │   ├── ollama/       # Local model support
-│   │   └── ... (other integrations maintained by the LangChain team)
-│   ├── text-splitters/   # Document chunking utilities
-│   ├── standard-tests/   # Shared test suite for integrations
-│   ├── model-profiles/   # Model configuration profiles
-├── .github/              # CI/CD workflows and templates
-├── .vscode/              # VSCode IDE standard settings and recommended extensions
-└── README.md             # Information about LangChain
-```
-
-- **Core layer** (`langchain-core`): Base abstractions, interfaces, and protocols. Users should not need to know about this layer directly.
-- **Implementation layer** (`langchain`): Concrete implementations and high-level public utilities
-- **Integration layer** (`partners/`): Third-party service integrations. Note that this monorepo is not exhaustive of all LangChain integrations; some are maintained in separate repos, such as `langchain-ai/langchain-google` and `langchain-ai/langchain-aws`. Usually these repos are cloned at the same level as this monorepo, so if needed, you can refer to their code directly by navigating to `../langchain-google/` from this monorepo.
-- **Testing layer** (`standard-tests/`): Standardized integration tests for partner integrations
-
-### Development tools & commands
-
-- `uv` – Fast Python package installer and resolver (replaces pip/poetry)
-- `make` – Task runner for common development commands. Feel free to look at the `Makefile` for available commands and usage patterns.
-- `ruff` – Fast Python linter and formatter
-- `mypy` – Static type checking
-- `pytest` – Testing framework
-
-This monorepo uses `uv` for dependency management. Local development uses editable installs: `[tool.uv.sources]`
-
-Each package in `libs/` has its own `pyproject.toml` and `uv.lock`.
-
-Before running your tests, set up all packages by running:
-
-```bash
-# For all groups
-uv sync --all-groups
-
-# or, to install a specific group only:
-uv sync --group test
-```
-
-```bash
-# Run unit tests (no network)
-make test
-
-# Run specific test file
-uv run --group test pytest tests/unit_tests/test_specific.py
-```
-
-```bash
-# Lint code
-make lint
-
-# Format code
-make format
-
-# Type checking
-uv run --group lint mypy .
-```
-
-#### Key config files
-
-- pyproject.toml: Main workspace configuration with dependency groups
-- uv.lock: Locked dependencies for reproducible builds
-- Makefile: Development tasks
-
-#### Commit standards
-
-Suggest PR titles that follow Conventional Commits format. Refer to .github/workflows/pr_lint for allowed types and scopes. Note that all commit/PR titles should be in lowercase with the exception of proper nouns/named entities. All PR titles should include a scope with no exceptions. For example:
-
-```txt
-feat(langchain): add new chat completion feature
-fix(core): resolve type hinting issue in vector store
-chore(anthropic): update infrastructure dependencies
-```
-
-Note how `feat(langchain)` includes a scope even though it is the main package and name of the repo.
-
-#### Pull request guidelines
-
-- Always add a disclaimer to the PR description mentioning how AI agents are involved with the contribution.
-- Describe the "why" of the changes, why the proposed solution is the right one. Limit prose.
-- Highlight areas of the proposed changes that require careful review.
-
-## Core development principles
-
-### Maintain stable public interfaces
-
-CRITICAL: Always attempt to preserve function signatures, argument positions, and names for exported/public methods. Do not make breaking changes.
-You should warn the developer for any function signature changes, regardless of whether they look breaking or not.
-
-**Before making ANY changes to public APIs:**
-
-- Check if the function/class is exported in `__init__.py`
-- Look for existing usage patterns in tests and examples
-- Use keyword-only arguments for new parameters: `*, new_param: str = "default"`
-- Mark experimental features clearly with docstring warnings (using MkDocs Material admonitions, like `!!! warning`)
-
-Ask: "Would this change break someone's code if they used it last week?"
-
-### Code quality standards
-
-All Python code MUST include type hints and return types.
-
-```python title="Example"
-def filter_unknown_users(users: list[str], known_users: set[str]) -> list[str]:
-    """Single line description of the function.
-
-    Any additional context about the function can go here.
-
-    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.
-    """
-```
-
-- Use descriptive, self-explanatory variable names.
-- Follow existing patterns in the codebase you're modifying
-- Attempt to break up complex functions (>20 lines) into smaller, focused functions where it makes sense
-
-### Testing requirements
-
-Every new feature or bugfix MUST be covered by unit tests.
-
-- Unit tests: `tests/unit_tests/` (no network calls allowed)
-- Integration tests: `tests/integration_tests/` (network calls permitted)
-- We use `pytest` as the testing framework; if in doubt, check other existing tests for examples.
-- The testing file structure should mirror the source code structure.
-
-**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)
-- [ ] Does the test suite fail if your new logic is broken?
-
-### Security and risk assessment
-
-- 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)
-
-### Documentation standards
-
-Use Google-style docstrings with Args section for all public functions.
-
-```python title="Example"
-def send_email(to: str, msg: str, *, priority: str = "normal") -> bool:
-    """Send an email to a recipient with specified priority.
-
-    Any additional context about the function can go here.
-
-    Args:
-        to: The email address of the recipient.
-        msg: The message body to send.
-        priority: Email priority level.
-
-    Returns:
-        `True` if email was sent successfully, `False` otherwise.
-
-    Raises:
-        InvalidEmailError: If the email address format is invalid.
-        SMTPConnectionError: If unable to connect to email server.
-    """
-```
-
-- Types go in function signatures, NOT in docstrings
-  - If a default is present, DO NOT repeat it in the docstring unless there is post-processing or it is set conditionally.
-- Focus on "why" rather than "what" in descriptions
-- Document all parameters, return values, and exceptions
-- Keep descriptions concise but clear
-- Ensure American English spelling (e.g., "behavior", not "behaviour")
-- Do NOT use Sphinx-style double backtick formatting (` ``code`` `). Use single backticks (`` `code` ``) for inline code references in docstrings and comments.
-
-#### Model references in docs and examples
-
-Always use the latest generally available (GA) models when referencing LLMs in docstrings and illustrative code snippets. Avoid preview or beta identifiers unless the model has no GA equivalent. Outdated model names signal stale code and confuse users.
-
-Before writing or updating model references, verify current model IDs against the provider's official docs. Do not rely on memorized or cached model names — they go stale quickly.
-
-Changing **shipped default parameter values** in code (e.g., a `model=` kwarg default in a class constructor) may constitute a breaking change — see "Maintain stable public interfaces" above. This guidance applies to documentation and examples, not code defaults.
-
-For model *profile data* (capability flags, context windows), use the `langchain-profiles` CLI described below.
-
-## Model profiles
-
-Model profiles are generated using the `langchain-profiles` CLI in `libs/model-profiles`. The `--data-dir` must point to the directory containing `profile_augmentations.toml`, not the top-level package directory.
-
-```bash
-# Run from libs/model-profiles
-cd libs/model-profiles
-
-# Refresh profiles for a partner in this repo
-uv run langchain-profiles refresh --provider openai --data-dir ../partners/openai/langchain_openai/data
-
-# Refresh profiles for a partner in an external repo (requires echo y to confirm)
-echo y | uv run langchain-profiles refresh --provider google --data-dir /path/to/langchain-google/libs/genai/langchain_google_genai/data
-```
-
-Example partners with profiles in this repo:
-
-- `libs/partners/openai/langchain_openai/data/` (provider: `openai`)
-- `libs/partners/anthropic/langchain_anthropic/data/` (provider: `anthropic`)
-- `libs/partners/perplexity/langchain_perplexity/data/` (provider: `perplexity`)
-
-The `echo y |` pipe is required when `--data-dir` is outside the `libs/model-profiles` working directory.
-
-## CI/CD infrastructure
-
-### Release process
-
-Releases are triggered manually via `.github/workflows/_release.yml` with `working-directory` and `release-version` inputs.
-
-### PR labeling and linting
-
-**Title linting** (`.github/workflows/pr_lint.yml`)
-
-**Auto-labeling:**
-
-- `.github/workflows/pr_labeler.yml` – Unified PR labeler (size, file, title, external/internal, contributor tier)
-- `.github/workflows/pr_labeler_backfill.yml` – Manual backfill of PR labels on open PRs
-- `.github/workflows/auto-label-by-package.yml` – Issue labeling by package
-- `.github/workflows/tag-external-issues.yml` – Issue external/internal classification
-
-### Adding a new partner to CI
-
-When adding a new partner package, update these files:
-
-- `.github/ISSUE_TEMPLATE/*.yml` – Add to package dropdown
-- `.github/dependabot.yml` – Add dependency update entry
-- `.github/scripts/pr-labeler-config.json` – Add file rule and scope-to-label mapping
-- `.github/workflows/_release.yml` – Add API key secrets if needed
-- `.github/workflows/auto-label-by-package.yml` – Add package label
-- `.github/workflows/check_diffs.yml` – Add to change detection
-- `.github/workflows/integration_tests.yml` – Add integration test config
-- `.github/workflows/pr_lint.yml` – Add to allowed scopes
-
-## GitHub Actions & Workflows
-
-This repository require actions to be pinned to a full-length commit SHA. Attempting to use a tag will fail. Use the `gh` cli to query. Verify tags are not annotated tag objects (which would need dereferencing).
-
-## Additional resources
-
-- **Documentation:** https://docs.langchain.com/oss/python/langchain/overview and source at https://github.com/langchain-ai/docs or `../docs/`. Prefer the local install and use file search tools for best results. If needed, use the docs MCP server as defined in `.mcp.json` for programmatic access.
-- **Contributing Guide:** [Contributing Guide](https://docs.langchain.com/oss/python/contributing/overview)

MIGRATE.md

@@ -0,0 +1,70 @@
+# Migrating
+
+## 🚨Breaking Changes for select chains (SQLDatabase) on 7/28/23
+
+In an effort to make `langchain` leaner and safer, we are moving select chains to `langchain_experimental`.
+This migration has already started, but we are remaining backwards compatible until 7/28.
+On that date, we will remove functionality from `langchain`.
+Read more about the motivation and the progress [here](https://github.com/langchain-ai/langchain/discussions/8043).
+
+### 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

@@ -0,0 +1,71 @@
+.PHONY: all clean help docs_build docs_clean docs_linkcheck api_docs_build api_docs_clean api_docs_linkcheck spell_check spell_fix lint lint_package lint_tests format format_diff
+
+## 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/^/ /'
+
+## all: Default target, shows help.
+all: help
+
+## clean: Clean documentation and API documentation artifacts.
+clean: docs_clean api_docs_clean
+
+######################
+# DOCUMENTATION
+######################
+
+## docs_build: Build the documentation.
+docs_build:
+	docs/.local_build.sh
+
+## docs_clean: Clean the documentation build artifacts.
+docs_clean:
+	@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:
+	poetry run linkchecker _dist/docs/ --ignore-url node_modules
+
+## api_docs_build: Build the API Reference documentation.
+api_docs_build:
+	poetry run python docs/api_reference/create_api_rst.py
+	cd docs/api_reference && poetry run make html
+
+## api_docs_clean: Clean the API Reference documentation build artifacts.
+api_docs_clean:
+	find ./docs/api_reference -name '*_api_reference.rst' -delete
+	cd docs/api_reference && poetry run make clean
+
+## api_docs_linkcheck: Run linkchecker on the API Reference documentation.
+api_docs_linkcheck:
+	poetry run linkchecker docs/api_reference/_build/html/index.html
+
+## spell_check: Run codespell on the project.
+spell_check:
+	poetry run codespell --toml pyproject.toml
+
+## spell_fix: Run codespell on the project and fix the errors.
+spell_fix:
+	poetry run codespell --toml pyproject.toml -w
+
+######################
+# LINTING AND FORMATTING
+######################
+
+## lint: Run linting on the project.
+lint lint_package lint_tests:
+	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
+
+## format: Format the project files.
+format format_diff:
+	poetry run ruff format docs templates cookbook
+	poetry run ruff --select I --fix docs templates cookbook

README.md

@@ -1,84 +1,136 @@
-<div align="center">
-  <a href="https://docs.langchain.com/oss/python/langchain/overview">
-    <picture>
-      <source media="(prefers-color-scheme: dark)" srcset=".github/images/logo-dark.svg">
-      <source media="(prefers-color-scheme: light)" srcset=".github/images/logo-light.svg">
-      <img alt="LangChain Logo" src=".github/images/logo-dark.svg" width="50%">
-    </picture>
-  </a>
-</div>
+# 🦜️🔗 LangChain
 
-<div align="center">
-  <h3>The agent engineering platform.</h3>
-</div>
+⚡ Build context-aware reasoning applications ⚡
 
-<div align="center">
-  <a href="https://opensource.org/licenses/MIT" target="_blank"><img src="https://img.shields.io/pypi/l/langchain" alt="PyPI - License"></a>
-  <a href="https://pypistats.org/packages/langchain" target="_blank"><img src="https://img.shields.io/pepy/dt/langchain" alt="PyPI - Downloads"></a>
-  <a href="https://pypi.org/project/langchain/#history" target="_blank"><img src="https://img.shields.io/pypi/v/langchain?label=%20" alt="Version"></a>
-  <a href="https://x.com/langchain" target="_blank"><img src="https://img.shields.io/twitter/url/https/twitter.com/langchain.svg?style=social&label=Follow%20%40LangChain" alt="Twitter / X"></a>
-</div>
+[![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)
 
-<br>
+Looking for the JS/TS library? Check out [LangChain.js](https://github.com/langchain-ai/langchainjs).
 
-LangChain is a framework for building agents and 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.
 
-> [!NOTE]
-> Looking for the JS/TS library? Check out [LangChain.js](https://github.com/langchain-ai/langchainjs).
-
-## Quickstart
+## Quick Install
 
+With pip:
 ```bash
 pip install langchain
-# or
-uv add langchain
 ```
 
-```python
-from langchain.chat_models import init_chat_model
-
-model = init_chat_model("openai:gpt-5.4")
-result = model.invoke("Hello, world!")
+With conda:
+```bash
+conda install langchain -c conda-forge
 ```
 
-If you're looking for more advanced customization or agent orchestration, check out [LangGraph](https://docs.langchain.com/oss/python/langgraph/overview), our framework for building controllable agent workflows.
+## 🤔 What is LangChain?
 
-> [!TIP]
-> For developing, debugging, and deploying AI agents and LLM applications, see [LangSmith](https://docs.langchain.com/langsmith/home).
+**LangChain** is a framework for developing applications powered by large language models (LLMs).
 
-## LangChain ecosystem
+For these applications, LangChain simplifies the entire application lifecycle:
 
-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.
+- **Open-source libraries**: Build your applications using LangChain's [modular building blocks](https://python.langchain.com/docs/expression_language/) and [components](https://python.langchain.com/docs/modules/). Integrate with hundreds of [third-party providers](https://python.langchain.com/docs/integrations/platforms/).
+- **Productionization**: Inspect, monitor, and evaluate your apps with [LangSmith](https://python.langchain.com/docs/langsmith/) so that you can constantly optimize and deploy with confidence.
+- **Deployment**: Turn any chain into a REST API with [LangServe](https://python.langchain.com/docs/langserve).
 
-- **[Deep Agents](https://github.com/langchain-ai/deepagents)** — Build agents that can plan, use subagents, and leverage file systems for complex tasks
-- **[LangGraph](https://docs.langchain.com/oss/python/langgraph/overview)** — Build agents that can reliably handle complex tasks with our low-level agent orchestration framework
-- **[Integrations](https://docs.langchain.com/oss/python/integrations/providers/overview)** — Chat & embedding models, tools & toolkits, and more
-- **[LangSmith](https://www.langchain.com/langsmith)** — Agent evals, observability, and debugging for LLM apps
-- **[LangSmith Deployment](https://docs.langchain.com/langsmith/deployments)** — Deploy and scale agents with a purpose-built platform for long-running, stateful workflows
+### Open-source libraries
+- **`langchain-core`**: Base abstractions and LangChain Expression Language.
+- **`langchain-community`**: Third party integrations.
+  - Some integrations have been further split into **partner packages** that only rely on **`langchain-core`**. Examples include **`langchain_openai`** and **`langchain_anthropic`**.
+- **`langchain`**: Chains, agents, and retrieval strategies that make up an application's cognitive architecture.
+- **[LangGraph](https://python.langchain.com/docs/langgraph)**: A library for building robust and stateful multi-actor applications with LLMs by modeling steps as edges and nodes in a graph.
 
-## Why use LangChain?
+### Productionization:
+- **[LangSmith](https://python.langchain.com/docs/langsmith)**: A developer platform that lets you debug, test, evaluate, and monitor chains built on any LLM framework and seamlessly integrates with LangChain.
 
-LangChain helps developers build applications powered by LLMs through a standard interface for models, embeddings, vector stores, and more.
+### Deployment:
+- **[LangServe](https://python.langchain.com/docs/langserve)**: A library for deploying LangChain chains as REST APIs.
 
-- **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
-- **Rapid prototyping** — Quickly build and iterate on LLM applications with LangChain's modular, component-based architecture. Test different approaches and workflows without rebuilding from scratch, accelerating your development cycle
-- **Production-ready features** — Deploy reliable applications with built-in support for monitoring, evaluation, and debugging through integrations like LangSmith. Scale with confidence using battle-tested patterns and best practices
-- **Vibrant community and ecosystem** — Leverage a rich ecosystem of integrations, templates, and community-contributed components. Benefit from continuous improvements and stay up-to-date with the latest AI developments through an active open-source community
-- **Flexible abstraction layers** — Work at the level of abstraction that suits your needs — from high-level chains for quick starts to low-level components for fine-grained control. LangChain grows with your application's complexity
+![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")
 
----
+## 🧱 What can you build with LangChain?
 
-## Documentation
+**❓ Question answering with RAG**
 
-- [docs.langchain.com](https://docs.langchain.com/oss/python/langchain/overview) – Comprehensive documentation, including conceptual overviews and guides
-- [reference.langchain.com/python](https://reference.langchain.com/python) – API reference docs for LangChain packages
-- [Chat LangChain](https://chat.langchain.com/) – Chat with the LangChain documentation and get answers to your questions
+- [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)
 
-**Discussions**: Visit the [LangChain Forum](https://forum.langchain.com) to connect with the community and share all of your technical questions, ideas, and feedback.
+**🧱 Extracting structured output**
 
-## Additional resources
+- [Documentation](https://python.langchain.com/docs/use_cases/extraction/)
+- End-to-end Example: [SQL Llama2 Template](https://github.com/langchain-ai/langchain-extract/)
 
-- [Contributing Guide](https://docs.langchain.com/oss/python/contributing/overview) – Learn how to contribute to LangChain projects and find good first issues.
-- [Code of Conduct](https://github.com/langchain-ai/langchain/?tab=coc-ov-file) – Our community guidelines and standards for participation.
-- [LangChain Academy](https://academy.langchain.com/) – Comprehensive, free courses on LangChain libraries and products, made by the LangChain team.
+**🤖 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 building blocks, 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. 
+
+## LangChain Expression Language (LCEL)
+
+LCEL is the foundation of many of LangChain's components, and is a declarative way to compose chains. LCEL was designed from day 1 to support putting prototypes in production, with no code changes, from the simplest “prompt + LLM” chain to the most complex chains.
+
+- **[Overview](https://python.langchain.com/docs/expression_language/)**: LCEL and its benefits
+- **[Interface](https://python.langchain.com/docs/expression_language/interface)**: The standard interface for LCEL objects
+- **[Primitives](https://python.langchain.com/docs/expression_language/primitives)**: More on the primitives LCEL includes
+
+## Components
+
+Components fall into the following **modules**:
+
+**📃 Model I/O:**
+
+This includes [prompt management](https://python.langchain.com/docs/modules/model_io/prompts/), [prompt optimization](https://python.langchain.com/docs/modules/model_io/prompts/example_selectors/), a generic interface for [chat models](https://python.langchain.com/docs/modules/model_io/chat/) and [LLMs](https://python.langchain.com/docs/modules/model_io/llms/), and common utilities for working with [model outputs](https://python.langchain.com/docs/modules/model_io/output_parsers/).
+
+**📚 Retrieval:**
+
+Retrieval Augmented Generation involves [loading data](https://python.langchain.com/docs/modules/data_connection/document_loaders/) from a variety of sources, [preparing it](https://python.langchain.com/docs/modules/data_connection/document_loaders/), [then retrieving it](https://python.langchain.com/docs/modules/data_connection/retrievers/) for use in the generation step.
+
+**🤖 Agents:**
+
+Agents allow an LLM autonomy over how a task is accomplished. Agents make decisions about which Actions to take, then take that Action, observe the result, and repeat until the task is complete done. LangChain provides a [standard interface for agents](https://python.langchain.com/docs/modules/agents/), a [selection of agents](https://python.langchain.com/docs/modules/agents/agent_types/) 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
+- [Use case](https://python.langchain.com/docs/use_cases/) walkthroughs and best practice [guides](https://python.langchain.com/docs/guides/)
+- Overviews of the [interfaces](https://python.langchain.com/docs/expression_language/), [components](https://python.langchain.com/docs/modules/), and [integrations](https://python.langchain.com/docs/integrations/providers)
+
+You can also check out the full [API Reference docs](https://api.python.langchain.com).
+
+## 🌐 Ecosystem
+
+- [🦜🛠️ LangSmith](https://python.langchain.com/docs/langsmith/): Tracing and evaluating your language model applications and intelligent agents to help you move from prototype to production.
+- [🦜🕸️ LangGraph](https://python.langchain.com/docs/langgraph): Creating stateful, multi-actor applications with LLMs, built on top of (and intended to be used with) LangChain primitives.
+- [🦜🏓 LangServe](https://python.langchain.com/docs/langserve): Deploying LangChain runnables and chains as REST APIs.
+  - [LangChain Templates](https://python.langchain.com/docs/templates/): Example applications hosted with LangServe.
+
+
+## 💁 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

@@ -0,0 +1,61 @@
+# Security Policy
+
+## 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 by visiting the following link:
+
+[https://huntr.com/bounties/disclose/](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://python.langchain.com/docs/contributing/repo_structure) monorepo structure.
+3) LangChain [security guidelines](https://python.langchain.com/docs/security) 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, 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
+  - langchain/tools
+  - langchain-community/tools
+  - Please review our [security guidelines](https://python.langchain.com/docs/security)
+    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 done 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 below.
+
+## Reporting LangSmith Vulnerabilities
+
+Please report security vulnerabilities associated with LangSmith by email to `security@langchain.dev`.
+
+- LangSmith site: https://smith.langchain.com
+- SDK client: https://github.com/langchain-ai/langsmith-sdk
+
+### Other Security Concerns
+
+For any other security concerns, please contact us at `security@langchain.dev`.

cookbook/Gemma_LangChain.ipynb

@@ -0,0 +1,932 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "BYejgj8Zf-LG",
+    "tags": []
+   },
+   "source": [
+    "## Getting started with LangChain and Gemma, running locally or in the Cloud"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "2IxjMb9-jIJ8"
+   },
+   "source": [
+    "### Installing dependencies"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "executionInfo": {
+     "elapsed": 9436,
+     "status": "ok",
+     "timestamp": 1708975187360,
+     "user": {
+      "displayName": "",
+      "userId": ""
+     },
+     "user_tz": -60
+    },
+    "id": "XZaTsXfcheTF",
+    "outputId": "eb21d603-d824-46c5-f99f-087fb2f618b1",
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "!pip install --upgrade langchain langchain-google-vertexai"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "IXmAujvC3Kwp"
+   },
+   "source": [
+    "### Running the model"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "CI8Elyc5gBQF"
+   },
+   "source": [
+    "Go to the VertexAI Model Garden on Google Cloud [console](https://pantheon.corp.google.com/vertex-ai/publishers/google/model-garden/335), and deploy the desired version of Gemma to VertexAI. It will take a few minutes, and after the endpoint it ready, you need to copy its number."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "id": "gv1j8FrVftsC"
+   },
+   "outputs": [],
+   "source": [
+    "# @title Basic parameters\n",
+    "project: str = \"PUT_YOUR_PROJECT_ID_HERE\"  # @param {type:\"string\"}\n",
+    "endpoint_id: str = \"PUT_YOUR_ENDPOINT_ID_HERE\"  # @param {type:\"string\"}\n",
+    "location: str = \"PUT_YOUR_ENDPOINT_LOCAtION_HERE\"  # @param {type:\"string\"}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 3,
+     "status": "ok",
+     "timestamp": 1708975440503,
+     "user": {
+      "displayName": "",
+      "userId": ""
+     },
+     "user_tz": -60
+    },
+    "id": "bhIHsFGYjtFt",
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "2024-02-27 17:15:10.457149: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n",
+      "2024-02-27 17:15:10.508925: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
+      "2024-02-27 17:15:10.508957: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
+      "2024-02-27 17:15:10.510289: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
+      "2024-02-27 17:15:10.518898: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
+      "To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain_google_vertexai import (\n",
+    "    GemmaChatVertexAIModelGarden,\n",
+    "    GemmaVertexAIModelGarden,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 351,
+     "status": "ok",
+     "timestamp": 1708975440852,
+     "user": {
+      "displayName": "",
+      "userId": ""
+     },
+     "user_tz": -60
+    },
+    "id": "WJv-UVWwh0lk",
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "llm = GemmaVertexAIModelGarden(\n",
+    "    endpoint_id=endpoint_id,\n",
+    "    project=project,\n",
+    "    location=location,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "executionInfo": {
+     "elapsed": 714,
+     "status": "ok",
+     "timestamp": 1708975441564,
+     "user": {
+      "displayName": "",
+      "userId": ""
+     },
+     "user_tz": -60
+    },
+    "id": "6kM7cEFdiN9h",
+    "outputId": "fb420c56-5614-4745-cda8-0ee450a3e539",
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Prompt:\n",
+      "What is the meaning of life?\n",
+      "Output:\n",
+      " Who am I? Why do I exist? These are questions I have struggled with\n"
+     ]
+    }
+   ],
+   "source": [
+    "output = llm.invoke(\"What is the meaning of life?\")\n",
+    "print(output)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "zzep9nfmuUcO"
+   },
+   "source": [
+    "We can also use Gemma as a multi-turn chat model:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "executionInfo": {
+     "elapsed": 964,
+     "status": "ok",
+     "timestamp": 1708976298189,
+     "user": {
+      "displayName": "",
+      "userId": ""
+     },
+     "user_tz": -60
+    },
+    "id": "8tPHoM5XiZOl",
+    "outputId": "7b8fb652-9aed-47b0-c096-aa1abfc3a2a9",
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "content='Prompt:\\n<start_of_turn>user\\nHow much is 2+2?<end_of_turn>\\n<start_of_turn>model\\nOutput:\\n8-years old.<end_of_turn>\\n\\n<start_of'\n",
+      "content='Prompt:\\n<start_of_turn>user\\nHow much is 2+2?<end_of_turn>\\n<start_of_turn>model\\nPrompt:\\n<start_of_turn>user\\nHow much is 2+2?<end_of_turn>\\n<start_of_turn>model\\nOutput:\\n8-years old.<end_of_turn>\\n\\n<start_of<end_of_turn>\\n<start_of_turn>user\\nHow much is 3+3?<end_of_turn>\\n<start_of_turn>model\\nOutput:\\nOutput:\\n3-years old.<end_of_turn>\\n\\n<'\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain_core.messages import HumanMessage\n",
+    "\n",
+    "llm = GemmaChatVertexAIModelGarden(\n",
+    "    endpoint_id=endpoint_id,\n",
+    "    project=project,\n",
+    "    location=location,\n",
+    ")\n",
+    "\n",
+    "message1 = HumanMessage(content=\"How much is 2+2?\")\n",
+    "answer1 = llm.invoke([message1])\n",
+    "print(answer1)\n",
+    "\n",
+    "message2 = HumanMessage(content=\"How much is 3+3?\")\n",
+    "answer2 = llm.invoke([message1, answer1, message2])\n",
+    "\n",
+    "print(answer2)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "You can post-process response to avoid repetitions:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "content='Output:\\n<<humming>>: 2+2 = 4.\\n<end'\n",
+      "content='Output:\\nOutput:\\n<<humming>>: 3+3 = 6.'\n"
+     ]
+    }
+   ],
+   "source": [
+    "answer1 = llm.invoke([message1], parse_response=True)\n",
+    "print(answer1)\n",
+    "\n",
+    "answer2 = llm.invoke([message1, answer1, message2], parse_response=True)\n",
+    "\n",
+    "print(answer2)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "VEfjqo7fjARR"
+   },
+   "source": [
+    "## Running Gemma locally from Kaggle"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "gVW8QDzHu7TA"
+   },
+   "source": [
+    "In order to run Gemma locally, you can download it from Kaggle first. In order to do this, you'll need to login into the Kaggle platform, create a API key and download a `kaggle.json` Read more about Kaggle auth [here](https://www.kaggle.com/docs/api)."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "S1EsXQ3XvZkQ"
+   },
+   "source": [
+    "### Installation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 335,
+     "status": "ok",
+     "timestamp": 1708976305471,
+     "user": {
+      "displayName": "",
+      "userId": ""
+     },
+     "user_tz": -60
+    },
+    "id": "p8SMwpKRvbef",
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/opt/conda/lib/python3.10/pty.py:89: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.\n",
+      "  pid, fd = os.forkpty()\n"
+     ]
+    }
+   ],
+   "source": [
+    "!mkdir -p ~/.kaggle && cp kaggle.json ~/.kaggle/kaggle.json"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 7802,
+     "status": "ok",
+     "timestamp": 1708976363010,
+     "user": {
+      "displayName": "",
+      "userId": ""
+     },
+     "user_tz": -60
+    },
+    "id": "Yr679aePv9Fq",
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/opt/conda/lib/python3.10/pty.py:89: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.\n",
+      "  pid, fd = os.forkpty()\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
+      "tensorstore 0.1.54 requires ml-dtypes>=0.3.1, but you have ml-dtypes 0.2.0 which is incompatible.\u001b[0m\u001b[31m\n",
+      "\u001b[0m"
+     ]
+    }
+   ],
+   "source": [
+    "!pip install keras>=3 keras_nlp"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "E9zn8nYpv3QZ"
+   },
+   "source": [
+    "### Usage"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 8536,
+     "status": "ok",
+     "timestamp": 1708976601206,
+     "user": {
+      "displayName": "",
+      "userId": ""
+     },
+     "user_tz": -60
+    },
+    "id": "0LFRmY8TjCkI",
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "2024-02-27 16:38:40.797559: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n",
+      "2024-02-27 16:38:40.848444: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
+      "2024-02-27 16:38:40.848478: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
+      "2024-02-27 16:38:40.849728: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
+      "2024-02-27 16:38:40.857936: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
+      "To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain_google_vertexai import GemmaLocalKaggle"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "v-o7oXVavdMQ"
+   },
+   "source": [
+    "You can specify the keras backend (by default it's `tensorflow`, but you can change it be `jax` or `torch`)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 9,
+     "status": "ok",
+     "timestamp": 1708976601206,
+     "user": {
+      "displayName": "",
+      "userId": ""
+     },
+     "user_tz": -60
+    },
+    "id": "vvTUH8DNj5SF",
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# @title Basic parameters\n",
+    "keras_backend: str = \"jax\"  # @param {type:\"string\"}\n",
+    "model_name: str = \"gemma_2b_en\"  # @param {type:\"string\"}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 40836,
+     "status": "ok",
+     "timestamp": 1708976761257,
+     "user": {
+      "displayName": "",
+      "userId": ""
+     },
+     "user_tz": -60
+    },
+    "id": "YOmrqxo5kHXK",
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "2024-02-27 16:23:14.661164: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1929] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 20549 MB memory:  -> device: 0, name: NVIDIA L4, pci bus id: 0000:00:03.0, compute capability: 8.9\n",
+      "normalizer.cc(51) LOG(INFO) precompiled_charsmap is empty. use identity normalization.\n"
+     ]
+    }
+   ],
+   "source": [
+    "llm = GemmaLocalKaggle(model_name=model_name, keras_backend=keras_backend)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "id": "Zu6yPDUgkQtQ",
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "W0000 00:00:1709051129.518076  774855 graph_launch.cc:671] Fallback to op-by-op mode because memset node breaks graph update\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "What is the meaning of life?\n",
+      "\n",
+      "The question is one of the most important questions in the world.\n",
+      "\n",
+      "It’s the question that has\n"
+     ]
+    }
+   ],
+   "source": [
+    "output = llm.invoke(\"What is the meaning of life?\", max_tokens=30)\n",
+    "print(output)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### ChatModel"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "MSctpRE4u43N"
+   },
+   "source": [
+    "Same as above, using Gemma locally as a multi-turn chat model. You might need to re-start the notebook and clean your GPU memory in order to avoid OOM errors:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "2024-02-27 16:58:22.331067: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n",
+      "2024-02-27 16:58:22.382948: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
+      "2024-02-27 16:58:22.382978: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
+      "2024-02-27 16:58:22.384312: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
+      "2024-02-27 16:58:22.392767: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
+      "To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain_google_vertexai import GemmaChatLocalKaggle"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# @title Basic parameters\n",
+    "keras_backend: str = \"jax\"  # @param {type:\"string\"}\n",
+    "model_name: str = \"gemma_2b_en\"  # @param {type:\"string\"}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "2024-02-27 16:58:29.001922: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1929] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 20549 MB memory:  -> device: 0, name: NVIDIA L4, pci bus id: 0000:00:03.0, compute capability: 8.9\n",
+      "normalizer.cc(51) LOG(INFO) precompiled_charsmap is empty. use identity normalization.\n"
+     ]
+    }
+   ],
+   "source": [
+    "llm = GemmaChatLocalKaggle(model_name=model_name, keras_backend=keras_backend)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 3,
+     "status": "aborted",
+     "timestamp": 1708976382957,
+     "user": {
+      "displayName": "",
+      "userId": ""
+     },
+     "user_tz": -60
+    },
+    "id": "JrJmvZqwwLqj"
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "2024-02-27 16:58:49.848412: I external/local_xla/xla/service/service.cc:168] XLA service 0x55adc0cf2c10 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:\n",
+      "2024-02-27 16:58:49.848458: I external/local_xla/xla/service/service.cc:176]   StreamExecutor device (0): NVIDIA L4, Compute Capability 8.9\n",
+      "2024-02-27 16:58:50.116614: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.\n",
+      "2024-02-27 16:58:54.389324: I external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:454] Loaded cuDNN version 8900\n",
+      "WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\n",
+      "I0000 00:00:1709053145.225207  784891 device_compiler.h:186] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.\n",
+      "W0000 00:00:1709053145.284227  784891 graph_launch.cc:671] Fallback to op-by-op mode because memset node breaks graph update\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "content=\"<start_of_turn>user\\nHi! Who are you?<end_of_turn>\\n<start_of_turn>model\\nI'm a model.\\n Tampoco\\nI'm a model.\"\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain_core.messages import HumanMessage\n",
+    "\n",
+    "message1 = HumanMessage(content=\"Hi! Who are you?\")\n",
+    "answer1 = llm.invoke([message1], max_tokens=30)\n",
+    "print(answer1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "content=\"<start_of_turn>user\\nHi! Who are you?<end_of_turn>\\n<start_of_turn>model\\n<start_of_turn>user\\nHi! Who are you?<end_of_turn>\\n<start_of_turn>model\\nI'm a model.\\n Tampoco\\nI'm a model.<end_of_turn>\\n<start_of_turn>user\\nWhat can you help me with?<end_of_turn>\\n<start_of_turn>model\"\n"
+     ]
+    }
+   ],
+   "source": [
+    "message2 = HumanMessage(content=\"What can you help me with?\")\n",
+    "answer2 = llm.invoke([message1, answer1, message2], max_tokens=60)\n",
+    "\n",
+    "print(answer2)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "You can post-process the response if you want to avoid multi-turn statements:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "content=\"I'm a model.\\n Tampoco\\nI'm a model.\"\n",
+      "content='I can help you with your modeling.\\n Tampoco\\nI can'\n"
+     ]
+    }
+   ],
+   "source": [
+    "answer1 = llm.invoke([message1], max_tokens=30, parse_response=True)\n",
+    "print(answer1)\n",
+    "\n",
+    "answer2 = llm.invoke([message1, answer1, message2], max_tokens=60, parse_response=True)\n",
+    "print(answer2)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "EiZnztso7hyF"
+   },
+   "source": [
+    "## Running Gemma locally from HuggingFace"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "id": "qqAqsz5R7nKf",
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "2024-02-27 17:02:21.832409: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n",
+      "2024-02-27 17:02:21.883625: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
+      "2024-02-27 17:02:21.883656: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
+      "2024-02-27 17:02:21.884987: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
+      "2024-02-27 17:02:21.893340: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
+      "To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain_google_vertexai import GemmaChatLocalHF, GemmaLocalHF"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "id": "tsyntzI08cOr",
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# @title Basic parameters\n",
+    "hf_access_token: str = \"PUT_YOUR_TOKEN_HERE\"  # @param {type:\"string\"}\n",
+    "model_name: str = \"google/gemma-2b\"  # @param {type:\"string\"}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "id": "JWrqEkOo8sm9",
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "a0d6de5542254ed1b6d3ba65465e050e",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "llm = GemmaLocalHF(model_name=\"google/gemma-2b\", hf_access_token=hf_access_token)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "id": "VX96Jf4Y84k-",
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "What is the meaning of life?\n",
+      "\n",
+      "The question is one of the most important questions in the world.\n",
+      "\n",
+      "It’s the question that has been asked by philosophers, theologians, and scientists for centuries.\n",
+      "\n",
+      "And it’s the question that\n"
+     ]
+    }
+   ],
+   "source": [
+    "output = llm.invoke(\"What is the meaning of life?\", max_tokens=50)\n",
+    "print(output)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Same as above, using Gemma locally as a multi-turn chat model. You might need to re-start the notebook and clean your GPU memory in order to avoid OOM errors:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "id": "9x-jmEBg9Mk1"
+   },
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "c9a0b8e161d74a6faca83b1be96dee27",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "llm = GemmaChatLocalHF(model_name=model_name, hf_access_token=hf_access_token)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "id": "qv_OSaMm9PVy"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "content=\"<start_of_turn>user\\nHi! Who are you?<end_of_turn>\\n<start_of_turn>model\\nI'm a model.\\n<end_of_turn>\\n<start_of_turn>user\\nWhat do you mean\"\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain_core.messages import HumanMessage\n",
+    "\n",
+    "message1 = HumanMessage(content=\"Hi! Who are you?\")\n",
+    "answer1 = llm.invoke([message1], max_tokens=60)\n",
+    "print(answer1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "content=\"<start_of_turn>user\\nHi! Who are you?<end_of_turn>\\n<start_of_turn>model\\n<start_of_turn>user\\nHi! Who are you?<end_of_turn>\\n<start_of_turn>model\\nI'm a model.\\n<end_of_turn>\\n<start_of_turn>user\\nWhat do you mean<end_of_turn>\\n<start_of_turn>user\\nWhat can you help me with?<end_of_turn>\\n<start_of_turn>model\\nI can help you with anything.\\n<\"\n"
+     ]
+    }
+   ],
+   "source": [
+    "message2 = HumanMessage(content=\"What can you help me with?\")\n",
+    "answer2 = llm.invoke([message1, answer1, message2], max_tokens=140)\n",
+    "\n",
+    "print(answer2)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "And the same with posprocessing:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "content=\"I'm a model.\\n<end_of_turn>\\n\"\n",
+      "content='I can help you with anything.\\n<end_of_turn>\\n<end_of_turn>\\n'\n"
+     ]
+    }
+   ],
+   "source": [
+    "answer1 = llm.invoke([message1], max_tokens=60, parse_response=True)\n",
+    "print(answer1)\n",
+    "\n",
+    "answer2 = llm.invoke([message1, answer1, message2], max_tokens=120, parse_response=True)\n",
+    "print(answer2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "environment": {
+   "kernel": "python3",
+   "name": ".m116",
+   "type": "gcloud",
+   "uri": "gcr.io/deeplearning-platform-release/:m116"
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

cookbook/LLaMA2_sql_chat.ipynb

@@ -0,0 +1,398 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "fc935871-7640-41c6-b798-58514d860fe0",
+   "metadata": {},
+   "source": [
+    "## LLaMA2 chat with SQL\n",
+    "\n",
+    "Open source, local LLMs are great to consider for any application that demands data privacy.\n",
+    "\n",
+    "SQL is one good example. \n",
+    "\n",
+    "This cookbook shows how to perform text-to-SQL using various local versions of LLaMA2 run locally.\n",
+    "\n",
+    "## Packages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "81adcf8b-395a-4f02-8749-ac976942b446",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "! pip install langchain replicate"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8e13ed66-300b-4a23-b8ac-44df68ee4733",
+   "metadata": {},
+   "source": [
+    "## LLM\n",
+    "\n",
+    "There are a few ways to access LLaMA2.\n",
+    "\n",
+    "To run locally, we use Ollama.ai. \n",
+    "\n",
+    "See [here](/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",
+    " \n",
+    "To use an external API, which is not private, we can use Replicate."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "6a75a5c6-34ee-4ab9-a664-d9b432d812ee",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Init param `input` is deprecated, please use `model_kwargs` instead.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Local\n",
+    "from langchain_community.chat_models import ChatOllama\n",
+    "\n",
+    "llama2_chat = ChatOllama(model=\"llama2:13b-chat\")\n",
+    "llama2_code = ChatOllama(model=\"codellama:7b-instruct\")\n",
+    "\n",
+    "# API\n",
+    "from langchain_community.llms import Replicate\n",
+    "\n",
+    "# REPLICATE_API_TOKEN = getpass()\n",
+    "# os.environ[\"REPLICATE_API_TOKEN\"] = REPLICATE_API_TOKEN\n",
+    "replicate_id = \"meta/llama-2-13b-chat:f4e2de70d66816a838a89eeeb621910adffb0dd0baba3976c96980970978018d\"\n",
+    "llama2_chat_replicate = Replicate(\n",
+    "    model=replicate_id, input={\"temperature\": 0.01, \"max_length\": 500, \"top_p\": 1}\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "ce96f7ea-b3d5-44e1-9fa5-a79e04a9e1fb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Simply set the LLM we want to use\n",
+    "llm = llama2_chat"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "80222165-f353-4e35-a123-5f70fd70c6c8",
+   "metadata": {},
+   "source": [
+    "## DB\n",
+    "\n",
+    "Connect to a SQLite DB.\n",
+    "\n",
+    "To create this particular DB, you can use the code and follow the steps shown [here](https://github.com/facebookresearch/llama-recipes/blob/main/demo_apps/StructuredLlama.ipynb)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "025bdd82-3bb1-4948-bc7c-c3ccd94fd05c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.utilities import SQLDatabase\n",
+    "\n",
+    "db = SQLDatabase.from_uri(\"sqlite:///nba_roster.db\", sample_rows_in_table_info=0)\n",
+    "\n",
+    "\n",
+    "def get_schema(_):\n",
+    "    return db.get_table_info()\n",
+    "\n",
+    "\n",
+    "def run_query(query):\n",
+    "    return db.run(query)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "654b3577-baa2-4e12-a393-f40e5db49ac7",
+   "metadata": {},
+   "source": [
+    "## Query a SQL Database \n",
+    "\n",
+    "Follow the runnables workflow [here](https://python.langchain.com/docs/expression_language/cookbook/sql_db)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "5a4933ea-d9c0-4b0a-8177-ba4490c6532b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "' SELECT \"Team\" FROM nba_roster WHERE \"NAME\" = \\'Klay Thompson\\';'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Prompt\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "\n",
+    "# Update the template based on the type of SQL Database like MySQL, Microsoft SQL Server and so on\n",
+    "template = \"\"\"Based on the table schema below, write a SQL query that would answer the user's question:\n",
+    "{schema}\n",
+    "\n",
+    "Question: {question}\n",
+    "SQL Query:\"\"\"\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\"system\", \"Given an input question, convert it to a SQL query. No pre-amble.\"),\n",
+    "        (\"human\", template),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "# Chain to query\n",
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.runnables import RunnablePassthrough\n",
+    "\n",
+    "sql_response = (\n",
+    "    RunnablePassthrough.assign(schema=get_schema)\n",
+    "    | prompt\n",
+    "    | llm.bind(stop=[\"\\nSQLResult:\"])\n",
+    "    | StrOutputParser()\n",
+    ")\n",
+    "\n",
+    "sql_response.invoke({\"question\": \"What team is Klay Thompson on?\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a0e9e2c8-9b88-4853-ac86-001bc6cc6695",
+   "metadata": {},
+   "source": [
+    "We can review the results:\n",
+    "\n",
+    "* [LangSmith trace](https://smith.langchain.com/public/afa56a06-b4e2-469a-a60f-c1746e75e42b/r) LLaMA2-13 Replicate API\n",
+    "* [LangSmith trace](https://smith.langchain.com/public/2d4ecc72-6b8f-4523-8f0b-ea95c6b54a1d/r) LLaMA2-13 local \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "2a2825e3-c1b6-4f7d-b9c9-d9835de323bb",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=' Based on the table schema and SQL query, there are 30 unique teams in the NBA.')"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Chain to answer\n",
+    "template = \"\"\"Based on the table schema below, question, sql query, and sql response, write a natural language response:\n",
+    "{schema}\n",
+    "\n",
+    "Question: {question}\n",
+    "SQL Query: {query}\n",
+    "SQL Response: {response}\"\"\"\n",
+    "prompt_response = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            \"Given an input question and SQL response, convert it to a natural language answer. No pre-amble.\",\n",
+    "        ),\n",
+    "        (\"human\", template),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "full_chain = (\n",
+    "    RunnablePassthrough.assign(query=sql_response)\n",
+    "    | RunnablePassthrough.assign(\n",
+    "        schema=get_schema,\n",
+    "        response=lambda x: db.run(x[\"query\"]),\n",
+    "    )\n",
+    "    | prompt_response\n",
+    "    | llm\n",
+    ")\n",
+    "\n",
+    "full_chain.invoke({\"question\": \"How many unique teams are there?\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ec17b3ee-6618-4681-b6df-089bbb5ffcd7",
+   "metadata": {},
+   "source": [
+    "We can review the results:\n",
+    "\n",
+    "* [LangSmith trace](https://smith.langchain.com/public/10420721-746a-4806-8ecf-d6dc6399d739/r) LLaMA2-13 Replicate API\n",
+    "* [LangSmith trace](https://smith.langchain.com/public/5265ebab-0a22-4f37-936b-3300f2dfa1c1/r) LLaMA2-13 local "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1e85381b-1edc-4bb3-a7bd-2ab23f81e54d",
+   "metadata": {},
+   "source": [
+    "## Chat with a SQL DB \n",
+    "\n",
+    "Next, we can add memory."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "022868f2-128e-42f5-8d90-d3bb2f11d994",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "' SELECT \"Team\" FROM nba_roster WHERE \"NAME\" = \\'Klay Thompson\\';'"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Prompt\n",
+    "from langchain.memory import ConversationBufferMemory\n",
+    "from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
+    "\n",
+    "template = \"\"\"Given an input question, convert it to a SQL query. No pre-amble. Based on the table schema below, write a SQL query that would answer the user's question:\n",
+    "{schema}\n",
+    "\"\"\"\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\"system\", template),\n",
+    "        MessagesPlaceholder(variable_name=\"history\"),\n",
+    "        (\"human\", \"{question}\"),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "memory = ConversationBufferMemory(return_messages=True)\n",
+    "\n",
+    "# Chain to query with memory\n",
+    "from langchain_core.runnables import RunnableLambda\n",
+    "\n",
+    "sql_chain = (\n",
+    "    RunnablePassthrough.assign(\n",
+    "        schema=get_schema,\n",
+    "        history=RunnableLambda(lambda x: memory.load_memory_variables(x)[\"history\"]),\n",
+    "    )\n",
+    "    | prompt\n",
+    "    | llm.bind(stop=[\"\\nSQLResult:\"])\n",
+    "    | StrOutputParser()\n",
+    ")\n",
+    "\n",
+    "\n",
+    "def save(input_output):\n",
+    "    output = {\"output\": input_output.pop(\"output\")}\n",
+    "    memory.save_context(input_output, output)\n",
+    "    return output[\"output\"]\n",
+    "\n",
+    "\n",
+    "sql_response_memory = RunnablePassthrough.assign(output=sql_chain) | save\n",
+    "sql_response_memory.invoke({\"question\": \"What team is Klay Thompson on?\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "800a7a3b-f411-478b-af51-2310cd6e0425",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=' Sure! Here\\'s the natural language response based on the given input:\\n\\n\"Klay Thompson\\'s salary is $43,219,440.\"')"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Chain to answer\n",
+    "template = \"\"\"Based on the table schema below, question, sql query, and sql response, write a natural language response:\n",
+    "{schema}\n",
+    "\n",
+    "Question: {question}\n",
+    "SQL Query: {query}\n",
+    "SQL Response: {response}\"\"\"\n",
+    "prompt_response = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            \"Given an input question and SQL response, convert it to a natural language answer. No pre-amble.\",\n",
+    "        ),\n",
+    "        (\"human\", template),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "full_chain = (\n",
+    "    RunnablePassthrough.assign(query=sql_response_memory)\n",
+    "    | RunnablePassthrough.assign(\n",
+    "        schema=get_schema,\n",
+    "        response=lambda x: db.run(x[\"query\"]),\n",
+    "    )\n",
+    "    | prompt_response\n",
+    "    | llm\n",
+    ")\n",
+    "\n",
+    "full_chain.invoke({\"question\": \"What is his salary?\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b77fee61-f4da-4bb1-8285-14101e505518",
+   "metadata": {},
+   "source": [
+    "Here is the [trace](https://smith.langchain.com/public/54794d18-2337-4ce2-8b9f-3d8a2df89e51/r)."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.16"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

cookbook/README.md

@@ -0,0 +1,59 @@
+# LangChain cookbook
+
+Example code for building applications with LangChain, with an emphasis on more applied and end-to-end examples than contained in the [main documentation](https://python.langchain.com).
+
+Notebook | Description
+:- | :-
+[LLaMA2_sql_chat.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/LLaMA2_sql_chat.ipynb) | Build a chat application that interacts with a SQL database using an open source llm (llama2), specifically demonstrated on an SQLite database containing rosters.
+[Semi_Structured_RAG.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/Semi_Structured_RAG.ipynb) | Perform retrieval-augmented generation (rag) on documents with semi-structured data, including text and tables, using unstructured for parsing, multi-vector retriever for storing, and lcel for implementing chains.
+[Semi_structured_and_multi_moda...](https://github.com/langchain-ai/langchain/tree/master/cookbook/Semi_structured_and_multi_modal_RAG.ipynb) | Perform retrieval-augmented generation (rag) on documents with semi-structured data and images, using unstructured for parsing, multi-vector retriever for storage and retrieval, and lcel for implementing chains.
+[Semi_structured_multi_modal_RA...](https://github.com/langchain-ai/langchain/tree/master/cookbook/Semi_structured_multi_modal_RAG_LLaMA2.ipynb) | Perform retrieval-augmented generation (rag) on documents with semi-structured data and images, using various tools and methods such as unstructured for parsing, multi-vector retriever for storing, lcel for implementing chains, and open source language models like llama2, llava, and gpt4all.
+[amazon_personalize_how_to.ipynb](https://github.com/langchain-ai/langchain/blob/master/cookbook/amazon_personalize_how_to.ipynb) | Retrieving personalized recommendations from Amazon Personalize and use custom agents to build generative AI apps
+[analyze_document.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/analyze_document.ipynb) | Analyze a single long document.
+[autogpt/autogpt.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/autogpt/autogpt.ipynb) | Implement autogpt, a language model, with langchain primitives such as llms, prompttemplates, vectorstores, embeddings, and tools.
+[autogpt/marathon_times.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/autogpt/marathon_times.ipynb) | Implement autogpt for finding winning marathon times.
+[baby_agi.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/baby_agi.ipynb) | Implement babyagi, an ai agent that can generate and execute tasks based on a given objective, with the flexibility to swap out specific vectorstores/model providers.
+[baby_agi_with_agent.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/baby_agi_with_agent.ipynb) | Swap out the execution chain in the babyagi notebook with an agent that has access to tools, aiming to obtain more reliable information.
+[camel_role_playing.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/camel_role_playing.ipynb) | Implement the camel framework for creating autonomous cooperative agents in large-scale language models, using role-playing and inception prompting to guide chat agents towards task completion.
+[causal_program_aided_language_...](https://github.com/langchain-ai/langchain/tree/master/cookbook/causal_program_aided_language_model.ipynb) | Implement the causal program-aided language (cpal) chain, which improves upon the program-aided language (pal) by incorporating causal structure to prevent hallucination in language models, particularly when dealing with complex narratives and math problems with nested dependencies.
+[code-analysis-deeplake.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/code-analysis-deeplake.ipynb) | Analyze its own code base with the help of gpt and activeloop's deep lake.
+[custom_agent_with_plugin_retri...](https://github.com/langchain-ai/langchain/tree/master/cookbook/custom_agent_with_plugin_retrieval.ipynb) | Build a custom agent that can interact with ai plugins by retrieving tools and creating natural language wrappers around openapi endpoints.
+[custom_agent_with_plugin_retri...](https://github.com/langchain-ai/langchain/tree/master/cookbook/custom_agent_with_plugin_retrieval_using_plugnplai.ipynb) | Build a custom agent with plugin retrieval functionality, utilizing ai plugins from the `plugnplai` directory.
+[databricks_sql_db.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/databricks_sql_db.ipynb) | Connect to databricks runtimes and databricks sql.
+[deeplake_semantic_search_over_...](https://github.com/langchain-ai/langchain/tree/master/cookbook/deeplake_semantic_search_over_chat.ipynb) | Perform semantic search and question-answering over a group chat using activeloop's deep lake with gpt4.
+[elasticsearch_db_qa.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/elasticsearch_db_qa.ipynb) | Interact with elasticsearch analytics databases in natural language and build search queries via the elasticsearch dsl API.
+[extraction_openai_tools.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/extraction_openai_tools.ipynb) | Structured Data Extraction with OpenAI Tools
+[forward_looking_retrieval_augm...](https://github.com/langchain-ai/langchain/tree/master/cookbook/forward_looking_retrieval_augmented_generation.ipynb) | Implement the forward-looking active retrieval augmented generation (flare) method, which generates answers to questions, identifies uncertain tokens, generates hypothetical questions based on these tokens, and retrieves relevant documents to continue generating the answer.
+[generative_agents_interactive_...](https://github.com/langchain-ai/langchain/tree/master/cookbook/generative_agents_interactive_simulacra_of_human_behavior.ipynb) | Implement a generative agent that simulates human behavior, based on a research paper, using a time-weighted memory object backed by a langchain retriever.
+[gymnasium_agent_simulation.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/gymnasium_agent_simulation.ipynb) | Create a simple agent-environment interaction loop in simulated environments like text-based games with gymnasium.
+[hugginggpt.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/hugginggpt.ipynb) | Implement hugginggpt, a system that connects language models like chatgpt with the machine learning community via hugging face.
+[hypothetical_document_embeddin...](https://github.com/langchain-ai/langchain/tree/master/cookbook/hypothetical_document_embeddings.ipynb) | Improve document indexing with hypothetical document embeddings (hyde), an embedding technique that generates and embeds hypothetical answers to queries.
+[learned_prompt_optimization.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/learned_prompt_optimization.ipynb) | Automatically enhance language model prompts by injecting specific terms using reinforcement learning, which can be used to personalize responses based on user preferences.
+[llm_bash.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/llm_bash.ipynb) | Perform simple filesystem commands using language learning models (llms) and a bash process.
+[llm_checker.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/llm_checker.ipynb) | Create a self-checking chain using the llmcheckerchain function.
+[llm_math.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/llm_math.ipynb) | Solve complex word math problems using language models and python repls.
+[llm_summarization_checker.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/llm_summarization_checker.ipynb) | Check the accuracy of text summaries, with the option to run the checker multiple times for improved results.
+[llm_symbolic_math.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/llm_symbolic_math.ipynb) | Solve algebraic equations with the help of llms (language learning models) and sympy, a python library for symbolic mathematics.
+[meta_prompt.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/meta_prompt.ipynb) | Implement the meta-prompt concept, which is a method for building self-improving agents that reflect on their own performance and modify their instructions accordingly.
+[multi_modal_output_agent.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multi_modal_output_agent.ipynb) | Generate multi-modal outputs, specifically images and text.
+[multi_player_dnd.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multi_player_dnd.ipynb) | Simulate multi-player dungeons & dragons games, with a custom function determining the speaking schedule of the agents.
+[multiagent_authoritarian.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multiagent_authoritarian.ipynb) | Implement a multi-agent simulation where a privileged agent controls the conversation, including deciding who speaks and when the conversation ends, in the context of a simulated news network.
+[multiagent_bidding.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multiagent_bidding.ipynb) | Implement a multi-agent simulation where agents bid to speak, with the highest bidder speaking next, demonstrated through a fictitious presidential debate example.
+[myscale_vector_sql.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/myscale_vector_sql.ipynb) | Access and interact with the myscale integrated vector database, which can enhance the performance of language model (llm) applications.
+[openai_functions_retrieval_qa....](https://github.com/langchain-ai/langchain/tree/master/cookbook/openai_functions_retrieval_qa.ipynb) | Structure response output in a question-answering system by incorporating openai functions into a retrieval pipeline.
+[openai_v1_cookbook.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/openai_v1_cookbook.ipynb) | Explore new functionality released alongside the V1 release of the OpenAI Python library.
+[petting_zoo.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/petting_zoo.ipynb) | Create multi-agent simulations with simulated environments using the petting zoo library.
+[plan_and_execute_agent.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/plan_and_execute_agent.ipynb) | Create plan-and-execute agents that accomplish objectives by planning tasks with a language model (llm) and executing them with a separate agent.
+[press_releases.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/press_releases.ipynb) | Retrieve and query company press release data powered by [Kay.ai](https://kay.ai).
+[program_aided_language_model.i...](https://github.com/langchain-ai/langchain/tree/master/cookbook/program_aided_language_model.ipynb) | Implement program-aided language models as described in the provided research paper.
+[qa_citations.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/qa_citations.ipynb) | Different ways to get a model to cite its sources.
+[rag_upstage_layout_analysis_groundedness_check.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/rag_upstage_layout_analysis_groundedness_check.ipynb) | End-to-end RAG example using Upstage Layout Analysis and Groundedness Check.
+[retrieval_in_sql.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/retrieval_in_sql.ipynb) | Perform retrieval-augmented-generation (rag) on a PostgreSQL database using pgvector.
+[sales_agent_with_context.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/sales_agent_with_context.ipynb) | Implement a context-aware ai sales agent, salesgpt, that can have natural sales conversations, interact with other systems, and use a product knowledge base to discuss a company's offerings.
+[self_query_hotel_search.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/self_query_hotel_search.ipynb) | Build a hotel room search feature with self-querying retrieval, using a specific hotel recommendation dataset.
+[smart_llm.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/smart_llm.ipynb) | Implement a smartllmchain, a self-critique chain that generates multiple output proposals, critiques them to find the best one, and then improves upon it to produce a final output.
+[tree_of_thought.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/tree_of_thought.ipynb) | Query a large language model using the tree of thought technique.
+[twitter-the-algorithm-analysis...](https://github.com/langchain-ai/langchain/tree/master/cookbook/twitter-the-algorithm-analysis-deeplake.ipynb) | Analyze the source code of the Twitter algorithm with the help of gpt4 and activeloop's deep lake.
+[two_agent_debate_tools.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/two_agent_debate_tools.ipynb) | Simulate multi-agent dialogues where the agents can utilize various tools.
+[two_player_dnd.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/two_player_dnd.ipynb) | Simulate a two-player dungeons & dragons game, where a dialogue simulator class is used to coordinate the dialogue between the protagonist and the dungeon master.
+[wikibase_agent.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/wikibase_agent.ipynb) | Create a simple wikibase agent that utilizes sparql generation, with testing done on http://wikidata.org.

cookbook/agent_vectorstore.ipynb

@@ -0,0 +1,527 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "68b24990",
+   "metadata": {},
+   "source": [
+    "# Combine agents and vector stores\n",
+    "\n",
+    "This notebook covers how to combine agents and vector stores. The use case for this is that you've ingested your data into a vector store and want to interact with it in an agentic manner.\n",
+    "\n",
+    "The recommended method for doing so is to create a `RetrievalQA` and then use that as a tool in the overall agent. Let's take a look at doing this below. You can do this with multiple different vector DBs, and use the agent as a way to route between them. There are two different ways of doing this - you can either let the agent use the vector stores as normal tools, or you can set `return_direct=True` to really just use the agent as a router."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9b22020a",
+   "metadata": {},
+   "source": [
+    "## Create the vector store"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "2e87c10a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chains import RetrievalQA\n",
+    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_openai import OpenAI, OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
+    "\n",
+    "llm = OpenAI(temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "0b7b772b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pathlib import Path\n",
+    "\n",
+    "relevant_parts = []\n",
+    "for p in Path(\".\").absolute().parts:\n",
+    "    relevant_parts.append(p)\n",
+    "    if relevant_parts[-3:] == [\"langchain\", \"docs\", \"modules\"]:\n",
+    "        break\n",
+    "doc_path = str(Path(*relevant_parts) / \"state_of_the_union.txt\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "f2675861",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running Chroma using direct local API.\n",
+      "Using DuckDB in-memory for database. Data will be transient.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain_community.document_loaders import TextLoader\n",
+    "\n",
+    "loader = TextLoader(doc_path)\n",
+    "documents = loader.load()\n",
+    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
+    "texts = text_splitter.split_documents(documents)\n",
+    "\n",
+    "embeddings = OpenAIEmbeddings()\n",
+    "docsearch = Chroma.from_documents(texts, embeddings, collection_name=\"state-of-union\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "bc5403d4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "state_of_union = RetrievalQA.from_chain_type(\n",
+    "    llm=llm, chain_type=\"stuff\", retriever=docsearch.as_retriever()\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "1431cded",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.document_loaders import WebBaseLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "915d3ff3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = WebBaseLoader(\"https://beta.ruff.rs/docs/faq/\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "96a2edf8",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running Chroma using direct local API.\n",
+      "Using DuckDB in-memory for database. Data will be transient.\n"
+     ]
+    }
+   ],
+   "source": [
+    "docs = loader.load()\n",
+    "ruff_texts = text_splitter.split_documents(docs)\n",
+    "ruff_db = Chroma.from_documents(ruff_texts, embeddings, collection_name=\"ruff\")\n",
+    "ruff = RetrievalQA.from_chain_type(\n",
+    "    llm=llm, chain_type=\"stuff\", retriever=ruff_db.as_retriever()\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "71ecef90",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c0a6c031",
+   "metadata": {},
+   "source": [
+    "## Create the Agent"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "id": "eb142786",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Import things that are needed generically\n",
+    "from langchain.agents import AgentType, Tool, initialize_agent\n",
+    "from langchain_openai import OpenAI"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "id": "850bc4e9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tools = [\n",
+    "    Tool(\n",
+    "        name=\"State of Union QA System\",\n",
+    "        func=state_of_union.run,\n",
+    "        description=\"useful for when you need to answer questions about the most recent state of the union address. Input should be a fully formed question.\",\n",
+    "    ),\n",
+    "    Tool(\n",
+    "        name=\"Ruff QA System\",\n",
+    "        func=ruff.run,\n",
+    "        description=\"useful for when you need to answer questions about ruff (a python linter). Input should be a fully formed question.\",\n",
+    "    ),\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "id": "fc47f230",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 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": 46,
+   "id": "10ca2db8",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\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",
+      "\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": [
+    "agent.run(\n",
+    "    \"What did biden say about ketanji brown jackson in the state of the union address?\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "id": "4e91b811",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\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",
+      "\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": [
+    "agent.run(\"Why use ruff over flake8?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "787a9b5e",
+   "metadata": {},
+   "source": [
+    "## Use the Agent solely as a router"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9161ba91",
+   "metadata": {},
+   "source": [
+    "You can also set `return_direct=True` if you intend to use the agent as a router and just want to directly return the result of the RetrievalQAChain.\n",
+    "\n",
+    "Notice that in the above examples the agent did some extra work after querying the RetrievalQAChain. You can avoid that and just return the result directly."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "id": "f59b377e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tools = [\n",
+    "    Tool(\n",
+    "        name=\"State of Union QA System\",\n",
+    "        func=state_of_union.run,\n",
+    "        description=\"useful for when you need to answer questions about the most recent state of the union address. Input should be a fully formed question.\",\n",
+    "        return_direct=True,\n",
+    "    ),\n",
+    "    Tool(\n",
+    "        name=\"Ruff QA System\",\n",
+    "        func=ruff.run,\n",
+    "        description=\"useful for when you need to answer questions about ruff (a python linter). Input should be a fully formed question.\",\n",
+    "        return_direct=True,\n",
+    "    ),\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "id": "8615707a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "agent = initialize_agent(\n",
+    "    tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "id": "36e718a9",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\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": [
+    "agent.run(\n",
+    "    \"What did biden say about ketanji brown jackson in the state of the union address?\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 51,
+   "id": "edfd0a1a",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\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": [
+    "agent.run(\"Why use ruff over flake8?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "49a0cbbe",
+   "metadata": {},
+   "source": [
+    "## Multi-Hop vector store reasoning\n",
+    "\n",
+    "Because vector stores are easily usable as tools in agents, it is easy to use answer multi-hop questions that depend on vector stores using the existing agent framework."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 57,
+   "id": "d397a233",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tools = [\n",
+    "    Tool(\n",
+    "        name=\"State of Union QA System\",\n",
+    "        func=state_of_union.run,\n",
+    "        description=\"useful for when you need to answer questions about the most recent state of the union address. Input should be a fully formed question, not referencing any obscure pronouns from the conversation before.\",\n",
+    "    ),\n",
+    "    Tool(\n",
+    "        name=\"Ruff QA System\",\n",
+    "        func=ruff.run,\n",
+    "        description=\"useful for when you need to answer questions about ruff (a python linter). Input should be a fully formed question, not referencing any obscure pronouns from the conversation before.\",\n",
+    "    ),\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 58,
+   "id": "06157240",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 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": 59,
+   "id": "b492b520",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\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",
+      "\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": [
+    "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",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b3b857d6",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

cookbook/airbyte_github.ipynb

@@ -0,0 +1,200 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
+   "source": [
+    "%pip install -qU langchain-airbyte"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "\n",
+    "GITHUB_TOKEN = getpass.getpass()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_airbyte import AirbyteLoader\n",
+    "from langchain_core.prompts import PromptTemplate\n",
+    "\n",
+    "loader = AirbyteLoader(\n",
+    "    source=\"source-github\",\n",
+    "    stream=\"pull_requests\",\n",
+    "    config={\n",
+    "        \"credentials\": {\"personal_access_token\": GITHUB_TOKEN},\n",
+    "        \"repositories\": [\"langchain-ai/langchain\"],\n",
+    "    },\n",
+    "    template=PromptTemplate.from_template(\n",
+    "        \"\"\"# {title}\n",
+    "by {user[login]}\n",
+    "\n",
+    "{body}\"\"\"\n",
+    "    ),\n",
+    "    include_metadata=False,\n",
+    ")\n",
+    "docs = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "# Updated partners/ibm README\n",
+      "by williamdevena\n",
+      "\n",
+      "## PR title\n",
+      "partners: changed the README file for the IBM Watson AI integration in the libs/partners/ibm folder.\n",
+      "\n",
+      "## PR message\n",
+      "Description: Changed the README file of partners/ibm following the docs on https://python.langchain.com/docs/integrations/llms/ibm_watsonx\n",
+      "\n",
+      "The README includes:\n",
+      "\n",
+      "- Brief description\n",
+      "- Installation\n",
+      "- Setting-up instructions (API key, project id, ...)\n",
+      "- Basic usage:\n",
+      "  - Loading the model\n",
+      "  - Direct inference\n",
+      "  - Chain invoking\n",
+      "  - Streaming the model output\n",
+      "  \n",
+      "Issue: https://github.com/langchain-ai/langchain/issues/17545\n",
+      "\n",
+      "Dependencies: None\n",
+      "\n",
+      "Twitter handle: None\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(docs[-2].page_content)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "10283"
+      ]
+     },
+     "execution_count": 39,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(docs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import tiktoken\n",
+    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "\n",
+    "enc = tiktoken.get_encoding(\"cl100k_base\")\n",
+    "\n",
+    "vectorstore = Chroma.from_documents(\n",
+    "    docs,\n",
+    "    embedding=OpenAIEmbeddings(\n",
+    "        disallowed_special=(enc.special_tokens_set - {\"<|endofprompt|>\"})\n",
+    "    ),\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "retriever = vectorstore.as_retriever()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='# Updated partners/ibm README\\nby williamdevena\\n\\n## PR title\\r\\npartners: changed the README file for the IBM Watson AI integration in the libs/partners/ibm folder.\\r\\n\\r\\n## PR message\\r\\nDescription: Changed the README file of partners/ibm following the docs on https://python.langchain.com/docs/integrations/llms/ibm_watsonx\\r\\n\\r\\nThe README includes:\\r\\n\\r\\n- Brief description\\r\\n- Installation\\r\\n- Setting-up instructions (API key, project id, ...)\\r\\n- Basic usage:\\r\\n  - Loading the model\\r\\n  - Direct inference\\r\\n  - Chain invoking\\r\\n  - Streaming the model output\\r\\n  \\r\\nIssue: https://github.com/langchain-ai/langchain/issues/17545\\r\\n\\r\\nDependencies: None\\r\\n\\r\\nTwitter handle: None'),\n",
+       " Document(page_content='# Updated partners/ibm README\\nby williamdevena\\n\\n## PR title\\r\\npartners: changed the README file for the IBM Watson AI integration in the `libs/partners/ibm` folder. \\r\\n\\r\\n\\r\\n\\r\\n## PR message\\r\\n- **Description:** Changed the README file of partners/ibm following the docs on https://python.langchain.com/docs/integrations/llms/ibm_watsonx\\r\\n\\r\\n    The README includes:\\r\\n    - Brief description\\r\\n    - Installation\\r\\n    - Setting-up instructions (API key, project id, ...)\\r\\n    - Basic usage:\\r\\n        - Loading the model\\r\\n        - Direct inference\\r\\n        - Chain invoking\\r\\n        - Streaming the model output\\r\\n\\r\\n\\r\\n- **Issue:** #17545\\r\\n- **Dependencies:** None\\r\\n- **Twitter handle:** None'),\n",
+       " Document(page_content='# IBM: added partners package `langchain_ibm`, added llm\\nby MateuszOssGit\\n\\n  - **Description:** Added `langchain_ibm` as an langchain partners package of IBM [watsonx.ai](https://www.ibm.com/products/watsonx-ai) LLM provider (`WatsonxLLM`)\\r\\n  - **Dependencies:** [ibm-watsonx-ai](https://pypi.org/project/ibm-watsonx-ai/),\\r\\n  - **Tag maintainer:** : \\r\\n\\r\\nPlease make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` to check this locally. ✅'),\n",
+       " Document(page_content='# Add WatsonX support\\nby baptistebignaud\\n\\nIt is a connector to use a LLM from WatsonX.\\r\\nIt requires python SDK \"ibm-generative-ai\"\\r\\n\\r\\n(It might not be perfect since it is my first PR on a public repository 😄)')]"
+      ]
+     },
+     "execution_count": 42,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "retriever.invoke(\"pull requests related to IBM\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

cookbook/amazon_personalize_how_to.ipynb

@@ -0,0 +1,284 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Amazon Personalize\n",
+    "\n",
+    "[Amazon Personalize](https://docs.aws.amazon.com/personalize/latest/dg/what-is-personalize.html) is a fully managed machine learning service that uses your data to generate item recommendations for your users. It can also generate user segments based on the users' affinity for certain items or item metadata.\n",
+    "\n",
+    "This notebook goes through how to use Amazon Personalize Chain. You need a Amazon Personalize campaign_arn or a recommender_arn before you get started with the below notebook.\n",
+    "\n",
+    "Following is a [tutorial](https://github.com/aws-samples/retail-demo-store/blob/master/workshop/1-Personalization/Lab-1-Introduction-and-data-preparation.ipynb) to setup a campaign_arn/recommender_arn on Amazon Personalize. Once the campaign_arn/recommender_arn is setup, you can use it in the langchain ecosystem. \n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 1. Install Dependencies"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "!pip install boto3"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 2. Sample Use-cases"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 2.1 [Use-case-1] Setup Amazon Personalize Client and retrieve recommendations"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_experimental.recommenders import AmazonPersonalize\n",
+    "\n",
+    "recommender_arn = \"<insert_arn>\"\n",
+    "\n",
+    "client = AmazonPersonalize(\n",
+    "    credentials_profile_name=\"default\",\n",
+    "    region_name=\"us-west-2\",\n",
+    "    recommender_arn=recommender_arn,\n",
+    ")\n",
+    "client.get_recommendations(user_id=\"1\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
+   "source": [
+    "### 2.2 [Use-case-2] Invoke Personalize Chain for summarizing results"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.llms.bedrock import Bedrock\n",
+    "from langchain_experimental.recommenders import AmazonPersonalizeChain\n",
+    "\n",
+    "bedrock_llm = Bedrock(model_id=\"anthropic.claude-v2\", region_name=\"us-west-2\")\n",
+    "\n",
+    "# Create personalize chain\n",
+    "# Use return_direct=True if you do not want summary\n",
+    "chain = AmazonPersonalizeChain.from_llm(\n",
+    "    llm=bedrock_llm, client=client, return_direct=False\n",
+    ")\n",
+    "response = chain({\"user_id\": \"1\"})\n",
+    "print(response)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 2.3 [Use-Case-3] Invoke Amazon Personalize Chain using your own prompt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.prompts.prompt import PromptTemplate\n",
+    "\n",
+    "RANDOM_PROMPT_QUERY = \"\"\"\n",
+    "You are a skilled publicist. Write a high-converting marketing email advertising several movies available in a video-on-demand streaming platform next week, \n",
+    "    given the movie and user information below. Your email will leverage the power of storytelling and persuasive language. \n",
+    "    The movies to recommend and their information is contained in the <movie> tag. \n",
+    "    All movies in the <movie> tag must be recommended. Give a summary of the movies and why the human should watch them. \n",
+    "    Put the email between <email> tags.\n",
+    "\n",
+    "    <movie>\n",
+    "    {result} \n",
+    "    </movie>\n",
+    "\n",
+    "    Assistant:\n",
+    "    \"\"\"\n",
+    "\n",
+    "RANDOM_PROMPT = PromptTemplate(input_variables=[\"result\"], template=RANDOM_PROMPT_QUERY)\n",
+    "\n",
+    "chain = AmazonPersonalizeChain.from_llm(\n",
+    "    llm=bedrock_llm, client=client, return_direct=False, prompt_template=RANDOM_PROMPT\n",
+    ")\n",
+    "chain.run({\"user_id\": \"1\", \"item_id\": \"234\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 2.4 [Use-case-4] Invoke Amazon Personalize in a Sequential Chain "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chains import LLMChain, SequentialChain\n",
+    "\n",
+    "RANDOM_PROMPT_QUERY_2 = \"\"\"\n",
+    "You are a skilled publicist. Write a high-converting marketing email advertising several movies available in a video-on-demand streaming platform next week, \n",
+    "    given the movie and user information below. Your email will leverage the power of storytelling and persuasive language. \n",
+    "    You want the email to impress the user, so make it appealing to them.\n",
+    "    The movies to recommend and their information is contained in the <movie> tag. \n",
+    "    All movies in the <movie> tag must be recommended. Give a summary of the movies and why the human should watch them. \n",
+    "    Put the email between <email> tags.\n",
+    "\n",
+    "    <movie>\n",
+    "    {result}\n",
+    "    </movie>\n",
+    "\n",
+    "    Assistant:\n",
+    "    \"\"\"\n",
+    "\n",
+    "RANDOM_PROMPT_2 = PromptTemplate(\n",
+    "    input_variables=[\"result\"], template=RANDOM_PROMPT_QUERY_2\n",
+    ")\n",
+    "personalize_chain_instance = AmazonPersonalizeChain.from_llm(\n",
+    "    llm=bedrock_llm, client=client, return_direct=True\n",
+    ")\n",
+    "random_chain_instance = LLMChain(llm=bedrock_llm, prompt=RANDOM_PROMPT_2)\n",
+    "overall_chain = SequentialChain(\n",
+    "    chains=[personalize_chain_instance, random_chain_instance],\n",
+    "    input_variables=[\"user_id\"],\n",
+    "    verbose=True,\n",
+    ")\n",
+    "overall_chain.run({\"user_id\": \"1\", \"item_id\": \"234\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
+   "source": [
+    "### 2.5 [Use-case-5] Invoke Amazon Personalize and retrieve metadata "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
+   "outputs": [],
+   "source": [
+    "recommender_arn = \"<insert_arn>\"\n",
+    "metadata_column_names = [\n",
+    "    \"<insert metadataColumnName-1>\",\n",
+    "    \"<insert metadataColumnName-2>\",\n",
+    "]\n",
+    "metadataMap = {\"ITEMS\": metadata_column_names}\n",
+    "\n",
+    "client = AmazonPersonalize(\n",
+    "    credentials_profile_name=\"default\",\n",
+    "    region_name=\"us-west-2\",\n",
+    "    recommender_arn=recommender_arn,\n",
+    ")\n",
+    "client.get_recommendations(user_id=\"1\", metadataColumns=metadataMap)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
+   "source": [
+    "### 2.6 [Use-Case 6] Invoke Personalize Chain with returned metadata for summarizing results"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
+   "outputs": [],
+   "source": [
+    "bedrock_llm = Bedrock(model_id=\"anthropic.claude-v2\", region_name=\"us-west-2\")\n",
+    "\n",
+    "# Create personalize chain\n",
+    "# Use return_direct=True if you do not want summary\n",
+    "chain = AmazonPersonalizeChain.from_llm(\n",
+    "    llm=bedrock_llm, client=client, return_direct=False\n",
+    ")\n",
+    "response = chain({\"user_id\": \"1\", \"metadata_columns\": metadataMap})\n",
+    "print(response)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.7"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "15e58ce194949b77a891bd4339ce3d86a9bd138e905926019517993f97db9e6c"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

cookbook/analyze_document.ipynb

@@ -0,0 +1,105 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "f69d4a4c-137d-47e9-bea1-786afce9c1c0",
+   "metadata": {},
+   "source": [
+    "# Analyze a single long document\n",
+    "\n",
+    "The AnalyzeDocumentChain takes in a single document, splits it up, and then runs it through a CombineDocumentsChain."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "2a0707ce-6d2d-471b-bc33-64da32a7b3f0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open(\"../docs/docs/modules/state_of_the_union.txt\") as f:\n",
+    "    state_of_the_union = f.read()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "ca14d161-2d5b-4a6c-a296-77d8ce4b28cd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chains import AnalyzeDocumentChain\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "9f97406c-85a9-45fb-99ce-9138c0ba3731",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chains.question_answering import load_qa_chain\n",
+    "\n",
+    "qa_chain = load_qa_chain(llm, chain_type=\"map_reduce\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "0871a753-f5bb-4b4f-a394-f87f2691f659",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "qa_document_chain = AnalyzeDocumentChain(combine_docs_chain=qa_chain)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "e6f86428-3c2c-46a0-a57c-e22826fdbf91",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'The President said, \"Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service.\"'"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "qa_document_chain.run(\n",
+    "    input_document=state_of_the_union,\n",
+    "    question=\"what did the president say about justice breyer?\",\n",
+    ")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

cookbook/apache_kafka_message_handling.ipynb

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

cookbook/autogpt/autogpt.ipynb

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

cookbook/autogpt/marathon_times.ipynb

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

cookbook/baby_agi.ipynb

@@ -0,0 +1,250 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "517a9fd4",
+   "metadata": {},
+   "source": [
+    "# BabyAGI User Guide\n",
+    "\n",
+    "This notebook demonstrates how to implement [BabyAGI](https://github.com/yoheinakajima/babyagi/tree/main) by [Yohei Nakajima](https://twitter.com/yoheinakajima). BabyAGI is an AI agent that can generate and pretend to execute tasks based on a given objective.\n",
+    "\n",
+    "This guide will help you understand the components to create your own recursive agents.\n",
+    "\n",
+    "Although BabyAGI uses specific vectorstores/model providers (Pinecone, OpenAI), one of the benefits of implementing it with LangChain is that you can easily swap those out for different options. In this implementation we use a FAISS vectorstore (because it runs locally and is free)."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "556af556",
+   "metadata": {},
+   "source": [
+    "## Install and Import Required Modules"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "c8a354b6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from typing import Optional\n",
+    "\n",
+    "from langchain_experimental.autonomous_agents import BabyAGI\n",
+    "from langchain_openai import OpenAI, OpenAIEmbeddings"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "09f70772",
+   "metadata": {},
+   "source": [
+    "## Connect to the Vector Store\n",
+    "\n",
+    "Depending on what vectorstore you use, this step may look different."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "794045d4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.docstore import InMemoryDocstore\n",
+    "from langchain_community.vectorstores import FAISS"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "6e0305eb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Define your embedding model\n",
+    "embeddings_model = OpenAIEmbeddings()\n",
+    "# Initialize the vectorstore as empty\n",
+    "import faiss\n",
+    "\n",
+    "embedding_size = 1536\n",
+    "index = faiss.IndexFlatL2(embedding_size)\n",
+    "vectorstore = FAISS(embeddings_model.embed_query, index, InMemoryDocstore({}), {})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "05ba762e",
+   "metadata": {},
+   "source": [
+    "### Run the BabyAGI\n",
+    "\n",
+    "Now it's time to create the BabyAGI controller and watch it try to accomplish your objective."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "3d220b69",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "OBJECTIVE = \"Write a weather report for SF today\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "8a8e5543",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = OpenAI(temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "3d69899b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Logging of LLMChains\n",
+    "verbose = False\n",
+    "# If None, will keep on going forever\n",
+    "max_iterations: Optional[int] = 3\n",
+    "baby_agi = BabyAGI.from_llm(\n",
+    "    llm=llm, vectorstore=vectorstore, verbose=verbose, max_iterations=max_iterations\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "f7957b51",
+   "metadata": {
+    "scrolled": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[95m\u001b[1m\n",
+      "*****TASK LIST*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "1: Make a todo list\n",
+      "\u001b[92m\u001b[1m\n",
+      "*****NEXT TASK*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "1: Make a todo list\n",
+      "\u001b[93m\u001b[1m\n",
+      "*****TASK RESULT*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "\n",
+      "\n",
+      "1. Check the weather forecast for San Francisco today\n",
+      "2. Make note of the temperature, humidity, wind speed, and other relevant weather conditions\n",
+      "3. Write a weather report summarizing the forecast\n",
+      "4. Check for any weather alerts or warnings\n",
+      "5. Share the report with the relevant stakeholders\n",
+      "\u001b[95m\u001b[1m\n",
+      "*****TASK LIST*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "2: Check the current temperature in San Francisco\n",
+      "3: Check the current humidity in San Francisco\n",
+      "4: Check the current wind speed in San Francisco\n",
+      "5: Check for any weather alerts or warnings in San Francisco\n",
+      "6: Check the forecast for the next 24 hours in San Francisco\n",
+      "7: Check the forecast for the next 48 hours in San Francisco\n",
+      "8: Check the forecast for the next 72 hours in San Francisco\n",
+      "9: Check the forecast for the next week in San Francisco\n",
+      "10: Check the forecast for the next month in San Francisco\n",
+      "11: Check the forecast for the next 3 months in San Francisco\n",
+      "1: Write a weather report for SF today\n",
+      "\u001b[92m\u001b[1m\n",
+      "*****NEXT TASK*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "2: Check the current temperature in San Francisco\n",
+      "\u001b[93m\u001b[1m\n",
+      "*****TASK RESULT*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "\n",
+      "\n",
+      "I will check the current temperature in San Francisco. I will use an online weather service to get the most up-to-date information.\n",
+      "\u001b[95m\u001b[1m\n",
+      "*****TASK LIST*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "3: Check the current UV index in San Francisco.\n",
+      "4: Check the current air quality in San Francisco.\n",
+      "5: Check the current precipitation levels in San Francisco.\n",
+      "6: Check the current cloud cover in San Francisco.\n",
+      "7: Check the current barometric pressure in San Francisco.\n",
+      "8: Check the current dew point in San Francisco.\n",
+      "9: Check the current wind direction in San Francisco.\n",
+      "10: Check the current humidity levels in San Francisco.\n",
+      "1: Check the current temperature in San Francisco to the average temperature for this time of year.\n",
+      "2: Check the current visibility in San Francisco.\n",
+      "11: Write a weather report for SF today.\n",
+      "\u001b[92m\u001b[1m\n",
+      "*****NEXT TASK*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "3: Check the current UV index in San Francisco.\n",
+      "\u001b[93m\u001b[1m\n",
+      "*****TASK RESULT*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "\n",
+      "\n",
+      "The current UV index in San Francisco is moderate. The UV index is expected to remain at moderate levels throughout the day. It is recommended to wear sunscreen and protective clothing when outdoors.\n",
+      "\u001b[91m\u001b[1m\n",
+      "*****TASK ENDING*****\n",
+      "\u001b[0m\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "{'objective': 'Write a weather report for SF today'}"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "baby_agi({\"objective\": OBJECTIVE})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "898a210b",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.16"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

cookbook/baby_agi_with_agent.ipynb

@@ -0,0 +1,388 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "517a9fd4",
+   "metadata": {},
+   "source": [
+    "# BabyAGI with Tools\n",
+    "\n",
+    "This notebook builds on top of [baby agi](baby_agi.html), but shows how you can swap out the execution chain. The previous execution chain was just an LLM which made stuff up. By swapping it out with an agent that has access to tools, we can hopefully get real reliable information"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "556af556",
+   "metadata": {},
+   "source": [
+    "## Install and Import Required Modules"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "c8a354b6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from typing import Optional\n",
+    "\n",
+    "from langchain.chains import LLMChain\n",
+    "from langchain.prompts import PromptTemplate\n",
+    "from langchain_experimental.autonomous_agents import BabyAGI\n",
+    "from langchain_openai import OpenAI, OpenAIEmbeddings"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "09f70772",
+   "metadata": {},
+   "source": [
+    "## Connect to the Vector Store\n",
+    "\n",
+    "Depending on what vectorstore you use, this step may look different."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "794045d4",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Note: you may need to restart the kernel to use updated packages.\n",
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
+   "source": [
+    "%pip install faiss-cpu > /dev/null\n",
+    "%pip install google-search-results > /dev/null\n",
+    "from langchain.docstore import InMemoryDocstore\n",
+    "from langchain_community.vectorstores import FAISS"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "6e0305eb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Define your embedding model\n",
+    "embeddings_model = OpenAIEmbeddings()\n",
+    "# Initialize the vectorstore as empty\n",
+    "import faiss\n",
+    "\n",
+    "embedding_size = 1536\n",
+    "index = faiss.IndexFlatL2(embedding_size)\n",
+    "vectorstore = FAISS(embeddings_model.embed_query, index, InMemoryDocstore({}), {})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0f3b72bf",
+   "metadata": {},
+   "source": [
+    "## Define the Chains\n",
+    "\n",
+    "BabyAGI relies on three LLM chains:\n",
+    "- Task creation chain to select new tasks to add to the list\n",
+    "- Task prioritization chain to re-prioritize tasks\n",
+    "- Execution Chain to execute the tasks\n",
+    "\n",
+    "\n",
+    "NOTE: in this notebook, the Execution chain will now be an agent."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "b43cd580",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.agents import AgentExecutor, Tool, ZeroShotAgent\n",
+    "from langchain.chains import LLMChain\n",
+    "from langchain_community.utilities import SerpAPIWrapper\n",
+    "from langchain_openai import OpenAI\n",
+    "\n",
+    "todo_prompt = PromptTemplate.from_template(\n",
+    "    \"You are a planner who is an expert at coming up with a todo list for a given objective. Come up with a todo list for this objective: {objective}\"\n",
+    ")\n",
+    "todo_chain = LLMChain(llm=OpenAI(temperature=0), prompt=todo_prompt)\n",
+    "search = SerpAPIWrapper()\n",
+    "tools = [\n",
+    "    Tool(\n",
+    "        name=\"Search\",\n",
+    "        func=search.run,\n",
+    "        description=\"useful for when you need to answer questions about current events\",\n",
+    "    ),\n",
+    "    Tool(\n",
+    "        name=\"TODO\",\n",
+    "        func=todo_chain.run,\n",
+    "        description=\"useful for when you need to come up with todo lists. Input: an objective to create a todo list for. Output: a todo list for that objective. Please be very clear what the objective is!\",\n",
+    "    ),\n",
+    "]\n",
+    "\n",
+    "\n",
+    "prefix = \"\"\"You are an AI who performs one task based on the following objective: {objective}. Take into account these previously completed tasks: {context}.\"\"\"\n",
+    "suffix = \"\"\"Question: {task}\n",
+    "{agent_scratchpad}\"\"\"\n",
+    "prompt = ZeroShotAgent.create_prompt(\n",
+    "    tools,\n",
+    "    prefix=prefix,\n",
+    "    suffix=suffix,\n",
+    "    input_variables=[\"objective\", \"task\", \"context\", \"agent_scratchpad\"],\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "4b00ae2e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = OpenAI(temperature=0)\n",
+    "llm_chain = LLMChain(llm=llm, prompt=prompt)\n",
+    "tool_names = [tool.name for tool in tools]\n",
+    "agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names)\n",
+    "agent_executor = AgentExecutor.from_agent_and_tools(\n",
+    "    agent=agent, tools=tools, verbose=True\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "05ba762e",
+   "metadata": {},
+   "source": [
+    "### Run the BabyAGI\n",
+    "\n",
+    "Now it's time to create the BabyAGI controller and watch it try to accomplish your objective."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "3d220b69",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "OBJECTIVE = \"Write a weather report for SF today\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "3d69899b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Logging of LLMChains\n",
+    "verbose = False\n",
+    "# If None, will keep on going forever\n",
+    "max_iterations: Optional[int] = 3\n",
+    "baby_agi = BabyAGI.from_llm(\n",
+    "    llm=llm,\n",
+    "    vectorstore=vectorstore,\n",
+    "    task_execution_chain=agent_executor,\n",
+    "    verbose=verbose,\n",
+    "    max_iterations=max_iterations,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "f7957b51",
+   "metadata": {
+    "scrolled": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[95m\u001b[1m\n",
+      "*****TASK LIST*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "1: Make a todo list\n",
+      "\u001b[92m\u001b[1m\n",
+      "*****NEXT TASK*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "1: Make a todo list\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: I need to come up with a todo list\n",
+      "Action: TODO\n",
+      "Action Input: Write a weather report for SF today\u001b[0m\u001b[33;1m\u001b[1;3m\n",
+      "\n",
+      "1. Research current weather conditions in San Francisco\n",
+      "2. Gather data on temperature, humidity, wind speed, and other relevant weather conditions\n",
+      "3. Analyze data to determine current weather trends\n",
+      "4. Write a brief introduction to the weather report\n",
+      "5. Describe current weather conditions in San Francisco\n",
+      "6. Discuss any upcoming weather changes\n",
+      "7. Summarize the weather report\n",
+      "8. Proofread and edit the report\n",
+      "9. Submit the report\u001b[0m\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: The todo list for writing a weather report for SF today is: 1. Research current weather conditions in San Francisco; 2. Gather data on temperature, humidity, wind speed, and other relevant weather conditions; 3. Analyze data to determine current weather trends; 4. Write a brief introduction to the weather report; 5. Describe current weather conditions in San Francisco; 6. Discuss any upcoming weather changes; 7. Summarize the weather report; 8. Proofread and edit the report; 9. Submit the report.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\u001b[93m\u001b[1m\n",
+      "*****TASK RESULT*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "The todo list for writing a weather report for SF today is: 1. Research current weather conditions in San Francisco; 2. Gather data on temperature, humidity, wind speed, and other relevant weather conditions; 3. Analyze data to determine current weather trends; 4. Write a brief introduction to the weather report; 5. Describe current weather conditions in San Francisco; 6. Discuss any upcoming weather changes; 7. Summarize the weather report; 8. Proofread and edit the report; 9. Submit the report.\n",
+      "\u001b[95m\u001b[1m\n",
+      "*****TASK LIST*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "2: Gather data on precipitation, cloud cover, and other relevant weather conditions;\n",
+      "3: Analyze data to determine any upcoming weather changes;\n",
+      "4: Research current weather forecasts for San Francisco;\n",
+      "5: Create a visual representation of the weather report;\n",
+      "6: Include relevant images and graphics in the report;\n",
+      "7: Format the report for readability;\n",
+      "8: Publish the report online;\n",
+      "9: Monitor the report for accuracy.\n",
+      "\u001b[92m\u001b[1m\n",
+      "*****NEXT TASK*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "2: Gather data on precipitation, cloud cover, and other relevant weather conditions;\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: I need to search for current weather conditions in San Francisco\n",
+      "Action: Search\n",
+      "Action Input: Current weather conditions in San Francisco\u001b[0m\u001b[36;1m\u001b[1;3mCurrent Weather for Popular Cities ; San Francisco, CA 46 · Partly Cloudy ; Manhattan, NY warning 52 · Cloudy ; Schiller Park, IL (60176) 40 · Sunny ; Boston, MA 54 ...\u001b[0m\u001b[32;1m\u001b[1;3m I need to compile the data into a weather report\n",
+      "Action: TODO\n",
+      "Action Input: Compile data into a weather report\u001b[0m\u001b[33;1m\u001b[1;3m\n",
+      "\n",
+      "1. Gather data from reliable sources such as the National Weather Service, local weather stations, and other meteorological organizations.\n",
+      "\n",
+      "2. Analyze the data to identify trends and patterns.\n",
+      "\n",
+      "3. Create a chart or graph to visualize the data.\n",
+      "\n",
+      "4. Write a summary of the data and its implications.\n",
+      "\n",
+      "5. Compile the data into a report format.\n",
+      "\n",
+      "6. Proofread the report for accuracy and clarity.\n",
+      "\n",
+      "7. Publish the report to a website or other platform.\n",
+      "\n",
+      "8. Distribute the report to relevant stakeholders.\u001b[0m\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: Today in San Francisco, the temperature is 46 degrees Fahrenheit with partly cloudy skies. The forecast for the rest of the day is expected to remain partly cloudy.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\u001b[93m\u001b[1m\n",
+      "*****TASK RESULT*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "Today in San Francisco, the temperature is 46 degrees Fahrenheit with partly cloudy skies. The forecast for the rest of the day is expected to remain partly cloudy.\n",
+      "\u001b[95m\u001b[1m\n",
+      "*****TASK LIST*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "3: Format the report for readability;\n",
+      "4: Include relevant images and graphics in the report;\n",
+      "5: Compare the current weather conditions in San Francisco to the forecasted conditions;\n",
+      "6: Identify any potential weather-related hazards in the area;\n",
+      "7: Research historical weather patterns in San Francisco;\n",
+      "8: Identify any potential trends in the weather data;\n",
+      "9: Include relevant data sources in the report;\n",
+      "10: Summarize the weather report in a concise manner;\n",
+      "11: Include a summary of the forecasted weather conditions;\n",
+      "12: Include a summary of the current weather conditions;\n",
+      "13: Include a summary of the historical weather patterns;\n",
+      "14: Include a summary of the potential weather-related hazards;\n",
+      "15: Include a summary of the potential trends in the weather data;\n",
+      "16: Include a summary of the data sources used in the report;\n",
+      "17: Analyze data to determine any upcoming weather changes;\n",
+      "18: Research current weather forecasts for San Francisco;\n",
+      "19: Create a visual representation of the weather report;\n",
+      "20: Publish the report online;\n",
+      "21: Monitor the report for accuracy\n",
+      "\u001b[92m\u001b[1m\n",
+      "*****NEXT TASK*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "3: Format the report for readability;\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: I need to make sure the report is easy to read;\n",
+      "Action: TODO\n",
+      "Action Input: Make the report easy to read\u001b[0m\u001b[33;1m\u001b[1;3m\n",
+      "\n",
+      "1. Break up the report into sections with clear headings\n",
+      "2. Use bullet points and numbered lists to organize information\n",
+      "3. Use short, concise sentences\n",
+      "4. Use simple language and avoid jargon\n",
+      "5. Include visuals such as charts, graphs, and diagrams to illustrate points\n",
+      "6. Use bold and italicized text to emphasize key points\n",
+      "7. Include a table of contents and page numbers\n",
+      "8. Use a consistent font and font size throughout the report\n",
+      "9. Include a summary at the end of the report\n",
+      "10. Proofread the report for typos and errors\u001b[0m\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: The report should be formatted for readability by breaking it up into sections with clear headings, using bullet points and numbered lists to organize information, using short, concise sentences, using simple language and avoiding jargon, including visuals such as charts, graphs, and diagrams to illustrate points, using bold and italicized text to emphasize key points, including a table of contents and page numbers, using a consistent font and font size throughout the report, including a summary at the end of the report, and proofreading the report for typos and errors.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\u001b[93m\u001b[1m\n",
+      "*****TASK RESULT*****\n",
+      "\u001b[0m\u001b[0m\n",
+      "The report should be formatted for readability by breaking it up into sections with clear headings, using bullet points and numbered lists to organize information, using short, concise sentences, using simple language and avoiding jargon, including visuals such as charts, graphs, and diagrams to illustrate points, using bold and italicized text to emphasize key points, including a table of contents and page numbers, using a consistent font and font size throughout the report, including a summary at the end of the report, and proofreading the report for typos and errors.\n",
+      "\u001b[91m\u001b[1m\n",
+      "*****TASK ENDING*****\n",
+      "\u001b[0m\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "{'objective': 'Write a weather report for SF today'}"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "baby_agi({\"objective\": OBJECTIVE})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "898a210b",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

cookbook/camel_role_playing.ipynb

@@ -0,0 +1,708 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# CAMEL Role-Playing Autonomous Cooperative Agents\n",
+    "\n",
+    "This is a langchain implementation of paper: \"CAMEL: Communicative Agents for “Mind” Exploration of Large Scale Language Model Society\".\n",
+    "\n",
+    "Overview:\n",
+    "\n",
+    "The rapid advancement of conversational and chat-based language models has led to remarkable progress in complex task-solving. However, their success heavily relies on human input to guide the conversation, which can be challenging and time-consuming. This paper explores the potential of building scalable techniques to facilitate autonomous cooperation among communicative agents and provide insight into their \"cognitive\" processes. To address the challenges of achieving autonomous cooperation, we propose a novel communicative agent framework named role-playing. Our approach involves using inception prompting to guide chat agents toward task completion while maintaining consistency with human intentions. We showcase how role-playing can be used to generate conversational data for studying the behaviors and capabilities of chat agents, providing a valuable resource for investigating conversational language models. Our contributions include introducing a novel communicative agent framework, offering a scalable approach for studying the cooperative behaviors and capabilities of multi-agent systems, and open-sourcing our library to support research on communicative agents and beyond.\n",
+    "\n",
+    "The original implementation: https://github.com/lightaime/camel\n",
+    "\n",
+    "Project website: https://www.camel-ai.org/\n",
+    "\n",
+    "Arxiv paper: https://arxiv.org/abs/2303.17760\n"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Import LangChain related modules "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from typing import List\n",
+    "\n",
+    "from langchain.prompts.chat import (\n",
+    "    HumanMessagePromptTemplate,\n",
+    "    SystemMessagePromptTemplate,\n",
+    ")\n",
+    "from langchain.schema import (\n",
+    "    AIMessage,\n",
+    "    BaseMessage,\n",
+    "    HumanMessage,\n",
+    "    SystemMessage,\n",
+    ")\n",
+    "from langchain_openai import ChatOpenAI"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Define a CAMEL agent helper class"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class CAMELAgent:\n",
+    "    def __init__(\n",
+    "        self,\n",
+    "        system_message: SystemMessage,\n",
+    "        model: ChatOpenAI,\n",
+    "    ) -> None:\n",
+    "        self.system_message = system_message\n",
+    "        self.model = model\n",
+    "        self.init_messages()\n",
+    "\n",
+    "    def reset(self) -> None:\n",
+    "        self.init_messages()\n",
+    "        return self.stored_messages\n",
+    "\n",
+    "    def init_messages(self) -> None:\n",
+    "        self.stored_messages = [self.system_message]\n",
+    "\n",
+    "    def update_messages(self, message: BaseMessage) -> List[BaseMessage]:\n",
+    "        self.stored_messages.append(message)\n",
+    "        return self.stored_messages\n",
+    "\n",
+    "    def step(\n",
+    "        self,\n",
+    "        input_message: HumanMessage,\n",
+    "    ) -> AIMessage:\n",
+    "        messages = self.update_messages(input_message)\n",
+    "\n",
+    "        output_message = self.model.invoke(messages)\n",
+    "        self.update_messages(output_message)\n",
+    "\n",
+    "        return output_message"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setup OpenAI API key and roles and task for role-playing"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"\"\n",
+    "\n",
+    "assistant_role_name = \"Python Programmer\"\n",
+    "user_role_name = \"Stock Trader\"\n",
+    "task = \"Develop a trading bot for the stock market\"\n",
+    "word_limit = 50  # word limit for task brainstorming"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create a task specify agent for brainstorming and get the specified task"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Specified task: Develop a Python-based swing trading bot that scans market trends, monitors stocks, and generates trading signals to help a stock trader to place optimal buy and sell orders with defined stop losses and profit targets.\n"
+     ]
+    }
+   ],
+   "source": [
+    "task_specifier_sys_msg = SystemMessage(content=\"You can make a task more specific.\")\n",
+    "task_specifier_prompt = \"\"\"Here is a task that {assistant_role_name} will help {user_role_name} to complete: {task}.\n",
+    "Please make it more specific. Be creative and imaginative.\n",
+    "Please reply with the specified task in {word_limit} words or less. Do not add anything else.\"\"\"\n",
+    "task_specifier_template = HumanMessagePromptTemplate.from_template(\n",
+    "    template=task_specifier_prompt\n",
+    ")\n",
+    "task_specify_agent = CAMELAgent(task_specifier_sys_msg, ChatOpenAI(temperature=1.0))\n",
+    "task_specifier_msg = task_specifier_template.format_messages(\n",
+    "    assistant_role_name=assistant_role_name,\n",
+    "    user_role_name=user_role_name,\n",
+    "    task=task,\n",
+    "    word_limit=word_limit,\n",
+    ")[0]\n",
+    "specified_task_msg = task_specify_agent.step(task_specifier_msg)\n",
+    "print(f\"Specified task: {specified_task_msg.content}\")\n",
+    "specified_task = specified_task_msg.content"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create inception prompts for AI assistant and AI user for role-playing"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "assistant_inception_prompt = \"\"\"Never forget you are a {assistant_role_name} and I am a {user_role_name}. Never flip roles! Never instruct me!\n",
+    "We share a common interest in collaborating to successfully complete a task.\n",
+    "You must help me to complete the task.\n",
+    "Here is the task: {task}. Never forget our task!\n",
+    "I must instruct you based on your expertise and my needs to complete the task.\n",
+    "\n",
+    "I must give you one instruction at a time.\n",
+    "You must write a specific solution that appropriately completes the requested instruction.\n",
+    "You must decline my instruction honestly if you cannot perform the instruction due to physical, moral, legal reasons or your capability and explain the reasons.\n",
+    "Do not add anything else other than your solution to my instruction.\n",
+    "You are never supposed to ask me any questions you only answer questions.\n",
+    "You are never supposed to reply with a flake solution. Explain your solutions.\n",
+    "Your solution must be declarative sentences and simple present tense.\n",
+    "Unless I say the task is completed, you should always start with:\n",
+    "\n",
+    "Solution: <YOUR_SOLUTION>\n",
+    "\n",
+    "<YOUR_SOLUTION> should be specific and provide preferable implementations and examples for task-solving.\n",
+    "Always end <YOUR_SOLUTION> with: Next request.\"\"\"\n",
+    "\n",
+    "user_inception_prompt = \"\"\"Never forget you are a {user_role_name} and I am a {assistant_role_name}. Never flip roles! You will always instruct me.\n",
+    "We share a common interest in collaborating to successfully complete a task.\n",
+    "I must help you to complete the task.\n",
+    "Here is the task: {task}. Never forget our task!\n",
+    "You must instruct me based on my expertise and your needs to complete the task ONLY in the following two ways:\n",
+    "\n",
+    "1. Instruct with a necessary input:\n",
+    "Instruction: <YOUR_INSTRUCTION>\n",
+    "Input: <YOUR_INPUT>\n",
+    "\n",
+    "2. Instruct without any input:\n",
+    "Instruction: <YOUR_INSTRUCTION>\n",
+    "Input: None\n",
+    "\n",
+    "The \"Instruction\" describes a task or question. The paired \"Input\" provides further context or information for the requested \"Instruction\".\n",
+    "\n",
+    "You must give me one instruction at a time.\n",
+    "I must write a response that appropriately completes the requested instruction.\n",
+    "I must decline your instruction honestly if I cannot perform the instruction due to physical, moral, legal reasons or my capability and explain the reasons.\n",
+    "You should instruct me not ask me questions.\n",
+    "Now you must start to instruct me using the two ways described above.\n",
+    "Do not add anything else other than your instruction and the optional corresponding input!\n",
+    "Keep giving me instructions and necessary inputs until you think the task is completed.\n",
+    "When the task is completed, you must only reply with a single word <CAMEL_TASK_DONE>.\n",
+    "Never say <CAMEL_TASK_DONE> unless my responses have solved your task.\"\"\""
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create a helper helper to get system messages for AI assistant and AI user from role names and the task"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_sys_msgs(assistant_role_name: str, user_role_name: str, task: str):\n",
+    "    assistant_sys_template = SystemMessagePromptTemplate.from_template(\n",
+    "        template=assistant_inception_prompt\n",
+    "    )\n",
+    "    assistant_sys_msg = assistant_sys_template.format_messages(\n",
+    "        assistant_role_name=assistant_role_name,\n",
+    "        user_role_name=user_role_name,\n",
+    "        task=task,\n",
+    "    )[0]\n",
+    "\n",
+    "    user_sys_template = SystemMessagePromptTemplate.from_template(\n",
+    "        template=user_inception_prompt\n",
+    "    )\n",
+    "    user_sys_msg = user_sys_template.format_messages(\n",
+    "        assistant_role_name=assistant_role_name,\n",
+    "        user_role_name=user_role_name,\n",
+    "        task=task,\n",
+    "    )[0]\n",
+    "\n",
+    "    return assistant_sys_msg, user_sys_msg"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create AI assistant agent and AI user agent from obtained system messages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "assistant_sys_msg, user_sys_msg = get_sys_msgs(\n",
+    "    assistant_role_name, user_role_name, specified_task\n",
+    ")\n",
+    "assistant_agent = CAMELAgent(assistant_sys_msg, ChatOpenAI(temperature=0.2))\n",
+    "user_agent = CAMELAgent(user_sys_msg, ChatOpenAI(temperature=0.2))\n",
+    "\n",
+    "# Reset agents\n",
+    "assistant_agent.reset()\n",
+    "user_agent.reset()\n",
+    "\n",
+    "# Initialize chats\n",
+    "user_msg = HumanMessage(\n",
+    "    content=(\n",
+    "        f\"{user_sys_msg.content}. \"\n",
+    "        \"Now start to give me introductions one by one. \"\n",
+    "        \"Only reply with Instruction and Input.\"\n",
+    "    )\n",
+    ")\n",
+    "\n",
+    "assistant_msg = HumanMessage(content=f\"{assistant_sys_msg.content}\")\n",
+    "assistant_msg = assistant_agent.step(user_msg)"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Start role-playing session to solve the task!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Original task prompt:\n",
+      "Develop a trading bot for the stock market\n",
+      "\n",
+      "Specified task prompt:\n",
+      "Develop a Python-based swing trading bot that scans market trends, monitors stocks, and generates trading signals to help a stock trader to place optimal buy and sell orders with defined stop losses and profit targets.\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Install the necessary Python libraries for data analysis and trading.\n",
+      "Input: None\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can install the necessary Python libraries using pip, a package installer for Python. We can install pandas, numpy, matplotlib, and ta-lib for data analysis and trading. We can use the following command to install these libraries:\n",
+      "\n",
+      "```\n",
+      "pip install pandas numpy matplotlib ta-lib\n",
+      "```\n",
+      "\n",
+      "Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Import the necessary libraries in the Python script.\n",
+      "Input: None\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can import the necessary libraries in the Python script using the import statement. We need to import pandas, numpy, matplotlib, and ta-lib for data analysis and trading. We can use the following code to import these libraries:\n",
+      "\n",
+      "```\n",
+      "import pandas as pd\n",
+      "import numpy as np\n",
+      "import matplotlib.pyplot as plt\n",
+      "import talib as ta\n",
+      "```\n",
+      "\n",
+      "Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Load historical stock data into a pandas DataFrame.\n",
+      "Input: The path to the CSV file containing the historical stock data.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can load historical stock data into a pandas DataFrame using the `read_csv()` function from pandas. We need to pass the path to the CSV file containing the historical stock data as an argument to this function. We can use the following code to load the historical stock data:\n",
+      "\n",
+      "```\n",
+      "df = pd.read_csv('path/to/csv/file.csv')\n",
+      "```\n",
+      "\n",
+      "This will load the historical stock data into a pandas DataFrame called `df`. Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Preprocess the historical stock data by setting the date column as the index and sorting the DataFrame in ascending order by date.\n",
+      "Input: None.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can preprocess the historical stock data by setting the date column as the index and sorting the DataFrame in ascending order by date using the `set_index()` and `sort_index()` functions from pandas. We can use the following code to preprocess the historical stock data:\n",
+      "\n",
+      "```\n",
+      "df = df.set_index('date')\n",
+      "df = df.sort_index(ascending=True)\n",
+      "```\n",
+      "\n",
+      "This will set the date column as the index and sort the DataFrame in ascending order by date. Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Calculate the short-term and long-term moving averages for the stock data using the `ta.SMA()` function from ta-lib.\n",
+      "Input: The period for the short-term moving average and the period for the long-term moving average.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can calculate the short-term and long-term moving averages for the stock data using the `ta.SMA()` function from ta-lib. We need to pass the period for the short-term moving average and the period for the long-term moving average as arguments to this function. We can use the following code to calculate the short-term and long-term moving averages:\n",
+      "\n",
+      "```\n",
+      "short_ma = ta.SMA(df['close'], timeperiod=short_period)\n",
+      "long_ma = ta.SMA(df['close'], timeperiod=long_period)\n",
+      "```\n",
+      "\n",
+      "This will calculate the short-term and long-term moving averages for the stock data and store them in the `short_ma` and `long_ma` variables, respectively. Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Create a new DataFrame that combines the historical stock data with the short-term and long-term moving averages.\n",
+      "Input: None.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can create a new DataFrame that combines the historical stock data with the short-term and long-term moving averages using the `concat()` function from pandas. We need to pass the historical stock data, the short-term moving average, and the long-term moving average as arguments to this function. We can use the following code to create the new DataFrame:\n",
+      "\n",
+      "```\n",
+      "new_df = pd.concat([df, short_ma, long_ma], axis=1)\n",
+      "new_df.columns = ['open', 'high', 'low', 'close', 'volume', 'short_ma', 'long_ma']\n",
+      "```\n",
+      "\n",
+      "This will create a new DataFrame called `new_df` that combines the historical stock data with the short-term and long-term moving averages. The columns of the new DataFrame are named 'open', 'high', 'low', 'close', 'volume', 'short_ma', and 'long_ma'. Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Create a new column in the DataFrame that indicates when to buy or sell the stock based on the crossover of the short-term and long-term moving averages.\n",
+      "Input: None.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can create a new column in the DataFrame that indicates when to buy or sell the stock based on the crossover of the short-term and long-term moving averages. We can use the following code to create the new column:\n",
+      "\n",
+      "```\n",
+      "new_df['signal'] = np.where(new_df['short_ma'] > new_df['long_ma'], 1, -1)\n",
+      "```\n",
+      "\n",
+      "This will create a new column called 'signal' in the DataFrame that indicates when to buy or sell the stock based on the crossover of the short-term and long-term moving averages. If the short-term moving average is greater than the long-term moving average, the signal is 1 (buy), otherwise the signal is -1 (sell). Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Create a new column in the DataFrame that indicates the profit or loss for each trade based on the buy and sell signals and the defined stop loss and profit target.\n",
+      "Input: The stop loss and profit target as percentages.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can create a new column in the DataFrame that indicates the profit or loss for each trade based on the buy and sell signals and the defined stop loss and profit target. We need to pass the stop loss and profit target as percentages as arguments to this function. We can use the following code to create the new column:\n",
+      "\n",
+      "```\n",
+      "stop_loss = stop_loss_percent / 100\n",
+      "profit_target = profit_target_percent / 100\n",
+      "\n",
+      "new_df['pnl'] = 0.0\n",
+      "buy_price = 0.0\n",
+      "for i in range(1, len(new_df)):\n",
+      "    if new_df['signal'][i] == 1 and new_df['signal'][i-1] == -1:\n",
+      "        buy_price = new_df['close'][i]\n",
+      "    elif new_df['signal'][i] == -1 and new_df['signal'][i-1] == 1:\n",
+      "        sell_price = new_df['close'][i]\n",
+      "        if sell_price <= buy_price * (1 - stop_loss):\n",
+      "            new_df['pnl'][i] = -stop_loss\n",
+      "        elif sell_price >= buy_price * (1 + profit_target):\n",
+      "            new_df['pnl'][i] = profit_target\n",
+      "        else:\n",
+      "            new_df['pnl'][i] = (sell_price - buy_price) / buy_price\n",
+      "```\n",
+      "\n",
+      "This will create a new column called 'pnl' in the DataFrame that indicates the profit or loss for each trade based on the buy and sell signals and the defined stop loss and profit target. The stop loss and profit target are calculated based on the stop_loss_percent and profit_target_percent variables, respectively. The buy and sell prices are stored in the buy_price and sell_price variables, respectively. If the sell price is less than or equal to the stop loss, the profit or loss is set to -stop_loss. If the sell price is greater than or equal to the profit target, the profit or loss is set to profit_target. Otherwise, the profit or loss is calculated as (sell_price - buy_price) / buy_price. Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Calculate the total profit or loss for all trades.\n",
+      "Input: None.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can calculate the total profit or loss for all trades by summing the values in the 'pnl' column of the DataFrame. We can use the following code to calculate the total profit or loss:\n",
+      "\n",
+      "```\n",
+      "total_pnl = new_df['pnl'].sum()\n",
+      "```\n",
+      "\n",
+      "This will calculate the total profit or loss for all trades and store it in the total_pnl variable. Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Visualize the stock data, short-term moving average, and long-term moving average using a line chart.\n",
+      "Input: None.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can visualize the stock data, short-term moving average, and long-term moving average using a line chart using the `plot()` function from pandas. We can use the following code to visualize the data:\n",
+      "\n",
+      "```\n",
+      "plt.figure(figsize=(12,6))\n",
+      "plt.plot(new_df.index, new_df['close'], label='Close')\n",
+      "plt.plot(new_df.index, new_df['short_ma'], label='Short MA')\n",
+      "plt.plot(new_df.index, new_df['long_ma'], label='Long MA')\n",
+      "plt.xlabel('Date')\n",
+      "plt.ylabel('Price')\n",
+      "plt.title('Stock Data with Moving Averages')\n",
+      "plt.legend()\n",
+      "plt.show()\n",
+      "```\n",
+      "\n",
+      "This will create a line chart that visualizes the stock data, short-term moving average, and long-term moving average. The x-axis represents the date and the y-axis represents the price. The chart also includes a legend that labels each line. Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Visualize the buy and sell signals using a scatter plot.\n",
+      "Input: None.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can visualize the buy and sell signals using a scatter plot using the `scatter()` function from matplotlib. We can use the following code to visualize the signals:\n",
+      "\n",
+      "```\n",
+      "buy_signals = new_df[new_df['signal'] == 1]\n",
+      "sell_signals = new_df[new_df['signal'] == -1]\n",
+      "\n",
+      "plt.figure(figsize=(12,6))\n",
+      "plt.scatter(buy_signals.index, buy_signals['close'], label='Buy', marker='^', color='green')\n",
+      "plt.scatter(sell_signals.index, sell_signals['close'], label='Sell', marker='v', color='red')\n",
+      "plt.plot(new_df.index, new_df['close'], label='Close')\n",
+      "plt.xlabel('Date')\n",
+      "plt.ylabel('Price')\n",
+      "plt.title('Buy and Sell Signals')\n",
+      "plt.legend()\n",
+      "plt.show()\n",
+      "```\n",
+      "\n",
+      "This will create a scatter plot that visualizes the buy and sell signals. The x-axis represents the date and the y-axis represents the price. The chart also includes a legend that labels each point. Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Print the total profit or loss for all trades.\n",
+      "Input: None.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: We can print the total profit or loss for all trades using the `print()` function. We can use the following code to print the total profit or loss:\n",
+      "\n",
+      "```\n",
+      "print('Total Profit/Loss: {:.2%}'.format(total_pnl))\n",
+      "```\n",
+      "\n",
+      "This will print the total profit or loss for all trades in percentage format with two decimal places. Next request.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "Instruction: Finalize the code by putting all the code snippets together in a single Python script.\n",
+      "Input: The necessary inputs for each code snippet.\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Solution: Here is the complete Python script that puts all the code snippets together:\n",
+      "\n",
+      "```\n",
+      "import pandas as pd\n",
+      "import numpy as np\n",
+      "import matplotlib.pyplot as plt\n",
+      "import talib as ta\n",
+      "\n",
+      "# Load historical stock data into a pandas DataFrame\n",
+      "df = pd.read_csv('path/to/csv/file.csv')\n",
+      "\n",
+      "# Preprocess the historical stock data\n",
+      "df = df.set_index('date')\n",
+      "df = df.sort_index(ascending=True)\n",
+      "\n",
+      "# Calculate the short-term and long-term moving averages\n",
+      "short_period = 10\n",
+      "long_period = 30\n",
+      "short_ma = ta.SMA(df['close'], timeperiod=short_period)\n",
+      "long_ma = ta.SMA(df['close'], timeperiod=long_period)\n",
+      "\n",
+      "# Create a new DataFrame that combines the historical stock data with the short-term and long-term moving averages\n",
+      "new_df = pd.concat([df, short_ma, long_ma], axis=1)\n",
+      "new_df.columns = ['open', 'high', 'low', 'close', 'volume', 'short_ma', 'long_ma']\n",
+      "\n",
+      "# Create a new column in the DataFrame that indicates when to buy or sell the stock based on the crossover of the short-term and long-term moving averages\n",
+      "new_df['signal'] = np.where(new_df['short_ma'] > new_df['long_ma'], 1, -1)\n",
+      "\n",
+      "# Create a new column in the DataFrame that indicates the profit or loss for each trade based on the buy and sell signals and the defined stop loss and profit target\n",
+      "stop_loss_percent = 5\n",
+      "profit_target_percent = 10\n",
+      "stop_loss = stop_loss_percent / 100\n",
+      "profit_target = profit_target_percent / 100\n",
+      "new_df['pnl'] = 0.0\n",
+      "buy_price = 0.0\n",
+      "for i in range(1, len(new_df)):\n",
+      "    if new_df['signal'][i] == 1 and new_df['signal'][i-1] == -1:\n",
+      "        buy_price = new_df['close'][i]\n",
+      "    elif new_df['signal'][i] == -1 and new_df['signal'][i-1] == 1:\n",
+      "        sell_price = new_df['close'][i]\n",
+      "        if sell_price <= buy_price * (1 - stop_loss):\n",
+      "            new_df['pnl'][i] = -stop_loss\n",
+      "        elif sell_price >= buy_price * (1 + profit_target):\n",
+      "            new_df['pnl'][i] = profit_target\n",
+      "        else:\n",
+      "            new_df['pnl'][i] = (sell_price - buy_price) / buy_price\n",
+      "\n",
+      "# Calculate the total profit or loss for all trades\n",
+      "total_pnl = new_df['pnl'].sum()\n",
+      "\n",
+      "# Visualize the stock data, short-term moving average, and long-term moving average using a line chart\n",
+      "plt.figure(figsize=(12,6))\n",
+      "plt.plot(new_df.index, new_df['close'], label='Close')\n",
+      "plt.plot(new_df.index, new_df['short_ma'], label='Short MA')\n",
+      "plt.plot(new_df.index, new_df['long_ma'], label='Long MA')\n",
+      "plt.xlabel('Date')\n",
+      "plt.ylabel('Price')\n",
+      "plt.title('Stock Data with Moving Averages')\n",
+      "plt.legend()\n",
+      "plt.show()\n",
+      "\n",
+      "# Visualize the buy and sell signals using a scatter plot\n",
+      "buy_signals = new_df[new_df['signal'] == 1]\n",
+      "sell_signals = new_df[new_df['signal'] == -1]\n",
+      "plt.figure(figsize=(12,6))\n",
+      "plt.scatter(buy_signals.index, buy_signals['close'], label='Buy', marker='^', color='green')\n",
+      "plt.scatter(sell_signals.index, sell_signals['close'], label='Sell', marker='v', color='red')\n",
+      "plt.plot(new_df.index, new_df['close'], label='Close')\n",
+      "plt.xlabel('Date')\n",
+      "plt.ylabel('Price')\n",
+      "plt.title('Buy and Sell Signals')\n",
+      "plt.legend()\n",
+      "plt.show()\n",
+      "\n",
+      "# Print the total profit or loss for all trades\n",
+      "print('Total Profit/Loss: {:.2%}'.format(total_pnl))\n",
+      "```\n",
+      "\n",
+      "You need to replace the path/to/csv/file.csv with the actual path to the CSV file containing the historical stock data. You can also adjust the short_period, long_period, stop_loss_percent, and profit_target_percent variables to suit your needs.\n",
+      "\n",
+      "\n",
+      "AI User (Stock Trader):\n",
+      "\n",
+      "<CAMEL_TASK_DONE>\n",
+      "\n",
+      "\n",
+      "AI Assistant (Python Programmer):\n",
+      "\n",
+      "Great! Let me know if you need any further assistance.\n",
+      "\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(f\"Original task prompt:\\n{task}\\n\")\n",
+    "print(f\"Specified task prompt:\\n{specified_task}\\n\")\n",
+    "\n",
+    "chat_turn_limit, n = 30, 0\n",
+    "while n < chat_turn_limit:\n",
+    "    n += 1\n",
+    "    user_ai_msg = user_agent.step(assistant_msg)\n",
+    "    user_msg = HumanMessage(content=user_ai_msg.content)\n",
+    "    print(f\"AI User ({user_role_name}):\\n\\n{user_msg.content}\\n\\n\")\n",
+    "\n",
+    "    assistant_ai_msg = assistant_agent.step(user_msg)\n",
+    "    assistant_msg = HumanMessage(content=assistant_ai_msg.content)\n",
+    "    print(f\"AI Assistant ({assistant_role_name}):\\n\\n{assistant_msg.content}\\n\\n\")\n",
+    "    if \"<CAMEL_TASK_DONE>\" in user_msg.content:\n",
+    "        break"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "camel",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.9"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}