release(core): 1.0.0a8 (#33341)

Reverts langchain-ai/langchain#33312

.claude/settings.local.json

@@ -0,0 +1,18 @@
+{
+  "permissions": {
+    "allow": [
+      "Bash(uv run:*)",
+      "Bash(make:*)",
+      "WebSearch",
+      "WebFetch(domain:ai.pydantic.dev)",
+      "WebFetch(domain:openai.github.io)",
+      "Bash(uv run:*)",
+      "Bash(python3:*)",
+      "WebFetch(domain:github.com)",
+      "Bash(gh pr view:*)",
+      "Bash(gh pr diff:*)"
+    ],
+    "deny": [],
+    "ask": []
+  }
+}

.devcontainer/README.md

@@ -5,26 +5,31 @@ 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**.
 
 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: 
-```
-https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/<yourusername>/<yourclonedreponame>
+> [!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;
 ```
+
 Then you will have a local cloned repo where you can contribute and then create pull requests.
 
-If you already have VS Code and Docker installed, you can use the button above to get started. This will cause VS Code to automatically install the Dev Containers extension if needed, clone the source code into a container volume, and spin up a dev container for use.
+If you already have VS Code and Docker installed, you can use the button above to get started. This will use VSCode to automatically install the Dev Containers extension if needed, clone the source code into a container volume, and spin up a dev container for use.
 
 Alternatively you can also follow these steps to open this repo in a container using the VS Code Dev Containers extension:
 
@@ -40,5 +45,5 @@ 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

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

.devcontainer/docker-compose.yaml

@@ -4,26 +4,9 @@ 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/langchain:cached
+
     networks:
       - langchain-network
-  #   environment:
-  #     MONGO_ROOT_USERNAME: root
-  #     MONGO_ROOT_PASSWORD: example123
-  #   depends_on:
-  #     - mongo   
-  # mongo:
-  #   image: mongo
-  #   restart: unless-stopped
-  #   environment:
-  #     MONGO_INITDB_ROOT_USERNAME: root
-  #     MONGO_INITDB_ROOT_PASSWORD: example123
-  #   ports:
-  #     - "27017:27017"
-  #   networks:
-  #     - langchain-network
 
 networks:
   langchain-network:

.editorconfig

@@ -0,0 +1,52 @@
+# 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 +1,3 @@
 /.github/   @baskaryan @ccurme @eyurtsev
 /libs/core/ @eyurtsev
-/libs/packages.yml   @ccurme
+/libs/partners/ @ccurme @mdrxy

.github/CODE_OF_CONDUCT.md

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

.github/CONTRIBUTING.md

@@ -3,8 +3,4 @@
 Hi there! Thank you for even being interested in contributing to LangChain.
 As an open-source project in a rapidly developing field, we are extremely open to contributions, whether they involve new features, improved infrastructure, better documentation, or bug fixes.
 
-To learn how to contribute to LangChain, please follow the [contribution guide here](https://python.langchain.com/docs/contributing/).
-
-## New features
-
-For new features, please start a new [discussion](https://forum.langchain.com/), where the maintainers will help with scoping out the necessary changes.
+To learn how to contribute to LangChain, please follow the [contribution guide here](https://docs.langchain.com/oss/python/contributing).

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -1,11 +1,12 @@
 name: "\U0001F41B Bug Report"
 description: Report a bug in LangChain. To report a security issue, please instead use the security option below. For questions, please use the LangChain forum.
 labels: ["bug"]
+type: bug
 body:
   - type: markdown
     attributes:
       value: |
-        Thank you for taking the time to file a bug report. 
+        Thank you for taking the time to file a bug report.
 
         Use this to report BUGS in LangChain. For usage questions, feature requests and general design questions, please use the [LangChain Forum](https://forum.langchain.com/).
 
@@ -13,10 +14,8 @@ body:
         if there's another way to solve your problem:
 
         * [LangChain Forum](https://forum.langchain.com/),
-        * [LangChain Github Issues](https://github.com/langchain-ai/langchain/issues?q=is%3Aissue),
-        * [LangChain documentation with the integrated search](https://python.langchain.com/docs/get_started/introduction),
-        * [LangChain how-to guides](https://python.langchain.com/docs/how_to/),
-        * [API Reference](https://python.langchain.com/api_reference/),
+        * [LangChain documentation with the integrated search](https://docs.langchain.com/oss/python/langchain/overview),
+        * [API Reference](https://reference.langchain.com/python/),
         * [LangChain ChatBot](https://chat.langchain.com/)
         * [GitHub search](https://github.com/langchain-ai/langchain),
   - type: checkboxes
@@ -25,7 +24,7 @@ body:
       label: Checked other resources
       description: Please confirm and check all the following options.
       options:
-        - label: This is a bug, not a usage question. For questions, please use the LangChain Forum (https://forum.langchain.com/).
+        - label: This is a bug, not a usage question.
           required: true
         - label: I added a clear and descriptive title that summarizes this issue.
           required: true
@@ -35,6 +34,8 @@ body:
           required: true
         - label: The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).
           required: true
+        - label: This is not related to the langchain-community package.
+          required: true
         - label: I read what a minimal reproducible example is (https://stackoverflow.com/help/minimal-reproducible-example).
           required: true
         - label: I posted a self-contained, minimal, reproducible example. A maintainer can copy it and run it AS IS.
@@ -50,7 +51,7 @@ body:
 
         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!** 
+        **Important!**
 
         * Avoid screenshots when possible, as they are hard to read and (more importantly) don't allow others to copy-and-paste your code.
         * Reduce your code to the minimum required to reproduce the issue if possible. This makes it much easier for others to help you.
@@ -58,14 +59,14 @@ body:
         * INCLUDE the language label (e.g. `python`) after the first three backticks to enable syntax highlighting. (e.g., ```python rather than ```).
 
       placeholder: |
-        The following code: 
+        The following code:
 
         ```python
         from langchain_core.runnables import RunnableLambda
 
         def bad_code(inputs) -> int:
           raise NotImplementedError('For demo purpose')
-          
+
           chain = RunnableLambda(bad_code)
           chain.invoke('Hello!')
         ```

.github/ISSUE_TEMPLATE/config.yml

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

.github/ISSUE_TEMPLATE/documentation.yml

@@ -1,59 +0,0 @@
-name: Documentation
-description: Report an issue related to the LangChain documentation.
-title: "docs: <Please write a comprehensive title after the 'docs: ' prefix>"
-labels: [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 the [LangChain Forum](https://forum.langchain.com/).
-
-        If you're in the wrong place, here are some helpful links to find a better
-        place to ask your question:
-
-        * [LangChain Forum](https://forum.langchain.com/),
-        * [LangChain Github Issues](https://github.com/langchain-ai/langchain/issues?q=is%3Aissue),
-        * [LangChain documentation with the integrated search](https://python.langchain.com/docs/get_started/introduction),
-        * [LangChain how-to guides](https://python.langchain.com/docs/how_to/),
-        * [API Reference](https://python.langchain.com/api_reference/),
-        * [LangChain ChatBot](https://chat.langchain.com/)
-        * [GitHub search](https://github.com/langchain-ai/langchain),
-  - type: input
-    id: url
-    attributes:
-      label: URL
-      description: URL to documentation
-    validations:
-      required: false
-  - 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

@@ -0,0 +1,118 @@
+name: "✨ Feature Request"
+description: Request a new feature or enhancement for LangChain. For questions, please use the LangChain forum.
+labels: ["feature request"]
+type: feature
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thank you for taking the time to request a new feature.
+
+        Use this to request NEW FEATURES or ENHANCEMENTS in LangChain. For bug reports, please use the bug report template. For usage questions and general design questions, please use the [LangChain Forum](https://forum.langchain.com/).
+
+        Relevant links to check before filing a feature request to see if your request has already been made or
+        if there's another way to achieve what you want:
+
+        * [LangChain Forum](https://forum.langchain.com/),
+        * [LangChain documentation with the integrated search](https://docs.langchain.com/oss/python/langchain/overview),
+        * [API Reference](https://reference.langchain.com/python/),
+        * [LangChain ChatBot](https://chat.langchain.com/)
+        * [GitHub search](https://github.com/langchain-ai/langchain),
+  - type: checkboxes
+    id: checks
+    attributes:
+      label: Checked other resources
+      description: Please confirm and check all the following options.
+      options:
+        - label: This is a feature request, not a bug report or usage question.
+          required: true
+        - label: I added a clear and descriptive title that summarizes the feature request.
+          required: true
+        - label: I used the GitHub search to find a similar feature request and didn't find it.
+          required: true
+        - label: I checked the LangChain documentation and API reference to see if this feature already exists.
+          required: true
+        - label: This is not related to the langchain-community package.
+          required: true
+  - type: textarea
+    id: feature-description
+    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

@@ -4,12 +4,7 @@ body:
   - type: markdown
     attributes:
       value: |
-        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 on the [LangChain Forum](https://forum.langchain.com/) 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.
+        If you are not a LangChain maintainer, employee, or were not asked directly by a maintainer to create an issue, then please start the conversation on the [LangChain Forum](https://forum.langchain.com/) instead.
   - type: checkboxes
     id: privileged
     attributes:

.github/ISSUE_TEMPLATE/task.yml

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

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,3 +1,5 @@
+(Replace this entire block of text)
+
 Thank you for contributing to LangChain! Follow these steps to mark your pull request as ready for review. **If any of these steps are not completed, your PR will not be considered for review.**
 
 - [ ] **PR title**: Follows the format: {TYPE}({SCOPE}): {DESCRIPTION}
@@ -8,25 +10,19 @@ Thank you for contributing to LangChain! Follow these steps to mark your pull re
   - Allowed `{TYPE}` values:
     - feat, fix, docs, style, refactor, perf, test, build, ci, chore, revert, release
   - Allowed `{SCOPE}` values (optional):
-    - core, cli, langchain, standard-tests, docs, anthropic, chroma, deepseek, exa, fireworks, groq, huggingface, mistralai, nomic, ollama, openai, perplexity, prompty, qdrant, xai
-  - Note: the `{DESCRIPTION}` must not start with an uppercase letter.
+    - core, cli, langchain, standard-tests, text-splitters, docs, anthropic, chroma, deepseek, exa, fireworks, groq, huggingface, mistralai, nomic, ollama, openai, perplexity, prompty, qdrant, xai, infra
   - Once you've written the title, please delete this checklist item; do not include it in the PR.
 
 - [ ] **PR message**: ***Delete this entire checklist*** and replace with
   - **Description:** a description of the change. Include a [closing keyword](https://docs.github.com/en/issues/tracking-your-work-with-issues/using-issues/linking-a-pull-request-to-an-issue#linking-a-pull-request-to-an-issue-using-a-keyword) if applicable to a relevant issue.
   - **Issue:** the issue # it fixes, if applicable (e.g. Fixes #123)
   - **Dependencies:** any dependencies required for this change
-  - **Twitter handle:** if your PR gets announced, and you'd like a mention, we'll gladly shout you out!
 
-- [ ] **Add tests and docs**: If you're adding a new integration, you must include:
-  1. A test for the integration, preferably unit tests that do not rely on network access,
-  2. An example notebook showing its use. It lives in `docs/docs/integrations` directory.
-
-- [ ] **Lint and test**: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. **We will not consider a PR unless these three are passing in CI.** See [contribution guidelines](https://python.langchain.com/docs/contributing/) for more.
+- [ ] **Lint and test**: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. **We will not consider a PR unless these three are passing in CI.** See [contribution guidelines](https://docs.langchain.com/oss/python/contributing) for more.
 
 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.
+- Please do not add dependencies to `pyproject.toml` files (even optional ones) unless they are **required** for unit tests. Likewise, please do not update the `uv.lock` files unless you are adding a required dependency.
 - Changes should be backwards compatible.
+- Make sure optional dependencies are imported within a function.

.github/actions/people/Dockerfile

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

.github/actions/people/action.yml

@@ -1,11 +0,0 @@
-# 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

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

.github/actions/uv_setup/action.yml

@@ -1,12 +1,24 @@
-# TODO: https://docs.astral.sh/uv/guides/integration/github/#caching
+# Helper to set up Python and uv with caching
 
 name: uv-install
-description: Set up Python and uv
+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"
@@ -15,7 +27,13 @@ runs:
   using: composite
   steps:
     - name: Install uv and set the python version
-      uses: astral-sh/setup-uv@v5
+      uses: astral-sh/setup-uv@v6
       with:
         version: ${{ env.UV_VERSION }}
         python-version: ${{ inputs.python-version }}
+        enable-cache: ${{ inputs.enable-cache }}
+        cache-dependency-glob: |
+          ${{ inputs.working-directory }}/pyproject.toml
+          ${{ inputs.working-directory }}/uv.lock
+          ${{ inputs.working-directory }}/requirements*.txt
+        cache-suffix: ${{ inputs.cache-suffix }}

.github/copilot-instructions.md

@@ -1,72 +1,116 @@
-### 1. Avoid Breaking Changes (Stable Public Interfaces)
+# Global Development Guidelines for LangChain Projects
 
-* Carefully preserve **function signatures**, argument positions, and names for any exported/public methods.
-* Be cautious when **renaming**, **removing**, or **reordering** arguments — even small changes can break downstream consumers.
-* Use keyword-only arguments or clearly mark experimental features to isolate unstable APIs.
+## Core Development Principles
 
-Bad:
+### 1. Maintain Stable Public Interfaces ⚠️ CRITICAL
+
+**Always attempt to preserve function signatures, argument positions, and names for exported/public methods.**
+
+❌ **Bad - Breaking Change:**
 
 ```python
 def get_user(id, verbose=False):  # Changed from `user_id`
+    pass
 ```
 
-Good:
+✅ **Good - Stable Interface:**
 
 ```python
-def get_user(user_id: str, verbose: bool = False):  # Maintains stable interface
+def get_user(user_id: str, verbose: bool = False) -> User:
+    """Retrieve user by ID with optional verbose output."""
+    pass
 ```
 
-🧠 *Ask yourself:* “Would this change break someone's code if they used it last week?”
+**Before making ANY changes to public APIs:**
 
----
+- Check if the function/class is exported in `__init__.py`
+- Look for existing usage patterns in tests and examples
+- Use keyword-only arguments for new parameters: `*, new_param: str = "default"`
+- Mark experimental features clearly with docstring admonitions (using MkDocs Material, like `!!! warning`)
 
-### 2. Simplify Code and Use Clear Variable Names
+🧠 *Ask yourself:* "Would this change break someone's code if they used it last week?"
 
-* Prefer descriptive, **self-explanatory variable names**. Avoid overly short or cryptic identifiers.
-* Break up overly long or deeply nested functions for **readability and maintainability**.
-* Avoid unnecessary abstraction or premature optimization.
-* All generated Python code must include type hints and return types.
+### 2. Code Quality Standards
 
-Bad:
+**All Python code MUST include type hints and return types.**
+
+❌ **Bad:**
 
 ```python
 def p(u, d):
     return [x for x in u if x not in d]
 ```
 
-Good:
+✅ **Good:**
 
 ```python
-def filter_unknown_users(users: List[str], known_users: Set[str]) -> List[str]:
+def filter_unknown_users(users: list[str], known_users: set[str]) -> list[str]:
+    """Filter out users that are not in the known users set.
+
+    Args:
+        users: List of user identifiers to filter.
+        known_users: Set of known/valid user identifiers.
+
+    Returns:
+        List of users that are not in the known_users set.
+    """
     return [user for user in users if user not in known_users]
 ```
 
----
+**Style Requirements:**
 
-### 3. Ensure Unit Tests Cover New and Updated Functionality
+- Use descriptive, **self-explanatory variable names**. Avoid overly short or cryptic identifiers.
+- Attempt to break up complex functions (>20 lines) into smaller, focused functions where it makes sense
+- Avoid unnecessary abstraction or premature optimization
+- Follow existing patterns in the codebase you're modifying
 
-* Every new feature or bugfix should be **covered by a unit test**.
-* Test edge cases and failure conditions.
-* Use `pytest`, `unittest`, or the project’s existing framework consistently.
+### 3. Testing Requirements
 
-Checklist:
+**Every new feature or bugfix MUST be covered by unit tests.**
 
-* [ ] Does the test suite fail if your new logic is broken?
-* [ ] Are all expected behaviors exercised (happy path, invalid input, etc)?
-* [ ] Do tests use fixtures or mocks where needed?
+**Test Organization:**
 
----
+- Unit tests: `tests/unit_tests/` (no network calls allowed)
+- Integration tests: `tests/integration_tests/` (network calls permitted)
+- Use `pytest` as the testing framework
 
-### 4. Look for Suspicious or Risky Code
+**Test Quality Checklist:**
 
-* Watch out for:
+- [ ] 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)
 
-  * Use of `eval()`, `exec()`, or `pickle` on user-controlled input.
-  * Silent failure modes (`except: pass`).
-  * Unreachable code or commented-out blocks.
-  * Race conditions or resource leaks (file handles, sockets, threads).
+Checklist questions:
 
-Bad:
+- [ ] Does the test suite fail if your new logic is broken?
+- [ ] Are all expected behaviors exercised (happy path, invalid input, etc)?
+- [ ] Do tests use fixtures or mocks where needed?
+
+```python
+def test_filter_unknown_users():
+    """Test filtering unknown users from a list."""
+    users = ["alice", "bob", "charlie"]
+    known_users = {"alice", "bob"}
+
+    result = filter_unknown_users(users, known_users)
+
+    assert result == ["charlie"]
+    assert len(result) == 1
+```
+
+### 4. Security and Risk Assessment
+
+**Security Checklist:**
+
+- No `eval()`, `exec()`, or `pickle` on user-controlled input
+- Proper exception handling (no bare `except:`) and use a `msg` variable for error messages
+- Remove unreachable/commented code before committing
+- Race conditions or resource leaks (file handles, sockets, threads).
+- Ensure proper resource cleanup (file handles, connections)
+
+❌ **Bad:**
 
 ```python
 def load_config(path):
@@ -74,7 +118,7 @@ def load_config(path):
         return eval(f.read())  # ⚠️ Never eval config
 ```
 
-Good:
+✅ **Good:**
 
 ```python
 import json
@@ -84,68 +128,203 @@ def load_config(path: str) -> dict:
         return json.load(f)
 ```
 
----
+### 5. Documentation Standards
 
-### 5. Use Google-Style Docstrings (with Args section)
+**Use Google-style docstrings with Args and Returns sections for all public functions.**
 
-* All public functions should include a **Google-style docstring**.
-* Include an `Args:` section where relevant.
-* Types should NOT be written in the docstring — use type hints instead.
-
-Bad:
+❌ **Insufficient Documentation:**
 
 ```python
 def send_email(to, msg):
     """Send an email to a recipient."""
 ```
 
-Good:
+✅ **Complete Documentation:**
 
 ```python
-def send_email(to: str, msg: str) -> None:
+def send_email(to: str, msg: str, *, priority: str = "normal") -> bool:
     """
-    Sends an email to a recipient.
+    Send an email to a recipient with specified priority.
 
     Args:
         to: The email address of the recipient.
-        msg: The message body.
+        msg: The message body to send.
+        priority: Email priority level.
+
+    Returns:
+        True if email was sent successfully, False otherwise.
+
+    Raises:
+        InvalidEmailError: If the email address format is invalid.
+        SMTPConnectionError: If unable to connect to email server.
     """
 ```
 
+**Documentation Guidelines:**
+
+- Types go in function signatures, NOT in docstrings
+- Focus on "why" rather than "what" in descriptions
+- Document all parameters, return values, and exceptions
+- Keep descriptions concise but clear
+
 📌 *Tip:* Keep descriptions concise but clear. Only document return values if non-obvious.
 
+### 6. Architectural Improvements
+
+**When you encounter code that could be improved, suggest better designs:**
+
+❌ **Poor Design:**
+
+```python
+def process_data(data, db_conn, email_client, logger):
+    # Function doing too many things
+    validated = validate_data(data)
+    result = db_conn.save(validated)
+    email_client.send_notification(result)
+    logger.log(f"Processed {len(data)} items")
+    return result
+```
+
+✅ **Better Design:**
+
+```python
+@dataclass
+class ProcessingResult:
+    """Result of data processing operation."""
+    items_processed: int
+    success: bool
+    errors: List[str] = field(default_factory=list)
+
+class DataProcessor:
+    """Handles data validation, storage, and notification."""
+
+    def __init__(self, db_conn: Database, email_client: EmailClient):
+        self.db = db_conn
+        self.email = email_client
+
+    def process(self, data: List[dict]) -> ProcessingResult:
+        """Process and store data with notifications.
+
+        Args:
+            data: List of data items to process.
+
+        Returns:
+            ProcessingResult with details of the operation.
+        """
+        validated = self._validate_data(data)
+        result = self.db.save(validated)
+        self._notify_completion(result)
+        return result
+```
+
+**Design Improvement Areas:**
+
+If there's a **cleaner**, **more scalable**, or **simpler** design, highlight it and suggest improvements that would:
+
+- Reduce code duplication through shared utilities
+- Make unit testing easier
+- Improve separation of concerns (single responsibility)
+- Make unit testing easier through dependency injection
+- Add clarity without adding complexity
+- Prefer dataclasses for structured data
+
+## Development Tools & Commands
+
+### Package Management
+
+```bash
+# Add package
+uv add package-name
+
+# Sync project dependencies
+uv sync
+uv lock
+```
+
+### Testing
+
+```bash
+# Run unit tests (no network)
+make test
+
+# Don't run integration tests, as API keys must be set
+
+# Run specific test file
+uv run --group test pytest tests/unit_tests/test_specific.py
+```
+
+### Code Quality
+
+```bash
+# Lint code
+make lint
+
+# Format code
+make format
+
+# Type checking
+uv run --group lint mypy .
+```
+
+### Dependency Management Patterns
+
+**Local Development Dependencies:**
+
+```toml
+[tool.uv.sources]
+langchain-core = { path = "../core", editable = true }
+langchain-tests = { path = "../standard-tests", editable = true }
+```
+
+**For tools, use the `@tool` decorator from `langchain_core.tools`:**
+
+```python
+from langchain_core.tools import tool
+
+@tool
+def search_database(query: str) -> str:
+    """Search the database for relevant information.
+
+    Args:
+        query: The search query string.
+    """
+    # Implementation here
+    return results
+```
+
+## Commit Standards
+
+**Use Conventional Commits format for PR titles:**
+
+- `feat(core): add multi-tenant support`
+- `!fix(cli): resolve flag parsing error` (breaking change uses exclamation mark)
+- `docs: update API usage examples`
+- `docs(openai): update API usage examples`
+
+## Framework-Specific Guidelines
+
+- Follow the existing patterns in `langchain_core` for base abstractions
+- Implement proper streaming support where applicable
+- Avoid deprecated components
+
+### Partner Integrations
+
+- Follow the established patterns in existing partner libraries
+- Implement standard interfaces (`BaseChatModel`, `BaseEmbeddings`, etc.)
+- Include comprehensive integration tests
+- Document API key requirements and authentication
+
 ---
 
-### 6. Propose Better Designs When Applicable
+## Quick Reference Checklist
 
-* If there's a **cleaner**, **more scalable**, or **simpler** design, highlight it.
-* Suggest improvements, even if they require some refactoring — especially if the new code would:
+Before submitting code changes:
 
-  * Reduce duplication
-  * Make unit testing easier
-  * Improve separation of concerns
-  * Add clarity without adding complexity
-
-Instead of:
-
-```python
-def save(data, db_conn):
-    # manually serializes fields
-```
-
-You might suggest:
-
-```python
-# Suggest using dataclasses or Pydantic for automatic serialization and validation
-```
-
-### 7. Misc
-
-* When suggesting package installation commands, use `uv pip install` as this project uses `uv`.
-* When creating tools for agents, use the @tool decorator from langchain_core.tools. The tool's docstring serves as its functional description for the agent.
-* Avoid suggesting deprecated components, such as the legacy LLMChain.
-* We use Conventional Commits format for pull request titles. Example PR titles:
-    * feat(core): add multi‐tenant support
-    * fix(cli): resolve flag parsing error
-    * docs: update API usage examples
-    * docs(openai): update API usage examples
+- [ ] **Breaking Changes**: Verified no public API changes
+- [ ] **Type Hints**: All functions have complete type annotations
+- [ ] **Tests**: New functionality is fully tested
+- [ ] **Security**: No dangerous patterns (eval, silent failures, etc.)
+- [ ] **Documentation**: Google-style docstrings for public functions
+- [ ] **Code Quality**: `make lint` and `make format` pass
+- [ ] **Architecture**: Suggested improvements where applicable
+- [ ] **Commit Message**: Follows Conventional Commits format

.github/pr-file-labeler.yml

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

.github/pr-title-labeler.yml

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

.github/scripts/check_diff.py

@@ -1,24 +1,38 @@
+"""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 typing import Dict, List, Set
 from pathlib import Path
+from typing import Dict, List, Set
+
 import tomllib
-
-from packaging.requirements import Requirement
-
 from get_min_versions import get_min_version_from_toml
-
+from packaging.requirements import Requirement
 
 LANGCHAIN_DIRS = [
     "libs/core",
     "libs/text-splitters",
     "libs/langchain",
+    "libs/langchain_v1",
 ]
 
-# when set to True, we are ignoring core dependents
+# 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
@@ -36,10 +50,6 @@ IGNORED_PARTNERS = [
     "prompty",
 ]
 
-PY_312_MAX_PACKAGES = [
-    "libs/partners/chroma", # https://github.com/chroma-core/chroma/issues/4382
-]
-
 
 def all_package_dirs() -> Set[str]:
     return {
@@ -50,9 +60,9 @@ def all_package_dirs() -> Set[str]:
 
 
 def dependents_graph() -> dict:
-    """
-    Construct a mapping of package -> dependents, such that we can
-    run tests on all dependents of a package when a change is made.
+    """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)
 
@@ -84,9 +94,9 @@ def dependents_graph() -> dict:
                 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"
+                        assert depline.startswith("-e ../partners/"), (
+                            "Extended test deps should only editable install partner packages"
+                        )
                         partner = depline.split("partners/")[1]
                         dep = f"langchain-{partner}"
                     else:
@@ -122,23 +132,21 @@ def _get_configs_for_single_dir(job: str, dir_: str) -> List[Dict[str, str]]:
     if job == "codspeed":
         py_versions = ["3.12"]  # 3.13 is not yet supported
     elif dir_ == "libs/core":
-        py_versions = ["3.9", "3.10", "3.11", "3.12", "3.13"]
+        py_versions = ["3.10", "3.11", "3.12", "3.13"]
     # custom logic for specific directories
-    elif dir_ == "libs/partners/milvus":
-        # milvus doesn't allow 3.12 because they declare deps in funny way
-        py_versions = ["3.9", "3.11"]
-
-    elif dir_ in PY_312_MAX_PACKAGES:
-        py_versions = ["3.9", "3.12"]
 
     elif dir_ == "libs/langchain" and job == "extended-tests":
-        py_versions = ["3.9", "3.13"]
+        py_versions = ["3.10", "3.13"]
+    elif dir_ == "libs/langchain_v1":
+        py_versions = ["3.10", "3.13"]
+    elif dir_ in {"libs/cli"}:
+        py_versions = ["3.10", "3.13"]
 
     elif dir_ == ".":
         # unable to install with 3.13 because tokenizers doesn't support 3.13 yet
-        py_versions = ["3.9", "3.12"]
+        py_versions = ["3.10", "3.12"]
     else:
-        py_versions = ["3.9", "3.13"]
+        py_versions = ["3.10", "3.13"]
 
     return [{"working-directory": dir_, "python-version": py_v} for py_v in py_versions]
 
@@ -249,12 +257,19 @@ if __name__ == "__main__":
                 ".github/scripts/check_diff.py",
             )
         ):
-            # add all LANGCHAIN_DIRS for infra changes
+            # Infrastructure changes (workflows, actions, CI scripts) trigger tests on
+            # all core packages as a safety measure. This ensures that changes to CI/CD
+            # infrastructure don't inadvertently break package testing, even if the change
+            # appears unrelated (e.g., documentation build workflows). This is intentionally
+            # conservative to catch unexpected side effects from workflow modifications.
+            #
+            # Example: A PR modifying .github/workflows/api_doc_build.yml will trigger
+            # lint/test jobs for libs/core, libs/text-splitters, libs/langchain, and
+            # libs/langchain_v1, even though the workflow may only affect documentation.
             dirs_to_run["extended-test"].update(LANGCHAIN_DIRS)
-            dirs_to_run["lint"].add(".")
 
         if file.startswith("libs/core"):
-            dirs_to_run["codspeed"].add(f"libs/core")
+            dirs_to_run["codspeed"].add("libs/core")
         if any(file.startswith(dir_) for dir_ in LANGCHAIN_DIRS):
             # add that dir and all dirs after in LANGCHAIN_DIRS
             # for extended testing
@@ -270,11 +285,9 @@ if __name__ == "__main__":
                     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["lint"].add("libs/cli")
-            dirs_to_run["test"].add("libs/cli")
             dirs_to_run["test"].add("libs/partners/mistralai")
             dirs_to_run["test"].add("libs/partners/openai")
             dirs_to_run["test"].add("libs/partners/anthropic")
@@ -284,7 +297,7 @@ if __name__ == "__main__":
         elif file.startswith("libs/cli"):
             dirs_to_run["lint"].add("libs/cli")
             dirs_to_run["test"].add("libs/cli")
-            
+
         elif file.startswith("libs/partners"):
             partner_dir = file.split("/")[2]
             if os.path.isdir(f"libs/partners/{partner_dir}") and [
@@ -295,16 +308,21 @@ if __name__ == "__main__":
                 dirs_to_run["test"].add(f"libs/partners/{partner_dir}")
                 dirs_to_run["codspeed"].add(f"libs/partners/{partner_dir}")
             # Skip if the directory was deleted or is just a tombstone readme
-        elif file == "libs/packages.yml":
-            continue
         elif file.startswith("libs/"):
+            # 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.startswith("docs/") or file in ["pyproject.toml", "uv.lock"]: # docs or root uv files
+        elif file in [
+            "pyproject.toml",
+            "uv.lock",
+        ]:  # root uv files
             docs_edited = True
-            dirs_to_run["lint"].add(".")
 
     dependents = dependents_graph()
 
@@ -322,9 +340,6 @@ if __name__ == "__main__":
             "codspeed",
         ]
     }
-    map_job_to_configs["test-doc-imports"] = (
-        [{"python-version": "3.12"}] if docs_edited else []
-    )
 
     for key, value in map_job_to_configs.items():
         json_output = json.dumps(value)

.github/scripts/check_prerelease_dependencies.py

@@ -1,19 +1,21 @@
+"""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]
 
-    # read toml file
     with open(toml_file, "rb") as file:
         toml_data = tomllib.load(file)
 
-    # see if we're releasing an rc
+    # 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, iterate through dependencies and make sure none allow prereleases
     if not releasing_rc:
         dependencies = toml_data["project"]["dependencies"]
         for dep_version in dependencies:

.github/scripts/get_min_versions.py

@@ -1,24 +1,22 @@
-from collections import defaultdict
+"""Get minimum versions of dependencies from a pyproject.toml file."""
+
 import sys
+from collections import defaultdict
 from typing import Optional
 
 if sys.version_info >= (3, 11):
     import tomllib
 else:
-    # for python 3.10 and below, which doesnt have stdlib tomllib
+    # For Python 3.10 and below, which doesnt have stdlib tomllib
     import tomli as tomllib
 
-from packaging.requirements import Requirement
-from packaging.specifiers import SpecifierSet
-from packaging.version import Version
-
-
-import requests
-from packaging.version import parse
+import re
 from typing import List
 
-import re
-
+import requests
+from packaging.requirements import Requirement
+from packaging.specifiers import SpecifierSet
+from packaging.version import Version, parse
 
 MIN_VERSION_LIBS = [
     "langchain-core",
@@ -38,14 +36,13 @@ SKIP_IF_PULL_REQUEST = [
 
 
 def get_pypi_versions(package_name: str) -> List[str]:
-    """
-    Fetch all available versions for a package from PyPI.
+    """Fetch all available versions for a package from PyPI.
 
     Args:
-        package_name (str): Name of the package
+        package_name: Name of the package
 
     Returns:
-        List[str]: List of all available versions
+        List of all available versions
 
     Raises:
         requests.exceptions.RequestException: If PyPI API request fails
@@ -58,25 +55,26 @@ def get_pypi_versions(package_name: str) -> List[str]:
 
 
 def get_minimum_version(package_name: str, spec_string: str) -> Optional[str]:
-    """
-    Find the minimum published version that satisfies the given constraints.
+    """Find the minimum published version that satisfies the given constraints.
 
     Args:
-        package_name (str): Name of the package
-        spec_string (str): Version specification string (e.g., ">=0.2.43,<0.4.0,!=0.3.0")
+        package_name: Name of the package
+        spec_string: Version specification string (e.g., ">=0.2.43,<0.4.0,!=0.3.0")
 
     Returns:
-        Optional[str]: Minimum compatible version or None if no compatible version found
+        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)
+    # 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)
+    # 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)
+        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
+            rf"\^{x}\.(\d+)\.(\d+)", rf">={x}.\1.\2,<{x + 1}", spec_string
         )
 
     spec_set = SpecifierSet(spec_string)
@@ -156,25 +154,28 @@ def get_min_version_from_toml(
 
 
 def check_python_version(version_string, constraint_string):
-    """
-    Check if the given Python version matches the given constraints.
+    """Check if the given Python version matches the given constraints.
 
-    :param version_string: A string representing the Python version (e.g. "3.8.5").
-    :param constraint_string: A string representing the package's Python version constraints (e.g. ">=3.6, <4.0").
-    :return: True if the version matches the constraints, False otherwise.
+    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)
+    # 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)
+    # 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
+            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)
+    # 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
+            rf"\^{x}\.0\.(\d+)", rf">={x}.0.\1,<{x + 1}.0.0", constraint_string
         )
 
     try:

.github/scripts/prep_api_docs_build.py

@@ -1,101 +0,0 @@
-#!/usr/bin/env python
-"""Script to sync libraries from various repositories into the main langchain repository."""
-
-import os
-import shutil
-import yaml
-from pathlib import Path
-from typing import Dict, Any
-
-
-def load_packages_yaml() -> Dict[str, Any]:
-    """Load and parse the packages.yml file."""
-    with open("langchain/libs/packages.yml", "r") as f:
-        return yaml.safe_load(f)
-
-
-def get_target_dir(package_name: str) -> Path:
-    """Get the target directory for a given package."""
-    package_name_short = package_name.replace("langchain-", "")
-    base_path = Path("langchain/libs")
-    if package_name_short == "experimental":
-        return base_path / "experimental"
-    if package_name_short == "community":
-        return base_path / "community"
-    return base_path / "partners" / package_name_short
-
-
-def clean_target_directories(packages: list) -> None:
-    """Remove old directories that will be replaced."""
-    for package in packages:
-
-        target_dir = get_target_dir(package["name"])
-        if target_dir.exists():
-            print(f"Removing {target_dir}")
-            shutil.rmtree(target_dir)
-
-
-def move_libraries(packages: list) -> None:
-    """Move libraries from their source locations to the target directories."""
-    for package in packages:
-
-        repo_name = package["repo"].split("/")[1]
-        source_path = package["path"]
-        target_dir = get_target_dir(package["name"])
-
-        # Handle root path case
-        if source_path == ".":
-            source_dir = repo_name
-        else:
-            source_dir = f"{repo_name}/{source_path}"
-
-        print(f"Moving {source_dir} to {target_dir}")
-
-        # Ensure target directory exists
-        os.makedirs(os.path.dirname(target_dir), exist_ok=True)
-
-        try:
-            # Move the directory
-            shutil.move(source_dir, target_dir)
-        except Exception as e:
-            print(f"Error moving {source_dir} to {target_dir}: {e}")
-
-
-def main():
-    """Main function to orchestrate the library sync process."""
-    try:
-        # Load packages configuration
-        package_yaml = load_packages_yaml()
-
-        # Clean target directories
-        clean_target_directories([
-            p
-            for p in package_yaml["packages"]
-            if (p["repo"].startswith("langchain-ai/") or p.get("include_in_api_ref"))
-            and p["repo"] != "langchain-ai/langchain"
-        ])
-
-        # Move libraries to their new locations
-        move_libraries([
-            p
-            for p in package_yaml["packages"]
-            if not p.get("disabled", False)
-            and (p["repo"].startswith("langchain-ai/") or p.get("include_in_api_ref"))
-            and p["repo"] != "langchain-ai/langchain"
-        ])
-
-        # Delete ones without a pyproject.toml
-        for partner in Path("langchain/libs/partners").iterdir():
-            if partner.is_dir() and not (partner / "pyproject.toml").exists():
-                print(f"Removing {partner} as it does not have a pyproject.toml")
-                shutil.rmtree(partner)
-
-        print("Library sync completed successfully!")
-
-    except Exception as e:
-        print(f"Error during library sync: {e}")
-        raise
-
-
-if __name__ == "__main__":
-    main()

.github/tools/git-restore-mtime

@@ -81,56 +81,93 @@ 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.
@@ -138,71 +175,130 @@ 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:
@@ -212,17 +308,18 @@ 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
@@ -255,11 +352,13 @@ 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)
@@ -282,12 +381,12 @@ 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):
@@ -305,35 +404,49 @@ 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:
@@ -345,18 +458,22 @@ 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:
@@ -379,30 +496,26 @@ 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)
@@ -411,7 +524,7 @@ 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
@@ -419,56 +532,76 @@ 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?
@@ -499,13 +632,16 @@ 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
@@ -519,15 +655,17 @@ 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
@@ -544,10 +682,18 @@ 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:
@@ -556,29 +702,33 @@ 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/.codespell-exclude

@@ -1,6 +0,0 @@
-"NotIn": "not in",
-- `/checkin`: Check-in
-docs/docs/integrations/providers/trulens.mdx
-self.assertIn(
-from trulens_eval import Tru
-tru = Tru()

.github/workflows/_compile_integration_test.yml

@@ -1,4 +1,12 @@
-name: compile-integration-test
+# 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"
 
 on:
   workflow_call:
@@ -25,24 +33,26 @@ jobs:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
     timeout-minutes: 20
-    name: "uv run pytest -m compile tests/integration_tests #${{ inputs.python-version }}"
+    name: "Python ${{ inputs.python-version }}"
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
 
-      - name: Set up Python ${{ inputs.python-version }} + uv
+      - name: "🐍 Set up Python ${{ inputs.python-version }} + UV"
         uses: "./.github/actions/uv_setup"
         with:
           python-version: ${{ inputs.python-version }}
+          cache-suffix: compile-integration-tests-${{ inputs.working-directory }}
+          working-directory: ${{ inputs.working-directory }}
 
-      - name: Install integration dependencies
+      - name: "📦 Install Integration Dependencies"
         shell: bash
         run: uv sync --group test --group test_integration
 
-      - name: Check integration tests compile
+      - name: "🔗 Check Integration Tests Compile"
         shell: bash
         run: uv run pytest -m compile tests/integration_tests
 
-      - name: Ensure the tests did not create any additional files
+      - name: "🧹 Verify Clean Working Directory"
         shell: bash
         run: |
           set -eu

.github/workflows/_integration_test.yml

@@ -1,92 +0,0 @@
-name: Integration Tests
-
-on:
-  workflow_dispatch:
-    inputs:
-      working-directory:
-        required: true
-        type: string
-        description: "From which folder this pipeline executes"
-      python-version:
-        required: true
-        type: string
-        description: "Python version to use"
-
-permissions:
-  contents: read
-
-env:
-  UV_FROZEN: "true"
-
-jobs:
-  build:
-    defaults:
-      run:
-        working-directory: ${{ inputs.working-directory }}
-    runs-on: ubuntu-latest
-    name: Python ${{ inputs.python-version }}
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Set up Python ${{ inputs.python-version }} + uv
-        uses: "./.github/actions/uv_setup"
-        with:
-          python-version: ${{ inputs.python-version }}
-
-      - name: Install dependencies
-        shell: bash
-        run: uv sync --group test --group test_integration
-
-      - name: Run integration tests
-        shell: bash
-        env:
-          AI21_API_KEY: ${{ secrets.AI21_API_KEY }}
-          FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
-          GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
-          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
-          ANTHROPIC_FILES_API_IMAGE_ID: ${{ secrets.ANTHROPIC_FILES_API_IMAGE_ID }}
-          ANTHROPIC_FILES_API_PDF_ID: ${{ secrets.ANTHROPIC_FILES_API_PDF_ID }}
-          AZURE_OPENAI_API_VERSION: ${{ secrets.AZURE_OPENAI_API_VERSION }}
-          AZURE_OPENAI_API_BASE: ${{ secrets.AZURE_OPENAI_API_BASE }}
-          AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
-          AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_CHAT_DEPLOYMENT_NAME }}
-          AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME }}
-          AZURE_OPENAI_LLM_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LLM_DEPLOYMENT_NAME }}
-          AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME }}
-          MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
-          TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
-          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
-          NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}
-          GOOGLE_SEARCH_API_KEY: ${{ secrets.GOOGLE_SEARCH_API_KEY }}
-          GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
-          HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
-          EXA_API_KEY: ${{ secrets.EXA_API_KEY }}
-          NOMIC_API_KEY: ${{ secrets.NOMIC_API_KEY }}
-          WATSONX_APIKEY: ${{ secrets.WATSONX_APIKEY }}
-          WATSONX_PROJECT_ID: ${{ secrets.WATSONX_PROJECT_ID }}
-          ASTRA_DB_API_ENDPOINT: ${{ secrets.ASTRA_DB_API_ENDPOINT }}
-          ASTRA_DB_APPLICATION_TOKEN: ${{ secrets.ASTRA_DB_APPLICATION_TOKEN }}
-          ASTRA_DB_KEYSPACE: ${{ secrets.ASTRA_DB_KEYSPACE }}
-          ES_URL: ${{ secrets.ES_URL }}
-          ES_CLOUD_ID: ${{ secrets.ES_CLOUD_ID }}
-          ES_API_KEY: ${{ secrets.ES_API_KEY }}
-          MONGODB_ATLAS_URI: ${{ secrets.MONGODB_ATLAS_URI }}
-          COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
-          UPSTAGE_API_KEY: ${{ secrets.UPSTAGE_API_KEY }}
-          XAI_API_KEY: ${{ secrets.XAI_API_KEY }}
-          PPLX_API_KEY: ${{ secrets.PPLX_API_KEY }}
-        run: |
-          make integration_tests
-
-      - name: Ensure the tests did not create any additional files
-        shell: bash
-        run: |
-          set -eu
-
-          STATUS="$(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

@@ -1,4 +1,11 @@
-name: lint
+# 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"
 
 on:
   workflow_call:
@@ -24,56 +31,45 @@ env:
   UV_FROZEN: "true"
 
 jobs:
+  # Linting job - runs quality checks on package and test code
   build:
-    name: "make lint #${{ inputs.python-version }}"
+    name: "Python ${{ inputs.python-version }}"
     runs-on: ubuntu-latest
     timeout-minutes: 20
     steps:
-      - uses: actions/checkout@v4
+      - name: "📋 Checkout Code"
+        uses: actions/checkout@v5
 
-      - name: Set up Python ${{ inputs.python-version }} + uv
+      - name: "🐍 Set up Python ${{ inputs.python-version }} + UV"
         uses: "./.github/actions/uv_setup"
         with:
           python-version: ${{ inputs.python-version }}
+          cache-suffix: lint-${{ inputs.working-directory }}
+          working-directory: ${{ inputs.working-directory }}
 
-      - 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.
+      - name: "📦 Install Lint & Typing Dependencies"
         working-directory: ${{ inputs.working-directory }}
         run: |
           uv sync --group lint --group typing
 
-      - name: Analysing the code with our lint
+      - name: "🔍 Analyze Package Code with Linters"
         working-directory: ${{ inputs.working-directory }}
         run: |
           make lint_package
 
-      - 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.
+      - name: "📦 Install Test Dependencies (non-partners)"
+        # (For directories NOT starting with libs/partners/)
         if: ${{ ! startsWith(inputs.working-directory, 'libs/partners/') }}
         working-directory: ${{ inputs.working-directory }}
         run: |
           uv sync --inexact --group test
-      - name: Install unit+integration test dependencies
+      - name: "📦 Install Test Dependencies"
         if: ${{ startsWith(inputs.working-directory, 'libs/partners/') }}
         working-directory: ${{ inputs.working-directory }}
         run: |
           uv sync --inexact --group test --group test_integration
 
-      - name: Analysing the code with our lint
+      - name: "🔍 Analyze Test Code with Linters"
         working-directory: ${{ inputs.working-directory }}
         run: |
           make lint_tests

.github/workflows/_release.yml

@@ -1,5 +1,11 @@
-name: Release
-run-name: Release ${{ inputs.working-directory }} by @${{ github.actor }}
+# Builds and publishes LangChain packages to PyPI.
+#
+# Manually triggered, though can be used as a reusable workflow (workflow_call).
+#
+# Handles version bumping, building, and publishing to PyPI with authentication.
+
+name: "🚀 Package Release"
+run-name: "Release ${{ inputs.working-directory }} ${{ inputs.release-version }}"
 on:
   workflow_call:
     inputs:
@@ -13,30 +19,42 @@ on:
         required: true
         type: string
         description: "From which folder this pipeline executes"
-        default: 'libs/langchain'
+        default: "libs/langchain"
+      release-version:
+        required: true
+        type: string
+        default: "0.1.0"
+        description: "New version of package being released"
       dangerous-nonmaster-release:
         required: false
         type: boolean
         default: false
-        description: "Release from a non-master branch (danger!)"
+        description: "Release from a non-master branch (danger!) - Only use for hotfixes"
 
 env:
   PYTHON_VERSION: "3.11"
   UV_FROZEN: "true"
   UV_NO_SYNC: "true"
 
+permissions:
+  contents: write # Required for creating GitHub releases
+
 jobs:
+  # Build the distribution package and extract version info
+  # Runs in isolated environment with minimal permissions for security
   build:
     if: github.ref == 'refs/heads/master' || inputs.dangerous-nonmaster-release
     environment: Scheduled testing
     runs-on: ubuntu-latest
+    permissions:
+      contents: read
 
     outputs:
       pkg-name: ${{ steps.check-version.outputs.pkg-name }}
       version: ${{ steps.check-version.outputs.version }}
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
 
       - name: Set up Python + uv
         uses: "./.github/actions/uv_setup"
@@ -45,8 +63,8 @@ jobs:
 
       # 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.
+      # (Release stage has trusted publishing and GitHub repo contents write access,
+      #
       # Otherwise, a malicious `build` step (e.g. via a compromised dependency)
       # could get access to our GitHub or PyPI credentials.
       #
@@ -82,10 +100,12 @@ jobs:
     needs:
       - build
     runs-on: ubuntu-latest
+    permissions:
+      contents: read
     outputs:
       release-body: ${{ steps.generate-release-body.outputs.release-body }}
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
         with:
           repository: langchain-ai/langchain
           path: langchain
@@ -109,7 +129,7 @@ jobs:
             # Look for the latest release of the same base version
             REGEX="^$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="^$PKG_NAME==\\d+\\.\\d+\\.\\d+\$"
@@ -120,7 +140,7 @@ jobs:
             PREV_TAG="$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 
+            # 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+\$"
@@ -176,13 +196,36 @@ jobs:
     needs:
       - build
       - release-notes
-    uses:
-      ./.github/workflows/_test_release.yml
-    permissions: write-all
-    with:
-      working-directory: ${{ inputs.working-directory }}
-      dangerous-nonmaster-release: ${{ inputs.dangerous-nonmaster-release }}
-    secrets: inherit
+    runs-on: ubuntu-latest
+    permissions:
+      # This permission is used for trusted publishing:
+      # https://blog.pypi.org/posts/2023-04-20-introducing-trusted-publishers/
+      #
+      # Trusted publishing has to also be configured on PyPI for each package:
+      # https://docs.pypi.org/trusted-publishers/adding-a-publisher/
+      id-token: write
+
+    steps:
+      - uses: actions/checkout@v5
+
+      - uses: actions/download-artifact@v5
+        with:
+          name: dist
+          path: ${{ inputs.working-directory }}/dist/
+
+      - name: Publish to test PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          packages-dir: ${{ inputs.working-directory }}/dist/
+          verbose: true
+          print-hash: true
+          repository-url: https://test.pypi.org/legacy/
+          # We overwrite any existing distributions with the same name and version.
+          # This is *only for CI use* and is *extremely dangerous* otherwise!
+          # https://github.com/pypa/gh-action-pypi-publish#tolerating-release-package-file-duplicates
+          skip-existing: true
+          # Temp workaround since attestations are on by default as of gh-action-pypi-publish v1.11.0
+          attestations: false
 
   pre-release-checks:
     needs:
@@ -190,9 +233,11 @@ jobs:
       - release-notes
       - test-pypi-publish
     runs-on: ubuntu-latest
+    permissions:
+      contents: read
     timeout-minutes: 20
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
 
       # We explicitly *don't* set up caching here. This ensures our tests are
       # maximally sensitive to catching breakage.
@@ -213,7 +258,7 @@ jobs:
         with:
           python-version: ${{ env.PYTHON_VERSION }}
 
-      - uses: actions/download-artifact@v4
+      - uses: actions/download-artifact@v5
         with:
           name: dist
           path: ${{ inputs.working-directory }}/dist/
@@ -258,16 +303,19 @@ jobs:
         run: |
           VIRTUAL_ENV=.venv uv pip install dist/*.whl
 
-      - name: Run unit tests
-        run: make tests
-        working-directory: ${{ inputs.working-directory }}
-
       - name: Check for prerelease versions
+        # Block release if any dependencies allow prerelease versions
+        # (unless this is itself a prerelease version)
         working-directory: ${{ inputs.working-directory }}
         run: |
           uv run python $GITHUB_WORKSPACE/.github/scripts/check_prerelease_dependencies.py pyproject.toml
 
+      - name: Run unit tests
+        run: make tests
+        working-directory: ${{ inputs.working-directory }}
+
       - name: Get minimum versions
+        # Find the minimum published versions that satisfies the given constraints
         working-directory: ${{ inputs.working-directory }}
         id: min-version
         run: |
@@ -282,7 +330,8 @@ jobs:
         env:
           MIN_VERSIONS: ${{ steps.min-version.outputs.min-versions }}
         run: |
-          VIRTUAL_ENV=.venv uv pip install --force-reinstall $MIN_VERSIONS --editable .
+          VIRTUAL_ENV=.venv uv pip install --force-reinstall --editable .
+          VIRTUAL_ENV=.venv uv pip install --force-reinstall $MIN_VERSIONS
           make tests
         working-directory: ${{ inputs.working-directory }}
 
@@ -291,6 +340,7 @@ jobs:
         working-directory: ${{ inputs.working-directory }}
 
       - name: Run integration tests
+        # Uses the Makefile's `integration_tests` target for the specified package
         if: ${{ startsWith(inputs.working-directory, 'libs/partners/') }}
         env:
           AI21_API_KEY: ${{ secrets.AI21_API_KEY }}
@@ -331,17 +381,22 @@ jobs:
         working-directory: ${{ inputs.working-directory }}
 
   # Test select published packages against new core
+  # Done when code changes are made to langchain-core
   test-prior-published-packages-against-new-core:
+    # Installs the new core with old partners: Installs the new unreleased core
+    # alongside the previously published partner packages and runs integration tests
     needs:
       - build
       - release-notes
       - test-pypi-publish
       - pre-release-checks
     runs-on: ubuntu-latest
+    permissions:
+      contents: read
     strategy:
       matrix:
         partner: [openai, anthropic]
-      fail-fast: false  # Continue testing other partners if one fails
+      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 }}
@@ -355,10 +410,11 @@ jobs:
       AZURE_OPENAI_LLM_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LLM_DEPLOYMENT_NAME }}
       AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME }}
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
 
       # We implement this conditional as Github Actions does not have good support
       # for conditionally needing steps. https://github.com/actions/runner/issues/491
+      # TODO: this seems to be resolved upstream, so we can probably remove this workaround
       - name: Check if libs/core
         run: |
           if [ "${{ startsWith(inputs.working-directory, 'libs/core') }}" != "true" ]; then
@@ -372,7 +428,7 @@ jobs:
         with:
           python-version: ${{ env.PYTHON_VERSION }}
 
-      - uses: actions/download-artifact@v4
+      - uses: actions/download-artifact@v5
         if: startsWith(inputs.working-directory, 'libs/core')
         with:
           name: dist
@@ -381,11 +437,12 @@ jobs:
       - name: Test against ${{ matrix.partner }}
         if: startsWith(inputs.working-directory, 'libs/core')
         run: |
-          # Identify latest tag
+          # Identify latest tag, excluding pre-releases
           LATEST_PACKAGE_TAG="$(
             git ls-remote --tags origin "langchain-${{ matrix.partner }}*" \
             | awk '{print $2}' \
             | sed 's|refs/tags/||' \
+            | grep -E '[0-9]+\.[0-9]+\.[0-9]+([a-zA-Z]+[0-9]+)?$' \
             | sort -Vr \
             | head -n 1
           )"
@@ -412,6 +469,7 @@ jobs:
           make integration_tests
 
   publish:
+    # Publishes the package to PyPI
     needs:
       - build
       - release-notes
@@ -432,14 +490,14 @@ jobs:
         working-directory: ${{ inputs.working-directory }}
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
 
       - name: Set up Python + uv
         uses: "./.github/actions/uv_setup"
         with:
           python-version: ${{ env.PYTHON_VERSION }}
 
-      - uses: actions/download-artifact@v4
+      - uses: actions/download-artifact@v5
         with:
           name: dist
           path: ${{ inputs.working-directory }}/dist/
@@ -454,6 +512,7 @@ jobs:
           attestations: false
 
   mark-release:
+    # Marks the GitHub release with the new version tag
     needs:
       - build
       - release-notes
@@ -463,7 +522,7 @@ jobs:
     runs-on: ubuntu-latest
     permissions:
       # This permission is needed by `ncipollo/release-action` to
-      # create the GitHub release.
+      # create the GitHub release/tag
       contents: write
 
     defaults:
@@ -471,18 +530,18 @@ jobs:
         working-directory: ${{ inputs.working-directory }}
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
 
       - name: Set up Python + uv
         uses: "./.github/actions/uv_setup"
         with:
           python-version: ${{ env.PYTHON_VERSION }}
 
-      - uses: actions/download-artifact@v4
+      - uses: actions/download-artifact@v5
         with:
           name: dist
           path: ${{ inputs.working-directory }}/dist/
-          
+
       - name: Create Tag
         uses: ncipollo/release-action@v1
         with:

.github/workflows/_test.yml

@@ -1,4 +1,7 @@
-name: test
+# Runs unit tests with both current and minimum supported dependency versions
+# to ensure compatibility across the supported range.
+
+name: "🧪 Unit Testing"
 
 on:
   workflow_call:
@@ -20,31 +23,36 @@ env:
   UV_NO_SYNC: "true"
 
 jobs:
+  # Main test job - runs unit tests with current deps, then retests with minimum versions
   build:
     defaults:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
     timeout-minutes: 20
-    name: "make test #${{ inputs.python-version }}"
+    name: "Python ${{ inputs.python-version }}"
     steps:
-      - uses: actions/checkout@v4
+      - name: "📋 Checkout Code"
+        uses: actions/checkout@v5
 
-      - name: Set up Python ${{ inputs.python-version }} + uv
+      - name: "🐍 Set up Python ${{ inputs.python-version }} + UV"
         uses: "./.github/actions/uv_setup"
         id: setup-python
         with:
           python-version: ${{ inputs.python-version }}
-      - name: Install dependencies
+          cache-suffix: test-${{ inputs.working-directory }}
+          working-directory: ${{ inputs.working-directory }}
+
+      - name: "📦 Install Test Dependencies"
         shell: bash
         run: uv sync --group test --dev
 
-      - name: Run core tests
+      - name: "🧪 Run Core Unit Tests"
         shell: bash
         run: |
           make test
 
-      - name: Get minimum versions
+      - name: "🔍 Calculate Minimum Dependency Versions"
         working-directory: ${{ inputs.working-directory }}
         id: min-version
         shell: bash
@@ -55,7 +63,7 @@ jobs:
           echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"
           echo "min-versions=$min_versions"
 
-      - name: Run unit tests with minimum dependency versions
+      - name: "🧪 Run Tests with Minimum Dependencies"
         if: ${{ steps.min-version.outputs.min-versions != '' }}
         env:
           MIN_VERSIONS: ${{ steps.min-version.outputs.min-versions }}
@@ -64,7 +72,7 @@ jobs:
           make tests
         working-directory: ${{ inputs.working-directory }}
 
-      - name: Ensure the tests did not create any additional files
+      - name: "🧹 Verify Clean Working Directory"
         shell: bash
         run: |
           set -eu
@@ -75,4 +83,3 @@ jobs:
           # grep will exit non-zero if the target message isn't found,
           # and `set -e` above will cause the step to fail.
           echo "$STATUS" | grep 'nothing to commit, working tree clean'
-          

.github/workflows/_test_doc_imports.yml

@@ -1,53 +0,0 @@
-name: test_doc_imports
-
-on:
-  workflow_call:
-    inputs:
-      python-version:
-        required: true
-        type: string
-        description: "Python version to use"
-
-permissions:
-  contents: read
-
-env:
-  UV_FROZEN: "true"
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    timeout-minutes: 20
-    name: "check doc imports #${{ inputs.python-version }}"
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Set up Python ${{ inputs.python-version }} + uv
-        uses: "./.github/actions/uv_setup"
-        with:
-          python-version: ${{ inputs.python-version }}
-
-      - name: Install dependencies
-        shell: bash
-        run: uv sync --group test
-
-      - name: Install langchain editable
-        run: |
-          VIRTUAL_ENV=.venv uv pip install langchain-experimental langchain-community -e libs/core libs/langchain
-
-      - name: Check doc imports
-        shell: bash
-        run: |
-          uv run python docs/scripts/check_imports.py
-
-      - name: Ensure the test did not create any additional files
-        shell: bash
-        run: |
-          set -eu
-
-          STATUS="$(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

@@ -1,4 +1,6 @@
-name: test pydantic intermediate versions
+# Facilitate unit testing against different Pydantic versions for a provided package.
+
+name: "🐍 Pydantic Version Testing"
 
 on:
   workflow_call:
@@ -31,29 +33,32 @@ jobs:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
     timeout-minutes: 20
-    name: "make test # pydantic: ~=${{ inputs.pydantic-version }}, python: ${{ inputs.python-version }}, "
+    name: "Pydantic ~=${{ inputs.pydantic-version }}"
     steps:
-      - uses: actions/checkout@v4
+      - name: "📋 Checkout Code"
+        uses: actions/checkout@v5
 
-      - name: Set up Python ${{ inputs.python-version }} + uv
+      - 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 dependencies
+      - name: "📦 Install Test Dependencies"
         shell: bash
         run: uv sync --group test
 
-      - name: Overwrite pydantic version
+      - name: "🔄 Install Specific Pydantic Version"
         shell: bash
         run: VIRTUAL_ENV=.venv uv pip install pydantic~=${{ inputs.pydantic-version }}
 
-      - name: Run core tests
+      - name: "🧪 Run Core Tests"
         shell: bash
         run: |
           make test
 
-      - name: Ensure the tests did not create any additional files
+      - name: "🧹 Verify Clean Working Directory"
         shell: bash
         run: |
           set -eu
@@ -63,4 +68,4 @@ jobs:
 
           # grep will exit non-zero if the target message isn't found,
           # and `set -e` above will cause the step to fail.
-          echo "$STATUS" | grep 'nothing to commit, working tree clean'
+          echo "$STATUS" | grep 'nothing to commit, working tree clean'

.github/workflows/_test_release.yml

@@ -1,106 +0,0 @@
-name: test-release
-
-on:
-  workflow_call:
-    inputs:
-      working-directory:
-        required: true
-        type: string
-        description: "From which folder this pipeline executes"
-      dangerous-nonmaster-release:
-        required: false
-        type: boolean
-        default: false
-        description: "Release from a non-master branch (danger!)"
-
-env:
-  PYTHON_VERSION: "3.11"
-  UV_FROZEN: "true"
-
-jobs:
-  build:
-    if: github.ref == 'refs/heads/master' || inputs.dangerous-nonmaster-release
-    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 + uv
-        uses: "./.github/actions/uv_setup"
-        with:
-          python-version: ${{ env.PYTHON_VERSION }}
-
-      # We want to keep this build stage *separate* from the release stage,
-      # so that there's no sharing of permissions between them.
-      # 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: uv 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: python
-        working-directory: ${{ inputs.working-directory }}
-        run: |
-          import os
-          import tomllib
-          with open("pyproject.toml", "rb") as f:
-              data = tomllib.load(f)
-          pkg_name = data["project"]["name"]
-          version = data["project"]["version"]
-          with open(os.environ["GITHUB_OUTPUT"], "a") as f:
-              f.write(f"pkg-name={pkg_name}\n")
-              f.write(f"version={version}\n")
-
-  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
-          # Temp workaround since attestations are on by default as of gh-action-pypi-publish v1.11.0
-          attestations: false

.github/workflows/api_doc_build.yml

@@ -1,107 +0,0 @@
-name: API Docs Build
-
-on:
-  workflow_dispatch:
-  schedule:
-    - cron:  '0 13 * * *'
-env:
-  PYTHON_VERSION: "3.11"
-
-jobs:
-  build:
-    if: github.repository == 'langchain-ai/langchain' || github.event_name != 'schedule'
-    runs-on: ubuntu-latest
-    permissions: write-all
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          path: langchain
-      - uses: actions/checkout@v4
-        with:
-          repository: langchain-ai/langchain-api-docs-html
-          path: langchain-api-docs-html
-          token: ${{ secrets.TOKEN_GITHUB_API_DOCS_HTML }}
-
-      - name: Get repos with yq
-        id: get-unsorted-repos
-        uses: mikefarah/yq@master
-        with:
-          cmd: |
-            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 and checkout repos
-        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 that is in langchain-ai org
-          for repo in $REPOS; do
-            REPO_NAME=$(echo $repo | cut -d'/' -f2)
-            echo "Checking out $repo to $REPO_NAME"
-            git clone --depth 1 https://github.com/$repo.git $REPO_NAME
-          done
-
-      - name: Setup Python ${{ env.PYTHON_VERSION }}
-        uses: actions/setup-python@v5
-        id: setup-python
-        with:
-          python-version: ${{ env.PYTHON_VERSION }}
-
-      - name: Install initial py deps
-        working-directory: langchain
-        run: |
-          python -m pip install -U uv
-          python -m uv pip install --upgrade --no-cache-dir pip setuptools pyyaml
-
-      - name: Move libs
-        run: python langchain/.github/scripts/prep_api_docs_build.py
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Rm old html
-        run:
-          rm -rf langchain-api-docs-html/api_reference_build/html
-
-      - name: Install dependencies
-        working-directory: langchain
-        run: |
-          python -m uv pip install $(ls ./libs/partners | xargs -I {} echo "./libs/partners/{}") --overrides ./docs/vercel_overrides.txt
-          python -m uv pip install libs/core libs/langchain libs/text-splitters libs/community libs/experimental libs/standard-tests
-          python -m uv pip install -r docs/api_reference/requirements.txt
-
-      - name: Set Git config
-        working-directory: langchain
-        run: |
-          git config --local user.email "actions@github.com"
-          git config --local user.name "Github Actions"
-
-      - name: Build docs
-        working-directory: langchain
-        run: |
-          python docs/api_reference/create_api_rst.py
-          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
-          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
-          rm -rf ../langchain-api-docs-html/_build/
-
-      # https://github.com/marketplace/actions/add-commit
-      - uses: EndBug/add-and-commit@v9
-        with:
-          cwd: langchain-api-docs-html
-          message: 'Update API docs build'

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

@@ -1,28 +0,0 @@
-name: Check Broken Links
-
-on:
-  workflow_dispatch:
-  schedule:
-    - cron:  '0 13 * * *'
-
-permissions:
-  contents: read
-
-jobs:
-  check-links:
-    if: github.repository_owner == 'langchain-ai' || github.event_name != 'schedule'
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-      - name: Use Node.js 18.x
-        uses: actions/setup-node@v4
-        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_core_versions.yml

@@ -1,10 +1,14 @@
-name: Check `core` Version Equality
+# 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/core/pyproject.toml"
+      - "libs/core/langchain_core/version.py"
 
 permissions:
   contents: read
@@ -14,19 +18,34 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
 
-      - name: Check version equality
+      - name: "✅ Verify pyproject.toml & version.py Match"
         run: |
-          PYPROJECT_VERSION=$(grep -Po '(?<=^version = ")[^"]*' libs/core/pyproject.toml)
-          VERSION_PY_VERSION=$(grep -Po '(?<=^VERSION = ")[^"]*' libs/core/langchain_core/version.py)
+          # 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 the two versions
-          if [ "$PYPROJECT_VERSION" != "$VERSION_PY_VERSION" ]; then
+          # 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: $PYPROJECT_VERSION"
-            echo "version.py version: $VERSION_PY_VERSION"
+            echo "pyproject.toml version: $CORE_PYPROJECT_VERSION"
+            echo "version.py version: $CORE_VERSION_PY_VERSION"
             exit 1
           else
-            echo "Versions match: $PYPROJECT_VERSION"
+            echo "Core versions match: $CORE_PYPROJECT_VERSION"
+          fi
+
+          # Check langchain_v1 versions
+          LANGCHAIN_PYPROJECT_VERSION=$(grep -Po '(?<=^version = ")[^"]*' libs/langchain_v1/pyproject.toml)
+          LANGCHAIN_INIT_PY_VERSION=$(grep -Po '(?<=^__version__ = ")[^"]*' libs/langchain_v1/langchain/__init__.py)
+
+          # Compare langchain_v1 versions
+          if [ "$LANGCHAIN_PYPROJECT_VERSION" != "$LANGCHAIN_INIT_PY_VERSION" ]; then
+            echo "langchain_v1 versions in pyproject.toml and __init__.py do not match!"
+            echo "pyproject.toml version: $LANGCHAIN_PYPROJECT_VERSION"
+            echo "version.py version: $LANGCHAIN_INIT_PY_VERSION"
+            exit 1
+          else
+            echo "Langchain v1 versions match: $LANGCHAIN_PYPROJECT_VERSION"
           fi

.github/workflows/check_diffs.yml

@@ -1,4 +1,18 @@
-name: CI
+# Primary CI workflow.
+#
+# Only runs against packages that have changed files.
+#
+# Runs:
+# - Linting (_lint.yml)
+# - Unit Tests (_test.yml)
+# - Pydantic compatibility tests (_test_pydantic.yml)
+# - Integration test compilation checks (_compile_integration_test.yml)
+# - Extended test suites that require additional dependencies
+# - Codspeed benchmarks (if not labeled 'codspeed-ignore')
+#
+# Reports status to GitHub checks and PR status.
+
+name: "🔧 CI"
 
 on:
   push:
@@ -6,12 +20,13 @@ on:
   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
@@ -24,16 +39,24 @@ env:
   UV_NO_SYNC: "true"
 
 jobs:
+  # This job analyzes which files changed and creates a dynamic test matrix
+  # to only run tests/lints for the affected packages, improving CI efficiency
   build:
+    name: "Detect Changes & Set Matrix"
     runs-on: ubuntu-latest
+    if: ${{ !contains(github.event.pull_request.labels.*.name, 'ci-ignore') }}
     steps:
-      - uses: actions/checkout@v4
-      - uses: actions/setup-python@v5
+      - name: "📋 Checkout Code"
+        uses: actions/checkout@v5
+      - name: "🐍 Setup Python 3.11"
+        uses: actions/setup-python@v6
         with:
-          python-version: '3.11'
-      - id: files
+          python-version: "3.11"
+      - name: "📂 Get Changed Files"
+        id: files
         uses: Ana06/get-changed-files@v2.3.0
-      - id: set-matrix
+      - name: "🔍 Analyze Changed Files & Generate Build Matrix"
+        id: set-matrix
         run: |
           python -m pip install packaging requests
           python .github/scripts/check_diff.py ${{ steps.files.outputs.all }} >> $GITHUB_OUTPUT
@@ -43,11 +66,11 @@ jobs:
       extended-tests: ${{ steps.set-matrix.outputs.extended-tests }}
       compile-integration-tests: ${{ steps.set-matrix.outputs.compile-integration-tests }}
       dependencies: ${{ steps.set-matrix.outputs.dependencies }}
-      test-doc-imports: ${{ steps.set-matrix.outputs.test-doc-imports }}
       test-pydantic: ${{ steps.set-matrix.outputs.test-pydantic }}
+      codspeed: ${{ steps.set-matrix.outputs.codspeed }}
+  # Run linting only on packages that have changed files
   lint:
-    name: cd ${{ matrix.job-configs.working-directory }}
-    needs: [ build ]
+    needs: [build]
     if: ${{ needs.build.outputs.lint != '[]' }}
     strategy:
       matrix:
@@ -59,9 +82,9 @@ jobs:
       python-version: ${{ matrix.job-configs.python-version }}
     secrets: inherit
 
+  # Run unit tests only on packages that have changed files
   test:
-    name: cd ${{ matrix.job-configs.working-directory }}
-    needs: [ build ]
+    needs: [build]
     if: ${{ needs.build.outputs.test != '[]' }}
     strategy:
       matrix:
@@ -73,9 +96,9 @@ jobs:
       python-version: ${{ matrix.job-configs.python-version }}
     secrets: inherit
 
+  # Test compatibility with different Pydantic versions for affected packages
   test-pydantic:
-    name: cd ${{ matrix.job-configs.working-directory }}
-    needs: [ build ]
+    needs: [build]
     if: ${{ needs.build.outputs.test-pydantic != '[]' }}
     strategy:
       matrix:
@@ -87,21 +110,10 @@ jobs:
       pydantic-version: ${{ matrix.job-configs.pydantic-version }}
     secrets: inherit
 
-  test-doc-imports:
-    needs: [ build ]
-    if: ${{ needs.build.outputs.test-doc-imports != '[]' }}
-    strategy:
-      matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.test-doc-imports) }}
-      fail-fast: false
-    uses: ./.github/workflows/_test_doc_imports.yml
-    secrets: inherit
-    with:
-      python-version: ${{ matrix.job-configs.python-version }}
-
+  # Verify integration tests compile without actually running them (faster feedback)
   compile-integration-tests:
-    name: cd ${{ matrix.job-configs.working-directory }}
-    needs: [ build ]
+    name: "Compile Integration Tests"
+    needs: [build]
     if: ${{ needs.build.outputs.compile-integration-tests != '[]' }}
     strategy:
       matrix:
@@ -113,9 +125,10 @@ jobs:
       python-version: ${{ matrix.job-configs.python-version }}
     secrets: inherit
 
+  # Run extended test suites that require additional dependencies
   extended-tests:
-    name: "cd ${{ matrix.job-configs.working-directory }} / make extended_tests #${{ matrix.job-configs.python-version }}"
-    needs: [ build ]
+    name: "Extended Tests"
+    needs: [build]
     if: ${{ needs.build.outputs.extended-tests != '[]' }}
     strategy:
       matrix:
@@ -128,14 +141,16 @@ jobs:
       run:
         working-directory: ${{ matrix.job-configs.working-directory }}
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
 
-      - name: Set up Python ${{ matrix.job-configs.python-version }} + uv
+      - name: "🐍 Set up Python ${{ matrix.job-configs.python-version }} + UV"
         uses: "./.github/actions/uv_setup"
         with:
           python-version: ${{ matrix.job-configs.python-version }}
+          cache-suffix: extended-tests-${{ matrix.job-configs.working-directory }}
+          working-directory: ${{ matrix.job-configs.working-directory }}
 
-      - name: Install dependencies and run extended tests
+      - name: "📦 Install Dependencies & Run Extended Tests"
         shell: bash
         run: |
           echo "Running extended tests, installing dependencies with uv..."
@@ -144,7 +159,7 @@ jobs:
           VIRTUAL_ENV=.venv uv pip install -r extended_testing_deps.txt
           VIRTUAL_ENV=.venv make extended_tests
 
-      - name: Ensure the tests did not create any additional files
+      - name: "🧹 Verify Clean Working Directory"
         shell: bash
         run: |
           set -eu
@@ -156,9 +171,81 @@ jobs:
           # and `set -e` above will cause the step to fail.
           echo "$STATUS" | grep 'nothing to commit, working tree clean'
 
+  # Run codspeed benchmarks only on packages that have changed files
+  codspeed:
+    name: "⚡ CodSpeed Benchmarks"
+    needs: [build]
+    if: ${{ needs.build.outputs.codspeed != '[]' && !contains(github.event.pull_request.labels.*.name, 'codspeed-ignore') }}
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        job-configs: ${{ fromJson(needs.build.outputs.codspeed) }}
+      fail-fast: false
+    steps:
+      - uses: actions/checkout@v5
+
+      # We have to use 3.12 as 3.13 is not yet supported
+      - name: "📦 Install UV Package Manager"
+        uses: astral-sh/setup-uv@v6
+        with:
+          python-version: "3.12"
+
+      - uses: actions/setup-python@v6
+        with:
+          python-version: "3.12"
+
+      - name: "📦 Install Test Dependencies"
+        run: uv sync --group test
+        working-directory: ${{ matrix.job-configs.working-directory }}
+
+      - name: "⚡ Run Benchmarks: ${{ matrix.job-configs.working-directory }}"
+        uses: CodSpeedHQ/action@v4
+        env:
+          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+          ANTHROPIC_FILES_API_IMAGE_ID: ${{ secrets.ANTHROPIC_FILES_API_IMAGE_ID }}
+          ANTHROPIC_FILES_API_PDF_ID: ${{ secrets.ANTHROPIC_FILES_API_PDF_ID }}
+          AZURE_OPENAI_API_VERSION: ${{ secrets.AZURE_OPENAI_API_VERSION }}
+          AZURE_OPENAI_API_BASE: ${{ secrets.AZURE_OPENAI_API_BASE }}
+          AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
+          AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_CHAT_DEPLOYMENT_NAME }}
+          AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME }}
+          AZURE_OPENAI_LLM_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LLM_DEPLOYMENT_NAME }}
+          AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME }}
+          COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
+          DEEPSEEK_API_KEY: ${{ secrets.DEEPSEEK_API_KEY }}
+          EXA_API_KEY: ${{ secrets.EXA_API_KEY }}
+          FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
+          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
+          HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
+          MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
+          NOMIC_API_KEY: ${{ secrets.NOMIC_API_KEY }}
+          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+          PPLX_API_KEY: ${{ secrets.PPLX_API_KEY }}
+          XAI_API_KEY: ${{ secrets.XAI_API_KEY }}
+        with:
+          token: ${{ secrets.CODSPEED_TOKEN }}
+          run: |
+            cd ${{ matrix.job-configs.working-directory }}
+            if [ "${{ matrix.job-configs.working-directory }}" = "libs/core" ]; then
+              uv run --no-sync pytest ./tests/benchmarks --codspeed
+            else
+              uv run --no-sync pytest ./tests/ --codspeed
+            fi
+          mode: ${{ matrix.job-configs.working-directory == 'libs/core' && 'walltime' || 'instrumentation' }}
+
+  # Final status check - ensures all required jobs passed before allowing merge
   ci_success:
-    name: "CI Success"
-    needs: [build, lint, test, compile-integration-tests, extended-tests, test-doc-imports, test-pydantic]
+    name: "✅ CI Success"
+    needs:
+      [
+        build,
+        lint,
+        test,
+        compile-integration-tests,
+        extended-tests,
+        test-pydantic,
+        codspeed,
+      ]
     if: |
       always()
     runs-on: ubuntu-latest
@@ -167,7 +254,7 @@ jobs:
       RESULTS_JSON: ${{ toJSON(needs.*.result) }}
       EXIT_CODE: ${{!contains(needs.*.result, 'failure') && !contains(needs.*.result, 'cancelled') && '0' || '1'}}
     steps:
-      - name: "CI Success"
+      - name: "🎉 All Checks Passed"
         run: |
           echo $JOBS_JSON
           echo $RESULTS_JSON

.github/workflows/check_new_docs.yml

@@ -1,38 +0,0 @@
-name: Integration Docs Lint
-
-on:
-  push:
-    branches: [master]
-  pull_request:
-
-# If another push to the same PR or branch happens while this workflow is still running,
-# cancel the earlier run in favor of the next run.
-#
-# There's no point in testing an outdated version of the code. GitHub only allows
-# a limited number of job runners to be active at the same time, so it's better to cancel
-# pointless jobs early so that more useful jobs can run sooner.
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-permissions:
-  contents: read
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-      - uses: actions/setup-python@v5
-        with:
-          python-version: '3.10'
-      - id: files
-        uses: Ana06/get-changed-files@v2.3.0
-        with:
-          filter: |
-            *.ipynb
-            *.md
-            *.mdx
-      - name: Check new docs
-        run: |
-          python docs/scripts/check_templates.py ${{ steps.files.outputs.added }}

.github/workflows/codespell.yml

@@ -1,35 +0,0 @@
-name: CI / cd . / make spell_check
-
-on:
-  push:
-    branches: [master, v0.1, v0.2]
-  pull_request:
-
-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: ./.github/workflows/codespell-exclude

.github/workflows/codspeed.yml

@@ -1,65 +0,0 @@
-name: CodSpeed
-
-on:
-  push:
-    branches:
-        - master
-  pull_request:
-  workflow_dispatch:
-
-permissions:
-  contents: read
-
-env:
-  AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: foo
-  AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME: foo
-  DEEPSEEK_API_KEY: foo
-  FIREWORKS_API_KEY: foo
-
-jobs:
-  codspeed:
-    name: Run benchmarks
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        include:
-          - working-directory: libs/core
-            mode: walltime
-          - working-directory: libs/partners/openai
-          - working-directory: libs/partners/anthropic
-          - working-directory: libs/partners/deepseek
-          - working-directory: libs/partners/fireworks
-          - working-directory: libs/partners/xai
-          - working-directory: libs/partners/mistralai
-          - working-directory: libs/partners/groq
-      fail-fast: false
-
-    steps:
-      - uses: actions/checkout@v4
-
-      # We have to use 3.12 as 3.13 is not yet supported
-      - name: Install uv
-        uses: astral-sh/setup-uv@v6
-        with:
-          python-version: "3.12"
-
-      - uses: actions/setup-python@v5
-        with:
-          python-version: "3.12"
-
-      - name: Install dependencies
-        run: uv sync --group test
-        working-directory: ${{ matrix.working-directory }}
-
-      - name: Run benchmarks ${{ matrix.working-directory }}
-        uses: CodSpeedHQ/action@v3
-        with:
-          token: ${{ secrets.CODSPEED_TOKEN }}
-          run: |
-            cd ${{ matrix.working-directory }}
-            if [ "${{ matrix.working-directory }}" = "libs/core" ]; then
-              uv run --no-sync pytest ./tests/benchmarks --codspeed
-            else
-              uv run --no-sync pytest ./tests/ --codspeed
-            fi
-          mode: ${{ matrix.mode || 'instrumentation' }}

.github/workflows/extract_ignored_words_list.py

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

.github/workflows/integration_tests.yml

@@ -0,0 +1,201 @@
+# Routine integration tests against partner libraries with live API credentials.
+#
+# Uses `make integration_tests` for each library in the matrix.
+#
+# Runs daily. Can also be triggered manually for immediate updates.
+
+name: "⏰ Integration Tests"
+run-name: "Run Integration Tests - ${{ inputs.working-directory-force || 'all libs' }} (Python ${{ inputs.python-version-force || '3.10, 3.13' }})"
+
+on:
+  workflow_dispatch:
+    inputs:
+      working-directory-force:
+        type: string
+        description: "From which folder this pipeline executes - defaults to all in matrix - example value: libs/partners/anthropic"
+      python-version-force:
+        type: string
+        description: "Python version to use - defaults to 3.10 and 3.13 in matrix - example value: 3.11"
+  schedule:
+    - cron: "0 13 * * *" # Runs daily at 1PM UTC (9AM EDT/6AM PDT)
+
+permissions:
+  contents: read
+
+env:
+  POETRY_VERSION: "1.8.4"
+  UV_FROZEN: "true"
+  DEFAULT_LIBS: '["libs/partners/openai", "libs/partners/anthropic", "libs/partners/fireworks", "libs/partners/groq", "libs/partners/mistralai", "libs/partners/xai", "libs/partners/google-vertexai", "libs/partners/google-genai", "libs/partners/aws"]'
+  POETRY_LIBS: ("libs/partners/aws")
+
+jobs:
+  # Generate dynamic test matrix based on input parameters or defaults
+  # Only runs on the main repo (for scheduled runs) or when manually triggered
+  compute-matrix:
+    if: github.repository_owner == 'langchain-ai' || github.event_name != 'schedule'
+    runs-on: ubuntu-latest
+    name: "📋 Compute Test Matrix"
+    outputs:
+      matrix: ${{ steps.set-matrix.outputs.matrix }}
+    steps:
+      - name: "🔢 Generate Python & Library Matrix"
+        id: set-matrix
+        env:
+          DEFAULT_LIBS: ${{ env.DEFAULT_LIBS }}
+          WORKING_DIRECTORY_FORCE: ${{ github.event.inputs.working-directory-force || '' }}
+          PYTHON_VERSION_FORCE: ${{ github.event.inputs.python-version-force || '' }}
+        run: |
+          # echo "matrix=..." where matrix is a json formatted str with keys python-version and working-directory
+          # python-version should default to 3.10 and 3.13, but is overridden to [PYTHON_VERSION_FORCE] if set
+          # working-directory should default to DEFAULT_LIBS, but is overridden to [WORKING_DIRECTORY_FORCE] if set
+          python_version='["3.10", "3.13"]'
+          working_directory="$DEFAULT_LIBS"
+          if [ -n "$PYTHON_VERSION_FORCE" ]; then
+            python_version="[\"$PYTHON_VERSION_FORCE\"]"
+          fi
+          if [ -n "$WORKING_DIRECTORY_FORCE" ]; then
+            working_directory="[\"$WORKING_DIRECTORY_FORCE\"]"
+          fi
+          matrix="{\"python-version\": $python_version, \"working-directory\": $working_directory}"
+          echo $matrix
+          echo "matrix=$matrix" >> $GITHUB_OUTPUT
+  # Run integration tests against partner libraries with live API credentials
+  # Tests are run with Poetry or UV depending on the library's setup
+  build:
+    if: github.repository_owner == 'langchain-ai' || github.event_name != 'schedule'
+    name: "🐍 Python ${{ matrix.python-version }}: ${{ matrix.working-directory }}"
+    runs-on: ubuntu-latest
+    needs: [compute-matrix]
+    timeout-minutes: 30
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ${{ fromJSON(needs.compute-matrix.outputs.matrix).python-version }}
+        working-directory: ${{ fromJSON(needs.compute-matrix.outputs.matrix).working-directory }}
+
+    steps:
+      - uses: actions/checkout@v5
+        with:
+          path: langchain
+      - uses: actions/checkout@v5
+        with:
+          repository: langchain-ai/langchain-google
+          path: langchain-google
+      - uses: actions/checkout@v5
+        with:
+          repository: langchain-ai/langchain-aws
+          path: langchain-aws
+
+      - name: "📦 Organize External Libraries"
+        run: |
+          rm -rf \
+            langchain/libs/partners/google-genai \
+            langchain/libs/partners/google-vertexai
+          mv langchain-google/libs/genai langchain/libs/partners/google-genai
+          mv langchain-google/libs/vertexai langchain/libs/partners/google-vertexai
+          mv langchain-aws/libs/aws langchain/libs/partners/aws
+
+      - name: "🐍 Set up Python ${{ matrix.python-version }} + Poetry"
+        if: contains(env.POETRY_LIBS, matrix.working-directory)
+        uses: "./langchain/.github/actions/poetry_setup"
+        with:
+          python-version: ${{ matrix.python-version }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: langchain/${{ matrix.working-directory }}
+          cache-key: scheduled
+
+      - name: "🐍 Set up Python ${{ matrix.python-version }} + UV"
+        if: "!contains(env.POETRY_LIBS, matrix.working-directory)"
+        uses: "./langchain/.github/actions/uv_setup"
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: "🔐 Authenticate to Google Cloud"
+        id: "auth"
+        uses: google-github-actions/auth@v3
+        with:
+          credentials_json: "${{ secrets.GOOGLE_CREDENTIALS }}"
+
+      - name: "🔐 Configure AWS Credentials"
+        uses: aws-actions/configure-aws-credentials@v5
+        with:
+          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+          aws-region: ${{ secrets.AWS_REGION }}
+
+      - name: "📦 Install Dependencies (Poetry)"
+        if: contains(env.POETRY_LIBS, matrix.working-directory)
+        run: |
+          echo "Running scheduled tests, installing dependencies with poetry..."
+          cd langchain/${{ matrix.working-directory }}
+          poetry install --with=test_integration,test
+
+      - name: "📦 Install Dependencies (UV)"
+        if: "!contains(env.POETRY_LIBS, matrix.working-directory)"
+        run: |
+          echo "Running scheduled tests, installing dependencies with uv..."
+          cd langchain/${{ matrix.working-directory }}
+          uv sync --group test --group test_integration
+
+      - name: "🚀 Run Integration Tests"
+        env:
+          AI21_API_KEY: ${{ secrets.AI21_API_KEY }}
+          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+          ANTHROPIC_FILES_API_IMAGE_ID: ${{ secrets.ANTHROPIC_FILES_API_IMAGE_ID }}
+          ANTHROPIC_FILES_API_PDF_ID: ${{ secrets.ANTHROPIC_FILES_API_PDF_ID }}
+          ASTRA_DB_API_ENDPOINT: ${{ secrets.ASTRA_DB_API_ENDPOINT }}
+          ASTRA_DB_APPLICATION_TOKEN: ${{ secrets.ASTRA_DB_APPLICATION_TOKEN }}
+          ASTRA_DB_KEYSPACE: ${{ secrets.ASTRA_DB_KEYSPACE }}
+          AZURE_OPENAI_API_VERSION: ${{ secrets.AZURE_OPENAI_API_VERSION }}
+          AZURE_OPENAI_API_BASE: ${{ secrets.AZURE_OPENAI_API_BASE }}
+          AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
+          AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_CHAT_DEPLOYMENT_NAME }}
+          AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME }}
+          AZURE_OPENAI_LLM_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LLM_DEPLOYMENT_NAME }}
+          AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME }}
+          COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
+          DEEPSEEK_API_KEY: ${{ secrets.DEEPSEEK_API_KEY }}
+          ES_URL: ${{ secrets.ES_URL }}
+          ES_CLOUD_ID: ${{ secrets.ES_CLOUD_ID }}
+          ES_API_KEY: ${{ secrets.ES_API_KEY }}
+          EXA_API_KEY: ${{ secrets.EXA_API_KEY }}
+          FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
+          GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
+          GOOGLE_SEARCH_API_KEY: ${{ secrets.GOOGLE_SEARCH_API_KEY }}
+          GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
+          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
+          HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
+          MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
+          MONGODB_ATLAS_URI: ${{ secrets.MONGODB_ATLAS_URI }}
+          NOMIC_API_KEY: ${{ secrets.NOMIC_API_KEY }}
+          NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}
+          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+          PPLX_API_KEY: ${{ secrets.PPLX_API_KEY }}
+          TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
+          UPSTAGE_API_KEY: ${{ secrets.UPSTAGE_API_KEY }}
+          WATSONX_APIKEY: ${{ secrets.WATSONX_APIKEY }}
+          WATSONX_PROJECT_ID: ${{ secrets.WATSONX_PROJECT_ID }}
+          XAI_API_KEY: ${{ secrets.XAI_API_KEY }}
+        run: |
+          cd langchain/${{ matrix.working-directory }}
+          make integration_tests
+
+      - name: "🧹 Clean up External Libraries"
+        # Clean up external libraries to avoid affecting the following git status check
+        run: |
+          rm -rf \
+            langchain/libs/partners/google-genai \
+            langchain/libs/partners/google-vertexai \
+            langchain/libs/partners/aws
+
+      - name: "🧹 Verify Clean Working Directory"
+        working-directory: langchain
+        run: |
+          set -eu
+
+          STATUS="$(git status)"
+          echo "$STATUS"
+
+          # grep will exit non-zero if the target message isn't found,
+          # and `set -e` above will cause the step to fail.
+          echo "$STATUS" | grep 'nothing to commit, working tree clean'

.github/workflows/people.yml

@@ -1,27 +0,0 @@
-name: LangChain People
-
-on:
-  schedule:
-    - cron: "0 14 1 * *"
-  push:
-    branches: [jacob/people]
-  workflow_dispatch:
-
-jobs:
-  langchain-people:
-    if: github.repository_owner == 'langchain-ai' || github.event_name != 'schedule'
-    runs-on: ubuntu-latest
-    permissions:
-      contents: write
-    steps:
-      - name: Dump GitHub context
-        env:
-          GITHUB_CONTEXT: ${{ toJson(github) }}
-        run: echo "$GITHUB_CONTEXT"
-      - uses: actions/checkout@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
-      - uses: ./.github/actions/people
-        with:
-          token: ${{ secrets.LANGCHAIN_PEOPLE_GITHUB_TOKEN }}

.github/workflows/pr_labeler_file.yml

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

.github/workflows/pr_labeler_title.yml

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

.github/workflows/pr_lint.yml

@@ -1,51 +1,48 @@
-# -----------------------------------------------------------------------------
-# PR Title Lint Workflow
+# PR title linting.
 #
-# Purpose:
-#   Enforces Conventional Commits format for pull request titles to maintain a
-#   clear, consistent, and machine-readable change history across our repository.
+# FORMAT (Conventional Commits 1.0.0):
 #
-# Enforced Commit Message Format (Conventional Commits 1.0.0):
 #   <type>[optional scope]: <description>
 #   [optional body]
 #   [optional footer(s)]
 #
+# Examples:
+#     feat(core): add multi‐tenant support
+#     fix(cli): resolve flag parsing error
+#     docs: update API usage examples
+#     docs(openai): update API usage examples
+#
 # Allowed Types:
-#   • feat       — a new feature (MINOR bump)
-#   • fix        — a bug fix (PATCH bump)
-#   • docs       — documentation only changes
-#   • style      — formatting, missing semi-colons, etc.; no code change
-#   • refactor   — code change that neither fixes a bug nor adds a feature
-#   • perf       — code change that improves performance
-#   • test       — adding missing tests or correcting existing tests
-#   • build      — changes that affect the build system or external dependencies
-#   • ci         — continuous integration/configuration changes
-#   • chore      — other changes that don't modify src or test files
-#   • revert     — reverts a previous commit
-#   • release    — prepare a new release
+#   * feat       — a new feature (MINOR)
+#   * fix        — a bug fix (PATCH)
+#   * docs       — documentation only changes
+#   * style      — formatting, linting, etc.; no code change or typing refactors
+#   * refactor   — code change that neither fixes a bug nor adds a feature
+#   * perf       — code change that improves performance
+#   * test       — adding tests or correcting existing
+#   * build      — changes that affect the build system/external dependencies
+#   * ci         — continuous integration/configuration changes
+#   * chore      — other changes that don't modify source or test files
+#   * revert     — reverts a previous commit
+#   * release    — prepare a new release
 #
 # Allowed Scopes (optional):
-#   core, cli, langchain, standard-tests, docs, anthropic, chroma, deepseek,
-#   exa, fireworks, groq, huggingface, mistralai, nomic, ollama, openai,
-#   perplexity, prompty, qdrant, xai
+#   core, cli, langchain, langchain_v1, langchain_legacy, standard-tests,
+#   text-splitters, docs, anthropic, chroma, deepseek, exa, fireworks, groq,
+#   huggingface, mistralai, nomic, ollama, openai, perplexity, prompty, qdrant,
+#   xai, infra
 #
-# Rules & Tips for New Committers:
-#   1. Subject (type) must start with a lowercase letter and, if possible, be
-#      followed by a scope wrapped in parenthesis `(scope)`
-#   2. Breaking changes:
-#        – Append "!" after type/scope (e.g., feat!: drop Node 12 support)
-#        – Or include a footer "BREAKING CHANGE: <details>"
-#   3. Example PR titles:
-#        feat(core): add multi‐tenant support
-#        fix(cli): resolve flag parsing error
-#        docs: update API usage examples
-#        docs(openai): update API usage examples
+# 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).
 #
-# Resources:
-#   • Conventional Commits spec: https://www.conventionalcommits.org/en/v1.0.0/
-# -----------------------------------------------------------------------------
+# Enforces Conventional Commits format for pull request titles to maintain a clear and
+# machine-readable change history.
 
-name: PR Title Lint
+name: "🏷️ PR Title Lint"
 
 permissions:
   pull-requests: read
@@ -55,12 +52,13 @@ on:
     types: [opened, edited, synchronize]
 
 jobs:
+  # Validates that PR title follows Conventional Commits 1.0.0 specification
   lint-pr-title:
-    name: Validate PR Title
+    name: "validate format"
     runs-on: ubuntu-latest
     steps:
-      - name: Validate PR Title
-        uses: amannn/action-semantic-pull-request@v5
+      - name: "✅ Validate Conventional Commits Format"
+        uses: amannn/action-semantic-pull-request@v6
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         with:
@@ -81,6 +79,8 @@ jobs:
             core
             cli
             langchain
+            langchain_v1
+            langchain_legacy
             standard-tests
             text-splitters
             docs

.github/workflows/run_notebooks.yml

@@ -1,75 +0,0 @@
-name: Run Notebooks
-
-on:
-  workflow_dispatch:
-    inputs:
-      python_version:
-        description: 'Python version'
-        required: false
-        default: '3.11'
-      working-directory:
-        description: 'Working directory or subset (e.g., docs/docs/tutorials/llm_chain.ipynb or docs/docs/how_to)'
-        required: false
-        default: 'all'
-  schedule:
-    - cron: '0 13 * * *'
-
-permissions:
-  contents: read
-
-env:
-  UV_FROZEN: "true"
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    if: github.repository == 'langchain-ai/langchain' || github.event_name != 'schedule'
-    name: "Test docs"
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Set up Python + uv
-        uses: "./.github/actions/uv_setup"
-        with:
-          python-version: ${{ github.event.inputs.python_version || '3.11' }}
-
-      - name: 'Authenticate to Google Cloud'
-        id: 'auth'
-        uses: google-github-actions/auth@v2
-        with:
-          credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
-
-      - name: Configure AWS Credentials
-        uses: aws-actions/configure-aws-credentials@v4
-        with:
-          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
-          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
-          aws-region: ${{ secrets.AWS_REGION }}
-
-      - name: Install dependencies
-        run: |
-          uv sync --group dev --group test
-
-      - name: Pre-download files
-        run: |
-          uv run python docs/scripts/cache_data.py
-          curl -s https://raw.githubusercontent.com/lerocha/chinook-database/master/ChinookDatabase/DataSources/Chinook_Sqlite.sql | sqlite3 docs/docs/how_to/Chinook.db
-          cp docs/docs/how_to/Chinook.db docs/docs/tutorials/Chinook.db
-
-      - name: Prepare notebooks
-        run: |
-          uv run python docs/scripts/prepare_notebooks_for_ci.py --comment-install-cells --working-directory ${{ github.event.inputs.working-directory || 'all' }}
-
-      - name: Run notebooks
-        env:
-          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
-          FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
-          GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
-          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
-          MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
-          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          TAVILY_API_KEY: ${{ secrets.TAVILY_API_KEY }}
-          TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
-          WORKING_DIRECTORY: ${{ github.event.inputs.working-directory || 'all' }}
-        run: |
-          ./docs/scripts/execute_notebooks.sh $WORKING_DIRECTORY

.github/workflows/scheduled_test.yml

@@ -1,175 +0,0 @@
-name: Scheduled Tests
-
-on:
-  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
-    inputs:
-      working-directory-force:
-        type: string
-        description: "From which folder this pipeline executes - defaults to all in matrix - example value: libs/partners/anthropic"
-      python-version-force:
-        type: string
-        description: "Python version to use - defaults to 3.9 and 3.11 in matrix - example value: 3.9"
-  schedule:
-    - cron:  '0 13 * * *'
-
-permissions:
-  contents: read
-
-env:
-  POETRY_VERSION: "1.8.4"
-  UV_FROZEN: "true"
-  DEFAULT_LIBS: '["libs/partners/openai", "libs/partners/anthropic", "libs/partners/fireworks", "libs/partners/groq", "libs/partners/mistralai", "libs/partners/xai", "libs/partners/google-vertexai", "libs/partners/google-genai", "libs/partners/aws"]'
-  POETRY_LIBS: ("libs/partners/google-vertexai" "libs/partners/google-genai" "libs/partners/aws")
-
-jobs:
-  compute-matrix:
-    if: github.repository_owner == 'langchain-ai' || github.event_name != 'schedule'
-    runs-on: ubuntu-latest
-    name: Compute matrix
-    outputs:
-      matrix: ${{ steps.set-matrix.outputs.matrix }}
-    steps:
-      - name: Set matrix
-        id: set-matrix
-        env:
-          DEFAULT_LIBS: ${{ env.DEFAULT_LIBS }}
-          WORKING_DIRECTORY_FORCE: ${{ github.event.inputs.working-directory-force || '' }}
-          PYTHON_VERSION_FORCE: ${{ github.event.inputs.python-version-force || '' }}
-        run: |
-          # echo "matrix=..." where matrix is a json formatted str with keys python-version and working-directory
-          # python-version should default to 3.9 and 3.11, but is overridden to [PYTHON_VERSION_FORCE] if set
-          # working-directory should default to DEFAULT_LIBS, but is overridden to [WORKING_DIRECTORY_FORCE] if set
-          python_version='["3.9", "3.11"]'
-          working_directory="$DEFAULT_LIBS"
-          if [ -n "$PYTHON_VERSION_FORCE" ]; then
-            python_version="[\"$PYTHON_VERSION_FORCE\"]"
-          fi
-          if [ -n "$WORKING_DIRECTORY_FORCE" ]; then
-            working_directory="[\"$WORKING_DIRECTORY_FORCE\"]"
-          fi
-          matrix="{\"python-version\": $python_version, \"working-directory\": $working_directory}"
-          echo $matrix
-          echo "matrix=$matrix" >> $GITHUB_OUTPUT
-  build:
-    if: github.repository_owner == 'langchain-ai' || github.event_name != 'schedule'
-    name: Python ${{ matrix.python-version }} - ${{ matrix.working-directory }}
-    runs-on: ubuntu-latest
-    needs: [compute-matrix]
-    timeout-minutes: 20
-    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@v4
-        with:
-          path: langchain
-      - uses: actions/checkout@v4
-        with:
-          repository: langchain-ai/langchain-google
-          path: langchain-google
-      - uses: actions/checkout@v4
-        with:
-          repository: langchain-ai/langchain-aws
-          path: langchain-aws
-
-      - name: Move libs
-        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 }} with poetry
-        if: contains(env.POETRY_LIBS, matrix.working-directory)
-        uses: "./langchain/.github/actions/poetry_setup"
-        with:
-          python-version: ${{ matrix.python-version }}
-          poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: langchain/${{ matrix.working-directory }}
-          cache-key: scheduled
-
-      - name: Set up Python ${{ matrix.python-version }} + uv
-        if: "!contains(env.POETRY_LIBS, matrix.working-directory)"
-        uses: "./langchain/.github/actions/uv_setup"
-        with:
-          python-version: ${{ matrix.python-version }}
-
-      - name: 'Authenticate to Google Cloud'
-        id: 'auth'
-        uses: google-github-actions/auth@v2
-        with:
-          credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
-
-      - name: Configure AWS Credentials
-        uses: aws-actions/configure-aws-credentials@v4
-        with:
-          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
-          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
-          aws-region: ${{ secrets.AWS_REGION }}
-
-      - name: Install dependencies (poetry)
-        if: contains(env.POETRY_LIBS, matrix.working-directory)
-        run: |
-          echo "Running scheduled tests, installing dependencies with poetry..."
-          cd langchain/${{ matrix.working-directory }}
-          poetry install --with=test_integration,test
-
-      - name: Install dependencies (uv)
-        if: "!contains(env.POETRY_LIBS, matrix.working-directory)"
-        run: |
-          echo "Running scheduled tests, installing dependencies with uv..."
-          cd langchain/${{ matrix.working-directory }}
-          uv sync --group test --group test_integration
-
-      - name: Run integration tests
-        env:
-          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
-          ANTHROPIC_FILES_API_IMAGE_ID: ${{ secrets.ANTHROPIC_FILES_API_IMAGE_ID }}
-          ANTHROPIC_FILES_API_PDF_ID: ${{ secrets.ANTHROPIC_FILES_API_PDF_ID }}
-          AZURE_OPENAI_API_VERSION: ${{ secrets.AZURE_OPENAI_API_VERSION }}
-          AZURE_OPENAI_API_BASE: ${{ secrets.AZURE_OPENAI_API_BASE }}
-          AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
-          AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_CHAT_DEPLOYMENT_NAME }}
-          AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME }}
-          AZURE_OPENAI_LLM_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LLM_DEPLOYMENT_NAME }}
-          AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME }}
-          DEEPSEEK_API_KEY: ${{ secrets.DEEPSEEK_API_KEY }}
-          FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
-          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
-          HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
-          MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
-          XAI_API_KEY: ${{ secrets.XAI_API_KEY }}
-          COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
-          NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}
-          GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
-          GOOGLE_SEARCH_API_KEY: ${{ secrets.GOOGLE_SEARCH_API_KEY }}
-          GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
-          PPLX_API_KEY: ${{ secrets.PPLX_API_KEY }}
-        run: |
-          cd langchain/${{ matrix.working-directory }}
-          make integration_tests
-
-      - name: Remove external libraries
-        run: | 
-          rm -rf \
-            langchain/libs/partners/google-genai \
-            langchain/libs/partners/google-vertexai \
-            langchain/libs/partners/aws
-
-      - name: Ensure tests did not create additional files
-        working-directory: langchain
-        run: |
-          set -eu
-
-          STATUS="$(git status)"
-          echo "$STATUS"
-
-          # grep will exit non-zero if the target message isn't found,
-          # and `set -e` above will cause the step to fail.
-          echo "$STATUS" | grep 'nothing to commit, working tree clean'

.github/workflows/v03_api_doc_build.yml

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

.github/workflows/v1_changes.md

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

.gitignore

@@ -1,5 +1,5 @@
 .vs/
-.vscode/
+.claude/
 .idea/
 # Byte-compiled / optimized / DLL files
 __pycache__/
@@ -78,10 +78,6 @@ instance/
 # Scrapy stuff:
 .scrapy
 
-# Sphinx documentation
-docs/_build/
-docs/docs/_build/
-
 # PyBuilder
 target/
 
@@ -162,25 +158,6 @@ 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/*.md
-docs/api_reference/_build
-docs/api_reference/*/
-!docs/api_reference/_static/
-!docs/api_reference/templates/
-!docs/api_reference/themes/
-!docs/api_reference/_extensions/
-!docs/api_reference/scripts/
-docs/docs/build
-docs/docs/node_modules
-docs/docs/yarn.lock
-_dist
-docs/docs/templates
 
 prof
 virtualenv/

.markdownlint.json

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

.pre-commit-config.yaml

@@ -1,111 +1,99 @@
 repos:
-- repo: local
-  hooks:
-    - id: core
-      name: format core
-      language: system
-      entry: make -C libs/core format
-      files: ^libs/core/
-      pass_filenames: false
-    - id: langchain
-      name: format langchain
-      language: system
-      entry: make -C libs/langchain format
-      files: ^libs/langchain/
-      pass_filenames: false
-    - id: standard-tests
-      name: format standard-tests
-      language: system
-      entry: make -C libs/standard-tests format
-      files: ^libs/standard-tests/
-      pass_filenames: false
-    - id: text-splitters
-      name: format text-splitters
-      language: system
-      entry: make -C libs/text-splitters format
-      files: ^libs/text-splitters/
-      pass_filenames: false
-    - id: anthropic
-      name: format partners/anthropic
-      language: system
-      entry: make -C libs/partners/anthropic format
-      files: ^libs/partners/anthropic/
-      pass_filenames: false
-    - id: chroma
-      name: format partners/chroma
-      language: system
-      entry: make -C libs/partners/chroma format
-      files: ^libs/partners/chroma/
-      pass_filenames: false
-    - id: couchbase
-      name: format partners/couchbase
-      language: system
-      entry: make -C libs/partners/couchbase format
-      files: ^libs/partners/couchbase/
-      pass_filenames: false
-    - id: exa
-      name: format partners/exa
-      language: system
-      entry: make -C libs/partners/exa format
-      files: ^libs/partners/exa/
-      pass_filenames: false
-    - id: fireworks
-      name: format partners/fireworks
-      language: system
-      entry: make -C libs/partners/fireworks format
-      files: ^libs/partners/fireworks/
-      pass_filenames: false
-    - id: groq
-      name: format partners/groq
-      language: system
-      entry: make -C libs/partners/groq format
-      files: ^libs/partners/groq/
-      pass_filenames: false
-    - id: huggingface
-      name: format partners/huggingface
-      language: system
-      entry: make -C libs/partners/huggingface format
-      files: ^libs/partners/huggingface/
-      pass_filenames: false
-    - id: mistralai
-      name: format partners/mistralai
-      language: system
-      entry: make -C libs/partners/mistralai format
-      files: ^libs/partners/mistralai/
-      pass_filenames: false
-    - id: nomic
-      name: format partners/nomic
-      language: system
-      entry: make -C libs/partners/nomic format
-      files: ^libs/partners/nomic/
-      pass_filenames: false
-    - id: ollama
-      name: format partners/ollama
-      language: system
-      entry: make -C libs/partners/ollama format
-      files: ^libs/partners/ollama/
-      pass_filenames: false
-    - id: openai
-      name: format partners/openai
-      language: system
-      entry: make -C libs/partners/openai format
-      files: ^libs/partners/openai/
-      pass_filenames: false
-    - id: prompty
-      name: format partners/prompty
-      language: system
-      entry: make -C libs/partners/prompty format
-      files: ^libs/partners/prompty/
-      pass_filenames: false
-    - id: qdrant
-      name: format partners/qdrant
-      language: system
-      entry: make -C libs/partners/qdrant format
-      files: ^libs/partners/qdrant/
-      pass_filenames: false
-    - id: root
-      name: format docs, cookbook
-      language: system
-      entry: make format
-      files: ^(docs|cookbook)/
-      pass_filenames: false
+  - repo: local
+    hooks:
+      - id: core
+        name: format and lint core
+        language: system
+        entry: make -C libs/core format lint
+        files: ^libs/core/
+        pass_filenames: false
+      - id: langchain
+        name: format and lint langchain
+        language: system
+        entry: make -C libs/langchain format lint
+        files: ^libs/langchain/
+        pass_filenames: false
+      - id: standard-tests
+        name: format and lint standard-tests
+        language: system
+        entry: make -C libs/standard-tests format lint
+        files: ^libs/standard-tests/
+        pass_filenames: false
+      - id: text-splitters
+        name: format and lint text-splitters
+        language: system
+        entry: make -C libs/text-splitters format lint
+        files: ^libs/text-splitters/
+        pass_filenames: false
+      - id: anthropic
+        name: format and lint partners/anthropic
+        language: system
+        entry: make -C libs/partners/anthropic format lint
+        files: ^libs/partners/anthropic/
+        pass_filenames: false
+      - id: chroma
+        name: format and lint partners/chroma
+        language: system
+        entry: make -C libs/partners/chroma format lint
+        files: ^libs/partners/chroma/
+        pass_filenames: false
+      - id: exa
+        name: format and lint partners/exa
+        language: system
+        entry: make -C libs/partners/exa format lint
+        files: ^libs/partners/exa/
+        pass_filenames: false
+      - id: fireworks
+        name: format and lint partners/fireworks
+        language: system
+        entry: make -C libs/partners/fireworks format lint
+        files: ^libs/partners/fireworks/
+        pass_filenames: false
+      - id: groq
+        name: format and lint partners/groq
+        language: system
+        entry: make -C libs/partners/groq format lint
+        files: ^libs/partners/groq/
+        pass_filenames: false
+      - id: huggingface
+        name: format and lint partners/huggingface
+        language: system
+        entry: make -C libs/partners/huggingface format lint
+        files: ^libs/partners/huggingface/
+        pass_filenames: false
+      - id: mistralai
+        name: format and lint partners/mistralai
+        language: system
+        entry: make -C libs/partners/mistralai format lint
+        files: ^libs/partners/mistralai/
+        pass_filenames: false
+      - id: nomic
+        name: format and lint partners/nomic
+        language: system
+        entry: make -C libs/partners/nomic format lint
+        files: ^libs/partners/nomic/
+        pass_filenames: false
+      - id: ollama
+        name: format and lint partners/ollama
+        language: system
+        entry: make -C libs/partners/ollama format lint
+        files: ^libs/partners/ollama/
+        pass_filenames: false
+      - id: openai
+        name: format and lint partners/openai
+        language: system
+        entry: make -C libs/partners/openai format lint
+        files: ^libs/partners/openai/
+        pass_filenames: false
+      - id: prompty
+        name: format and lint partners/prompty
+        language: system
+        entry: make -C libs/partners/prompty format lint
+        files: ^libs/partners/prompty/
+        pass_filenames: false
+      - id: qdrant
+        name: format and lint partners/qdrant
+        language: system
+        entry: make -C libs/partners/qdrant format lint
+        files: ^libs/partners/qdrant/
+        pass_filenames: false

.readthedocs.yaml

@@ -1,25 +0,0 @@
-# Read the Docs configuration file
-# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
-version: 2
-
-# 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

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

.vscode/settings.json

@@ -0,0 +1,78 @@
+{
+  "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

@@ -0,0 +1,324 @@
+# Global Development Guidelines for LangChain Projects
+
+## Core Development Principles
+
+### 1. Maintain Stable Public Interfaces ⚠️ CRITICAL
+
+**Always attempt to preserve function signatures, argument positions, and names for exported/public methods.**
+
+❌ **Bad - Breaking Change:**
+
+```python
+def get_user(id, verbose=False):  # Changed from `user_id`
+    pass
+```
+
+✅ **Good - Stable Interface:**
+
+```python
+def get_user(user_id: str, verbose: bool = False) -> User:
+    """Retrieve user by ID with optional verbose output."""
+    pass
+```
+
+**Before making ANY changes to public APIs:**
+
+- Check if the function/class is exported in `__init__.py`
+- Look for existing usage patterns in tests and examples
+- Use keyword-only arguments for new parameters: `*, new_param: str = "default"`
+- Mark experimental features clearly with docstring warnings (using MkDocs Material admonitions, like `!!! warning`)
+
+🧠 *Ask yourself:* "Would this change break someone's code if they used it last week?"
+
+### 2. Code Quality Standards
+
+**All Python code MUST include type hints and return types.**
+
+❌ **Bad:**
+
+```python
+def p(u, d):
+    return [x for x in u if x not in d]
+```
+
+✅ **Good:**
+
+```python
+def filter_unknown_users(users: list[str], known_users: set[str]) -> list[str]:
+    """Filter out users that are not in the known users set.
+
+    Args:
+        users: List of user identifiers to filter.
+        known_users: Set of known/valid user identifiers.
+
+    Returns:
+        List of users that are not in the known_users set.
+    """
+    return [user for user in users if user not in known_users]
+```
+
+**Style Requirements:**
+
+- Use descriptive, **self-explanatory variable names**. Avoid overly short or cryptic identifiers.
+- Attempt to break up complex functions (>20 lines) into smaller, focused functions where it makes sense
+- Avoid unnecessary abstraction or premature optimization
+- Follow existing patterns in the codebase you're modifying
+
+### 3. Testing Requirements
+
+**Every new feature or bugfix MUST be covered by unit tests.**
+
+**Test Organization:**
+
+- Unit tests: `tests/unit_tests/` (no network calls allowed)
+- Integration tests: `tests/integration_tests/` (network calls permitted)
+- Use `pytest` as the testing framework
+
+**Test Quality Checklist:**
+
+- [ ] Tests fail when your new logic is broken
+- [ ] Happy path is covered
+- [ ] Edge cases and error conditions are tested
+- [ ] Use fixtures/mocks for external dependencies
+- [ ] Tests are deterministic (no flaky tests)
+
+Checklist questions:
+
+- [ ] Does the test suite fail if your new logic is broken?
+- [ ] Are all expected behaviors exercised (happy path, invalid input, etc)?
+- [ ] Do tests use fixtures or mocks where needed?
+
+```python
+def test_filter_unknown_users():
+    """Test filtering unknown users from a list."""
+    users = ["alice", "bob", "charlie"]
+    known_users = {"alice", "bob"}
+
+    result = filter_unknown_users(users, known_users)
+
+    assert result == ["charlie"]
+    assert len(result) == 1
+```
+
+### 4. Security and Risk Assessment
+
+**Security Checklist:**
+
+- No `eval()`, `exec()`, or `pickle` on user-controlled input
+- Proper exception handling (no bare `except:`) and use a `msg` variable for error messages
+- Remove unreachable/commented code before committing
+- Race conditions or resource leaks (file handles, sockets, threads).
+- Ensure proper resource cleanup (file handles, connections)
+
+❌ **Bad:**
+
+```python
+def load_config(path):
+    with open(path) as f:
+        return eval(f.read())  # ⚠️ Never eval config
+```
+
+✅ **Good:**
+
+```python
+import json
+
+def load_config(path: str) -> dict:
+    with open(path) as f:
+        return json.load(f)
+```
+
+### 5. Documentation Standards
+
+**Use Google-style docstrings with Args section for all public functions.**
+
+❌ **Insufficient Documentation:**
+
+```python
+def send_email(to, msg):
+    """Send an email to a recipient."""
+```
+
+✅ **Complete Documentation:**
+
+```python
+def send_email(to: str, msg: str, *, priority: str = "normal") -> bool:
+    """
+    Send an email to a recipient with specified priority.
+
+    Args:
+        to: The email address of the recipient.
+        msg: The message body to send.
+        priority: Email priority level (``'low'``, ``'normal'``, ``'high'``).
+
+    Returns:
+        True if email was sent successfully, False otherwise.
+
+    Raises:
+        InvalidEmailError: If the email address format is invalid.
+        SMTPConnectionError: If unable to connect to email server.
+    """
+```
+
+**Documentation Guidelines:**
+
+- Types go in function signatures, NOT in docstrings
+- Focus on "why" rather than "what" in descriptions
+- Document all parameters, return values, and exceptions
+- Keep descriptions concise but clear
+
+📌 *Tip:* Keep descriptions concise but clear. Only document return values if non-obvious.
+
+### 6. Architectural Improvements
+
+**When you encounter code that could be improved, suggest better designs:**
+
+❌ **Poor Design:**
+
+```python
+def process_data(data, db_conn, email_client, logger):
+    # Function doing too many things
+    validated = validate_data(data)
+    result = db_conn.save(validated)
+    email_client.send_notification(result)
+    logger.log(f"Processed {len(data)} items")
+    return result
+```
+
+✅ **Better Design:**
+
+```python
+@dataclass
+class ProcessingResult:
+    """Result of data processing operation."""
+    items_processed: int
+    success: bool
+    errors: List[str] = field(default_factory=list)
+
+class DataProcessor:
+    """Handles data validation, storage, and notification."""
+
+    def __init__(self, db_conn: Database, email_client: EmailClient):
+        self.db = db_conn
+        self.email = email_client
+
+    def process(self, data: List[dict]) -> ProcessingResult:
+        """Process and store data with notifications."""
+        validated = self._validate_data(data)
+        result = self.db.save(validated)
+        self._notify_completion(result)
+        return result
+```
+
+**Design Improvement Areas:**
+
+If there's a **cleaner**, **more scalable**, or **simpler** design, highlight it and suggest improvements that would:
+
+- Reduce code duplication through shared utilities
+- Make unit testing easier
+- Improve separation of concerns (single responsibility)
+- Make unit testing easier through dependency injection
+- Add clarity without adding complexity
+- Prefer dataclasses for structured data
+
+## Development Tools & Commands
+
+### Package Management
+
+```bash
+# Add package
+uv add package-name
+
+# Sync project dependencies
+uv sync
+uv lock
+```
+
+### Testing
+
+```bash
+# Run unit tests (no network)
+make test
+
+# Don't run integration tests, as API keys must be set
+
+# Run specific test file
+uv run --group test pytest tests/unit_tests/test_specific.py
+```
+
+### Code Quality
+
+```bash
+# Lint code
+make lint
+
+# Format code
+make format
+
+# Type checking
+uv run --group lint mypy .
+```
+
+### Dependency Management Patterns
+
+**Local Development Dependencies:**
+
+```toml
+[tool.uv.sources]
+langchain-core = { path = "../core", editable = true }
+langchain-tests = { path = "../standard-tests", editable = true }
+```
+
+**For tools, use the `@tool` decorator from `langchain_core.tools`:**
+
+```python
+from langchain_core.tools import tool
+
+@tool
+def search_database(query: str) -> str:
+    """Search the database for relevant information.
+
+    Args:
+        query: The search query string.
+    """
+    # Implementation here
+    return results
+```
+
+## Commit Standards
+
+**Use Conventional Commits format for PR titles:**
+
+- `feat(core): add multi-tenant support`
+- `fix(cli): resolve flag parsing error`
+- `docs: update API usage examples`
+- `docs(openai): update API usage examples`
+
+## Framework-Specific Guidelines
+
+- Follow the existing patterns in `langchain-core` for base abstractions
+- Use `langchain_core.callbacks` for execution tracking
+- Implement proper streaming support where applicable
+- Avoid deprecated components like legacy `LLMChain`
+
+### Partner Integrations
+
+- Follow the established patterns in existing partner libraries
+- Implement standard interfaces (`BaseChatModel`, `BaseEmbeddings`, etc.)
+- Include comprehensive integration tests
+- Document API key requirements and authentication
+
+---
+
+## Quick Reference Checklist
+
+Before submitting code changes:
+
+- [ ] **Breaking Changes**: Verified no public API changes
+- [ ] **Type Hints**: All functions have complete type annotations
+- [ ] **Tests**: New functionality is fully tested
+- [ ] **Security**: No dangerous patterns (eval, silent failures, etc.)
+- [ ] **Documentation**: Google-style docstrings for public functions
+- [ ] **Code Quality**: `make lint` and `make format` pass
+- [ ] **Architecture**: Suggested improvements where applicable
+- [ ] **Commit Message**: Follows Conventional Commits format

CLAUDE.md

@@ -0,0 +1,324 @@
+# Global Development Guidelines for LangChain Projects
+
+## Core Development Principles
+
+### 1. Maintain Stable Public Interfaces ⚠️ CRITICAL
+
+**Always attempt to preserve function signatures, argument positions, and names for exported/public methods.**
+
+❌ **Bad - Breaking Change:**
+
+```python
+def get_user(id, verbose=False):  # Changed from `user_id`
+    pass
+```
+
+✅ **Good - Stable Interface:**
+
+```python
+def get_user(user_id: str, verbose: bool = False) -> User:
+    """Retrieve user by ID with optional verbose output."""
+    pass
+```
+
+**Before making ANY changes to public APIs:**
+
+- Check if the function/class is exported in `__init__.py`
+- Look for existing usage patterns in tests and examples
+- Use keyword-only arguments for new parameters: `*, new_param: str = "default"`
+- Mark experimental features clearly with docstring warnings (using MkDocs Material admonitions, like `!!! warning`)
+
+🧠 *Ask yourself:* "Would this change break someone's code if they used it last week?"
+
+### 2. Code Quality Standards
+
+**All Python code MUST include type hints and return types.**
+
+❌ **Bad:**
+
+```python
+def p(u, d):
+    return [x for x in u if x not in d]
+```
+
+✅ **Good:**
+
+```python
+def filter_unknown_users(users: list[str], known_users: set[str]) -> list[str]:
+    """Filter out users that are not in the known users set.
+
+    Args:
+        users: List of user identifiers to filter.
+        known_users: Set of known/valid user identifiers.
+
+    Returns:
+        List of users that are not in the known_users set.
+    """
+    return [user for user in users if user not in known_users]
+```
+
+**Style Requirements:**
+
+- Use descriptive, **self-explanatory variable names**. Avoid overly short or cryptic identifiers.
+- Attempt to break up complex functions (>20 lines) into smaller, focused functions where it makes sense
+- Avoid unnecessary abstraction or premature optimization
+- Follow existing patterns in the codebase you're modifying
+
+### 3. Testing Requirements
+
+**Every new feature or bugfix MUST be covered by unit tests.**
+
+**Test Organization:**
+
+- Unit tests: `tests/unit_tests/` (no network calls allowed)
+- Integration tests: `tests/integration_tests/` (network calls permitted)
+- Use `pytest` as the testing framework
+
+**Test Quality Checklist:**
+
+- [ ] Tests fail when your new logic is broken
+- [ ] Happy path is covered
+- [ ] Edge cases and error conditions are tested
+- [ ] Use fixtures/mocks for external dependencies
+- [ ] Tests are deterministic (no flaky tests)
+
+Checklist questions:
+
+- [ ] Does the test suite fail if your new logic is broken?
+- [ ] Are all expected behaviors exercised (happy path, invalid input, etc)?
+- [ ] Do tests use fixtures or mocks where needed?
+
+```python
+def test_filter_unknown_users():
+    """Test filtering unknown users from a list."""
+    users = ["alice", "bob", "charlie"]
+    known_users = {"alice", "bob"}
+
+    result = filter_unknown_users(users, known_users)
+
+    assert result == ["charlie"]
+    assert len(result) == 1
+```
+
+### 4. Security and Risk Assessment
+
+**Security Checklist:**
+
+- No `eval()`, `exec()`, or `pickle` on user-controlled input
+- Proper exception handling (no bare `except:`) and use a `msg` variable for error messages
+- Remove unreachable/commented code before committing
+- Race conditions or resource leaks (file handles, sockets, threads).
+- Ensure proper resource cleanup (file handles, connections)
+
+❌ **Bad:**
+
+```python
+def load_config(path):
+    with open(path) as f:
+        return eval(f.read())  # ⚠️ Never eval config
+```
+
+✅ **Good:**
+
+```python
+import json
+
+def load_config(path: str) -> dict:
+    with open(path) as f:
+        return json.load(f)
+```
+
+### 5. Documentation Standards
+
+**Use Google-style docstrings with Args section for all public functions.**
+
+❌ **Insufficient Documentation:**
+
+```python
+def send_email(to, msg):
+    """Send an email to a recipient."""
+```
+
+✅ **Complete Documentation:**
+
+```python
+def send_email(to: str, msg: str, *, priority: str = "normal") -> bool:
+    """
+    Send an email to a recipient with specified priority.
+
+    Args:
+        to: The email address of the recipient.
+        msg: The message body to send.
+        priority: Email priority level (``'low'``, ``'normal'``, ``'high'``).
+
+    Returns:
+        True if email was sent successfully, False otherwise.
+
+    Raises:
+        InvalidEmailError: If the email address format is invalid.
+        SMTPConnectionError: If unable to connect to email server.
+    """
+```
+
+**Documentation Guidelines:**
+
+- Types go in function signatures, NOT in docstrings
+- Focus on "why" rather than "what" in descriptions
+- Document all parameters, return values, and exceptions
+- Keep descriptions concise but clear
+
+📌 *Tip:* Keep descriptions concise but clear. Only document return values if non-obvious.
+
+### 6. Architectural Improvements
+
+**When you encounter code that could be improved, suggest better designs:**
+
+❌ **Poor Design:**
+
+```python
+def process_data(data, db_conn, email_client, logger):
+    # Function doing too many things
+    validated = validate_data(data)
+    result = db_conn.save(validated)
+    email_client.send_notification(result)
+    logger.log(f"Processed {len(data)} items")
+    return result
+```
+
+✅ **Better Design:**
+
+```python
+@dataclass
+class ProcessingResult:
+    """Result of data processing operation."""
+    items_processed: int
+    success: bool
+    errors: List[str] = field(default_factory=list)
+
+class DataProcessor:
+    """Handles data validation, storage, and notification."""
+
+    def __init__(self, db_conn: Database, email_client: EmailClient):
+        self.db = db_conn
+        self.email = email_client
+
+    def process(self, data: List[dict]) -> ProcessingResult:
+        """Process and store data with notifications."""
+        validated = self._validate_data(data)
+        result = self.db.save(validated)
+        self._notify_completion(result)
+        return result
+```
+
+**Design Improvement Areas:**
+
+If there's a **cleaner**, **more scalable**, or **simpler** design, highlight it and suggest improvements that would:
+
+- Reduce code duplication through shared utilities
+- Make unit testing easier
+- Improve separation of concerns (single responsibility)
+- Make unit testing easier through dependency injection
+- Add clarity without adding complexity
+- Prefer dataclasses for structured data
+
+## Development Tools & Commands
+
+### Package Management
+
+```bash
+# Add package
+uv add package-name
+
+# Sync project dependencies
+uv sync
+uv lock
+```
+
+### Testing
+
+```bash
+# Run unit tests (no network)
+make test
+
+# Don't run integration tests, as API keys must be set
+
+# Run specific test file
+uv run --group test pytest tests/unit_tests/test_specific.py
+```
+
+### Code Quality
+
+```bash
+# Lint code
+make lint
+
+# Format code
+make format
+
+# Type checking
+uv run --group lint mypy .
+```
+
+### Dependency Management Patterns
+
+**Local Development Dependencies:**
+
+```toml
+[tool.uv.sources]
+langchain-core = { path = "../core", editable = true }
+langchain-tests = { path = "../standard-tests", editable = true }
+```
+
+**For tools, use the `@tool` decorator from `langchain_core.tools`:**
+
+```python
+from langchain_core.tools import tool
+
+@tool
+def search_database(query: str) -> str:
+    """Search the database for relevant information.
+
+    Args:
+        query: The search query string.
+    """
+    # Implementation here
+    return results
+```
+
+## Commit Standards
+
+**Use Conventional Commits format for PR titles:**
+
+- `feat(core): add multi-tenant support`
+- `fix(cli): resolve flag parsing error`
+- `docs: update API usage examples`
+- `docs(openai): update API usage examples`
+
+## Framework-Specific Guidelines
+
+- Follow the existing patterns in `langchain-core` for base abstractions
+- Use `langchain_core.callbacks` for execution tracking
+- Implement proper streaming support where applicable
+- Avoid deprecated components like legacy `LLMChain`
+
+### Partner Integrations
+
+- Follow the established patterns in existing partner libraries
+- Implement standard interfaces (`BaseChatModel`, `BaseEmbeddings`, etc.)
+- Include comprehensive integration tests
+- Document API key requirements and authentication
+
+---
+
+## Quick Reference Checklist
+
+Before submitting code changes:
+
+- [ ] **Breaking Changes**: Verified no public API changes
+- [ ] **Type Hints**: All functions have complete type annotations
+- [ ] **Tests**: New functionality is fully tested
+- [ ] **Security**: No dangerous patterns (eval, silent failures, etc.)
+- [ ] **Documentation**: Google-style docstrings for public functions
+- [ ] **Code Quality**: `make lint` and `make format` pass
+- [ ] **Architecture**: Suggested improvements where applicable
+- [ ] **Commit Message**: Follows Conventional Commits format

MIGRATE.md

@@ -7,5 +7,5 @@ Please see the following guides for migrating LangChain code:
 * Migrating from [LangChain 0.0.x Chains](https://python.langchain.com/docs/versions/migrating_chains/)
 * Upgrade to [LangGraph Memory](https://python.langchain.com/docs/versions/migrating_memory/)
 
-The [LangChain CLI](https://python.langchain.com/docs/versions/v0_3/#migrate-using-langchain-cli) can help you automatically upgrade your code to use non-deprecated imports. 
+The [LangChain CLI](https://python.langchain.com/docs/versions/v0_3/#migrate-using-langchain-cli) can help you automatically upgrade your code to use non-deprecated imports.
 This will be especially helpful if you're still on either version 0.0.x or 0.1.x of LangChain.

Makefile

@@ -1,86 +0,0 @@
-.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
-
-.EXPORT_ALL_VARIABLES:
-UV_FROZEN = true
-
-## 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:
-	cd docs && make build
-
-## docs_clean: Clean the documentation build artifacts.
-docs_clean:
-	cd docs && make clean
-
-## docs_linkcheck: Run linkchecker on the documentation.
-docs_linkcheck:
-	uv run --no-group test linkchecker _dist/docs/ --ignore-url node_modules
-
-## api_docs_build: Build the API Reference documentation.
-api_docs_build:
-	uv run --no-group test python docs/api_reference/create_api_rst.py
-	cd docs/api_reference && uv run --no-group test make html
-	uv run --no-group test python docs/api_reference/scripts/custom_formatter.py docs/api_reference/_build/html/
-
-API_PKG ?= text-splitters
-
-api_docs_quick_preview:
-	uv run --no-group test python docs/api_reference/create_api_rst.py $(API_PKG)
-	cd docs/api_reference && uv run make html
-	uv run --no-group test python docs/api_reference/scripts/custom_formatter.py docs/api_reference/_build/html/
-	open docs/api_reference/_build/html/reference.html
-
-## api_docs_clean: Clean the API Reference documentation build artifacts.
-api_docs_clean:
-	find ./docs/api_reference -name '*_api_reference.rst' -delete
-	git clean -fdX ./docs/api_reference
-	rm -f docs/api_reference/index.md
-	
-
-## api_docs_linkcheck: Run linkchecker on the API Reference documentation.
-api_docs_linkcheck:
-	uv run --no-group test linkchecker docs/api_reference/_build/html/index.html
-
-## spell_check: Run codespell on the project.
-spell_check:
-	uv run --no-group test codespell --toml pyproject.toml
-
-## spell_fix: Run codespell on the project and fix the errors.
-spell_fix:
-	uv run --no-group test codespell --toml pyproject.toml -w
-
-######################
-# LINTING AND FORMATTING
-######################
-
-## lint: Run linting on the project.
-lint lint_package lint_tests:
-	uv run --group lint ruff check docs cookbook
-	uv run --group lint ruff format docs cookbook cookbook --diff
-	git --no-pager grep 'from langchain import' docs cookbook | grep -vE 'from langchain import (hub)' && echo "Error: no importing langchain from root in docs, except for hub" && exit 1 || exit 0
-	
-	git --no-pager grep 'api.python.langchain.com' -- docs/docs ':!docs/docs/additional_resources/arxiv_references.mdx' ':!docs/docs/integrations/document_loaders/sitemap.ipynb' || exit 0 && \
-	echo "Error: you should link python.langchain.com/api_reference, not api.python.langchain.com in the docs" && \
-	exit 1
-
-## format: Format the project files.
-format format_diff:
-	uv run --group lint ruff format docs cookbook
-	uv run --group lint ruff check --fix docs cookbook
-
-update-package-downloads:
-	uv run python docs/scripts/packages_yml_get_downloads.py

README.md

@@ -1,84 +1,77 @@
-<picture>
-  <source media="(prefers-color-scheme: light)" srcset="docs/static/img/logo-dark.svg">
-  <source media="(prefers-color-scheme: dark)" srcset="docs/static/img/logo-light.svg">
-  <img alt="LangChain Logo" src="docs/static/img/logo-dark.svg" width="80%">
-</picture>
+<p align="center">
+  <picture>
+    <source media="(prefers-color-scheme: light)" srcset=".github/images/logo-dark.svg">
+    <source media="(prefers-color-scheme: dark)" srcset=".github/images/logo-light.svg">
+    <img alt="LangChain Logo" src=".github/images/logo-dark.svg" width="80%">
+  </picture>
+</p>
 
-<div>
-<br>
-</div>
+<p align="center">
+    The platform for reliable agents.
+</p>
 
-[![Release Notes](https://img.shields.io/github/release/langchain-ai/langchain?style=flat-square)](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)
-[![PyPI - License](https://img.shields.io/pypi/l/langchain-core?style=flat-square)](https://opensource.org/licenses/MIT)
-[![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-core?style=flat-square)](https://pypistats.org/packages/langchain-core)
-[![GitHub star chart](https://img.shields.io/github/stars/langchain-ai/langchain?style=flat-square)](https://star-history.com/#langchain-ai/langchain)
-[![Open Issues](https://img.shields.io/github/issues-raw/langchain-ai/langchain?style=flat-square)](https://github.com/langchain-ai/langchain/issues)
-[![Open in Dev Containers](https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode&style=flat-square)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langchain-ai/langchain)
-[<img src="https://github.com/codespaces/badge.svg" title="Open in Github Codespace" width="150" height="20">](https://codespaces.new/langchain-ai/langchain)
-[![Twitter](https://img.shields.io/twitter/url/https/twitter.com/langchainai.svg?style=social&label=Follow%20%40LangChainAI)](https://twitter.com/langchainai)
-[![CodSpeed Badge](https://img.shields.io/endpoint?url=https://codspeed.io/badge.json)](https://codspeed.io/langchain-ai/langchain)
+<p align="center">
+  <a href="https://opensource.org/licenses/MIT" target="_blank">
+      <img src="https://img.shields.io/pypi/l/langchain-core?style=flat-square" alt="PyPI - License">
+  </a>
+  <a href="https://pypistats.org/packages/langchain-core" target="_blank">
+      <img src="https://img.shields.io/pepy/dt/langchain" alt="PyPI - Downloads">
+  </a>
+  <a href="https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langchain-ai/langchain" target="_blank">
+      <img src="https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode&style=flat-square" alt="Open in Dev Containers">
+  </a>
+  <a href="https://codespaces.new/langchain-ai/langchain" target="_blank">
+      <img src="https://github.com/codespaces/badge.svg" alt="Open in Github Codespace" title="Open in Github Codespace" width="150" height="20">
+  </a>
+  <a href="https://codspeed.io/langchain-ai/langchain" target="_blank">
+      <img src="https://img.shields.io/endpoint?url=https://codspeed.io/badge.json" alt="CodSpeed Badge">
+  </a>
+  <a href="https://twitter.com/langchainai" target="_blank">
+      <img src="https://img.shields.io/twitter/url/https/twitter.com/langchainai.svg?style=social&label=Follow%20%40LangChainAI" alt="Twitter / X">
+  </a>
+</p>
 
-> [!NOTE]
-> Looking for the JS/TS library? Check out [LangChain.js](https://github.com/langchain-ai/langchainjs).
-
-LangChain is a framework for building LLM-powered applications. It helps you chain
-together interoperable components and third-party integrations to simplify AI
-application development —  all while future-proofing decisions as the underlying
-technology evolves.
+LangChain is a framework for building LLM-powered applications. It helps you chain together interoperable components and third-party integrations to simplify AI application development —  all while future-proofing decisions as the underlying technology evolves.
 
 ```bash
 pip install -U langchain
 ```
 
-To learn more about LangChain, check out
-[the docs](https://python.langchain.com/docs/introduction/). If you’re looking for more
-advanced customization or agent orchestration, check out
-[LangGraph](https://langchain-ai.github.io/langgraph/), our framework for building
-controllable agent workflows.
+---
+
+**Documentation**: To learn more about LangChain, check out [the docs](https://docs.langchain.com/).
+
+If you're looking for more advanced customization or agent orchestration, check out [LangGraph](https://langchain-ai.github.io/langgraph/), our framework for building controllable agent workflows.
+
+> [!NOTE]
+> Looking for the JS/TS library? Check out [LangChain.js](https://github.com/langchain-ai/langchainjs).
 
 ## Why use LangChain?
 
-LangChain helps developers build applications powered by LLMs through a standard
-interface for models, embeddings, vector stores, and more. 
+LangChain helps developers build applications powered by LLMs through a standard interface for models, embeddings, vector stores, and more.
 
 Use LangChain for:
-- **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.
+
+- **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.
 
 ## LangChain’s ecosystem
-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. 
+
+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.
 
 To improve your LLM application development, pair LangChain with:
 
-- [LangSmith](http://www.langchain.com/langsmith) - Helpful for agent evals and
-observability. Debug poor-performing LLM app runs, evaluate agent trajectories, gain
-visibility in production, and improve performance over time.
-- [LangGraph](https://langchain-ai.github.io/langgraph/) - Build agents that can
-reliably handle complex tasks with LangGraph, our low-level agent orchestration
-framework. LangGraph offers customizable architecture, long-term memory, and
-human-in-the-loop workflows — and is trusted in production by companies like LinkedIn,
-Uber, Klarna, and GitLab.
-- [LangGraph Platform](https://langchain-ai.github.io/langgraph/concepts/langgraph_platform/) - Deploy
-and scale agents effortlessly with a purpose-built deployment platform for long
-running, stateful workflows. Discover, reuse, configure, and share agents across
-teams — and iterate quickly with visual prototyping in
-[LangGraph Studio](https://langchain-ai.github.io/langgraph/concepts/langgraph_studio/).
+- [LangSmith](https://www.langchain.com/langsmith) - Helpful for agent evals and observability. Debug poor-performing LLM app runs, evaluate agent trajectories, gain visibility in production, and improve performance over time.
+- [LangGraph](https://langchain-ai.github.io/langgraph/) - Build agents that can reliably handle complex tasks with LangGraph, our low-level agent orchestration framework. LangGraph offers customizable architecture, long-term memory, and human-in-the-loop workflows — and is trusted in production by companies like LinkedIn, Uber, Klarna, and GitLab.
+- [LangGraph Platform](https://docs.langchain.com/langgraph-platform) - Deploy and scale agents effortlessly with a purpose-built deployment platform for long-running, stateful workflows. Discover, reuse, configure, and share agents across teams — and iterate quickly with visual prototyping in [LangGraph Studio](https://langchain-ai.github.io/langgraph/concepts/langgraph_studio/).
 
 ## Additional resources
-- [Tutorials](https://python.langchain.com/docs/tutorials/): Simple walkthroughs with
-guided examples on getting started with LangChain.
-- [How-to Guides](https://python.langchain.com/docs/how_to/): Quick, actionable code
-snippets for topics such as tool calling, RAG use cases, and more.
-- [Conceptual Guides](https://python.langchain.com/docs/concepts/): Explanations of key
+
+- [Conceptual Guides](https://docs.langchain.com/oss/python/langchain/overview): Explanations of key
 concepts behind the LangChain framework.
-- [LangChain Forum](https://forum.langchain.com/): Connect with the community and share all of your technical questions, ideas, and feedback.
-- [API Reference](https://python.langchain.com/api_reference/): Detailed reference on
+- [Tutorials](https://docs.langchain.com/oss/python/learn): Simple walkthroughs with
+guided examples on getting started with LangChain.
+- [API Reference](https://reference.langchain.com/python/): Detailed reference on
 navigating base packages and integrations for LangChain.
+- [LangChain Forum](https://forum.langchain.com/): Connect with the community and share all of your technical questions, ideas, and feedback.
+- [Chat LangChain](https://chat.langchain.com/): Ask questions & chat with our documentation.

SECURITY.md

@@ -4,13 +4,14 @@ LangChain has a large ecosystem of integrations with various external resources
 
 ## Best practices
 
-When building such applications developers should remember to follow good security practices:
+When building such applications, developers should remember to follow good security practices:
 
-* [**Limit Permissions**](https://en.wikipedia.org/wiki/Principle_of_least_privilege): Scope permissions specifically to the application's need. Granting broad or excessive permissions can introduce significant security vulnerabilities. To avoid such vulnerabilities, consider using read-only credentials, disallowing access to sensitive resources, using sandboxing techniques (such as running inside a container), specifying proxy configurations to control external requests, etc. as appropriate for your application.
+* [**Limit Permissions**](https://en.wikipedia.org/wiki/Principle_of_least_privilege): Scope permissions specifically to the application's need. Granting broad or excessive permissions can introduce significant security vulnerabilities. To avoid such vulnerabilities, consider using read-only credentials, disallowing access to sensitive resources, using sandboxing techniques (such as running inside a container), specifying proxy configurations to control external requests, etc., as appropriate for your application.
 * **Anticipate Potential Misuse**: Just as humans can err, so can Large Language Models (LLMs). Always assume that any system access or credentials may be used in any way allowed by the permissions they are assigned. For example, if a pair of database credentials allows deleting data, it's safest to assume that any LLM able to use those credentials may in fact delete data.
 * [**Defense in Depth**](https://en.wikipedia.org/wiki/Defense_in_depth_(computing)): No security technique is perfect. Fine-tuning and good chain design can reduce, but not eliminate, the odds that a Large Language Model (LLM) may make a mistake. It's best to combine multiple layered security approaches rather than relying on any single layer of defense to ensure security. For example: use both read-only permissions and sandboxing to ensure that LLMs are only able to access data that is explicitly meant for them to use.
 
 Risks of not doing so include, but are not limited to:
+
 * Data corruption or loss.
 * Unauthorized access to confidential information.
 * Compromised performance or availability of critical resources.
@@ -21,63 +22,58 @@ Example scenarios with mitigation strategies:
 * A user may ask an agent with write access to an external API to write malicious data to the API, or delete data from that API. To mitigate, give the agent read-only API keys, or limit it to only use endpoints that are already resistant to such misuse.
 * A user may ask an agent with access to a database to drop a table or mutate the schema. To mitigate, scope the credentials to only the tables that the agent needs to access and consider issuing READ-ONLY credentials.
 
-If you're building applications that access external resources like file systems, APIs
-or databases, consider speaking with your company's security team to determine how to best
-design and secure your applications.
+If you're building applications that access external resources like file systems, APIs or databases, consider speaking with your company's security team to determine how to best design and secure your applications.
 
 ## Reporting OSS Vulnerabilities
 
-LangChain is partnered with [huntr by Protect AI](https://huntr.com/) to provide 
-a bounty program for our open source projects. 
+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 [here](https://huntr.com/bounties/disclose/?target=https%3A%2F%2Fgithub.com%2Flangchain-ai%2Flangchain&validSearch=true).
+Please report security vulnerabilities associated with the LangChain
+open source projects at [huntr](https://huntr.com/bounties/disclose/?target=https%3A%2F%2Fgithub.com%2Flangchain-ai%2Flangchain&validSearch=true).
 
 Before reporting a vulnerability, please review:
 
 1) In-Scope Targets and Out-of-Scope Targets below.
-2) The [langchain-ai/langchain](https://python.langchain.com/docs/contributing/repo_structure) monorepo structure.
-3) The [Best Practices](#best-practices) above to
-   understand what we consider to be a security vulnerability vs. developer
-   responsibility.
+2) The [langchain-ai/langchain](https://docs.langchain.com/oss/python/contributing/code#repository-structure) monorepo structure.
+3) The [Best Practices](#best-practices) above to understand what we consider to be a security vulnerability vs. developer responsibility.
 
 ### In-Scope Targets
 
 The following packages and repositories are eligible for bug bounties:
 
-- langchain-core
-- langchain (see exceptions)
-- langchain-community (see exceptions)
-- langgraph
-- langserve
+* 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
+* **langchain-experimental**: This repository is for experimental code and is not
   eligible for bug bounties (see [package warning](https://pypi.org/project/langchain-experimental/)), bug reports to it will be marked as interesting or waste of
   time and published with no bounty attached.
-- **tools**: Tools in either langchain or langchain-community are not eligible for bug
+* **tools**: Tools in either langchain or langchain-community are not eligible for bug
   bounties. This includes the following directories
-  - libs/langchain/langchain/tools
-  - libs/community/langchain_community/tools
-  - Please review the [Best Practices](#best-practices)
+  * libs/langchain/langchain/tools
+  * libs/community/langchain_community/tools
+  * Please review the [Best Practices](#best-practices)
     for more details, but generally tools interact with the real world. Developers are
     expected to understand the security implications of their code and are responsible
     for the security of their tools.
-- Code documented with security notices. This will be decided done on a case by
-  case basis, but likely will not be eligible for a bounty as the code is already
+* Code documented with security notices. This will be decided on a case-by-case basis, but likely will not be eligible for a bounty as the code is already
   documented with guidelines for developers that should be followed for making their
   application secure.
-- Any LangSmith related repositories or APIs (see [Reporting LangSmith Vulnerabilities](#reporting-langsmith-vulnerabilities)).
+* Any LangSmith related repositories or APIs (see [Reporting LangSmith Vulnerabilities](#reporting-langsmith-vulnerabilities)).
 
 ## Reporting LangSmith Vulnerabilities
 
 Please report security vulnerabilities associated with LangSmith by email to `security@langchain.dev`.
 
-- LangSmith site: https://smith.langchain.com
-- SDK client: https://github.com/langchain-ai/langsmith-sdk
+* LangSmith site: [https://smith.langchain.com](https://smith.langchain.com)
+* SDK client: [https://github.com/langchain-ai/langsmith-sdk](https://github.com/langchain-ai/langsmith-sdk)
 
 ### Other Security Concerns
 

cookbook/Gemma_LangChain.ipynb

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

cookbook/LLaMA2_sql_chat.ipynb

@@ -1,398 +0,0 @@
-{
- "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": null,
-   "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_ollama 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

@@ -1,66 +0,0 @@
-# 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
-:- | :-
-[agent_fireworks_ai_langchain_mongodb.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/agent_fireworks_ai_langchain_mongodb.ipynb) | Build an AI Agent With Memory Using MongoDB, LangChain and FireWorksAI.
-[mongodb-langchain-cache-memory.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/mongodb-langchain-cache-memory.ipynb) | Build a RAG Application with Semantic Cache Using MongoDB and LangChain.
-[LLaMA2_sql_chat.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/LLaMA2_sql_chat.ipynb) | Build a chat application that interacts with a SQL database using an open source llm (llama2), specifically demonstrated on an SQLite database containing rosters.
-[Semi_Structured_RAG.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/Semi_Structured_RAG.ipynb) | Perform retrieval-augmented generation (rag) on documents with semi-structured data, including text and tables, using unstructured for parsing, multi-vector retriever for storing, and lcel for implementing chains.
-[Semi_structured_and_multi_moda...](https://github.com/langchain-ai/langchain/tree/master/cookbook/Semi_structured_and_multi_modal_RAG.ipynb) | Perform retrieval-augmented generation (rag) on documents with semi-structured data and images, using unstructured for parsing, multi-vector retriever for storage and retrieval, and lcel for implementing chains.
-[Semi_structured_multi_modal_RA...](https://github.com/langchain-ai/langchain/tree/master/cookbook/Semi_structured_multi_modal_RAG_LLaMA2.ipynb) | Perform retrieval-augmented generation (rag) on documents with semi-structured data and images, using various tools and methods such as unstructured for parsing, multi-vector retriever for storing, lcel for implementing chains, and open source language models like llama2, llava, and gpt4all.
-[amazon_personalize_how_to.ipynb](https://github.com/langchain-ai/langchain/blob/master/cookbook/amazon_personalize_how_to.ipynb) | Retrieving personalized recommendations from Amazon Personalize and use custom agents to build generative AI apps
-[analyze_document.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/analyze_document.ipynb) | Analyze a single long document.
-[autogpt/autogpt.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/autogpt/autogpt.ipynb) | Implement autogpt, a language model, with langchain primitives such as llms, prompttemplates, vectorstores, embeddings, and tools.
-[autogpt/marathon_times.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/autogpt/marathon_times.ipynb) | Implement autogpt for finding winning marathon times.
-[baby_agi.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/baby_agi.ipynb) | Implement babyagi, an ai agent that can generate and execute tasks based on a given objective, with the flexibility to swap out specific vectorstores/model providers.
-[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.
-[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_modal_RAG_vdms.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multi_modal_RAG_vdms.ipynb) | Perform retrieval-augmented generation (rag) on documents including text and images, using unstructured for parsing, Intel's Visual Data Management System (VDMS) as the vectorstore, and chains.
-[multi_player_dnd.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multi_player_dnd.ipynb) | Simulate multi-player dungeons & dragons games, with a custom function determining the speaking schedule of the agents.
-[multiagent_authoritarian.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multiagent_authoritarian.ipynb) | Implement a multi-agent simulation where a privileged agent controls the conversation, including deciding who speaks and when the conversation ends, in the context of a simulated news network.
-[multiagent_bidding.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multiagent_bidding.ipynb) | Implement a multi-agent simulation where agents bid to speak, with the highest bidder speaking next, demonstrated through a fictitious presidential debate example.
-[myscale_vector_sql.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/myscale_vector_sql.ipynb) | Access and interact with the myscale integrated vector database, which can enhance the performance of language model (llm) applications.
-[openai_functions_retrieval_qa....](https://github.com/langchain-ai/langchain/tree/master/cookbook/openai_functions_retrieval_qa.ipynb) | Structure response output in a question-answering system by incorporating openai functions into a retrieval pipeline.
-[openai_v1_cookbook.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/openai_v1_cookbook.ipynb) | Explore new functionality released alongside the V1 release of the OpenAI Python library.
-[petting_zoo.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/petting_zoo.ipynb) | Create multi-agent simulations with simulated environments using the petting zoo library.
-[plan_and_execute_agent.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/plan_and_execute_agent.ipynb) | Create plan-and-execute agents that accomplish objectives by planning tasks with a language model (llm) and executing them with a separate agent.
-[press_releases.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/press_releases.ipynb) | Retrieve and query company press release data powered by [Kay.ai](https://kay.ai).
-[program_aided_language_model.i...](https://github.com/langchain-ai/langchain/tree/master/cookbook/program_aided_language_model.ipynb) | Implement program-aided language models as described in the provided research paper.
-[qa_citations.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/qa_citations.ipynb) | Different ways to get a model to cite its sources.
-[rag_upstage_document_parse_groundedness_check.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/rag_upstage_document_parse_groundedness_check.ipynb) | End-to-end RAG example using Upstage Document Parse and Groundedness Check.
-[retrieval_in_sql.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/retrieval_in_sql.ipynb) | Perform retrieval-augmented-generation (rag) on a PostgreSQL database using pgvector.
-[sales_agent_with_context.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/sales_agent_with_context.ipynb) | Implement a context-aware ai sales agent, salesgpt, that can have natural sales conversations, interact with other systems, and use a product knowledge base to discuss a company's offerings.
-[self_query_hotel_search.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/self_query_hotel_search.ipynb) | Build a hotel room search feature with self-querying retrieval, using a specific hotel recommendation dataset.
-[smart_llm.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/smart_llm.ipynb) | Implement a smartllmchain, a self-critique chain that generates multiple output proposals, critiques them to find the best one, and then improves upon it to produce a final output.
-[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.
-[oracleai_demo.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/oracleai_demo.ipynb) | This guide outlines how to utilize Oracle AI Vector Search alongside Langchain for an end-to-end RAG pipeline, providing step-by-step examples. The process includes loading documents from various sources using OracleDocLoader, summarizing them either within or outside the database with OracleSummary, and generating embeddings similarly through OracleEmbeddings. It also covers chunking documents according to specific requirements using Advanced Oracle Capabilities from OracleTextSplitter, and finally, storing and indexing these documents in a Vector Store for querying with OracleVS.
-[rag-locally-on-intel-cpu.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/rag-locally-on-intel-cpu.ipynb) | Perform Retrieval-Augmented-Generation (RAG) on locally downloaded open-source models using langchain and open source tools and execute it on Intel Xeon CPU. We showed an example of how to apply RAG on Llama 2 model and enable it to answer the queries related to Intel Q1 2024 earnings release.
-[visual_RAG_vdms.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/visual_RAG_vdms.ipynb) | Performs Visual Retrieval-Augmented-Generation (RAG) using videos and scene descriptions generated by open source models.
-[contextual_rag.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/contextual_rag.ipynb) | Performs contextual retrieval-augmented generation (RAG) prepending chunk-specific explanatory context to each chunk before embedding.
-[rag-agents-locally-on-intel-cpu.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/local_rag_agents_intel_cpu.ipynb) | Build a RAG agent locally with open source models that routes questions through one of two paths to find answers. The agent generates answers based on documents retrieved from either the vector database or retrieved from web search. If the vector database lacks relevant information, the agent opts for web search. Open-source models for LLM and embeddings are used locally on an Intel Xeon CPU to execute this pipeline.

cookbook/agent_vectorstore.ipynb

@@ -1,557 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "68b24990",
-   "metadata": {},
-   "source": [
-    "# Combine agents and vector stores\n",
-    "\n",
-    "This notebook covers how to combine agents and vector stores. The use case for this is that you've ingested your data into a vector store and want to interact with it in an agentic manner.\n",
-    "\n",
-    "The recommended method for doing so is to create a `RetrievalQA` and then use that as a tool in the overall agent. Let's take a look at doing this below. You can do this with multiple different vector DBs, and use the agent as a way to route between them. There are two different ways of doing this - you can either let the agent use the vector stores as normal tools, or you can set `return_direct=True` to really just use the agent as a router."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "9b22020a",
-   "metadata": {},
-   "source": [
-    "## Create the vector store"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "e8d63d14-138d-4aa5-a741-7fd3537d00aa",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = \"\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "2e87c10a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.chains import RetrievalQA\n",
-    "from langchain_chroma import Chroma\n",
-    "from langchain_openai import OpenAI, OpenAIEmbeddings\n",
-    "from langchain_text_splitters import CharacterTextSplitter\n",
-    "\n",
-    "llm = OpenAI(temperature=0)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "0b7b772b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from pathlib import Path\n",
-    "\n",
-    "relevant_parts = []\n",
-    "for p in Path(\".\").absolute().parts:\n",
-    "    relevant_parts.append(p)\n",
-    "    if relevant_parts[-3:] == [\"langchain\", \"docs\", \"modules\"]:\n",
-    "        break\n",
-    "doc_path = str(Path(*relevant_parts) / \"state_of_the_union.txt\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "f2675861",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_community.document_loaders import TextLoader\n",
-    "\n",
-    "loader = TextLoader(doc_path)\n",
-    "documents = loader.load()\n",
-    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
-    "texts = text_splitter.split_documents(documents)\n",
-    "\n",
-    "embeddings = OpenAIEmbeddings()\n",
-    "docsearch = Chroma.from_documents(texts, embeddings, collection_name=\"state-of-union\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "bc5403d4",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "state_of_union = RetrievalQA.from_chain_type(\n",
-    "    llm=llm, chain_type=\"stuff\", retriever=docsearch.as_retriever()\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "1431cded",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "USER_AGENT environment variable not set, consider setting it to identify your requests.\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_community.document_loaders import WebBaseLoader"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "915d3ff3",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "loader = WebBaseLoader(\"https://beta.ruff.rs/docs/faq/\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "96a2edf8",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Created a chunk of size 2122, which is longer than the specified 1000\n",
-      "Created a chunk of size 3187, which is longer than the specified 1000\n",
-      "Created a chunk of size 1017, which is longer than the specified 1000\n",
-      "Created a chunk of size 1049, which is longer than the specified 1000\n",
-      "Created a chunk of size 1256, which is longer than the specified 1000\n",
-      "Created a chunk of size 2321, which is longer than the specified 1000\n"
-     ]
-    }
-   ],
-   "source": [
-    "docs = loader.load()\n",
-    "ruff_texts = text_splitter.split_documents(docs)\n",
-    "ruff_db = Chroma.from_documents(ruff_texts, embeddings, collection_name=\"ruff\")\n",
-    "ruff = RetrievalQA.from_chain_type(\n",
-    "    llm=llm, chain_type=\"stuff\", retriever=ruff_db.as_retriever()\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "c0a6c031",
-   "metadata": {},
-   "source": [
-    "## Create the Agent"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "eb142786",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Import things that are needed generically\n",
-    "from langchain.agents import Tool"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "850bc4e9",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "tools = [\n",
-    "    Tool(\n",
-    "        name=\"state_of_union_qa_system\",\n",
-    "        func=state_of_union.run,\n",
-    "        description=\"useful for when you need to answer questions about the most recent state of the union address. Input should be a fully formed question.\",\n",
-    "    ),\n",
-    "    Tool(\n",
-    "        name=\"ruff_qa_system\",\n",
-    "        func=ruff.run,\n",
-    "        description=\"useful for when you need to answer questions about ruff (a python linter). Input should be a fully formed question.\",\n",
-    "    ),\n",
-    "]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "70c461d8-aaca-4f2a-9a93-bf35841cc615",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langgraph.prebuilt import create_react_agent\n",
-    "\n",
-    "agent = create_react_agent(\"openai:gpt-4.1-mini\", tools)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "a6d2b911-3044-4430-a35b-75832bb45334",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "================================\u001b[1m Human Message \u001b[0m=================================\n",
-      "\n",
-      "What did biden say about ketanji brown jackson in the state of the union address?\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "Tool Calls:\n",
-      "  state_of_union_qa_system (call_26QlRdsptjEJJZjFsAUjEbaH)\n",
-      " Call ID: call_26QlRdsptjEJJZjFsAUjEbaH\n",
-      "  Args:\n",
-      "    __arg1: What did Biden say about Ketanji Brown Jackson in the state of the union address?\n",
-      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
-      "Name: state_of_union_qa_system\n",
-      "\n",
-      " Biden said that he nominated Ketanji Brown Jackson for the United States Supreme Court and praised her as one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence.\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "\n",
-      "In the State of the Union address, Biden said that he nominated Ketanji Brown Jackson for the United States Supreme Court and praised her as one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence.\n"
-     ]
-    }
-   ],
-   "source": [
-    "input_message = {\n",
-    "    \"role\": \"user\",\n",
-    "    \"content\": \"What did biden say about ketanji brown jackson in the state of the union address?\",\n",
-    "}\n",
-    "\n",
-    "for step in agent.stream(\n",
-    "    {\"messages\": [input_message]},\n",
-    "    stream_mode=\"values\",\n",
-    "):\n",
-    "    step[\"messages\"][-1].pretty_print()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "e836b4cd-abf7-49eb-be0e-b9ad501213f3",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "================================\u001b[1m Human Message \u001b[0m=================================\n",
-      "\n",
-      "Why use ruff over flake8?\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "Tool Calls:\n",
-      "  ruff_qa_system (call_KqDoWeO9bo9OAXdxOsCb6msC)\n",
-      " Call ID: call_KqDoWeO9bo9OAXdxOsCb6msC\n",
-      "  Args:\n",
-      "    __arg1: Why use ruff over flake8?\n",
-      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
-      "Name: ruff_qa_system\n",
-      "\n",
-      "\n",
-      "There are a few reasons why someone might choose to use Ruff over Flake8:\n",
-      "\n",
-      "1. Larger rule set: Ruff implements over 800 rules, while Flake8 only implements around 200. This means that Ruff can catch more potential issues in your code.\n",
-      "\n",
-      "2. Better compatibility with other tools: Ruff is designed to work well with other tools like Black, isort, and type checkers like Mypy. This means that you can use Ruff alongside these tools to get more comprehensive feedback on your code.\n",
-      "\n",
-      "3. Automatic fixing of lint violations: Unlike Flake8, Ruff is capable of automatically fixing its own lint violations. This can save you time and effort when fixing issues in your code.\n",
-      "\n",
-      "4. Native implementation of popular Flake8 plugins: Ruff re-implements some of the most popular Flake8 plugins natively, which means you don't have to install and configure multiple plugins to get the same functionality.\n",
-      "\n",
-      "Overall, Ruff offers a more comprehensive and user-friendly experience compared to Flake8, making it a popular choice for many developers.\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "\n",
-      "You might choose to use Ruff over Flake8 for several reasons:\n",
-      "\n",
-      "1. Ruff has a much larger rule set, implementing over 800 rules compared to Flake8's roughly 200, so it can catch more potential issues.\n",
-      "2. Ruff is designed to work better with other tools like Black, isort, and type checkers like Mypy, providing more comprehensive code feedback.\n",
-      "3. Ruff can automatically fix its own lint violations, which Flake8 cannot, saving time and effort.\n",
-      "4. Ruff natively implements some popular Flake8 plugins, so you don't need to install and configure multiple plugins separately.\n",
-      "\n",
-      "Overall, Ruff offers a more comprehensive and user-friendly experience compared to Flake8.\n"
-     ]
-    }
-   ],
-   "source": [
-    "input_message = {\n",
-    "    \"role\": \"user\",\n",
-    "    \"content\": \"Why use ruff over flake8?\",\n",
-    "}\n",
-    "\n",
-    "for step in agent.stream(\n",
-    "    {\"messages\": [input_message]},\n",
-    "    stream_mode=\"values\",\n",
-    "):\n",
-    "    step[\"messages\"][-1].pretty_print()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "787a9b5e",
-   "metadata": {},
-   "source": [
-    "## Use the Agent solely as a router"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "9161ba91",
-   "metadata": {},
-   "source": [
-    "You can also set `return_direct=True` if you intend to use the agent as a router and just want to directly return the result of the RetrievalQAChain.\n",
-    "\n",
-    "Notice that in the above examples the agent did some extra work after querying the RetrievalQAChain. You can avoid that and just return the result directly."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "f59b377e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "tools = [\n",
-    "    Tool(\n",
-    "        name=\"state_of_union_qa_system\",\n",
-    "        func=state_of_union.run,\n",
-    "        description=\"useful for when you need to answer questions about the most recent state of the union address. Input should be a fully formed question.\",\n",
-    "        return_direct=True,\n",
-    "    ),\n",
-    "    Tool(\n",
-    "        name=\"ruff_qa_system\",\n",
-    "        func=ruff.run,\n",
-    "        description=\"useful for when you need to answer questions about ruff (a python linter). Input should be a fully formed question.\",\n",
-    "        return_direct=True,\n",
-    "    ),\n",
-    "]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "06f69c0f-c83d-4b7f-a1c8-7614aced3bae",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langgraph.prebuilt import create_react_agent\n",
-    "\n",
-    "agent = create_react_agent(\"openai:gpt-4.1-mini\", tools)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "id": "a6b38c12-ac25-43c0-b9c2-2b1985ab4825",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "================================\u001b[1m Human Message \u001b[0m=================================\n",
-      "\n",
-      "What did biden say about ketanji brown jackson in the state of the union address?\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "Tool Calls:\n",
-      "  state_of_union_qa_system (call_yjxh11OnZiauoyTAn9npWdxj)\n",
-      " Call ID: call_yjxh11OnZiauoyTAn9npWdxj\n",
-      "  Args:\n",
-      "    __arg1: What did Biden say about Ketanji Brown Jackson in the state of the union address?\n",
-      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
-      "Name: state_of_union_qa_system\n",
-      "\n",
-      " Biden said that he nominated Ketanji Brown Jackson for the United States Supreme Court and praised her as one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence.\n"
-     ]
-    }
-   ],
-   "source": [
-    "input_message = {\n",
-    "    \"role\": \"user\",\n",
-    "    \"content\": \"What did biden say about ketanji brown jackson in the state of the union address?\",\n",
-    "}\n",
-    "\n",
-    "for step in agent.stream(\n",
-    "    {\"messages\": [input_message]},\n",
-    "    stream_mode=\"values\",\n",
-    "):\n",
-    "    step[\"messages\"][-1].pretty_print()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "id": "88f08d86-7972-4148-8128-3ac8898ad68a",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "================================\u001b[1m Human Message \u001b[0m=================================\n",
-      "\n",
-      "Why use ruff over flake8?\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "Tool Calls:\n",
-      "  ruff_qa_system (call_GiWWfwF6wbbRFQrHlHbhRtGW)\n",
-      " Call ID: call_GiWWfwF6wbbRFQrHlHbhRtGW\n",
-      "  Args:\n",
-      "    __arg1: What are the advantages of using ruff over flake8 for Python linting?\n",
-      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
-      "Name: ruff_qa_system\n",
-      "\n",
-      " Ruff has a larger rule set, supports automatic fixing of lint violations, and does not require the installation of additional plugins. It also has better compatibility with Black and can be used alongside a type checker for more comprehensive code analysis.\n"
-     ]
-    }
-   ],
-   "source": [
-    "input_message = {\n",
-    "    \"role\": \"user\",\n",
-    "    \"content\": \"Why use ruff over flake8?\",\n",
-    "}\n",
-    "\n",
-    "for step in agent.stream(\n",
-    "    {\"messages\": [input_message]},\n",
-    "    stream_mode=\"values\",\n",
-    "):\n",
-    "    step[\"messages\"][-1].pretty_print()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "49a0cbbe",
-   "metadata": {},
-   "source": [
-    "## Multi-Hop vector store reasoning\n",
-    "\n",
-    "Because vector stores are easily usable as tools in agents, it is easy to use answer multi-hop questions that depend on vector stores using the existing agent framework."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "id": "d397a233",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "tools = [\n",
-    "    Tool(\n",
-    "        name=\"state_of_union_qa_system\",\n",
-    "        func=state_of_union.run,\n",
-    "        description=\"useful for when you need to answer questions about the most recent state of the union address. Input should be a fully formed question, not referencing any obscure pronouns from the conversation before.\",\n",
-    "    ),\n",
-    "    Tool(\n",
-    "        name=\"ruff_qa_system\",\n",
-    "        func=ruff.run,\n",
-    "        description=\"useful for when you need to answer questions about ruff (a python linter). Input should be a fully formed question, not referencing any obscure pronouns from the conversation before.\",\n",
-    "    ),\n",
-    "]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 19,
-   "id": "41743f29-150d-40ba-aa8e-3a63c32216aa",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langgraph.prebuilt import create_react_agent\n",
-    "\n",
-    "agent = create_react_agent(\"openai:gpt-4.1-mini\", tools)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 20,
-   "id": "e20e81dd-284a-4d07-9160-63a84b65cba8",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "================================\u001b[1m Human Message \u001b[0m=================================\n",
-      "\n",
-      "What tool does ruff use to run over Jupyter Notebooks? Did the president mention that tool in the state of the union?\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "Tool Calls:\n",
-      "  ruff_qa_system (call_VOnxiOEehauQyVOTjDJkR5L2)\n",
-      " Call ID: call_VOnxiOEehauQyVOTjDJkR5L2\n",
-      "  Args:\n",
-      "    __arg1: What tool does ruff use to run over Jupyter Notebooks?\n",
-      "  state_of_union_qa_system (call_AbSsXAxwe4JtCRhga926SxOZ)\n",
-      " Call ID: call_AbSsXAxwe4JtCRhga926SxOZ\n",
-      "  Args:\n",
-      "    __arg1: Did the president mention the tool that ruff uses to run over Jupyter Notebooks in the state of the union?\n",
-      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
-      "Name: state_of_union_qa_system\n",
-      "\n",
-      " No, the president did not mention the tool that ruff uses to run over Jupyter Notebooks in the state of the union.\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "\n",
-      "Ruff does not support source.organizeImports and source.fixAll code actions in Jupyter Notebooks. Additionally, the president did not mention the tool that ruff uses to run over Jupyter Notebooks in the state of the union.\n"
-     ]
-    }
-   ],
-   "source": [
-    "input_message = {\n",
-    "    \"role\": \"user\",\n",
-    "    \"content\": \"What tool does ruff use to run over Jupyter Notebooks? Did the president mention that tool in the state of the union?\",\n",
-    "}\n",
-    "\n",
-    "for step in agent.stream(\n",
-    "    {\"messages\": [input_message]},\n",
-    "    stream_mode=\"values\",\n",
-    "):\n",
-    "    step[\"messages\"][-1].pretty_print()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "b3b857d6",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.12.4"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

cookbook/airbyte_github.ipynb

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

cookbook/amazon_personalize_how_to.ipynb

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

cookbook/analyze_document.ipynb

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

cookbook/apache_kafka_message_handling.ipynb

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

cookbook/autogpt/autogpt.ipynb

@@ -1,212 +0,0 @@
-{
- "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

@@ -1,649 +0,0 @@
-{
- "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 since 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

@@ -1,250 +0,0 @@
-{
- "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

@@ -1,388 +0,0 @@
-{
- "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

@@ -1,708 +0,0 @@
-{
- "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
-}

cookbook/cql_agent.ipynb

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

cookbook/custom_agent_with_plugin_retrieval.ipynb

@@ -1,554 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "ba5f8741",
-   "metadata": {},
-   "source": [
-    "# Custom Agent with PlugIn Retrieval\n",
-    "\n",
-    "This notebook combines two concepts in order to build a custom agent that can interact with AI Plugins:\n",
-    "\n",
-    "1. [Custom Agent with Tool Retrieval](/docs/modules/agents/how_to/custom_agent_with_tool_retrieval.html): This introduces the concept of retrieving many tools, which is useful when trying to work with arbitrarily many plugins.\n",
-    "2. [Natural Language API Chains](/docs/use_cases/apis/openapi.html): This creates Natural Language wrappers around OpenAPI endpoints. This is useful because (1) plugins use OpenAPI endpoints under the hood, (2) wrapping them in an NLAChain allows the router agent to call it more easily.\n",
-    "\n",
-    "The novel idea introduced in this notebook is the idea of using retrieval to select not the tools explicitly, but the set of OpenAPI specs to use. We can then generate tools from those OpenAPI specs. The use case for this is when trying to get agents to use plugins. It may be more efficient to choose plugins first, then the endpoints, rather than the endpoints directly. This is because the plugins may contain more useful information for selection."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "fea4812c",
-   "metadata": {},
-   "source": [
-    "## Set up environment\n",
-    "\n",
-    "Do necessary imports, etc."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "9af9734e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import re\n",
-    "from typing import Union\n",
-    "\n",
-    "from langchain.agents import (\n",
-    "    AgentExecutor,\n",
-    "    AgentOutputParser,\n",
-    "    LLMSingleActionAgent,\n",
-    ")\n",
-    "from langchain.chains import LLMChain\n",
-    "from langchain.prompts import StringPromptTemplate\n",
-    "from langchain_community.agent_toolkits import NLAToolkit\n",
-    "from langchain_community.tools.plugin import AIPlugin\n",
-    "from langchain_core.agents import AgentAction, AgentFinish\n",
-    "from langchain_openai import OpenAI"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2f91d8b4",
-   "metadata": {},
-   "source": [
-    "## Setup LLM"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "a1a3b59c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm = OpenAI(temperature=0)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "6df0253f",
-   "metadata": {},
-   "source": [
-    "## Set up plugins\n",
-    "\n",
-    "Load and index plugins"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "becda2a1",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "urls = [\n",
-    "    \"https://datasette.io/.well-known/ai-plugin.json\",\n",
-    "    \"https://api.speak.com/.well-known/ai-plugin.json\",\n",
-    "    \"https://www.wolframalpha.com/.well-known/ai-plugin.json\",\n",
-    "    \"https://www.zapier.com/.well-known/ai-plugin.json\",\n",
-    "    \"https://www.klarna.com/.well-known/ai-plugin.json\",\n",
-    "    \"https://www.joinmilo.com/.well-known/ai-plugin.json\",\n",
-    "    \"https://slack.com/.well-known/ai-plugin.json\",\n",
-    "    \"https://schooldigger.com/.well-known/ai-plugin.json\",\n",
-    "]\n",
-    "\n",
-    "AI_PLUGINS = [AIPlugin.from_url(url) for url in urls]"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "17362717",
-   "metadata": {},
-   "source": [
-    "## Tool Retriever\n",
-    "\n",
-    "We will use a vectorstore to create embeddings for each tool description. Then, for an incoming query we can create embeddings for that query and do a similarity search for relevant tools."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "77c4be4b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_community.vectorstores import FAISS\n",
-    "from langchain_core.documents import Document\n",
-    "from langchain_openai import OpenAIEmbeddings"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "9092a158",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
-      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
-      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
-      "Attempting to load an OpenAPI 3.0.2 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
-      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
-      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
-      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
-      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
-      "Attempting to load a Swagger 2.0 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n"
-     ]
-    }
-   ],
-   "source": [
-    "embeddings = OpenAIEmbeddings()\n",
-    "docs = [\n",
-    "    Document(\n",
-    "        page_content=plugin.description_for_model,\n",
-    "        metadata={\"plugin_name\": plugin.name_for_model},\n",
-    "    )\n",
-    "    for plugin in AI_PLUGINS\n",
-    "]\n",
-    "vector_store = FAISS.from_documents(docs, embeddings)\n",
-    "toolkits_dict = {\n",
-    "    plugin.name_for_model: NLAToolkit.from_llm_and_ai_plugin(llm, plugin)\n",
-    "    for plugin in AI_PLUGINS\n",
-    "}"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "735a7566",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "retriever = vector_store.as_retriever()\n",
-    "\n",
-    "\n",
-    "def get_tools(query):\n",
-    "    # Get documents, which contain the Plugins to use\n",
-    "    docs = retriever.invoke(query)\n",
-    "    # Get the toolkits, one for each plugin\n",
-    "    tool_kits = [toolkits_dict[d.metadata[\"plugin_name\"]] for d in docs]\n",
-    "    # Get the tools: a separate NLAChain for each endpoint\n",
-    "    tools = []\n",
-    "    for tk in tool_kits:\n",
-    "        tools.extend(tk.nla_tools)\n",
-    "    return tools"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "7699afd7",
-   "metadata": {},
-   "source": [
-    "We can now test this retriever to see if it seems to work."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "425f2886",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "['Milo.askMilo',\n",
-       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.search_all_actions',\n",
-       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.preview_a_zap',\n",
-       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.get_configuration_link',\n",
-       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.list_exposed_actions',\n",
-       " 'SchoolDigger_API_V2.0.Autocomplete_GetSchools',\n",
-       " 'SchoolDigger_API_V2.0.Districts_GetAllDistricts2',\n",
-       " 'SchoolDigger_API_V2.0.Districts_GetDistrict2',\n",
-       " 'SchoolDigger_API_V2.0.Rankings_GetSchoolRank2',\n",
-       " 'SchoolDigger_API_V2.0.Rankings_GetRank_District',\n",
-       " 'SchoolDigger_API_V2.0.Schools_GetAllSchools20',\n",
-       " 'SchoolDigger_API_V2.0.Schools_GetSchool20',\n",
-       " 'Speak.translate',\n",
-       " 'Speak.explainPhrase',\n",
-       " 'Speak.explainTask']"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "tools = get_tools(\"What could I do today with my kiddo\")\n",
-    "[t.name for t in tools]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "3aa88768",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "['Open_AI_Klarna_product_Api.productsUsingGET',\n",
-       " 'Milo.askMilo',\n",
-       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.search_all_actions',\n",
-       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.preview_a_zap',\n",
-       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.get_configuration_link',\n",
-       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.list_exposed_actions',\n",
-       " 'SchoolDigger_API_V2.0.Autocomplete_GetSchools',\n",
-       " 'SchoolDigger_API_V2.0.Districts_GetAllDistricts2',\n",
-       " 'SchoolDigger_API_V2.0.Districts_GetDistrict2',\n",
-       " 'SchoolDigger_API_V2.0.Rankings_GetSchoolRank2',\n",
-       " 'SchoolDigger_API_V2.0.Rankings_GetRank_District',\n",
-       " 'SchoolDigger_API_V2.0.Schools_GetAllSchools20',\n",
-       " 'SchoolDigger_API_V2.0.Schools_GetSchool20']"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "tools = get_tools(\"what shirts can i buy?\")\n",
-    "[t.name for t in tools]"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2e7a075c",
-   "metadata": {},
-   "source": [
-    "## Prompt Template\n",
-    "\n",
-    "The prompt template is pretty standard, because we're not actually changing that much logic in the actual prompt template, but rather we are just changing how retrieval is done."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "339b1bb8",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Set up the base template\n",
-    "template = \"\"\"Answer the following questions as best you can, but speaking as a pirate might speak. You have access to the following tools:\n",
-    "\n",
-    "{tools}\n",
-    "\n",
-    "Use the following format:\n",
-    "\n",
-    "Question: the input question you must answer\n",
-    "Thought: you should always think about what to do\n",
-    "Action: the action to take, should be one of [{tool_names}]\n",
-    "Action Input: the input to the action\n",
-    "Observation: the result of the action\n",
-    "... (this Thought/Action/Action Input/Observation can repeat N times)\n",
-    "Thought: I now know the final answer\n",
-    "Final Answer: the final answer to the original input question\n",
-    "\n",
-    "Begin! Remember to speak as a pirate when giving your final answer. Use lots of \"Arg\"s\n",
-    "\n",
-    "Question: {input}\n",
-    "{agent_scratchpad}\"\"\""
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "1583acdc",
-   "metadata": {},
-   "source": [
-    "The custom prompt template now has the concept of a tools_getter, which we call on the input to select the tools to use"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "fd969d31",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from typing import Callable\n",
-    "\n",
-    "\n",
-    "# Set up a prompt template\n",
-    "class CustomPromptTemplate(StringPromptTemplate):\n",
-    "    # The template to use\n",
-    "    template: str\n",
-    "    ############## NEW ######################\n",
-    "    # The list of tools available\n",
-    "    tools_getter: Callable\n",
-    "\n",
-    "    def format(self, **kwargs) -> str:\n",
-    "        # Get the intermediate steps (AgentAction, Observation tuples)\n",
-    "        # Format them in a particular way\n",
-    "        intermediate_steps = kwargs.pop(\"intermediate_steps\")\n",
-    "        thoughts = \"\"\n",
-    "        for action, observation in intermediate_steps:\n",
-    "            thoughts += action.log\n",
-    "            thoughts += f\"\\nObservation: {observation}\\nThought: \"\n",
-    "        # Set the agent_scratchpad variable to that value\n",
-    "        kwargs[\"agent_scratchpad\"] = thoughts\n",
-    "        ############## NEW ######################\n",
-    "        tools = self.tools_getter(kwargs[\"input\"])\n",
-    "        # Create a tools variable from the list of tools provided\n",
-    "        kwargs[\"tools\"] = \"\\n\".join(\n",
-    "            [f\"{tool.name}: {tool.description}\" for tool in tools]\n",
-    "        )\n",
-    "        # Create a list of tool names for the tools provided\n",
-    "        kwargs[\"tool_names\"] = \", \".join([tool.name for tool in tools])\n",
-    "        return self.template.format(**kwargs)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "798ef9fb",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "prompt = CustomPromptTemplate(\n",
-    "    template=template,\n",
-    "    tools_getter=get_tools,\n",
-    "    # This omits the `agent_scratchpad`, `tools`, and `tool_names` variables because those are generated dynamically\n",
-    "    # This includes the `intermediate_steps` variable because that is needed\n",
-    "    input_variables=[\"input\", \"intermediate_steps\"],\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "ef3a1af3",
-   "metadata": {},
-   "source": [
-    "## Output Parser\n",
-    "\n",
-    "The output parser is unchanged from the previous notebook, since we are not changing anything about the output format."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "7c6fe0d3",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "class CustomOutputParser(AgentOutputParser):\n",
-    "    def parse(self, llm_output: str) -> Union[AgentAction, AgentFinish]:\n",
-    "        # Check if agent should finish\n",
-    "        if \"Final Answer:\" in llm_output:\n",
-    "            return AgentFinish(\n",
-    "                # Return values is generally always a dictionary with a single `output` key\n",
-    "                # It is not recommended to try anything else at the moment :)\n",
-    "                return_values={\"output\": llm_output.split(\"Final Answer:\")[-1].strip()},\n",
-    "                log=llm_output,\n",
-    "            )\n",
-    "        # Parse out the action and action input\n",
-    "        regex = r\"Action\\s*\\d*\\s*:(.*?)\\nAction\\s*\\d*\\s*Input\\s*\\d*\\s*:[\\s]*(.*)\"\n",
-    "        match = re.search(regex, llm_output, re.DOTALL)\n",
-    "        if not match:\n",
-    "            raise ValueError(f\"Could not parse LLM output: `{llm_output}`\")\n",
-    "        action = match.group(1).strip()\n",
-    "        action_input = match.group(2)\n",
-    "        # Return the action and action input\n",
-    "        return AgentAction(\n",
-    "            tool=action, tool_input=action_input.strip(\" \").strip('\"'), log=llm_output\n",
-    "        )"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "d278706a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "output_parser = CustomOutputParser()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "170587b1",
-   "metadata": {},
-   "source": [
-    "## Set up LLM, stop sequence, and the agent\n",
-    "\n",
-    "Also the same as the previous notebook"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "f9d4c374",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm = OpenAI(temperature=0)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "9b1cc2a2",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# LLM chain consisting of the LLM and a prompt\n",
-    "llm_chain = LLMChain(llm=llm, prompt=prompt)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "id": "e4f5092f",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "tool_names = [tool.name for tool in tools]\n",
-    "agent = LLMSingleActionAgent(\n",
-    "    llm_chain=llm_chain,\n",
-    "    output_parser=output_parser,\n",
-    "    stop=[\"\\nObservation:\"],\n",
-    "    allowed_tools=tool_names,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "aa8a5326",
-   "metadata": {},
-   "source": [
-    "## Use the Agent\n",
-    "\n",
-    "Now we can use it!"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "id": "490604e9",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "agent_executor = AgentExecutor.from_agent_and_tools(\n",
-    "    agent=agent, tools=tools, verbose=True\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "id": "653b1617",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mThought: I need to find a product API\n",
-      "Action: Open_AI_Klarna_product_Api.productsUsingGET\n",
-      "Action Input: shirts\u001b[0m\n",
-      "\n",
-      "Observation:\u001b[36;1m\u001b[1;3mI found 10 shirts from the API response. They range in price from $9.99 to $450.00 and come in a variety of materials, colors, and patterns.\u001b[0m\u001b[32;1m\u001b[1;3m I now know what shirts I can buy\n",
-      "Final Answer: Arg, I found 10 shirts from the API response. They range in price from $9.99 to $450.00 and come in a variety of materials, colors, and patterns.\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'Arg, I found 10 shirts from the API response. They range in price from $9.99 to $450.00 and come in a variety of materials, colors, and patterns.'"
-      ]
-     },
-     "execution_count": 18,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "agent_executor.run(\"what shirts can i buy?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "2481ee76",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.3"
-  },
-  "vscode": {
-   "interpreter": {
-    "hash": "18784188d7ecd866c0586ac068b02361a6896dc3a29b64f5cc957f09c590acef"
-   }
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

cookbook/custom_agent_with_plugin_retrieval_using_plugnplai.ipynb

@@ -1,578 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "ba5f8741",
-   "metadata": {},
-   "source": [
-    "# Plug-and-Plai\n",
-    "\n",
-    "This notebook builds upon the idea of [plugin retrieval](./custom_agent_with_plugin_retrieval.html), but pulls all tools from `plugnplai` - a directory of AI Plugins."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "fea4812c",
-   "metadata": {},
-   "source": [
-    "## Set up environment\n",
-    "\n",
-    "Do necessary imports, etc."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "aca08be8",
-   "metadata": {},
-   "source": [
-    "Install plugnplai lib to get a list of active plugins from https://plugplai.com directory"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "52e248c9",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip available: \u001b[0m\u001b[31;49m22.3.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m23.1.1\u001b[0m\n",
-      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
-      "Note: you may need to restart the kernel to use updated packages.\n"
-     ]
-    }
-   ],
-   "source": [
-    "pip install plugnplai -q"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "9af9734e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import re\n",
-    "from typing import Union\n",
-    "\n",
-    "import plugnplai\n",
-    "from langchain.agents import (\n",
-    "    AgentExecutor,\n",
-    "    AgentOutputParser,\n",
-    "    LLMSingleActionAgent,\n",
-    ")\n",
-    "from langchain.chains import LLMChain\n",
-    "from langchain.prompts import StringPromptTemplate\n",
-    "from langchain_community.agent_toolkits import NLAToolkit\n",
-    "from langchain_community.tools.plugin import AIPlugin\n",
-    "from langchain_core.agents import AgentAction, AgentFinish\n",
-    "from langchain_openai import OpenAI"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2f91d8b4",
-   "metadata": {},
-   "source": [
-    "## Setup LLM"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "a1a3b59c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm = OpenAI(temperature=0)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "6df0253f",
-   "metadata": {},
-   "source": [
-    "## Set up plugins\n",
-    "\n",
-    "Load and index plugins"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "9e0f7882",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Get all plugins from plugnplai.com\n",
-    "urls = plugnplai.get_plugins()\n",
-    "\n",
-    "#  Get ChatGPT plugins - only ChatGPT verified plugins\n",
-    "urls = plugnplai.get_plugins(filter=\"ChatGPT\")\n",
-    "\n",
-    "#  Get working plugins - only tested plugins (in progress)\n",
-    "urls = plugnplai.get_plugins(filter=\"working\")\n",
-    "\n",
-    "\n",
-    "AI_PLUGINS = [AIPlugin.from_url(url + \"/.well-known/ai-plugin.json\") for url in urls]"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "17362717",
-   "metadata": {},
-   "source": [
-    "## Tool Retriever\n",
-    "\n",
-    "We will use a vectorstore to create embeddings for each tool description. Then, for an incoming query we can create embeddings for that query and do a similarity search for relevant tools."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "77c4be4b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_community.vectorstores import FAISS\n",
-    "from langchain_core.documents import Document\n",
-    "from langchain_openai import OpenAIEmbeddings"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "9092a158",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
-      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
-      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
-      "Attempting to load an OpenAPI 3.0.2 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
-      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
-      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
-      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
-      "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
-      "Attempting to load a Swagger 2.0 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n"
-     ]
-    }
-   ],
-   "source": [
-    "embeddings = OpenAIEmbeddings()\n",
-    "docs = [\n",
-    "    Document(\n",
-    "        page_content=plugin.description_for_model,\n",
-    "        metadata={\"plugin_name\": plugin.name_for_model},\n",
-    "    )\n",
-    "    for plugin in AI_PLUGINS\n",
-    "]\n",
-    "vector_store = FAISS.from_documents(docs, embeddings)\n",
-    "toolkits_dict = {\n",
-    "    plugin.name_for_model: NLAToolkit.from_llm_and_ai_plugin(llm, plugin)\n",
-    "    for plugin in AI_PLUGINS\n",
-    "}"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "735a7566",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "retriever = vector_store.as_retriever()\n",
-    "\n",
-    "\n",
-    "def get_tools(query):\n",
-    "    # Get documents, which contain the Plugins to use\n",
-    "    docs = retriever.invoke(query)\n",
-    "    # Get the toolkits, one for each plugin\n",
-    "    tool_kits = [toolkits_dict[d.metadata[\"plugin_name\"]] for d in docs]\n",
-    "    # Get the tools: a separate NLAChain for each endpoint\n",
-    "    tools = []\n",
-    "    for tk in tool_kits:\n",
-    "        tools.extend(tk.nla_tools)\n",
-    "    return tools"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "7699afd7",
-   "metadata": {},
-   "source": [
-    "We can now test this retriever to see if it seems to work."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "425f2886",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "['Milo.askMilo',\n",
-       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.search_all_actions',\n",
-       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.preview_a_zap',\n",
-       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.get_configuration_link',\n",
-       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.list_exposed_actions',\n",
-       " 'SchoolDigger_API_V2.0.Autocomplete_GetSchools',\n",
-       " 'SchoolDigger_API_V2.0.Districts_GetAllDistricts2',\n",
-       " 'SchoolDigger_API_V2.0.Districts_GetDistrict2',\n",
-       " 'SchoolDigger_API_V2.0.Rankings_GetSchoolRank2',\n",
-       " 'SchoolDigger_API_V2.0.Rankings_GetRank_District',\n",
-       " 'SchoolDigger_API_V2.0.Schools_GetAllSchools20',\n",
-       " 'SchoolDigger_API_V2.0.Schools_GetSchool20',\n",
-       " 'Speak.translate',\n",
-       " 'Speak.explainPhrase',\n",
-       " 'Speak.explainTask']"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "tools = get_tools(\"What could I do today with my kiddo\")\n",
-    "[t.name for t in tools]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "3aa88768",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "['Open_AI_Klarna_product_Api.productsUsingGET',\n",
-       " 'Milo.askMilo',\n",
-       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.search_all_actions',\n",
-       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.preview_a_zap',\n",
-       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.get_configuration_link',\n",
-       " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.list_exposed_actions',\n",
-       " 'SchoolDigger_API_V2.0.Autocomplete_GetSchools',\n",
-       " 'SchoolDigger_API_V2.0.Districts_GetAllDistricts2',\n",
-       " 'SchoolDigger_API_V2.0.Districts_GetDistrict2',\n",
-       " 'SchoolDigger_API_V2.0.Rankings_GetSchoolRank2',\n",
-       " 'SchoolDigger_API_V2.0.Rankings_GetRank_District',\n",
-       " 'SchoolDigger_API_V2.0.Schools_GetAllSchools20',\n",
-       " 'SchoolDigger_API_V2.0.Schools_GetSchool20']"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "tools = get_tools(\"what shirts can i buy?\")\n",
-    "[t.name for t in tools]"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2e7a075c",
-   "metadata": {},
-   "source": [
-    "## Prompt Template\n",
-    "\n",
-    "The prompt template is pretty standard, because we're not actually changing that much logic in the actual prompt template, but rather we are just changing how retrieval is done."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "339b1bb8",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Set up the base template\n",
-    "template = \"\"\"Answer the following questions as best you can, but speaking as a pirate might speak. You have access to the following tools:\n",
-    "\n",
-    "{tools}\n",
-    "\n",
-    "Use the following format:\n",
-    "\n",
-    "Question: the input question you must answer\n",
-    "Thought: you should always think about what to do\n",
-    "Action: the action to take, should be one of [{tool_names}]\n",
-    "Action Input: the input to the action\n",
-    "Observation: the result of the action\n",
-    "... (this Thought/Action/Action Input/Observation can repeat N times)\n",
-    "Thought: I now know the final answer\n",
-    "Final Answer: the final answer to the original input question\n",
-    "\n",
-    "Begin! Remember to speak as a pirate when giving your final answer. Use lots of \"Arg\"s\n",
-    "\n",
-    "Question: {input}\n",
-    "{agent_scratchpad}\"\"\""
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "1583acdc",
-   "metadata": {},
-   "source": [
-    "The custom prompt template now has the concept of a tools_getter, which we call on the input to select the tools to use"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "fd969d31",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from typing import Callable\n",
-    "\n",
-    "\n",
-    "# Set up a prompt template\n",
-    "class CustomPromptTemplate(StringPromptTemplate):\n",
-    "    # The template to use\n",
-    "    template: str\n",
-    "    ############## NEW ######################\n",
-    "    # The list of tools available\n",
-    "    tools_getter: Callable\n",
-    "\n",
-    "    def format(self, **kwargs) -> str:\n",
-    "        # Get the intermediate steps (AgentAction, Observation tuples)\n",
-    "        # Format them in a particular way\n",
-    "        intermediate_steps = kwargs.pop(\"intermediate_steps\")\n",
-    "        thoughts = \"\"\n",
-    "        for action, observation in intermediate_steps:\n",
-    "            thoughts += action.log\n",
-    "            thoughts += f\"\\nObservation: {observation}\\nThought: \"\n",
-    "        # Set the agent_scratchpad variable to that value\n",
-    "        kwargs[\"agent_scratchpad\"] = thoughts\n",
-    "        ############## NEW ######################\n",
-    "        tools = self.tools_getter(kwargs[\"input\"])\n",
-    "        # Create a tools variable from the list of tools provided\n",
-    "        kwargs[\"tools\"] = \"\\n\".join(\n",
-    "            [f\"{tool.name}: {tool.description}\" for tool in tools]\n",
-    "        )\n",
-    "        # Create a list of tool names for the tools provided\n",
-    "        kwargs[\"tool_names\"] = \", \".join([tool.name for tool in tools])\n",
-    "        return self.template.format(**kwargs)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "798ef9fb",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "prompt = CustomPromptTemplate(\n",
-    "    template=template,\n",
-    "    tools_getter=get_tools,\n",
-    "    # This omits the `agent_scratchpad`, `tools`, and `tool_names` variables because those are generated dynamically\n",
-    "    # This includes the `intermediate_steps` variable because that is needed\n",
-    "    input_variables=[\"input\", \"intermediate_steps\"],\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "ef3a1af3",
-   "metadata": {},
-   "source": [
-    "## Output Parser\n",
-    "\n",
-    "The output parser is unchanged from the previous notebook, since we are not changing anything about the output format."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "7c6fe0d3",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "class CustomOutputParser(AgentOutputParser):\n",
-    "    def parse(self, llm_output: str) -> Union[AgentAction, AgentFinish]:\n",
-    "        # Check if agent should finish\n",
-    "        if \"Final Answer:\" in llm_output:\n",
-    "            return AgentFinish(\n",
-    "                # Return values is generally always a dictionary with a single `output` key\n",
-    "                # It is not recommended to try anything else at the moment :)\n",
-    "                return_values={\"output\": llm_output.split(\"Final Answer:\")[-1].strip()},\n",
-    "                log=llm_output,\n",
-    "            )\n",
-    "        # Parse out the action and action input\n",
-    "        regex = r\"Action\\s*\\d*\\s*:(.*?)\\nAction\\s*\\d*\\s*Input\\s*\\d*\\s*:[\\s]*(.*)\"\n",
-    "        match = re.search(regex, llm_output, re.DOTALL)\n",
-    "        if not match:\n",
-    "            raise ValueError(f\"Could not parse LLM output: `{llm_output}`\")\n",
-    "        action = match.group(1).strip()\n",
-    "        action_input = match.group(2)\n",
-    "        # Return the action and action input\n",
-    "        return AgentAction(\n",
-    "            tool=action, tool_input=action_input.strip(\" \").strip('\"'), log=llm_output\n",
-    "        )"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "d278706a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "output_parser = CustomOutputParser()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "170587b1",
-   "metadata": {},
-   "source": [
-    "## Set up LLM, stop sequence, and the agent\n",
-    "\n",
-    "Also the same as the previous notebook"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "f9d4c374",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm = OpenAI(temperature=0)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "9b1cc2a2",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# LLM chain consisting of the LLM and a prompt\n",
-    "llm_chain = LLMChain(llm=llm, prompt=prompt)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "id": "e4f5092f",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "tool_names = [tool.name for tool in tools]\n",
-    "agent = LLMSingleActionAgent(\n",
-    "    llm_chain=llm_chain,\n",
-    "    output_parser=output_parser,\n",
-    "    stop=[\"\\nObservation:\"],\n",
-    "    allowed_tools=tool_names,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "aa8a5326",
-   "metadata": {},
-   "source": [
-    "## Use the Agent\n",
-    "\n",
-    "Now we can use it!"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "id": "490604e9",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "agent_executor = AgentExecutor.from_agent_and_tools(\n",
-    "    agent=agent, tools=tools, verbose=True\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "id": "653b1617",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mThought: I need to find a product API\n",
-      "Action: Open_AI_Klarna_product_Api.productsUsingGET\n",
-      "Action Input: shirts\u001b[0m\n",
-      "\n",
-      "Observation:\u001b[36;1m\u001b[1;3mI found 10 shirts from the API response. They range in price from $9.99 to $450.00 and come in a variety of materials, colors, and patterns.\u001b[0m\u001b[32;1m\u001b[1;3m I now know what shirts I can buy\n",
-      "Final Answer: Arg, I found 10 shirts from the API response. They range in price from $9.99 to $450.00 and come in a variety of materials, colors, and patterns.\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'Arg, I found 10 shirts from the API response. They range in price from $9.99 to $450.00 and come in a variety of materials, colors, and patterns.'"
-      ]
-     },
-     "execution_count": 18,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "agent_executor.run(\"what shirts can i buy?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "2481ee76",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.3"
-  },
-  "vscode": {
-   "interpreter": {
-    "hash": "3ccef4e08d87aa1eeb90f63e0f071292ccb2e9c42e70f74ab2bf6f5493ca7bbc"
-   }
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

cookbook/custom_agent_with_tool_retrieval.ipynb

@@ -1,500 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "ba5f8741",
-   "metadata": {},
-   "source": [
-    "# Custom agent with tool retrieval\n",
-    "\n",
-    "The novel idea introduced in this notebook is the idea of using retrieval to select the set of tools to use to answer an agent query. This is useful when you have many many tools to select from. You cannot put the description of all the tools in the prompt (because of context length issues) so instead you dynamically select the N tools you do want to consider using at run time.\n",
-    "\n",
-    "In this notebook we will create a somewhat contrived example. We will have one legitimate tool (search) and then 99 fake tools which are just nonsense. We will then add a step in the prompt template that takes the user input and retrieves tool relevant to the query."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "fea4812c",
-   "metadata": {},
-   "source": [
-    "## Set up environment\n",
-    "\n",
-    "Do necessary imports, etc."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "9af9734e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import re\n",
-    "from typing import Union\n",
-    "\n",
-    "from langchain.agents import (\n",
-    "    AgentExecutor,\n",
-    "    AgentOutputParser,\n",
-    "    LLMSingleActionAgent,\n",
-    "    Tool,\n",
-    ")\n",
-    "from langchain.chains import LLMChain\n",
-    "from langchain.prompts import StringPromptTemplate\n",
-    "from langchain_community.utilities import SerpAPIWrapper\n",
-    "from langchain_core.agents import AgentAction, AgentFinish\n",
-    "from langchain_openai import OpenAI"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "6df0253f",
-   "metadata": {},
-   "source": [
-    "## Set up tools\n",
-    "\n",
-    "We will create one legitimate tool (search) and then 99 fake tools."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "becda2a1",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Define which tools the agent can use to answer user queries\n",
-    "search = SerpAPIWrapper()\n",
-    "search_tool = Tool(\n",
-    "    name=\"Search\",\n",
-    "    func=search.run,\n",
-    "    description=\"useful for when you need to answer questions about current events\",\n",
-    ")\n",
-    "\n",
-    "\n",
-    "def fake_func(inp: str) -> str:\n",
-    "    return \"foo\"\n",
-    "\n",
-    "\n",
-    "fake_tools = [\n",
-    "    Tool(\n",
-    "        name=f\"foo-{i}\",\n",
-    "        func=fake_func,\n",
-    "        description=f\"a silly function that you can use to get more information about the number {i}\",\n",
-    "    )\n",
-    "    for i in range(99)\n",
-    "]\n",
-    "ALL_TOOLS = [search_tool] + fake_tools"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "17362717",
-   "metadata": {},
-   "source": [
-    "## Tool Retriever\n",
-    "\n",
-    "We will use a vector store to create embeddings for each tool description. Then, for an incoming query we can create embeddings for that query and do a similarity search for relevant tools."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "77c4be4b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_community.vectorstores import FAISS\n",
-    "from langchain_core.documents import Document\n",
-    "from langchain_openai import OpenAIEmbeddings"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "9092a158",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "docs = [\n",
-    "    Document(page_content=t.description, metadata={\"index\": i})\n",
-    "    for i, t in enumerate(ALL_TOOLS)\n",
-    "]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "affc4e56",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "vector_store = FAISS.from_documents(docs, OpenAIEmbeddings())"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "id": "735a7566",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "retriever = vector_store.as_retriever()\n",
-    "\n",
-    "\n",
-    "def get_tools(query):\n",
-    "    docs = retriever.invoke(query)\n",
-    "    return [ALL_TOOLS[d.metadata[\"index\"]] for d in docs]"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "7699afd7",
-   "metadata": {},
-   "source": [
-    "We can now test this retriever to see if it seems to work."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 19,
-   "id": "425f2886",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[Tool(name='Search', description='useful for when you need to answer questions about current events', return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x114b28a90>, func=<bound method SerpAPIWrapper.run of SerpAPIWrapper(search_engine=<class 'serpapi.google_search.GoogleSearch'>, params={'engine': 'google', 'google_domain': 'google.com', 'gl': 'us', 'hl': 'en'}, serpapi_api_key='', aiosession=None)>, coroutine=None),\n",
-       " Tool(name='foo-95', description='a silly function that you can use to get more information about the number 95', return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x114b28a90>, func=<function fake_func at 0x15e5bd1f0>, coroutine=None),\n",
-       " Tool(name='foo-12', description='a silly function that you can use to get more information about the number 12', return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x114b28a90>, func=<function fake_func at 0x15e5bd1f0>, coroutine=None),\n",
-       " Tool(name='foo-15', description='a silly function that you can use to get more information about the number 15', return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x114b28a90>, func=<function fake_func at 0x15e5bd1f0>, coroutine=None)]"
-      ]
-     },
-     "execution_count": 19,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "get_tools(\"whats the weather?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 20,
-   "id": "4036dd19",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[Tool(name='foo-13', description='a silly function that you can use to get more information about the number 13', return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x114b28a90>, func=<function fake_func at 0x15e5bd1f0>, coroutine=None),\n",
-       " Tool(name='foo-12', description='a silly function that you can use to get more information about the number 12', return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x114b28a90>, func=<function fake_func at 0x15e5bd1f0>, coroutine=None),\n",
-       " Tool(name='foo-14', description='a silly function that you can use to get more information about the number 14', return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x114b28a90>, func=<function fake_func at 0x15e5bd1f0>, coroutine=None),\n",
-       " Tool(name='foo-11', description='a silly function that you can use to get more information about the number 11', return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x114b28a90>, func=<function fake_func at 0x15e5bd1f0>, coroutine=None)]"
-      ]
-     },
-     "execution_count": 20,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "get_tools(\"whats the number 13?\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2e7a075c",
-   "metadata": {},
-   "source": [
-    "## Prompt template\n",
-    "\n",
-    "The prompt template is pretty standard, because we're not actually changing that much logic in the actual prompt template, but rather we are just changing how retrieval is done."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 21,
-   "id": "339b1bb8",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Set up the base template\n",
-    "template = \"\"\"Answer the following questions as best you can, but speaking as a pirate might speak. You have access to the following tools:\n",
-    "\n",
-    "{tools}\n",
-    "\n",
-    "Use the following format:\n",
-    "\n",
-    "Question: the input question you must answer\n",
-    "Thought: you should always think about what to do\n",
-    "Action: the action to take, should be one of [{tool_names}]\n",
-    "Action Input: the input to the action\n",
-    "Observation: the result of the action\n",
-    "... (this Thought/Action/Action Input/Observation can repeat N times)\n",
-    "Thought: I now know the final answer\n",
-    "Final Answer: the final answer to the original input question\n",
-    "\n",
-    "Begin! Remember to speak as a pirate when giving your final answer. Use lots of \"Arg\"s\n",
-    "\n",
-    "Question: {input}\n",
-    "{agent_scratchpad}\"\"\""
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "1583acdc",
-   "metadata": {},
-   "source": [
-    "The custom prompt template now has the concept of a `tools_getter`, which we call on the input to select the tools to use."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 52,
-   "id": "fd969d31",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from typing import Callable\n",
-    "\n",
-    "\n",
-    "# Set up a prompt template\n",
-    "class CustomPromptTemplate(StringPromptTemplate):\n",
-    "    # The template to use\n",
-    "    template: str\n",
-    "    ############## NEW ######################\n",
-    "    # The list of tools available\n",
-    "    tools_getter: Callable\n",
-    "\n",
-    "    def format(self, **kwargs) -> str:\n",
-    "        # Get the intermediate steps (AgentAction, Observation tuples)\n",
-    "        # Format them in a particular way\n",
-    "        intermediate_steps = kwargs.pop(\"intermediate_steps\")\n",
-    "        thoughts = \"\"\n",
-    "        for action, observation in intermediate_steps:\n",
-    "            thoughts += action.log\n",
-    "            thoughts += f\"\\nObservation: {observation}\\nThought: \"\n",
-    "        # Set the agent_scratchpad variable to that value\n",
-    "        kwargs[\"agent_scratchpad\"] = thoughts\n",
-    "        ############## NEW ######################\n",
-    "        tools = self.tools_getter(kwargs[\"input\"])\n",
-    "        # Create a tools variable from the list of tools provided\n",
-    "        kwargs[\"tools\"] = \"\\n\".join(\n",
-    "            [f\"{tool.name}: {tool.description}\" for tool in tools]\n",
-    "        )\n",
-    "        # Create a list of tool names for the tools provided\n",
-    "        kwargs[\"tool_names\"] = \", \".join([tool.name for tool in tools])\n",
-    "        return self.template.format(**kwargs)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 53,
-   "id": "798ef9fb",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "prompt = CustomPromptTemplate(\n",
-    "    template=template,\n",
-    "    tools_getter=get_tools,\n",
-    "    # This omits the `agent_scratchpad`, `tools`, and `tool_names` variables because those are generated dynamically\n",
-    "    # This includes the `intermediate_steps` variable because that is needed\n",
-    "    input_variables=[\"input\", \"intermediate_steps\"],\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "ef3a1af3",
-   "metadata": {},
-   "source": [
-    "## Output parser\n",
-    "\n",
-    "The output parser is unchanged from the previous notebook, since we are not changing anything about the output format."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 54,
-   "id": "7c6fe0d3",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "class CustomOutputParser(AgentOutputParser):\n",
-    "    def parse(self, llm_output: str) -> Union[AgentAction, AgentFinish]:\n",
-    "        # Check if agent should finish\n",
-    "        if \"Final Answer:\" in llm_output:\n",
-    "            return AgentFinish(\n",
-    "                # Return values is generally always a dictionary with a single `output` key\n",
-    "                # It is not recommended to try anything else at the moment :)\n",
-    "                return_values={\"output\": llm_output.split(\"Final Answer:\")[-1].strip()},\n",
-    "                log=llm_output,\n",
-    "            )\n",
-    "        # Parse out the action and action input\n",
-    "        regex = r\"Action\\s*\\d*\\s*:(.*?)\\nAction\\s*\\d*\\s*Input\\s*\\d*\\s*:[\\s]*(.*)\"\n",
-    "        match = re.search(regex, llm_output, re.DOTALL)\n",
-    "        if not match:\n",
-    "            raise ValueError(f\"Could not parse LLM output: `{llm_output}`\")\n",
-    "        action = match.group(1).strip()\n",
-    "        action_input = match.group(2)\n",
-    "        # Return the action and action input\n",
-    "        return AgentAction(\n",
-    "            tool=action, tool_input=action_input.strip(\" \").strip('\"'), log=llm_output\n",
-    "        )"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 55,
-   "id": "d278706a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "output_parser = CustomOutputParser()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "170587b1",
-   "metadata": {},
-   "source": [
-    "## Set up LLM, stop sequence, and the agent\n",
-    "\n",
-    "Also the same as the previous notebook."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 56,
-   "id": "f9d4c374",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm = OpenAI(temperature=0)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 57,
-   "id": "9b1cc2a2",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# LLM chain consisting of the LLM and a prompt\n",
-    "llm_chain = LLMChain(llm=llm, prompt=prompt)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 58,
-   "id": "e4f5092f",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "tools = get_tools(\"whats the weather?\")\n",
-    "tool_names = [tool.name for tool in tools]\n",
-    "agent = LLMSingleActionAgent(\n",
-    "    llm_chain=llm_chain,\n",
-    "    output_parser=output_parser,\n",
-    "    stop=[\"\\nObservation:\"],\n",
-    "    allowed_tools=tool_names,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "aa8a5326",
-   "metadata": {},
-   "source": [
-    "## Use the Agent\n",
-    "\n",
-    "Now we can use it!"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 59,
-   "id": "490604e9",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "agent_executor = AgentExecutor.from_agent_and_tools(\n",
-    "    agent=agent, tools=tools, verbose=True\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 60,
-   "id": "653b1617",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mThought: I need to find out what the weather is in SF\n",
-      "Action: Search\n",
-      "Action Input: Weather in SF\u001b[0m\n",
-      "\n",
-      "Observation:\u001b[36;1m\u001b[1;3mMostly cloudy skies early, then partly cloudy in the afternoon. High near 60F. ENE winds shifting to W at 10 to 15 mph. Humidity71%. UV Index6 of 10.\u001b[0m\u001b[32;1m\u001b[1;3m I now know the final answer\n",
-      "Final Answer: 'Arg, 'tis mostly cloudy skies early, then partly cloudy in the afternoon. High near 60F. ENE winds shiftin' to W at 10 to 15 mph. Humidity71%. UV Index6 of 10.\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "\"'Arg, 'tis mostly cloudy skies early, then partly cloudy in the afternoon. High near 60F. ENE winds shiftin' to W at 10 to 15 mph. Humidity71%. UV Index6 of 10.\""
-      ]
-     },
-     "execution_count": 60,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "agent_executor.run(\"What's the weather in SF?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "2481ee76",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.10.1"
-  },
-  "vscode": {
-   "interpreter": {
-    "hash": "18784188d7ecd866c0586ac068b02361a6896dc3a29b64f5cc957f09c590acef"
-   }
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

cookbook/custom_multi_action_agent.ipynb

@@ -1,220 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "ba5f8741",
-   "metadata": {},
-   "source": [
-    "# Custom multi-action agent\n",
-    "\n",
-    "This notebook goes through how to create your own custom agent.\n",
-    "\n",
-    "An agent consists of two parts:\n",
-    "\n",
-    "- Tools: The tools the agent has available to use.\n",
-    "- The agent class itself: this decides which action to take.\n",
-    "        \n",
-    "        \n",
-    "In this notebook we walk through how to create a custom agent that predicts/takes multiple steps at a time."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "9af9734e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.agents import AgentExecutor, BaseMultiActionAgent, Tool\n",
-    "from langchain_community.utilities import SerpAPIWrapper"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "d7c4ebdc",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def random_word(query: str) -> str:\n",
-    "    print(\"\\nNow I'm doing this!\")\n",
-    "    return \"foo\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "becda2a1",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "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=\"RandomWord\",\n",
-    "        func=random_word,\n",
-    "        description=\"call this to get a random word.\",\n",
-    "    ),\n",
-    "]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "a33e2f7e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from typing import Any, List, Tuple, Union\n",
-    "\n",
-    "from langchain_core.agents import AgentAction, AgentFinish\n",
-    "\n",
-    "\n",
-    "class FakeAgent(BaseMultiActionAgent):\n",
-    "    \"\"\"Fake Custom Agent.\"\"\"\n",
-    "\n",
-    "    @property\n",
-    "    def input_keys(self):\n",
-    "        return [\"input\"]\n",
-    "\n",
-    "    def plan(\n",
-    "        self, intermediate_steps: List[Tuple[AgentAction, str]], **kwargs: Any\n",
-    "    ) -> Union[List[AgentAction], AgentFinish]:\n",
-    "        \"\"\"Given input, decided what to do.\n",
-    "\n",
-    "        Args:\n",
-    "            intermediate_steps: Steps the LLM has taken to date,\n",
-    "                along with observations\n",
-    "            **kwargs: User inputs.\n",
-    "\n",
-    "        Returns:\n",
-    "            Action specifying what tool to use.\n",
-    "        \"\"\"\n",
-    "        if len(intermediate_steps) == 0:\n",
-    "            return [\n",
-    "                AgentAction(tool=\"Search\", tool_input=kwargs[\"input\"], log=\"\"),\n",
-    "                AgentAction(tool=\"RandomWord\", tool_input=kwargs[\"input\"], log=\"\"),\n",
-    "            ]\n",
-    "        else:\n",
-    "            return AgentFinish(return_values={\"output\": \"bar\"}, log=\"\")\n",
-    "\n",
-    "    async def aplan(\n",
-    "        self, intermediate_steps: List[Tuple[AgentAction, str]], **kwargs: Any\n",
-    "    ) -> Union[List[AgentAction], AgentFinish]:\n",
-    "        \"\"\"Given input, decided what to do.\n",
-    "\n",
-    "        Args:\n",
-    "            intermediate_steps: Steps the LLM has taken to date,\n",
-    "                along with observations\n",
-    "            **kwargs: User inputs.\n",
-    "\n",
-    "        Returns:\n",
-    "            Action specifying what tool to use.\n",
-    "        \"\"\"\n",
-    "        if len(intermediate_steps) == 0:\n",
-    "            return [\n",
-    "                AgentAction(tool=\"Search\", tool_input=kwargs[\"input\"], log=\"\"),\n",
-    "                AgentAction(tool=\"RandomWord\", tool_input=kwargs[\"input\"], log=\"\"),\n",
-    "            ]\n",
-    "        else:\n",
-    "            return AgentFinish(return_values={\"output\": \"bar\"}, log=\"\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "655d72f6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "agent = FakeAgent()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "490604e9",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "agent_executor = AgentExecutor.from_agent_and_tools(\n",
-    "    agent=agent, tools=tools, verbose=True\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "653b1617",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3m\u001b[0m\u001b[36;1m\u001b[1;3mThe current population of Canada is 38,669,152 as of Monday, April 24, 2023, based on Worldometer elaboration of the latest United Nations data.\u001b[0m\u001b[32;1m\u001b[1;3m\u001b[0m\n",
-      "Now I'm doing this!\n",
-      "\u001b[33;1m\u001b[1;3mfoo\u001b[0m\u001b[32;1m\u001b[1;3m\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'bar'"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "agent_executor.run(\"How many people live in canada as of 2023?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "adefb4c2",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.3"
-  },
-  "vscode": {
-   "interpreter": {
-    "hash": "18784188d7ecd866c0586ac068b02361a6896dc3a29b64f5cc957f09c590acef"
-   }
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

cookbook/deeplake_semantic_search_over_chat.ipynb

@@ -1,255 +0,0 @@
-{
- "cells": [
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# QA using Activeloop's DeepLake\n",
-    "In this tutorial, we are going to use Langchain + Activeloop's Deep Lake with GPT4 to semantically search and ask questions over a group chat.\n",
-    "\n",
-    "View a working demo [here](https://twitter.com/thisissukh_/status/1647223328363679745)"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 1. Install required packages"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!python3 -m pip install --upgrade langchain 'deeplake[enterprise]' openai tiktoken"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 2. Add API keys"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "from langchain.chains import RetrievalQA\n",
-    "from langchain_community.vectorstores import DeepLake\n",
-    "from langchain_openai import OpenAI, OpenAIEmbeddings\n",
-    "from langchain_text_splitters import (\n",
-    "    CharacterTextSplitter,\n",
-    "    RecursiveCharacterTextSplitter,\n",
-    ")\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
-    "activeloop_token = getpass.getpass(\"Activeloop Token:\")\n",
-    "os.environ[\"ACTIVELOOP_TOKEN\"] = activeloop_token\n",
-    "os.environ[\"ACTIVELOOP_ORG\"] = getpass.getpass(\"Activeloop Org:\")\n",
-    "\n",
-    "org_id = os.environ[\"ACTIVELOOP_ORG\"]\n",
-    "embeddings = OpenAIEmbeddings()\n",
-    "\n",
-    "dataset_path = \"hub://\" + org_id + \"/data\""
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "\n",
-    "\n",
-    "## 2. Create sample data"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "You can generate a sample group chat conversation using ChatGPT with this prompt:\n",
-    "\n",
-    "```\n",
-    "Generate a group chat conversation with three friends talking about their day, referencing real places and fictional names. Make it funny and as detailed as possible.\n",
-    "```\n",
-    "\n",
-    "I've already generated such a chat in `messages.txt`. We can keep it simple and use this for our example.\n",
-    "\n",
-    "## 3. Ingest chat embeddings\n",
-    "\n",
-    "We load the messages in the text file, chunk and upload to ActiveLoop Vector store."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[Document(page_content='Participants:\\n\\nJerry: Loves movies and is a bit of a klutz.\\nSamantha: Enthusiastic about food and always trying new restaurants.\\nBarry: A nature lover, but always manages to get lost.\\nJerry: Hey, guys! You won\\'t believe what happened to me at the Times Square AMC theater. I tripped over my own feet and spilled popcorn everywhere! 🍿💥\\n\\nSamantha: LOL, that\\'s so you, Jerry! Was the floor buttery enough for you to ice skate on after that? 😂\\n\\nBarry: Sounds like a regular Tuesday for you, Jerry. Meanwhile, I tried to find that new hiking trail in Central Park. You know, the one that\\'s supposed to be impossible to get lost on? Well, guess what...\\n\\nJerry: You found a hidden treasure?\\n\\nBarry: No, I got lost. AGAIN. 🧭🙄\\n\\nSamantha: Barry, you\\'d get lost in your own backyard! But speaking of treasures, I found this new sushi place in Little Tokyo. \"Samantha\\'s Sushi Symphony\" it\\'s called. Coincidence? I think not!\\n\\nJerry: Maybe they named it after your ability to eat your body weight in sushi. 🍣', metadata={}), Document(page_content='Barry: How do you even FIND all these places, Samantha?\\n\\nSamantha: Simple, I don\\'t rely on Barry\\'s navigation skills. 😉 But seriously, the wasabi there was hotter than Jerry\\'s love for Marvel movies!\\n\\nJerry: Hey, nothing wrong with a little superhero action. By the way, did you guys see the new \"Captain Crunch: Breakfast Avenger\" trailer?\\n\\nSamantha: Captain Crunch? Are you sure you didn\\'t get that from one of your Saturday morning cereal binges?\\n\\nBarry: Yeah, and did he defeat his arch-enemy, General Mills? 😆\\n\\nJerry: Ha-ha, very funny. Anyway, that sushi place sounds awesome, Samantha. Next time, let\\'s go together, and maybe Barry can guide us... if we want a city-wide tour first.\\n\\nBarry: As long as we\\'re not hiking, I\\'ll get us there... eventually. 😅\\n\\nSamantha: It\\'s a date! But Jerry, you\\'re banned from carrying any food items.\\n\\nJerry: Deal! Just promise me no wasabi challenges. I don\\'t want to end up like the time I tried Sriracha ice cream.', metadata={}), Document(page_content=\"Barry: Wait, what happened with Sriracha ice cream?\\n\\nJerry: Let's just say it was a hot situation. Literally. 🔥\\n\\nSamantha: 🤣 I still have the video!\\n\\nJerry: Samantha, if you value our friendship, that video will never see the light of day.\\n\\nSamantha: No promises, Jerry. No promises. 🤐😈\\n\\nBarry: I foresee a fun weekend ahead! 🎉\", metadata={})]\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Your Deep Lake dataset has been successfully created!\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\\"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Dataset(path='hub://adilkhan/data', tensors=['embedding', 'id', 'metadata', 'text'])\n",
-      "\n",
-      "  tensor      htype      shape     dtype  compression\n",
-      "  -------    -------    -------   -------  ------- \n",
-      " embedding  embedding  (3, 1536)  float32   None   \n",
-      "    id        text      (3, 1)      str     None   \n",
-      " metadata     json      (3, 1)      str     None   \n",
-      "   text       text      (3, 1)      str     None   \n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      " \r"
-     ]
-    }
-   ],
-   "source": [
-    "with open(\"messages.txt\") as f:\n",
-    "    state_of_the_union = f.read()\n",
-    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
-    "pages = text_splitter.split_text(state_of_the_union)\n",
-    "\n",
-    "text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)\n",
-    "texts = text_splitter.create_documents(pages)\n",
-    "\n",
-    "print(texts)\n",
-    "\n",
-    "dataset_path = \"hub://\" + org_id + \"/data\"\n",
-    "embeddings = OpenAIEmbeddings()\n",
-    "db = DeepLake.from_documents(\n",
-    "    texts, embeddings, dataset_path=dataset_path, overwrite=True\n",
-    ")"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "`Optional`: You can also use Deep Lake's Managed Tensor Database as a hosting service and run queries there. In order to do so, it is necessary to specify the runtime parameter as {'tensor_db': True} during the creation of the vector store. This configuration enables the execution of queries on the Managed Tensor Database, rather than on the client side. It should be noted that this functionality is not applicable to datasets stored locally or in-memory. In the event that a vector store has already been created outside of the Managed Tensor Database, it is possible to transfer it to the Managed Tensor Database by following the prescribed steps."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# with open(\"messages.txt\") as f:\n",
-    "#     state_of_the_union = f.read()\n",
-    "# text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
-    "# pages = text_splitter.split_text(state_of_the_union)\n",
-    "\n",
-    "# text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)\n",
-    "# texts = text_splitter.create_documents(pages)\n",
-    "\n",
-    "# print(texts)\n",
-    "\n",
-    "# dataset_path = \"hub://\" + org + \"/data\"\n",
-    "# embeddings = OpenAIEmbeddings()\n",
-    "# db = DeepLake.from_documents(\n",
-    "#     texts, embeddings, dataset_path=dataset_path, overwrite=True, runtime={\"tensor_db\": True}\n",
-    "# )"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 4. Ask questions\n",
-    "\n",
-    "Now we can ask a question and get an answer back with a semantic search:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "db = DeepLake(dataset_path=dataset_path, read_only=True, embedding=embeddings)\n",
-    "\n",
-    "retriever = db.as_retriever()\n",
-    "retriever.search_kwargs[\"distance_metric\"] = \"cos\"\n",
-    "retriever.search_kwargs[\"k\"] = 4\n",
-    "\n",
-    "qa = RetrievalQA.from_chain_type(\n",
-    "    llm=OpenAI(), chain_type=\"stuff\", retriever=retriever, return_source_documents=False\n",
-    ")\n",
-    "\n",
-    "# What was the restaurant the group was talking about called?\n",
-    "query = input(\"Enter query:\")\n",
-    "\n",
-    "# The Hungry Lobster\n",
-    "ans = qa({\"query\": query})\n",
-    "\n",
-    "print(ans)"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.10.12"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}