RAG from scrath video series

.devcontainer/README.md

@@ -10,7 +10,7 @@ You can use the dev container configuration in this folder to build and run the
 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 on the **Codespaces** tab.
-1. Click **Create codespace on master**.
+1. Click **Create codespace on master** .
 
 For more info, check out the [GitHub documentation](https://docs.github.com/en/free-pro-team@latest/github/developing-online-with-codespaces/creating-a-codespace#creating-a-codespace).
   

.devcontainer/devcontainer.json

@@ -12,7 +12,7 @@
 
 	// 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",
+	"workspaceFolder": "/workspaces/${localWorkspaceFolderBasename}",
 
 	// Prevent the container from shutting down
 	"overrideCommand": true

.devcontainer/docker-compose.yaml

@@ -5,10 +5,10 @@ services:
       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
+   # Update this to wherever you want VS Code to mount the folder of your project
+      - ..:/workspaces:cached
     networks:
-      - langchain-network
+      - langchain-network 
   #   environment:
   #     MONGO_ROOT_USERNAME: root
   #     MONGO_ROOT_PASSWORD: example123
@@ -28,3 +28,5 @@ services:
 networks:
   langchain-network:
     driver: bridge
+    
+    

.github/CONTRIBUTING.md

@@ -3,4 +3,43 @@
 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/).
+To learn about how to contribute, please follow the [guides here](https://python.langchain.com/docs/contributing/)
+
+## 🗺️ Guidelines
+
+### 👩‍💻 Ways to contribute
+
+There are many ways to contribute to LangChain. Here are some common ways people contribute:
+
+- [**Documentation**](https://python.langchain.com/docs/contributing/documentation): Help improve our docs, including this one!
+- [**Code**](https://python.langchain.com/docs/contributing/code): Help us write code, fix bugs, or improve our infrastructure.
+- [**Integrations**](https://python.langchain.com/docs/contributing/integration): Help us integrate with your favorite vendors and tools.
+
+### 🚩GitHub Issues
+
+Our [issues](https://github.com/langchain-ai/langchain/issues) page is kept up to date with bugs, improvements, and feature requests.
+
+There is a taxonomy of labels to help with sorting and discovery of issues of interest. Please use these to help organize issues.
+
+If you start working on an issue, please assign it to yourself.
+
+If you are adding an issue, please try to keep it focused on a single, modular bug/improvement/feature.
+If two issues are related, or blocking, please link them rather than combining them.
+
+We will try to keep these issues as up-to-date as possible, though
+with the rapid rate of development in this field some may get out of date.
+If you notice this happening, please let us know.
+
+### 🙋Getting Help
+
+Our goal is to have the simplest developer setup possible. Should you experience any difficulty getting setup, please
+contact a maintainer! Not only do we want to help get you unblocked, but we also want to make sure that the process is
+smooth for future contributors.
+
+In a similar vein, we do enforce certain linting, formatting, and documentation standards in the codebase.
+If you are finding these difficult (or even just annoying) to work with, feel free to contact a maintainer for help -
+we do not want these to get in the way of getting good code into the codebase.
+
+### Contributor Documentation
+
+To learn about how to contribute, please follow the [guides here](https://python.langchain.com/docs/contributing/)

.github/DISCUSSION_TEMPLATE/ideas.yml

@@ -1,38 +0,0 @@
-labels: [idea]
-body:
-  - type: checkboxes
-    id: checks
-    attributes:
-      label: Checked
-      description: Please confirm and check all the following options.
-      options:
-        - label: I searched existing ideas and did not find a similar one
-          required: true
-        - label: I added a very descriptive title
-          required: true
-        - label: I've clearly described the feature request and motivation for it
-          required: true
-  - type: textarea
-    id: feature-request
-    validations:
-      required: true
-    attributes:
-      label: Feature request
-      description: |
-        A clear and concise description of the feature proposal. Please provide links to any relevant GitHub repos, papers, or other resources if relevant.
-  - type: textarea
-    id: motivation
-    validations:
-      required: true
-    attributes:
-      label: Motivation
-      description: |
-        Please outline the motivation for the proposal. Is your feature request related to a problem? e.g., I'm always frustrated when [...]. If this is related to another GitHub issue, please link here too.
-  - type: textarea
-    id: proposal
-    validations:
-      required: false
-    attributes:
-      label: Proposal (If applicable)
-      description: |
-        If you would like to propose a solution, please describe it here. 

.github/DISCUSSION_TEMPLATE/q-a.yml

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

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -1,5 +1,5 @@
 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 GitHub Discussions.
+description: Submit a bug report to help us improve LangChain. To report a security issue, please instead use the security option below.
 labels: ["02 Bug Report"]
 body:
   - type: markdown
@@ -7,11 +7,6 @@ body:
       value: >
         Thank you for taking the time to file a bug report. 
         
-        Use this to report bugs in LangChain. 
-        
-        If you're not certain that your issue is due to a bug in LangChain, please use [GitHub Discussions](https://github.com/langchain-ai/langchain/discussions)
-        to ask for help with your issue.
-        
         Relevant links to check before filing a bug report to see if your issue has already been reported, fixed or
         if there's another way to solve your problem:
         
@@ -19,8 +14,7 @@ body:
         [API Reference](https://api.python.langchain.com/en/stable/),
         [GitHub search](https://github.com/langchain-ai/langchain),
         [LangChain Github Discussions](https://github.com/langchain-ai/langchain/discussions),
-        [LangChain Github Issues](https://github.com/langchain-ai/langchain/issues?q=is%3Aissue),
-        [LangChain ChatBot](https://chat.langchain.com/)
+        [LangChain Github Issues](https://github.com/langchain-ai/langchain/issues?q=is%3Aissue)
   - type: checkboxes
     id: checks
     attributes:
@@ -33,10 +27,6 @@ body:
           required: true
         - label: I used the GitHub search to find a similar question and didn't find it.
           required: true
-        - label: I am sure that this is a bug in LangChain rather than my code.
-          required: true
-        - label: The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).
-          required: true
   - type: textarea
     id: reproduction
     validations:
@@ -48,12 +38,10 @@ 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!** 
+        If you're including an error message, please include the full stack trace not just the last error.
         
-        * Use code tags (e.g., ```python ... ```) to correctly [format your code](https://help.github.com/en/github/writing-on-github/creating-and-highlighting-code-blocks#syntax-highlighting).
-        * INCLUDE the language label (e.g. `python`) after the first three backticks to enable syntax highlighting. (e.g., ```python rather than ```).
-        * Reduce your code to the minimum required to reproduce the issue if possible. This makes it much easier for others to help you.
-        * Avoid screenshots when possible, as they are hard to read and (more importantly) don't allow others to copy-and-paste your code.
+        **Important!** Use code tags to correctly format your code. See https://help.github.com/en/github/writing-on-github/creating-and-highlighting-code-blocks#syntax-highlighting
+        Avoid screenshots when possible, as they are hard to read and (more importantly) don't allow others to copy-and-paste your code.
 
       placeholder: |
         The following code: 
@@ -67,16 +55,9 @@ body:
           chain = RunnableLambda(bad_code)
           chain.invoke('Hello!')
         ```
-  - type: textarea
-    id: error
-    validations:
-      required: false
-    attributes:
-      label: Error Message and Stack Trace (if applicable)
-      description: |
-        If you are reporting an error, please include the full error message and stack trace.
-      placeholder: |
-        Exception + full stack trace
+        
+        Include both the error and the full stack trace if reporting an exception!
+
   - type: textarea
     id: description
     attributes:
@@ -95,26 +76,28 @@ body:
     id: system-info
     attributes:
       label: System Info
-      description: |
-        Please share your system info with us. 
-        
-        "pip freeze | grep langchain" 
-        platform (windows / linux / mac)
-        python version
-        
-        OR if you're on a recent version of langchain-core you can paste the output of:
-        
-        python -m langchain_core.sys_info
+      description: Please share your system info with us.
       placeholder: |
         "pip freeze | grep langchain"
         platform
         python version
-        
-        Alternatively, if you're on a recent version of langchain-core you can paste the output of:
-        
-        python -m langchain_core.sys_info
-        
-        These will only surface LangChain packages, don't forget to include any other relevant
-        packages you're using (if you're not sure what's relevant, you can paste the entire output of `pip freeze`).
     validations:
       required: true
+  - type: checkboxes
+    id: related-components
+    attributes:
+      label: Related Components
+      description: "Select the components related to the issue (if applicable):"
+      options:
+        - label: "LLMs/Chat Models"
+        - label: "Embedding Models"
+        - label: "Prompts / Prompt Templates / Prompt Selectors"
+        - label: "Output Parsers"
+        - label: "Document Loaders"
+        - label: "Vector Stores / Retrievers"
+        - label: "Memory"
+        - label: "Agents / Agent Executors"
+        - label: "Tools / Toolkits"
+        - label: "Chains"
+        - label: "Callbacks/Tracing"
+        - label: "Async"

.github/ISSUE_TEMPLATE/config.yml

@@ -4,9 +4,9 @@ contact_links:
   - name: 🤔 Question or Problem
     about: Ask a question or ask about a problem in GitHub Discussions.
     url: https://www.github.com/langchain-ai/langchain/discussions/categories/q-a
-  - name: Feature Request
-    url: https://www.github.com/langchain-ai/langchain/discussions/categories/ideas
-    about: Suggest a feature or an idea
+  - name: Discord
+    url: https://discord.gg/6adMQxSpJS
+    about: General community discussions
   - name: Show and tell
     about: Show what you built with LangChain
     url: https://www.github.com/langchain-ai/langchain/discussions/categories/show-and-tell

.github/ISSUE_TEMPLATE/documentation.yml

@@ -4,55 +4,16 @@ title: "DOC: <Please write a comprehensive title after the 'DOC: ' prefix>"
 labels: [03 - Documentation]
 
 body:
-- type: markdown
-  attributes:
-    value: >
-      Thank you for taking the time to report an issue in the documentation.
-      
-      Only report issues with documentation here, explain if there are
-      any missing topics or if you found a mistake in the documentation.
-      
-      Do **NOT** use this to ask usage questions or reporting issues with your code.
-      
-      If you have usage questions or need help solving some problem, 
-      please use [GitHub Discussions](https://github.com/langchain-ai/langchain/discussions).
-      
-      If you're in the wrong place, here are some helpful links to find a better
-      place to ask your question:
-      
-      [LangChain documentation with the integrated search](https://python.langchain.com/docs/get_started/introduction),
-      [API Reference](https://api.python.langchain.com/en/stable/),
-      [GitHub search](https://github.com/langchain-ai/langchain),
-      [LangChain Github Discussions](https://github.com/langchain-ai/langchain/discussions),
-      [LangChain Github Issues](https://github.com/langchain-ai/langchain/issues?q=is%3Aissue),
-      [LangChain ChatBot](https://chat.langchain.com/)
-- type: 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.
+      referring to.
+
 - type: textarea
   attributes:
     label: "Idea or request for content:"
     description: >
       Please describe as clearly as possible what topics you think are missing
-      from the current documentation.
+      from the current documentation.

.github/ISSUE_TEMPLATE/feature-request.yml

@@ -0,0 +1,30 @@
+name: "\U0001F680 Feature request"
+description: Submit a proposal/request for a new LangChain feature
+labels: ["02 Feature Request"]
+body:
+  - type: textarea
+    id: feature-request
+    validations:
+      required: true
+    attributes:
+      label: Feature request
+      description: |
+        A clear and concise description of the feature proposal. Please provide links to any relevant GitHub repos, papers, or other resources if relevant.
+
+  - type: textarea
+    id: motivation
+    validations:
+      required: true
+    attributes:
+      label: Motivation
+      description: |
+        Please outline the motivation for the proposal. Is your feature request related to a problem? e.g., I'm always frustrated when [...]. If this is related to another GitHub issue, please link here too.
+
+  - type: textarea
+    id: contribution
+    validations:
+      required: true
+    attributes:
+      label: Your contribution
+      description: |
+        Is there any way that you could help, e.g. by submitting a PR? Make sure to read the [Contributing Guide](https://python.langchain.com/docs/contributing/)

.github/ISSUE_TEMPLATE/privileged.yml

@@ -9,7 +9,7 @@ body:
         If you are not a LangChain maintainer or were not asked directly by a maintainer to create an issue, then please start the conversation in a [Question in GitHub Discussions](https://github.com/langchain-ai/langchain/discussions/categories/q-a) instead.
         
         You are a LangChain maintainer if you maintain any of the packages inside of the LangChain repository 
-        or are a regular contributor to LangChain with previous merged pull requests.
+        or are a regular contributor to LangChain with previous merged merged pull requests.
   - type: checkboxes
     id: privileged
     attributes:

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,29 +1,20 @@
-Thank you for contributing to LangChain!
+<!-- Thank you for contributing to LangChain!
 
-- [ ] **PR title**: "package: description"
-  - Where "package" is whichever of langchain, community, core, experimental, etc. is being modified. Use "docs: ..." for purely docs changes, "templates: ..." for template changes, "infra: ..." for CI changes.
-  - Example: "community: add foobar LLM"
+Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified.
 
+Replace this entire comment with:
+  - **Description:** a description of the change, 
+  - **Issue:** the issue # it fixes if applicable,
+  - **Dependencies:** any dependencies required for this change,
+  - **Twitter handle:** we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out!
 
-- [ ] **PR message**: ***Delete this entire checklist*** and replace with
-    - **Description:** a description of the change
-    - **Issue:** the issue # it fixes, if applicable
-    - **Dependencies:** any dependencies required for this change
-    - **Twitter handle:** if your PR gets announced, and you'd like a mention, we'll gladly shout you out!
+Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally.
 
+See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/
 
-- [ ] **Add tests and docs**: If you're adding a new integration, please include
+If you're adding a new integration, please include:
   1. a test for the integration, preferably unit tests that do not rely on network access,
   2. an example notebook showing its use. It lives in `docs/docs/integrations` directory.
 
-
-- [ ] **Lint and test**: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. See contribution guidelines for more: https://python.langchain.com/docs/contributing/
-
-Additional guidelines:
-- Make sure optional dependencies are imported within a function.
-- Please do not add dependencies to pyproject.toml files (even optional ones) unless they are required for unit tests.
-- Most PRs should not touch more than one package.
-- Changes should be backwards compatible.
-- If you are adding something to community, do not re-import it in langchain.
-
-If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
+If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17.
+ -->

.github/actions/people/Dockerfile

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

.github/actions/people/action.yml

@@ -1,11 +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/poetry_setup/action.yml

@@ -32,7 +32,7 @@ runs:
       with:
         python-version: ${{ inputs.python-version }}
 
-    - uses: actions/cache@v4
+    - uses: actions/cache@v3
       id: cache-bin-poetry
       name: Cache Poetry binary - Python ${{ inputs.python-version }}
       env:
@@ -79,7 +79,7 @@ runs:
       run: pipx install "poetry==$POETRY_VERSION" --python '${{ steps.setup-python.outputs.python-path }}' --verbose
 
     - name: Restore pip and poetry cached dependencies
-      uses: actions/cache@v4
+      uses: actions/cache@v3
       env:
         SEGMENT_DOWNLOAD_TIMEOUT_MIN: "4"
         WORKDIR: ${{ inputs.working-directory == '' && '.' || inputs.working-directory }}

.github/scripts/check_diff.py

@@ -1,170 +1,22 @@
-import glob
 import json
-import os
 import sys
-import tomllib
-from collections import defaultdict
-from typing import Dict, List, Set
-from pathlib import Path
+import os
 
-
-LANGCHAIN_DIRS = [
+LANGCHAIN_DIRS = {
     "libs/core",
-    "libs/text-splitters",
     "libs/langchain",
-    "libs/community",
     "libs/experimental",
-]
-
-# ignored partners are removed from dependents
-# but still run if directly edited
-IGNORED_PARTNERS = [
-    # remove huggingface from dependents because of CI instability
-    # specifically in huggingface jobs
-    # https://github.com/langchain-ai/langchain/issues/25558
-    "huggingface",
-]
-
-
-def all_package_dirs() -> Set[str]:
-    return {
-        "/".join(path.split("/")[:-1]).lstrip("./")
-        for path in glob.glob("./libs/**/pyproject.toml", recursive=True)
-        if "libs/cli" not in path and "libs/standard-tests" not in path
-    }
-
-
-def dependents_graph() -> dict:
-    """
-    Construct a mapping of package -> dependents, such that we can
-    run tests on all dependents of a package when a change is made.
-    """
-    dependents = defaultdict(set)
-
-    for path in glob.glob("./libs/**/pyproject.toml", recursive=True):
-        if "template" in path:
-            continue
-
-        # load regular and test deps from pyproject.toml
-        with open(path, "rb") as f:
-            pyproject = tomllib.load(f)["tool"]["poetry"]
-
-        pkg_dir = "libs" + "/".join(path.split("libs")[1].split("/")[:-1])
-        for dep in [
-            *pyproject["dependencies"].keys(),
-            *pyproject["group"]["test"]["dependencies"].keys(),
-        ]:
-            if "langchain" in dep:
-                dependents[dep].add(pkg_dir)
-                continue
-
-        # load extended deps from extended_testing_deps.txt
-        package_path = Path(path).parent
-        extended_requirement_path = package_path / "extended_testing_deps.txt"
-        if extended_requirement_path.exists():
-            with open(extended_requirement_path, "r") as f:
-                extended_deps = f.read().splitlines()
-                for depline in extended_deps:
-                    if depline.startswith("-e "):
-                        # editable dependency
-                        assert depline.startswith(
-                            "-e ../partners/"
-                        ), "Extended test deps should only editable install partner packages"
-                        partner = depline.split("partners/")[1]
-                        dep = f"langchain-{partner}"
-                    else:
-                        dep = depline.split("==")[0]
-
-                    if "langchain" in dep:
-                        dependents[dep].add(pkg_dir)
-
-    for k in dependents:
-        for partner in IGNORED_PARTNERS:
-            if f"libs/partners/{partner}" in dependents[k]:
-                dependents[k].remove(f"libs/partners/{partner}")
-    return dependents
-
-
-def add_dependents(dirs_to_eval: Set[str], dependents: dict) -> List[str]:
-    updated = set()
-    for dir_ in dirs_to_eval:
-        # handle core manually because it has so many dependents
-        if "core" in dir_:
-            updated.add(dir_)
-            continue
-        pkg = "langchain-" + dir_.split("/")[-1]
-        updated.update(dependents[pkg])
-        updated.add(dir_)
-    return list(updated)
-
-
-def _get_configs_for_single_dir(job: str, dir_: str) -> List[Dict[str, str]]:
-    if dir_ == "libs/core":
-        return [
-            {"working-directory": dir_, "python-version": f"3.{v}"}
-            for v in range(8, 13)
-        ]
-    min_python = "3.8"
-    max_python = "3.12"
-
-    # custom logic for specific directories
-    if dir_ == "libs/partners/milvus":
-        # milvus poetry doesn't allow 3.12 because they
-        # declare deps in funny way
-        max_python = "3.11"
-
-    if dir_ in ["libs/community", "libs/langchain"] and job == "extended-tests":
-        # community extended test resolution in 3.12 is slow
-        # even in uv
-        max_python = "3.11"
-
-    if dir_ == "libs/community" and job == "compile-integration-tests":
-        # community integration deps are slow in 3.12
-        max_python = "3.11"
-
-    return [
-        {"working-directory": dir_, "python-version": min_python},
-        {"working-directory": dir_, "python-version": max_python},
-    ]
-
-
-def _get_configs_for_multi_dirs(
-    job: str, dirs_to_run: List[str], dependents: dict
-) -> List[Dict[str, str]]:
-    if job == "lint":
-        dirs = add_dependents(
-            dirs_to_run["lint"] | dirs_to_run["test"] | dirs_to_run["extended-test"],
-            dependents,
-        )
-    elif job in ["test", "compile-integration-tests", "dependencies"]:
-        dirs = add_dependents(
-            dirs_to_run["test"] | dirs_to_run["extended-test"], dependents
-        )
-    elif job == "extended-tests":
-        dirs = list(dirs_to_run["extended-test"])
-    else:
-        raise ValueError(f"Unknown job: {job}")
-
-    return [
-        config for dir_ in dirs for config in _get_configs_for_single_dir(job, dir_)
-    ]
-
+    "libs/community",
+}
 
 if __name__ == "__main__":
     files = sys.argv[1:]
+    dirs_to_run = set()
 
-    dirs_to_run: Dict[str, set] = {
-        "lint": set(),
-        "test": set(),
-        "extended-test": set(),
-    }
-    docs_edited = False
-
-    if len(files) >= 300:
+    if len(files) == 300:
         # max diff length is 300 files - there are likely files missing
-        dirs_to_run["lint"] = all_package_dirs()
-        dirs_to_run["test"] = all_package_dirs()
-        dirs_to_run["extended-test"] = set(LANGCHAIN_DIRS)
+        raise ValueError("Max diff reached. Please manually run CI on changed libs.")
+
     for file in files:
         if any(
             file.startswith(dir_)
@@ -172,73 +24,33 @@ if __name__ == "__main__":
                 ".github/workflows",
                 ".github/tools",
                 ".github/actions",
+                "libs/core",
                 ".github/scripts/check_diff.py",
             )
         ):
-            # add all LANGCHAIN_DIRS for infra changes
-            dirs_to_run["extended-test"].update(LANGCHAIN_DIRS)
-            dirs_to_run["lint"].add(".")
-
-        if any(file.startswith(dir_) for dir_ in LANGCHAIN_DIRS):
-            # add that dir and all dirs after in LANGCHAIN_DIRS
-            # for extended testing
-            found = False
-            for dir_ in LANGCHAIN_DIRS:
-                if file.startswith(dir_):
-                    found = True
-                if found:
-                    dirs_to_run["extended-test"].add(dir_)
-        elif file.startswith("libs/standard-tests"):
-            # TODO: update to include all packages that rely on standard-tests (all partner packages)
-            # note: won't run on external repo partners
-            dirs_to_run["lint"].add("libs/standard-tests")
-            dirs_to_run["test"].add("libs/partners/mistralai")
-            dirs_to_run["test"].add("libs/partners/openai")
-            dirs_to_run["test"].add("libs/partners/anthropic")
-            dirs_to_run["test"].add("libs/partners/fireworks")
-            dirs_to_run["test"].add("libs/partners/groq")
-
-        elif file.startswith("libs/cli"):
-            # todo: add cli makefile
-            pass
-        elif file.startswith("libs/partners"):
-            partner_dir = file.split("/")[2]
-            if os.path.isdir(f"libs/partners/{partner_dir}") and [
-                filename
-                for filename in os.listdir(f"libs/partners/{partner_dir}")
-                if not filename.startswith(".")
-            ] != ["README.md"]:
-                dirs_to_run["test"].add(f"libs/partners/{partner_dir}")
-            # Skip if the directory was deleted or is just a tombstone readme
-        elif file.startswith("libs/"):
-            raise ValueError(
-                f"Unknown lib: {file}. check_diff.py likely needs "
-                "an update for this new library!"
+            dirs_to_run.update(LANGCHAIN_DIRS)
+        elif "libs/community" in file:
+            dirs_to_run.update(
+                ("libs/community", "libs/langchain", "libs/experimental")
             )
-        elif any(file.startswith(p) for p in ["docs/", "templates/", "cookbook/"]):
-            if file.startswith("docs/"):
-                docs_edited = True
-            dirs_to_run["lint"].add(".")
-
-    dependents = dependents_graph()
-
-    # we now have dirs_by_job
-    # todo: clean this up
-
-    map_job_to_configs = {
-        job: _get_configs_for_multi_dirs(job, dirs_to_run, dependents)
-        for job in [
-            "lint",
-            "test",
-            "extended-tests",
-            "compile-integration-tests",
-            "dependencies",
-        ]
-    }
-    map_job_to_configs["test-doc-imports"] = (
-        [{"python-version": "3.12"}] if docs_edited else []
-    )
-
-    for key, value in map_job_to_configs.items():
-        json_output = json.dumps(value)
-        print(f"{key}={json_output}")
+        elif "libs/partners" in file:
+            partner_dir = file.split("/")[2]
+            if os.path.isdir(f"libs/partners/{partner_dir}"):
+                dirs_to_run.update(
+                    (
+                        f"libs/partners/{partner_dir}",
+                        "libs/langchain",
+                        "libs/experimental",
+                    )
+                )
+            # Skip if the directory was deleted
+        elif "libs/langchain" in file:
+            dirs_to_run.update(("libs/langchain", "libs/experimental"))
+        elif "libs/experimental" in file:
+            dirs_to_run.add("libs/experimental")
+        elif file.startswith("libs/"):
+            dirs_to_run.update(LANGCHAIN_DIRS)
+        else:
+            pass
+    json_output = json.dumps(list(dirs_to_run))
+    print(f"dirs-to-run={json_output}")

.github/scripts/check_prerelease_dependencies.py

@@ -1,35 +0,0 @@
-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
-    version = toml_data["tool"]["poetry"]["version"]
-    releasing_rc = "rc" in version
-
-    # if not, iterate through dependencies and make sure none allow prereleases
-    if not releasing_rc:
-        dependencies = toml_data["tool"]["poetry"]["dependencies"]
-        for lib in dependencies:
-            dep_version = dependencies[lib]
-            dep_version_string = (
-                dep_version["version"] if isinstance(dep_version, dict) else dep_version
-            )
-
-            if "rc" in dep_version_string:
-                raise ValueError(
-                    f"Dependency {lib} has a prerelease version. Please remove this."
-                )
-
-            if isinstance(dep_version, dict) and dep_version.get(
-                "allow-prereleases", False
-            ):
-                raise ValueError(
-                    f"Dependency {lib} has allow-prereleases set to true. Please remove this."
-                )

.github/scripts/get_min_versions.py

@@ -1,91 +0,0 @@
-import sys
-
-if sys.version_info >= (3, 11):
-    import tomllib
-else:
-    # for python 3.10 and below, which doesnt have stdlib tomllib
-    import tomli as tomllib
-
-from packaging.version import parse as parse_version
-import re
-
-MIN_VERSION_LIBS = [
-    "langchain-core",
-    "langchain-community",
-    "langchain",
-    "langchain-text-splitters",
-    "SQLAlchemy",
-]
-
-SKIP_IF_PULL_REQUEST = ["langchain-core"]
-
-
-def get_min_version(version: str) -> str:
-    # base regex for x.x.x with cases for rc/post/etc
-    # valid strings: https://peps.python.org/pep-0440/#public-version-identifiers
-    vstring = r"\d+(?:\.\d+){0,2}(?:(?:a|b|rc|\.post|\.dev)\d+)?"
-    # case ^x.x.x
-    _match = re.match(f"^\\^({vstring})$", version)
-    if _match:
-        return _match.group(1)
-
-    # case >=x.x.x,<y.y.y
-    _match = re.match(f"^>=({vstring}),<({vstring})$", version)
-    if _match:
-        _min = _match.group(1)
-        _max = _match.group(2)
-        assert parse_version(_min) < parse_version(_max)
-        return _min
-
-    # case x.x.x
-    _match = re.match(f"^({vstring})$", version)
-    if _match:
-        return _match.group(1)
-
-    raise ValueError(f"Unrecognized version format: {version}")
-
-
-def get_min_version_from_toml(toml_path: str, versions_for: str):
-    # Parse the TOML file
-    with open(toml_path, "rb") as file:
-        toml_data = tomllib.load(file)
-
-    # Get the dependencies from tool.poetry.dependencies
-    dependencies = toml_data["tool"]["poetry"]["dependencies"]
-
-    # Initialize a dictionary to store the minimum versions
-    min_versions = {}
-
-    # Iterate over the libs in MIN_VERSION_LIBS
-    for lib in MIN_VERSION_LIBS:
-        if versions_for == "pull_request" and lib in SKIP_IF_PULL_REQUEST:
-            # some libs only get checked on release because of simultaneous
-            # changes
-            continue
-        # Check if the lib is present in the dependencies
-        if lib in dependencies:
-            # Get the version string
-            version_string = dependencies[lib]
-
-            if isinstance(version_string, dict):
-                version_string = version_string["version"]
-
-            # Use parse_version to get the minimum supported version from version_string
-            min_version = get_min_version(version_string)
-
-            # Store the minimum version in the min_versions dictionary
-            min_versions[lib] = min_version
-
-    return min_versions
-
-
-if __name__ == "__main__":
-    # Get the TOML file path from the command line argument
-    toml_file = sys.argv[1]
-    versions_for = sys.argv[2]
-    assert versions_for in ["release", "pull_request"]
-
-    # Call the function to get the minimum versions
-    min_versions = get_min_version_from_toml(toml_file, versions_for)
-
-    print(" ".join([f"{lib}=={version}" for lib, version in min_versions.items()]))

.github/workflows/.codespell-exclude

@@ -1,7 +0,0 @@
-libs/community/langchain_community/llms/yuan2.py
-"NotIn": "not in",
-- `/checkin`: Check-in
-docs/docs/integrations/providers/trulens.mdx
-self.assertIn(
-from trulens_eval import Tru
-tru = Tru()

.github/workflows/_all_ci.yml

@@ -0,0 +1,106 @@
+---
+name: langchain CI
+
+on:
+  workflow_call:
+    inputs:
+      working-directory:
+        required: true
+        type: string
+        description: "From which folder this pipeline executes"
+  workflow_dispatch:
+    inputs:
+      working-directory:
+        required: true
+        type: choice
+        default: 'libs/langchain'
+        options:
+        - libs/langchain
+        - libs/core
+        - libs/experimental
+        - libs/community
+
+
+# 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 }}-${{ inputs.working-directory }}
+  cancel-in-progress: true
+
+env:
+  POETRY_VERSION: "1.7.1"
+
+jobs:
+  lint:
+    uses: ./.github/workflows/_lint.yml
+    with:
+      working-directory: ${{ inputs.working-directory }}
+    secrets: inherit
+
+  test:
+    uses: ./.github/workflows/_test.yml
+    with:
+      working-directory: ${{ inputs.working-directory }}
+    secrets: inherit
+
+  compile-integration-tests:
+    uses: ./.github/workflows/_compile_integration_test.yml
+    with:
+      working-directory: ${{ inputs.working-directory }}
+    secrets: inherit
+
+  dependencies:
+    uses: ./.github/workflows/_dependencies.yml
+    with:
+      working-directory: ${{ inputs.working-directory }}
+    secrets: inherit
+
+  extended-tests:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
+    name: Python ${{ matrix.python-version }} extended tests
+    defaults:
+      run:
+        working-directory: ${{ inputs.working-directory }}
+    if: ${{ ! startsWith(inputs.working-directory, 'libs/partners/') }}
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
+        with:
+          python-version: ${{ matrix.python-version }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: ${{ inputs.working-directory }}
+          cache-key: extended
+
+      - name: Install dependencies
+        shell: bash
+        run: |
+          echo "Running extended tests, installing dependencies with poetry..."
+          poetry install -E extended_testing --with test
+
+      - name: Run extended tests
+        run: make extended_tests
+
+      - name: Ensure the tests did not create any additional files
+        shell: bash
+        run: |
+          set -eu
+
+          STATUS="$(git status)"
+          echo "$STATUS"
+
+          # grep will exit non-zero if the target message isn't found,
+          # and `set -e` above will cause the step to fail.
+          echo "$STATUS" | grep 'nothing to commit, working tree clean'

.github/workflows/_compile_integration_test.yml

@@ -7,10 +7,6 @@ on:
         required: true
         type: string
         description: "From which folder this pipeline executes"
-      python-version:
-        required: true
-        type: string
-        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -21,14 +17,21 @@ jobs:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
-    name: "poetry run pytest -m compile tests/integration_tests #${{ inputs.python-version }}"
+    strategy:
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
+    name: Python ${{ matrix.python-version }}
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ inputs.python-version }}
+          python-version: ${{ matrix.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
           cache-key: compile-integration

.github/workflows/_dependencies.yml

@@ -11,10 +11,6 @@ on:
         required: false
         type: string
         description: "Relative path to the langchain library folder"
-      python-version:
-        required: true
-        type: string
-        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -25,14 +21,21 @@ jobs:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
-    name: dependency checks ${{ inputs.python-version }}
+    strategy:
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
+    name: dependencies - Python ${{ matrix.python-version }}
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ inputs.python-version }}
+          python-version: ${{ matrix.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
           cache-key: pydantic-cross-compat
@@ -60,8 +63,6 @@ jobs:
       - name: Install the opposite major version of pydantic
         # If normal tests use pydantic v1, here we'll use v2, and vice versa.
         shell: bash
-        # airbyte currently doesn't support pydantic v2
-        if: ${{ !startsWith(inputs.working-directory, 'libs/partners/airbyte') }}
         run: |
           # Determine the major part of pydantic version
           REGULAR_VERSION=$(poetry run python -c "import pydantic; print(pydantic.__version__)" | cut -d. -f1)
@@ -96,8 +97,6 @@ jobs:
           fi
           echo "Found pydantic version ${CURRENT_VERSION}, as expected"
       - name: Run pydantic compatibility tests
-        # airbyte currently doesn't support pydantic v2
-        if: ${{ !startsWith(inputs.working-directory, 'libs/partners/airbyte') }}
         shell: bash
         run: make test
 

.github/workflows/_integration_test.yml

@@ -6,28 +6,30 @@ on:
       working-directory:
         required: true
         type: string
-      python-version:
-        required: true
-        type: string
-        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
 
 jobs:
   build:
+    environment: Scheduled testing
     defaults:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
-    name: Python ${{ inputs.python-version }}
+    strategy:
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.11"
+    name: Python ${{ matrix.python-version }}
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ inputs.python-version }}
+          python-version: ${{ matrix.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
           cache-key: core
@@ -36,11 +38,6 @@ jobs:
         shell: bash
         run: poetry install --with test,test_integration
 
-      - name: Install deps outside pyproject
-        if: ${{ startsWith(inputs.working-directory, 'libs/community/') }}
-        shell: bash
-        run: poetry run pip install "boto3<2" "google-cloud-aiplatform<2"
-
       - name: 'Authenticate to Google Cloud'
         id: 'auth'
         uses: google-github-actions/auth@v2
@@ -50,41 +47,14 @@ jobs:
       - 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 }}
-          AZURE_OPENAI_API_VERSION: ${{ secrets.AZURE_OPENAI_API_VERSION }}
-          AZURE_OPENAI_API_BASE: ${{ secrets.AZURE_OPENAI_API_BASE }}
-          AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
-          AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_CHAT_DEPLOYMENT_NAME }}
-          AZURE_OPENAI_LLM_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LLM_DEPLOYMENT_NAME }}
-          AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME }}
           MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
           TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
           NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}
           GOOGLE_SEARCH_API_KEY: ${{ secrets.GOOGLE_SEARCH_API_KEY }}
           GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
-          HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
-          EXA_API_KEY: ${{ secrets.EXA_API_KEY }}
-          NOMIC_API_KEY: ${{ secrets.NOMIC_API_KEY }}
-          WATSONX_APIKEY: ${{ secrets.WATSONX_APIKEY }}
-          WATSONX_PROJECT_ID: ${{ secrets.WATSONX_PROJECT_ID }}
-          PINECONE_API_KEY: ${{ secrets.PINECONE_API_KEY }}
-          PINECONE_ENVIRONMENT: ${{ secrets.PINECONE_ENVIRONMENT }}
-          ASTRA_DB_API_ENDPOINT: ${{ secrets.ASTRA_DB_API_ENDPOINT }}
-          ASTRA_DB_APPLICATION_TOKEN: ${{ secrets.ASTRA_DB_APPLICATION_TOKEN }}
-          ASTRA_DB_KEYSPACE: ${{ secrets.ASTRA_DB_KEYSPACE }}
-          ES_URL: ${{ secrets.ES_URL }}
-          ES_CLOUD_ID: ${{ secrets.ES_CLOUD_ID }}
-          ES_API_KEY: ${{ secrets.ES_API_KEY }}
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} # for airbyte
-          MONGODB_ATLAS_URI: ${{ secrets.MONGODB_ATLAS_URI }}
-          VOYAGE_API_KEY: ${{ secrets.VOYAGE_API_KEY }}
-          COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
-          UPSTAGE_API_KEY: ${{ secrets.UPSTAGE_API_KEY }}
         run: |
           make integration_tests
 

.github/workflows/_lint.yml

@@ -11,10 +11,6 @@ on:
         required: false
         type: string
         description: "Relative path to the langchain library folder"
-      python-version:
-        required: true
-        type: string
-        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -25,15 +21,26 @@ env:
 
 jobs:
   build:
-    name: "make lint #${{ inputs.python-version }}"
     runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        # Only lint on the min and max supported Python versions.
+        # It's extremely unlikely that there's a lint issue on any version in between
+        # that doesn't show up on the min or max versions.
+        #
+        # GitHub rate-limits how many jobs can be running at any one time.
+        # Starting new jobs is also relatively slow,
+        # so linting on fewer versions makes CI faster.
+        python-version:
+          - "3.8"
+          - "3.11"
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ inputs.python-version }}
+          python-version: ${{ matrix.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
           cache-key: lint-with-extras
@@ -72,13 +79,13 @@ jobs:
           poetry run pip install -e "$LANGCHAIN_LOCATION"
 
       - name: Get .mypy_cache to speed up mypy
-        uses: actions/cache@v4
+        uses: actions/cache@v3
         env:
           SEGMENT_DOWNLOAD_TIMEOUT_MIN: "2"
         with:
           path: |
             ${{ env.WORKDIR }}/.mypy_cache
-          key: mypy-lint-${{ runner.os }}-${{ runner.arch }}-py${{ inputs.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}
+          key: mypy-lint-${{ runner.os }}-${{ runner.arch }}-py${{ matrix.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', env.WORKDIR)) }}
 
 
       - name: Analysing the code with our lint
@@ -86,7 +93,7 @@ jobs:
         run: |
           make lint_package
 
-      - name: Install unit test dependencies
+      - name: Install 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:
@@ -95,24 +102,18 @@ jobs:
         # If you change this configuration, make sure to change the `cache-key`
         # in the `poetry_setup` action above to stop using the old cache.
         # It doesn't matter how you change it, any change will cause a cache-bust.
-        if: ${{ ! startsWith(inputs.working-directory, 'libs/partners/') }}
         working-directory: ${{ inputs.working-directory }}
         run: |
           poetry install --with test
-      - name: Install unit+integration test dependencies
-        if: ${{ startsWith(inputs.working-directory, 'libs/partners/') }}
-        working-directory: ${{ inputs.working-directory }}
-        run: |
-          poetry install --with test,test_integration
 
       - name: Get .mypy_cache_test to speed up mypy
-        uses: actions/cache@v4
+        uses: actions/cache@v3
         env:
           SEGMENT_DOWNLOAD_TIMEOUT_MIN: "2"
         with:
           path: |
             ${{ env.WORKDIR }}/.mypy_cache_test
-          key: mypy-test-${{ runner.os }}-${{ runner.arch }}-py${{ inputs.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}
+          key: mypy-test-${{ runner.os }}-${{ runner.arch }}-py${{ matrix.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', env.WORKDIR)) }}
 
       - name: Analysing the code with our lint
         working-directory: ${{ inputs.working-directory }}

.github/workflows/_release.yml

@@ -13,19 +13,14 @@ on:
         required: true
         type: string
         default: 'libs/langchain'
-      dangerous-nonmaster-release:
-        required: false
-        type: boolean
-        default: false
-        description: "Release from a non-master branch (danger!)"
 
 env:
-  PYTHON_VERSION: "3.11"
+  PYTHON_VERSION: "3.10"
   POETRY_VERSION: "1.7.1"
 
 jobs:
   build:
-    if: github.ref == 'refs/heads/master' || inputs.dangerous-nonmaster-release
+    if: github.ref == 'refs/heads/master'
     environment: Scheduled testing
     runs-on: ubuntu-latest
 
@@ -60,7 +55,7 @@ jobs:
         working-directory: ${{ inputs.working-directory }}
 
       - name: Upload build
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v3
         with:
           name: dist
           path: ${{ inputs.working-directory }}/dist/
@@ -72,78 +67,19 @@ jobs:
         run: |
           echo pkg-name="$(poetry version | cut -d ' ' -f 1)" >> $GITHUB_OUTPUT
           echo version="$(poetry version --short)" >> $GITHUB_OUTPUT
-  release-notes:
-    needs:
-      - build
-    runs-on: ubuntu-latest
-    outputs:
-      release-body: ${{ steps.generate-release-body.outputs.release-body }}
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          repository: langchain-ai/langchain
-          path: langchain
-          sparse-checkout: | # this only grabs files for relevant dir
-            ${{ inputs.working-directory }}
-          ref: ${{ github.ref }} # this scopes to just ref'd branch
-          fetch-depth: 0 # this fetches entire commit history
-      - name: Check Tags
-        id: check-tags
-        shell: bash
-        working-directory: langchain/${{ inputs.working-directory }}
-        env:
-          PKG_NAME: ${{ needs.build.outputs.pkg-name }}
-          VERSION: ${{ needs.build.outputs.version }}
-        run: |
-          REGEX="^$PKG_NAME==\\d+\\.\\d+\\.\\d+\$"
-          echo $REGEX
-          PREV_TAG=$(git tag --sort=-creatordate | grep -P $REGEX || true | head -1)
-          TAG="${PKG_NAME}==${VERSION}"
-          if [ "$TAG" == "$PREV_TAG" ]; then
-            echo "No new version to release"
-            exit 1
-          fi
-          echo tag="$TAG" >> $GITHUB_OUTPUT
-          echo prev-tag="$PREV_TAG" >> $GITHUB_OUTPUT
-      - name: Generate release body
-        id: generate-release-body
-        working-directory: langchain
-        env:
-          WORKING_DIR: ${{ inputs.working-directory }}
-          PKG_NAME: ${{ needs.build.outputs.pkg-name }}
-          TAG: ${{ steps.check-tags.outputs.tag }}
-          PREV_TAG: ${{ steps.check-tags.outputs.prev-tag }}
-        run: |
-          PREAMBLE="Changes since $PREV_TAG"
-          # if PREV_TAG is empty, then we are releasing the first version
-          if [ -z "$PREV_TAG" ]; then
-            PREAMBLE="Initial release"
-            PREV_TAG=$(git rev-list --max-parents=0 HEAD)
-          fi
-          {
-            echo 'release-body<<EOF'
-            echo $PREAMBLE
-            echo
-            git log --format="%s" "$PREV_TAG"..HEAD -- $WORKING_DIR
-            echo EOF
-          } >> "$GITHUB_OUTPUT"
 
   test-pypi-publish:
     needs:
       - build
-      - release-notes
     uses:
       ./.github/workflows/_test_release.yml
-    permissions: write-all
     with:
       working-directory: ${{ inputs.working-directory }}
-      dangerous-nonmaster-release: ${{ inputs.dangerous-nonmaster-release }}
     secrets: inherit
 
   pre-release-checks:
     needs:
       - build
-      - release-notes
       - test-pypi-publish
     runs-on: ubuntu-latest
     steps:
@@ -176,7 +112,7 @@ jobs:
           PKG_NAME: ${{ needs.build.outputs.pkg-name }}
           VERSION: ${{ needs.build.outputs.version }}
         # Here we use:
-        # - The default regular PyPI index as the *primary* index, meaning
+        # - The default regular PyPI index as the *primary* index, meaning 
         #   that it takes priority (https://pypi.org/simple)
         # - The test PyPI index as an extra index, so that any dependencies that
         #   are not found on test PyPI can be resolved and installed anyway.
@@ -189,7 +125,7 @@ jobs:
             --extra-index-url https://test.pypi.org/simple/ \
             "$PKG_NAME==$VERSION" || \
           ( \
-            sleep 15 && \
+            sleep 5 && \
             poetry run pip install \
               --extra-index-url https://test.pypi.org/simple/ \
               "$PKG_NAME==$VERSION" \
@@ -202,7 +138,7 @@ jobs:
           poetry run python -c "import $IMPORT_NAME; print(dir($IMPORT_NAME))"
 
       - name: Import test dependencies
-        run: poetry install --with test
+        run: poetry install --with test,test_integration
         working-directory: ${{ inputs.working-directory }}
 
       # Overwrite the local version of the package with the test PyPI version.
@@ -221,84 +157,36 @@ jobs:
         run: make tests
         working-directory: ${{ inputs.working-directory }}
 
-      - name: Check for prerelease versions
-        working-directory: ${{ inputs.working-directory }}
-        run: |
-          poetry run python $GITHUB_WORKSPACE/.github/scripts/check_prerelease_dependencies.py pyproject.toml
-
-      - name: Get minimum versions
-        working-directory: ${{ inputs.working-directory }}
-        id: min-version
-        run: |
-          poetry run pip install packaging
-          min_versions="$(poetry run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml release)"
-          echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"
-          echo "min-versions=$min_versions"
-
-      - name: Run unit tests with minimum dependency versions
-        if: ${{ steps.min-version.outputs.min-versions != '' }}
-        env:
-          MIN_VERSIONS: ${{ steps.min-version.outputs.min-versions }}
-        run: |
-          poetry run pip install --force-reinstall $MIN_VERSIONS --editable .
-          make tests
-        working-directory: ${{ inputs.working-directory }}
-
       - name: 'Authenticate to Google Cloud'
         id: 'auth'
         uses: google-github-actions/auth@v2
         with:
           credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
 
-      - name: Import integration test dependencies
-        run: poetry install --with test,test_integration
-        working-directory: ${{ inputs.working-directory }}
-
       - name: Run integration tests
         if: ${{ startsWith(inputs.working-directory, 'libs/partners/') }}
         env:
-          AI21_API_KEY: ${{ secrets.AI21_API_KEY }}
           GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
           ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
           MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
           TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          AZURE_OPENAI_API_VERSION: ${{ secrets.AZURE_OPENAI_API_VERSION }}
-          AZURE_OPENAI_API_BASE: ${{ secrets.AZURE_OPENAI_API_BASE }}
-          AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
-          AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_CHAT_DEPLOYMENT_NAME }}
-          AZURE_OPENAI_LLM_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LLM_DEPLOYMENT_NAME }}
-          AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME }}
           NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}
           GOOGLE_SEARCH_API_KEY: ${{ secrets.GOOGLE_SEARCH_API_KEY }}
           GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
-          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
-          HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
-          EXA_API_KEY: ${{ secrets.EXA_API_KEY }}
-          NOMIC_API_KEY: ${{ secrets.NOMIC_API_KEY }}
-          WATSONX_APIKEY: ${{ secrets.WATSONX_APIKEY }}
-          WATSONX_PROJECT_ID: ${{ secrets.WATSONX_PROJECT_ID }}
-          PINECONE_API_KEY: ${{ secrets.PINECONE_API_KEY }}
-          PINECONE_ENVIRONMENT: ${{ secrets.PINECONE_ENVIRONMENT }}
-          ASTRA_DB_API_ENDPOINT: ${{ secrets.ASTRA_DB_API_ENDPOINT }}
-          ASTRA_DB_APPLICATION_TOKEN: ${{ secrets.ASTRA_DB_APPLICATION_TOKEN }}
-          ASTRA_DB_KEYSPACE: ${{ secrets.ASTRA_DB_KEYSPACE }}
-          ES_URL: ${{ secrets.ES_URL }}
-          ES_CLOUD_ID: ${{ secrets.ES_CLOUD_ID }}
-          ES_API_KEY: ${{ secrets.ES_API_KEY }}
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} # for airbyte
-          MONGODB_ATLAS_URI: ${{ secrets.MONGODB_ATLAS_URI }}
-          VOYAGE_API_KEY: ${{ secrets.VOYAGE_API_KEY }}
-          UPSTAGE_API_KEY: ${{ secrets.UPSTAGE_API_KEY }}
-          FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
-          UNSTRUCTURED_API_KEY: ${{ secrets.UNSTRUCTURED_API_KEY }}
         run: make integration_tests
         working-directory: ${{ inputs.working-directory }}
 
+      - name: Run unit tests with minimum dependency versions
+        if: ${{ (inputs.working-directory == 'libs/langchain') || (inputs.working-directory == 'libs/community') || (inputs.working-directory == 'libs/experimental') }}
+        run: |
+          poetry run pip install -r _test_minimum_requirements.txt
+          make tests
+        working-directory: ${{ inputs.working-directory }}
+
   publish:
     needs:
       - build
-      - release-notes
       - test-pypi-publish
       - pre-release-checks
     runs-on: ubuntu-latest
@@ -325,7 +213,7 @@ jobs:
           working-directory: ${{ inputs.working-directory }}
           cache-key: release
 
-      - uses: actions/download-artifact@v4
+      - uses: actions/download-artifact@v3
         with:
           name: dist
           path: ${{ inputs.working-directory }}/dist/
@@ -336,13 +224,10 @@ jobs:
           packages-dir: ${{ inputs.working-directory }}/dist/
           verbose: true
           print-hash: true
-          # Temp workaround since attestations are on by default as of gh-action-pypi-publish v1.11.0
-          attestations: false
 
   mark-release:
     needs:
       - build
-      - release-notes
       - test-pypi-publish
       - pre-release-checks
       - publish
@@ -367,18 +252,18 @@ jobs:
           working-directory: ${{ inputs.working-directory }}
           cache-key: release
 
-      - uses: actions/download-artifact@v4
+      - uses: actions/download-artifact@v3
         with:
           name: dist
           path: ${{ inputs.working-directory }}/dist/
-          
-      - name: Create Tag
+
+      - name: Create Release
         uses: ncipollo/release-action@v1
+        if: ${{ inputs.working-directory == 'libs/langchain' }}
         with:
           artifacts: "dist/*"
           token: ${{ secrets.GITHUB_TOKEN }}
-          generateReleaseNotes: false
-          tag: ${{needs.build.outputs.pkg-name}}==${{ needs.build.outputs.version }}
-          body: ${{ needs.release-notes.outputs.release-body }}
-          commit: ${{ github.sha }}
-          makeLatest: ${{ needs.build.outputs.pkg-name == 'langchain-core'}}
+          draft: false
+          generateReleaseNotes: true
+          tag: v${{ needs.build.outputs.version }}
+          commit: master

.github/workflows/_test.yml

@@ -11,10 +11,6 @@ on:
         required: false
         type: string
         description: "Relative path to the langchain library folder"
-      python-version:
-        required: true
-        type: string
-        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -25,14 +21,21 @@ jobs:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
-    name: "make test #${{ inputs.python-version }}"
+    strategy:
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
+    name: Python ${{ matrix.python-version }}
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ inputs.python-version }}
+          python-version: ${{ matrix.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
           cache-key: core
@@ -65,21 +68,3 @@ jobs:
           # grep will exit non-zero if the target message isn't found,
           # and `set -e` above will cause the step to fail.
           echo "$STATUS" | grep 'nothing to commit, working tree clean'
-          
-      - name: Get minimum versions
-        working-directory: ${{ inputs.working-directory }}
-        id: min-version
-        run: |
-          poetry run pip install packaging tomli
-          min_versions="$(poetry run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml pull_request)"
-          echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"
-          echo "min-versions=$min_versions"
-
-      - name: Run unit tests with minimum dependency versions
-        if: ${{ steps.min-version.outputs.min-versions != '' }}
-        env:
-          MIN_VERSIONS: ${{ steps.min-version.outputs.min-versions }}
-        run: |
-          poetry run pip install --force-reinstall $MIN_VERSIONS --editable .
-          make tests
-        working-directory: ${{ inputs.working-directory }}

.github/workflows/_test_doc_imports.yml

@@ -1,51 +0,0 @@
-name: test_doc_imports
-
-on:
-  workflow_call:
-    inputs:
-      python-version:
-        required: true
-        type: string
-        description: "Python version to use"
-
-env:
-  POETRY_VERSION: "1.7.1"
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    name: "check doc imports #${{ inputs.python-version }}"
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
-        uses: "./.github/actions/poetry_setup"
-        with:
-          python-version: ${{ inputs.python-version }}
-          poetry-version: ${{ env.POETRY_VERSION }}
-          cache-key: core
-
-      - name: Install dependencies
-        shell: bash
-        run: poetry install --with test
-
-      - name: Install langchain editable
-        run: |
-          poetry run pip install -e libs/core libs/langchain libs/community libs/experimental
-
-      - name: Check doc imports
-        shell: bash
-        run: |
-          poetry run python docs/scripts/check_imports.py
-
-      - name: Ensure the test did not create any additional files
-        shell: bash
-        run: |
-          set -eu
-
-          STATUS="$(git status)"
-          echo "$STATUS"
-
-          # grep will exit non-zero if the target message isn't found,
-          # and `set -e` above will cause the step to fail.
-          echo "$STATUS" | grep 'nothing to commit, working tree clean'

.github/workflows/_test_release.yml

@@ -7,11 +7,6 @@ on:
         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:
   POETRY_VERSION: "1.7.1"
@@ -19,7 +14,7 @@ env:
 
 jobs:
   build:
-    if: github.ref == 'refs/heads/master' || inputs.dangerous-nonmaster-release
+    if: github.ref == 'refs/heads/master'
     runs-on: ubuntu-latest
 
     outputs:
@@ -53,7 +48,7 @@ jobs:
         working-directory: ${{ inputs.working-directory }}
 
       - name: Upload build
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v3
         with:
           name: test-dist
           path: ${{ inputs.working-directory }}/dist/
@@ -81,7 +76,7 @@ jobs:
     steps:
       - uses: actions/checkout@v4
 
-      - uses: actions/download-artifact@v4
+      - uses: actions/download-artifact@v3
         with:
           name: test-dist
           path: ${{ inputs.working-directory }}/dist/
@@ -98,5 +93,3 @@ jobs:
           # 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/check-broken-links.yml

@@ -1,25 +0,0 @@
-name: Check Broken Links
-
-on:
-  workflow_dispatch:
-  schedule:
-    - cron:  '0 13 * * *'
-
-jobs:
-  check-links:
-    if: github.repository_owner == 'langchain-ai'
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-      - name: Use Node.js 18.x
-        uses: actions/setup-node@v3
-        with:
-          node-version: 18.x
-          cache: "yarn"
-          cache-dependency-path: ./docs/yarn.lock
-      - name: Install dependencies
-        run: yarn install --immutable --mode=skip-build
-        working-directory: ./docs
-      - name: Check broken links
-        run: yarn check-broken-links
-        working-directory: ./docs

.github/workflows/check_diffs.yml

@@ -1,5 +1,5 @@
 ---
-name: CI
+name: Check library diffs
 
 on:
   push:
@@ -16,9 +16,6 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
   cancel-in-progress: true
 
-env:
-  POETRY_VERSION: "1.7.1"
-
 jobs:
   build:
     runs-on: ubuntu-latest
@@ -26,141 +23,21 @@ jobs:
       - uses: actions/checkout@v4
       - uses: actions/setup-python@v5
         with:
-          python-version: '3.11'
+          python-version: '3.10'
       - id: files
         uses: Ana06/get-changed-files@v2.2.0
       - id: set-matrix
         run: |
           python .github/scripts/check_diff.py ${{ steps.files.outputs.all }} >> $GITHUB_OUTPUT
     outputs:
-      lint: ${{ steps.set-matrix.outputs.lint }}
-      test: ${{ steps.set-matrix.outputs.test }}
-      extended-tests: ${{ steps.set-matrix.outputs.extended-tests }}
-      compile-integration-tests: ${{ steps.set-matrix.outputs.compile-integration-tests }}
-      dependencies: ${{ steps.set-matrix.outputs.dependencies }}
-      test-doc-imports: ${{ steps.set-matrix.outputs.test-doc-imports }}
-  lint:
-    name: cd ${{ matrix.job-configs.working-directory }}
+      dirs-to-run: ${{ steps.set-matrix.outputs.dirs-to-run }}
+  ci:
     needs: [ build ]
-    if: ${{ needs.build.outputs.lint != '[]' }}
     strategy:
       matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.lint) }}
-    uses: ./.github/workflows/_lint.yml
+        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-run) }}
+    uses: ./.github/workflows/_all_ci.yml
     with:
-      working-directory: ${{ matrix.job-configs.working-directory }}
-      python-version: ${{ matrix.job-configs.python-version }}
-    secrets: inherit
+      working-directory: ${{ matrix.working-directory }}
 
-  test:
-    name: cd ${{ matrix.job-configs.working-directory }}
-    needs: [ build ]
-    if: ${{ needs.build.outputs.test != '[]' }}
-    strategy:
-      matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.test) }}
-    uses: ./.github/workflows/_test.yml
-    with:
-      working-directory: ${{ matrix.job-configs.working-directory }}
-      python-version: ${{ matrix.job-configs.python-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) }}
-    uses: ./.github/workflows/_test_doc_imports.yml
-    secrets: inherit
-    with:
-      python-version: ${{ matrix.job-configs.python-version }}
-
-  compile-integration-tests:
-    name: cd ${{ matrix.job-configs.working-directory }}
-    needs: [ build ]
-    if: ${{ needs.build.outputs.compile-integration-tests != '[]' }}
-    strategy:
-      matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.compile-integration-tests) }}
-    uses: ./.github/workflows/_compile_integration_test.yml
-    with:
-      working-directory: ${{ matrix.job-configs.working-directory }}
-      python-version: ${{ matrix.job-configs.python-version }}
-    secrets: inherit
-
-  dependencies:
-    name: cd ${{ matrix.job-configs.working-directory }}
-    needs: [ build ]
-    if: ${{ needs.build.outputs.dependencies != '[]' }}
-    strategy:
-      matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.dependencies) }}
-    uses: ./.github/workflows/_dependencies.yml
-    with:
-      working-directory: ${{ matrix.job-configs.working-directory }}
-      python-version: ${{ matrix.job-configs.python-version }}
-    secrets: inherit
-
-  extended-tests:
-    name: "cd ${{ matrix.job-configs.working-directory }} / make extended_tests #${{ matrix.job-configs.python-version }}"
-    needs: [ build ]
-    if: ${{ needs.build.outputs.extended-tests != '[]' }}
-    strategy:
-      matrix:
-        # note different variable for extended test dirs
-        job-configs: ${{ fromJson(needs.build.outputs.extended-tests) }}
-    runs-on: ubuntu-latest
-    defaults:
-      run:
-        working-directory: ${{ matrix.job-configs.working-directory }}
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Set up Python ${{ matrix.job-configs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
-        uses: "./.github/actions/poetry_setup"
-        with:
-          python-version: ${{ matrix.job-configs.python-version }}
-          poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: ${{ matrix.job-configs.working-directory }}
-          cache-key: extended
-
-      - name: Install dependencies
-        shell: bash
-        run: |
-          echo "Running extended tests, installing dependencies with poetry..."
-          poetry install --with test
-          poetry run pip install uv
-          poetry run uv pip install -r extended_testing_deps.txt
-
-      - name: Run extended tests
-        run: make extended_tests
-
-      - name: Ensure the tests did not create any additional files
-        shell: bash
-        run: |
-          set -eu
-
-          STATUS="$(git status)"
-          echo "$STATUS"
-
-          # grep will exit non-zero if the target message isn't found,
-          # and `set -e` above will cause the step to fail.
-          echo "$STATUS" | grep 'nothing to commit, working tree clean'
-  ci_success:
-    name: "CI Success"
-    needs: [build, lint, test, compile-integration-tests, dependencies, extended-tests, test-doc-imports]
-    if: |
-      always()
-    runs-on: ubuntu-latest
-    env:
-      JOBS_JSON: ${{ toJSON(needs) }}
-      RESULTS_JSON: ${{ toJSON(needs.*.result) }}
-      EXIT_CODE: ${{!contains(needs.*.result, 'failure') && !contains(needs.*.result, 'cancelled') && '0' || '1'}}
-    steps:
-      - name: "CI Success"
-        run: |
-          echo $JOBS_JSON
-          echo $RESULTS_JSON
-          echo "Exiting with $EXIT_CODE"
-          exit $EXIT_CODE

.github/workflows/check_new_docs.yml

@@ -1,36 +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
-
-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@v2.2.0
-        with:
-          filter: |
-            *.ipynb
-            *.md
-            *.mdx
-      - name: Check new docs
-        run: |
-          python docs/scripts/check_templates.py ${{ steps.files.outputs.added }}

.github/workflows/codespell.yml

@@ -1,17 +1,18 @@
 ---
-name: CI / cd . / make spell_check
+name: Codespell
 
 on:
   push:
-    branches: [master, v0.1, v0.2]
+    branches: [master]
   pull_request:
+    branches: [master]
 
 permissions:
   contents: read
 
 jobs:
   codespell:
-    name: (Check for spelling errors)
+    name: Check for spelling errors
     runs-on: ubuntu-latest
 
     steps:
@@ -28,9 +29,8 @@ jobs:
           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
+      - name: Codespell
+        uses: codespell-project/actions-codespell@v2
+        with:
+          skip: guide_imports.json
+          ignore_words_list: ${{ steps.extract_ignore_words.outputs.ignore_words_list }}

.github/workflows/doc_lint.yml

@@ -0,0 +1,35 @@
+---
+name: Docs, templates, cookbook lint
+
+on:
+  push:
+    branches: [ master ]
+  pull_request:
+    paths:
+      - 'docs/**'
+      - 'templates/**'
+      - 'cookbook/**'
+      - '.github/workflows/_lint.yml'
+      - '.github/workflows/doc_lint.yml'
+  workflow_dispatch:
+
+jobs:
+  check:
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v4
+
+    - name: Run import check
+      run: |
+        # We should not encourage imports directly from main init file
+        # Expect for hub
+        git grep 'from langchain import' {docs/docs,templates,cookbook} | grep -vE 'from langchain import (hub)' && exit 1 || exit 0
+
+  lint:
+      uses:
+        ./.github/workflows/_lint.yml
+      with:
+        working-directory: "."
+      secrets: inherit

.github/workflows/langchain_cli_release.yml

@@ -0,0 +1,13 @@
+---
+name: libs/cli Release
+
+on:
+  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
+
+jobs:
+  release:
+    uses:
+      ./.github/workflows/_release.yml
+    with:
+      working-directory: libs/cli
+    secrets: inherit

.github/workflows/langchain_community_release.yml

@@ -0,0 +1,13 @@
+---
+name: libs/community Release
+
+on:
+  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
+
+jobs:
+  release:
+    uses:
+      ./.github/workflows/_release.yml
+    with:
+      working-directory: libs/community
+    secrets: inherit

.github/workflows/langchain_core_release.yml

@@ -0,0 +1,13 @@
+---
+name: libs/core Release
+
+on:
+  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
+
+jobs:
+  release:
+    uses:
+      ./.github/workflows/_release.yml
+    with:
+      working-directory: libs/core
+    secrets: inherit

.github/workflows/langchain_experimental_release.yml

@@ -0,0 +1,13 @@
+---
+name: libs/experimental Release
+
+on:
+  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
+
+jobs:
+  release:
+    uses:
+      ./.github/workflows/_release.yml
+    with:
+      working-directory: libs/experimental
+    secrets: inherit

.github/workflows/langchain_experimental_test_release.yml

@@ -0,0 +1,13 @@
+---
+name: Experimental Test Release
+
+on:
+  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
+
+jobs:
+  release:
+    uses:
+      ./.github/workflows/_test_release.yml
+    with:
+      working-directory: libs/experimental
+    secrets: inherit

.github/workflows/langchain_openai_release.yml

@@ -0,0 +1,13 @@
+---
+name: libs/core Release
+
+on:
+  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
+
+jobs:
+  release:
+    uses:
+      ./.github/workflows/_release.yml
+    with:
+      working-directory: libs/core
+    secrets: inherit

.github/workflows/langchain_release.yml

@@ -0,0 +1,27 @@
+---
+name: libs/langchain Release
+
+on:
+  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
+
+jobs:
+  release:
+    uses:
+      ./.github/workflows/_release.yml
+    with:
+      working-directory: libs/langchain
+    secrets: inherit
+
+  # N.B.: It's possible that PyPI doesn't make the new release visible / available
+  #       immediately after publishing. If that happens, the docker build might not
+  #       create a new docker image for the new release, since it won't see it.
+  #
+  #       If this ends up being a problem, add a check to the end of the `_release.yml`
+  #       workflow that prevents the workflow from finishing until the new release
+  #       is visible and installable on PyPI.
+  release-docker:
+    needs:
+      - release
+    uses:
+      ./.github/workflows/langchain_release_docker.yml
+    secrets: inherit

.github/workflows/langchain_test_release.yml

@@ -0,0 +1,13 @@
+---
+name: Test Release
+
+on:
+  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
+
+jobs:
+  release:
+    uses:
+      ./.github/workflows/_test_release.yml
+    with:
+      working-directory: libs/langchain
+    secrets: inherit

.github/workflows/people.yml

@@ -1,37 +0,0 @@
-name: LangChain People
-
-on:
-  schedule:
-    - cron: "0 14 1 * *"
-  push:
-    branches: [jacob/people]
-  workflow_dispatch:
-    inputs:
-      debug_enabled:
-        description: 'Run the build with tmate debugging enabled (https://github.com/marketplace/actions/debugging-with-tmate)'
-        required: false
-        default: 'false'
-
-jobs:
-  langchain-people:
-    if: github.repository_owner == 'langchain-ai'
-    runs-on: ubuntu-latest
-    permissions: write-all
-    steps:
-      - name: Dump GitHub context
-        env:
-          GITHUB_CONTEXT: ${{ toJson(github) }}
-        run: echo "$GITHUB_CONTEXT"
-      - uses: actions/checkout@v4
-      # Ref: https://github.com/actions/runner/issues/2033
-      - name: Fix git safe.directory in container
-        run: mkdir -p /home/runner/work/_temp/_github_home && printf "[safe]\n\tdirectory = /github/workspace" > /home/runner/work/_temp/_github_home/.gitconfig
-      # Allow debugging with tmate
-      - name: Setup tmate session
-        uses: mxschmitt/action-tmate@v3
-        if: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.debug_enabled == 'true' }}
-        with:
-          limit-access-to-actor: true
-      - uses: ./.github/actions/people
-        with:
-          token: ${{ secrets.LANGCHAIN_PEOPLE_GITHUB_TOKEN }}

.github/workflows/scheduled_test.yml

@@ -10,53 +10,28 @@ env:
 
 jobs:
   build:
-    if: github.repository_owner == 'langchain-ai'
-    name: Python ${{ matrix.python-version }} - ${{ matrix.working-directory }}
+    defaults:
+      run:
+        working-directory: libs/langchain
     runs-on: ubuntu-latest
+    environment: Scheduled testing
     strategy:
-      fail-fast: false
       matrix:
         python-version:
           - "3.8"
+          - "3.9"
+          - "3.10"
           - "3.11"
-        working-directory:
-          - "libs/partners/openai"
-          - "libs/partners/anthropic"
-          - "libs/partners/fireworks"
-          - "libs/partners/groq"
-          - "libs/partners/mistralai"
-          - "libs/partners/google-vertexai"
-          - "libs/partners/google-genai"
-          - "libs/partners/aws"
-
+    name: Python ${{ matrix.python-version }}
     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 }}
-        uses: "./langchain/.github/actions/poetry_setup"
+        uses: "./.github/actions/poetry_setup"
         with:
           python-version: ${{ matrix.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: langchain/${{ matrix.working-directory }}
+          working-directory: libs/langchain
           cache-key: scheduled
 
       - name: 'Authenticate to Google Cloud'
@@ -70,15 +45,17 @@ jobs:
         with:
           aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
           aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
-          aws-region: ${{ secrets.AWS_REGION }}
+          aws-region: ${{ vars.AWS_REGION }}
 
       - name: Install dependencies
+        working-directory: libs/langchain
+        shell: bash
         run: |
           echo "Running scheduled tests, installing dependencies with poetry..."
-          cd langchain/${{ matrix.working-directory }}
           poetry install --with=test_integration,test
 
-      - name: Run integration tests
+      - name: Run tests
+        shell: bash
         env:
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
           ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
@@ -89,27 +66,11 @@ jobs:
           AZURE_OPENAI_LLM_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LLM_DEPLOYMENT_NAME }}
           AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME }}
           FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
-          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
-          HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
-          MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
-          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: ${{ secrets.GOOGLE_CSE_ID }}
         run: |
-          cd langchain/${{ 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
+          make scheduled_tests
 
       - name: Ensure the tests did not create any additional files
-        working-directory: langchain
+        shell: bash
         run: |
           set -eu
 

.github/workflows/templates_ci.yml

@@ -0,0 +1,36 @@
+---
+name: templates CI
+
+on:
+  push:
+    branches: [ master ]
+  pull_request:
+    paths:
+      - '.github/actions/poetry_setup/action.yml'
+      - '.github/tools/**'
+      - '.github/workflows/_lint.yml'
+      - '.github/workflows/templates_ci.yml'
+      - 'templates/**'
+  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
+
+# If another push to the same PR or branch happens while this workflow is still running,
+# cancel the earlier run in favor of the next run.
+#
+# There's no point in testing an outdated version of the code. GitHub only allows
+# a limited number of job runners to be active at the same time, so it's better to cancel
+# pointless jobs early so that more useful jobs can run sooner.
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+env:
+  POETRY_VERSION: "1.7.1"
+  WORKDIR: "templates"
+
+jobs:
+  lint:
+    uses:
+      ./.github/workflows/_lint.yml
+    with:
+      working-directory: templates
+    secrets: inherit

.gitignore

@@ -115,11 +115,13 @@ celerybeat.pid
 # Environments
 .env
 .envrc
-.venv*
-venv*
+.venv
+.venvs
 env/
+venv/
 ENV/
 env.bak/
+venv.bak/
 
 # Spyder project settings
 .spyderproject
@@ -133,7 +135,6 @@ env.bak/
 
 # mypy
 .mypy_cache/
-.mypy_cache_test/
 .dmypy.json
 dmypy.json
 
@@ -167,19 +168,13 @@ 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/
+docs/docs/templates

.readthedocs.yaml

@@ -4,17 +4,21 @@
 # Required
 version: 2
 
-formats:
-  - pdf
-
 # Set the version of Python and other tools you might need
 build:
   os: ubuntu-22.04
   tools:
     python: "3.11"
   commands:
-    - mkdir -p $READTHEDOCS_OUTPUT
-    - cp -r api_reference_build/* $READTHEDOCS_OUTPUT
+      - python -m virtualenv $READTHEDOCS_VIRTUALENV_PATH
+      - python -m pip install --upgrade --no-cache-dir pip setuptools
+      - python -m pip install --upgrade --no-cache-dir sphinx readthedocs-sphinx-ext
+      - python -m pip install ./libs/partners/*
+      - python -m pip install --exists-action=w --no-cache-dir -r docs/api_reference/requirements.txt
+      - python docs/api_reference/create_api_rst.py
+      - cat docs/api_reference/conf.py
+      - python -m sphinx -T -E -b html -d _build/doctrees -c docs/api_reference docs/api_reference $READTHEDOCS_OUTPUT/html -j auto
+
 # Build documentation in the docs/ directory with Sphinx
 sphinx:
    configuration: docs/api_reference/conf.py

MIGRATE.md

@@ -52,7 +52,7 @@ Now:
 
 `from langchain_experimental.sql import SQLDatabaseChain`
 
-Alternatively, if you are just interested in using the query generation part of the SQL chain, you can check out this [`SQL question-answering tutorial`](https://python.langchain.com/v0.2/docs/tutorials/sql_qa/#convert-question-to-sql-query)
+Alternatively, if you are just interested in using the query generation part of the SQL chain, you can check out [`create_sql_query_chain`](https://github.com/langchain-ai/langchain/blob/master/docs/extras/use_cases/tabular/sql_query.ipynb)
 
 `from langchain.chains import create_sql_query_chain`
 

Makefile

@@ -1,63 +1,39 @@
-.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
+.PHONY: all clean docs_build docs_clean docs_linkcheck api_docs_build api_docs_clean api_docs_linkcheck
 
-## 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.
+# Default target executed when no arguments are given to make.
 all: help
 
-## clean: Clean documentation and API documentation artifacts.
-clean: docs_clean api_docs_clean
 
 ######################
 # DOCUMENTATION
 ######################
 
-## docs_build: Build the documentation.
+clean: docs_clean api_docs_clean
+
+
 docs_build:
-	cd docs && make build
+	docs/.local_build.sh
 
-## docs_clean: Clean the documentation build artifacts.
 docs_clean:
-	cd docs && make clean
+	rm -r _dist
 
-## docs_linkcheck: Run linkchecker on the documentation.
 docs_linkcheck:
 	poetry run linkchecker _dist/docs/ --ignore-url node_modules
 
-## api_docs_build: Build the API Reference documentation.
 api_docs_build:
 	poetry run python docs/api_reference/create_api_rst.py
 	cd docs/api_reference && poetry run make html
-	poetry run python docs/api_reference/scripts/custom_formatter.py docs/api_reference/_build/html/
 
-API_PKG ?= text-splitters
-
-api_docs_quick_preview:
-	poetry run pip install "pydantic<2"
-	poetry run python docs/api_reference/create_api_rst.py $(API_PKG)
-	cd docs/api_reference && poetry run make html
-	poetry run 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 docs/api_reference/index.md
-	
+	rm -f docs/api_reference/api_reference.rst
+	cd docs/api_reference && poetry run make clean
 
-## api_docs_linkcheck: Run linkchecker on the API Reference documentation.
 api_docs_linkcheck:
 	poetry run linkchecker docs/api_reference/_build/html/index.html
 
-## spell_check: Run codespell on the project.
 spell_check:
 	poetry run codespell --toml pyproject.toml
 
-## spell_fix: Run codespell on the project and fix the errors.
 spell_fix:
 	poetry run codespell --toml pyproject.toml -w
 
@@ -65,14 +41,29 @@ spell_fix:
 # LINTING AND FORMATTING
 ######################
 
-## lint: Run linting on the project.
 lint lint_package lint_tests:
-	poetry run ruff check docs templates cookbook
+	poetry run ruff docs templates cookbook
 	poetry run ruff format docs templates cookbook --diff
-	poetry run ruff check --select I docs templates cookbook
-	git grep 'from langchain import' docs/docs templates cookbook | grep -vE 'from langchain import (hub)' && exit 1 || exit 0
+	poetry run ruff --select I docs templates cookbook
 
-## format: Format the project files.
 format format_diff:
 	poetry run ruff format docs templates cookbook
-	poetry run ruff check --select I --fix docs templates cookbook
+	poetry run ruff --select I --fix docs templates cookbook
+
+######################
+# HELP
+######################
+
+help:
+	@echo '===================='
+	@echo '-- DOCUMENTATION --'
+	@echo 'clean                        - run docs_clean and api_docs_clean'
+	@echo 'docs_build                   - build the documentation'
+	@echo 'docs_clean                   - clean the documentation build artifacts'
+	@echo 'docs_linkcheck               - run linkchecker on the documentation'
+	@echo 'api_docs_build               - build the API Reference documentation'
+	@echo 'api_docs_clean               - clean the API Reference documentation build artifacts'
+	@echo 'api_docs_linkcheck           - run linkchecker on the API Reference documentation'
+	@echo 'spell_check               	- run codespell on the project'
+	@echo 'spell_fix               		- run codespell on the project and fix the errors'
+	@echo '-- TEST and LINT tasks are within libs/*/ per-package --'

README.md

@@ -1,140 +1,111 @@
 # 🦜️🔗 LangChain
 
-⚡ Build context-aware reasoning applications ⚡
+⚡ Building applications with LLMs through composability ⚡
 
-[![Release Notes](https://img.shields.io/github/release/langchain-ai/langchain?style=flat-square)](https://github.com/langchain-ai/langchain/releases)
+[![Release Notes](https://img.shields.io/github/release/langchain-ai/langchain)](https://github.com/langchain-ai/langchain/releases)
 [![CI](https://github.com/langchain-ai/langchain/actions/workflows/check_diffs.yml/badge.svg)](https://github.com/langchain-ai/langchain/actions/workflows/check_diffs.yml)
-[![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)
-[![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/langchain-ai/langchain)
+[![Downloads](https://static.pepy.tech/badge/langchain/month)](https://pepy.tech/project/langchain)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 [![Twitter](https://img.shields.io/twitter/url/https/twitter.com/langchainai.svg?style=social&label=Follow%20%40LangChainAI)](https://twitter.com/langchainai)
+[![](https://dcbadge.vercel.app/api/server/6adMQxSpJS?compact=true&style=flat)](https://discord.gg/6adMQxSpJS)
+[![Open in Dev Containers](https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langchain-ai/langchain)
+[![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/langchain-ai/langchain)
+[![GitHub star chart](https://img.shields.io/github/stars/langchain-ai/langchain?style=social)](https://star-history.com/#langchain-ai/langchain)
+[![Dependency Status](https://img.shields.io/librariesio/github/langchain-ai/langchain)](https://libraries.io/github/langchain-ai/langchain)
+[![Open Issues](https://img.shields.io/github/issues-raw/langchain-ai/langchain)](https://github.com/langchain-ai/langchain/issues)
 
 Looking for the JS/TS library? Check out [LangChain.js](https://github.com/langchain-ai/langchainjs).
 
-To help you ship LangChain apps to production faster, check out [LangSmith](https://smith.langchain.com).
-[LangSmith](https://smith.langchain.com) is a unified developer platform for building, testing, and monitoring LLM applications.
-Fill out [this form](https://www.langchain.com/contact-sales) to speak with our sales team.
+To help you ship LangChain apps to production faster, check out [LangSmith](https://smith.langchain.com). 
+[LangSmith](https://smith.langchain.com) is a unified developer platform for building, testing, and monitoring LLM applications. 
+Fill out [this form](https://airtable.com/appwQzlErAS2qiP0L/shrGtGaVBVAz7NcV2) to get off the waitlist or speak with our sales team.
 
 ## Quick Install
 
 With pip:
-
 ```bash
 pip install langchain
 ```
 
 With conda:
-
 ```bash
 conda install langchain -c conda-forge
 ```
 
 ## 🤔 What is LangChain?
 
-**LangChain** is a framework for developing applications powered by large language models (LLMs).
+**LangChain** is a framework for developing applications powered by language models. It enables applications that:
+- **Are context-aware**: connect a language model to sources of context (prompt instructions, few shot examples, content to ground its response in, etc.)
+- **Reason**: rely on a language model to reason (about how to answer based on provided context, what actions to take, etc.)
 
-For these applications, LangChain simplifies the entire application lifecycle:
+This framework consists of several parts.
+- **LangChain Libraries**: The Python and JavaScript libraries. Contains interfaces and integrations for a myriad of components, a basic run time for combining these components into chains and agents, and off-the-shelf implementations of chains and agents.
+- **[LangChain Templates](templates)**: A collection of easily deployable reference architectures for a wide variety of tasks.
+- **[LangServe](https://github.com/langchain-ai/langserve)**: A library for deploying LangChain chains as a REST API.
+- **[LangSmith](https://smith.langchain.com)**: A developer platform that lets you debug, test, evaluate, and monitor chains built on any LLM framework and seamlessly integrates with LangChain.
 
-- **Open-source libraries**: Build your applications using LangChain's open-source [building blocks](https://python.langchain.com/v0.2/docs/concepts#langchain-expression-language-lcel), [components](https://python.langchain.com/v0.2/docs/concepts), and [third-party integrations](https://python.langchain.com/v0.2/docs/integrations/platforms/).
-  Use [LangGraph](/docs/concepts/#langgraph) to build stateful agents with first-class streaming and human-in-the-loop support.
-- **Productionization**: Inspect, monitor, and evaluate your apps with [LangSmith](https://docs.smith.langchain.com/) so that you can constantly optimize and deploy with confidence.
-- **Deployment**: Turn your LangGraph applications into production-ready APIs and Assistants with [LangGraph Cloud](https://langchain-ai.github.io/langgraph/cloud/).
+The LangChain libraries themselves are made up of several different packages.
+- **[`langchain-core`](libs/core)**: Base abstractions and LangChain Expression Language.
+- **[`langchain-community`](libs/community)**: Third party integrations.
+- **[`langchain`](libs/langchain)**: Chains, agents, and retrieval strategies that make up an application's cognitive architecture.
 
-### Open-source libraries
-
-- **`langchain-core`**: Base abstractions and LangChain Expression Language.
-- **`langchain-community`**: Third party integrations.
-  - Some integrations have been further split into **partner packages** that only rely on **`langchain-core`**. Examples include **`langchain_openai`** and **`langchain_anthropic`**.
-- **`langchain`**: Chains, agents, and retrieval strategies that make up an application's cognitive architecture.
-- **[`LangGraph`](https://langchain-ai.github.io/langgraph/)**: A library for building robust and stateful multi-actor applications with LLMs by modeling steps as edges and nodes in a graph. Integrates smoothly with LangChain, but can be used without it. To learn more about LangGraph, check out our first LangChain Academy course, *Introduction to LangGraph*, available [here](https://academy.langchain.com/courses/intro-to-langgraph).
-
-### Productionization:
-
-- **[LangSmith](https://docs.smith.langchain.com/)**: A developer platform that lets you debug, test, evaluate, and monitor chains built on any LLM framework and seamlessly integrates with LangChain.
-
-### Deployment:
-
-- **[LangGraph Cloud](https://langchain-ai.github.io/langgraph/cloud/)**: Turn your LangGraph applications into production-ready APIs and Assistants.
-
-![Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers.](docs/static/svg/langchain_stack_062024.svg "LangChain Architecture Overview")
+![Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers.](docs/static/img/langchain_stack.png "LangChain Architecture Overview")
 
 ## 🧱 What can you build with LangChain?
+**❓ Retrieval augmented generation**
 
-**❓ Question answering with RAG**
-
-- [Documentation](https://python.langchain.com/v0.2/docs/tutorials/rag/)
+- [Documentation](https://python.langchain.com/docs/use_cases/question_answering/)
 - End-to-end Example: [Chat LangChain](https://chat.langchain.com) and [repo](https://github.com/langchain-ai/chat-langchain)
 
-**🧱 Extracting structured output**
+**💬 Analyzing structured data**
 
-- [Documentation](https://python.langchain.com/v0.2/docs/tutorials/extraction/)
-- End-to-end Example: [SQL Llama2 Template](https://github.com/langchain-ai/langchain-extract/)
+- [Documentation](https://python.langchain.com/docs/use_cases/qa_structured/sql)
+- End-to-end Example: [SQL Llama2 Template](https://github.com/langchain-ai/langchain/tree/master/templates/sql-llama2)
 
 **🤖 Chatbots**
 
-- [Documentation](https://python.langchain.com/v0.2/docs/tutorials/chatbot/)
+- [Documentation](https://python.langchain.com/docs/use_cases/chatbots)
 - End-to-end Example: [Web LangChain (web researcher chatbot)](https://weblangchain.vercel.app) and [repo](https://github.com/langchain-ai/weblangchain)
 
-And much more! Head to the [Tutorials](https://python.langchain.com/v0.2/docs/tutorials/) section of the docs for more.
+And much more! Head to the [Use cases](https://python.langchain.com/docs/use_cases/) section of the docs for more.
 
 ## 🚀 How does LangChain help?
-
 The main value props of the LangChain libraries are:
-
-1. **Components**: composable building blocks, tools and integrations for working with language models. Components are modular and easy-to-use, whether you are using the rest of the LangChain framework or not
+1. **Components**: composable tools and integrations for working with language models. Components are modular and easy-to-use, whether you are using the rest of the LangChain framework or not
 2. **Off-the-shelf chains**: built-in assemblages of components for accomplishing higher-level tasks
 
-Off-the-shelf chains make it easy to get started. Components make it easy to customize existing chains and build new ones.
-
-## LangChain Expression Language (LCEL)
-
-LCEL is a key part of LangChain, allowing you to build and organize chains of processes in a straightforward, declarative manner. It was designed to support taking prototypes directly into production without needing to alter any code. This means you can use LCEL to set up everything from basic "prompt + LLM" setups to intricate, multi-step workflows.
-
-- **[Overview](https://python.langchain.com/v0.2/docs/concepts/#langchain-expression-language-lcel)**: LCEL and its benefits
-- **[Interface](https://python.langchain.com/v0.2/docs/concepts/#runnable-interface)**: The standard Runnable interface for LCEL objects
-- **[Primitives](https://python.langchain.com/v0.2/docs/how_to/#langchain-expression-language-lcel)**: More on the primitives LCEL includes
-- **[Cheatsheet](https://python.langchain.com/v0.2/docs/how_to/lcel_cheatsheet/)**: Quick overview of the most common usage patterns
-
-## Components
+Off-the-shelf chains make it easy to get started. Components make it easy to customize existing chains and build new ones. 
 
 Components fall into the following **modules**:
 
-**📃 Model I/O**
+**📃 Model I/O:**
 
-This includes [prompt management](https://python.langchain.com/v0.2/docs/concepts/#prompt-templates), [prompt optimization](https://python.langchain.com/v0.2/docs/concepts/#example-selectors), a generic interface for [chat models](https://python.langchain.com/v0.2/docs/concepts/#chat-models) and [LLMs](https://python.langchain.com/v0.2/docs/concepts/#llms), and common utilities for working with [model outputs](https://python.langchain.com/v0.2/docs/concepts/#output-parsers).
+This includes prompt management, prompt optimization, a generic interface for all LLMs, and common utilities for working with LLMs.
 
-**📚 Retrieval**
+**📚 Retrieval:**
 
-Retrieval Augmented Generation involves [loading data](https://python.langchain.com/v0.2/docs/concepts/#document-loaders) from a variety of sources, [preparing it](https://python.langchain.com/v0.2/docs/concepts/#text-splitters), then [searching over (a.k.a. retrieving from)](https://python.langchain.com/v0.2/docs/concepts/#retrievers) it for use in the generation step.
+Data Augmented Generation involves specific types of chains that first interact with an external data source to fetch data for use in the generation step. Examples include summarization of long pieces of text and question/answering over specific data sources.
 
-**🤖 Agents**
+**🤖 Agents:**
 
-Agents allow an LLM autonomy over how a task is accomplished. Agents make decisions about which Actions to take, then take that Action, observe the result, and repeat until the task is complete. LangChain provides a [standard interface for agents](https://python.langchain.com/v0.2/docs/concepts/#agents), along with [LangGraph](https://github.com/langchain-ai/langgraph) for building custom agents.
+Agents involve an LLM making decisions about which Actions to take, taking that Action, seeing an Observation, and repeating that until done. LangChain provides a standard interface for agents, a selection of agents to choose from, and examples of end-to-end agents.
 
 ## 📖 Documentation
 
 Please see [here](https://python.langchain.com) for full documentation, which includes:
 
-- [Introduction](https://python.langchain.com/v0.2/docs/introduction/): Overview of the framework and the structure of the docs.
-- [Tutorials](https://python.langchain.com/docs/use_cases/): If you're looking to build something specific or are more of a hands-on learner, check out our tutorials. This is the best place to get started.
-- [How-to guides](https://python.langchain.com/v0.2/docs/how_to/): Answers to “How do I….?” type questions. These guides are goal-oriented and concrete; they're meant to help you complete a specific task.
-- [Conceptual guide](https://python.langchain.com/v0.2/docs/concepts/): Conceptual explanations of the key parts of the framework.
-- [API Reference](https://api.python.langchain.com): Thorough documentation of every class and method.
+- [Getting started](https://python.langchain.com/docs/get_started/introduction): installation, setting up the environment, simple examples
+- Overview of the [interfaces](https://python.langchain.com/docs/expression_language/), [modules](https://python.langchain.com/docs/modules/), and [integrations](https://python.langchain.com/docs/integrations/providers)
+- [Use case](https://python.langchain.com/docs/use_cases/qa_structured/sql) walkthroughs and best practice [guides](https://python.langchain.com/docs/guides/adapters/openai)
+- [LangSmith](https://python.langchain.com/docs/langsmith/), [LangServe](https://python.langchain.com/docs/langserve), and [LangChain Template](https://python.langchain.com/docs/templates/) overviews
+- [Reference](https://api.python.langchain.com): full API docs
 
-## 🌐 Ecosystem
-
-- [🦜🛠️ LangSmith](https://docs.smith.langchain.com/): Trace and evaluate your language model applications and intelligent agents to help you move from prototype to production.
-- [🦜🕸️ LangGraph](https://langchain-ai.github.io/langgraph/): Create stateful, multi-actor applications with LLMs. Integrates smoothly with LangChain, but can be used without it.
-- [🦜🏓 LangServe](https://python.langchain.com/docs/langserve): Deploy LangChain runnables and chains as REST APIs.
 
 ## 💁 Contributing
 
 As an open-source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of a new feature, improved infrastructure, or better documentation.
 
-For detailed information on how to contribute, see [here](https://python.langchain.com/v0.2/docs/contributing/).
+For detailed information on how to contribute, see [here](https://python.langchain.com/docs/contributing/).
 
 ## 🌟 Contributors
 

SECURITY.md

@@ -1,61 +1,6 @@
 # Security Policy
 
-## Reporting OSS Vulnerabilities
+## Reporting a Vulnerability
 
-LangChain is partnered with [huntr by Protect AI](https://huntr.com/) to provide 
-a bounty program for our open source projects. 
-
-Please report security vulnerabilities associated with the LangChain 
-open source projects by visiting the following link:
-
-[https://huntr.com/bounties/disclose/](https://huntr.com/bounties/disclose/?target=https%3A%2F%2Fgithub.com%2Flangchain-ai%2Flangchain&validSearch=true)
-
-Before reporting a vulnerability, please review:
-
-1) In-Scope Targets and Out-of-Scope Targets below.
-2) The [langchain-ai/langchain](https://python.langchain.com/docs/contributing/repo_structure) monorepo structure.
-3) LangChain [security guidelines](https://python.langchain.com/docs/security) to
-   understand what we consider to be a security vulnerability vs. developer
-   responsibility.
-
-### In-Scope Targets
-
-The following packages and repositories are eligible for bug bounties:
-
-- langchain-core
-- langchain (see exceptions)
-- langchain-community (see exceptions)
-- langgraph
-- langserve
-
-### Out of Scope Targets
-
-All out of scope targets defined by huntr as well as:
-
-- **langchain-experimental**: This repository is for experimental code and is not
-  eligible for bug bounties, bug reports to it will be marked as interesting or waste of
-  time and published with no bounty attached.
-- **tools**: Tools in either langchain or langchain-community are not eligible for bug
-  bounties. This includes the following directories
-  - langchain/tools
-  - langchain-community/tools
-  - Please review our [security guidelines](https://python.langchain.com/docs/security)
-    for more details, but generally tools interact with the real world. Developers are
-    expected to understand the security implications of their code and are responsible
-    for the security of their tools.
-- Code documented with security notices. This will be decided done on a case by
-  case basis, but likely will not be eligible for a bounty as the code is already
-  documented with guidelines for developers that should be followed for making their
-  application secure.
-- Any LangSmith related repositories or APIs see below.
-
-## Reporting LangSmith Vulnerabilities
-
-Please report security vulnerabilities associated with LangSmith by email to `security@langchain.dev`.
-
-- LangSmith site: https://smith.langchain.com
-- SDK client: https://github.com/langchain-ai/langsmith-sdk
-
-### Other Security Concerns
-
-For any other security concerns, please contact us at `security@langchain.dev`.
+Please report security vulnerabilities by email to `security@langchain.dev`.
+This email is an alias to a subset of our maintainers, and will ensure the issue is promptly triaged and acted upon as needed.

cookbook/Gemma_LangChain.ipynb

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

cookbook/LLaMA2_sql_chat.ipynb

@@ -38,9 +38,9 @@
     "\n",
     "To run locally, we use Ollama.ai. \n",
     "\n",
-    "See [here](/docs/integrations/chat/ollama) for details on installation and setup.\n",
+    "See [here](https://python.langchain.com/docs/integrations/chat/ollama) for details on installation and setup.\n",
     "\n",
-    "Also, see [here](/docs/guides/development/local_llms) for our full guide on local LLMs.\n",
+    "Also, see [here](https://python.langchain.com/docs/guides/local_llms) for our full guide on local LLMs.\n",
     " \n",
     "To use an external API, which is not private, we can use Replicate."
    ]

cookbook/Multi_modal_RAG.ipynb

@@ -64,7 +64,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install -U langchain openai langchain-chroma langchain-experimental # (newest versions required for multi-modal)"
+    "! pip install -U langchain openai chromadb langchain-experimental # (newest versions required for multi-modal)"
    ]
   },
   {
@@ -116,7 +116,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_text_splitters import CharacterTextSplitter\n",
+    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from unstructured.partition.pdf import partition_pdf\n",
     "\n",
     "\n",
@@ -355,7 +355,7 @@
     "\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryStore\n",
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_core.documents import Document\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
@@ -464,8 +464,8 @@
     "    Check if the base64 data is an image by looking at the start of the data\n",
     "    \"\"\"\n",
     "    image_signatures = {\n",
-    "        b\"\\xff\\xd8\\xff\": \"jpg\",\n",
-    "        b\"\\x89\\x50\\x4e\\x47\\x0d\\x0a\\x1a\\x0a\": \"png\",\n",
+    "        b\"\\xFF\\xD8\\xFF\": \"jpg\",\n",
+    "        b\"\\x89\\x50\\x4E\\x47\\x0D\\x0A\\x1A\\x0A\": \"png\",\n",
     "        b\"\\x47\\x49\\x46\\x38\": \"gif\",\n",
     "        b\"\\x52\\x49\\x46\\x46\": \"webp\",\n",
     "    }\n",
@@ -604,7 +604,7 @@
    "source": [
     "# Check retrieval\n",
     "query = \"Give me company names that are interesting investments based on EV / NTM and NTM rev growth. Consider EV / NTM multiples vs historical?\"\n",
-    "docs = retriever_multi_vector_img.invoke(query, limit=6)\n",
+    "docs = retriever_multi_vector_img.get_relevant_documents(query, limit=6)\n",
     "\n",
     "# We get 4 docs\n",
     "len(docs)"
@@ -630,7 +630,7 @@
    "source": [
     "# Check retrieval\n",
     "query = \"What are the EV / NTM and NTM rev growth for MongoDB, Cloudflare, and Datadog?\"\n",
-    "docs = retriever_multi_vector_img.invoke(query, limit=6)\n",
+    "docs = retriever_multi_vector_img.get_relevant_documents(query, limit=6)\n",
     "\n",
     "# We get 4 docs\n",
     "len(docs)"

cookbook/Multi_modal_RAG_google.ipynb

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

cookbook/README.md

@@ -4,13 +4,10 @@ Example code for building applications with LangChain, with an emphasis on more
 
 Notebook | Description
 :- | :-
-[agent_fireworks_ai_langchain_mongodb.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/agent_fireworks_ai_langchain_mongodb.ipynb) | Build an AI Agent With Memory Using MongoDB, LangChain and FireWorksAI.
-[mongodb-langchain-cache-memory.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/mongodb-langchain-cache-memory.ipynb) | Build a RAG Application with Semantic Cache Using MongoDB and LangChain.
 [LLaMA2_sql_chat.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/LLaMA2_sql_chat.ipynb) | Build a chat application that interacts with a SQL database using an open source llm (llama2), specifically demonstrated on an SQLite database containing rosters.
 [Semi_Structured_RAG.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/Semi_Structured_RAG.ipynb) | Perform retrieval-augmented generation (rag) on documents with semi-structured data, including text and tables, using unstructured for parsing, multi-vector retriever for storing, and lcel for implementing chains.
 [Semi_structured_and_multi_moda...](https://github.com/langchain-ai/langchain/tree/master/cookbook/Semi_structured_and_multi_modal_RAG.ipynb) | Perform retrieval-augmented generation (rag) on documents with semi-structured data and images, using unstructured for parsing, multi-vector retriever for storage and retrieval, and lcel for implementing chains.
 [Semi_structured_multi_modal_RA...](https://github.com/langchain-ai/langchain/tree/master/cookbook/Semi_structured_multi_modal_RAG_LLaMA2.ipynb) | Perform retrieval-augmented generation (rag) on documents with semi-structured data and images, using various tools and methods such as unstructured for parsing, multi-vector retriever for storing, lcel for implementing chains, and open source language models like llama2, llava, and gpt4all.
-[amazon_personalize_how_to.ipynb](https://github.com/langchain-ai/langchain/blob/master/cookbook/amazon_personalize_how_to.ipynb) | Retrieving personalized recommendations from Amazon Personalize and use custom agents to build generative AI apps
 [analyze_document.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/analyze_document.ipynb) | Analyze a single long document.
 [autogpt/autogpt.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/autogpt/autogpt.ipynb) | Implement autogpt, a language model, with langchain primitives such as llms, prompttemplates, vectorstores, embeddings, and tools.
 [autogpt/marathon_times.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/autogpt/marathon_times.ipynb) | Implement autogpt for finding winning marathon times.
@@ -38,7 +35,6 @@ Notebook | Description
 [llm_symbolic_math.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/llm_symbolic_math.ipynb) | Solve algebraic equations with the help of llms (language learning models) and sympy, a python library for symbolic mathematics.
 [meta_prompt.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/meta_prompt.ipynb) | Implement the meta-prompt concept, which is a method for building self-improving agents that reflect on their own performance and modify their instructions accordingly.
 [multi_modal_output_agent.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multi_modal_output_agent.ipynb) | Generate multi-modal outputs, specifically images and text.
-[multi_modal_RAG_vdms.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multi_modal_RAG_vdms.ipynb) | Perform retrieval-augmented generation (rag) on documents including text and images, using unstructured for parsing, Intel's Visual Data Management System (VDMS) as the vectorstore, and chains.
 [multi_player_dnd.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multi_player_dnd.ipynb) | Simulate multi-player dungeons & dragons games, with a custom function determining the speaking schedule of the agents.
 [multiagent_authoritarian.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multiagent_authoritarian.ipynb) | Implement a multi-agent simulation where a privileged agent controls the conversation, including deciding who speaks and when the conversation ends, in the context of a simulated news network.
 [multiagent_bidding.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multiagent_bidding.ipynb) | Implement a multi-agent simulation where agents bid to speak, with the highest bidder speaking next, demonstrated through a fictitious presidential debate example.
@@ -50,7 +46,6 @@ Notebook | Description
 [press_releases.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/press_releases.ipynb) | Retrieve and query company press release data powered by [Kay.ai](https://kay.ai).
 [program_aided_language_model.i...](https://github.com/langchain-ai/langchain/tree/master/cookbook/program_aided_language_model.ipynb) | Implement program-aided language models as described in the provided research paper.
 [qa_citations.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/qa_citations.ipynb) | Different ways to get a model to cite its sources.
-[rag_upstage_layout_analysis_groundedness_check.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/rag_upstage_layout_analysis_groundedness_check.ipynb) | End-to-end RAG example using Upstage Layout Analysis and Groundedness Check.
 [retrieval_in_sql.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/retrieval_in_sql.ipynb) | Perform retrieval-augmented-generation (rag) on a PostgreSQL database using pgvector.
 [sales_agent_with_context.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/sales_agent_with_context.ipynb) | Implement a context-aware ai sales agent, salesgpt, that can have natural sales conversations, interact with other systems, and use a product knowledge base to discuss a company's offerings.
 [self_query_hotel_search.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/self_query_hotel_search.ipynb) | Build a hotel room search feature with self-querying retrieval, using a specific hotel recommendation dataset.
@@ -60,6 +55,3 @@ Notebook | Description
 [two_agent_debate_tools.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/two_agent_debate_tools.ipynb) | Simulate multi-agent dialogues where the agents can utilize various tools.
 [two_player_dnd.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/two_player_dnd.ipynb) | Simulate a two-player dungeons & dragons game, where a dialogue simulator class is used to coordinate the dialogue between the protagonist and the dungeon master.
 [wikibase_agent.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/wikibase_agent.ipynb) | Create a simple wikibase agent that utilizes sparql generation, with testing done on http://wikidata.org.
-[oracleai_demo.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/oracleai_demo.ipynb) | This guide outlines how to utilize Oracle AI Vector Search alongside Langchain for an end-to-end RAG pipeline, providing step-by-step examples. The process includes loading documents from various sources using OracleDocLoader, summarizing them either within or outside the database with OracleSummary, and generating embeddings similarly through OracleEmbeddings. It also covers chunking documents according to specific requirements using Advanced Oracle Capabilities from OracleTextSplitter, and finally, storing and indexing these documents in a Vector Store for querying with OracleVS.
-[rag-locally-on-intel-cpu.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/rag-locally-on-intel-cpu.ipynb) | Perform Retrieval-Augmented-Generation (RAG) on locally downloaded open-source models using langchain and open source tools and execute it on Intel Xeon CPU. We showed an example of how to apply RAG on Llama 2 model and enable it to answer the queries related to Intel Q1 2024 earnings release.
-[visual_RAG_vdms.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/visual_RAG_vdms.ipynb) | Performs Visual Retrieval-Augmented-Generation (RAG) using videos and scene descriptions generated by open source models.

cookbook/Semi_Structured_RAG.ipynb

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

cookbook/Semi_structured_and_multi_modal_RAG.ipynb

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

cookbook/Semi_structured_multi_modal_RAG_LLaMA2.ipynb

@@ -59,7 +59,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain langchain-chroma \"unstructured[all-docs]\" pydantic lxml"
+    "! pip install langchain unstructured[all-docs] pydantic lxml"
    ]
   },
   {
@@ -191,15 +191,15 @@
    "source": [
     "## Multi-vector retriever\n",
     "\n",
-    "Use [multi-vector-retriever](/docs/modules/data_connection/retrievers/multi_vector#summary).\n",
+    "Use [multi-vector-retriever](https://python.langchain.com/docs/modules/data_connection/retrievers/multi_vector#summary).\n",
     "\n",
     "Summaries are used to retrieve raw tables and / or raw chunks of text.\n",
     "\n",
     "### Text and Table summaries\n",
     "\n",
-    "Here, we use Ollama to run LLaMA2 locally. \n",
+    "Here, we use ollama.ai to run LLaMA2 locally. \n",
     "\n",
-    "See details on installation [here](/docs/guides/development/local_llms)."
+    "See details on installation [here](https://python.langchain.com/docs/guides/local_llms)."
    ]
   },
   {
@@ -378,8 +378,8 @@
     "\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryStore\n",
-    "from langchain_chroma import Chroma\n",
     "from langchain_community.embeddings import GPT4AllEmbeddings\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_core.documents import Document\n",
     "\n",
     "# The vectorstore to use to index the child chunks\n",
@@ -501,7 +501,9 @@
     }
    ],
    "source": [
-    "retriever.invoke(\"Images / figures with playful and creative examples\")[0]"
+    "retriever.get_relevant_documents(\"Images / figures with playful and creative examples\")[\n",
+    "    0\n",
+    "]"
    ]
   },
   {

cookbook/advanced_rag_eval.ipynb

@@ -19,7 +19,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install -U langchain openai langchain_chroma langchain-experimental # (newest versions required for multi-modal)"
+    "! pip install -U langchain openai chromadb langchain-experimental # (newest versions required for multi-modal)"
    ]
   },
   {
@@ -68,7 +68,7 @@
     "pdf_pages = loader.load()\n",
     "\n",
     "# Split\n",
-    "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
+    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
     "\n",
     "text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)\n",
     "all_splits_pypdf = text_splitter.split_documents(pdf_pages)\n",
@@ -132,7 +132,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
     "baseline = Chroma.from_texts(\n",
@@ -342,7 +342,7 @@
     "# Testing on retrieval\n",
     "query = \"What percentage of CPI is dedicated to Housing, and how does it compare to the combined percentage of Medical Care, Apparel, and Other Goods and Services?\"\n",
     "suffix_for_images = \" Include any pie charts, graphs, or tables.\"\n",
-    "docs = retriever_multi_vector_img.invoke(query + suffix_for_images)"
+    "docs = retriever_multi_vector_img.get_relevant_documents(query + suffix_for_images)"
    ]
   },
   {
@@ -520,7 +520,7 @@
    "source": [
     "import re\n",
     "\n",
-    "from langchain_core.documents import Document\n",
+    "from langchain.schema import Document\n",
     "from langchain_core.runnables import RunnableLambda\n",
     "\n",
     "\n",
@@ -532,8 +532,8 @@
     "def is_image_data(b64data):\n",
     "    \"\"\"Check if the base64 data is an image by looking at the start of the data.\"\"\"\n",
     "    image_signatures = {\n",
-    "        b\"\\xff\\xd8\\xff\": \"jpg\",\n",
-    "        b\"\\x89\\x50\\x4e\\x47\\x0d\\x0a\\x1a\\x0a\": \"png\",\n",
+    "        b\"\\xFF\\xD8\\xFF\": \"jpg\",\n",
+    "        b\"\\x89\\x50\\x4E\\x47\\x0D\\x0A\\x1A\\x0A\": \"png\",\n",
     "        b\"\\x47\\x49\\x46\\x38\": \"gif\",\n",
     "        b\"\\x52\\x49\\x46\\x46\": \"webp\",\n",
     "    }\n",

cookbook/agent_vectorstore.ipynb

@@ -28,9 +28,9 @@
    "outputs": [],
    "source": [
     "from langchain.chains import RetrievalQA\n",
-    "from langchain_chroma import Chroma\n",
+    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_openai import OpenAI, OpenAIEmbeddings\n",
-    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "llm = OpenAI(temperature=0)"
    ]

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/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/marathon_times.ipynb

@@ -40,13 +40,11 @@
     "import nest_asyncio\n",
     "import pandas as pd\n",
     "from langchain.docstore.document import Document\n",
-    "from langchain_experimental.agents.agent_toolkits.pandas.base import (\n",
-    "    create_pandas_dataframe_agent,\n",
-    ")\n",
+    "from langchain_community.agent_toolkits.pandas.base import create_pandas_dataframe_agent\n",
     "from langchain_experimental.autonomous_agents import AutoGPT\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "# Needed since jupyter runs an async eventloop\n",
+    "# Needed synce jupyter runs an async eventloop\n",
     "nest_asyncio.apply()"
    ]
   },
@@ -59,7 +57,7 @@
    },
    "outputs": [],
    "source": [
-    "llm = ChatOpenAI(model=\"gpt-4\", temperature=1.0)"
+    "llm = ChatOpenAI(model_name=\"gpt-4\", temperature=1.0)"
    ]
   },
   {
@@ -229,8 +227,8 @@
     "    BaseCombineDocumentsChain,\n",
     "    load_qa_with_sources_chain,\n",
     ")\n",
+    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
     "from langchain.tools import BaseTool, DuckDuckGoSearchRun\n",
-    "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
     "from pydantic import Field\n",
     "\n",
     "\n",

cookbook/camel_role_playing.ipynb

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

cookbook/code-analysis-deeplake.ipynb

@@ -24,7 +24,7 @@
    "source": [
     "1. Prepare data:\n",
     "   1. Upload all python project files using the `langchain_community.document_loaders.TextLoader`. We will call these files the **documents**.\n",
-    "   2. Split all documents to chunks using the `langchain_text_splitters.CharacterTextSplitter`.\n",
+    "   2. Split all documents to chunks using the `langchain.text_splitter.CharacterTextSplitter`.\n",
     "   3. Embed chunks and upload them into the DeepLake using `langchain.embeddings.openai.OpenAIEmbeddings` and `langchain_community.vectorstores.DeepLake`\n",
     "2. Question-Answering:\n",
     "   1. Build a chain from `langchain.chat_models.ChatOpenAI` and `langchain.chains.ConversationalRetrievalChain`\n",
@@ -621,7 +621,7 @@
     }
    ],
    "source": [
-    "from langchain_text_splitters import CharacterTextSplitter\n",
+    "from langchain.text_splitter import CharacterTextSplitter\n",
     "\n",
     "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
     "texts = text_splitter.split_documents(docs)\n",
@@ -933,7 +933,7 @@
       "**Answer**: The LangChain class includes various types of retrievers such as:\n",
       "\n",
       "- ArxivRetriever\n",
-      "- AzureAISearchRetriever\n",
+      "- AzureCognitiveSearchRetriever\n",
       "- BM25Retriever\n",
       "- ChaindeskRetriever\n",
       "- ChatGPTPluginRetriever\n",
@@ -993,7 +993,7 @@
     {
      "data": {
       "text/plain": [
-       "{'question': 'LangChain possesses a variety of retrievers including:\\n\\n1. ArxivRetriever\\n2. AzureAISearchRetriever\\n3. BM25Retriever\\n4. ChaindeskRetriever\\n5. ChatGPTPluginRetriever\\n6. ContextualCompressionRetriever\\n7. DocArrayRetriever\\n8. ElasticSearchBM25Retriever\\n9. EnsembleRetriever\\n10. GoogleVertexAISearchRetriever\\n11. AmazonKendraRetriever\\n12. KNNRetriever\\n13. LlamaIndexGraphRetriever\\n14. LlamaIndexRetriever\\n15. MergerRetriever\\n16. MetalRetriever\\n17. MilvusRetriever\\n18. MultiQueryRetriever\\n19. ParentDocumentRetriever\\n20. PineconeHybridSearchRetriever\\n21. PubMedRetriever\\n22. RePhraseQueryRetriever\\n23. RemoteLangChainRetriever\\n24. SelfQueryRetriever\\n25. SVMRetriever\\n26. TFIDFRetriever\\n27. TimeWeightedVectorStoreRetriever\\n28. VespaRetriever\\n29. WeaviateHybridSearchRetriever\\n30. WebResearchRetriever\\n31. WikipediaRetriever\\n32. ZepRetriever\\n33. ZillizRetriever\\n\\nIt also includes self query translators like:\\n\\n1. ChromaTranslator\\n2. DeepLakeTranslator\\n3. MyScaleTranslator\\n4. PineconeTranslator\\n5. QdrantTranslator\\n6. WeaviateTranslator\\n\\nAnd remote retrievers like:\\n\\n1. RemoteLangChainRetriever'}"
+       "{'question': 'LangChain possesses a variety of retrievers including:\\n\\n1. ArxivRetriever\\n2. AzureCognitiveSearchRetriever\\n3. BM25Retriever\\n4. ChaindeskRetriever\\n5. ChatGPTPluginRetriever\\n6. ContextualCompressionRetriever\\n7. DocArrayRetriever\\n8. ElasticSearchBM25Retriever\\n9. EnsembleRetriever\\n10. GoogleVertexAISearchRetriever\\n11. AmazonKendraRetriever\\n12. KNNRetriever\\n13. LlamaIndexGraphRetriever\\n14. LlamaIndexRetriever\\n15. MergerRetriever\\n16. MetalRetriever\\n17. MilvusRetriever\\n18. MultiQueryRetriever\\n19. ParentDocumentRetriever\\n20. PineconeHybridSearchRetriever\\n21. PubMedRetriever\\n22. RePhraseQueryRetriever\\n23. RemoteLangChainRetriever\\n24. SelfQueryRetriever\\n25. SVMRetriever\\n26. TFIDFRetriever\\n27. TimeWeightedVectorStoreRetriever\\n28. VespaRetriever\\n29. WeaviateHybridSearchRetriever\\n30. WebResearchRetriever\\n31. WikipediaRetriever\\n32. ZepRetriever\\n33. ZillizRetriever\\n\\nIt also includes self query translators like:\\n\\n1. ChromaTranslator\\n2. DeepLakeTranslator\\n3. MyScaleTranslator\\n4. PineconeTranslator\\n5. QdrantTranslator\\n6. WeaviateTranslator\\n\\nAnd remote retrievers like:\\n\\n1. RemoteLangChainRetriever'}"
       ]
      },
      "execution_count": 31,
@@ -1117,7 +1117,7 @@
       "The LangChain class includes various types of retrievers such as:\n",
       "\n",
       "- ArxivRetriever\n",
-      "- AzureAISearchRetriever\n",
+      "- AzureCognitiveSearchRetriever\n",
       "- BM25Retriever\n",
       "- ChaindeskRetriever\n",
       "- ChatGPTPluginRetriever\n",

cookbook/cql_agent.ipynb

@@ -1,557 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Setup Environment"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Python Modules"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Install the following Python modules:\n",
-    "\n",
-    "```bash\n",
-    "pip install ipykernel python-dotenv cassio pandas langchain_openai langchain langchain-community langchainhub langchain_experimental openai-multi-tool-use-parallel-patch\n",
-    "```"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Load the `.env` File"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Connection is via `cassio` using `auto=True` parameter, and the notebook uses OpenAI. You should create a `.env` file accordingly.\n",
-    "\n",
-    "For Cassandra, set:\n",
-    "```bash\n",
-    "CASSANDRA_CONTACT_POINTS\n",
-    "CASSANDRA_USERNAME\n",
-    "CASSANDRA_PASSWORD\n",
-    "CASSANDRA_KEYSPACE\n",
-    "```\n",
-    "\n",
-    "For Astra, set:\n",
-    "```bash\n",
-    "ASTRA_DB_APPLICATION_TOKEN\n",
-    "ASTRA_DB_DATABASE_ID\n",
-    "ASTRA_DB_KEYSPACE\n",
-    "```\n",
-    "\n",
-    "For example:\n",
-    "\n",
-    "```bash\n",
-    "# Connection to Astra:\n",
-    "ASTRA_DB_DATABASE_ID=a1b2c3d4-...\n",
-    "ASTRA_DB_APPLICATION_TOKEN=AstraCS:...\n",
-    "ASTRA_DB_KEYSPACE=notebooks\n",
-    "\n",
-    "# Also set \n",
-    "OPENAI_API_KEY=sk-....\n",
-    "```\n",
-    "\n",
-    "(You may also modify the below code to directly connect with `cassio`.)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from dotenv import load_dotenv\n",
-    "\n",
-    "load_dotenv(override=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Connect to Cassandra"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "\n",
-    "import cassio\n",
-    "\n",
-    "cassio.init(auto=True)\n",
-    "session = cassio.config.resolve_session()\n",
-    "if not session:\n",
-    "    raise Exception(\n",
-    "        \"Check environment configuration or manually configure cassio connection parameters\"\n",
-    "    )\n",
-    "\n",
-    "keyspace = os.environ.get(\n",
-    "    \"ASTRA_DB_KEYSPACE\", os.environ.get(\"CASSANDRA_KEYSPACE\", None)\n",
-    ")\n",
-    "if not keyspace:\n",
-    "    raise ValueError(\"a KEYSPACE environment variable must be set\")\n",
-    "\n",
-    "session.set_keyspace(keyspace)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Setup Database"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "This needs to be done one time only!"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Download Data"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The dataset used is from Kaggle, the [Environmental Sensor Telemetry Data](https://www.kaggle.com/datasets/garystafford/environmental-sensor-data-132k?select=iot_telemetry_data.csv). The next cell will download and unzip the data into a Pandas dataframe. The following cell is instructions to download manually. \n",
-    "\n",
-    "The net result of this section is you should have a Pandas dataframe variable `df`."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Download Automatically"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from io import BytesIO\n",
-    "from zipfile import ZipFile\n",
-    "\n",
-    "import pandas as pd\n",
-    "import requests\n",
-    "\n",
-    "datasetURL = \"https://storage.googleapis.com/kaggle-data-sets/788816/1355729/bundle/archive.zip?X-Goog-Algorithm=GOOG4-RSA-SHA256&X-Goog-Credential=gcp-kaggle-com%40kaggle-161607.iam.gserviceaccount.com%2F20240404%2Fauto%2Fstorage%2Fgoog4_request&X-Goog-Date=20240404T115828Z&X-Goog-Expires=259200&X-Goog-SignedHeaders=host&X-Goog-Signature=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\"\n",
-    "\n",
-    "response = requests.get(datasetURL)\n",
-    "if response.status_code == 200:\n",
-    "    zip_file = ZipFile(BytesIO(response.content))\n",
-    "    csv_file_name = zip_file.namelist()[0]\n",
-    "else:\n",
-    "    print(\"Failed to download the file\")\n",
-    "\n",
-    "with zip_file.open(csv_file_name) as csv_file:\n",
-    "    df = pd.read_csv(csv_file)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Download Manually"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "You can download the `.zip` file and unpack the `.csv` contained within. Comment in the next line, and adjust the path to this `.csv` file appropriately."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# df = pd.read_csv(\"/path/to/iot_telemetry_data.csv\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Load Data into Cassandra"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "This section assumes the existence of a dataframe `df`, the following cell validates its structure. The Download section above creates this object."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "assert df is not None, \"Dataframe 'df' must be set\"\n",
-    "expected_columns = [\n",
-    "    \"ts\",\n",
-    "    \"device\",\n",
-    "    \"co\",\n",
-    "    \"humidity\",\n",
-    "    \"light\",\n",
-    "    \"lpg\",\n",
-    "    \"motion\",\n",
-    "    \"smoke\",\n",
-    "    \"temp\",\n",
-    "]\n",
-    "assert all(\n",
-    "    [column in df.columns for column in expected_columns]\n",
-    "), \"DataFrame does not have the expected columns\""
-   ]
-  },
-  {
-   "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

@@ -42,9 +42,9 @@
     ")\n",
     "from langchain.chains import LLMChain\n",
     "from langchain.prompts import StringPromptTemplate\n",
+    "from langchain.schema import AgentAction, AgentFinish\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"
    ]
   },
@@ -114,8 +114,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "from langchain.schema import Document\n",
     "from langchain_community.vectorstores import FAISS\n",
-    "from langchain_core.documents import Document\n",
     "from langchain_openai import OpenAIEmbeddings"
    ]
   },
@@ -169,7 +169,7 @@
     "\n",
     "def get_tools(query):\n",
     "    # Get documents, which contain the Plugins to use\n",
-    "    docs = retriever.invoke(query)\n",
+    "    docs = retriever.get_relevant_documents(query)\n",
     "    # Get the toolkits, one for each plugin\n",
     "    tool_kits = [toolkits_dict[d.metadata[\"plugin_name\"]] for d in docs]\n",
     "    # Get the tools: a separate NLAChain for each endpoint\n",

cookbook/custom_agent_with_plugin_retrieval_using_plugnplai.ipynb

@@ -67,9 +67,9 @@
     ")\n",
     "from langchain.chains import LLMChain\n",
     "from langchain.prompts import StringPromptTemplate\n",
+    "from langchain.schema import AgentAction, AgentFinish\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"
    ]
   },
@@ -138,8 +138,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "from langchain.schema import Document\n",
     "from langchain_community.vectorstores import FAISS\n",
-    "from langchain_core.documents import Document\n",
     "from langchain_openai import OpenAIEmbeddings"
    ]
   },
@@ -193,7 +193,7 @@
     "\n",
     "def get_tools(query):\n",
     "    # Get documents, which contain the Plugins to use\n",
-    "    docs = retriever.invoke(query)\n",
+    "    docs = retriever.get_relevant_documents(query)\n",
     "    # Get the toolkits, one for each plugin\n",
     "    tool_kits = [toolkits_dict[d.metadata[\"plugin_name\"]] for d in docs]\n",
     "    # Get the tools: a separate NLAChain for each endpoint\n",

cookbook/custom_agent_with_tool_retrieval.ipynb

@@ -40,8 +40,8 @@
     ")\n",
     "from langchain.chains import LLMChain\n",
     "from langchain.prompts import StringPromptTemplate\n",
+    "from langchain.schema import AgentAction, AgentFinish\n",
     "from langchain_community.utilities import SerpAPIWrapper\n",
-    "from langchain_core.agents import AgentAction, AgentFinish\n",
     "from langchain_openai import OpenAI"
    ]
   },
@@ -103,8 +103,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "from langchain.schema import Document\n",
     "from langchain_community.vectorstores import FAISS\n",
-    "from langchain_core.documents import Document\n",
     "from langchain_openai import OpenAIEmbeddings"
    ]
   },
@@ -142,7 +142,7 @@
     "\n",
     "\n",
     "def get_tools(query):\n",
-    "    docs = retriever.invoke(query)\n",
+    "    docs = retriever.get_relevant_documents(query)\n",
     "    return [ALL_TOOLS[d.metadata[\"index\"]] for d in docs]"
    ]
   },

cookbook/custom_multi_action_agent.ipynb

@@ -72,7 +72,7 @@
    "source": [
     "from typing import Any, List, Tuple, Union\n",
     "\n",
-    "from langchain_core.agents import AgentAction, AgentFinish\n",
+    "from langchain.schema import AgentAction, AgentFinish\n",
     "\n",
     "\n",
     "class FakeAgent(BaseMultiActionAgent):\n",

cookbook/databricks_sql_db.ipynb

@@ -166,7 +166,7 @@
    "source": [
     "### SQL Database Agent example\n",
     "\n",
-    "This example demonstrates the use of the [SQL Database Agent](/docs/integrations/tools/sql_database) for answering questions over a Databricks database."
+    "This example demonstrates the use of the [SQL Database Agent](/docs/integrations/toolkits/sql_database.html) for answering questions over a Databricks database."
    ]
   },
   {

cookbook/deeplake_semantic_search_over_chat.ipynb

@@ -52,12 +52,12 @@
     "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",
+    "from langchain.text_splitter import (\n",
     "    CharacterTextSplitter,\n",
     "    RecursiveCharacterTextSplitter,\n",
     ")\n",
+    "from langchain_community.vectorstores import DeepLake\n",
+    "from langchain_openai import OpenAI, OpenAIEmbeddings\n",
     "\n",
     "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
     "activeloop_token = getpass.getpass(\"Activeloop Token:\")\n",

cookbook/docugami_xml_kg_rag.ipynb

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

cookbook/elasticsearch_db_qa.ipynb

@@ -84,7 +84,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "llm = ChatOpenAI(model=\"gpt-4\", temperature=0)\n",
+    "llm = ChatOpenAI(model_name=\"gpt-4\", temperature=0)\n",
     "chain = ElasticsearchDatabaseChain.from_llm(llm=llm, database=db, verbose=True)"
    ]
   },

cookbook/fake_llm.ipynb

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

cookbook/fireworks_rag.ipynb

@@ -1,245 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "0fc0309d-4d49-4bb5-bec0-bd92c6fddb28",
-   "metadata": {},
-   "source": [
-    "## Fireworks.AI + LangChain + RAG\n",
-    " \n",
-    "[Fireworks AI](https://python.langchain.com/docs/integrations/llms/fireworks) wants to provide the best experience when working with LangChain, and here is an example of Fireworks + LangChain doing RAG\n",
-    "\n",
-    "See [our models page](https://fireworks.ai/models) for the full list of models. We use `accounts/fireworks/models/mixtral-8x7b-instruct` for RAG In this tutorial.\n",
-    "\n",
-    "For the RAG target, we will use the Gemma technical report https://storage.googleapis.com/deepmind-media/gemma/gemma-report.pdf "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "d12fb75a-f707-48d5-82a5-efe2d041813c",
-   "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 is available: \u001b[0m\u001b[31;49m23.2.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.0\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",
-      "Found existing installation: langchain-fireworks 0.0.1\n",
-      "Uninstalling langchain-fireworks-0.0.1:\n",
-      "  Successfully uninstalled langchain-fireworks-0.0.1\n",
-      "Note: you may need to restart the kernel to use updated packages.\n",
-      "Obtaining file:///mnt/disks/data/langchain/libs/partners/fireworks\n",
-      "  Installing build dependencies ... \u001b[?25ldone\n",
-      "\u001b[?25h  Checking if build backend supports build_editable ... \u001b[?25ldone\n",
-      "\u001b[?25h  Getting requirements to build editable ... \u001b[?25ldone\n",
-      "\u001b[?25h  Preparing editable metadata (pyproject.toml) ... \u001b[?25ldone\n",
-      "\u001b[?25hRequirement already satisfied: aiohttp<4.0.0,>=3.9.1 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from langchain-fireworks==0.0.1) (3.9.3)\n",
-      "Requirement already satisfied: fireworks-ai<0.13.0,>=0.12.0 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from langchain-fireworks==0.0.1) (0.12.0)\n",
-      "Requirement already satisfied: langchain-core<0.2,>=0.1 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from langchain-fireworks==0.0.1) (0.1.23)\n",
-      "Requirement already satisfied: requests<3,>=2 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from langchain-fireworks==0.0.1) (2.31.0)\n",
-      "Requirement already satisfied: aiosignal>=1.1.2 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from aiohttp<4.0.0,>=3.9.1->langchain-fireworks==0.0.1) (1.3.1)\n",
-      "Requirement already satisfied: attrs>=17.3.0 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from aiohttp<4.0.0,>=3.9.1->langchain-fireworks==0.0.1) (23.1.0)\n",
-      "Requirement already satisfied: frozenlist>=1.1.1 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from aiohttp<4.0.0,>=3.9.1->langchain-fireworks==0.0.1) (1.4.0)\n",
-      "Requirement already satisfied: multidict<7.0,>=4.5 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from aiohttp<4.0.0,>=3.9.1->langchain-fireworks==0.0.1) (6.0.4)\n",
-      "Requirement already satisfied: yarl<2.0,>=1.0 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from aiohttp<4.0.0,>=3.9.1->langchain-fireworks==0.0.1) (1.9.2)\n",
-      "Requirement already satisfied: async-timeout<5.0,>=4.0 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from aiohttp<4.0.0,>=3.9.1->langchain-fireworks==0.0.1) (4.0.3)\n",
-      "Requirement already satisfied: httpx in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from fireworks-ai<0.13.0,>=0.12.0->langchain-fireworks==0.0.1) (0.26.0)\n",
-      "Requirement already satisfied: httpx-sse in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from fireworks-ai<0.13.0,>=0.12.0->langchain-fireworks==0.0.1) (0.4.0)\n",
-      "Requirement already satisfied: pydantic in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from fireworks-ai<0.13.0,>=0.12.0->langchain-fireworks==0.0.1) (2.4.2)\n",
-      "Requirement already satisfied: Pillow in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from fireworks-ai<0.13.0,>=0.12.0->langchain-fireworks==0.0.1) (10.2.0)\n",
-      "Requirement already satisfied: PyYAML>=5.3 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from langchain-core<0.2,>=0.1->langchain-fireworks==0.0.1) (6.0.1)\n",
-      "Requirement already satisfied: anyio<5,>=3 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from langchain-core<0.2,>=0.1->langchain-fireworks==0.0.1) (3.7.1)\n",
-      "Requirement already satisfied: jsonpatch<2.0,>=1.33 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from langchain-core<0.2,>=0.1->langchain-fireworks==0.0.1) (1.33)\n",
-      "Requirement already satisfied: langsmith<0.2.0,>=0.1.0 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from langchain-core<0.2,>=0.1->langchain-fireworks==0.0.1) (0.1.5)\n",
-      "Requirement already satisfied: packaging<24.0,>=23.2 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from langchain-core<0.2,>=0.1->langchain-fireworks==0.0.1) (23.2)\n",
-      "Requirement already satisfied: tenacity<9.0.0,>=8.1.0 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from langchain-core<0.2,>=0.1->langchain-fireworks==0.0.1) (8.2.3)\n",
-      "Requirement already satisfied: charset-normalizer<4,>=2 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from requests<3,>=2->langchain-fireworks==0.0.1) (3.3.0)\n",
-      "Requirement already satisfied: idna<4,>=2.5 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from requests<3,>=2->langchain-fireworks==0.0.1) (3.4)\n",
-      "Requirement already satisfied: urllib3<3,>=1.21.1 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from requests<3,>=2->langchain-fireworks==0.0.1) (2.0.6)\n",
-      "Requirement already satisfied: certifi>=2017.4.17 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from requests<3,>=2->langchain-fireworks==0.0.1) (2023.7.22)\n",
-      "Requirement already satisfied: sniffio>=1.1 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from anyio<5,>=3->langchain-core<0.2,>=0.1->langchain-fireworks==0.0.1) (1.3.0)\n",
-      "Requirement already satisfied: exceptiongroup in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from anyio<5,>=3->langchain-core<0.2,>=0.1->langchain-fireworks==0.0.1) (1.1.3)\n",
-      "Requirement already satisfied: jsonpointer>=1.9 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from jsonpatch<2.0,>=1.33->langchain-core<0.2,>=0.1->langchain-fireworks==0.0.1) (2.4)\n",
-      "Requirement already satisfied: annotated-types>=0.4.0 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from pydantic->fireworks-ai<0.13.0,>=0.12.0->langchain-fireworks==0.0.1) (0.5.0)\n",
-      "Requirement already satisfied: pydantic-core==2.10.1 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from pydantic->fireworks-ai<0.13.0,>=0.12.0->langchain-fireworks==0.0.1) (2.10.1)\n",
-      "Requirement already satisfied: typing-extensions>=4.6.1 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from pydantic->fireworks-ai<0.13.0,>=0.12.0->langchain-fireworks==0.0.1) (4.8.0)\n",
-      "Requirement already satisfied: httpcore==1.* in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from httpx->fireworks-ai<0.13.0,>=0.12.0->langchain-fireworks==0.0.1) (1.0.2)\n",
-      "Requirement already satisfied: h11<0.15,>=0.13 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from httpcore==1.*->httpx->fireworks-ai<0.13.0,>=0.12.0->langchain-fireworks==0.0.1) (0.14.0)\n",
-      "Building wheels for collected packages: langchain-fireworks\n",
-      "  Building editable for langchain-fireworks (pyproject.toml) ... \u001b[?25ldone\n",
-      "\u001b[?25h  Created wheel for langchain-fireworks: filename=langchain_fireworks-0.0.1-py3-none-any.whl size=2228 sha256=564071b120b09ec31f2dc737733448a33bbb26e40b49fcde0c129ad26045259d\n",
-      "  Stored in directory: /tmp/pip-ephem-wheel-cache-oz368vdk/wheels/e0/ad/31/d7e76dd73d61905ff7f369f5b0d21a4b5e7af4d3cb7487aece\n",
-      "Successfully built langchain-fireworks\n",
-      "Installing collected packages: langchain-fireworks\n",
-      "Successfully installed langchain-fireworks-0.0.1\n",
-      "\n",
-      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.2.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.0\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 --quiet pypdf langchain-chroma tiktoken openai \n",
-    "%pip uninstall -y langchain-fireworks\n",
-    "%pip install --editable /mnt/disks/data/langchain/libs/partners/fireworks"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "cf719376",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "<module 'fireworks' from '/mnt/disks/data/langchain/.venv/lib/python3.9/site-packages/fireworks/__init__.py'>\n"
-     ]
-    }
-   ],
-   "source": [
-    "import fireworks\n",
-    "\n",
-    "print(fireworks)\n",
-    "import fireworks.client"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "9ab49327-0532-4480-804c-d066c302a322",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Load\n",
-    "import requests\n",
-    "from langchain_community.document_loaders import PyPDFLoader\n",
-    "\n",
-    "# Download the PDF from a URL and save it to a temporary location\n",
-    "url = \"https://storage.googleapis.com/deepmind-media/gemma/gemma-report.pdf\"\n",
-    "response = requests.get(url, stream=True)\n",
-    "file_name = \"temp_file.pdf\"\n",
-    "with open(file_name, \"wb\") as pdf:\n",
-    "    pdf.write(response.content)\n",
-    "\n",
-    "loader = PyPDFLoader(file_name)\n",
-    "data = loader.load()\n",
-    "\n",
-    "# Split\n",
-    "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
-    "\n",
-    "text_splitter = RecursiveCharacterTextSplitter(chunk_size=2000, chunk_overlap=0)\n",
-    "all_splits = text_splitter.split_documents(data)\n",
-    "\n",
-    "# Add to vectorDB\n",
-    "from langchain_chroma import Chroma\n",
-    "from langchain_fireworks.embeddings import FireworksEmbeddings\n",
-    "\n",
-    "vectorstore = Chroma.from_documents(\n",
-    "    documents=all_splits,\n",
-    "    collection_name=\"rag-chroma\",\n",
-    "    embedding=FireworksEmbeddings(),\n",
-    ")\n",
-    "\n",
-    "retriever = vectorstore.as_retriever()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "4efaddd9-3dbb-455c-ba54-0ad7f2d2ce0f",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_core.pydantic_v1 import BaseModel\n",
-    "from langchain_core.runnables import RunnableParallel, RunnablePassthrough\n",
-    "\n",
-    "# RAG prompt\n",
-    "template = \"\"\"Answer the question based only on the following context:\n",
-    "{context}\n",
-    "\n",
-    "Question: {question}\n",
-    "\"\"\"\n",
-    "prompt = ChatPromptTemplate.from_template(template)\n",
-    "\n",
-    "# LLM\n",
-    "from langchain_together import Together\n",
-    "\n",
-    "llm = Together(\n",
-    "    model=\"mistralai/Mixtral-8x7B-Instruct-v0.1\",\n",
-    "    temperature=0.0,\n",
-    "    max_tokens=2000,\n",
-    "    top_k=1,\n",
-    ")\n",
-    "\n",
-    "# RAG chain\n",
-    "chain = (\n",
-    "    RunnableParallel({\"context\": retriever, \"question\": RunnablePassthrough()})\n",
-    "    | prompt\n",
-    "    | llm\n",
-    "    | StrOutputParser()\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "88b1ee51-1b0f-4ebf-bb32-e50e843f0eeb",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'\\nAnswer: The architectural details of Mixtral are as follows:\\n- Dimension (dim): 4096\\n- Number of layers (n\\\\_layers): 32\\n- Dimension of each head (head\\\\_dim): 128\\n- Hidden dimension (hidden\\\\_dim): 14336\\n- Number of heads (n\\\\_heads): 32\\n- Number of kv heads (n\\\\_kv\\\\_heads): 8\\n- Context length (context\\\\_len): 32768\\n- Vocabulary size (vocab\\\\_size): 32000\\n- Number of experts (num\\\\_experts): 8\\n- Number of top k experts (top\\\\_k\\\\_experts): 2\\n\\nMixtral is based on a transformer architecture and uses the same modifications as described in [18], with the notable exceptions that Mixtral supports a fully dense context length of 32k tokens, and the feedforward block picks from a set of 8 distinct groups of parameters. At every layer, for every token, a router network chooses two of these groups (the “experts”) to process the token and combine their output additively. This technique increases the number of parameters of a model while controlling cost and latency, as the model only uses a fraction of the total set of parameters per token. Mixtral is pretrained with multilingual data using a context size of 32k tokens. It either matches or exceeds the performance of Llama 2 70B and GPT-3.5, over several benchmarks. In particular, Mixtral vastly outperforms Llama 2 70B on mathematics, code generation, and multilingual benchmarks.'"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.invoke(\"What are the Architectural details of Mixtral?\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "755cf871-26b7-4e30-8b91-9ffd698470f4",
-   "metadata": {},
-   "source": [
-    "Trace: \n",
-    "\n",
-    "https://smith.langchain.com/public/935fd642-06a6-4b42-98e3-6074f93115cd/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": "3.9.12"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

cookbook/forward_looking_retrieval_augmented_generation.ipynb

@@ -73,9 +73,8 @@
     "    AsyncCallbackManagerForRetrieverRun,\n",
     "    CallbackManagerForRetrieverRun,\n",
     ")\n",
+    "from langchain.schema import BaseRetriever, Document\n",
     "from langchain_community.utilities import GoogleSerperAPIWrapper\n",
-    "from langchain_core.documents import Document\n",
-    "from langchain_core.retrievers import BaseRetriever\n",
     "from langchain_openai import ChatOpenAI, OpenAI"
    ]
   },
@@ -362,7 +361,7 @@
    ],
    "source": [
     "llm = OpenAI()\n",
-    "llm.invoke(query)"
+    "llm(query)"
    ]
   },
   {

cookbook/gymnasium_agent_simulation.ipynb

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

cookbook/hypothetical_document_embeddings.ipynb

@@ -170,8 +170,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_chroma import Chroma\n",
-    "from langchain_text_splitters import CharacterTextSplitter\n",
+    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "\n",
     "with open(\"../../state_of_the_union.txt\") as f:\n",
     "    state_of_the_union = f.read()\n",

cookbook/llm_bash.ipynb

@@ -52,7 +52,7 @@
     "\n",
     "bash_chain = LLMBashChain.from_llm(llm, verbose=True)\n",
     "\n",
-    "bash_chain.invoke(text)"
+    "bash_chain.run(text)"
    ]
   },
   {
@@ -135,7 +135,7 @@
     "\n",
     "text = \"Please write a bash script that prints 'Hello World' to the console.\"\n",
     "\n",
-    "bash_chain.invoke(text)"
+    "bash_chain.run(text)"
    ]
   },
   {
@@ -190,7 +190,7 @@
     "\n",
     "text = \"List the current directory then move up a level.\"\n",
     "\n",
-    "bash_chain.invoke(text)"
+    "bash_chain.run(text)"
    ]
   },
   {
@@ -231,7 +231,7 @@
    ],
    "source": [
     "# Run the same command again and see that the state is maintained between calls\n",
-    "bash_chain.invoke(text)"
+    "bash_chain.run(text)"
    ]
   }
  ],

cookbook/llm_checker.ipynb

@@ -50,7 +50,7 @@
     "\n",
     "checker_chain = LLMCheckerChain.from_llm(llm, verbose=True)\n",
     "\n",
-    "checker_chain.invoke(text)"
+    "checker_chain.run(text)"
    ]
   },
   {

cookbook/llm_math.ipynb

@@ -51,7 +51,7 @@
     "llm = OpenAI(temperature=0)\n",
     "llm_math = LLMMathChain.from_llm(llm, verbose=True)\n",
     "\n",
-    "llm_math.invoke(\"What is 13 raised to the .3432 power?\")"
+    "llm_math.run(\"What is 13 raised to the .3432 power?\")"
    ]
   },
   {

cookbook/llm_symbolic_math.ipynb

@@ -45,7 +45,7 @@
     }
    ],
    "source": [
-    "llm_symbolic_math.invoke(\"What is the derivative of sin(x)*exp(x) with respect to x?\")"
+    "llm_symbolic_math.run(\"What is the derivative of sin(x)*exp(x) with respect to x?\")"
    ]
   },
   {
@@ -65,7 +65,7 @@
     }
    ],
    "source": [
-    "llm_symbolic_math.invoke(\n",
+    "llm_symbolic_math.run(\n",
     "    \"What is the integral of exp(x)*sin(x) + exp(x)*cos(x) with respect to x?\"\n",
     ")"
    ]
@@ -94,7 +94,7 @@
     }
    ],
    "source": [
-    "llm_symbolic_math.invoke('Solve the differential equation y\" - y = e^t')"
+    "llm_symbolic_math.run('Solve the differential equation y\" - y = e^t')"
    ]
   },
   {
@@ -114,7 +114,7 @@
     }
    ],
    "source": [
-    "llm_symbolic_math.invoke(\"What are the solutions to this equation y^3 + 1/3y?\")"
+    "llm_symbolic_math.run(\"What are the solutions to this equation y^3 + 1/3y?\")"
    ]
   },
   {
@@ -134,7 +134,7 @@
     }
    ],
    "source": [
-    "llm_symbolic_math.invoke(\"x = y + 5, y = z - 3, z = x * y. Solve for x, y, z\")"
+    "llm_symbolic_math.run(\"x = y + 5, y = z - 3, z = x * y. Solve for x, y, z\")"
    ]
   }
  ],

cookbook/mongodb-langchain-cache-memory.ipynb

@@ -1,818 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "70b333e6",
-   "metadata": {},
-   "source": [
-    "[![View Article](https://img.shields.io/badge/View%20Article-blue)](https://www.mongodb.com/developer/products/atlas/advanced-rag-langchain-mongodb/)\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "d84a72ea",
-   "metadata": {},
-   "source": [
-    "# Adding Semantic Caching and Memory to your RAG Application using MongoDB and LangChain\n",
-    "\n",
-    "In this notebook, we will see how to use the new MongoDBCache and MongoDBChatMessageHistory in your RAG application.\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "65527202",
-   "metadata": {},
-   "source": [
-    "## Step 1: Install required libraries\n",
-    "\n",
-    "- **datasets**: Python library to get access to datasets available on Hugging Face Hub\n",
-    "\n",
-    "- **langchain**: Python toolkit for LangChain\n",
-    "\n",
-    "- **langchain-mongodb**: Python package to use MongoDB as a vector store, semantic cache, chat history store etc. in LangChain\n",
-    "\n",
-    "- **langchain-openai**: Python package to use OpenAI models with LangChain\n",
-    "\n",
-    "- **pymongo**: Python toolkit for MongoDB\n",
-    "\n",
-    "- **pandas**: Python library for data analysis, exploration, and manipulation"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "cbc22fa4",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "! pip install -qU datasets langchain langchain-mongodb langchain-openai pymongo pandas"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "39c41e87",
-   "metadata": {},
-   "source": [
-    "## Step 2: Setup pre-requisites\n",
-    "\n",
-    "* Set the MongoDB connection string. Follow the steps [here](https://www.mongodb.com/docs/manual/reference/connection-string/) to get the connection string from the Atlas UI.\n",
-    "\n",
-    "* Set the OpenAI API key. Steps to obtain an API key as [here](https://help.openai.com/en/articles/4936850-where-do-i-find-my-openai-api-key)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "b56412ae",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import getpass"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "16a20d7a",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Enter your MongoDB connection string:········\n"
-     ]
-    }
-   ],
-   "source": [
-    "MONGODB_URI = getpass.getpass(\"Enter your MongoDB connection string:\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "978682d4",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Enter your OpenAI API key:········\n"
-     ]
-    }
-   ],
-   "source": [
-    "OPENAI_API_KEY = getpass.getpass(\"Enter your OpenAI API key:\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "606081c5",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "········\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Optional-- If you want to enable Langsmith -- good for debugging\n",
-    "import os\n",
-    "\n",
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "f6b8302c",
-   "metadata": {},
-   "source": [
-    "## Step 3: Download the dataset\n",
-    "\n",
-    "We will be using MongoDB's [embedded_movies](https://huggingface.co/datasets/MongoDB/embedded_movies) dataset"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "1a3433a6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import pandas as pd\n",
-    "from datasets import load_dataset"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "aee5311b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Ensure you have an HF_TOKEN in your development enviornment:\n",
-    "# access tokens can be created or copied from the Hugging Face platform (https://huggingface.co/docs/hub/en/security-tokens)\n",
-    "\n",
-    "# Load MongoDB's embedded_movies dataset from Hugging Face\n",
-    "# https://huggingface.co/datasets/MongoDB/airbnb_embeddings\n",
-    "\n",
-    "data = load_dataset(\"MongoDB/embedded_movies\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "1d630a26",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df = pd.DataFrame(data[\"train\"])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "a1f94f43",
-   "metadata": {},
-   "source": [
-    "## Step 4: Data analysis\n",
-    "\n",
-    "Make sure length of the dataset is what we expect, drop Nones etc."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "b276df71",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>fullplot</th>\n",
-       "      <th>type</th>\n",
-       "      <th>plot_embedding</th>\n",
-       "      <th>num_mflix_comments</th>\n",
-       "      <th>runtime</th>\n",
-       "      <th>writers</th>\n",
-       "      <th>imdb</th>\n",
-       "      <th>countries</th>\n",
-       "      <th>rated</th>\n",
-       "      <th>plot</th>\n",
-       "      <th>title</th>\n",
-       "      <th>languages</th>\n",
-       "      <th>metacritic</th>\n",
-       "      <th>directors</th>\n",
-       "      <th>awards</th>\n",
-       "      <th>genres</th>\n",
-       "      <th>poster</th>\n",
-       "      <th>cast</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>Young Pauline is left a lot of money when her ...</td>\n",
-       "      <td>movie</td>\n",
-       "      <td>[0.00072939653, -0.026834568, 0.013515796, -0....</td>\n",
-       "      <td>0</td>\n",
-       "      <td>199.0</td>\n",
-       "      <td>[Charles W. Goddard (screenplay), Basil Dickey...</td>\n",
-       "      <td>{'id': 4465, 'rating': 7.6, 'votes': 744}</td>\n",
-       "      <td>[USA]</td>\n",
-       "      <td>None</td>\n",
-       "      <td>Young Pauline is left a lot of money when her ...</td>\n",
-       "      <td>The Perils of Pauline</td>\n",
-       "      <td>[English]</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[Louis J. Gasnier, Donald MacKenzie]</td>\n",
-       "      <td>{'nominations': 0, 'text': '1 win.', 'wins': 1}</td>\n",
-       "      <td>[Action]</td>\n",
-       "      <td>https://m.media-amazon.com/images/M/MV5BMzgxOD...</td>\n",
-       "      <td>[Pearl White, Crane Wilbur, Paul Panzer, Edwar...</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                                            fullplot   type  \\\n",
-       "0  Young Pauline is left a lot of money when her ...  movie   \n",
-       "\n",
-       "                                      plot_embedding  num_mflix_comments  \\\n",
-       "0  [0.00072939653, -0.026834568, 0.013515796, -0....                   0   \n",
-       "\n",
-       "   runtime                                            writers  \\\n",
-       "0    199.0  [Charles W. Goddard (screenplay), Basil Dickey...   \n",
-       "\n",
-       "                                        imdb countries rated  \\\n",
-       "0  {'id': 4465, 'rating': 7.6, 'votes': 744}     [USA]  None   \n",
-       "\n",
-       "                                                plot                  title  \\\n",
-       "0  Young Pauline is left a lot of money when her ...  The Perils of Pauline   \n",
-       "\n",
-       "   languages  metacritic                             directors  \\\n",
-       "0  [English]         NaN  [Louis J. Gasnier, Donald MacKenzie]   \n",
-       "\n",
-       "                                            awards    genres  \\\n",
-       "0  {'nominations': 0, 'text': '1 win.', 'wins': 1}  [Action]   \n",
-       "\n",
-       "                                              poster  \\\n",
-       "0  https://m.media-amazon.com/images/M/MV5BMzgxOD...   \n",
-       "\n",
-       "                                                cast  \n",
-       "0  [Pearl White, Crane Wilbur, Paul Panzer, Edwar...  "
-      ]
-     },
-     "execution_count": 10,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Previewing the contents of the data\n",
-    "df.head(1)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "22ab375d",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Only keep records where the fullplot field is not null\n",
-    "df = df[df[\"fullplot\"].notna()]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "fceed99a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Renaming the embedding field to \"embedding\" -- required by LangChain\n",
-    "df.rename(columns={\"plot_embedding\": \"embedding\"}, inplace=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "aedec13a",
-   "metadata": {},
-   "source": [
-    "## Step 5: Create a simple RAG chain using MongoDB as the vector store"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "11d292f3",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_mongodb import MongoDBAtlasVectorSearch\n",
-    "from pymongo import MongoClient\n",
-    "\n",
-    "# Initialize MongoDB python client\n",
-    "client = MongoClient(MONGODB_URI, appname=\"devrel.content.python\")\n",
-    "\n",
-    "DB_NAME = \"langchain_chatbot\"\n",
-    "COLLECTION_NAME = \"data\"\n",
-    "ATLAS_VECTOR_SEARCH_INDEX_NAME = \"vector_index\"\n",
-    "collection = client[DB_NAME][COLLECTION_NAME]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "d8292d53",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "DeleteResult({'n': 1000, 'electionId': ObjectId('7fffffff00000000000000f6'), 'opTime': {'ts': Timestamp(1710523288, 1033), 't': 246}, 'ok': 1.0, '$clusterTime': {'clusterTime': Timestamp(1710523288, 1042), 'signature': {'hash': b\"i\\xa8\\xe9'\\x1ed\\xf2u\\xf3L\\xff\\xb1\\xf5\\xbfA\\x90\\xabJ\\x12\\x83\", 'keyId': 7299545392000008318}}, 'operationTime': Timestamp(1710523288, 1033)}, acknowledged=True)"
-      ]
-     },
-     "execution_count": 14,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Delete any existing records in the collection\n",
-    "collection.delete_many({})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "id": "36c68914",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Data ingestion into MongoDB completed\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Data Ingestion\n",
-    "records = df.to_dict(\"records\")\n",
-    "collection.insert_many(records)\n",
-    "\n",
-    "print(\"Data ingestion into MongoDB completed\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "id": "cbfca0b8",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_openai import OpenAIEmbeddings\n",
-    "\n",
-    "# Using the text-embedding-ada-002 since that's what was used to create embeddings in the movies dataset\n",
-    "embeddings = OpenAIEmbeddings(\n",
-    "    openai_api_key=OPENAI_API_KEY, model=\"text-embedding-ada-002\"\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 19,
-   "id": "798e176c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Vector Store Creation\n",
-    "vector_store = MongoDBAtlasVectorSearch.from_connection_string(\n",
-    "    connection_string=MONGODB_URI,\n",
-    "    namespace=DB_NAME + \".\" + COLLECTION_NAME,\n",
-    "    embedding=embeddings,\n",
-    "    index_name=ATLAS_VECTOR_SEARCH_INDEX_NAME,\n",
-    "    text_key=\"fullplot\",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 49,
-   "id": "c71cd087",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Using the MongoDB vector store as a retriever in a RAG chain\n",
-    "retriever = vector_store.as_retriever(search_type=\"similarity\", search_kwargs={\"k\": 5})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 25,
-   "id": "b6588cd3",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_core.runnables import RunnablePassthrough\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "# Generate context using the retriever, and pass the user question through\n",
-    "retrieve = {\n",
-    "    \"context\": retriever | (lambda docs: \"\\n\\n\".join([d.page_content for d in docs])),\n",
-    "    \"question\": RunnablePassthrough(),\n",
-    "}\n",
-    "template = \"\"\"Answer the question based only on the following context: \\\n",
-    "{context}\n",
-    "\n",
-    "Question: {question}\n",
-    "\"\"\"\n",
-    "# Defining the chat prompt\n",
-    "prompt = ChatPromptTemplate.from_template(template)\n",
-    "# Defining the model to be used for chat completion\n",
-    "model = ChatOpenAI(temperature=0, openai_api_key=OPENAI_API_KEY)\n",
-    "# Parse output as a string\n",
-    "parse_output = StrOutputParser()\n",
-    "\n",
-    "# Naive RAG chain\n",
-    "naive_rag_chain = retrieve | prompt | model | parse_output"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 26,
-   "id": "aaae21f5",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Once a Thief'"
-      ]
-     },
-     "execution_count": 26,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "naive_rag_chain.invoke(\"What is the best movie to watch when sad?\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "75f929ef",
-   "metadata": {},
-   "source": [
-    "## Step 6: Create a RAG chain with chat history"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 27,
-   "id": "94e7bd4a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.prompts import MessagesPlaceholder\n",
-    "from langchain_core.runnables.history import RunnableWithMessageHistory\n",
-    "from langchain_mongodb.chat_message_histories import MongoDBChatMessageHistory"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 29,
-   "id": "5bb30860",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def get_session_history(session_id: str) -> MongoDBChatMessageHistory:\n",
-    "    return MongoDBChatMessageHistory(\n",
-    "        MONGODB_URI, session_id, database_name=DB_NAME, collection_name=\"history\"\n",
-    "    )"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 50,
-   "id": "f51d0f35",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Given a follow-up question and history, create a standalone question\n",
-    "standalone_system_prompt = \"\"\"\n",
-    "Given a chat history and a follow-up question, rephrase the follow-up question to be a standalone question. \\\n",
-    "Do NOT answer the question, just reformulate it if needed, otherwise return it as is. \\\n",
-    "Only return the final standalone question. \\\n",
-    "\"\"\"\n",
-    "standalone_question_prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\"system\", standalone_system_prompt),\n",
-    "        MessagesPlaceholder(variable_name=\"history\"),\n",
-    "        (\"human\", \"{question}\"),\n",
-    "    ]\n",
-    ")\n",
-    "\n",
-    "question_chain = standalone_question_prompt | model | parse_output"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 51,
-   "id": "f3ef3354",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Generate context by passing output of the question_chain i.e. the standalone question to the retriever\n",
-    "retriever_chain = RunnablePassthrough.assign(\n",
-    "    context=question_chain\n",
-    "    | retriever\n",
-    "    | (lambda docs: \"\\n\\n\".join([d.page_content for d in docs]))\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 55,
-   "id": "5afb7345",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Create a prompt that includes the context, history and the follow-up question\n",
-    "rag_system_prompt = \"\"\"Answer the question based only on the following context: \\\n",
-    "{context}\n",
-    "\"\"\"\n",
-    "rag_prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\"system\", rag_system_prompt),\n",
-    "        MessagesPlaceholder(variable_name=\"history\"),\n",
-    "        (\"human\", \"{question}\"),\n",
-    "    ]\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 56,
-   "id": "f95f47d0",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# RAG chain\n",
-    "rag_chain = retriever_chain | rag_prompt | model | parse_output"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 57,
-   "id": "9618d395",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'The best movie to watch when feeling down could be \"Last Action Hero.\" It\\'s a fun and action-packed film that blends reality and fantasy, offering an escape from the real world and providing an entertaining distraction.'"
-      ]
-     },
-     "execution_count": 57,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# RAG chain with history\n",
-    "with_message_history = RunnableWithMessageHistory(\n",
-    "    rag_chain,\n",
-    "    get_session_history,\n",
-    "    input_messages_key=\"question\",\n",
-    "    history_messages_key=\"history\",\n",
-    ")\n",
-    "with_message_history.invoke(\n",
-    "    {\"question\": \"What is the best movie to watch when sad?\"},\n",
-    "    {\"configurable\": {\"session_id\": \"1\"}},\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 58,
-   "id": "6e3080d1",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'I apologize for the confusion. Another movie that might lift your spirits when you\\'re feeling sad is \"Smilla\\'s Sense of Snow.\" It\\'s a mystery thriller that could engage your mind and distract you from your sadness with its intriguing plot and suspenseful storyline.'"
-      ]
-     },
-     "execution_count": 58,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "with_message_history.invoke(\n",
-    "    {\n",
-    "        \"question\": \"Hmmm..I don't want to watch that one. Can you suggest something else?\"\n",
-    "    },\n",
-    "    {\"configurable\": {\"session_id\": \"1\"}},\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 59,
-   "id": "daea2953",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'For a lighter movie option, you might enjoy \"Cousins.\" It\\'s a comedy film set in Barcelona with action and humor, offering a fun and entertaining escape from reality. The storyline is engaging and filled with comedic moments that could help lift your spirits.'"
-      ]
-     },
-     "execution_count": 59,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "with_message_history.invoke(\n",
-    "    {\"question\": \"How about something more light?\"},\n",
-    "    {\"configurable\": {\"session_id\": \"1\"}},\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0de23a88",
-   "metadata": {},
-   "source": [
-    "## Step 7: Get faster responses using Semantic Cache\n",
-    "\n",
-    "**NOTE:** Semantic cache only caches the input to the LLM. When using it in retrieval chains, remember that documents retrieved can change between runs resulting in cache misses for semantically similar queries."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 61,
-   "id": "5d6b6741",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.globals import set_llm_cache\n",
-    "from langchain_mongodb.cache import MongoDBAtlasSemanticCache\n",
-    "\n",
-    "set_llm_cache(\n",
-    "    MongoDBAtlasSemanticCache(\n",
-    "        connection_string=MONGODB_URI,\n",
-    "        embedding=embeddings,\n",
-    "        collection_name=\"semantic_cache\",\n",
-    "        database_name=DB_NAME,\n",
-    "        index_name=ATLAS_VECTOR_SEARCH_INDEX_NAME,\n",
-    "        wait_until_ready=True,  # Optional, waits until the cache is ready to be used\n",
-    "    )\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 62,
-   "id": "9825bc7b",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "CPU times: user 87.8 ms, sys: 670 µs, total: 88.5 ms\n",
-      "Wall time: 1.24 s\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'Once a Thief'"
-      ]
-     },
-     "execution_count": 62,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "%%time\n",
-    "naive_rag_chain.invoke(\"What is the best movie to watch when sad?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 63,
-   "id": "a5e518cf",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "CPU times: user 43.5 ms, sys: 4.16 ms, total: 47.7 ms\n",
-      "Wall time: 255 ms\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'Once a Thief'"
-      ]
-     },
-     "execution_count": 63,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "%%time\n",
-    "naive_rag_chain.invoke(\"What is the best movie to watch when sad?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 64,
-   "id": "3d3d3ad3",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "CPU times: user 115 ms, sys: 171 µs, total: 115 ms\n",
-      "Wall time: 1.38 s\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'I would recommend watching \"Last Action Hero\" when sad, as it is a fun and action-packed film that can help lift your spirits.'"
-      ]
-     },
-     "execution_count": 64,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "%%time\n",
-    "naive_rag_chain.invoke(\"Which movie do I watch when sad?\")"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "conda_pytorch_p310",
-   "language": "python",
-   "name": "conda_pytorch_p310"
-  },
-  "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": 5
-}

cookbook/multi_modal_RAG_chroma.ipynb

@@ -58,7 +58,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install -U langchain openai langchain-chroma langchain-experimental # (newest versions required for multi-modal)"
+    "! pip install -U langchain openai chromadb langchain-experimental # (newest versions required for multi-modal)"
    ]
   },
   {
@@ -187,7 +187,7 @@
     "\n",
     "import chromadb\n",
     "import numpy as np\n",
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_experimental.open_clip import OpenCLIPEmbeddings\n",
     "from PIL import Image as _PILImage\n",
     "\n",
@@ -435,7 +435,7 @@
     "    display(HTML(image_html))\n",
     "\n",
     "\n",
-    "docs = retriever.invoke(\"Woman with children\", k=10)\n",
+    "docs = retriever.get_relevant_documents(\"Woman with children\", k=10)\n",
     "for doc in docs:\n",
     "    if is_base64(doc.page_content):\n",
     "        plt_img_base64(doc.page_content)\n",

cookbook/multi_player_dnd.ipynb

@@ -74,7 +74,7 @@
     "        Applies the chatmodel to the message history\n",
     "        and returns the message string\n",
     "        \"\"\"\n",
-    "        message = self.model.invoke(\n",
+    "        message = self.model(\n",
     "            [\n",
     "                self.system_message,\n",
     "                HumanMessage(content=\"\\n\".join(self.message_history + [self.prefix])),\n",

cookbook/multiagent_authoritarian.ipynb

@@ -79,7 +79,7 @@
     "        Applies the chatmodel to the message history\n",
     "        and returns the message string\n",
     "        \"\"\"\n",
-    "        message = self.model.invoke(\n",
+    "        message = self.model(\n",
     "            [\n",
     "                self.system_message,\n",
     "                HumanMessage(content=\"\\n\".join(self.message_history + [self.prefix])),\n",
@@ -234,7 +234,7 @@
     "            termination_clause=self.termination_clause if self.stop else \"\",\n",
     "        )\n",
     "\n",
-    "        self.response = self.model.invoke(\n",
+    "        self.response = self.model(\n",
     "            [\n",
     "                self.system_message,\n",
     "                HumanMessage(content=response_prompt),\n",
@@ -263,7 +263,7 @@
     "            speaker_names=speaker_names,\n",
     "        )\n",
     "\n",
-    "        choice_string = self.model.invoke(\n",
+    "        choice_string = self.model(\n",
     "            [\n",
     "                self.system_message,\n",
     "                HumanMessage(content=choice_prompt),\n",
@@ -299,7 +299,7 @@
     "                ),\n",
     "                next_speaker=self.next_speaker,\n",
     "            )\n",
-    "            message = self.model.invoke(\n",
+    "            message = self.model(\n",
     "                [\n",
     "                    self.system_message,\n",
     "                    HumanMessage(content=next_prompt),\n",

cookbook/multiagent_bidding.ipynb

@@ -71,7 +71,7 @@
     "        Applies the chatmodel to the message history\n",
     "        and returns the message string\n",
     "        \"\"\"\n",
-    "        message = self.model.invoke(\n",
+    "        message = self.model(\n",
     "            [\n",
     "                self.system_message,\n",
     "                HumanMessage(content=\"\\n\".join(self.message_history + [self.prefix])),\n",
@@ -164,7 +164,7 @@
     "            message_history=\"\\n\".join(self.message_history),\n",
     "            recent_message=self.message_history[-1],\n",
     "        )\n",
-    "        bid_string = self.model.invoke([SystemMessage(content=prompt)]).content\n",
+    "        bid_string = self.model([SystemMessage(content=prompt)]).content\n",
     "        return bid_string"
    ]
   },