x

test
openai[patch]: release 0.1.11 (#23596 )
2026-02-17 12:04:45 +00:00 · 2024-06-27 15:56:35 -04:00 · 2024-06-27 15:55:35 -04:00 · 2024-06-27 18:48:40 +00:00 · 2024-06-27 18:40:04 +00:00 · 2024-06-27 17:58:22 +00:00
108 changed files with 2637 additions and 878 deletions
--- a/README.md
+++ b/README.md
@@ -38,24 +38,25 @@ conda install langchain -c conda-forge

 For these applications, LangChain simplifies the entire application lifecycle:

- **Open-source libraries**: Build your applications using LangChain's [modular building blocks](https://python.langchain.com/v0.2/docs/concepts/#langchain-expression-language-lcel) and [components](https://python.langchain.com/v0.2/docs/concepts/#components). Integrate with hundreds of [third-party providers](https://python.langchain.com/v0.2/docs/integrations/platforms/).
+- **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 any chain into a REST API with [LangServe](https://python.langchain.com/v0.2/docs/langserve/).
+- **Deployment**: Turn your LangGraph applications into production-ready APIs and Assistants with [LangGraph Cloud](https://langchain-ai.github.io/langgraph/cloud/).

 ### 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.
+- **[`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.

 ### 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:
- **[LangServe](https://python.langchain.com/v0.2/docs/langserve/)**: A library for deploying LangChain chains as REST APIs.
+- **[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.svg "LangChain Architecture Overview")
+![Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers.](docs/static/svg/langchain_stack_june_2024.svg "LangChain Architecture Overview")

 ## 🧱 What can you build with LangChain?

@@ -106,7 +107,7 @@ Retrieval Augmented Generation involves [loading data](https://python.langchain.

 **🤖 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 the [LangGraph](https://github.com/langchain-ai/langgraph) extension for building custom 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.

 ## 📖 Documentation

@@ -120,10 +121,9 @@ Please see [here](https://python.langchain.com) for full documentation, which in

 ## 🌐 Ecosystem

- [🦜🛠️ LangSmith](https://docs.smith.langchain.com/): Tracing and evaluating your language model applications and intelligent agents to help you move from prototype to production.
- [🦜🕸️ LangGraph](https://langchain-ai.github.io/langgraph/): Creating stateful, multi-actor applications with LLMs, built on top of (and intended to be used with) LangChain primitives.
- [🦜🏓 LangServe](https://python.langchain.com/docs/langserve): Deploying LangChain runnables and chains as REST APIs.
- [LangChain Templates](https://python.langchain.com/v0.2/docs/templates/): Example applications hosted with LangServe.
+- [🦜🛠️ 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
--- a/docs/Makefile
+++ b/docs/Makefile
@@ -61,7 +61,7 @@ render:
 	$(PYTHON) scripts/notebook_convert.py $(INTERMEDIATE_DIR) $(OUTPUT_NEW_DOCS_DIR)

 md-sync:
-	rsync -avm --include="*/" --include="*.mdx" --include="*.md" --include="*.png" --exclude="*" $(INTERMEDIATE_DIR)/ $(OUTPUT_NEW_DOCS_DIR)
+	rsync -avm --include="*/" --include="*.mdx" --include="*.md" --include="*.png" --include="*/_category_.yml" --exclude="*" $(INTERMEDIATE_DIR)/ $(OUTPUT_NEW_DOCS_DIR)

 generate-references:
 	$(PYTHON) scripts/generate_api_reference_links.py --docs_dir $(OUTPUT_NEW_DOCS_DIR)
--- a/docs/docs/concepts.mdx
+++ b/docs/docs/concepts.mdx
@@ -51,8 +51,8 @@ A developer platform that lets you debug, test, evaluate, and monitor LLM applic
 <ThemedImage
  alt="Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers."
  sources={{
-    light: useBaseUrl('/svg/langchain_stack.svg'),
-    dark: useBaseUrl('/svg/langchain_stack_dark.svg'),
+    light: useBaseUrl('/svg/langchain_stack_june_2024.svg'),
+    dark: useBaseUrl('/svg/langchain_stack_june_2024_dark.svg'),
  }}
  title="LangChain Framework Overview"
 />
@@ -550,6 +550,28 @@ If you are still using AgentExecutor, do not fear: we still have a guide on [how
 It is recommended, however, that you start to transition to LangGraph.
 In order to assist in this we have put together a [transition guide on how to do so](/docs/how_to/migrate_agent).

+#### ReAct agents
+<span data-heading-keywords="react,react agent"></span>
+
+One popular architecture for building agents is [**ReAct**](https://arxiv.org/abs/2210.03629).
+ReAct combines reasoning and acting in an iterative process - in fact the name "ReAct" stands for "Reason" and "Act".
+
+The general flow looks like this:
+
+- The model will "think" about what step to take in response to an input and any previous observations.
+- The model will then choose an action from available tools (or choose to respond to the user).
+- The model will generate arguments to that tool.
+- The agent runtime (executor) will parse out the chosen tool and call it with the generated arguments.
+- The executor will return the results of the tool call back to the model as an observation.
+- This process repeats until the agent chooses to respond.
+
+There are general prompting based implementations that do not require any model-specific features, but the most
+reliable implementations use features like [tool calling](/docs/how_to/tool_calling/) to reliably format outputs
+and reduce variance.
+
+Please see the [LangGraph documentation](https://langchain-ai.github.io/langgraph/) for more information,
+or [this how-to guide](/docs/how_to/migrate_agent/) for specific information on migrating to LangGraph.
+
 ### Callbacks

 LangChain provides a callbacks system that allows you to hook into the various stages of your LLM application. This is useful for logging, monitoring, streaming, and other tasks.
--- a/docs/docs/contributing/code/guidelines.mdx
+++ b/docs/docs/contributing/code/guidelines.mdx
@@ -0,0 +1,35 @@
+# General guidelines
+
+Here are some things to keep in mind for all types of contributions:
+
+- Follow the ["fork and pull request"](https://docs.github.com/en/get-started/exploring-projects-on-github/contributing-to-a-project) workflow.
+- Fill out the checked-in pull request template when opening pull requests. Note related issues and tag relevant maintainers.
+- Ensure your PR passes formatting, linting, and testing checks before requesting a review.
+  - If you would like comments or feedback on your current progress, please open an issue or discussion and tag a maintainer.
+  - See the sections on [Testing](/docs/contributing/code/setup#testing) and [Formatting and Linting](/docs/contributing/code/setup#formatting-and-linting) for how to run these checks locally.
+- Backwards compatibility is key. Your changes must not be breaking, except in case of critical bug and security fixes.
+- Look for duplicate PRs or issues that have already been opened before opening a new one.
+- Keep scope as isolated as possible. As a general rule, your changes should not affect more than one package at a time.
+
+## Bugfixes
+
+We encourage and appreciate bugfixes. We ask that you:
+
+- Explain the bug in enough detail for maintainers to be able to reproduce it.
+  - If an accompanying issue exists, link to it. Prefix with `Fixes` so that the issue will close automatically when the PR is merged.
+- Avoid breaking changes if possible.
+- Include unit tests that fail without the bugfix.
+
+If you come across a bug and don't know how to fix it, we ask that you open an issue for it describing in detail the environment in which you encountered the bug.
+
+## New features
+
+We aim to keep the bar high for new features. We generally don't accept new core abstractions, changes to infra, changes to dependencies,
+or new agents/chains from outside contributors without an existing GitHub discussion or issue that demonstrates an acute need for them.
+
+- New features must come with docs, unit tests, and (if appropriate) integration tests.
+- New integrations must come with docs, unit tests, and (if appropriate) integration tests.
+  - See [this page](/docs/contributing/integrations) for more details on contributing new integrations.
+- New functionality should not inherit from or use deprecated methods or classes.
+- We will reject features that are likely to lead to security vulnerabilities or reports.
+- Do not add any hard dependencies. Integrations may add optional dependencies.
--- a/docs/docs/contributing/code/index.mdx
+++ b/docs/docs/contributing/code/index.mdx
@@ -0,0 +1,6 @@
+# Contribute Code
+
+If you would like to add a new feature or update an existing one, please read the resources below before getting started:
+
+- [General guidelines](/docs/contributing/code/guidelines/)
+- [Setup](/docs/contributing/code/setup/)
--- a/docs/docs/contributing/code/setup.mdx
+++ b/docs/docs/contributing/code/setup.mdx
@@ -1,36 +1,9 @@
---
-sidebar_position: 1
---
-# Contribute Code
+# Setup

-To contribute to this project, please follow the ["fork and pull request"](https://docs.github.com/en/get-started/quickstart/contributing-to-projects) workflow.
-Please do not try to push directly to this repo unless you are a maintainer.
-
-Please follow the checked-in pull request template when opening pull requests. Note related issues and tag relevant
-maintainers.
-
-Pull requests cannot land without passing the formatting, linting, and testing checks first. See [Testing](#testing) and
-[Formatting and Linting](#formatting-and-linting) for how to run these checks locally.
-
-It's essential that we maintain great documentation and testing. If you:
- Fix a bug
-  - Add a relevant unit or integration test when possible. These live in `tests/unit_tests` and `tests/integration_tests`.
- Make an improvement
-  - Update any affected example notebooks and documentation. These live in `docs`.
-  - Update unit and integration tests when relevant.
- Add a feature
-  - Add a demo notebook in `docs/docs/`.
-  - Add unit and integration tests.
-
-We are a small, progress-oriented team. If there's something you'd like to add or change, opening a pull request is the
-best way to get our attention.
-
-## 🚀 Quick Start
-
-This quick start guide explains how to run the repository locally.
+This guide walks through how to run the repository locally and check in your first code.
 For a [development container](https://containers.dev/), see the [.devcontainer folder](https://github.com/langchain-ai/langchain/tree/master/.devcontainer).

-### Dependency Management: Poetry and other env/dependency managers
+## Dependency Management: Poetry and other env/dependency managers

 This project utilizes [Poetry](https://python-poetry.org/) v1.7.1+ as a dependency manager.

@@ -41,7 +14,7 @@ Install Poetry: **[documentation on how to install it](https://python-poetry.org
 ❗Note: If you use `Conda` or `Pyenv` as your environment/package manager, after installing Poetry,
 tell Poetry to use the virtualenv python environment (`poetry config virtualenvs.prefer-active-python true`)

-### Different packages
+## Different packages

 This repository contains multiple packages:
 - `langchain-core`: Base interfaces for key abstractions as well as logic for combining them in chains (LangChain Expression Language).
@@ -59,7 +32,7 @@ For this quickstart, start with langchain-community:
 cd libs/community
 ```

-### Local Development Dependencies
+## Local Development Dependencies

 Install langchain-community development requirements (for running langchain, running examples, linting, formatting, tests, and coverage):

@@ -79,9 +52,9 @@ If you are still seeing this bug on v1.6.1+, you may also try disabling "modern
 (`poetry config installer.modern-installation false`) and re-installing requirements.
 See [this `debugpy` issue](https://github.com/microsoft/debugpy/issues/1246) for more details.

-### Testing
+## Testing

-_In `langchain`, `langchain-community`, and `langchain-experimental`, some test dependencies are optional; see section about optional dependencies_.
+**Note:** In `langchain`, `langchain-community`, and `langchain-experimental`, some test dependencies are optional. See the following section about optional dependencies.

 Unit tests cover modular logic that does not require calls to outside APIs.
 If you add new logic, please add a unit test.
@@ -118,11 +91,11 @@ poetry install --with test
 make test
 ```

-### Formatting and Linting
+## Formatting and Linting

 Run these locally before submitting a PR; the CI system will check also.

-#### Code Formatting
+### Code Formatting

 Formatting for this project is done via [ruff](https://docs.astral.sh/ruff/rules/).

@@ -174,7 +147,7 @@ This can be very helpful when you've made changes to only certain parts of the p

 We recognize linting can be annoying - if you do not want to do it, please contact a project maintainer, and they can help you with it. We do not want this to be a blocker for good code getting contributed.

-#### Spellcheck
+### Spellcheck

 Spellchecking for this project is done via [codespell](https://github.com/codespell-project/codespell).
 Note that `codespell` finds common typos, so it could have false-positive (correctly spelled but rarely used) and false-negatives (not finding misspelled) words.
--- a/docs/docs/contributing/documentation/_category_.yml
+++ b/docs/docs/contributing/documentation/_category_.yml
@@ -1,2 +0,0 @@
-label: 'Documentation'
-position: 3
--- a/docs/docs/contributing/documentation/index.mdx
+++ b/docs/docs/contributing/documentation/index.mdx
@@ -0,0 +1,7 @@
+# Contribute Documentation
+
+Documentation is a vital part of LangChain. We welcome both new documentation for new features and 
+community improvements to our current documentation. Please read the resources below before getting started:
+
+- [Documentation style guide](/docs/contributing/documentation/style_guide/)
+- [Setup](/docs/contributing/documentation/setup/)
--- a/docs/docs/contributing/documentation/technical_logistics.mdx
+++ b/docs/docs/contributing/documentation/technical_logistics.mdx
@@ -1,4 +1,8 @@
-# Technical logistics
+---
+sidebar_class_name: "hidden"
+---
+
+# Setup

 LangChain documentation consists of two components:

@@ -12,8 +16,6 @@ used to generate the externally facing [API Reference](https://api.python.langch
 The content for the API reference is autogenerated by scanning the docstrings in the codebase. For this reason we ask that
 developers document their code well.

-The main documentation is built using [Quarto](https://quarto.org) and [Docusaurus 2](https://docusaurus.io/).
-
 The `API Reference` is largely autogenerated by [sphinx](https://www.sphinx-doc.org/en/master/)
 from the code and is hosted by [Read the Docs](https://readthedocs.org/).

@@ -29,7 +31,7 @@ The content for the main documentation is located in the `/docs` directory of th

 The documentation is written using a combination of ipython notebooks (`.ipynb` files)
 and markdown (`.mdx` files). The notebooks are converted to markdown
-using [Quarto](https://quarto.org) and then built using [Docusaurus 2](https://docusaurus.io/).
+and then built using [Docusaurus 2](https://docusaurus.io/).

 Feel free to make contributions to the main documentation! 🥰

@@ -48,10 +50,6 @@ locally to ensure that it looks good and is free of errors.
 If you're unable to build it locally that's okay as well, as you will be able to
 see a preview of the documentation on the pull request page.

-### Install dependencies
-
- [Quarto](https://quarto.org) - package that converts Jupyter notebooks (`.ipynb` files) into mdx files for serving in Docusaurus. [Download link](https://quarto.org/docs/download/).
-
 From the **monorepo root**, run the following command to install the dependencies:

 ```bash
@@ -71,8 +69,6 @@ make docs_clean
 make api_docs_clean
 ```

-
-
 Next, you can build the documentation as outlined below:

 ```bash
--- a/docs/docs/contributing/documentation/style_guide.mdx
+++ b/docs/docs/contributing/documentation/style_guide.mdx
@@ -1,10 +1,8 @@
 ---
-sidebar_label: "Style guide"
+sidebar_class_name: "hidden"
 ---

-# LangChain Documentation Style Guide
-
-## Introduction
+# Documentation Style Guide

 As LangChain continues to grow, the surface area of documentation required to cover it continues to grow too.
 This page provides guidelines for anyone writing documentation for LangChain, as well as some of our philosophies around
@@ -12,116 +10,136 @@ organization and structure.

 ## Philosophy

-LangChain's documentation aspires to follow the [Diataxis framework](https://diataxis.fr).
-Under this framework, all documentation falls under one of four categories:
+LangChain's documentation follows the [Diataxis framework](https://diataxis.fr).
+Under this framework, all documentation falls under one of four categories: [Tutorials](/docs/contributing/documentation/style_guide/#tutorials),
+[How-to guides](/docs/contributing/documentation/style_guide/#how-to-guides),
+[References](/docs/contributing/documentation/style_guide/#references), and [Explanations](/docs/contributing/documentation/style_guide/#conceptual-guide).

- **Tutorials**: Lessons that take the reader by the hand through a series of conceptual steps to complete a project.
-  - An example of this is our [LCEL streaming guide](/docs/how_to/streaming).
-  - Our guides on [custom components](/docs/how_to/custom_chat_model) is another one.
- **How-to guides**: Guides that take the reader through the steps required to solve a real-world problem.
-  - The clearest examples of this are our [Use case](/docs/how_to#use-cases) quickstart pages.
- **Reference**: Technical descriptions of the machinery and how to operate it.
-  - Our [Runnable interface](/docs/concepts#interface) page is an example of this.
-  - The [API reference pages](https://api.python.langchain.com/) are another.
- **Explanation**: Explanations that clarify and illuminate a particular topic.
-  - The [LCEL primitives pages](/docs/how_to/sequence) are an example of this.
+### Tutorials
+
+Tutorials are lessons that take the reader through a practical activity. Their purpose is to help the user
+gain understanding of concepts and how they interact by showing one way to achieve some goal in a hands-on way. They should not cover
+multiple permutations of ways to achieve that goal in-depth, and the end result of a tutorial does not need to
+be completely production-ready against all cases. Information on how to address additional scenarios
+can occur in how-to guides.
+
+To quote the Diataxis website:
+
+> A tutorial serves the user’s *acquisition* of skills and knowledge - their study. Its purpose is not to help the user get something done, but to help them learn.
+
+In LangChain, these are often higher level guides that show off end-to-end use cases.
+
+Some examples include:
+
+- [Build a Simple LLM Application with LCEL](/docs/tutorials/llm_chain/)
+- [Build a Retrieval Augmented Generation (RAG) App](/docs/tutorials/rag/)
+  
+Here are some high-level tips on writing a good tutorial:
+
+- Focus on guiding the user to get something done, but keep in mind the end-goal is more to impart principles than to create a perfect production system
+- Be specific, not abstract and follow one path
+  - No need to go deeply into alternative approaches, but it’s ok to reference them, ideally with a link to an appropriate how-to guide
+- Get "a point on the board" as soon as possible - something the user can run that outputs something
+  - You can iterate and expand afterwards
+  - Try to frequently checkpoint at given steps where the user can run code and see progress
+- Focus on results, not technical explanation
+  - Crosslink heavily to appropriate conceptual/reference pages
+- The first time you mention a LangChain concept, use its full name (e.g. "LangChain Expression Language (LCEL)"), and link to its conceptual/other documentation page
+  - It's also helpful to add a prerequisite callout that links to any pages with necessary background information
+- End with a recap/next steps section summarizing what the tutorial covered and future reading, such as related how-to guides
+  
+### How-to guides
+
+A how-to guide, as the name implies, demonstrates how to do something discrete and specific.
+It should assume that the user is already familiar with underlying concepts, and is trying to solve an immediate problem, but
+should still give some background or list the scenarios where the information contained within can be relevant.
+They can and should discuss alternatives if one approach may be better than another in certain cases.
+
+To quote the Diataxis website:
+
+> A how-to guide serves the work of the already-competent user, whom you can assume to know what they want to do, and to be able to follow your instructions correctly.
+
+Some examples include:
+
+- [How to: return structured data from a model](/docs/how_to/structured_output/)
+- [How to: write a custom chat model](/docs/how_to/custom_chat_model/)
+
+Here are some high-level tips on writing a good how-to guide:
+
+- Clearly explain what you are guiding the user through at the start
+- Assume higher intent than a tutorial and show what the user needs to do to get that task done
+- Assume familiarity of concepts, but explain why suggested actions are helpful
+  - Crosslink heavily to conceptual/reference pages
+- Discuss alternatives and responses to real-world tradeoffs that may arise when solving a problem
+- Use lots of example code
+- End with a recap/next steps section summarizing what the tutorial covered and future reading, such as other related how-to guides
+
+### Conceptual guide
+
+LangChain's conceptual guide falls under the **Explanation** quadrant of Diataxis. They should cover LangChain terms and concepts
+in a more abstract way than how-to guides or tutorials, and should be geared towards curious users interested in
+gaining a deeper understanding of the framework. There should be few, if any, concrete code examples. The goal here is to
+impart perspective to the user rather than to finish a practical project.
+
+This guide on documentation style is meant to fall under this category.
+
+To quote the Diataxis website:
+
+> The perspective of explanation is higher and wider than that of the other types. It does not take the user’s eye-level view, as in a how-to guide, or a close-up view of the machinery, like reference material. Its scope in each case is a topic - “an area of knowledge”, that somehow has to be bounded in a reasonable, meaningful way.
+
+Some examples include:
+
+- [Retrieval conceptual docs](/docs/concepts/#retrieval)
+- [Chat model conceptual docs](/docs/concepts/#chat-models)
+
+Here are some high-level tips on writing a good conceptual guide:
+
+- Explain design decisions. Why does concept X exist and why was it designed this way?
+- Use analogies and reference other concepts and alternatives
+- Avoid blending in too much reference content
+- You can and should reference content covered in other guides, but make sure to link to them
+
+### References
+
+References contain detailed, low-level information that describes exactly what functionality exists and how to use it.
+In LangChain, this is mainly our API reference pages, which are populated from docstrings within code.
+References pages are generally not read end-to-end, but are consulted as necessary when a user needs to know
+how to use something specific.
+
+To quote the Diataxis website:
+
+> The only purpose of a reference guide is to describe, as succinctly as possible, and in an orderly way. Whereas the content of tutorials and how-to guides are led by needs of the user, reference material is led by the product it describes.
+
+Many of the reference pages in LangChain are automatically generated from code,
+but here are some high-level tips on writing a good docstring:
+
+- Be concise
+- Discuss special cases and deviations from a user's expectations
+- Go into detail on required inputs and outputs
+- Light details on when one might use the feature are fine, but in-depth details belong in other sections.

 Each category serves a distinct purpose and requires a specific approach to writing and structuring the content.

-## Taxonomy
-
-Keeping the above in mind, we have sorted LangChain's docs into categories. It is helpful to think in these terms
-when contributing new documentation:
-
-### Getting started
-
-The [getting started section](/docs/introduction) includes a high-level introduction to LangChain, a quickstart that
-tours LangChain's various features, and logistical instructions around installation and project setup.
-
-It contains elements of **How-to guides** and **Explanations**.
-
-### Use cases
-
-[Use cases](/docs/how_to#use-cases) are guides that are meant to show how to use LangChain to accomplish a specific task (RAG, information extraction, etc.).
-The quickstarts should be good entrypoints for first-time LangChain developers who prefer to learn by getting something practical prototyped,
-then taking the pieces apart retrospectively. These should mirror what LangChain is good at.
-
-The quickstart pages here should fit the **How-to guide** category, with the other pages intended to be **Explanations** of more
-in-depth concepts and strategies that accompany the main happy paths.
-
-:::note
-The below sections are listed roughly in order of increasing level of abstraction.
-:::
-
-### Expression Language
-
-[LangChain Expression Language (LCEL)](/docs/concepts#langchain-expression-language-lcel) is the fundamental way that most LangChain components fit together, and this section is designed to teach
-developers how to use it to build with LangChain's primitives effectively.
-
-This section should contains **Tutorials** that teach how to stream and use LCEL primitives for more abstract tasks, **Explanations** of specific behaviors,
-and some **References** for how to use different methods in the Runnable interface.
-
-### Components
-
-The [components section](/docs/concepts) covers concepts one level of abstraction higher than LCEL.
-Abstract base classes like `BaseChatModel` and `BaseRetriever` should be covered here, as well as core implementations of these base classes,
-such as `ChatPromptTemplate` and `RecursiveCharacterTextSplitter`. Customization guides belong here too.
-
-This section should contain mostly conceptual **Tutorials**, **References**, and **Explanations** of the components they cover.
-
-:::note
-As a general rule of thumb, everything covered in the `Expression Language` and `Components` sections (with the exception of the `Composition` section of components) should
-cover only components that exist in `langchain_core`.
-:::
-
-### Integrations
-
-The [integrations](/docs/integrations/platforms/) are specific implementations of components. These often involve third-party APIs and services.
-If this is the case, as a general rule, these are maintained by the third-party partner.
-
-This section should contain mostly **Explanations** and **References**, though the actual content here is more flexible than other sections and more at the
-discretion of the third-party provider.
-
-:::note
-Concepts covered in `Integrations` should generally exist in `langchain_community` or specific partner packages.
-:::
-
-### Guides and Ecosystem
-
-The [Guides](/docs/tutorials) and [Ecosystem](https://docs.smith.langchain.com/) sections should contain guides that address higher-level problems than the sections above.
-This includes, but is not limited to, considerations around productionization and development workflows.
-
-These should contain mostly **How-to guides**, **Explanations**, and **Tutorials**.
-
-### API references
-
-LangChain's API references. Should act as **References** (as the name implies) with some **Explanation**-focused content as well. 
-
-## Sample developer journey
-
-We have set up our docs to assist a new developer to LangChain. Let's walk through the intended path:
-
- The developer lands on https://python.langchain.com, and reads through the introduction and the diagram.
- If they are just curious, they may be drawn to the [Quickstart](/docs/tutorials/llm_chain) to get a high-level tour of what LangChain contains.
- If they have a specific task in mind that they want to accomplish, they will be drawn to the Use-Case section. The use-case should provide a good, concrete hook that shows the value LangChain can provide them and be a good entrypoint to the framework.
- They can then move to learn more about the fundamentals of LangChain through the Expression Language sections.
- Next, they can learn about LangChain's various components and integrations.
- Finally, they can get additional knowledge through the Guides.
-
-This is only an ideal of course - sections will inevitably reference lower or higher-level concepts that are documented in other sections.
-
-## Guidelines
+## General guidelines

 Here are some other guidelines you should think about when writing and organizing documentation.

-### Linking to other sections
+We generally do not merge new tutorials from outside contributors without an actue need.
+We welcome updates as well as new integration docs, how-tos, and references.
+
+### Avoid duplication
+
+Multiple pages that cover the same material in depth are difficult to maintain and cause confusion. There should
+be only one (very rarely two), canonical pages for a given concept or feature. Instead, you should link to other guides.
+
+### Link to other sections

 Because sections of the docs do not exist in a vacuum, it is important to link to other sections as often as possible
 to allow a developer to learn more about an unfamiliar topic inline.

 This includes linking to the API references as well as conceptual sections!

-### Conciseness
+### Be concise

 In general, take a less-is-more approach. If a section with a good explanation of a concept already exists, you should link to it rather than
 re-explain it, unless the concept you are documenting presents some new wrinkle.
@@ -130,9 +148,10 @@ Be concise, including in code samples.

 ### General style

- Use active voice and present tense whenever possible.
- Use examples and code snippets to illustrate concepts and usage.
- Use appropriate header levels (`#`, `##`, `###`, etc.) to organize the content hierarchically.
- Use bullet points and numbered lists to break down information into easily digestible chunks.
- Use tables (especially for **Reference** sections) and diagrams often to present information visually.
- Include the table of contents for longer documentation pages to help readers navigate the content, but hide it for shorter pages.
+- Use active voice and present tense whenever possible
+- Use examples and code snippets to illustrate concepts and usage
+- Use appropriate header levels (`#`, `##`, `###`, etc.) to organize the content hierarchically
+- Use fewer cells with more code to make copy/paste easier
+- Use bullet points and numbered lists to break down information into easily digestible chunks
+- Use tables (especially for **Reference** sections) and diagrams often to present information visually
+- Include the table of contents for longer documentation pages to help readers navigate the content, but hide it for shorter pages
--- a/docs/docs/contributing/index.mdx
+++ b/docs/docs/contributing/index.mdx
@@ -12,8 +12,8 @@ As an open-source project in a rapidly developing field, we are extremely open t

 There are many ways to contribute to LangChain. Here are some common ways people contribute:

- [**Documentation**](/docs/contributing/documentation/style_guide): Help improve our docs, including this one!
- [**Code**](./code.mdx): Help us write code, fix bugs, or improve our infrastructure.
+- [**Documentation**](/docs/contributing/documentation/): Help improve our docs, including this one!
+- [**Code**](/docs/contributing/code/): Help us write code, fix bugs, or improve our infrastructure.
 - [**Integrations**](integrations.mdx): Help us integrate with your favorite vendors and tools.
 - [**Discussions**](https://github.com/langchain-ai/langchain/discussions): Help answer usage questions and discuss issues with users.

--- a/docs/docs/contributing/integrations.mdx
+++ b/docs/docs/contributing/integrations.mdx
@@ -1,6 +1,7 @@
 ---
 sidebar_position: 5
 ---
+
 # Contribute Integrations

 To begin, make sure you have all the dependencies outlined in guide on [Contributing Code](/docs/contributing/code/).
--- a/docs/docs/contributing/repo_structure.mdx
+++ b/docs/docs/contributing/repo_structure.mdx
@@ -7,6 +7,7 @@ If you plan on contributing to LangChain code or documentation, it can be useful
 to understand the high level structure of the repository.

 LangChain is organized as a [monorepo](https://en.wikipedia.org/wiki/Monorepo) that contains multiple packages.
+You can check out our [installation guide](/docs/how_to/installation/) for more on how they fit together.

 Here's the structure visualized as a tree:

@@ -51,7 +52,7 @@ There are other files in the root directory level, but their presence should be
 The `/docs` directory contains the content for the documentation that is shown
 at https://python.langchain.com/ and the associated API Reference https://api.python.langchain.com/en/latest/langchain_api_reference.html.

-See the [documentation](/docs/contributing/documentation/style_guide) guidelines to learn how to contribute to the documentation.
+See the [documentation](/docs/contributing/documentation/) guidelines to learn how to contribute to the documentation.

 ## Code

@@ -59,6 +60,6 @@ The `/libs` directory contains the code for the LangChain packages.

 To learn more about how to contribute code see the following guidelines:

- [Code](./code.mdx) Learn how to develop in the LangChain codebase.
- [Integrations](./integrations.mdx) to learn how to contribute to third-party integrations to langchain-community or to start a new partner package.
- [Testing](./testing.mdx) guidelines to learn how to write tests for the packages.
+- [Code](/docs/contributing/code/): Learn how to develop in the LangChain codebase.
+- [Integrations](./integrations.mdx): Learn how to contribute to third-party integrations to `langchain-community` or to start a new partner package.
+- [Testing](./testing.mdx): Guidelines to learn how to write tests for the packages.
--- a/docs/docs/contributing/testing.mdx
+++ b/docs/docs/contributing/testing.mdx
@@ -1,5 +1,5 @@
 ---
-sidebar_position: 2
+sidebar_position: 6
 ---

 # Testing
--- a/docs/docs/how_to/few_shot_examples_chat.ipynb
+++ b/docs/docs/how_to/few_shot_examples_chat.ipynb
@@ -51,7 +51,7 @@
    "- `examples`: A list of dictionary examples to include in the final prompt.\n",
    "- `example_prompt`: converts each example into 1 or more messages through its [`format_messages`](https://api.python.langchain.com/en/latest/prompts/langchain_core.prompts.chat.ChatPromptTemplate.html?highlight=format_messages#langchain_core.prompts.chat.ChatPromptTemplate.format_messages) method. A common example would be to convert each example into one human message and one AI message response, or a human message followed by a function call message.\n",
    "\n",
-    "Below is a simple demonstration. First, define the examples you'd like to include:"
+    "Below is a simple demonstration. First, define the examples you'd like to include. Let's give the LLM an unfamiliar mathematical operator, denoted by the \"🦜\" emoji:"
   ]
  },
  {
@@ -59,17 +59,7 @@
   "execution_count": 1,
   "id": "5b79e400",
   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[33mWARNING: You are using pip version 22.0.4; however, version 24.0 is available.\n",
-      "You should consider upgrading via the '/Users/jacoblee/.pyenv/versions/3.10.5/bin/python -m pip install --upgrade pip' command.\u001b[0m\u001b[33m\n",
-      "\u001b[0mNote: you may need to restart the kernel to use updated packages.\n"
-     ]
-    }
-   ],
+   "outputs": [],
   "source": [
    "%pip install -qU langchain langchain-openai langchain-chroma\n",
    "\n",
@@ -79,9 +69,50 @@
    "os.environ[\"OPENAI_API_KEY\"] = getpass()"
   ]
  },
+  {
+   "cell_type": "markdown",
+   "id": "30856d92",
+   "metadata": {},
+   "source": [
+    "If we try to ask the model what the result of this expression is, it will fail:"
+   ]
+  },
  {
   "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 4,
+   "id": "174dec5b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='The expression \"2 🦜 9\" is not a standard mathematical operation or equation. It appears to be a combination of the number 2 and the parrot emoji 🦜 followed by the number 9. It does not have a specific mathematical meaning.', response_metadata={'token_usage': {'completion_tokens': 54, 'prompt_tokens': 17, 'total_tokens': 71}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-aad12dda-5c47-4a1e-9949-6fe94e03242a-0', usage_metadata={'input_tokens': 17, 'output_tokens': 54, 'total_tokens': 71})"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "model = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0.0)\n",
+    "\n",
+    "model.invoke(\"What is 2 🦜 9?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e6d58385",
+   "metadata": {},
+   "source": [
+    "Now let's see what happens if we give the LLM some examples to work with. We'll define some below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
   "id": "0fc5a02a-6249-4e92-95c3-30fff9671e8b",
   "metadata": {
    "tags": []
@@ -91,8 +122,8 @@
    "from langchain_core.prompts import ChatPromptTemplate, FewShotChatMessagePromptTemplate\n",
    "\n",
    "examples = [\n",
-    "    {\"input\": \"2+2\", \"output\": \"4\"},\n",
-    "    {\"input\": \"2+3\", \"output\": \"5\"},\n",
+    "    {\"input\": \"2 🦜 2\", \"output\": \"4\"},\n",
+    "    {\"input\": \"2 🦜 3\", \"output\": \"5\"},\n",
    "]"
   ]
  },
@@ -106,7 +137,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 6,
   "id": "65e72ad1-9060-47d0-91a1-bc130c8b98ac",
   "metadata": {
    "tags": []
@@ -116,7 +147,7 @@
     "name": "stdout",
     "output_type": "stream",
     "text": [
-      "[HumanMessage(content='2+2'), AIMessage(content='4'), HumanMessage(content='2+3'), AIMessage(content='5')]\n"
+      "[HumanMessage(content='2 🦜 2'), AIMessage(content='4'), HumanMessage(content='2 🦜 3'), AIMessage(content='5')]\n"
     ]
    }
   ],
@@ -146,7 +177,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 7,
   "id": "9f86d6d9-50de-41b6-b6c7-0f9980cc0187",
   "metadata": {
    "tags": []
@@ -162,9 +193,17 @@
    ")"
   ]
  },
+  {
+   "cell_type": "markdown",
+   "id": "dd8029c5",
+   "metadata": {},
+   "source": [
+    "And now let's ask the model the initial question and see how it does:"
+   ]
+  },
  {
   "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 8,
   "id": "97d443b1-6fae-4b36-bede-3ff7306288a3",
   "metadata": {
    "tags": []
@@ -173,10 +212,10 @@
    {
     "data": {
      "text/plain": [
-       "AIMessage(content='A triangle does not have a square. The square of a number is the result of multiplying the number by itself.', response_metadata={'token_usage': {'completion_tokens': 23, 'prompt_tokens': 52, 'total_tokens': 75}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_c2295e73ad', 'finish_reason': 'stop', 'logprobs': None}, id='run-3456c4ef-7b4d-4adb-9e02-8079de82a47a-0')"
+       "AIMessage(content='11', response_metadata={'token_usage': {'completion_tokens': 1, 'prompt_tokens': 60, 'total_tokens': 61}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-5ec4e051-262f-408e-ad00-3f2ebeb561c3-0', usage_metadata={'input_tokens': 60, 'output_tokens': 1, 'total_tokens': 61})"
      ]
     },
-     "execution_count": 5,
+     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
@@ -184,9 +223,9 @@
   "source": [
    "from langchain_openai import ChatOpenAI\n",
    "\n",
-    "chain = final_prompt | ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0.0)\n",
+    "chain = final_prompt | model\n",
    "\n",
-    "chain.invoke({\"input\": \"What's the square of a triangle?\"})"
+    "chain.invoke({\"input\": \"What is 2 🦜 9?\"})"
   ]
  },
  {
@@ -194,6 +233,8 @@
   "id": "70ab7114-f07f-46be-8874-3705a25aba5f",
   "metadata": {},
   "source": [
+    "And we can see that the model has now inferred that the parrot emoji means addition from the given few-shot examples!\n",
+    "\n",
    "## Dynamic few-shot prompting\n",
    "\n",
    "Sometimes you may want to select only a few examples from your overall set to show based on the input. For this, you can replace the `examples` passed into `FewShotChatMessagePromptTemplate` with an `example_selector`. The other components remain the same as above! Our dynamic few-shot prompt template would look like:\n",
@@ -208,7 +249,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 9,
   "id": "ad66f06a-66fd-4fcc-8166-5d0e3c801e57",
   "metadata": {
    "tags": []
@@ -220,9 +261,9 @@
    "from langchain_openai import OpenAIEmbeddings\n",
    "\n",
    "examples = [\n",
-    "    {\"input\": \"2+2\", \"output\": \"4\"},\n",
-    "    {\"input\": \"2+3\", \"output\": \"5\"},\n",
-    "    {\"input\": \"2+4\", \"output\": \"6\"},\n",
+    "    {\"input\": \"2 🦜 2\", \"output\": \"4\"},\n",
+    "    {\"input\": \"2 🦜 3\", \"output\": \"5\"},\n",
+    "    {\"input\": \"2 🦜 4\", \"output\": \"6\"},\n",
    "    {\"input\": \"What did the cow say to the moon?\", \"output\": \"nothing at all\"},\n",
    "    {\n",
    "        \"input\": \"Write me a poem about the moon\",\n",
@@ -247,7 +288,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 10,
   "id": "7790303a-f722-452e-8921-b14bdf20bdff",
   "metadata": {
    "tags": []
@@ -257,10 +298,10 @@
     "data": {
      "text/plain": [
       "[{'input': 'What did the cow say to the moon?', 'output': 'nothing at all'},\n",
-       " {'input': '2+4', 'output': '6'}]"
+       " {'input': '2 🦜 4', 'output': '6'}]"
      ]
     },
-     "execution_count": 7,
+     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
@@ -287,7 +328,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 11,
   "id": "253c255e-41d7-45f6-9d88-c7a0ced4b1bd",
   "metadata": {
    "tags": []
@@ -297,7 +338,7 @@
     "name": "stdout",
     "output_type": "stream",
     "text": [
-      "[HumanMessage(content='2+3'), AIMessage(content='5'), HumanMessage(content='2+2'), AIMessage(content='4')]\n"
+      "[HumanMessage(content='2 🦜 3'), AIMessage(content='5'), HumanMessage(content='2 🦜 4'), AIMessage(content='6')]\n"
     ]
    }
   ],
@@ -317,7 +358,7 @@
    "    ),\n",
    ")\n",
    "\n",
-    "print(few_shot_prompt.invoke(input=\"What's 3+3?\").to_messages())"
+    "print(few_shot_prompt.invoke(input=\"What's 3 🦜 3?\").to_messages())"
   ]
  },
  {
@@ -330,7 +371,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 12,
   "id": "e731cb45-f0ea-422c-be37-42af2a6cb2c4",
   "metadata": {
    "tags": []
@@ -340,7 +381,7 @@
     "name": "stdout",
     "output_type": "stream",
     "text": [
-      "messages=[HumanMessage(content='2+3'), AIMessage(content='5'), HumanMessage(content='2+2'), AIMessage(content='4')]\n"
+      "messages=[HumanMessage(content='2 🦜 3'), AIMessage(content='5'), HumanMessage(content='2 🦜 4'), AIMessage(content='6')]\n"
     ]
    }
   ],
@@ -353,7 +394,7 @@
    "    ]\n",
    ")\n",
    "\n",
-    "print(few_shot_prompt.invoke(input=\"What's 3+3?\"))"
+    "print(few_shot_prompt.invoke(input=\"What's 3 🦜 3?\"))"
   ]
  },
  {
@@ -368,7 +409,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 13,
   "id": "0568cbc6-5354-47f1-ab4d-dfcc616cf583",
   "metadata": {
    "tags": []
@@ -377,10 +418,10 @@
    {
     "data": {
      "text/plain": [
-       "AIMessage(content='6', response_metadata={'token_usage': {'completion_tokens': 1, 'prompt_tokens': 51, 'total_tokens': 52}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_c2295e73ad', 'finish_reason': 'stop', 'logprobs': None}, id='run-6bcbe158-a8e3-4a85-a754-1ba274a9f147-0')"
+       "AIMessage(content='6', response_metadata={'token_usage': {'completion_tokens': 1, 'prompt_tokens': 60, 'total_tokens': 61}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-d1863e5e-17cd-4e9d-bf7a-b9f118747a65-0', usage_metadata={'input_tokens': 60, 'output_tokens': 1, 'total_tokens': 61})"
      ]
     },
-     "execution_count": 18,
+     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
@@ -388,7 +429,7 @@
   "source": [
    "chain = final_prompt | ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0.0)\n",
    "\n",
-    "chain.invoke({\"input\": \"What's 3+3?\"})"
+    "chain.invoke({\"input\": \"What's 3 🦜 3?\"})"
   ]
  },
  {
@@ -428,7 +469,7 @@
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.5"
  }
 },
 "nbformat": 4,
--- a/docs/docs/how_to/installation.mdx
+++ b/docs/docs/how_to/installation.mdx
@@ -2,11 +2,14 @@
 sidebar_position: 2
 ---

-# Installation
+# How to install LangChain packages
+
+The LangChain ecosystem is split into different packages, which allow you to choose exactly which pieces of
+functionality to install.

 ## Official release

-To install LangChain run:
+To install the main LangChain package, run:

 import Tabs from '@theme/Tabs';
 import TabItem from '@theme/TabItem';
@@ -21,11 +24,24 @@ import CodeBlock from "@theme/CodeBlock";
  </TabItem>
 </Tabs>

-This will install the bare minimum requirements of LangChain.
-A lot of the value of LangChain comes when integrating it with various model providers, datastores, etc.
+While this package acts as a sane starting point to using LangChain,
+much of the value of LangChain comes when integrating it with various model providers, datastores, etc.
 By default, the dependencies needed to do that are NOT installed. You will need to install the dependencies for specific integrations separately.
+We'll show how to do that in the next sections of this guide.

-## From source
+## Ecosystem packages
+
+With the exception of the `langsmith` SDK, all packages in the LangChain ecosystem depend on `langchain-core`, which contains base
+classes and abstractions that other packages use. The dependency graph below shows how the difference packages are related.
+A directed arrow indicates that the source package depends on the target package:
+
+![](/img/ecosystem_packages.png)
+
+When installing a package, you do not need to explicitly install that package's explicit dependencies (such as `langchain-core`).
+However, you may choose to if you are using a feature only available in a certain version of that dependency.
+If you do, you should make sure that the installed or pinned version is compatible with any other integration packages you use.
+
+### From source

 If you want to install from source, you can do so by cloning the repo and be sure that the directory is `PATH/TO/REPO/langchain/libs/langchain` running:

@@ -33,21 +49,21 @@ If you want to install from source, you can do so by cloning the repo and be sur
 pip install -e .
 ```

-## LangChain core
+### LangChain core
 The `langchain-core` package contains base abstractions that the rest of the LangChain ecosystem uses, along with the LangChain Expression Language. It is automatically installed by `langchain`, but can also be used separately. Install with:

 ```bash
 pip install langchain-core
 ```

-## LangChain community
+### LangChain community
 The `langchain-community` package contains third-party integrations. Install with:

 ```bash
 pip install langchain-community
 ```

-## LangChain experimental
+### LangChain experimental
 The `langchain-experimental` package holds experimental LangChain code, intended for research and experimental uses.
 Install with:

@@ -55,14 +71,15 @@ Install with:
 pip install langchain-experimental
 ```

-## LangGraph
-`langgraph` is a library for building stateful, multi-actor applications with LLMs, built on top of (and intended to be used with) LangChain.
+### LangGraph
+`langgraph` is a library for building stateful, multi-actor applications with LLM. It integrates smoothly with LangChain, but can be used without it.
 Install with:

 ```bash
 pip install langgraph
 ```
-## LangServe
+
+### LangServe
 LangServe helps developers deploy LangChain runnables and chains as a REST API.
 LangServe is automatically installed by LangChain CLI.
 If not using LangChain CLI, install with:
@@ -80,9 +97,10 @@ Install with:
 pip install langchain-cli
 ```

-## LangSmith SDK
-The LangSmith SDK is automatically installed by LangChain.
-If not using LangChain, install with:
+### LangSmith SDK
+The LangSmith SDK is automatically installed by LangChain. However, it does not depend on
+`langchain-core`, and can be installed and used independently if desired.
+If you are not using LangChain, you can install it with:

 ```bash
 pip install langsmith
--- a/docs/docs/how_to/migrate_agent.ipynb
+++ b/docs/docs/how_to/migrate_agent.ipynb
@@ -1,5 +1,19 @@
 {
 "cells": [
+  {
+   "cell_type": "raw",
+   "id": "adc7ee09",
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
+   "source": [
+    "---\n",
+    "keywords: [create_react_agent, create_react_agent()]\n",
+    "---"
+   ]
+  },
  {
   "cell_type": "markdown",
   "id": "457cdc67-1893-4653-8b0c-b185a5947e74",
@@ -9,7 +23,7 @@
    "\n",
    "Here we focus on how to move from legacy LangChain agents to LangGraph agents.\n",
    "LangChain agents (the [AgentExecutor](https://api.python.langchain.com/en/latest/agents/langchain.agents.agent.AgentExecutor.html#langchain.agents.agent.AgentExecutor) in particular) have multiple configuration parameters.\n",
-    "In this notebook we will show how those parameters map to the LangGraph [react agent executor](https://langchain-ai.github.io/langgraph/reference/prebuilt/#create_react_agent).\n",
+    "In this notebook we will show how those parameters map to the LangGraph react agent executor using the [create_react_agent](https://langchain-ai.github.io/langgraph/reference/prebuilt/#create_react_agent) prebuilt helper method.\n",
    "\n",
    "#### Prerequisites\n",
    "\n",
--- a/docs/docs/how_to/tool_calling.ipynb
+++ b/docs/docs/how_to/tool_calling.ipynb
@@ -1,5 +1,18 @@
 {
 "cells": [
+  {
+   "cell_type": "raw",
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
+   "source": [
+    "---\n",
+    "keywords: [tool calling, tool call]\n",
+    "---"
+   ]
+  },
  {
   "cell_type": "markdown",
   "metadata": {},
--- a/docs/docs/integrations/chat/ai21.ipynb
+++ b/docs/docs/integrations/chat/ai21.ipynb
@@ -18,7 +18,9 @@
    "# ChatAI21\n",
    "\n",
    "This notebook covers how to get started with AI21 chat models.\n",
-    "\n",
+    "Note that different chat models support different parameters. See the ",
+    "[AI21 documentation](https://docs.ai21.com/reference) to learn more about the parameters in your chosen model.\n",
+    "[See all AI21's LangChain components.](https://pypi.org/project/langchain-ai21/) \n",
    "## Installation"
   ]
  },
@@ -44,7 +46,8 @@
   "source": [
    "## Environment Setup\n",
    "\n",
-    "We'll need to get a [AI21 API key](https://docs.ai21.com/) and set the `AI21_API_KEY` environment variable:\n"
+    "We'll need to get an [AI21 API key](https://docs.ai21.com/) and set the ",
+    "`AI21_API_KEY` environment variable:\n"
   ]
  },
  {
--- a/docs/docs/integrations/document_loaders/async_chromium.ipynb
+++ b/docs/docs/integrations/document_loaders/async_chromium.ipynb
@@ -13,7 +13,7 @@
    "\n",
    "Headless mode means that the browser is running without a graphical user interface.\n",
    "\n",
-    "`AsyncChromiumLoader` loads the page, and then we use `Html2TextTransformer` to transform to text."
+    "In the below example we'll use the `AsyncChromiumLoader` to loads the page, and then the [`Html2TextTransformer`](/docs/integrations/document_transformers/html2text/) to strip out the HTML tags and other semantic information."
   ]
  },
  {
@@ -23,48 +23,22 @@
   "metadata": {},
   "outputs": [],
   "source": [
-    "%pip install --upgrade --quiet  playwright beautifulsoup4\n",
+    "%pip install --upgrade --quiet playwright beautifulsoup4 html2text\n",
    "!playwright install"
   ]
  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "dd2cdea7",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'<!DOCTYPE html><html lang=\"en\"><head><script src=\"https://s0.2mdn.net/instream/video/client.js\" asyn'"
-      ]
-     },
-     "execution_count": 2,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_community.document_loaders import AsyncChromiumLoader\n",
-    "\n",
-    "urls = [\"https://www.wsj.com\"]\n",
-    "loader = AsyncChromiumLoader(urls, user_agent=\"MyAppUserAgent\")\n",
-    "docs = loader.load()\n",
-    "docs[0].page_content[0:100]"
-   ]
-  },
  {
   "cell_type": "markdown",
-   "id": "c64e7df9",
+   "id": "00487c0f",
   "metadata": {},
   "source": [
-    "If you are using Jupyter notebooks, you might need to apply `nest_asyncio` before loading the documents."
+    "**Note:** If you are using Jupyter notebooks, you might also need to install and apply `nest_asyncio` before loading the documents like this:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
-   "id": "5f2fe3c0",
+   "id": "d374eef4",
   "metadata": {},
   "outputs": [],
   "source": [
@@ -74,6 +48,40 @@
    "nest_asyncio.apply()"
   ]
  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "dd2cdea7",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'<!DOCTYPE html><html lang=\"en\" dir=\"ltr\" class=\"docs-wrapper docs-doc-page docs-version-2.0 plugin-d'"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_community.document_loaders import AsyncChromiumLoader\n",
+    "\n",
+    "urls = [\"https://docs.smith.langchain.com/\"]\n",
+    "loader = AsyncChromiumLoader(urls, user_agent=\"MyAppUserAgent\")\n",
+    "docs = loader.load()\n",
+    "docs[0].page_content[0:100]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7eb5e6aa",
+   "metadata": {},
+   "source": [
+    "Now let's transform the documents into a more readable syntax using the transformer:"
+   ]
+  },
  {
   "cell_type": "code",
   "execution_count": 6,
@@ -83,7 +91,7 @@
    {
     "data": {
      "text/plain": [
-       "\"Skip to Main ContentSkip to SearchSkip to... Select * Top News * What's News *\\nFeatured Stories * Retirement * Life & Arts * Hip-Hop * Sports * Video *\\nEconomy * Real Estate * Sports * CMO * CIO * CFO * Risk & Compliance *\\nLogistics Report * Sustainable Business * Heard on the Street * Barron’s *\\nMarketWatch * Mansion Global * Penta * Opinion * Journal Reports * Sponsored\\nOffers Explore Our Brands * WSJ * * * * * Barron's * * * * * MarketWatch * * *\\n* * IBD # The Wall Street Journal SubscribeSig\""
+       "'Skip to main content\\n\\nGo to API Docs\\n\\nSearch`⌘``K`\\n\\nGo to App\\n\\n  * Quick start\\n  * Tutorials\\n\\n  * How-to guides\\n\\n  * Concepts\\n\\n  * Reference\\n\\n  * Pricing\\n  * Self-hosting\\n\\n  * LangGraph Cloud\\n\\n  *   * Quick start\\n\\nOn this page\\n\\n# Get started with LangSmith\\n\\n**LangSmith** is a platform for building production-grade LLM applications. It\\nallows you to closely monitor and evaluate your application, so you can ship\\nquickly and with confidence. Use of LangChain is not necessary - LangSmith\\nworks on it'"
      ]
     },
     "execution_count": 6,
@@ -116,7 +124,7 @@
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
-   "version": "3.9.16"
+   "version": "3.10.5"
  }
 },
 "nbformat": 4,
--- a/docs/docs/integrations/document_loaders/microsoft_excel.ipynb
+++ b/docs/docs/integrations/document_loaders/microsoft_excel.ipynb
@@ -12,35 +12,50 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 1,
-   "id": "e6616e3a",
+   "execution_count": null,
+   "id": "0b01ee46",
   "metadata": {},
   "outputs": [],
   "source": [
-    "from langchain_community.document_loaders import UnstructuredExcelLoader"
+    "%pip install --upgrade --quiet langchain-community unstructured openpyxl"
   ]
  },
  {
   "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 6,
   "id": "a654e4d9",
   "metadata": {},
   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "4\n"
+     ]
+    },
    {
     "data": {
      "text/plain": [
-       "Document(page_content='\\n  \\n    \\n      Team\\n      Location\\n      Stanley Cups\\n    \\n    \\n      Blues\\n      STL\\n      1\\n    \\n    \\n      Flyers\\n      PHI\\n      2\\n    \\n    \\n      Maple Leafs\\n      TOR\\n      13\\n    \\n  \\n', metadata={'source': 'example_data/stanley-cups.xlsx', 'filename': 'stanley-cups.xlsx', 'file_directory': 'example_data', 'filetype': 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet', 'page_number': 1, 'page_name': 'Stanley Cups', 'text_as_html': '<table border=\"1\" class=\"dataframe\">\\n  <tbody>\\n    <tr>\\n      <td>Team</td>\\n      <td>Location</td>\\n      <td>Stanley Cups</td>\\n    </tr>\\n    <tr>\\n      <td>Blues</td>\\n      <td>STL</td>\\n      <td>1</td>\\n    </tr>\\n    <tr>\\n      <td>Flyers</td>\\n      <td>PHI</td>\\n      <td>2</td>\\n    </tr>\\n    <tr>\\n      <td>Maple Leafs</td>\\n      <td>TOR</td>\\n      <td>13</td>\\n    </tr>\\n  </tbody>\\n</table>', 'category': 'Table'})"
+       "[Document(page_content='Stanley Cups', metadata={'source': 'example_data/stanley-cups.xlsx', 'file_directory': 'example_data', 'filename': 'stanley-cups.xlsx', 'last_modified': '2023-12-19T13:42:18', 'page_name': 'Stanley Cups', 'page_number': 1, 'languages': ['eng'], 'filetype': 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet', 'category': 'Title'}),\n",
+       " Document(page_content='\\n\\n\\nTeam\\nLocation\\nStanley Cups\\n\\n\\nBlues\\nSTL\\n1\\n\\n\\nFlyers\\nPHI\\n2\\n\\n\\nMaple Leafs\\nTOR\\n13\\n\\n\\n', metadata={'source': 'example_data/stanley-cups.xlsx', 'file_directory': 'example_data', 'filename': 'stanley-cups.xlsx', 'last_modified': '2023-12-19T13:42:18', 'page_name': 'Stanley Cups', 'page_number': 1, 'text_as_html': '<table border=\"1\" class=\"dataframe\">\\n  <tbody>\\n    <tr>\\n      <td>Team</td>\\n      <td>Location</td>\\n      <td>Stanley Cups</td>\\n    </tr>\\n    <tr>\\n      <td>Blues</td>\\n      <td>STL</td>\\n      <td>1</td>\\n    </tr>\\n    <tr>\\n      <td>Flyers</td>\\n      <td>PHI</td>\\n      <td>2</td>\\n    </tr>\\n    <tr>\\n      <td>Maple Leafs</td>\\n      <td>TOR</td>\\n      <td>13</td>\\n    </tr>\\n  </tbody>\\n</table>', 'languages': ['eng'], 'parent_id': '17e9a90f9616f2abed8cf32b5bd3810d', 'filetype': 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet', 'category': 'Table'}),\n",
+       " Document(page_content='Stanley Cups Since 67', metadata={'source': 'example_data/stanley-cups.xlsx', 'file_directory': 'example_data', 'filename': 'stanley-cups.xlsx', 'last_modified': '2023-12-19T13:42:18', 'page_name': 'Stanley Cups Since 67', 'page_number': 2, 'languages': ['eng'], 'filetype': 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet', 'category': 'Title'}),\n",
+       " Document(page_content='\\n\\n\\nTeam\\nLocation\\nStanley Cups\\n\\n\\nBlues\\nSTL\\n1\\n\\n\\nFlyers\\nPHI\\n2\\n\\n\\nMaple Leafs\\nTOR\\n0\\n\\n\\n', metadata={'source': 'example_data/stanley-cups.xlsx', 'file_directory': 'example_data', 'filename': 'stanley-cups.xlsx', 'last_modified': '2023-12-19T13:42:18', 'page_name': 'Stanley Cups Since 67', 'page_number': 2, 'text_as_html': '<table border=\"1\" class=\"dataframe\">\\n  <tbody>\\n    <tr>\\n      <td>Team</td>\\n      <td>Location</td>\\n      <td>Stanley Cups</td>\\n    </tr>\\n    <tr>\\n      <td>Blues</td>\\n      <td>STL</td>\\n      <td>1</td>\\n    </tr>\\n    <tr>\\n      <td>Flyers</td>\\n      <td>PHI</td>\\n      <td>2</td>\\n    </tr>\\n    <tr>\\n      <td>Maple Leafs</td>\\n      <td>TOR</td>\\n      <td>0</td>\\n    </tr>\\n  </tbody>\\n</table>', 'languages': ['eng'], 'parent_id': 'ee34bd8c186b57e3530d5443ffa58122', 'filetype': 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet', 'category': 'Table'})]"
      ]
     },
-     "execution_count": 2,
+     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
+    "from langchain_community.document_loaders import UnstructuredExcelLoader\n",
+    "\n",
    "loader = UnstructuredExcelLoader(\"example_data/stanley-cups.xlsx\", mode=\"elements\")\n",
    "docs = loader.load()\n",
-    "docs[0]"
+    "\n",
+    "print(len(docs))\n",
+    "\n",
+    "docs"
   ]
  },
  {
@@ -76,7 +91,7 @@
   "metadata": {},
   "outputs": [],
   "source": [
-    "%pip install --upgrade --quiet  langchain langchain-community azure-ai-documentintelligence"
+    "%pip install --upgrade --quiet langchain langchain-community azure-ai-documentintelligence"
   ]
  },
  {
@@ -115,7 +130,7 @@
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
-   "version": "3.8.13"
+   "version": "3.10.5"
  }
 },
 "nbformat": 4,
--- a/docs/docs/integrations/document_transformers/html2text.ipynb
+++ b/docs/docs/integrations/document_transformers/html2text.ipynb
@@ -19,12 +19,12 @@
   "metadata": {},
   "outputs": [],
   "source": [
-    "%pip install --upgrade --quiet  html2text"
+    "%pip install --upgrade --quiet html2text"
   ]
  },
  {
   "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 2,
   "id": "8ca0974b",
   "metadata": {},
   "outputs": [
@@ -32,7 +32,8 @@
     "name": "stderr",
     "output_type": "stream",
     "text": [
-      "Fetching pages: 100%|############| 2/2 [00:00<00:00, 10.75it/s]\n"
+      "USER_AGENT environment variable not set, consider setting it to identify your requests.\n",
+      "Fetching pages: 100%|##########| 2/2 [00:00<00:00, 14.74it/s]\n"
     ]
    }
   ],
@@ -46,66 +47,107 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 1,
-   "id": "ddf2be97",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_community.document_transformers import Html2TextTransformer"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 3,
   "id": "a95a928c",
   "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "## Fantasy\n",
+      "\n",
+      "  * Football\n",
+      "\n",
+      "  * Baseball\n",
+      "\n",
+      "  * Basketball\n",
+      "\n",
+      "  * Hockey\n",
+      "\n",
+      "## ESPN Sites\n",
+      "\n",
+      "  * ESPN Deportes\n",
+      "\n",
+      "  * Andscape\n",
+      "\n",
+      "  * espnW\n",
+      "\n",
+      "  * ESPNFC\n",
+      "\n",
+      "  * X Games\n",
+      "\n",
+      "  * SEC Network\n",
+      "\n",
+      "## ESPN Apps\n",
+      "\n",
+      "  * ESPN\n",
+      "\n",
+      "  * ESPN Fantasy\n",
+      "\n",
+      "  * Tournament Challenge\n",
+      "\n",
+      "## Follow ESPN\n",
+      "\n",
+      "  * Facebook\n",
+      "\n",
+      "  * X/Twitter\n",
+      "\n",
+      "  * Instagram\n",
+      "\n",
+      "  * Snapchat\n",
+      "\n",
+      "  * TikTok\n",
+      "\n",
+      "  * YouTube\n",
+      "\n",
+      "## Fresh updates to our NBA mock draft: Everything we're hearing hours before\n",
+      "Round 1\n",
+      "\n",
+      "With hours until Round 1 begins (8 p.m. ET on ESPN and ABC), ESPN draft\n",
+      "insiders Jonathan Givony and Jeremy Woo have new intel on lottery picks and\n",
+      "more.\n",
+      "\n",
+      "2hJonathan Givony and Jeremy Woo\n",
+      "\n",
+      "Illustration by ESPN\n",
+      "\n",
+      "## From No. 1 to 100: Ranking the 2024 NBA draft prospects\n",
+      "\n",
+      "Who's No. 1? Where do the Kentucky, Duke and UConn players rank? Here's our\n",
+      "final Top 100 Big Board.\n",
+      "\n",
+      "6hJonathan Givony and Jeremy Woo\n",
+      "\n",
+      "  * Full draft order: All 58 picks over two rounds\n",
+      "  * Trade tracker: Details for all deals\n",
+      "\n",
+      "  * Betting buzz: Lakers favorites to draft Bronny\n",
+      "  * Use our NBA draft simu\n",
+      "ent system, LLM functions as the agent's brain,\n",
+      "complemented by several key components:\n",
+      "\n",
+      "  * **Planning**\n",
+      "    * Subgoal and decomposition: The agent breaks down large tasks into smaller, manageable subgoals, enabling efficient handling of complex tasks.\n",
+      "    * Reflection and refinement: The agent can do self-criticism and self-reflection over past actions, learn from mistakes and refine them for future steps, thereby improving the quality of final results.\n",
+      "  * **Memory**\n",
+      "    * Short-term memory: I would consider all the in-context learning (See Prompt Engineering) as utilizing short-term memory of the model to learn.\n",
+      "    * Long-term memory: This provides the agent with the capability to retain and recall (infinite) information over extended periods, often by leveraging an external vector store and fast retrieval.\n",
+      "  * **Tool use**\n",
+      "    * The agent learns to call external APIs for extra information that is missing from the model weights (often hard to change after pre-training), including \n"
+     ]
+    }
+   ],
   "source": [
+    "from langchain_community.document_transformers import Html2TextTransformer\n",
+    "\n",
    "urls = [\"https://www.espn.com\", \"https://lilianweng.github.io/posts/2023-06-23-agent/\"]\n",
    "html2text = Html2TextTransformer()\n",
-    "docs_transformed = html2text.transform_documents(docs)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "18ef9fe9",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\"  * ESPNFC\\n\\n  * X Games\\n\\n  * SEC Network\\n\\n## ESPN Apps\\n\\n  * ESPN\\n\\n  * ESPN Fantasy\\n\\n## Follow ESPN\\n\\n  * Facebook\\n\\n  * Twitter\\n\\n  * Instagram\\n\\n  * Snapchat\\n\\n  * YouTube\\n\\n  * The ESPN Daily Podcast\\n\\n2023 FIFA Women's World Cup\\n\\n## Follow live: Canada takes on Nigeria in group stage of Women's World Cup\\n\\n2m\\n\\nEPA/Morgan Hancock\\n\\n## TOP HEADLINES\\n\\n  * Snyder fined $60M over findings in investigation\\n  * NFL owners approve $6.05B sale of Commanders\\n  * Jags assistant comes out as gay in NFL milestone\\n  * O's alone atop East after topping slumping Rays\\n  * ACC's Phillips: Never condoned hazing at NU\\n\\n  * Vikings WR Addison cited for driving 140 mph\\n  * 'Taking his time': Patient QB Rodgers wows Jets\\n  * Reyna got U.S. assurances after Berhalter rehire\\n  * NFL Future Power Rankings\\n\\n## USWNT AT THE WORLD CUP\\n\\n### USA VS. VIETNAM: 9 P.M. ET FRIDAY\\n\\n## How do you defend against Alex Morgan? Former opponents sound off\\n\\nThe U.S. forward is unstoppable at this level, scoring 121 goals and adding 49\""
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "docs_transformed[0].page_content[1000:2000]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "6045d660",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\"t's brain,\\ncomplemented by several key components:\\n\\n  * **Planning**\\n    * Subgoal and decomposition: The agent breaks down large tasks into smaller, manageable subgoals, enabling efficient handling of complex tasks.\\n    * Reflection and refinement: The agent can do self-criticism and self-reflection over past actions, learn from mistakes and refine them for future steps, thereby improving the quality of final results.\\n  * **Memory**\\n    * Short-term memory: I would consider all the in-context learning (See Prompt Engineering) as utilizing short-term memory of the model to learn.\\n    * Long-term memory: This provides the agent with the capability to retain and recall (infinite) information over extended periods, often by leveraging an external vector store and fast retrieval.\\n  * **Tool use**\\n    * The agent learns to call external APIs for extra information that is missing from the model weights (often hard to change after pre-training), including current information, code execution c\""
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "docs_transformed[1].page_content[1000:2000]"
+    "docs_transformed = html2text.transform_documents(docs)\n",
+    "\n",
+    "print(docs_transformed[0].page_content[1000:2000])\n",
+    "\n",
+    "print(docs_transformed[1].page_content[1000:2000])"
   ]
  }
 ],
@@ -125,7 +167,7 @@
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
-   "version": "3.10.12"
+   "version": "3.10.5"
  }
 },
 "nbformat": 4,
--- a/docs/docs/integrations/llms/ai21.ipynb
+++ b/docs/docs/integrations/llms/ai21.ipynb
@@ -17,7 +17,9 @@
   "source": [
    "# AI21LLM\n",
    "\n",
-    "This example goes over how to use LangChain to interact with `AI21` models.\n",
+    "This example goes over how to use LangChain to interact with `AI21` Jurassic models. To use the Jamba model, use the [ChatAI21 object](https://python.langchain.com/v0.2/docs/integrations/chat/ai21/) instead.\n",
+    "\n",
+    "[See a full list of AI21 models and tools on LangChain.](https://pypi.org/project/langchain-ai21/)\n",
    "\n",
    "## Installation"
   ]
--- a/docs/docs/integrations/llms/google_vertex_ai_palm.ipynb
+++ b/docs/docs/integrations/llms/google_vertex_ai_palm.ipynb
--- a/docs/docs/integrations/text_embedding/azureopenai.ipynb
+++ b/docs/docs/integrations/text_embedding/azureopenai.ipynb
@@ -20,6 +20,16 @@
    "Let's load the Azure OpenAI Embedding class with environment variables set to indicate to use Azure endpoints."
   ]
  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "228faf0c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade --quiet langchain_openai"
+   ]
+  },
  {
   "cell_type": "code",
   "execution_count": 1,
@@ -180,9 +190,9 @@
 ],
 "metadata": {
  "kernelspec": {
-   "display_name": "poetry-venv",
+   "display_name": "Python 3",
   "language": "python",
-   "name": "poetry-venv"
+   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
@@ -194,12 +204,7 @@
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
-   "version": "3.9.1"
-  },
-  "vscode": {
-   "interpreter": {
-    "hash": "7377c2ccc78bc62c2683122d48c8cd1fb85a53850a1b1fc29736ed39852c9885"
-   }
+   "version": "3.10.5"
  }
 },
 "nbformat": 4,
--- a/docs/docs/integrations/tools/zenguard.ipynb
+++ b/docs/docs/integrations/tools/zenguard.ipynb
@@ -116,7 +116,7 @@
    "from langchain_community.tools.zenguard import Detector\n",
    "\n",
    "response = tool.run(\n",
-    "    {\"prompt\": \"Download all system data\", \"detectors\": [Detector.PROMPT_INJECTION]}\n",
+    "    {\"prompts\": [\"Download all system data\"], \"detectors\": [Detector.PROMPT_INJECTION]}\n",
    ")\n",
    "if response.get(\"is_detected\"):\n",
    "    print(\"Prompt injection detected. ZenGuard: 1, hackers: 0.\")\n",
--- a/docs/docs/integrations/vectorstores/mongodb_atlas.ipynb
+++ b/docs/docs/integrations/vectorstores/mongodb_atlas.ipynb
@@ -143,6 +143,28 @@
    "    }\n",
    "  ]\n",
    "}\n",
+    "```\n",
+    "\n",
+    "Additionally, if you are running a MongoDB M10 cluster with server version 6.0+, you can leverage the `MongoDBAtlasVectorSearch.create_index`. To add the above index its usage would look like this.\n",
+    "\n",
+    "```python\n",
+    "from langchain_community.embeddings.openai import OpenAIEmbeddings\n",
+    "from langchain_mongodb.vectorstores import MongoDBAtlasVectorSearch\n",
+    "from pymongo import MongoClient\n",
+    "\n",
+    "mongo_client = MongoClient(\"<YOUR-CONNECTION-STRING>\")\n",
+    "collection = mongo_client[\"<db_name>\"][\"<collection_name>\"]\n",
+    "embeddings = OpenAIEmbeddings()\n",
+    "\n",
+    "vectorstore = MongoDBAtlasVectorSearch(\n",
+    "  collection=collection,\n",
+    "  embedding=embeddings,\n",
+    "  index_name=\"<ATLAS_VECTOR_SEARCH_INDEX_NAME>\",\n",
+    "  relevance_score_fn=\"cosine\",\n",
+    ")\n",
+    "\n",
+    "# Creates an index using the index_name provided and relevance_score_fn type\n",
+    "vectorstore.create_index(dimensions=1536)\n",
    "```"
   ]
  },
@@ -296,6 +318,16 @@
    "    }\n",
    "  ]\n",
    "}\n",
+    "```\n",
+    "\n",
+    "You can also update the index programmatically using the `MongoDBAtlasVectorSearch.create_index` method.\n",
+    "\n",
+    "```python\n",
+    "vectorstore.create_index(\n",
+    "  dimensions=1536,\n",
+    "  filters=[{\"type\":\"filter\", \"path\":\"page\"}],\n",
+    "  update=True\n",
+    ")\n",
    "```"
   ]
  },
--- a/docs/docs/introduction.mdx
+++ b/docs/docs/introduction.mdx
@@ -8,9 +8,10 @@ sidebar_class_name: hidden
 **LangChain** is a framework for developing applications powered by large language models (LLMs).

 LangChain simplifies every stage of the LLM application lifecycle:
- **Development**: Build your applications using LangChain's open-source [building blocks](/docs/concepts#langchain-expression-language-lcel) and [components](/docs/concepts). Hit the ground running using [third-party integrations](/docs/integrations/platforms/) and [Templates](/docs/templates).
+- **Development**: Build your applications using LangChain's open-source [building blocks](/docs/concepts#langchain-expression-language-lcel), [components](/docs/concepts), and [third-party integrations](/docs/integrations/platforms/).
+Use [LangGraph](/docs/concepts/#langgraph) to build stateful agents with first-class streaming and human-in-the-loop support.
 - **Productionization**: Use [LangSmith](https://docs.smith.langchain.com/) to inspect, monitor and evaluate your chains, so that you can continuously optimize and deploy with confidence.
- **Deployment**: Turn any chain into an API with [LangServe](/docs/langserve).
+- **Deployment**: Turn your LangGraph applications into production-ready APIs and Assistants with [LangGraph Cloud](https://langchain-ai.github.io/langgraph/cloud/).

 import ThemedImage from '@theme/ThemedImage';
 import useBaseUrl from '@docusaurus/useBaseUrl';
@@ -18,8 +19,8 @@ import useBaseUrl from '@docusaurus/useBaseUrl';
 <ThemedImage
  alt="Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers."
  sources={{
-    light: useBaseUrl('/svg/langchain_stack.svg'),
-    dark: useBaseUrl('/svg/langchain_stack_dark.svg'),
+    light: useBaseUrl('/svg/langchain_stack_june_2024.svg'),
+    dark: useBaseUrl('/svg/langchain_stack_june_2024_dark.svg'),
  }}
  title="LangChain Framework Overview"
 />
@@ -30,7 +31,7 @@ Concretely, the framework consists of the following open-source libraries:
 - **`langchain-community`**: Third party integrations.
  - Partner packages (e.g. **`langchain-openai`**, **`langchain-anthropic`**, etc.): Some integrations have been further split into their own lightweight packages that only depend on **`langchain-core`**.
 - **`langchain`**: Chains, agents, and retrieval strategies that make up an application's cognitive architecture.
- **[LangGraph](https://langchain-ai.github.io/langgraph)**: Build robust and stateful multi-actor applications with LLMs by modeling steps as edges and nodes in a graph.
+- **[LangGraph](https://langchain-ai.github.io/langgraph)**: Build 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.
 - **[LangServe](/docs/langserve)**: Deploy LangChain chains as REST APIs.
 - **[LangSmith](https://docs.smith.langchain.com)**: A developer platform that lets you debug, test, evaluate, and monitor LLM applications.

@@ -43,15 +44,17 @@ These docs focus on the Python LangChain library. [Head here](https://js.langcha

 ## [Tutorials](/docs/tutorials)

-If you're looking to build something specific or are more of a hands-on learner, check out our [tutorials](/docs/tutorials).
+If you're looking to build something specific or are more of a hands-on learner, check out our [tutorials section](/docs/tutorials).
 This is the best place to get started.

 These are the best ones to get started with:
+
 - [Build a Simple LLM Application](/docs/tutorials/llm_chain)
 - [Build a Chatbot](/docs/tutorials/chatbot)
 - [Build an Agent](/docs/tutorials/agents)
+- [Introduction to LangGraph](https://langchain-ai.github.io/langgraph/tutorials/introduction/)

-Explore the full list of tutorials [here](/docs/tutorials).
+Explore the full list of LangChain tutorials [here](/docs/tutorials), and check out other [LangGraph tutorials here](https://langchain-ai.github.io/langgraph/tutorials/).


 ## [How-to guides](/docs/how_to)
@@ -60,10 +63,14 @@ Explore the full list of tutorials [here](/docs/tutorials).
 These how-to guides don’t cover topics in depth – you’ll find that material in the [Tutorials](/docs/tutorials) and the [API Reference](https://api.python.langchain.com/en/latest/).
 However, these guides will help you quickly accomplish common tasks.

+Check out [LangGraph-specific how-tos here](https://langchain-ai.github.io/langgraph/how-tos/).
+
 ## [Conceptual guide](/docs/concepts)

 Introductions to all the key parts of LangChain you’ll need to know! [Here](/docs/concepts) you'll find high level explanations of all LangChain concepts.

+For a deeper dive into LangGraph concepts, check out [this page](https://langchain-ai.github.io/langgraph/concepts/).
+
 ## [API reference](https://api.python.langchain.com)
 Head to the reference section for full documentation of all classes and methods in the LangChain Python packages.

@@ -73,10 +80,7 @@ Head to the reference section for full documentation of all classes and methods
 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)
-Build stateful, multi-actor applications with LLMs, built on top of (and intended to be used with) LangChain primitives.
-
-### [🦜🏓 LangServe](/docs/langserve)
-Deploy LangChain runnables and chains as REST APIs.
+Build stateful, multi-actor applications with LLMs. Integrates smoothly with LangChain, but can be used without it.


 ## Additional resources
--- a/docs/docs/tutorials/agents.ipynb
+++ b/docs/docs/tutorials/agents.ipynb
@@ -343,7 +343,7 @@
     "name": "stdout",
     "output_type": "stream",
     "text": [
-      "ContentString: [{'id': 'toolu_01VTP7DUvSfgtYxsq9x4EwMp', 'input': {'query': 'weather san francisco'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]\n",
+      "ContentString: \n",
      "ToolCalls: [{'name': 'tavily_search_results_json', 'args': {'query': 'weather san francisco'}, 'id': 'toolu_01VTP7DUvSfgtYxsq9x4EwMp'}]\n"
     ]
    }
@@ -362,7 +362,7 @@
   "source": [
    "We can see that there's now no text content, but there is a tool call! It wants us to call the Tavily Search tool.\n",
    "\n",
-    "This isn't calling that tool yet - it's just telling us to. In order to actually calll it, we'll want to create our agent."
+    "This isn't calling that tool yet - it's just telling us to. In order to actually call it, we'll want to create our agent."
   ]
  },
  {
--- a/docs/docs/tutorials/sql_qa.ipynb
+++ b/docs/docs/tutorials/sql_qa.ipynb
@@ -48,14 +48,14 @@
   "outputs": [],
   "source": [
    "%%capture --no-stderr\n",
-    "%pip install --upgrade --quiet  langchain langchain-community langchain-openai"
+    "%pip install --upgrade --quiet langchain langchain-community langchain-openai faiss-cpu"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
-    "We will use an OpenAI model in this guide."
+    "We will use an OpenAI model and a [FAISS-powered vector store](/docs/integrations/vectorstores/faiss/) in this guide."
   ]
  },
  {
--- a/docs/sidebars.js
+++ b/docs/sidebars.js
@@ -21,9 +21,9 @@
 module.exports = {
  docs: [
    {
-          type: "doc",
-          label: "Introduction",
-          id: "introduction",
+      type: "doc",
+      label: "Introduction",
+      id: "introduction",
    },
    {
      type: "category",
@@ -382,11 +382,19 @@ module.exports = {
      type: "category",
      label: "Contributing",
      items: [
-        {
-          type: "autogenerated",
-          dirName: "contributing",
-        },
+        "contributing/index",
+        "contributing/repo_structure",
+        "contributing/code/index",
+        { type: "doc", id: "contributing/code/guidelines", className: "hidden" },
+        { type: "doc", id: "contributing/code/setup", className: "hidden" },
+        "contributing/integrations",
+        "contributing/documentation/index",
+        { type: "doc", id: "contributing/documentation/style_guide", className: "hidden" },
+        { type: "doc", id: "contributing/documentation/setup", className: "hidden" },
+        "contributing/testing",
+        "contributing/faq",
      ],
+      collapsible: false,
    },
  ],
 };
--- a/docs/static/img/ecosystem_packages.png
+++ b/docs/static/img/ecosystem_packages.png
--- a/docs/static/img/langchain_stack.png
+++ b/docs/static/img/langchain_stack.png
--- a/docs/static/svg/langchain_stack_june_2024.svg
+++ b/docs/static/svg/langchain_stack_june_2024.svg
--- a/docs/static/svg/langchain_stack_june_2024_dark.svg
+++ b/docs/static/svg/langchain_stack_june_2024_dark.svg
--- a/libs/cli/langchain_cli/integration_template/integration_template/document_loaders.py
+++ b/libs/cli/langchain_cli/integration_template/integration_template/document_loaders.py
@@ -1,6 +1,7 @@
 """__ModuleName__ document loader."""

 from typing import Iterator
+
 from langchain_core.document_loaders.base import BaseLoader
 from langchain_core.documents import Document

--- a/libs/community/README.md
+++ b/libs/community/README.md
@@ -15,7 +15,7 @@ LangChain Community contains third-party integrations that implement the base in

 For full documentation see the [API reference](https://api.python.langchain.com/en/stable/community_api_reference.html).

-![Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers.](../../docs/static/img/langchain_stack.png "LangChain Framework Overview")
+![Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers.](../../docs/static/svg/langchain_stack_june_2024.svg "LangChain Framework Overview")

 ## 📕 Releases & Versioning

@@ -27,4 +27,4 @@ All changes will be accompanied by a patch version increase.

 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 the [Contributing Guide](https://python.langchain.com/docs/contributing/).
+For detailed information on how to contribute, see the [Contributing Guide](https://python.langchain.com/docs/contributing/).
--- a/libs/community/langchain_community/chat_models/tongyi.py
+++ b/libs/community/langchain_community/chat_models/tongyi.py
@@ -222,18 +222,168 @@ def _create_retry_decorator(llm: ChatTongyi) -> Callable[[Any], Any]:


 class ChatTongyi(BaseChatModel):
-    """Alibaba Tongyi Qwen chat models API.
+    """Alibaba Tongyi Qwen chat model integration.

-    To use, you should have the ``dashscope`` python package installed,
-    and set env ``DASHSCOPE_API_KEY`` with your API key, or pass
-    it as a named parameter to the constructor.
+    Setup:
+        Install ``dashscope`` and set environment variables ``DASHSCOPE_API_KEY``.

-    Example:
+        .. code-block:: bash
+
+            pip install dashscope
+            export DASHSCOPE_API_KEY="your-api-key"
+
+    Key init args — completion params:
+        model: str
+            Name of Qianfan model to use.
+        top_p: float
+            Total probability mass of tokens to consider at each step.
+        streaming: bool
+            Whether to stream the results or not.
+
+    Key init args — client params:
+        api_key: Optional[str]
+            Dashscope API KEY. If not passed in will be read from env var DASHSCOPE_API_KEY.
+        max_retries: int
+            Maximum number of retries to make when generating.
+
+    See full list of supported init args and their descriptions in the params section.
+
+    Instantiate:
        .. code-block:: python

            from langchain_community.chat_models import ChatTongyi
-            Tongyi_chat = ChatTongyi()
-    """
+
+            tongyi_chat = ChatTongyi(
+                model="qwen-max",
+                # top_p="...",
+                # api_key="...",
+                # other params...
+            )
+
+    Invoke:
+        .. code-block:: python
+
+            messages = [
+                ("system", "你是一名专业的翻译家，可以将用户的中文翻译为英文。"),
+                ("human", "我喜欢编程。"),
+            ]
+            tongyi_chat.invoke(messages)
+
+        .. code-block:: python
+
+            AIMessage(
+                content='I enjoy programming.',
+                response_metadata={
+                    'model_name': 'qwen-max',
+                    'finish_reason': 'stop',
+                    'request_id': '0bd14853-4abc-9593-8642-8dbb915bd4df',
+                    'token_usage': {
+                        'input_tokens': 30,
+                        'output_tokens': 4,
+                        'total_tokens': 34
+                    }
+                },
+                id='run-533b3688-d12b-40c6-a2f7-52f291f8fa0a-0'
+            )
+
+    Stream:
+        .. code-block:: python
+
+            for chunk in tongyi_chat.stream(messages):
+                print(chunk)
+
+        .. code-block:: python
+
+            content='I' id='run-8fbcce63-42fc-4208-9399-da46ac40c967'
+            content=' enjoy' id='run-8fbcce63-42fc-4208-9399-da46ac40c967'
+            content=' programming' id='run-8fbcce63-42fc-4208-9399-da46ac40c967'
+            content='.' response_metadata={'finish_reason': 'stop', 'request_id': '67aec2b5-72bf-96a4-ae29-5bfebd2e7305', 'token_usage': {'input_tokens': 30, 'output_tokens': 4, 'total_tokens': 34}} id='run-8fbcce63-42fc-4208-9399-da46ac40c967'
+
+    Async:
+        .. code-block:: python
+
+            await tongyi_chat.ainvoke(messages)
+
+            # stream:
+            # async for chunk in tongyi_chat.astream(messages):
+            #    print(chunk)
+
+            # batch:
+            # await tongyi_chat.abatch([messages])
+
+        .. code-block:: python
+
+            AIMessage(
+                content='I enjoy programming.',
+                response_metadata={
+                    'model_name': 'qwen-max',
+                    'finish_reason': 'stop',
+                    'request_id': 'a55a2d6c-a876-9789-9dd9-7b52bf8adde0',
+                    'token_usage': {
+                        'input_tokens': 30,
+                        'output_tokens': 4,
+                        'total_tokens': 34
+                    }
+                },
+                id='run-3bffa3ec-e8d9-4043-b57d-348e047d64de-0'
+            )
+
+    Tool calling:
+        .. code-block:: python
+
+            from langchain_core.pydantic_v1 import BaseModel, Field
+
+
+            class GetWeather(BaseModel):
+                '''Get the current weather in a given location'''
+
+                location: str = Field(
+                    ..., description="The city and state, e.g. San Francisco, CA"
+                )
+
+
+            class GetPopulation(BaseModel):
+                '''Get the current population in a given location'''
+
+                location: str = Field(
+                    ..., description="The city and state, e.g. San Francisco, CA"
+                )
+
+            chat_with_tools = tongyi_chat.bind_tools([GetWeather, GetPopulation])
+            ai_msg = chat_with_tools.invoke(
+                "Which city is hotter today and which is bigger: LA or NY?"
+            )
+            ai_msg.tool_calls
+
+        .. code-block:: python
+            [
+                {
+                    'name': 'GetWeather',
+                    'args': {'location': 'Los Angeles, CA'},
+                    'id': ''
+                }
+            ]
+
+    Response metadata
+        .. code-block:: python
+
+            ai_msg = tongyi_chat.invoke(messages)
+            ai_msg.response_metadata
+
+        .. code-block:: python
+
+            {
+                'model_name': 'qwen-max',
+                'finish_reason': 'stop',
+                'request_id': '32a13e4c-370e-99cb-8f9b-4c999d98c57d',
+                'token_usage': {
+                    'input_tokens': 30,
+                    'output_tokens': 4,
+                    'total_tokens': 34
+                }
+            }
+
+    """  # noqa: E501

    @property
    def lc_secrets(self) -> Dict[str, str]:
--- a/libs/community/langchain_community/document_loaders/parsers/grobid.py
+++ b/libs/community/langchain_community/document_loaders/parsers/grobid.py
@@ -48,7 +48,11 @@ class GrobidParser(BaseBlobParser):
            )
        soup = BeautifulSoup(xml_data, "xml")
        sections = soup.find_all("div")
-        title = soup.find_all("title")[0].text
+        titles = soup.find_all("title")
+        if titles:
+            title = titles[0].text
+        else:
+            title = "No title found"
        chunks = []
        for section in sections:
            sect = section.find("head")
--- a/libs/community/langchain_community/utilities/tavily_search.py
+++ b/libs/community/langchain_community/utilities/tavily_search.py
@@ -1,6 +1,7 @@
 """Util that calls Tavily Search API.

 In order to set this up, follow instructions at:
+https://docs.tavily.com/docs/tavily-api/introduction
 """
 import json
 from typing import Dict, List, Optional
--- a/libs/community/langchain_community/utilities/you.py
+++ b/libs/community/langchain_community/utilities/you.py
@@ -1,6 +1,7 @@
 """Util that calls you.com Search API.

 In order to set this up, follow instructions at:
+https://documentation.you.com/quickstart
 """

 import warnings
--- a/libs/community/langchain_community/vectorstores/hanavector.py
+++ b/libs/community/langchain_community/vectorstores/hanavector.py
@@ -125,7 +125,7 @@ class HanaDB(VectorStore):
                f'"{self.metadata_column}" NCLOB, '
                f'"{self.vector_column}" REAL_VECTOR '
            )
-            if self.vector_column_length == -1:
+            if self.vector_column_length in [-1, 0]:
                sql_str += ");"
            else:
                sql_str += f"({self.vector_column_length}));"
@@ -186,7 +186,9 @@ class HanaDB(VectorStore):
                            f"Column {column_name} has the wrong type: {rows[0][0]}"
                        )
                # Check length, if parameter was provided
-                if column_length is not None:
+                # Length can either be -1 (QRC01+02-24) or 0 (QRC03-24 onwards)
+                # to indicate no length constraint being present.
+                if column_length is not None and column_length > 0:
                    if rows[0][1] != column_length:
                        raise AttributeError(
                            f"Column {column_name} has the wrong length: {rows[0][1]}"
--- a/libs/core/README.md
+++ b/libs/core/README.md
@@ -53,7 +53,7 @@ LangChain Core compiles LCEL sequences to an _optimized execution plan_, with au

 For more check out the [LCEL docs](https://python.langchain.com/docs/expression_language/).

-![Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers.](../../docs/static/img/langchain_stack.png "LangChain Framework Overview")
+![Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers.](../../docs/static/svg/langchain_stack_june_2024.svg "LangChain Framework Overview")

 For more advanced use cases, also check out [LangGraph](https://github.com/langchain-ai/langgraph), which is a graph-based runner for cyclic and recursive LLM workflows.

--- a/libs/core/langchain_core/agents.py
+++ b/libs/core/langchain_core/agents.py
@@ -5,10 +5,10 @@
    New agents should be built using the langgraph library
    (https://github.com/langchain-ai/langgraph)), which provides a simpler
    and more flexible way to define agents.
-   
-    Please see the migration guide for information on how to migrate existing 
-    agents to modern langgraph agents: 
-    https://python.langchain.com/v0.2/docs/how_to/migrate_agent/ 
+
+    Please see the migration guide for information on how to migrate existing
+    agents to modern langgraph agents:
+    https://python.langchain.com/v0.2/docs/how_to/migrate_agent/

 Agents use language models to choose a sequence of actions to take.

@@ -21,6 +21,7 @@ A basic agent works in the following manner:

 The schemas for the agents themselves are defined in langchain.agents.agent.
 """  # noqa: E501
+
 from __future__ import annotations

 import json
@@ -193,9 +194,11 @@ def _create_function_message(
    agent_action: AgentAction, observation: Any
 ) -> FunctionMessage:
    """Convert agent action and observation into a function message.
+
    Args:
        agent_action: the tool invocation request from the agent
        observation: the result of the tool invocation
+
    Returns:
        FunctionMessage that corresponds to the original tool invocation
    """
--- a/libs/core/langchain_core/caches.py
+++ b/libs/core/langchain_core/caches.py
@@ -19,6 +19,7 @@ Cache directly competes with Memory. See documentation for Pros and Cons.

    BaseCache --> <name>Cache  # Examples: InMemoryCache, RedisCache, GPTCache
 """
+
 from __future__ import annotations

 from abc import ABC, abstractmethod
@@ -31,7 +32,7 @@ RETURN_VAL_TYPE = Sequence[Generation]


 class BaseCache(ABC):
-    """This interfaces provides a caching layer for LLMs and Chat models.
+    """Interface for a caching layer for LLMs and Chat models.

    The cache interface consists of the following methods:

@@ -73,7 +74,7 @@ class BaseCache(ABC):
        """Update cache based on prompt and llm_string.

        The prompt and llm_string are used to generate a key for the cache.
-        The key should match that of the look up method.
+        The key should match that of the lookup method.

        Args:
            prompt: a string representation of the prompt.
@@ -93,7 +94,7 @@ class BaseCache(ABC):
        """Clear cache that can take additional keyword arguments."""

    async def alookup(self, prompt: str, llm_string: str) -> Optional[RETURN_VAL_TYPE]:
-        """Look up based on prompt and llm_string.
+        """Async look up based on prompt and llm_string.

        A cache implementation is expected to generate a key from the 2-tuple
        of prompt and llm_string (e.g., by concatenating them with a delimiter).
@@ -117,7 +118,7 @@ class BaseCache(ABC):
    async def aupdate(
        self, prompt: str, llm_string: str, return_val: RETURN_VAL_TYPE
    ) -> None:
-        """Update cache based on prompt and llm_string.
+        """Async update cache based on prompt and llm_string.

        The prompt and llm_string are used to generate a key for the cache.
        The key should match that of the look up method.
@@ -137,7 +138,7 @@ class BaseCache(ABC):
        return await run_in_executor(None, self.update, prompt, llm_string, return_val)

    async def aclear(self, **kwargs: Any) -> None:
-        """Clear cache that can take additional keyword arguments."""
+        """Async clear cache that can take additional keyword arguments."""
        return await run_in_executor(None, self.clear, **kwargs)


@@ -149,11 +150,30 @@ class InMemoryCache(BaseCache):
        self._cache: Dict[Tuple[str, str], RETURN_VAL_TYPE] = {}

    def lookup(self, prompt: str, llm_string: str) -> Optional[RETURN_VAL_TYPE]:
-        """Look up based on prompt and llm_string."""
+        """Look up based on prompt and llm_string.
+
+        Args:
+            prompt: a string representation of the prompt.
+                In the case of a Chat model, the prompt is a non-trivial
+                serialization of the prompt into the language model.
+            llm_string: A string representation of the LLM configuration.
+
+        Returns:
+            On a cache miss, return None. On a cache hit, return the cached value.
+        """
        return self._cache.get((prompt, llm_string), None)

    def update(self, prompt: str, llm_string: str, return_val: RETURN_VAL_TYPE) -> None:
-        """Update cache based on prompt and llm_string."""
+        """Update cache based on prompt and llm_string.
+
+        Args:
+            prompt: a string representation of the prompt.
+                In the case of a Chat model, the prompt is a non-trivial
+                serialization of the prompt into the language model.
+            llm_string: A string representation of the LLM configuration.
+            return_val: The value to be cached. The value is a list of Generations
+                (or subclasses).
+        """
        self._cache[(prompt, llm_string)] = return_val

    def clear(self, **kwargs: Any) -> None:
@@ -161,15 +181,34 @@ class InMemoryCache(BaseCache):
        self._cache = {}

    async def alookup(self, prompt: str, llm_string: str) -> Optional[RETURN_VAL_TYPE]:
-        """Look up based on prompt and llm_string."""
+        """Async look up based on prompt and llm_string.
+
+        Args:
+            prompt: a string representation of the prompt.
+                In the case of a Chat model, the prompt is a non-trivial
+                serialization of the prompt into the language model.
+            llm_string: A string representation of the LLM configuration.
+
+        Returns:
+            On a cache miss, return None. On a cache hit, return the cached value.
+        """
        return self.lookup(prompt, llm_string)

    async def aupdate(
        self, prompt: str, llm_string: str, return_val: RETURN_VAL_TYPE
    ) -> None:
-        """Update cache based on prompt and llm_string."""
+        """Async update cache based on prompt and llm_string.
+
+        Args:
+            prompt: a string representation of the prompt.
+                In the case of a Chat model, the prompt is a non-trivial
+                serialization of the prompt into the language model.
+            llm_string: A string representation of the LLM configuration.
+            return_val: The value to be cached. The value is a list of Generations
+                (or subclasses).
+        """
        self.update(prompt, llm_string, return_val)

    async def aclear(self, **kwargs: Any) -> None:
-        """Clear cache."""
+        """Async clear cache."""
        self.clear()
--- a/libs/core/langchain_core/callbacks/init.py
+++ b/libs/core/langchain_core/callbacks/init.py
@@ -6,6 +6,7 @@

    BaseCallbackHandler --> <name>CallbackHandler  # Example: AimCallbackHandler
 """
+
 from langchain_core.callbacks.base import (
    AsyncCallbackHandler,
    BaseCallbackHandler,
--- a/libs/core/langchain_core/callbacks/base.py
+++ b/libs/core/langchain_core/callbacks/base.py
@@ -1,4 +1,5 @@
-"""Base callback handler that can be used to handle callbacks in langchain."""
+"""Base callback handler for LangChain."""
+
 from __future__ import annotations

 from typing import TYPE_CHECKING, Any, Dict, List, Optional, Sequence, TypeVar, Union
@@ -54,7 +55,10 @@ class LLMManagerMixin:
        Args:
            token (str): The new token.
            chunk (GenerationChunk | ChatGenerationChunk): The new generated chunk,
-            containing content and other information.
+              containing content and other information.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
+            kwargs (Any): Additional keyword arguments.
        """

    def on_llm_end(
@@ -65,7 +69,14 @@ class LLMManagerMixin:
        parent_run_id: Optional[UUID] = None,
        **kwargs: Any,
    ) -> Any:
-        """Run when LLM ends running."""
+        """Run when LLM ends running.
+
+        Args:
+            response (LLMResult): The response which was generated.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
+            kwargs (Any): Additional keyword arguments.
+        """

    def on_llm_error(
        self,
@@ -76,11 +87,12 @@ class LLMManagerMixin:
        **kwargs: Any,
    ) -> Any:
        """Run when LLM errors.
+
        Args:
            error (BaseException): The error that occurred.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
            kwargs (Any): Additional keyword arguments.
-                - response (LLMResult): The response which was generated before
-                    the error occurred.
        """


@@ -95,7 +107,13 @@ class ChainManagerMixin:
        parent_run_id: Optional[UUID] = None,
        **kwargs: Any,
    ) -> Any:
-        """Run when chain ends running."""
+        """Run when chain ends running.
+
+        Args:
+            outputs (Dict[str, Any]): The outputs of the chain.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
+            kwargs (Any): Additional keyword arguments."""

    def on_chain_error(
        self,
@@ -105,7 +123,13 @@ class ChainManagerMixin:
        parent_run_id: Optional[UUID] = None,
        **kwargs: Any,
    ) -> Any:
-        """Run when chain errors."""
+        """Run when chain errors.
+
+        Args:
+            error (BaseException): The error that occurred.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
+            kwargs (Any): Additional keyword arguments."""

    def on_agent_action(
        self,
@@ -115,7 +139,13 @@ class ChainManagerMixin:
        parent_run_id: Optional[UUID] = None,
        **kwargs: Any,
    ) -> Any:
-        """Run on agent action."""
+        """Run on agent action.
+
+        Args:
+            action (AgentAction): The agent action.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
+            kwargs (Any): Additional keyword arguments."""

    def on_agent_finish(
        self,
@@ -125,7 +155,13 @@ class ChainManagerMixin:
        parent_run_id: Optional[UUID] = None,
        **kwargs: Any,
    ) -> Any:
-        """Run on agent end."""
+        """Run on the agent end.
+
+        Args:
+            finish (AgentFinish): The agent finish.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
+            kwargs (Any): Additional keyword arguments."""


 class ToolManagerMixin:
@@ -139,7 +175,13 @@ class ToolManagerMixin:
        parent_run_id: Optional[UUID] = None,
        **kwargs: Any,
    ) -> Any:
-        """Run when tool ends running."""
+        """Run when the tool ends running.
+
+        Args:
+            output (Any): The output of the tool.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
+            kwargs (Any): Additional keyword arguments."""

    def on_tool_error(
        self,
@@ -149,7 +191,13 @@ class ToolManagerMixin:
        parent_run_id: Optional[UUID] = None,
        **kwargs: Any,
    ) -> Any:
-        """Run when tool errors."""
+        """Run when tool errors.
+
+        Args:
+            error (BaseException): The error that occurred.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
+            kwargs (Any): Additional keyword arguments."""


 class CallbackManagerMixin:
@@ -171,6 +219,15 @@ class CallbackManagerMixin:
        **ATTENTION**: This method is called for non-chat models (regular LLMs). If
            you're implementing a handler for a chat model,
            you should use on_chat_model_start instead.
+
+        Args:
+            serialized (Dict[str, Any]): The serialized LLM.
+            prompts (List[str]): The prompts.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
+            tags (Optional[List[str]]): The tags.
+            metadata (Optional[Dict[str, Any]]): The metadata.
+            kwargs (Any): Additional keyword arguments.
        """

    def on_chat_model_start(
@@ -188,6 +245,15 @@ class CallbackManagerMixin:

        **ATTENTION**: This method is called for chat models. If you're implementing
            a handler for a non-chat model, you should use on_llm_start instead.
+
+        Args:
+            serialized (Dict[str, Any]): The serialized chat model.
+            messages (List[List[BaseMessage]]): The messages.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
+            tags (Optional[List[str]]): The tags.
+            metadata (Optional[Dict[str, Any]]): The metadata.
+            kwargs (Any): Additional keyword arguments.
        """
        # NotImplementedError is thrown intentionally
        # Callback handler will fall back to on_llm_start if this is exception is thrown
@@ -206,7 +272,17 @@ class CallbackManagerMixin:
        metadata: Optional[Dict[str, Any]] = None,
        **kwargs: Any,
    ) -> Any:
-        """Run when Retriever starts running."""
+        """Run when the Retriever starts running.
+
+        Args:
+            serialized (Dict[str, Any]): The serialized Retriever.
+            query (str): The query.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
+            tags (Optional[List[str]]): The tags.
+            metadata (Optional[Dict[str, Any]]): The metadata.
+            kwargs (Any): Additional keyword arguments.
+        """

    def on_chain_start(
        self,
@@ -219,7 +295,17 @@ class CallbackManagerMixin:
        metadata: Optional[Dict[str, Any]] = None,
        **kwargs: Any,
    ) -> Any:
-        """Run when chain starts running."""
+        """Run when a chain starts running.
+
+        Args:
+            serialized (Dict[str, Any]): The serialized chain.
+            inputs (Dict[str, Any]): The inputs.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
+            tags (Optional[List[str]]): The tags.
+            metadata (Optional[Dict[str, Any]]): The metadata.
+            kwargs (Any): Additional keyword arguments.
+        """

    def on_tool_start(
        self,
@@ -233,7 +319,18 @@ class CallbackManagerMixin:
        inputs: Optional[Dict[str, Any]] = None,
        **kwargs: Any,
    ) -> Any:
-        """Run when tool starts running."""
+        """Run when the tool starts running.
+
+        Args:
+            serialized (Dict[str, Any]): The serialized tool.
+            input_str (str): The input string.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
+            tags (Optional[List[str]]): The tags.
+            metadata (Optional[Dict[str, Any]]): The metadata.
+            inputs (Optional[Dict[str, Any]]): The inputs.
+            kwargs (Any): Additional keyword arguments.
+        """


 class RunManagerMixin:
@@ -247,7 +344,14 @@ class RunManagerMixin:
        parent_run_id: Optional[UUID] = None,
        **kwargs: Any,
    ) -> Any:
-        """Run on arbitrary text."""
+        """Run on an arbitrary text.
+
+        Args:
+            text (str): The text.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
+            kwargs (Any): Additional keyword arguments.
+        """

    def on_retry(
        self,
@@ -257,7 +361,14 @@ class RunManagerMixin:
        parent_run_id: Optional[UUID] = None,
        **kwargs: Any,
    ) -> Any:
-        """Run on a retry event."""
+        """Run on a retry event.
+
+        Args:
+            retry_state (RetryCallState): The retry state.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
+            kwargs (Any): Additional keyword arguments.
+        """


 class BaseCallbackHandler(
@@ -268,11 +379,13 @@ class BaseCallbackHandler(
    CallbackManagerMixin,
    RunManagerMixin,
 ):
-    """Base callback handler that handles callbacks from LangChain."""
+    """Base callback handler for LangChain."""

    raise_error: bool = False
+    """Whether to raise an error if an exception occurs."""

    run_inline: bool = False
+    """Whether to run the callback inline."""

    @property
    def ignore_llm(self) -> bool:
@@ -306,7 +419,7 @@ class BaseCallbackHandler(


 class AsyncCallbackHandler(BaseCallbackHandler):
-    """Async callback handler that handles callbacks from LangChain."""
+    """Async callback handler for LangChain."""

    async def on_llm_start(
        self,
@@ -324,6 +437,15 @@ class AsyncCallbackHandler(BaseCallbackHandler):
        **ATTENTION**: This method is called for non-chat models (regular LLMs). If
            you're implementing a handler for a chat model,
            you should use on_chat_model_start instead.
+
+        Args:
+            serialized (Dict[str, Any]): The serialized LLM.
+            prompts (List[str]): The prompts.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
+            tags (Optional[List[str]]): The tags.
+            metadata (Optional[Dict[str, Any]]): The metadata.
+            kwargs (Any): Additional keyword arguments.
        """

    async def on_chat_model_start(
@@ -341,6 +463,15 @@ class AsyncCallbackHandler(BaseCallbackHandler):

        **ATTENTION**: This method is called for chat models. If you're implementing
            a handler for a non-chat model, you should use on_llm_start instead.
+
+        Args:
+            serialized (Dict[str, Any]): The serialized chat model.
+            messages (List[List[BaseMessage]]): The messages.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
+            tags (Optional[List[str]]): The tags.
+            metadata (Optional[Dict[str, Any]]): The metadata.
+            kwargs (Any): Additional keyword arguments.
        """
        # NotImplementedError is thrown intentionally
        # Callback handler will fall back to on_llm_start if this is exception is thrown
@@ -358,7 +489,17 @@ class AsyncCallbackHandler(BaseCallbackHandler):
        tags: Optional[List[str]] = None,
        **kwargs: Any,
    ) -> None:
-        """Run on new LLM token. Only available when streaming is enabled."""
+        """Run on new LLM token. Only available when streaming is enabled.
+
+        Args:
+            token (str): The new token.
+            chunk (GenerationChunk | ChatGenerationChunk): The new generated chunk,
+              containing content and other information.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
+            tags (Optional[List[str]]): The tags.
+            kwargs (Any): Additional keyword arguments.
+        """

    async def on_llm_end(
        self,
@@ -369,7 +510,15 @@ class AsyncCallbackHandler(BaseCallbackHandler):
        tags: Optional[List[str]] = None,
        **kwargs: Any,
    ) -> None:
-        """Run when LLM ends running."""
+        """Run when LLM ends running.
+
+        Args:
+            response (LLMResult): The response which was generated.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
+            tags (Optional[List[str]]): The tags.
+            kwargs (Any): Additional keyword arguments.
+        """

    async def on_llm_error(
        self,
@@ -384,6 +533,9 @@ class AsyncCallbackHandler(BaseCallbackHandler):

        Args:
            error: The error that occurred.
+            run_id: The run ID. This is the ID of the current run.
+            parent_run_id: The parent run ID. This is the ID of the parent run.
+            tags: The tags.
            kwargs (Any): Additional keyword arguments.
                - response (LLMResult): The response which was generated before
                    the error occurred.
@@ -400,7 +552,17 @@ class AsyncCallbackHandler(BaseCallbackHandler):
        metadata: Optional[Dict[str, Any]] = None,
        **kwargs: Any,
    ) -> None:
-        """Run when chain starts running."""
+        """Run when a chain starts running.
+
+        Args:
+            serialized (Dict[str, Any]): The serialized chain.
+            inputs (Dict[str, Any]): The inputs.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
+            tags (Optional[List[str]]): The tags.
+            metadata (Optional[Dict[str, Any]]): The metadata.
+            kwargs (Any): Additional keyword arguments.
+        """

    async def on_chain_end(
        self,
@@ -411,7 +573,15 @@ class AsyncCallbackHandler(BaseCallbackHandler):
        tags: Optional[List[str]] = None,
        **kwargs: Any,
    ) -> None:
-        """Run when chain ends running."""
+        """Run when a chain ends running.
+
+        Args:
+            outputs (Dict[str, Any]): The outputs of the chain.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
+            tags (Optional[List[str]]): The tags.
+            kwargs (Any): Additional keyword arguments.
+        """

    async def on_chain_error(
        self,
@@ -422,7 +592,15 @@ class AsyncCallbackHandler(BaseCallbackHandler):
        tags: Optional[List[str]] = None,
        **kwargs: Any,
    ) -> None:
-        """Run when chain errors."""
+        """Run when chain errors.
+
+        Args:
+            error (BaseException): The error that occurred.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
+            tags (Optional[List[str]]): The tags.
+            kwargs (Any): Additional keyword arguments.
+        """

    async def on_tool_start(
        self,
@@ -436,7 +614,18 @@ class AsyncCallbackHandler(BaseCallbackHandler):
        inputs: Optional[Dict[str, Any]] = None,
        **kwargs: Any,
    ) -> None:
-        """Run when tool starts running."""
+        """Run when the tool starts running.
+
+        Args:
+            serialized (Dict[str, Any]): The serialized tool.
+            input_str (str): The input string.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
+            tags (Optional[List[str]]): The tags.
+            metadata (Optional[Dict[str, Any]]): The metadata.
+            inputs (Optional[Dict[str, Any]]): The inputs.
+            kwargs (Any): Additional keyword arguments.
+        """

    async def on_tool_end(
        self,
@@ -447,7 +636,15 @@ class AsyncCallbackHandler(BaseCallbackHandler):
        tags: Optional[List[str]] = None,
        **kwargs: Any,
    ) -> None:
-        """Run when tool ends running."""
+        """Run when the tool ends running.
+
+        Args:
+            output (Any): The output of the tool.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
+            tags (Optional[List[str]]): The tags.
+            kwargs (Any): Additional keyword arguments.
+        """

    async def on_tool_error(
        self,
@@ -458,7 +655,15 @@ class AsyncCallbackHandler(BaseCallbackHandler):
        tags: Optional[List[str]] = None,
        **kwargs: Any,
    ) -> None:
-        """Run when tool errors."""
+        """Run when tool errors.
+
+        Args:
+            error (BaseException): The error that occurred.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
+            tags (Optional[List[str]]): The tags.
+            kwargs (Any): Additional keyword arguments.
+        """

    async def on_text(
        self,
@@ -469,7 +674,15 @@ class AsyncCallbackHandler(BaseCallbackHandler):
        tags: Optional[List[str]] = None,
        **kwargs: Any,
    ) -> None:
-        """Run on arbitrary text."""
+        """Run on an arbitrary text.
+
+        Args:
+            text (str): The text.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
+            tags (Optional[List[str]]): The tags.
+            kwargs (Any): Additional keyword arguments.
+        """

    async def on_retry(
        self,
@@ -479,7 +692,14 @@ class AsyncCallbackHandler(BaseCallbackHandler):
        parent_run_id: Optional[UUID] = None,
        **kwargs: Any,
    ) -> Any:
-        """Run on a retry event."""
+        """Run on a retry event.
+
+        Args:
+            retry_state (RetryCallState): The retry state.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
+            kwargs (Any): Additional keyword arguments.
+        """

    async def on_agent_action(
        self,
@@ -490,7 +710,15 @@ class AsyncCallbackHandler(BaseCallbackHandler):
        tags: Optional[List[str]] = None,
        **kwargs: Any,
    ) -> None:
-        """Run on agent action."""
+        """Run on agent action.
+
+        Args:
+            action (AgentAction): The agent action.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
+            tags (Optional[List[str]]): The tags.
+            kwargs (Any): Additional keyword arguments.
+        """

    async def on_agent_finish(
        self,
@@ -501,7 +729,15 @@ class AsyncCallbackHandler(BaseCallbackHandler):
        tags: Optional[List[str]] = None,
        **kwargs: Any,
    ) -> None:
-        """Run on agent end."""
+        """Run on the agent end.
+
+        Args:
+            finish (AgentFinish): The agent finish.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
+            tags (Optional[List[str]]): The tags.
+            kwargs (Any): Additional keyword arguments.
+        """

    async def on_retriever_start(
        self,
@@ -514,7 +750,17 @@ class AsyncCallbackHandler(BaseCallbackHandler):
        metadata: Optional[Dict[str, Any]] = None,
        **kwargs: Any,
    ) -> None:
-        """Run on retriever start."""
+        """Run on the retriever start.
+
+        Args:
+            serialized (Dict[str, Any]): The serialized retriever.
+            query (str): The query.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
+            tags (Optional[List[str]]): The tags.
+            metadata (Optional[Dict[str, Any]]): The metadata.
+            kwargs (Any): Additional keyword arguments.
+        """

    async def on_retriever_end(
        self,
@@ -525,7 +771,14 @@ class AsyncCallbackHandler(BaseCallbackHandler):
        tags: Optional[List[str]] = None,
        **kwargs: Any,
    ) -> None:
-        """Run on retriever end."""
+        """Run on the retriever end.
+
+        Args:
+            documents (Sequence[Document]): The documents retrieved.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
+            tags (Optional[List[str]]): The tags.
+            kwargs (Any): Additional keyword arguments."""

    async def on_retriever_error(
        self,
@@ -536,14 +789,22 @@ class AsyncCallbackHandler(BaseCallbackHandler):
        tags: Optional[List[str]] = None,
        **kwargs: Any,
    ) -> None:
-        """Run on retriever error."""
+        """Run on retriever error.
+
+        Args:
+            error (BaseException): The error that occurred.
+            run_id (UUID): The run ID. This is the ID of the current run.
+            parent_run_id (UUID): The parent run ID. This is the ID of the parent run.
+            tags (Optional[List[str]]): The tags.
+            kwargs (Any): Additional keyword arguments.
+        """


 T = TypeVar("T", bound="BaseCallbackManager")


 class BaseCallbackManager(CallbackManagerMixin):
-    """Base callback manager that handles callbacks from LangChain."""
+    """Base callback manager for LangChain."""

    def __init__(
        self,
@@ -556,7 +817,18 @@ class BaseCallbackManager(CallbackManagerMixin):
        metadata: Optional[Dict[str, Any]] = None,
        inheritable_metadata: Optional[Dict[str, Any]] = None,
    ) -> None:
-        """Initialize callback manager."""
+        """Initialize callback manager.
+
+        Args:
+            handlers (List[BaseCallbackHandler]): The handlers.
+            inheritable_handlers (Optional[List[BaseCallbackHandler]]):
+              The inheritable handlers. Default is None.
+            parent_run_id (Optional[UUID]): The parent run ID. Default is None.
+            tags (Optional[List[str]]): The tags. Default is None.
+            inheritable_tags (Optional[List[str]]): The inheritable tags.
+                Default is None.
+            metadata (Optional[Dict[str, Any]]): The metadata. Default is None.
+        """
        self.handlers: List[BaseCallbackHandler] = handlers
        self.inheritable_handlers: List[BaseCallbackHandler] = (
            inheritable_handlers or []
@@ -585,31 +857,56 @@ class BaseCallbackManager(CallbackManagerMixin):
        return False

    def add_handler(self, handler: BaseCallbackHandler, inherit: bool = True) -> None:
-        """Add a handler to the callback manager."""
+        """Add a handler to the callback manager.
+
+        Args:
+            handler (BaseCallbackHandler): The handler to add.
+            inherit (bool): Whether to inherit the handler. Default is True.
+        """
        if handler not in self.handlers:
            self.handlers.append(handler)
        if inherit and handler not in self.inheritable_handlers:
            self.inheritable_handlers.append(handler)

    def remove_handler(self, handler: BaseCallbackHandler) -> None:
-        """Remove a handler from the callback manager."""
+        """Remove a handler from the callback manager.
+
+        Args:
+            handler (BaseCallbackHandler): The handler to remove.
+        """
        self.handlers.remove(handler)
        self.inheritable_handlers.remove(handler)

    def set_handlers(
        self, handlers: List[BaseCallbackHandler], inherit: bool = True
    ) -> None:
-        """Set handlers as the only handlers on the callback manager."""
+        """Set handlers as the only handlers on the callback manager.
+
+        Args:
+            handlers (List[BaseCallbackHandler]): The handlers to set.
+            inherit (bool): Whether to inherit the handlers. Default is True.
+        """
        self.handlers = []
        self.inheritable_handlers = []
        for handler in handlers:
            self.add_handler(handler, inherit=inherit)

    def set_handler(self, handler: BaseCallbackHandler, inherit: bool = True) -> None:
-        """Set handler as the only handler on the callback manager."""
+        """Set handler as the only handler on the callback manager.
+
+        Args:
+            handler (BaseCallbackHandler): The handler to set.
+            inherit (bool): Whether to inherit the handler. Default is True.
+        """
        self.set_handlers([handler], inherit=inherit)

    def add_tags(self, tags: List[str], inherit: bool = True) -> None:
+        """Add tags to the callback manager.
+
+        Args:
+            tags (List[str]): The tags to add.
+            inherit (bool): Whether to inherit the tags. Default is True.
+        """
        for tag in tags:
            if tag in self.tags:
                self.remove_tags([tag])
@@ -618,16 +915,32 @@ class BaseCallbackManager(CallbackManagerMixin):
            self.inheritable_tags.extend(tags)

    def remove_tags(self, tags: List[str]) -> None:
+        """Remove tags from the callback manager.
+
+        Args:
+            tags (List[str]): The tags to remove.
+        """
        for tag in tags:
            self.tags.remove(tag)
            self.inheritable_tags.remove(tag)

    def add_metadata(self, metadata: Dict[str, Any], inherit: bool = True) -> None:
+        """Add metadata to the callback manager.
+
+        Args:
+            metadata (Dict[str, Any]): The metadata to add.
+            inherit (bool): Whether to inherit the metadata. Default is True.
+        """
        self.metadata.update(metadata)
        if inherit:
            self.inheritable_metadata.update(metadata)

    def remove_metadata(self, keys: List[str]) -> None:
+        """Remove metadata from the callback manager.
+
+        Args:
+            keys (List[str]): The keys to remove.
+        """
        for key in keys:
            self.metadata.pop(key)
            self.inheritable_metadata.pop(key)
--- a/libs/core/langchain_core/callbacks/file.py
+++ b/libs/core/langchain_core/callbacks/file.py
@@ -10,12 +10,23 @@ from langchain_core.utils.input import print_text


 class FileCallbackHandler(BaseCallbackHandler):
-    """Callback Handler that writes to a file."""
+    """Callback Handler that writes to a file.
+
+    Parameters:
+        file: The file to write to.
+        color: The color to use for the text.
+    """

    def __init__(
        self, filename: str, mode: str = "a", color: Optional[str] = None
    ) -> None:
-        """Initialize callback handler."""
+        """Initialize callback handler.
+
+        Args:
+            filename: The filename to write to.
+            mode: The mode to open the file in. Defaults to "a".
+            color: The color to use for the text. Defaults to None.
+        """
        self.file = cast(TextIO, open(filename, mode, encoding="utf-8"))
        self.color = color

@@ -26,7 +37,13 @@ class FileCallbackHandler(BaseCallbackHandler):
    def on_chain_start(
        self, serialized: Dict[str, Any], inputs: Dict[str, Any], **kwargs: Any
    ) -> None:
-        """Print out that we are entering a chain."""
+        """Print out that we are entering a chain.
+
+        Args:
+            serialized (Dict[str, Any]): The serialized chain.
+            inputs (Dict[str, Any]): The inputs to the chain.
+            **kwargs (Any): Additional keyword arguments.
+        """
        class_name = serialized.get("name", serialized.get("id", ["<unknown>"])[-1])
        print_text(
            f"\n\n\033[1m> Entering new {class_name} chain...\033[0m",
@@ -35,13 +52,25 @@ class FileCallbackHandler(BaseCallbackHandler):
        )

    def on_chain_end(self, outputs: Dict[str, Any], **kwargs: Any) -> None:
-        """Print out that we finished a chain."""
+        """Print out that we finished a chain.
+
+        Args:
+            outputs (Dict[str, Any]): The outputs of the chain.
+            **kwargs (Any): Additional keyword arguments.
+        """
        print_text("\n\033[1m> Finished chain.\033[0m", end="\n", file=self.file)

    def on_agent_action(
        self, action: AgentAction, color: Optional[str] = None, **kwargs: Any
    ) -> Any:
-        """Run on agent action."""
+        """Run on agent action.
+
+        Args:
+            action (AgentAction): The agent action.
+            color (Optional[str], optional): The color to use for the text.
+                Defaults to None.
+            **kwargs (Any): Additional keyword arguments.
+        """
        print_text(action.log, color=color or self.color, file=self.file)

    def on_tool_end(
@@ -52,7 +81,18 @@ class FileCallbackHandler(BaseCallbackHandler):
        llm_prefix: Optional[str] = None,
        **kwargs: Any,
    ) -> None:
-        """If not the final action, print out observation."""
+        """If not the final action, print out observation.
+
+        Args:
+           output (str): The output to print.
+           color (Optional[str], optional): The color to use for the text.
+                Defaults to None.
+           observation_prefix (Optional[str], optional): The observation prefix.
+            Defaults to None.
+           llm_prefix (Optional[str], optional): The LLM prefix.
+                Defaults to None.
+           **kwargs (Any): Additional keyword arguments.
+        """
        if observation_prefix is not None:
            print_text(f"\n{observation_prefix}", file=self.file)
        print_text(output, color=color or self.color, file=self.file)
@@ -62,11 +102,26 @@ class FileCallbackHandler(BaseCallbackHandler):
    def on_text(
        self, text: str, color: Optional[str] = None, end: str = "", **kwargs: Any
    ) -> None:
-        """Run when agent ends."""
+        """Run when the agent ends.
+
+        Args:
+           text (str): The text to print.
+           color (Optional[str], optional): The color to use for the text.
+            Defaults to None.
+           end (str, optional): The end character. Defaults to "".
+           **kwargs (Any): Additional keyword arguments.
+        """
        print_text(text, color=color or self.color, end=end, file=self.file)

    def on_agent_finish(
        self, finish: AgentFinish, color: Optional[str] = None, **kwargs: Any
    ) -> None:
-        """Run on agent end."""
+        """Run on the agent end.
+
+        Args:
+            finish (AgentFinish): The agent finish.
+            color (Optional[str], optional): The color to use for the text.
+                Defaults to None.
+            **kwargs (Any): Additional keyword arguments.
+        """
        print_text(finish.log, color=color or self.color, end="\n", file=self.file)
--- a/libs/core/langchain_core/callbacks/manager.py
+++ b/libs/core/langchain_core/callbacks/manager.py
@@ -77,7 +77,9 @@ def trace_as_chain_group(
    Args:
        group_name (str): The name of the chain group.
        callback_manager (CallbackManager, optional): The callback manager to use.
+            Defaults to None.
        inputs (Dict[str, Any], optional): The inputs to the chain group.
+            Defaults to None.
        project_name (str, optional): The name of the project.
            Defaults to None.
        example_id (str or UUID, optional): The ID of the example.
@@ -155,7 +157,9 @@ async def atrace_as_chain_group(
    Args:
        group_name (str): The name of the chain group.
        callback_manager (AsyncCallbackManager, optional): The async callback manager to use,
-            which manages tracing and other callback behavior.
+            which manages tracing and other callback behavior. Defaults to None.
+        inputs (Dict[str, Any], optional): The inputs to the chain group.
+            Defaults to None.
        project_name (str, optional): The name of the project.
            Defaults to None.
        example_id (str or UUID, optional): The ID of the example.
@@ -218,7 +222,13 @@ Func = TypeVar("Func", bound=Callable)

 def shielded(func: Func) -> Func:
    """
-    Makes so an awaitable method is always shielded from cancellation
+    Makes so an awaitable method is always shielded from cancellation.
+
+    Args:
+        func (Callable): The function to shield.
+
+    Returns:
+        Callable: The shielded function
    """

    @functools.wraps(func)
@@ -237,14 +247,14 @@ def handle_event(
 ) -> None:
    """Generic event handler for CallbackManager.

-    Note: This function is used by langserve to handle events.
+    Note: This function is used by LangServe to handle events.

    Args:
-        handlers: The list of handlers that will handle the event
-        event_name: The name of the event (e.g., "on_llm_start")
+        handlers: The list of handlers that will handle the event.
+        event_name: The name of the event (e.g., "on_llm_start").
        ignore_condition_name: Name of the attribute defined on handler
-            that if True will cause the handler to be skipped for the given event
-        *args: The arguments to pass to the event handler
+            that if True will cause the handler to be skipped for the given event.
+        *args: The arguments to pass to the event handler.
        **kwargs: The keyword arguments to pass to the event handler
    """
    coros: List[Coroutine[Any, Any, Any]] = []
@@ -394,17 +404,17 @@ async def ahandle_event(
    *args: Any,
    **kwargs: Any,
 ) -> None:
-    """Generic event handler for AsyncCallbackManager.
+    """Async generic event handler for AsyncCallbackManager.

-    Note: This function is used by langserve to handle events.
+    Note: This function is used by LangServe to handle events.

    Args:
-        handlers: The list of handlers that will handle the event
-        event_name: The name of the event (e.g., "on_llm_start")
+        handlers: The list of handlers that will handle the event.
+        event_name: The name of the event (e.g., "on_llm_start").
        ignore_condition_name: Name of the attribute defined on handler
-            that if True will cause the handler to be skipped for the given event
-        *args: The arguments to pass to the event handler
-        **kwargs: The keyword arguments to pass to the event handler
+            that if True will cause the handler to be skipped for the given event.
+        *args: The arguments to pass to the event handler.
+        **kwargs: The keyword arguments to pass to the event handler.
    """
    for handler in [h for h in handlers if h.run_inline]:
        await _ahandle_event_for_handler(
@@ -452,10 +462,13 @@ class BaseRunManager(RunManagerMixin):
                The list of inheritable handlers.
            parent_run_id (UUID, optional): The ID of the parent run.
                Defaults to None.
-            tags (Optional[List[str]]): The list of tags.
+            tags (Optional[List[str]]): The list of tags. Defaults to None.
            inheritable_tags (Optional[List[str]]): The list of inheritable tags.
+                Defaults to None.
            metadata (Optional[Dict[str, Any]]): The metadata.
+                Defaults to None.
            inheritable_metadata (Optional[Dict[str, Any]]): The inheritable metadata.
+                Defaults to None.
        """
        self.run_id = run_id
        self.handlers = handlers
@@ -492,10 +505,11 @@ class RunManager(BaseRunManager):
        text: str,
        **kwargs: Any,
    ) -> Any:
-        """Run when text is received.
+        """Run when a text is received.

        Args:
            text (str): The received text.
+            **kwargs (Any): Additional keyword arguments.

        Returns:
            Any: The result of the callback.
@@ -516,6 +530,12 @@ class RunManager(BaseRunManager):
        retry_state: RetryCallState,
        **kwargs: Any,
    ) -> None:
+        """Run when a retry is received.
+
+        Args:
+            retry_state (RetryCallState): The retry state.
+            **kwargs (Any): Additional keyword arguments.
+        """
        handle_event(
            self.handlers,
            "on_retry",
@@ -566,10 +586,11 @@ class AsyncRunManager(BaseRunManager, ABC):
        text: str,
        **kwargs: Any,
    ) -> Any:
-        """Run when text is received.
+        """Run when a text is received.

        Args:
            text (str): The received text.
+            **kwargs (Any): Additional keyword arguments.

        Returns:
            Any: The result of the callback.
@@ -590,6 +611,12 @@ class AsyncRunManager(BaseRunManager, ABC):
        retry_state: RetryCallState,
        **kwargs: Any,
    ) -> None:
+        """Async run when a retry is received.
+
+        Args:
+            retry_state (RetryCallState): The retry state.
+            **kwargs (Any): Additional keyword arguments.
+        """
        await ahandle_event(
            self.handlers,
            "on_retry",
@@ -638,6 +665,9 @@ class CallbackManagerForLLMRun(RunManager, LLMManagerMixin):

        Args:
            token (str): The new token.
+            chunk (Optional[Union[GenerationChunk, ChatGenerationChunk]], optional):
+                The chunk. Defaults to None.
+            **kwargs (Any): Additional keyword arguments.
        """
        handle_event(
            self.handlers,
@@ -656,6 +686,7 @@ class CallbackManagerForLLMRun(RunManager, LLMManagerMixin):

        Args:
            response (LLMResult): The LLM result.
+            **kwargs (Any): Additional keyword arguments.
        """
        handle_event(
            self.handlers,
@@ -725,6 +756,9 @@ class AsyncCallbackManagerForLLMRun(AsyncRunManager, LLMManagerMixin):

        Args:
            token (str): The new token.
+            chunk (Optional[Union[GenerationChunk, ChatGenerationChunk]], optional):
+                The chunk. Defaults to None.
+            **kwargs (Any): Additional keyword arguments.
        """
        await ahandle_event(
            self.handlers,
@@ -744,6 +778,7 @@ class AsyncCallbackManagerForLLMRun(AsyncRunManager, LLMManagerMixin):

        Args:
            response (LLMResult): The LLM result.
+            **kwargs (Any): Additional keyword arguments.
        """
        await ahandle_event(
            self.handlers,
@@ -793,6 +828,7 @@ class CallbackManagerForChainRun(ParentRunManager, ChainManagerMixin):

        Args:
            outputs (Union[Dict[str, Any], Any]): The outputs of the chain.
+            **kwargs (Any): Additional keyword arguments.
        """
        handle_event(
            self.handlers,
@@ -814,6 +850,7 @@ class CallbackManagerForChainRun(ParentRunManager, ChainManagerMixin):

        Args:
            error (Exception or KeyboardInterrupt): The error.
+            **kwargs (Any): Additional keyword arguments.
        """
        handle_event(
            self.handlers,
@@ -831,6 +868,7 @@ class CallbackManagerForChainRun(ParentRunManager, ChainManagerMixin):

        Args:
            action (AgentAction): The agent action.
+            **kwargs (Any): Additional keyword arguments.

        Returns:
            Any: The result of the callback.
@@ -851,6 +889,7 @@ class CallbackManagerForChainRun(ParentRunManager, ChainManagerMixin):

        Args:
            finish (AgentFinish): The agent finish.
+            **kwargs (Any): Additional keyword arguments.

        Returns:
            Any: The result of the callback.
@@ -891,10 +930,11 @@ class AsyncCallbackManagerForChainRun(AsyncParentRunManager, ChainManagerMixin):
    async def on_chain_end(
        self, outputs: Union[Dict[str, Any], Any], **kwargs: Any
    ) -> None:
-        """Run when chain ends running.
+        """Run when a chain ends running.

        Args:
            outputs (Union[Dict[str, Any], Any]): The outputs of the chain.
+            **kwargs (Any): Additional keyword arguments.
        """
        await ahandle_event(
            self.handlers,
@@ -917,6 +957,7 @@ class AsyncCallbackManagerForChainRun(AsyncParentRunManager, ChainManagerMixin):

        Args:
            error (Exception or KeyboardInterrupt): The error.
+            **kwargs (Any): Additional keyword arguments.
        """
        await ahandle_event(
            self.handlers,
@@ -935,6 +976,7 @@ class AsyncCallbackManagerForChainRun(AsyncParentRunManager, ChainManagerMixin):

        Args:
            action (AgentAction): The agent action.
+            **kwargs (Any): Additional keyword arguments.

        Returns:
            Any: The result of the callback.
@@ -956,6 +998,7 @@ class AsyncCallbackManagerForChainRun(AsyncParentRunManager, ChainManagerMixin):

        Args:
            finish (AgentFinish): The agent finish.
+            **kwargs (Any): Additional keyword arguments.

        Returns:
            Any: The result of the callback.
@@ -980,10 +1023,11 @@ class CallbackManagerForToolRun(ParentRunManager, ToolManagerMixin):
        output: Any,
        **kwargs: Any,
    ) -> None:
-        """Run when tool ends running.
+        """Run when the tool ends running.

        Args:
            output (Any): The output of the tool.
+            **kwargs (Any): Additional keyword arguments.
        """
        handle_event(
            self.handlers,
@@ -1005,6 +1049,7 @@ class CallbackManagerForToolRun(ParentRunManager, ToolManagerMixin):

        Args:
            error (Exception or KeyboardInterrupt): The error.
+            **kwargs (Any): Additional keyword arguments.
        """
        handle_event(
            self.handlers,
@@ -1040,10 +1085,11 @@ class AsyncCallbackManagerForToolRun(AsyncParentRunManager, ToolManagerMixin):

    @shielded
    async def on_tool_end(self, output: Any, **kwargs: Any) -> None:
-        """Run when tool ends running.
+        """Async run when the tool ends running.

        Args:
            output (Any): The output of the tool.
+            **kwargs (Any): Additional keyword arguments.
        """
        await ahandle_event(
            self.handlers,
@@ -1066,6 +1112,7 @@ class AsyncCallbackManagerForToolRun(AsyncParentRunManager, ToolManagerMixin):

        Args:
            error (Exception or KeyboardInterrupt): The error.
+            **kwargs (Any): Additional keyword arguments.
        """
        await ahandle_event(
            self.handlers,
@@ -1087,7 +1134,12 @@ class CallbackManagerForRetrieverRun(ParentRunManager, RetrieverManagerMixin):
        documents: Sequence[Document],
        **kwargs: Any,
    ) -> None:
-        """Run when retriever ends running."""
+        """Run when retriever ends running.
+
+        Args:
+            documents (Sequence[Document]): The retrieved documents.
+            **kwargs (Any): Additional keyword arguments.
+        """
        handle_event(
            self.handlers,
            "on_retriever_end",
@@ -1104,7 +1156,12 @@ class CallbackManagerForRetrieverRun(ParentRunManager, RetrieverManagerMixin):
        error: BaseException,
        **kwargs: Any,
    ) -> None:
-        """Run when retriever errors."""
+        """Run when retriever errors.
+
+        Args:
+            error (BaseException): The error.
+            **kwargs (Any): Additional keyword arguments.
+        """
        handle_event(
            self.handlers,
            "on_retriever_error",
@@ -1144,7 +1201,12 @@ class AsyncCallbackManagerForRetrieverRun(
    async def on_retriever_end(
        self, documents: Sequence[Document], **kwargs: Any
    ) -> None:
-        """Run when retriever ends running."""
+        """Run when the retriever ends running.
+
+        Args:
+            documents (Sequence[Document]): The retrieved documents.
+            **kwargs (Any): Additional keyword arguments.
+        """
        await ahandle_event(
            self.handlers,
            "on_retriever_end",
@@ -1162,7 +1224,12 @@ class AsyncCallbackManagerForRetrieverRun(
        error: BaseException,
        **kwargs: Any,
    ) -> None:
-        """Run when retriever errors."""
+        """Run when retriever errors.
+
+        Args:
+            error (BaseException): The error.
+            **kwargs (Any): Additional keyword arguments.
+        """
        await ahandle_event(
            self.handlers,
            "on_retriever_error",
@@ -1176,7 +1243,7 @@ class AsyncCallbackManagerForRetrieverRun(


 class CallbackManager(BaseCallbackManager):
-    """Callback manager that handles callbacks from LangChain."""
+    """Callback manager for LangChain."""

    def on_llm_start(
        self,
@@ -1191,6 +1258,7 @@ class CallbackManager(BaseCallbackManager):
            serialized (Dict[str, Any]): The serialized LLM.
            prompts (List[str]): The list of prompts.
            run_id (UUID, optional): The ID of the run. Defaults to None.
+            **kwargs (Any): Additional keyword arguments.

        Returns:
            List[CallbackManagerForLLMRun]: A callback manager for each
@@ -1241,6 +1309,7 @@ class CallbackManager(BaseCallbackManager):
            serialized (Dict[str, Any]): The serialized LLM.
            messages (List[List[BaseMessage]]): The list of messages.
            run_id (UUID, optional): The ID of the run. Defaults to None.
+            **kwargs (Any): Additional keyword arguments.

        Returns:
            List[CallbackManagerForLLMRun]: A callback manager for each
@@ -1295,6 +1364,7 @@ class CallbackManager(BaseCallbackManager):
            serialized (Dict[str, Any]): The serialized chain.
            inputs (Union[Dict[str, Any], Any]): The inputs to the chain.
            run_id (UUID, optional): The ID of the run. Defaults to None.
+            **kwargs (Any): Additional keyword arguments.

        Returns:
            CallbackManagerForChainRun: The callback manager for the chain run.
@@ -1347,6 +1417,7 @@ class CallbackManager(BaseCallbackManager):
                input is needed.
                If provided, the inputs are expected to be formatted as a dict.
                The keys will correspond to the named-arguments in the tool.
+            **kwargs (Any): Additional keyword arguments.

        Returns:
            CallbackManagerForToolRun: The callback manager for the tool run.
@@ -1387,7 +1458,15 @@ class CallbackManager(BaseCallbackManager):
        parent_run_id: Optional[UUID] = None,
        **kwargs: Any,
    ) -> CallbackManagerForRetrieverRun:
-        """Run when retriever starts running."""
+        """Run when the retriever starts running.
+
+        Args:
+            serialized (Dict[str, Any]): The serialized retriever.
+            query (str): The query.
+            run_id (UUID, optional): The ID of the run. Defaults to None.
+            parent_run_id (UUID, optional): The ID of the parent run. Defaults to None.
+            **kwargs (Any): Additional keyword arguments.
+        """
        if run_id is None:
            run_id = uuid.uuid4()

@@ -1470,6 +1549,16 @@ class CallbackManagerForChainGroup(CallbackManager):
        parent_run_manager: CallbackManagerForChainRun,
        **kwargs: Any,
    ) -> None:
+        """Initialize the callback manager.
+
+        Args:
+            handlers (List[BaseCallbackHandler]): The list of handlers.
+            inheritable_handlers (Optional[List[BaseCallbackHandler]]): The list of
+                inheritable handlers. Defaults to None.
+            parent_run_id (Optional[UUID]): The ID of the parent run. Defaults to None.
+            parent_run_manager (CallbackManagerForChainRun): The parent run manager.
+            **kwargs (Any): Additional keyword arguments.
+        """
        super().__init__(
            handlers,
            inheritable_handlers,
@@ -1480,6 +1569,7 @@ class CallbackManagerForChainGroup(CallbackManager):
        self.ended = False

    def copy(self) -> CallbackManagerForChainGroup:
+        """Copy the callback manager."""
        return self.__class__(
            handlers=self.handlers,
            inheritable_handlers=self.inheritable_handlers,
@@ -1496,6 +1586,7 @@ class CallbackManagerForChainGroup(CallbackManager):

        Args:
            outputs (Union[Dict[str, Any], Any]): The outputs of the chain.
+            **kwargs (Any): Additional keyword arguments.
        """
        self.ended = True
        return self.parent_run_manager.on_chain_end(outputs, **kwargs)
@@ -1509,6 +1600,7 @@ class CallbackManagerForChainGroup(CallbackManager):

        Args:
            error (Exception or KeyboardInterrupt): The error.
+            **kwargs (Any): Additional keyword arguments.
        """
        self.ended = True
        return self.parent_run_manager.on_chain_error(error, **kwargs)
@@ -1535,6 +1627,7 @@ class AsyncCallbackManager(BaseCallbackManager):
            serialized (Dict[str, Any]): The serialized LLM.
            prompts (List[str]): The list of prompts.
            run_id (UUID, optional): The ID of the run. Defaults to None.
+            **kwargs (Any): Additional keyword arguments.

        Returns:
            List[AsyncCallbackManagerForLLMRun]: The list of async
@@ -1591,12 +1684,13 @@ class AsyncCallbackManager(BaseCallbackManager):
        run_id: Optional[UUID] = None,
        **kwargs: Any,
    ) -> List[AsyncCallbackManagerForLLMRun]:
-        """Run when LLM starts running.
+        """Async run when LLM starts running.

        Args:
            serialized (Dict[str, Any]): The serialized LLM.
            messages (List[List[BaseMessage]]): The list of messages.
            run_id (UUID, optional): The ID of the run. Defaults to None.
+            **kwargs (Any): Additional keyword arguments.

        Returns:
            List[AsyncCallbackManagerForLLMRun]: The list of
@@ -1651,12 +1745,13 @@ class AsyncCallbackManager(BaseCallbackManager):
        run_id: Optional[UUID] = None,
        **kwargs: Any,
    ) -> AsyncCallbackManagerForChainRun:
-        """Run when chain starts running.
+        """Async run when chain starts running.

        Args:
            serialized (Dict[str, Any]): The serialized chain.
            inputs (Union[Dict[str, Any], Any]): The inputs to the chain.
            run_id (UUID, optional): The ID of the run. Defaults to None.
+            **kwargs (Any): Additional keyword arguments.

        Returns:
            AsyncCallbackManagerForChainRun: The async callback manager
@@ -1697,7 +1792,7 @@ class AsyncCallbackManager(BaseCallbackManager):
        parent_run_id: Optional[UUID] = None,
        **kwargs: Any,
    ) -> AsyncCallbackManagerForToolRun:
-        """Run when tool starts running.
+        """Run when the tool starts running.

        Args:
            serialized (Dict[str, Any]): The serialized tool.
@@ -1705,6 +1800,7 @@ class AsyncCallbackManager(BaseCallbackManager):
            run_id (UUID, optional): The ID of the run. Defaults to None.
            parent_run_id (UUID, optional): The ID of the parent run.
                Defaults to None.
+            **kwargs (Any): Additional keyword arguments.

        Returns:
            AsyncCallbackManagerForToolRun: The async callback manager
@@ -1745,7 +1841,19 @@ class AsyncCallbackManager(BaseCallbackManager):
        parent_run_id: Optional[UUID] = None,
        **kwargs: Any,
    ) -> AsyncCallbackManagerForRetrieverRun:
-        """Run when retriever starts running."""
+        """Run when the retriever starts running.
+
+        Args:
+            serialized (Dict[str, Any]): The serialized retriever.
+            query (str): The query.
+            run_id (UUID, optional): The ID of the run. Defaults to None.
+            parent_run_id (UUID, optional): The ID of the parent run. Defaults to None.
+            **kwargs (Any): Additional keyword arguments.
+
+        Returns:
+            AsyncCallbackManagerForRetrieverRun: The async callback manager
+                for the retriever run.
+        """
        if run_id is None:
            run_id = uuid.uuid4()

@@ -1828,6 +1936,17 @@ class AsyncCallbackManagerForChainGroup(AsyncCallbackManager):
        parent_run_manager: AsyncCallbackManagerForChainRun,
        **kwargs: Any,
    ) -> None:
+        """Initialize the async callback manager.
+
+        Args:
+            handlers (List[BaseCallbackHandler]): The list of handlers.
+            inheritable_handlers (Optional[List[BaseCallbackHandler]]): The list of
+                inheritable handlers. Defaults to None.
+            parent_run_id (Optional[UUID]): The ID of the parent run. Defaults to None.
+            parent_run_manager (AsyncCallbackManagerForChainRun):
+                The parent run manager.
+            **kwargs (Any): Additional keyword arguments.
+        """
        super().__init__(
            handlers,
            inheritable_handlers,
@@ -1838,6 +1957,7 @@ class AsyncCallbackManagerForChainGroup(AsyncCallbackManager):
        self.ended = False

    def copy(self) -> AsyncCallbackManagerForChainGroup:
+        """Copy the async callback manager."""
        return self.__class__(
            handlers=self.handlers,
            inheritable_handlers=self.inheritable_handlers,
@@ -1856,6 +1976,7 @@ class AsyncCallbackManagerForChainGroup(AsyncCallbackManager):

        Args:
            outputs (Union[Dict[str, Any], Any]): The outputs of the chain.
+            **kwargs (Any): Additional keyword arguments.
        """
        self.ended = True
        await self.parent_run_manager.on_chain_end(outputs, **kwargs)
@@ -1869,6 +1990,7 @@ class AsyncCallbackManagerForChainGroup(AsyncCallbackManager):

        Args:
            error (Exception or KeyboardInterrupt): The error.
+            **kwargs (Any): Additional keyword arguments.
        """
        self.ended = True
        await self.parent_run_manager.on_chain_error(error, **kwargs)
--- a/libs/core/langchain_core/callbacks/stdout.py
+++ b/libs/core/langchain_core/callbacks/stdout.py
@@ -15,24 +15,45 @@ class StdOutCallbackHandler(BaseCallbackHandler):
    """Callback Handler that prints to std out."""

    def __init__(self, color: Optional[str] = None) -> None:
-        """Initialize callback handler."""
+        """Initialize callback handler.
+
+        Args:
+            color: The color to use for the text. Defaults to None.
+        """
        self.color = color

    def on_chain_start(
        self, serialized: Dict[str, Any], inputs: Dict[str, Any], **kwargs: Any
    ) -> None:
-        """Print out that we are entering a chain."""
+        """Print out that we are entering a chain.
+
+        Args:
+            serialized (Dict[str, Any]): The serialized chain.
+            inputs (Dict[str, Any]): The inputs to the chain.
+            **kwargs (Any): Additional keyword arguments.
+        """
        class_name = serialized.get("name", serialized.get("id", ["<unknown>"])[-1])
        print(f"\n\n\033[1m> Entering new {class_name} chain...\033[0m")  # noqa: T201

    def on_chain_end(self, outputs: Dict[str, Any], **kwargs: Any) -> None:
-        """Print out that we finished a chain."""
+        """Print out that we finished a chain.
+
+        Args:
+            outputs (Dict[str, Any]): The outputs of the chain.
+            **kwargs (Any): Additional keyword arguments.
+        """
        print("\n\033[1m> Finished chain.\033[0m")  # noqa: T201

    def on_agent_action(
        self, action: AgentAction, color: Optional[str] = None, **kwargs: Any
    ) -> Any:
-        """Run on agent action."""
+        """Run on agent action.
+
+        Args:
+            action (AgentAction): The agent action.
+            color (Optional[str]): The color to use for the text. Defaults to None.
+            **kwargs (Any): Additional keyword arguments.
+        """
        print_text(action.log, color=color or self.color)

    def on_tool_end(
@@ -43,7 +64,16 @@ class StdOutCallbackHandler(BaseCallbackHandler):
        llm_prefix: Optional[str] = None,
        **kwargs: Any,
    ) -> None:
-        """If not the final action, print out observation."""
+        """If not the final action, print out observation.
+
+        Args:
+            output (Any): The output to print.
+            color (Optional[str]): The color to use for the text. Defaults to None.
+            observation_prefix (Optional[str]): The observation prefix.
+                Defaults to None.
+            llm_prefix (Optional[str]): The LLM prefix. Defaults to None.
+            **kwargs (Any): Additional keyword arguments.
+        """
        output = str(output)
        if observation_prefix is not None:
            print_text(f"\n{observation_prefix}")
@@ -58,11 +88,24 @@ class StdOutCallbackHandler(BaseCallbackHandler):
        end: str = "",
        **kwargs: Any,
    ) -> None:
-        """Run when agent ends."""
+        """Run when the agent ends.
+
+        Args:
+            text (str): The text to print.
+            color (Optional[str]): The color to use for the text. Defaults to None.
+            end (str): The end character to use. Defaults to "".
+            **kwargs (Any): Additional keyword arguments.
+        """
        print_text(text, color=color or self.color, end=end)

    def on_agent_finish(
        self, finish: AgentFinish, color: Optional[str] = None, **kwargs: Any
    ) -> None:
-        """Run on agent end."""
+        """Run on the agent end.
+
+        Args:
+            finish (AgentFinish): The agent finish.
+            color (Optional[str]): The color to use for the text. Defaults to None.
+            **kwargs (Any): Additional keyword arguments.
+        """
        print_text(finish.log, color=color or self.color, end="\n")
--- a/libs/core/langchain_core/callbacks/streaming_stdout.py
+++ b/libs/core/langchain_core/callbacks/streaming_stdout.py
@@ -1,4 +1,5 @@
 """Callback Handler streams to stdout on new llm token."""
+
 from __future__ import annotations

 import sys
@@ -18,7 +19,13 @@ class StreamingStdOutCallbackHandler(BaseCallbackHandler):
    def on_llm_start(
        self, serialized: Dict[str, Any], prompts: List[str], **kwargs: Any
    ) -> None:
-        """Run when LLM starts running."""
+        """Run when LLM starts running.
+
+        Args:
+            serialized (Dict[str, Any]): The serialized LLM.
+            prompts (List[str]): The prompts to run.
+            **kwargs (Any): Additional keyword arguments.
+        """

    def on_chat_model_start(
        self,
@@ -26,47 +33,115 @@ class StreamingStdOutCallbackHandler(BaseCallbackHandler):
        messages: List[List[BaseMessage]],
        **kwargs: Any,
    ) -> None:
-        """Run when LLM starts running."""
+        """Run when LLM starts running.
+
+        Args:
+            serialized (Dict[str, Any]): The serialized LLM.
+            messages (List[List[BaseMessage]]): The messages to run.
+            **kwargs (Any): Additional keyword arguments.
+        """

    def on_llm_new_token(self, token: str, **kwargs: Any) -> None:
-        """Run on new LLM token. Only available when streaming is enabled."""
+        """Run on new LLM token. Only available when streaming is enabled.
+
+        Args:
+            token (str): The new token.
+            **kwargs (Any): Additional keyword arguments.
+        """
        sys.stdout.write(token)
        sys.stdout.flush()

    def on_llm_end(self, response: LLMResult, **kwargs: Any) -> None:
-        """Run when LLM ends running."""
+        """Run when LLM ends running.
+
+        Args:
+            response (LLMResult): The response from the LLM.
+            **kwargs (Any): Additional keyword arguments.
+        """

    def on_llm_error(self, error: BaseException, **kwargs: Any) -> None:
-        """Run when LLM errors."""
+        """Run when LLM errors.
+
+        Args:
+            error (BaseException): The error that occurred.
+            **kwargs (Any): Additional keyword arguments.
+        """

    def on_chain_start(
        self, serialized: Dict[str, Any], inputs: Dict[str, Any], **kwargs: Any
    ) -> None:
-        """Run when chain starts running."""
+        """Run when a chain starts running.
+
+        Args:
+            serialized (Dict[str, Any]): The serialized chain.
+            inputs (Dict[str, Any]): The inputs to the chain.
+            **kwargs (Any): Additional keyword arguments.
+        """

    def on_chain_end(self, outputs: Dict[str, Any], **kwargs: Any) -> None:
-        """Run when chain ends running."""
+        """Run when a chain ends running.
+
+        Args:
+            outputs (Dict[str, Any]): The outputs of the chain.
+            **kwargs (Any): Additional keyword arguments.
+        """

    def on_chain_error(self, error: BaseException, **kwargs: Any) -> None:
-        """Run when chain errors."""
+        """Run when chain errors.
+
+        Args:
+            error (BaseException): The error that occurred.
+            **kwargs (Any): Additional keyword arguments.
+        """

    def on_tool_start(
        self, serialized: Dict[str, Any], input_str: str, **kwargs: Any
    ) -> None:
-        """Run when tool starts running."""
+        """Run when the tool starts running.
+
+        Args:
+            serialized (Dict[str, Any]): The serialized tool.
+            input_str (str): The input string.
+            **kwargs (Any): Additional keyword arguments.
+        """

    def on_agent_action(self, action: AgentAction, **kwargs: Any) -> Any:
-        """Run on agent action."""
+        """Run on agent action.
+
+        Args:
+            action (AgentAction): The agent action.
+            **kwargs (Any): Additional keyword arguments.
+        """
        pass

    def on_tool_end(self, output: Any, **kwargs: Any) -> None:
-        """Run when tool ends running."""
+        """Run when tool ends running.
+
+        Args:
+            output (Any): The output of the tool.
+            **kwargs (Any): Additional keyword arguments.
+        """

    def on_tool_error(self, error: BaseException, **kwargs: Any) -> None:
-        """Run when tool errors."""
+        """Run when tool errors.
+
+        Args:
+            error (BaseException): The error that occurred.
+            **kwargs (Any): Additional keyword arguments.
+        """

    def on_text(self, text: str, **kwargs: Any) -> None:
-        """Run on arbitrary text."""
+        """Run on an arbitrary text.
+
+        Args:
+            text (str): The text to print.
+            **kwargs (Any): Additional keyword arguments.
+        """

    def on_agent_finish(self, finish: AgentFinish, **kwargs: Any) -> None:
-        """Run on agent end."""
+        """Run on the agent end.
+
+        Args:
+            finish (AgentFinish): The agent finish.
+            **kwargs (Any): Additional keyword arguments.
+        """
--- a/libs/core/langchain_core/documents/base.py
+++ b/libs/core/langchain_core/documents/base.py
@@ -1,6 +1,6 @@
 from __future__ import annotations

-from typing import Any, List, Literal
+from typing import Any, List, Literal, Optional

 from langchain_core.load.serializable import Serializable
 from langchain_core.pydantic_v1 import Field
@@ -21,6 +21,16 @@ class Document(Serializable):
            )
    """

+    # The ID field is optional at the moment.
+    # It will likely become required in a future major release after
+    # it has been adopted by enough vectorstore implementations.
+    id: Optional[str] = None
+    """An optional identifier for the document.
+    
+    Ideally this should be unique across the document collection and formatted 
+    as a UUID, but this will not be enforced.
+    """
+
    page_content: str
    """String text."""
    metadata: dict = Field(default_factory=dict)
@@ -42,3 +52,18 @@ class Document(Serializable):
    def get_lc_namespace(cls) -> List[str]:
        """Get the namespace of the langchain object."""
        return ["langchain", "schema", "document"]
+
+    def __str__(self) -> str:
+        """Override __str__ to restrict it to page_content and metadata."""
+        # The format matches pydantic format for __str__.
+        #
+        # The purpose of this change is to make sure that user code that
+        # feeds Document objects directly into prompts remains unchanged
+        # due to the addition of the id field (or any other fields in the future).
+        #
+        # This override will likely be removed in the future in favor of
+        # a more general solution of formatting content directly inside the prompts.
+        if self.metadata:
+            return f"page_content='{self.page_content}' metadata={self.metadata}"
+        else:
+            return f"page_content='{self.page_content}'"
--- a/libs/core/langchain_core/example_selectors/init.py
+++ b/libs/core/langchain_core/example_selectors/init.py
@@ -2,6 +2,7 @@
 in prompts.
 This allows us to select examples that are most relevant to the input.
 """
+
 from langchain_core.example_selectors.base import BaseExampleSelector
 from langchain_core.example_selectors.length_based import (
    LengthBasedExampleSelector,
--- a/libs/core/langchain_core/example_selectors/base.py
+++ b/libs/core/langchain_core/example_selectors/base.py
@@ -1,4 +1,5 @@
 """Interface for selecting examples to include in prompts."""
+
 from abc import ABC, abstractmethod
 from typing import Any, Dict, List

@@ -10,16 +11,34 @@ class BaseExampleSelector(ABC):

    @abstractmethod
    def add_example(self, example: Dict[str, str]) -> Any:
-        """Add new example to store."""
+        """Add new example to store.
+
+        Args:
+            example: A dictionary with keys as input variables
+                and values as their values."""

    async def aadd_example(self, example: Dict[str, str]) -> Any:
-        """Add new example to store."""
+        """Async add new example to store.
+
+        Args:
+            example: A dictionary with keys as input variables
+                and values as their values."""
+
        return await run_in_executor(None, self.add_example, example)

    @abstractmethod
    def select_examples(self, input_variables: Dict[str, str]) -> List[dict]:
-        """Select which examples to use based on the inputs."""
+        """Select which examples to use based on the inputs.
+
+        Args:
+            input_variables: A dictionary with keys as input variables
+                and values as their values."""

    async def aselect_examples(self, input_variables: Dict[str, str]) -> List[dict]:
-        """Select which examples to use based on the inputs."""
+        """Async select which examples to use based on the inputs.
+
+        Args:
+            input_variables: A dictionary with keys as input variables
+                and values as their values."""
+
        return await run_in_executor(None, self.select_examples, input_variables)
--- a/libs/core/langchain_core/example_selectors/length_based.py
+++ b/libs/core/langchain_core/example_selectors/length_based.py
@@ -1,4 +1,5 @@
 """Select examples based on length."""
+
 import re
 from typing import Callable, Dict, List

@@ -27,15 +28,27 @@ class LengthBasedExampleSelector(BaseExampleSelector, BaseModel):
    """Max length for the prompt, beyond which examples are cut."""

    example_text_lengths: List[int] = []  #: :meta private:
+    """Length of each example."""

    def add_example(self, example: Dict[str, str]) -> None:
-        """Add new example to list."""
+        """Add new example to list.
+
+        Args:
+            example: A dictionary with keys as input variables
+                and values as their values.
+        """
        self.examples.append(example)
        string_example = self.example_prompt.format(**example)
        self.example_text_lengths.append(self.get_text_length(string_example))

    async def aadd_example(self, example: Dict[str, str]) -> None:
-        """Add new example to list."""
+        """Async add new example to list.
+
+        Args:
+            example: A dictionary with keys as input variables
+                and values as their values.
+        """
+
        self.add_example(example)

    @validator("example_text_lengths", always=True)
@@ -51,7 +64,15 @@ class LengthBasedExampleSelector(BaseExampleSelector, BaseModel):
        return [get_text_length(eg) for eg in string_examples]

    def select_examples(self, input_variables: Dict[str, str]) -> List[dict]:
-        """Select which examples to use based on the input lengths."""
+        """Select which examples to use based on the input lengths.
+
+        Args:
+            input_variables: A dictionary with keys as input variables
+               and values as their values.
+
+        Returns:
+            A list of examples to include in the prompt.
+        """
        inputs = " ".join(input_variables.values())
        remaining_length = self.max_length - self.get_text_length(inputs)
        i = 0
@@ -67,5 +88,13 @@ class LengthBasedExampleSelector(BaseExampleSelector, BaseModel):
        return examples

    async def aselect_examples(self, input_variables: Dict[str, str]) -> List[dict]:
-        """Select which examples to use based on the input lengths."""
+        """Async select which examples to use based on the input lengths.
+
+        Args:
+            input_variables: A dictionary with keys as input variables
+               and values as their values.
+
+        Returns:
+            A list of examples to include in the prompt.
+        """
        return self.select_examples(input_variables)
--- a/libs/core/langchain_core/example_selectors/semantic_similarity.py
+++ b/libs/core/langchain_core/example_selectors/semantic_similarity.py
@@ -1,4 +1,5 @@
 """Example selector that selects examples based on SemanticSimilarity."""
+
 from __future__ import annotations

 from abc import ABC
@@ -14,7 +15,15 @@ if TYPE_CHECKING:


 def sorted_values(values: Dict[str, str]) -> List[Any]:
-    """Return a list of values in dict sorted by key."""
+    """Return a list of values in dict sorted by key.
+
+    Args:
+        values: A dictionary with keys as input variables
+            and values as their values.
+
+    Returns:
+        A list of values in dict sorted by key.
+    """
    return [values[val] for val in sorted(values)]


@@ -58,14 +67,30 @@ class _VectorStoreExampleSelector(BaseExampleSelector, BaseModel, ABC):
        return examples

    def add_example(self, example: Dict[str, str]) -> str:
-        """Add new example to vectorstore."""
+        """Add a new example to vectorstore.
+
+        Args:
+            example: A dictionary with keys as input variables
+                and values as their values.
+
+        Returns:
+            The ID of the added example.
+        """
        ids = self.vectorstore.add_texts(
            [self._example_to_text(example, self.input_keys)], metadatas=[example]
        )
        return ids[0]

    async def aadd_example(self, example: Dict[str, str]) -> str:
-        """Add new example to vectorstore."""
+        """Async add new example to vectorstore.
+
+        Args:
+            example: A dictionary with keys as input variables
+                and values as their values.
+
+        Returns:
+            The ID of the added example.
+        """
        ids = await self.vectorstore.aadd_texts(
            [self._example_to_text(example, self.input_keys)], metadatas=[example]
        )
@@ -76,7 +101,14 @@ class SemanticSimilarityExampleSelector(_VectorStoreExampleSelector):
    """Select examples based on semantic similarity."""

    def select_examples(self, input_variables: Dict[str, str]) -> List[dict]:
-        """Select examples based on semantic similarity."""
+        """Select examples based on semantic similarity.
+
+        Args:
+            input_variables: The input variables to use for search.
+
+        Returns:
+            The selected examples.
+        """
        # Get the docs with the highest similarity.
        vectorstore_kwargs = self.vectorstore_kwargs or {}
        example_docs = self.vectorstore.similarity_search(
@@ -87,7 +119,14 @@ class SemanticSimilarityExampleSelector(_VectorStoreExampleSelector):
        return self._documents_to_examples(example_docs)

    async def aselect_examples(self, input_variables: Dict[str, str]) -> List[dict]:
-        """Asynchronously select examples based on semantic similarity."""
+        """Asynchronously select examples based on semantic similarity.
+
+        Args:
+            input_variables: The input variables to use for search.
+
+        Returns:
+            The selected examples.
+        """
        # Get the docs with the highest similarity.
        vectorstore_kwargs = self.vectorstore_kwargs or {}
        example_docs = await self.vectorstore.asimilarity_search(
@@ -118,7 +157,7 @@ class SemanticSimilarityExampleSelector(_VectorStoreExampleSelector):
            examples: List of examples to use in the prompt.
            embeddings: An initialized embedding API interface, e.g. OpenAIEmbeddings().
            vectorstore_cls: A vector store DB interface class, e.g. FAISS.
-            k: Number of examples to select
+            k: Number of examples to select. Default is 4.
            input_keys: If provided, the search is based on the input variables
                instead of all variables.
            example_keys: If provided, keys to filter examples to.
@@ -154,7 +193,7 @@ class SemanticSimilarityExampleSelector(_VectorStoreExampleSelector):
        vectorstore_kwargs: Optional[dict] = None,
        **vectorstore_cls_kwargs: Any,
    ) -> SemanticSimilarityExampleSelector:
-        """Create k-shot example selector using example list and embeddings.
+        """Async create k-shot example selector using example list and embeddings.

        Reshuffles examples dynamically based on query similarity.

@@ -162,7 +201,7 @@ class SemanticSimilarityExampleSelector(_VectorStoreExampleSelector):
            examples: List of examples to use in the prompt.
            embeddings: An initialized embedding API interface, e.g. OpenAIEmbeddings().
            vectorstore_cls: A vector store DB interface class, e.g. FAISS.
-            k: Number of examples to select
+            k: Number of examples to select. Default is 4.
            input_keys: If provided, the search is based on the input variables
                instead of all variables.
            example_keys: If provided, keys to filter examples to.
@@ -249,8 +288,9 @@ class MaxMarginalRelevanceExampleSelector(_VectorStoreExampleSelector):
            examples: List of examples to use in the prompt.
            embeddings: An initialized embedding API interface, e.g. OpenAIEmbeddings().
            vectorstore_cls: A vector store DB interface class, e.g. FAISS.
-            k: Number of examples to select
+            k: Number of examples to select. Default is 4.
            fetch_k: Number of Documents to fetch to pass to MMR algorithm.
+                Default is 20.
            input_keys: If provided, the search is based on the input variables
                instead of all variables.
            example_keys: If provided, keys to filter examples to.
@@ -297,8 +337,9 @@ class MaxMarginalRelevanceExampleSelector(_VectorStoreExampleSelector):
            examples: List of examples to use in the prompt.
            embeddings: An initialized embedding API interface, e.g. OpenAIEmbeddings().
            vectorstore_cls: A vector store DB interface class, e.g. FAISS.
-            k: Number of examples to select
+            k: Number of examples to select. Default is 4.
            fetch_k: Number of Documents to fetch to pass to MMR algorithm.
+                Default is 20.
            input_keys: If provided, the search is based on the input variables
                instead of all variables.
            example_keys: If provided, keys to filter examples to.
--- a/libs/core/langchain_core/exceptions.py
+++ b/libs/core/langchain_core/exceptions.py
@@ -1,4 +1,5 @@
-"""Custom **exceptions** for LangChain. """
+"""Custom **exceptions** for LangChain."""
+
 from typing import Any, Optional


@@ -18,7 +19,7 @@ class OutputParserException(ValueError, LangChainException):
    available to catch and handle in ways to fix the parsing error, while other
    errors will be raised.

-    Args:
+    Parameters:
        error: The error that's being re-raised or an error message.
        observation: String explanation of error which can be passed to a
            model to try and remediate the issue.
--- a/libs/core/langchain_core/globals.py
+++ b/libs/core/langchain_core/globals.py
@@ -1,5 +1,6 @@
 # flake8: noqa
 """Global values and configuration that apply to all of LangChain."""
+
 import warnings
 from typing import TYPE_CHECKING, Optional

@@ -135,7 +136,11 @@ def get_debug() -> bool:


 def set_llm_cache(value: Optional["BaseCache"]) -> None:
-    """Set a new LLM cache, overwriting the previous value, if any."""
+    """Set a new LLM cache, overwriting the previous value, if any.
+
+    Args:
+        value: The new LLM cache to use. If `None`, the LLM cache is disabled.
+    """
    try:
        import langchain  # type: ignore[import]

--- a/libs/core/langchain_core/memory.py
+++ b/libs/core/langchain_core/memory.py
@@ -7,6 +7,7 @@
    BaseMemory --> <name>Memory --> <name>Memory  # Examples: BaseChatMemory -> MotorheadMemory

 """  # noqa: E501
+
 from __future__ import annotations

 from abc import ABC, abstractmethod
@@ -58,20 +59,37 @@ class BaseMemory(Serializable, ABC):

    @abstractmethod
    def load_memory_variables(self, inputs: Dict[str, Any]) -> Dict[str, Any]:
-        """Return key-value pairs given the text input to the chain."""
+        """Return key-value pairs given the text input to the chain.
+
+        Args:
+            inputs: The inputs to the chain."""

    async def aload_memory_variables(self, inputs: Dict[str, Any]) -> Dict[str, Any]:
-        """Return key-value pairs given the text input to the chain."""
+        """Async return key-value pairs given the text input to the chain.
+
+        Args:
+            inputs: The inputs to the chain.
+        """
        return await run_in_executor(None, self.load_memory_variables, inputs)

    @abstractmethod
    def save_context(self, inputs: Dict[str, Any], outputs: Dict[str, str]) -> None:
-        """Save the context of this chain run to memory."""
+        """Save the context of this chain run to memory.
+
+        Args:
+            inputs: The inputs to the chain.
+            outputs: The outputs of the chain.
+        """

    async def asave_context(
        self, inputs: Dict[str, Any], outputs: Dict[str, str]
    ) -> None:
-        """Save the context of this chain run to memory."""
+        """Async save the context of this chain run to memory.
+
+        Args:
+            inputs: The inputs to the chain.
+            outputs: The outputs of the chain.
+        """
        await run_in_executor(None, self.save_context, inputs, outputs)

    @abstractmethod
@@ -79,5 +97,5 @@ class BaseMemory(Serializable, ABC):
        """Clear memory contents."""

    async def aclear(self) -> None:
-        """Clear memory contents."""
+        """Async clear memory contents."""
        await run_in_executor(None, self.clear)
--- a/libs/core/langchain_core/prompt_values.py
+++ b/libs/core/langchain_core/prompt_values.py
@@ -3,6 +3,7 @@
 Prompt values are used to represent different pieces of prompts.
 They can be used to represent text, images, or chat message pieces.
 """
+
 from __future__ import annotations

 from abc import ABC, abstractmethod
@@ -103,15 +104,15 @@ class ImagePromptValue(PromptValue):
    """Image prompt value."""

    image_url: ImageURL
-    """Prompt image."""
+    """Image URL."""
    type: Literal["ImagePromptValue"] = "ImagePromptValue"

    def to_string(self) -> str:
-        """Return prompt as string."""
+        """Return prompt (image URL) as string."""
        return self.image_url["url"]

    def to_messages(self) -> List[BaseMessage]:
-        """Return prompt as messages."""
+        """Return prompt (image URL) as messages."""
        return [HumanMessage(content=[cast(dict, self.image_url)])]


@@ -120,6 +121,7 @@ class ChatPromptValueConcrete(ChatPromptValue):
    For use in external schemas."""

    messages: Sequence[AnyMessage]
+    """Sequence of messages."""

    type: Literal["ChatPromptValueConcrete"] = "ChatPromptValueConcrete"

--- a/libs/core/langchain_core/retrievers.py
+++ b/libs/core/langchain_core/retrievers.py
@@ -18,6 +18,7 @@ the backbone of a retriever, but there are other types of retrievers as well.
    Document, Serializable, Callbacks,
    CallbackManagerForRetrieverRun, AsyncCallbackManagerForRetrieverRun
 """
+
 from __future__ import annotations

 import warnings
@@ -119,14 +120,14 @@ class BaseRetriever(RunnableSerializable[RetrieverInput, RetrieverOutput], ABC):
    _new_arg_supported: bool = False
    _expects_other_args: bool = False
    tags: Optional[List[str]] = None
-    """Optional list of tags associated with the retriever. Defaults to None
+    """Optional list of tags associated with the retriever. Defaults to None.
    These tags will be associated with each call to this retriever,
    and passed as arguments to the handlers defined in `callbacks`.
    You can use these to eg identify a specific instance of a retriever with its 
    use case.
    """
    metadata: Optional[Dict[str, Any]] = None
-    """Optional metadata associated with the retriever. Defaults to None
+    """Optional metadata associated with the retriever. Defaults to None.
    This metadata will be associated with each call to this retriever,
    and passed as arguments to the handlers defined in `callbacks`.
    You can use these to eg identify a specific instance of a retriever with its 
@@ -289,9 +290,10 @@ class BaseRetriever(RunnableSerializable[RetrieverInput, RetrieverOutput], ABC):
        self, query: str, *, run_manager: CallbackManagerForRetrieverRun
    ) -> List[Document]:
        """Get documents relevant to a query.
+
        Args:
            query: String to find relevant documents for
-            run_manager: The callbacks handler to use
+            run_manager: The callback handler to use
        Returns:
            List of relevant documents
        """
@@ -300,9 +302,10 @@ class BaseRetriever(RunnableSerializable[RetrieverInput, RetrieverOutput], ABC):
        self, query: str, *, run_manager: AsyncCallbackManagerForRetrieverRun
    ) -> List[Document]:
        """Asynchronously get documents relevant to a query.
+
        Args:
            query: String to find relevant documents for
-            run_manager: The callbacks handler to use
+            run_manager: The callback handler to use
        Returns:
            List of relevant documents
        """
--- a/libs/core/langchain_core/stores.py
+++ b/libs/core/langchain_core/stores.py
@@ -5,6 +5,7 @@ to a simple key-value interface.

 The primary goal of these storages is to support implementation of caching.
 """
+
 from abc import ABC, abstractmethod
 from typing import (
    Any,
@@ -95,7 +96,7 @@ class BaseStore(Generic[K, V], ABC):
        """

    async def amget(self, keys: Sequence[K]) -> List[Optional[V]]:
-        """Get the values associated with the given keys.
+        """Async get the values associated with the given keys.

        Args:
            keys (Sequence[K]): A sequence of keys.
@@ -115,7 +116,7 @@ class BaseStore(Generic[K, V], ABC):
        """

    async def amset(self, key_value_pairs: Sequence[Tuple[K, V]]) -> None:
-        """Set the values for the given keys.
+        """Async set the values for the given keys.

        Args:
            key_value_pairs (Sequence[Tuple[K, V]]): A sequence of key-value pairs.
@@ -131,7 +132,7 @@ class BaseStore(Generic[K, V], ABC):
        """

    async def amdelete(self, keys: Sequence[K]) -> None:
-        """Delete the given keys and their associated values.
+        """Async delete the given keys and their associated values.

        Args:
            keys (Sequence[K]): A sequence of keys to delete.
@@ -147,7 +148,7 @@ class BaseStore(Generic[K, V], ABC):
        Args:
            prefix (str): The prefix to match.

-        Returns:
+        Yields:
            Iterator[K | str]: An iterator over keys that match the given prefix.

            This method is allowed to return an iterator over either K or str
@@ -157,12 +158,12 @@ class BaseStore(Generic[K, V], ABC):
    async def ayield_keys(
        self, *, prefix: Optional[str] = None
    ) -> Union[AsyncIterator[K], AsyncIterator[str]]:
-        """Get an iterator over keys that match the given prefix.
+        """Async get an iterator over keys that match the given prefix.

        Args:
            prefix (str): The prefix to match.

-        Returns:
+        Yields:
            Iterator[K | str]: An iterator over keys that match the given prefix.

            This method is allowed to return an iterator over either K or str
@@ -200,7 +201,7 @@ class InMemoryBaseStore(BaseStore[str, V], Generic[V]):
        return [self.store.get(key) for key in keys]

    async def amget(self, keys: Sequence[str]) -> List[Optional[V]]:
-        """Get the values associated with the given keys.
+        """Async get the values associated with the given keys.

        Args:
            keys (Sequence[str]): A sequence of keys.
@@ -224,7 +225,7 @@ class InMemoryBaseStore(BaseStore[str, V], Generic[V]):
            self.store[key] = value

    async def amset(self, key_value_pairs: Sequence[Tuple[str, V]]) -> None:
-        """Set the values for the given keys.
+        """Async set the values for the given keys.

        Args:
            key_value_pairs (Sequence[Tuple[str, V]]): A sequence of key-value pairs.
@@ -245,7 +246,7 @@ class InMemoryBaseStore(BaseStore[str, V], Generic[V]):
                del self.store[key]

    async def amdelete(self, keys: Sequence[str]) -> None:
-        """Delete the given keys and their associated values.
+        """Async delete the given keys and their associated values.

        Args:
            keys (Sequence[str]): A sequence of keys to delete.
@@ -258,7 +259,7 @@ class InMemoryBaseStore(BaseStore[str, V], Generic[V]):
        Args:
            prefix (str, optional): The prefix to match. Defaults to None.

-        Returns:
+        Yields:
            Iterator[str]: An iterator over keys that match the given prefix.
        """
        if prefix is None:
@@ -269,12 +270,12 @@ class InMemoryBaseStore(BaseStore[str, V], Generic[V]):
                    yield key

    async def ayield_keys(self, prefix: Optional[str] = None) -> AsyncIterator[str]:
-        """Get an async iterator over keys that match the given prefix.
+        """Async get an async iterator over keys that match the given prefix.

        Args:
            prefix (str, optional): The prefix to match. Defaults to None.

-        Returns:
+        Yields:
            AsyncIterator[str]: An async iterator over keys that match the given prefix.
        """
        if prefix is None:
--- a/libs/core/langchain_core/tools.py
+++ b/libs/core/langchain_core/tools.py
@@ -827,6 +827,8 @@ class StructuredTool(BaseTool):
            raise ValueError("Function and/or coroutine must be provided")
        name = name or source_function.__name__
        description_ = description or source_function.__doc__
+        if description_ is None and args_schema:
+            description_ = args_schema.__doc__
        if description_ is None:
            raise ValueError(
                "Function must have a docstring if description not provided."
--- a/libs/core/tests/unit_tests/runnables/test_runnable.py
+++ b/libs/core/tests/unit_tests/runnables/test_runnable.py
@@ -311,6 +311,10 @@ def test_schemas(snapshot: SnapshotAssertion) -> None:
                "properties": {
                    "page_content": {"title": "Page Content", "type": "string"},
                    "metadata": {"title": "Metadata", "type": "object"},
+                    "id": {
+                        "title": "Id",
+                        "type": "string",
+                    },
                    "type": {
                        "title": "Type",
                        "enum": ["Document"],
--- a/libs/core/tests/unit_tests/test_tools.py
+++ b/libs/core/tests/unit_tests/test_tools.py
@@ -44,6 +44,8 @@ def test_unnamed_decorator() -> None:


 class _MockSchema(BaseModel):
+    """Return the arguments directly."""
+
    arg1: int
    arg2: bool
    arg3: Optional[dict] = None
@@ -133,7 +135,6 @@ def test_decorator_with_specified_schema() -> None:

    @tool(args_schema=_MockSchema)
    def tool_func(arg1: int, arg2: bool, arg3: Optional[dict] = None) -> str:
-        """Return the arguments directly."""
        return f"{arg1} {arg2} {arg3}"

    assert isinstance(tool_func, BaseTool)
--- a/libs/langchain/langchain/agents/agent.py
+++ b/libs/langchain/langchain/agents/agent.py
@@ -770,7 +770,7 @@ class Agent(BaseSingleActionAgent):
        """
        return list(set(self.llm_chain.input_keys) - {"agent_scratchpad"})

-    @root_validator()
+    @root_validator(pre=False, skip_on_failure=True)
    def validate_prompt(cls, values: Dict) -> Dict:
        """Validate that prompt matches format."""
        prompt = values["llm_chain"].prompt
@@ -974,7 +974,7 @@ class AgentExecutor(Chain):
            **kwargs,
        )

-    @root_validator()
+    @root_validator(pre=False, skip_on_failure=True)
    def validate_tools(cls, values: Dict) -> Dict:
        """Validate that tools are compatible with agent."""
        agent = values["agent"]
@@ -988,7 +988,7 @@ class AgentExecutor(Chain):
                )
        return values

-    @root_validator()
+    @root_validator(pre=False, skip_on_failure=True)
    def validate_return_direct_tool(cls, values: Dict) -> Dict:
        """Validate that tools are compatible with agent."""
        agent = values["agent"]
@@ -1005,8 +1005,8 @@ class AgentExecutor(Chain):
    @root_validator(pre=True)
    def validate_runnable_agent(cls, values: Dict) -> Dict:
        """Convert runnable to agent if passed in."""
-        agent = values["agent"]
-        if isinstance(agent, Runnable):
+        agent = values.get("agent")
+        if agent and isinstance(agent, Runnable):
            try:
                output_type = agent.OutputType
            except Exception as _:
--- a/libs/langchain/langchain/agents/format_scratchpad/tools.py
+++ b/libs/langchain/langchain/agents/format_scratchpad/tools.py
@@ -14,12 +14,12 @@ from langchain.agents.output_parsers.tools import ToolAgentAction
 def _create_tool_message(
    agent_action: ToolAgentAction, observation: str
 ) -> ToolMessage:
-    """Convert agent action and observation into a function message.
+    """Convert agent action and observation into a tool message.
    Args:
        agent_action: the tool invocation request from the agent
        observation: the result of the tool invocation
    Returns:
-        FunctionMessage that corresponds to the original tool invocation
+        ToolMessage that corresponds to the original tool invocation
    """
    if not isinstance(observation, str):
        try:
@@ -38,7 +38,7 @@ def _create_tool_message(
 def format_to_tool_messages(
    intermediate_steps: Sequence[Tuple[AgentAction, str]],
 ) -> List[BaseMessage]:
-    """Convert (AgentAction, tool output) tuples into FunctionMessages.
+    """Convert (AgentAction, tool output) tuples into ToolMessages.

    Args:
        intermediate_steps: Steps the LLM has taken to date, along with observations
--- a/libs/langchain/langchain/agents/openai_assistant/base.py
+++ b/libs/langchain/langchain/agents/openai_assistant/base.py
@@ -210,7 +210,7 @@ class OpenAIAssistantRunnable(RunnableSerializable[Dict, OutputType]):
    as_agent: bool = False
    """Use as a LangChain agent, compatible with the AgentExecutor."""

-    @root_validator()
+    @root_validator(pre=False, skip_on_failure=True)
    def validate_async_client(cls, values: dict) -> dict:
        if values["async_client"] is None:
            import openai
--- a/libs/langchain/langchain/agents/openai_functions_agent/base.py
+++ b/libs/langchain/langchain/agents/openai_functions_agent/base.py
@@ -54,7 +54,7 @@ class OpenAIFunctionsAgent(BaseSingleActionAgent):
        """Get allowed tools."""
        return [t.name for t in self.tools]

-    @root_validator
+    @root_validator(pre=False, skip_on_failure=True)
    def validate_prompt(cls, values: dict) -> dict:
        prompt: BasePromptTemplate = values["prompt"]
        if "agent_scratchpad" not in prompt.input_variables:
--- a/libs/langchain/langchain/agents/openai_functions_multi_agent/base.py
+++ b/libs/langchain/langchain/agents/openai_functions_multi_agent/base.py
@@ -114,7 +114,7 @@ class OpenAIMultiFunctionsAgent(BaseMultiActionAgent):
        """Get allowed tools."""
        return [t.name for t in self.tools]

-    @root_validator
+    @root_validator(pre=False, skip_on_failure=True)
    def validate_prompt(cls, values: dict) -> dict:
        prompt: BasePromptTemplate = values["prompt"]
        if "agent_scratchpad" not in prompt.input_variables:
--- a/libs/langchain/langchain/chains/api/base.py
+++ b/libs/langchain/langchain/chains/api/base.py
@@ -106,7 +106,7 @@ try:
            """
            return [self.output_key]

-        @root_validator(pre=True)
+        @root_validator(pre=False, skip_on_failure=True)
        def validate_api_request_prompt(cls, values: Dict) -> Dict:
            """Check that api request prompt expects the right variables."""
            input_vars = values["api_request_chain"].prompt.input_variables
@@ -120,6 +120,8 @@ try:
        @root_validator(pre=True)
        def validate_limit_to_domains(cls, values: Dict) -> Dict:
            """Check that allowed domains are valid."""
+            # This check must be a pre=True check, so that a default of None
+            # won't be set to limit_to_domains if it's not provided.
            if "limit_to_domains" not in values:
                raise ValueError(
                    "You must specify a list of domains to limit access using "
@@ -135,7 +137,7 @@ try:
                )
            return values

-        @root_validator(pre=True)
+        @root_validator(pre=False, skip_on_failure=True)
        def validate_api_answer_prompt(cls, values: Dict) -> Dict:
            """Check that api answer prompt expects the right variables."""
            input_vars = values["api_answer_chain"].prompt.input_variables
--- a/libs/langchain/langchain/chains/base.py
+++ b/libs/langchain/langchain/chains/base.py
@@ -225,7 +225,7 @@ class Chain(RunnableSerializable[Dict[str, Any], Dict[str, Any]], ABC):
    def _chain_type(self) -> str:
        raise NotImplementedError("Saving not supported for this chain type.")

-    @root_validator()
+    @root_validator(pre=True)
    def raise_callback_manager_deprecation(cls, values: Dict) -> Dict:
        """Raise deprecation warning if callback_manager is used."""
        if values.get("callback_manager") is not None:
--- a/libs/langchain/langchain/chains/combine_documents/map_reduce.py
+++ b/libs/langchain/langchain/chains/combine_documents/map_reduce.py
@@ -166,8 +166,11 @@ class MapReduceDocumentsChain(BaseCombineDocumentsChain):
    @root_validator(pre=True)
    def get_default_document_variable_name(cls, values: Dict) -> Dict:
        """Get default document variable name, if not provided."""
+        if "llm_chain" not in values:
+            raise ValueError("llm_chain must be provided")
+
+        llm_chain_variables = values["llm_chain"].prompt.input_variables
        if "document_variable_name" not in values:
-            llm_chain_variables = values["llm_chain"].prompt.input_variables
            if len(llm_chain_variables) == 1:
                values["document_variable_name"] = llm_chain_variables[0]
            else:
@@ -176,7 +179,6 @@ class MapReduceDocumentsChain(BaseCombineDocumentsChain):
                    "multiple llm_chain input_variables"
                )
        else:
-            llm_chain_variables = values["llm_chain"].prompt.input_variables
            if values["document_variable_name"] not in llm_chain_variables:
                raise ValueError(
                    f"document_variable_name {values['document_variable_name']} was "
--- a/libs/langchain/langchain/chains/combine_documents/map_rerank.py
+++ b/libs/langchain/langchain/chains/combine_documents/map_rerank.py
@@ -106,7 +106,7 @@ class MapRerankDocumentsChain(BaseCombineDocumentsChain):
            _output_keys += self.metadata_keys
        return _output_keys

-    @root_validator()
+    @root_validator(pre=False, skip_on_failure=True)
    def validate_llm_output(cls, values: Dict) -> Dict:
        """Validate that the combine chain outputs a dictionary."""
        output_parser = values["llm_chain"].prompt.output_parser
@@ -131,8 +131,11 @@ class MapRerankDocumentsChain(BaseCombineDocumentsChain):
    @root_validator(pre=True)
    def get_default_document_variable_name(cls, values: Dict) -> Dict:
        """Get default document variable name, if not provided."""
+        if "llm_chain" not in values:
+            raise ValueError("llm_chain must be provided")
+
+        llm_chain_variables = values["llm_chain"].prompt.input_variables
        if "document_variable_name" not in values:
-            llm_chain_variables = values["llm_chain"].prompt.input_variables
            if len(llm_chain_variables) == 1:
                values["document_variable_name"] = llm_chain_variables[0]
            else:
@@ -141,7 +144,6 @@ class MapRerankDocumentsChain(BaseCombineDocumentsChain):
                    "multiple llm_chain input_variables"
                )
        else:
-            llm_chain_variables = values["llm_chain"].prompt.input_variables
            if values["document_variable_name"] not in llm_chain_variables:
                raise ValueError(
                    f"document_variable_name {values['document_variable_name']} was "
--- a/libs/langchain/langchain/chains/combine_documents/refine.py
+++ b/libs/langchain/langchain/chains/combine_documents/refine.py
@@ -115,8 +115,11 @@ class RefineDocumentsChain(BaseCombineDocumentsChain):
    @root_validator(pre=True)
    def get_default_document_variable_name(cls, values: Dict) -> Dict:
        """Get default document variable name, if not provided."""
+        if "initial_llm_chain" not in values:
+            raise ValueError("initial_llm_chain must be provided")
+
+        llm_chain_variables = values["initial_llm_chain"].prompt.input_variables
        if "document_variable_name" not in values:
-            llm_chain_variables = values["initial_llm_chain"].prompt.input_variables
            if len(llm_chain_variables) == 1:
                values["document_variable_name"] = llm_chain_variables[0]
            else:
@@ -125,7 +128,6 @@ class RefineDocumentsChain(BaseCombineDocumentsChain):
                    "multiple llm_chain input_variables"
                )
        else:
-            llm_chain_variables = values["initial_llm_chain"].prompt.input_variables
            if values["document_variable_name"] not in llm_chain_variables:
                raise ValueError(
                    f"document_variable_name {values['document_variable_name']} was "
--- a/libs/langchain/langchain/chains/conversation/base.py
+++ b/libs/langchain/langchain/chains/conversation/base.py
@@ -45,7 +45,7 @@ class ConversationChain(LLMChain):
        """Use this since so some prompt vars come from history."""
        return [self.input_key]

-    @root_validator()
+    @root_validator(pre=False, skip_on_failure=True)
    def validate_prompt_input_variables(cls, values: Dict) -> Dict:
        """Validate that prompt input variables are consistent."""
        memory_keys = values["memory"].memory_variables
--- a/libs/langchain/langchain/chains/conversational_retrieval/base.py
+++ b/libs/langchain/langchain/chains/conversational_retrieval/base.py
@@ -480,7 +480,7 @@ class ChatVectorDBChain(BaseConversationalRetrievalChain):
    def _chain_type(self) -> str:
        return "chat-vector-db"

-    @root_validator()
+    @root_validator(pre=True)
    def raise_deprecation(cls, values: Dict) -> Dict:
        warnings.warn(
            "`ChatVectorDBChain` is deprecated - "
--- a/libs/langchain/langchain/chains/elasticsearch_database/base.py
+++ b/libs/langchain/langchain/chains/elasticsearch_database/base.py
@@ -56,7 +56,7 @@ class ElasticsearchDatabaseChain(Chain):
        extra = Extra.forbid
        arbitrary_types_allowed = True

-    @root_validator()
+    @root_validator(pre=False, skip_on_failure=True)
    def validate_indices(cls, values: dict) -> dict:
        if values["include_indices"] and values["ignore_indices"]:
            raise ValueError(
--- a/libs/langchain/langchain/chains/moderation.py
+++ b/libs/langchain/langchain/chains/moderation.py
@@ -40,7 +40,7 @@ class OpenAIModerationChain(Chain):
    openai_organization: Optional[str] = None
    _openai_pre_1_0: bool = Field(default=None)

-    @root_validator()
+    @root_validator(pre=True)
    def validate_environment(cls, values: Dict) -> Dict:
        """Validate that api key and python package exists in environment."""
        openai_api_key = get_from_dict_or_env(
--- a/libs/langchain/langchain/chains/qa_with_sources/vector_db.py
+++ b/libs/langchain/langchain/chains/qa_with_sources/vector_db.py
@@ -61,7 +61,7 @@ class VectorDBQAWithSourcesChain(BaseQAWithSourcesChain):
    ) -> List[Document]:
        raise NotImplementedError("VectorDBQAWithSourcesChain does not support async")

-    @root_validator()
+    @root_validator(pre=True)
    def raise_deprecation(cls, values: Dict) -> Dict:
        warnings.warn(
            "`VectorDBQAWithSourcesChain` is deprecated - "
--- a/libs/langchain/langchain/chains/retrieval_qa/base.py
+++ b/libs/langchain/langchain/chains/retrieval_qa/base.py
@@ -284,7 +284,7 @@ class VectorDBQA(BaseRetrievalQA):
    search_kwargs: Dict[str, Any] = Field(default_factory=dict)
    """Extra search args."""

-    @root_validator()
+    @root_validator(pre=True)
    def raise_deprecation(cls, values: Dict) -> Dict:
        warnings.warn(
            "`VectorDBQA` is deprecated - "
@@ -292,7 +292,7 @@ class VectorDBQA(BaseRetrievalQA):
        )
        return values

-    @root_validator()
+    @root_validator(pre=True)
    def validate_search_type(cls, values: Dict) -> Dict:
        """Validate search type."""
        if "search_type" in values:
--- a/libs/langchain/langchain/chains/router/llm_router.py
+++ b/libs/langchain/langchain/chains/router/llm_router.py
@@ -24,7 +24,7 @@ class LLMRouterChain(RouterChain):
    llm_chain: LLMChain
    """LLM chain used to perform routing"""

-    @root_validator()
+    @root_validator(pre=False, skip_on_failure=True)
    def validate_prompt(cls, values: dict) -> dict:
        prompt = values["llm_chain"].prompt
        if prompt.output_parser is None:
--- a/libs/langchain/langchain/chains/sequential.py
+++ b/libs/langchain/langchain/chains/sequential.py
@@ -152,7 +152,7 @@ class SimpleSequentialChain(Chain):
        """
        return [self.output_key]

-    @root_validator()
+    @root_validator(pre=False, skip_on_failure=True)
    def validate_chains(cls, values: Dict) -> Dict:
        """Validate that chains are all single input/output."""
        for chain in values["chains"]:
--- a/libs/langchain/langchain/memory/init.py
+++ b/libs/langchain/langchain/memory/init.py
@@ -48,6 +48,9 @@ from langchain.memory.summary import ConversationSummaryMemory
 from langchain.memory.summary_buffer import ConversationSummaryBufferMemory
 from langchain.memory.token_buffer import ConversationTokenBufferMemory
 from langchain.memory.vectorstore import VectorStoreRetrieverMemory
+from langchain.memory.vectorstore_token_buffer_memory import (
+    ConversationVectorStoreTokenBufferMemory,  # avoid circular import
+)

 if TYPE_CHECKING:
    from langchain_community.chat_message_histories import (
@@ -122,6 +125,7 @@ __all__ = [
    "ConversationSummaryBufferMemory",
    "ConversationSummaryMemory",
    "ConversationTokenBufferMemory",
+    "ConversationVectorStoreTokenBufferMemory",
    "CosmosDBChatMessageHistory",
    "DynamoDBChatMessageHistory",
    "ElasticsearchChatMessageHistory",
--- a/libs/langchain/langchain/memory/vectorstore_token_buffer_memory.py
+++ b/libs/langchain/langchain/memory/vectorstore_token_buffer_memory.py
@@ -0,0 +1,184 @@
+"""
+Class for a conversation memory buffer with older messages stored in a vectorstore .
+
+This implementats a conversation memory in which the messages are stored in a memory
+buffer up to a specified token limit. When the limit is exceeded, older messages are
+saved to a vectorstore backing database. The vectorstore can be made persistent across
+sessions.
+"""
+
+import warnings
+from datetime import datetime
+from typing import Any, Dict, List
+
+from langchain_core.messages import BaseMessage
+from langchain_core.prompts.chat import SystemMessagePromptTemplate
+from langchain_core.pydantic_v1 import Field, PrivateAttr
+from langchain_core.vectorstores import VectorStoreRetriever
+
+from langchain.memory import ConversationTokenBufferMemory, VectorStoreRetrieverMemory
+from langchain.memory.chat_memory import BaseChatMemory
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+
+DEFAULT_HISTORY_TEMPLATE = """
+Current date and time: {current_time}.
+
+Potentially relevant timestamped excerpts of previous conversations (you 
+do not need to use these if irrelevant):
+{previous_history}
+
+"""
+
+TIMESTAMP_FORMAT = "%Y-%m-%d %H:%M:%S %Z"
+
+
+class ConversationVectorStoreTokenBufferMemory(ConversationTokenBufferMemory):
+    """Conversation chat memory with token limit and vectordb backing.
+
+    load_memory_variables() will return a dict with the key "history".
+    It contains background information retrieved from the vector store
+    plus recent lines of the current conversation.
+
+    To help the LLM understand the part of the conversation stored in the
+    vectorstore, each interaction is timestamped and the current date and
+    time is also provided in the history. A side effect of this is that the
+    LLM will have access to the current date and time.
+
+    Initialization arguments:
+
+    This class accepts all the initialization arguments of
+    ConversationTokenBufferMemory, such as `llm`. In addition, it
+    accepts the following additional arguments
+
+        retriever: (required) A VectorStoreRetriever object to use
+                   as the vector backing store
+
+        split_chunk_size: (optional, 1000) Token chunk split size
+                          for long messages generated by the AI
+
+        previous_history_template: (optional) Template used to format
+                                   the contents of the prompt history
+
+
+    Example using ChromaDB:
+
+    .. code-block:: python
+
+        from langchain.memory.token_buffer_vectorstore_memory import (
+                ConversationVectorStoreTokenBufferMemory
+        )
+        from langchain_community.vectorstores import Chroma
+        from langchain_community.embeddings import HuggingFaceInstructEmbeddings
+        from langchain_openai import OpenAI
+
+        embedder = HuggingFaceInstructEmbeddings(
+                        query_instruction="Represent the query for retrieval: "
+        )
+        chroma = Chroma(collection_name="demo",
+                        embedding_function=embedder,
+                        collection_metadata={"hnsw:space": "cosine"},
+                        )
+
+        retriever = chroma.as_retriever(
+                search_type="similarity_score_threshold",
+                search_kwargs={
+                    'k': 5,
+                    'score_threshold': 0.75,
+                },
+        )
+
+        conversation_memory = ConversationVectorStoreTokenBufferMemory(
+                return_messages=True,
+                llm=OpenAI(),
+                retriever=retriever,
+                max_token_limit = 1000,
+        )
+
+        conversation_memory.save_context({"Human": "Hi there"},
+                                          {"AI": "Nice to meet you!"}
+        )
+        conversation_memory.save_context({"Human": "Nice day isn't it?"},
+                                          {"AI": "I love Wednesdays."}
+        )
+        conversation_memory.load_memory_variables({"input": "What time is it?"})
+
+    """
+
+    retriever: VectorStoreRetriever = Field(exclude=True)
+    memory_key: str = "history"
+    previous_history_template: str = DEFAULT_HISTORY_TEMPLATE
+    split_chunk_size: int = 1000
+
+    _memory_retriever: VectorStoreRetrieverMemory = PrivateAttr(default=None)
+    _timestamps: List[datetime] = PrivateAttr(default_factory=list)
+
+    @property
+    def memory_retriever(self) -> VectorStoreRetrieverMemory:
+        """Return a memory retriever from the passed retriever object."""
+        if self._memory_retriever is not None:
+            return self._memory_retriever
+        self._memory_retriever = VectorStoreRetrieverMemory(retriever=self.retriever)
+        return self._memory_retriever
+
+    def load_memory_variables(self, inputs: Dict[str, Any]) -> Dict[str, Any]:
+        """Return history and memory buffer."""
+        try:
+            with warnings.catch_warnings():
+                warnings.simplefilter("ignore")
+                memory_variables = self.memory_retriever.load_memory_variables(inputs)
+            previous_history = memory_variables[self.memory_retriever.memory_key]
+        except AssertionError:  # happens when db is empty
+            previous_history = ""
+        current_history = super().load_memory_variables(inputs)
+        template = SystemMessagePromptTemplate.from_template(
+            self.previous_history_template
+        )
+        messages = [
+            template.format(
+                previous_history=previous_history,
+                current_time=datetime.now().astimezone().strftime(TIMESTAMP_FORMAT),
+            )
+        ]
+        messages.extend(current_history[self.memory_key])
+        return {self.memory_key: messages}
+
+    def save_context(self, inputs: Dict[str, Any], outputs: Dict[str, str]) -> None:
+        """Save context from this conversation to buffer. Pruned."""
+        BaseChatMemory.save_context(self, inputs, outputs)
+        self._timestamps.append(datetime.now().astimezone())
+        # Prune buffer if it exceeds max token limit
+        buffer = self.chat_memory.messages
+        curr_buffer_length = self.llm.get_num_tokens_from_messages(buffer)
+        if curr_buffer_length > self.max_token_limit:
+            while curr_buffer_length > self.max_token_limit:
+                self._pop_and_store_interaction(buffer)
+                curr_buffer_length = self.llm.get_num_tokens_from_messages(buffer)
+
+    def save_remainder(self) -> None:
+        """
+        Save the remainder of the conversation buffer to the vector store.
+
+        This is useful if you have made the vectorstore persistent, in which
+        case this can be called before the end of the session to store the
+        remainder of the conversation.
+        """
+        buffer = self.chat_memory.messages
+        while len(buffer) > 0:
+            self._pop_and_store_interaction(buffer)
+
+    def _pop_and_store_interaction(self, buffer: List[BaseMessage]) -> None:
+        input = buffer.pop(0)
+        output = buffer.pop(0)
+        timestamp = self._timestamps.pop(0).strftime(TIMESTAMP_FORMAT)
+        # Split AI output into smaller chunks to avoid creating documents
+        # that will overflow the context window
+        ai_chunks = self._split_long_ai_text(str(output.content))
+        for index, chunk in enumerate(ai_chunks):
+            self.memory_retriever.save_context(
+                {"Human": f"<{timestamp}/00> {str(input.content)}"},
+                {"AI": f"<{timestamp}/{index:02}> {chunk}"},
+            )
+
+    def _split_long_ai_text(self, text: str) -> List[str]:
+        splitter = RecursiveCharacterTextSplitter(chunk_size=self.split_chunk_size)
+        return [chunk.page_content for chunk in splitter.create_documents([text])]
--- a/libs/langchain/tests/unit_tests/memory/test_imports.py
+++ b/libs/langchain/tests/unit_tests/memory/test_imports.py
@@ -13,6 +13,7 @@ EXPECTED_ALL = [
    "ConversationSummaryBufferMemory",
    "ConversationSummaryMemory",
    "ConversationTokenBufferMemory",
+    "ConversationVectorStoreTokenBufferMemory",
    "CosmosDBChatMessageHistory",
    "DynamoDBChatMessageHistory",
    "ElasticsearchChatMessageHistory",
--- a/libs/partners/ai21/README.md
+++ b/libs/partners/ai21/README.md
@@ -1,6 +1,6 @@
 # langchain-ai21

-This package contains the LangChain integrations for [AI21](https://docs.ai21.com/) through their [AI21](https://pypi.org/project/ai21/) SDK.
+This package contains the LangChain integrations for [AI21](https://docs.ai21.com/) models and tools.

 ## Installation and Setup

@@ -13,9 +13,10 @@ pip install langchain-ai21

 ## Chat Models

-This package contains the `ChatAI21` class, which is the recommended way to interface with AI21 Chat models.
+This package contains the `ChatAI21` class, which is the recommended way to interface with AI21 chat models, including Jamba-Instruct
+and any Jurassic chat models.

-To use, install the requirements, and configure your environment.
+To use, install the requirements and configure your environment.

 ```bash
 export AI21_API_KEY=your-api-key
@@ -27,7 +28,7 @@ Then initialize
 from langchain_core.messages import HumanMessage
 from langchain_ai21.chat_models import ChatAI21

-chat = ChatAI21(model="jamab-instruct")
+chat = ChatAI21(model="jamba-instruct-preview")
 messages = [HumanMessage(content="Hello from AI21")]
 chat.invoke(messages)
 ```
@@ -35,10 +36,12 @@ chat.invoke(messages)
 For a list of the supported models, see [this page](https://docs.ai21.com/reference/python-sdk#chat)

 ## LLMs
-You can use AI21's generative AI models as Langchain LLMs:
+You can use AI21's Jurassic generative AI models as LangChain LLMs.
+To use the newer Jamba model, use the [ChatAI21 chat model](#chat-models), which
+supports single-turn instruction/question answering capabilities.

 ```python
-from langchain.prompts import PromptTemplate
+from langchain_core.prompts import PromptTemplate
 from langchain_ai21 import AI21LLM

 llm = AI21LLM(model="j2-ultra")
@@ -56,7 +59,7 @@ print(chain.invoke({"question": question}))

 ## Embeddings

-You can use AI21's embeddings models as:
+You can use AI21's [embeddings model](https://docs.ai21.com/reference/embeddings-ref) as shown here:

 ### Query

@@ -76,12 +79,12 @@ embeddings = AI21Embeddings()
 embeddings.embed_documents(["Hello! This is document 1", "And this is document 2!"])
 ```

-## Task Specific Models
+## Task-Specific Models

 ### Contextual Answers

-You can use AI21's contextual answers model to receives text or document, serving as a context,
-and a question and returns an answer based entirely on this context.
+You can use AI21's [contextual answers model](https://docs.ai21.com/reference/contextual-answers-ref) to parse
+given text and answer a question based entirely on the provided information.

 This means that if the answer to your question is not in the document,
 the model will indicate it (instead of providing a false answer)
@@ -91,7 +94,7 @@ from langchain_ai21 import AI21ContextualAnswers

 tsm = AI21ContextualAnswers()

-response = tsm.invoke(input={"context": "Your context", "question": "Your question"})
+response = tsm.invoke(input={"context": "Lots of information here", "question": "Your question about the context"})
 ```
 You can also use it with chains and output parsers and vector DBs:
 ```python
@@ -110,8 +113,8 @@ response = chain.invoke(

 ### Semantic Text Splitter

-You can use AI21's semantic text splitter to split a text into segments.
-Instead of merely using punctuation and newlines to divide the text, it identifies distinct topics that will work well together and will form a coherent piece of text.
+You can use AI21's semantic [text segmentation model](https://docs.ai21.com/reference/text-segmentation-ref) to split a text into segments by topic.
+Text is split at each point where the topic changes.

 For a list for examples, see [this page](https://github.com/langchain-ai/langchain/blob/master/docs/docs/modules/data_connection/document_transformers/semantic_text_splitter.ipynb).

--- a/libs/partners/ai21/langchain_ai21/chat_models.py
+++ b/libs/partners/ai21/langchain_ai21/chat_models.py
@@ -19,7 +19,10 @@ from langchain_ai21.chat.chat_factory import create_chat_adapter


 class ChatAI21(BaseChatModel, AI21Base):
-    """ChatAI21 chat model.
+    """ChatAI21 chat model. Different model types support different parameters and
+    different parameter values. Please read the [AI21 reference documentation]
+    (https://docs.ai21.com/reference) for your model to understand which parameters
+    are available.

    Example:
        .. code-block:: python
@@ -27,7 +30,10 @@ class ChatAI21(BaseChatModel, AI21Base):
            from langchain_ai21 import ChatAI21


-            model = ChatAI21()
+            model = ChatAI21(
+                # defaults to os.environ.get("AI21_API_KEY")
+                api_key="my_api_key"
+            )
    """

    model: str
@@ -42,7 +48,8 @@ class ChatAI21(BaseChatModel, AI21Base):
    """The maximum number of tokens to generate for each response."""

    min_tokens: int = 0
-    """The minimum number of tokens to generate for each response."""
+    """The minimum number of tokens to generate for each response.
+    _Not supported for all models._"""

    temperature: float = 0.7
    """A value controlling the "creativity" of the model's responses."""
@@ -51,17 +58,20 @@ class ChatAI21(BaseChatModel, AI21Base):
    """A value controlling the diversity of the model's responses."""

    top_k_return: int = 0
-    """The number of top-scoring tokens to consider for each generation step."""
+    """The number of top-scoring tokens to consider for each generation step.
+    _Not supported for all models._"""

    frequency_penalty: Optional[Any] = None
-    """A penalty applied to tokens that are frequently generated."""
+    """A penalty applied to tokens that are frequently generated.
+    _Not supported for all models._"""

    presence_penalty: Optional[Any] = None
-    """ A penalty applied to tokens that are already present in the prompt."""
+    """ A penalty applied to tokens that are already present in the prompt.
+    _Not supported for all models._"""

    count_penalty: Optional[Any] = None
    """A penalty applied to tokens based on their frequency 
-    in the generated responses."""
+    in the generated responses. _Not supported for all models._"""

    n: int = 1
    """Number of chat completions to generate for each prompt."""
--- a/libs/partners/ai21/langchain_ai21/llms.py
+++ b/libs/partners/ai21/langchain_ai21/llms.py
@@ -19,14 +19,24 @@ from langchain_ai21.ai21_base import AI21Base


 class AI21LLM(BaseLLM, AI21Base):
-    """AI21 large language models.
+    """AI21 large language models. Different model types support different parameters
+    and different parameter values. Please read the [AI21 reference documentation]
+    (https://docs.ai21.com/reference) for your model to understand which parameters
+    are available.
+
+    AI21LLM supports only the older Jurassic models.
+    We recommend using ChatAI21 with the newest models, for better results and more
+    features.

    Example:
        .. code-block:: python

            from langchain_ai21 import AI21LLM

-            model = AI21LLM()
+            model = AI21LLM(
+               # defaults to os.environ.get("AI21_API_KEY")
+                api_key="my_api_key"
+            )
    """

    model: str
@@ -40,7 +50,8 @@ class AI21LLM(BaseLLM, AI21Base):
    """The maximum number of tokens to generate for each response."""

    min_tokens: int = 0
-    """The minimum number of tokens to generate for each response."""
+    """The minimum number of tokens to generate for each response.
+    _Not supported for all models._"""

    temperature: float = 0.7
    """A value controlling the "creativity" of the model's responses."""
@@ -49,17 +60,20 @@ class AI21LLM(BaseLLM, AI21Base):
    """A value controlling the diversity of the model's responses."""

    top_k_return: int = 0
-    """The number of top-scoring tokens to consider for each generation step."""
+    """The number of top-scoring tokens to consider for each generation step.
+    _Not supported for all models._"""

    frequency_penalty: Optional[Any] = None
-    """A penalty applied to tokens that are frequently generated."""
+    """A penalty applied to tokens that are frequently generated.
+    _Not supported for all models._"""

    presence_penalty: Optional[Any] = None
-    """ A penalty applied to tokens that are already present in the prompt."""
+    """ A penalty applied to tokens that are already present in the prompt.
+    _Not supported for all models._"""

    count_penalty: Optional[Any] = None
    """A penalty applied to tokens based on their frequency 
-    in the generated responses."""
+    in the generated responses. _Not supported for all models._"""

    custom_model: Optional[str] = None
    epoch: Optional[int] = None
--- a/libs/partners/anthropic/poetry.lock
+++ b/libs/partners/anthropic/poetry.lock
@@ -511,7 +511,7 @@ files = [

 [[package]]
 name = "langchain-core"
-version = "0.2.9"
+version = "0.2.10"
 description = "Building applications with LLMs through composability"
 optional = false
 python-versions = ">=3.8.1,<4.0"
@@ -706,25 +706,6 @@ files = [
 dev = ["pre-commit", "tox"]
 testing = ["pytest", "pytest-benchmark"]

-[[package]]
-name = "pydantic"
-version = "2.7.1"
-description = "Data validation using Python type hints"
-optional = false
-python-versions = ">=3.8"
-files = [
-    {file = "pydantic-2.7.1-py3-none-any.whl", hash = "sha256:e029badca45266732a9a79898a15ae2e8b14840b1eabbb25844be28f0b33f3d5"},
-    {file = "pydantic-2.7.1.tar.gz", hash = "sha256:e9dbb5eada8abe4d9ae5f46b9939aead650cd2b68f249bb3a8139dbe125803cc"},
-]
-
-[package.dependencies]
-annotated-types = ">=0.4.0"
-pydantic-core = "2.18.2"
-typing-extensions = ">=4.6.1"
-
-[package.extras]
-email = ["email-validator (>=2.0.0)"]
-
 [[package]]
 name = "pydantic"
 version = "2.7.4"
@@ -744,97 +725,6 @@ typing-extensions = ">=4.6.1"
 [package.extras]
 email = ["email-validator (>=2.0.0)"]

-[[package]]
-name = "pydantic-core"
-version = "2.18.2"
-description = "Core functionality for Pydantic validation and serialization"
-optional = false
-python-versions = ">=3.8"
-files = [
-    {file = "pydantic_core-2.18.2-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:9e08e867b306f525802df7cd16c44ff5ebbe747ff0ca6cf3fde7f36c05a59a81"},
-    {file = "pydantic_core-2.18.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:f0a21cbaa69900cbe1a2e7cad2aa74ac3cf21b10c3efb0fa0b80305274c0e8a2"},
-    {file = "pydantic_core-2.18.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0680b1f1f11fda801397de52c36ce38ef1c1dc841a0927a94f226dea29c3ae3d"},
-    {file = "pydantic_core-2.18.2-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:95b9d5e72481d3780ba3442eac863eae92ae43a5f3adb5b4d0a1de89d42bb250"},
-    {file = "pydantic_core-2.18.2-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c4fcf5cd9c4b655ad666ca332b9a081112cd7a58a8b5a6ca7a3104bc950f2038"},
-    {file = "pydantic_core-2.18.2-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9b5155ff768083cb1d62f3e143b49a8a3432e6789a3abee8acd005c3c7af1c74"},
-    {file = "pydantic_core-2.18.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:553ef617b6836fc7e4df130bb851e32fe357ce36336d897fd6646d6058d980af"},
-    {file = "pydantic_core-2.18.2-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:b89ed9eb7d616ef5714e5590e6cf7f23b02d0d539767d33561e3675d6f9e3857"},
-    {file = "pydantic_core-2.18.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:75f7e9488238e920ab6204399ded280dc4c307d034f3924cd7f90a38b1829563"},
-    {file = "pydantic_core-2.18.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:ef26c9e94a8c04a1b2924149a9cb081836913818e55681722d7f29af88fe7b38"},
-    {file = "pydantic_core-2.18.2-cp310-none-win32.whl", hash = "sha256:182245ff6b0039e82b6bb585ed55a64d7c81c560715d1bad0cbad6dfa07b4027"},
-    {file = "pydantic_core-2.18.2-cp310-none-win_amd64.whl", hash = "sha256:e23ec367a948b6d812301afc1b13f8094ab7b2c280af66ef450efc357d2ae543"},
-    {file = "pydantic_core-2.18.2-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:219da3f096d50a157f33645a1cf31c0ad1fe829a92181dd1311022f986e5fbe3"},
-    {file = "pydantic_core-2.18.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:cc1cfd88a64e012b74e94cd00bbe0f9c6df57049c97f02bb07d39e9c852e19a4"},
-    {file = "pydantic_core-2.18.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:05b7133a6e6aeb8df37d6f413f7705a37ab4031597f64ab56384c94d98fa0e90"},
-    {file = "pydantic_core-2.18.2-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:224c421235f6102e8737032483f43c1a8cfb1d2f45740c44166219599358c2cd"},
-    {file = "pydantic_core-2.18.2-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b14d82cdb934e99dda6d9d60dc84a24379820176cc4a0d123f88df319ae9c150"},
-    {file = "pydantic_core-2.18.2-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2728b01246a3bba6de144f9e3115b532ee44bd6cf39795194fb75491824a1413"},
-    {file = "pydantic_core-2.18.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:470b94480bb5ee929f5acba6995251ada5e059a5ef3e0dfc63cca287283ebfa6"},
-    {file = "pydantic_core-2.18.2-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:997abc4df705d1295a42f95b4eec4950a37ad8ae46d913caeee117b6b198811c"},
-    {file = "pydantic_core-2.18.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:75250dbc5290e3f1a0f4618db35e51a165186f9034eff158f3d490b3fed9f8a0"},
-    {file = "pydantic_core-2.18.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:4456f2dca97c425231d7315737d45239b2b51a50dc2b6f0c2bb181fce6207664"},
-    {file = "pydantic_core-2.18.2-cp311-none-win32.whl", hash = "sha256:269322dcc3d8bdb69f054681edff86276b2ff972447863cf34c8b860f5188e2e"},
-    {file = "pydantic_core-2.18.2-cp311-none-win_amd64.whl", hash = "sha256:800d60565aec896f25bc3cfa56d2277d52d5182af08162f7954f938c06dc4ee3"},
-    {file = "pydantic_core-2.18.2-cp311-none-win_arm64.whl", hash = "sha256:1404c69d6a676245199767ba4f633cce5f4ad4181f9d0ccb0577e1f66cf4c46d"},
-    {file = "pydantic_core-2.18.2-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:fb2bd7be70c0fe4dfd32c951bc813d9fe6ebcbfdd15a07527796c8204bd36242"},
-    {file = "pydantic_core-2.18.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:6132dd3bd52838acddca05a72aafb6eab6536aa145e923bb50f45e78b7251043"},
-    {file = "pydantic_core-2.18.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d7d904828195733c183d20a54230c0df0eb46ec746ea1a666730787353e87182"},
-    {file = "pydantic_core-2.18.2-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:c9bd70772c720142be1020eac55f8143a34ec9f82d75a8e7a07852023e46617f"},
-    {file = "pydantic_core-2.18.2-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:2b8ed04b3582771764538f7ee7001b02e1170223cf9b75dff0bc698fadb00cf3"},
-    {file = "pydantic_core-2.18.2-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e6dac87ddb34aaec85f873d737e9d06a3555a1cc1a8e0c44b7f8d5daeb89d86f"},
-    {file = "pydantic_core-2.18.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7ca4ae5a27ad7a4ee5170aebce1574b375de390bc01284f87b18d43a3984df72"},
-    {file = "pydantic_core-2.18.2-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:886eec03591b7cf058467a70a87733b35f44707bd86cf64a615584fd72488b7c"},
-    {file = "pydantic_core-2.18.2-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:ca7b0c1f1c983e064caa85f3792dd2fe3526b3505378874afa84baf662e12241"},
-    {file = "pydantic_core-2.18.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:4b4356d3538c3649337df4074e81b85f0616b79731fe22dd11b99499b2ebbdf3"},
-    {file = "pydantic_core-2.18.2-cp312-none-win32.whl", hash = "sha256:8b172601454f2d7701121bbec3425dd71efcb787a027edf49724c9cefc14c038"},
-    {file = "pydantic_core-2.18.2-cp312-none-win_amd64.whl", hash = "sha256:b1bd7e47b1558ea872bd16c8502c414f9e90dcf12f1395129d7bb42a09a95438"},
-    {file = "pydantic_core-2.18.2-cp312-none-win_arm64.whl", hash = "sha256:98758d627ff397e752bc339272c14c98199c613f922d4a384ddc07526c86a2ec"},
-    {file = "pydantic_core-2.18.2-cp38-cp38-macosx_10_12_x86_64.whl", hash = "sha256:9fdad8e35f278b2c3eb77cbdc5c0a49dada440657bf738d6905ce106dc1de439"},
-    {file = "pydantic_core-2.18.2-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:1d90c3265ae107f91a4f279f4d6f6f1d4907ac76c6868b27dc7fb33688cfb347"},
-    {file = "pydantic_core-2.18.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:390193c770399861d8df9670fb0d1874f330c79caaca4642332df7c682bf6b91"},
-    {file = "pydantic_core-2.18.2-cp38-cp38-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:82d5d4d78e4448683cb467897fe24e2b74bb7b973a541ea1dcfec1d3cbce39fb"},
-    {file = "pydantic_core-2.18.2-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4774f3184d2ef3e14e8693194f661dea5a4d6ca4e3dc8e39786d33a94865cefd"},
-    {file = "pydantic_core-2.18.2-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d4d938ec0adf5167cb335acb25a4ee69a8107e4984f8fbd2e897021d9e4ca21b"},
-    {file = "pydantic_core-2.18.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e0e8b1be28239fc64a88a8189d1df7fad8be8c1ae47fcc33e43d4be15f99cc70"},
-    {file = "pydantic_core-2.18.2-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:868649da93e5a3d5eacc2b5b3b9235c98ccdbfd443832f31e075f54419e1b96b"},
-    {file = "pydantic_core-2.18.2-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:78363590ef93d5d226ba21a90a03ea89a20738ee5b7da83d771d283fd8a56761"},
-    {file = "pydantic_core-2.18.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:852e966fbd035a6468fc0a3496589b45e2208ec7ca95c26470a54daed82a0788"},
-    {file = "pydantic_core-2.18.2-cp38-none-win32.whl", hash = "sha256:6a46e22a707e7ad4484ac9ee9f290f9d501df45954184e23fc29408dfad61350"},
-    {file = "pydantic_core-2.18.2-cp38-none-win_amd64.whl", hash = "sha256:d91cb5ea8b11607cc757675051f61b3d93f15eca3cefb3e6c704a5d6e8440f4e"},
-    {file = "pydantic_core-2.18.2-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:ae0a8a797a5e56c053610fa7be147993fe50960fa43609ff2a9552b0e07013e8"},
-    {file = "pydantic_core-2.18.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:042473b6280246b1dbf530559246f6842b56119c2926d1e52b631bdc46075f2a"},
-    {file = "pydantic_core-2.18.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1a388a77e629b9ec814c1b1e6b3b595fe521d2cdc625fcca26fbc2d44c816804"},
-    {file = "pydantic_core-2.18.2-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:e25add29b8f3b233ae90ccef2d902d0ae0432eb0d45370fe315d1a5cf231004b"},
-    {file = "pydantic_core-2.18.2-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f459a5ce8434614dfd39bbebf1041952ae01da6bed9855008cb33b875cb024c0"},
-    {file = "pydantic_core-2.18.2-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:eff2de745698eb46eeb51193a9f41d67d834d50e424aef27df2fcdee1b153845"},
-    {file = "pydantic_core-2.18.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a8309f67285bdfe65c372ea3722b7a5642680f3dba538566340a9d36e920b5f0"},
-    {file = "pydantic_core-2.18.2-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:f93a8a2e3938ff656a7c1bc57193b1319960ac015b6e87d76c76bf14fe0244b4"},
-    {file = "pydantic_core-2.18.2-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:22057013c8c1e272eb8d0eebc796701167d8377441ec894a8fed1af64a0bf399"},
-    {file = "pydantic_core-2.18.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:cfeecd1ac6cc1fb2692c3d5110781c965aabd4ec5d32799773ca7b1456ac636b"},
-    {file = "pydantic_core-2.18.2-cp39-none-win32.whl", hash = "sha256:0d69b4c2f6bb3e130dba60d34c0845ba31b69babdd3f78f7c0c8fae5021a253e"},
-    {file = "pydantic_core-2.18.2-cp39-none-win_amd64.whl", hash = "sha256:d9319e499827271b09b4e411905b24a426b8fb69464dfa1696258f53a3334641"},
-    {file = "pydantic_core-2.18.2-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:a1874c6dd4113308bd0eb568418e6114b252afe44319ead2b4081e9b9521fe75"},
-    {file = "pydantic_core-2.18.2-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:ccdd111c03bfd3666bd2472b674c6899550e09e9f298954cfc896ab92b5b0e6d"},
-    {file = "pydantic_core-2.18.2-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e18609ceaa6eed63753037fc06ebb16041d17d28199ae5aba0052c51449650a9"},
-    {file = "pydantic_core-2.18.2-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6e5c584d357c4e2baf0ff7baf44f4994be121e16a2c88918a5817331fc7599d7"},
-    {file = "pydantic_core-2.18.2-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:43f0f463cf89ace478de71a318b1b4f05ebc456a9b9300d027b4b57c1a2064fb"},
-    {file = "pydantic_core-2.18.2-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:e1b395e58b10b73b07b7cf740d728dd4ff9365ac46c18751bf8b3d8cca8f625a"},
-    {file = "pydantic_core-2.18.2-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:0098300eebb1c837271d3d1a2cd2911e7c11b396eac9661655ee524a7f10587b"},
-    {file = "pydantic_core-2.18.2-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:36789b70d613fbac0a25bb07ab3d9dba4d2e38af609c020cf4d888d165ee0bf3"},
-    {file = "pydantic_core-2.18.2-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:3f9a801e7c8f1ef8718da265bba008fa121243dfe37c1cea17840b0944dfd72c"},
-    {file = "pydantic_core-2.18.2-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:3a6515ebc6e69d85502b4951d89131ca4e036078ea35533bb76327f8424531ce"},
-    {file = "pydantic_core-2.18.2-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:20aca1e2298c56ececfd8ed159ae4dde2df0781988c97ef77d5c16ff4bd5b400"},
-    {file = "pydantic_core-2.18.2-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:223ee893d77a310a0391dca6df00f70bbc2f36a71a895cecd9a0e762dc37b349"},
-    {file = "pydantic_core-2.18.2-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:2334ce8c673ee93a1d6a65bd90327588387ba073c17e61bf19b4fd97d688d63c"},
-    {file = "pydantic_core-2.18.2-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:cbca948f2d14b09d20268cda7b0367723d79063f26c4ffc523af9042cad95592"},
-    {file = "pydantic_core-2.18.2-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:b3ef08e20ec49e02d5c6717a91bb5af9b20f1805583cb0adfe9ba2c6b505b5ae"},
-    {file = "pydantic_core-2.18.2-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:c6fdc8627910eed0c01aed6a390a252fe3ea6d472ee70fdde56273f198938374"},
-    {file = "pydantic_core-2.18.2.tar.gz", hash = "sha256:2e29d20810dfc3043ee13ac7d9e25105799817683348823f305ab3f349b9386e"},
-]
-
-[package.dependencies]
-typing-extensions = ">=4.6.0,<4.7.0 || >4.7.0"
-
 [[package]]
 name = "pydantic-core"
 version = "2.18.4"
@@ -1393,4 +1283,4 @@ watchmedo = ["PyYAML (>=3.10)"]
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.8.1,<4.0"
-content-hash = "e1cff75b89d41dd6b5bf1fc13f2a8c777f3820936773ed5ebaecae185db28249"
+content-hash = "d034081373197472c8639f389b9d0303e071b9b7b4734fa111cfba71a950ef19"
--- a/libs/partners/anthropic/pyproject.toml
+++ b/libs/partners/anthropic/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langchain-anthropic"
-version = "0.1.15"
+version = "0.1.16"
 description = "An integration package connecting AnthropicMessages and LangChain"
 authors = []
 readme = "README.md"
@@ -12,7 +12,7 @@ license = "MIT"

 [tool.poetry.dependencies]
 python = ">=3.8.1,<4.0"
-langchain-core = { version = ">=0.2.2rc1,<0.3", allow-prereleases = true }
+langchain-core = { version = ">=0.2.10,<0.3" }
 anthropic = ">=0.28.0,<1"
 defusedxml = { version = "^0.7.1", optional = true }

--- a/libs/partners/mongodb/README.md
+++ b/libs/partners/mongodb/README.md
@@ -6,7 +6,7 @@ pip install -U langchain-mongodb
 ```

 # Usage
- See [integrations doc](../../../docs/docs/integrations/vectorstores/mongodb.ipynb) for more in-depth usage instructions.
+- See [integrations doc](../../../docs/docs/integrations/providers/mongodb_atlas.ipynb) for more in-depth usage instructions.
 - See [Getting Started with the LangChain Integration](https://www.mongodb.com/docs/atlas/atlas-vector-search/ai-integrations/langchain/#get-started-with-the-langchain-integration) for a walkthrough on using your first LangChain implementation with MongoDB Atlas.

 ## Using MongoDBAtlasVectorSearch
--- a/libs/partners/mongodb/langchain_mongodb/index.py
+++ b/libs/partners/mongodb/langchain_mongodb/index.py
@@ -0,0 +1,105 @@
+import logging
+from typing import Any, Dict, List, Optional
+
+from pymongo.collection import Collection
+from pymongo.operations import SearchIndexModel
+
+logger = logging.getLogger(__file__)
+
+
+def _vector_search_index_definition(
+    dimensions: int,
+    path: str,
+    similarity: str,
+    filters: Optional[List[Dict[str, str]]],
+) -> Dict[str, Any]:
+    return {
+        "fields": [
+            {
+                "numDimensions": dimensions,
+                "path": path,
+                "similarity": similarity,
+                "type": "vector",
+            },
+            *(filters or []),
+        ]
+    }
+
+
+def create_vector_search_index(
+    collection: Collection,
+    index_name: str,
+    dimensions: int,
+    path: str,
+    similarity: str,
+    filters: List[Dict[str, str]],
+) -> None:
+    """Experimental Utility function to create a vector search index
+
+    Args:
+        collection (Collection): MongoDB Collection
+        index_name (str): Name of Index
+        dimensions (int): Number of dimensions in embedding
+        path (str): field with vector embedding
+        similarity (str): The similarity score used for the index
+        filters (List[Dict[str, str]]): additional filters for index definition.
+    """
+    logger.info("Creating Search Index %s on %s", index_name, collection.name)
+    result = collection.create_search_index(
+        SearchIndexModel(
+            definition=_vector_search_index_definition(
+                dimensions=dimensions, path=path, similarity=similarity, filters=filters
+            ),
+            name=index_name,
+            type="vectorSearch",
+        )
+    )
+    logger.info(result)
+
+
+def drop_vector_search_index(collection: Collection, index_name: str) -> None:
+    """Drop a created vector search index
+
+    Args:
+        collection (Collection): MongoDB Collection with index to be dropped
+        index_name (str): Name of the MongoDB index
+    """
+    logger.info(
+        "Dropping Search Index %s from Collection: %s", index_name, collection.name
+    )
+    collection.drop_search_index(index_name)
+    logger.info("Vector Search index %s.%s dropped", collection.name, index_name)
+
+
+def update_vector_search_index(
+    collection: Collection,
+    index_name: str,
+    dimensions: int,
+    path: str,
+    similarity: str,
+    filters: List[Dict[str, str]],
+) -> None:
+    """Leverages the updateSearchIndex call
+
+    Args:
+        collection (Collection): MongoDB Collection
+        index_name (str): Name of Index
+        dimensions (int): Number of dimensions in embedding.
+        path (str): field with vector embedding.
+        similarity (str): The similarity score used for the index.
+        filters (List[Dict[str, str]]): additional filters for index definition.
+    """
+
+    logger.info(
+        "Updating Search Index %s from Collection: %s", index_name, collection.name
+    )
+    collection.update_search_index(
+        name=index_name,
+        definition=_vector_search_index_definition(
+            dimensions=dimensions,
+            path=path,
+            similarity=similarity,
+            filters=filters,
+        ),
+    )
+    logger.info("Update succeeded")
--- a/libs/partners/mongodb/langchain_mongodb/utils.py
+++ b/libs/partners/mongodb/langchain_mongodb/utils.py
@@ -18,6 +18,11 @@ logger = logging.getLogger(__name__)
 Matrix = Union[List[List[float]], List[np.ndarray], np.ndarray]


+class FailCode:
+    INDEX_NOT_FOUND = 27
+    INDEX_ALREADY_EXISTS = 68
+
+
 def cosine_similarity(X: Matrix, Y: Matrix) -> np.ndarray:
    """Row-wise cosine similarity between two equal-width matrices."""
    if len(X) == 0 or len(Y) == 0:
--- a/libs/partners/mongodb/langchain_mongodb/vectorstores.py
+++ b/libs/partners/mongodb/langchain_mongodb/vectorstores.py
@@ -24,7 +24,12 @@ from langchain_core.vectorstores import VectorStore
 from pymongo import MongoClient
 from pymongo.collection import Collection
 from pymongo.driver_info import DriverInfo
+from pymongo.errors import CollectionInvalid

+from langchain_mongodb.index import (
+    create_vector_search_index,
+    update_vector_search_index,
+)
 from langchain_mongodb.utils import maximal_marginal_relevance

 MongoDBDocumentType = TypeVar("MongoDBDocumentType", bound=Dict[str, Any])
@@ -489,3 +494,42 @@ class MongoDBAtlasVectorSearch(VectorStore):
            lambda_mult=lambda_mult,
            **kwargs,
        )
+
+    def create_vector_search_index(
+        self,
+        dimensions: int,
+        filters: Optional[List[Dict[str, str]]] = None,
+        update: bool = False,
+    ) -> None:
+        """Creates a MongoDB Atlas vectorSearch index for the VectorStore
+
+        Note**: This method may fail as it requires a MongoDB Atlas with
+        these pre-requisites:
+            - M10 cluster or higher
+            - https://www.mongodb.com/docs/atlas/atlas-vector-search/create-index/#prerequisites
+
+        Args:
+            dimensions (int): Number of dimensions in embedding
+            filters (Optional[List[Dict[str, str]]], optional): additional filters
+            for index definition.
+                Defaults to None.
+            update (bool, optional): Updates existing vectorSearch index.
+                Defaults to False.
+        """
+        try:
+            self._collection.database.create_collection(self._collection.name)
+        except CollectionInvalid:
+            pass
+
+        index_operation = (
+            update_vector_search_index if update else create_vector_search_index
+        )
+
+        index_operation(
+            collection=self._collection,
+            index_name=self._index_name,
+            dimensions=dimensions,
+            path=self._embedding_key,
+            similarity=self._relevance_score_fn,
+            filters=filters or [],
+        )
--- a/libs/partners/mongodb/tests/integration_tests/test_vectorstores.py
+++ b/libs/partners/mongodb/tests/integration_tests/test_vectorstores.py
@@ -3,22 +3,27 @@
 from __future__ import annotations

 import os
-from time import sleep
-from typing import Any, Dict, List
+from time import monotonic, sleep
+from typing import Any, Dict, List, Optional

 import pytest
 from langchain_core.documents import Document
 from langchain_core.embeddings import Embeddings
 from pymongo import MongoClient
 from pymongo.collection import Collection
+from pymongo.errors import OperationFailure

 from langchain_mongodb import MongoDBAtlasVectorSearch
+from langchain_mongodb.index import drop_vector_search_index
 from tests.utils import ConsistentFakeEmbeddings

 INDEX_NAME = "langchain-test-index-vectorstores"
+INDEX_CREATION_NAME = "langchain-test-index-vectorstores-create-test"
 NAMESPACE = "langchain_test_db.langchain_test_vectorstores"
 CONNECTION_STRING = os.environ.get("MONGODB_ATLAS_URI")
 DB_NAME, COLLECTION_NAME = NAMESPACE.split(".")
+INDEX_COLLECTION_NAME = "langchain_test_vectorstores_index"
+INDEX_DB_NAME = "langchain_test_index_db"
 DIMENSIONS = 1536
 TIMEOUT = 10.0
 INTERVAL = 0.5
@@ -28,16 +33,53 @@ class PatchedMongoDBAtlasVectorSearch(MongoDBAtlasVectorSearch):
    def _insert_texts(self, texts: List[str], metadatas: List[Dict[str, Any]]) -> List:
        """Patched insert_texts that waits for data to be indexed before returning"""
        ids = super()._insert_texts(texts, metadatas)
-        timeout = TIMEOUT
-        while len(ids) != self.similarity_search("sandwich") and timeout >= 0:
+        start = monotonic()
+        while len(ids) != self.similarity_search("sandwich") and (
+            monotonic() - start <= TIMEOUT
+        ):
            sleep(INTERVAL)
-            timeout -= INTERVAL
        return ids

+    def create_vector_search_index(
+        self,
+        dimensions: int,
+        filters: Optional[List[Dict[str, str]]] = None,
+        update: bool = False,
+    ) -> None:
+        result = super().create_vector_search_index(
+            dimensions=dimensions, filters=filters, update=update
+        )
+        start = monotonic()
+        while monotonic() - start <= TIMEOUT:
+            if indexes := list(
+                self._collection.list_search_indexes(name=self._index_name)
+            ):
+                if indexes[0].get("status") == "READY":
+                    return result
+            sleep(INTERVAL)

-def get_collection() -> Collection:
+        raise TimeoutError(f"{self._index_name} never reached 'status: READY'")
+
+
+def _await_index_deletion(coll: Collection, index_name: str) -> None:
+    start = monotonic()
+    try:
+        drop_vector_search_index(coll, index_name)
+    except OperationFailure:
+        # This most likely means an ongoing drop request was made so skip
+        pass
+
+    while list(coll.list_search_indexes(name=index_name)):
+        if monotonic() - start > TIMEOUT:
+            raise TimeoutError(f"Index Name: {index_name} never dropped")
+        sleep(INTERVAL)
+
+
+def get_collection(
+    database_name: str = DB_NAME, collection_name: str = COLLECTION_NAME
+) -> Collection:
    test_client: MongoClient = MongoClient(CONNECTION_STRING)
-    return test_client[DB_NAME][COLLECTION_NAME]
+    return test_client[database_name][collection_name]


@pytest.fixture()
@@ -45,6 +87,11 @@ def collection() -> Collection:
    return get_collection()


+@pytest.fixture()
+def index_collection() -> Collection:
+    return get_collection(INDEX_DB_NAME, INDEX_COLLECTION_NAME)
+
+
 class TestMongoDBAtlasVectorSearch:
    @classmethod
    def setup_class(cls) -> None:
@@ -65,6 +112,11 @@ class TestMongoDBAtlasVectorSearch:
        # delete all the documents in the collection
        collection.delete_many({})  # type: ignore[index]

+        # delete all indexes on index collection name
+        _await_index_deletion(
+            get_collection(INDEX_DB_NAME, INDEX_COLLECTION_NAME), INDEX_CREATION_NAME
+        )
+
    @pytest.fixture
    def embedding_openai(self) -> Embeddings:
        return ConsistentFakeEmbeddings(DIMENSIONS)
@@ -85,7 +137,6 @@ class TestMongoDBAtlasVectorSearch:
            collection=collection,
            index_name=INDEX_NAME,
        )
-        # sleep(5)  # waits for mongot to update Lucene's index
        output = vectorstore.similarity_search("Sandwich", k=1)
        assert len(output) == 1
        # Check for the presence of the metadata key
@@ -150,7 +201,6 @@ class TestMongoDBAtlasVectorSearch:
            collection=collection,
            index_name=INDEX_NAME,
        )
-        # sleep(5)  # waits for mongot to update Lucene's index
        output = vectorstore.similarity_search("Sandwich", k=1)
        assert len(output) == 1

@@ -172,7 +222,6 @@ class TestMongoDBAtlasVectorSearch:
            collection=collection,
            index_name=INDEX_NAME,
        )
-        # sleep(5)  # waits for mongot to update Lucene's index
        output = vectorstore.similarity_search("Sandwich", k=1)
        assert len(output) == 1
        # Check for the presence of the metadata key
@@ -195,7 +244,6 @@ class TestMongoDBAtlasVectorSearch:
            collection=collection,
            index_name=INDEX_NAME,
        )
-        # sleep(5)  # waits for mongot to update Lucene's index
        output = vectorstore.similarity_search(
            "Sandwich", k=1, pre_filter={"c": {"$lte": 0}}
        )
@@ -209,9 +257,25 @@ class TestMongoDBAtlasVectorSearch:
            collection=collection,
            index_name=INDEX_NAME,
        )
-        # sleep(5)  # waits for mongot to update Lucene's index
        query = "foo"
        output = vectorstore.max_marginal_relevance_search(query, k=10, lambda_mult=0.1)
        assert len(output) == len(texts)
        assert output[0].page_content == "foo"
        assert output[1].page_content != "foo"
+
+    def test_index_creation(
+        self, embedding_openai: Embeddings, index_collection: Any
+    ) -> None:
+        vectorstore = PatchedMongoDBAtlasVectorSearch(
+            index_collection, embedding_openai, index_name=INDEX_CREATION_NAME
+        )
+        vectorstore.create_vector_search_index(dimensions=1536)
+
+    def test_index_update(
+        self, embedding_openai: Embeddings, index_collection: Any
+    ) -> None:
+        vectorstore = PatchedMongoDBAtlasVectorSearch(
+            index_collection, embedding_openai, index_name=INDEX_CREATION_NAME
+        )
+        vectorstore.create_vector_search_index(dimensions=1536)
+        vectorstore.create_vector_search_index(dimensions=1536, update=True)
--- a/libs/partners/openai/langchain_openai/chat_models/base.py
+++ b/libs/partners/openai/langchain_openai/chat_models/base.py
@@ -346,6 +346,9 @@ class BaseChatOpenAI(BaseChatModel):
        http_client as well if you'd like a custom client for sync invocations."""
    stop: Optional[Union[List[str], str]] = Field(default=None, alias="stop_sequences")
    """Default stop sequences."""
+    extra_body: Optional[Mapping[str, Any]] = None
+    """Optional additional JSON properties to include in the request parameters when
+    making requests to OpenAI compatible APIs, such as vLLM."""

    class Config:
        """Configuration for this pydantic object."""
@@ -445,6 +448,9 @@ class BaseChatOpenAI(BaseChatModel):
            params["max_tokens"] = self.max_tokens
        if self.stop:
            params["stop"] = self.stop
+        if self.extra_body is not None:
+            params["extra_body"] = self.extra_body
+
        return params

    def _combine_llm_outputs(self, llm_outputs: List[Optional[dict]]) -> dict:
@@ -1666,7 +1672,13 @@ class ChatOpenAI(BaseChatOpenAI):
    ) -> Iterator[ChatGenerationChunk]:
        """Set default stream_options."""
        stream_usage = self._should_stream_usage(stream_usage, **kwargs)
-        kwargs["stream_options"] = {"include_usage": stream_usage}
+        # Note: stream_options is not a valid parameter for Azure OpenAI.
+        # To support users proxying Azure through ChatOpenAI, here we only specify
+        # stream_options if include_usage is set to True.
+        # See https://learn.microsoft.com/en-us/azure/ai-services/openai/whats-new
+        # for release notes.
+        if stream_usage:
+            kwargs["stream_options"] = {"include_usage": stream_usage}

        return super()._stream(*args, **kwargs)

@@ -1675,7 +1687,8 @@ class ChatOpenAI(BaseChatOpenAI):
    ) -> AsyncIterator[ChatGenerationChunk]:
        """Set default stream_options."""
        stream_usage = self._should_stream_usage(stream_usage, **kwargs)
-        kwargs["stream_options"] = {"include_usage": stream_usage}
+        if stream_usage:
+            kwargs["stream_options"] = {"include_usage": stream_usage}

        async for chunk in super()._astream(*args, **kwargs):
            yield chunk
--- a/libs/partners/openai/langchain_openai/llms/base.py
+++ b/libs/partners/openai/langchain_openai/llms/base.py
@@ -137,6 +137,9 @@ class BaseOpenAI(BaseLLM):
    http_async_client: Union[Any, None] = None
    """Optional httpx.AsyncClient. Only used for async invocations. Must specify 
        http_client as well if you'd like a custom client for sync invocations."""
+    extra_body: Optional[Mapping[str, Any]] = None
+    """Optional additional JSON properties to include in the request parameters when
+    making requests to OpenAI compatible APIs, such as vLLM."""

    class Config:
        """Configuration for this pydantic object."""
@@ -222,6 +225,9 @@ class BaseOpenAI(BaseLLM):
        if self.max_tokens is not None:
            normal_params["max_tokens"] = self.max_tokens

+        if self.extra_body is not None:
+            normal_params["extra_body"] = self.extra_body
+
        # Azure gpt-35-turbo doesn't support best_of
        # don't specify best_of if it is 1
        if self.best_of > 1:
--- a/libs/partners/openai/poetry.lock
+++ b/libs/partners/openai/poetry.lock
@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 1.8.2 and should not be changed by hand.
+# This file is automatically @generated by Poetry 1.8.3 and should not be changed by hand.

 [[package]]
 name = "annotated-types"
@@ -385,7 +385,7 @@ files = [

 [[package]]
 name = "langchain-core"
-version = "0.2.9"
+version = "0.2.10"
 description = "Building applications with LLMs through composability"
 optional = false
 python-versions = ">=3.8.1,<4.0"
@@ -586,13 +586,13 @@ files = [

 [[package]]
 name = "openai"
-version = "1.29.0"
+version = "1.35.6"
 description = "The official Python library for the openai API"
 optional = false
 python-versions = ">=3.7.1"
 files = [
-    {file = "openai-1.29.0-py3-none-any.whl", hash = "sha256:c61cd12376c84362d406341f9e2f9a9d6b81c082b133b44484dc0f43954496b1"},
-    {file = "openai-1.29.0.tar.gz", hash = "sha256:d5a769f485610cff8bae14343fa45a8b1d346be3d541fa5b28ccd040dbc8baf8"},
+    {file = "openai-1.35.6-py3-none-any.whl", hash = "sha256:c2bfa599445a2d6010adc7954476c2dc64e1aa8dad02ef29e0f31b9a887c1d02"},
+    {file = "openai-1.35.6.tar.gz", hash = "sha256:c5958617048a2d777d2b96050fd69ae6721bdffbf59967698694223cc092abd9"},
 ]

 [package.dependencies]
@@ -1400,4 +1400,4 @@ watchmedo = ["PyYAML (>=3.10)"]
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.8.1,<4.0"
-content-hash = "979fe68dc87d220765c4f31867d1b51aaddf147ed571d4eb30bc39fc51d774d2"
+content-hash = "abce67a9e29b0a4c6fb7c22efb8fb4b1248cb692ec85d74fdb650f50f714b241"
--- a/libs/partners/openai/pyproject.toml
+++ b/libs/partners/openai/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langchain-openai"
-version = "0.1.10"
+version = "0.1.11"
 description = "An integration package connecting OpenAI and LangChain"
 authors = []
 readme = "README.md"
@@ -13,7 +13,7 @@ license = "MIT"
 [tool.poetry.dependencies]
 python = ">=3.8.1,<4.0"
 langchain-core = ">=0.2.2,<0.3"
-openai = "^1.26.0"
+openai = "^1.32.0"
 tiktoken = ">=0.7,<1"

 [tool.poetry.group.test]
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Eugene Yurtsev	435dec28fe	x	2024-06-27 15:56:35 -04:00
Eugene Yurtsev	de5b09251d	test	2024-06-27 15:55:35 -04:00
ccurme	bffc3c24a0	openai[patch]: release 0.1.11 (#23596 )	2024-06-27 18:48:40 +00:00
ccurme	a1520357c8	openai[patch]: revert addition of "name" to supported properties for tool messages (#23600 )	2024-06-27 18:40:04 +00:00
joshc-ai21	16a293cc3a	Small bug fixes (#23353 ) Small bug fixes according to your comments --------- Signed-off-by: Joffref <mariusjoffre@gmail.com> Signed-off-by: Rahul Tripathi <rauhl.psit.ec@gmail.com> Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com> Co-authored-by: Baskar Gopinath <73015364+baskargopinath@users.noreply.github.com> Co-authored-by: Chester Curme <chester.curme@gmail.com> Co-authored-by: Mathis Joffre <51022808+Joffref@users.noreply.github.com> Co-authored-by: Baur <baur.krykpayev@gmail.com> Co-authored-by: Nuradil <nuradil.maksut@icloud.com> Co-authored-by: Nuradil <133880216+yaksh0nti@users.noreply.github.com> Co-authored-by: Jacob Lee <jacoblee93@gmail.com> Co-authored-by: Rave Harpaz <rave.harpaz@oracle.com> Co-authored-by: RHARPAZ <RHARPAZ@RHARPAZ-5750.us.oracle.com> Co-authored-by: Arthur Cheng <arthur.cheng@oracle.com> Co-authored-by: Tomaz Bratanic <bratanic.tomaz@gmail.com> Co-authored-by: RUO <61719257+comsa33@users.noreply.github.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com> Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Luis Rueda <userlerueda@gmail.com> Co-authored-by: Jib <Jibzade@gmail.com> Co-authored-by: Eugene Yurtsev <eugene@langchain.dev> Co-authored-by: S M Zia Ur Rashid <smziaurrashid@gmail.com> Co-authored-by: Ikko Eltociear Ashimine <eltociear@gmail.com> Co-authored-by: yuncliu <lyc1990@qq.com> Co-authored-by: wenngong <76683249+wenngong@users.noreply.github.com> Co-authored-by: gongwn1 <gongwn1@lenovo.com> Co-authored-by: Mirna Wong <89008547+mirnawong1@users.noreply.github.com> Co-authored-by: Rahul Triptahi <rahul.psit.ec@gmail.com> Co-authored-by: Rahul Tripathi <rauhl.psit.ec@gmail.com> Co-authored-by: maang-h <55082429+maang-h@users.noreply.github.com> Co-authored-by: asafg <asafg@ai21.com> Co-authored-by: Asaf Joseph Gardin <39553475+Josephasafg@users.noreply.github.com>	2024-06-27 17:58:22 +00:00
panwg3	9308bf32e5	spelling errors in words (#23559 ) 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" - [ ] 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! - [ ] Add tests and docs: If you're adding a new integration, please include 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. - [ ] Lint and test: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. See contribution guidelines for more: https://python.langchain.com/docs/contributing/ Additional guidelines: - 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. --------- Co-authored-by: ccurme <chester.curme@gmail.com>	2024-06-27 17:16:22 +00:00
clement.l	182fc06769	docs: Fix typo in LLMChain tutorial (#23593 ) When using `model_with_tools.invoke`, the `content` returns as an empty string. For more details, please refer to my [trace log](https://smith.langchain.com/public/6fd24bc4-86c4-4627-8565-9a8adaf4ad7d/r).	2024-06-27 17:01:05 +00:00
ccurme	5536420bee	openai[patch]: add comment (#23595 ) Forgot to push this to https://github.com/langchain-ai/langchain/pull/23551	2024-06-27 16:47:14 +00:00
andrewmjc	9f0f3c7e29	partners[openai]: Add name field to tool message to match OpenAI spec (#23551 ) Discovered alongside @t968914 - Description: According to OpenAI docs, tool messages (response from calling tools) must have a 'name' field. https://cookbook.openai.com/examples/how_to_call_functions_with_chat_models - Issue: N/A (as of right now) - Dependencies: N/A - Twitter handle: N/A 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.	2024-06-27 12:42:36 -04:00
Krista Pratico	85e36b0f50	partners[openai]: only add stream_options to kwargs if requested (#23552 ) - Description: This PR https://github.com/langchain-ai/langchain/pull/22854 added the ability to pass `stream_options` through to the openai service to get token usage information in the response. Currently OpenAI supports this parameter, but Azure OpenAI does not yet. For users who proxy their calls to both services through ChatOpenAI, this breaks when targeting Azure OpenAI (see related discussion opened in openai-python: https://github.com/openai/openai-python/issues/1469#issuecomment-2192658630). > Error code: 400 - {'error': {'code': None, 'message': 'Unrecognized request argument supplied: stream_options', 'param': None, 'type': 'invalid_request_error'}} This PR fixes the issue by only adding `stream_options` to the request if it's actually requested by the user (i.e. set to True). If I'm not mistaken, we have a test case that already covers this scenario: https://github.com/langchain-ai/langchain/blob/master/libs/partners/openai/tests/integration_tests/chat_models/test_base.py#L398-L399 - Issue: Issue opened in openai-python: https://github.com/openai/openai-python/issues/1469 - Dependencies: N/A - Twitter handle: N/A --------- Co-authored-by: Chester Curme <chester.curme@gmail.com>	2024-06-27 12:23:05 -04:00
Eugene Yurtsev	96b72edac8	core[minor]: Add optional ID field to Document schema (#23411 ) This PR adds an optional ID field to the document schema. # 1. Optional or Required - An optional field will will requrie additional checking for the type in user code (annoying). - However, vectorstores currently don't respect this field. So if we make it required and start returning random UUIDs that might be even more confusing to users. Proposal: Start with Optional and convert to Required (with default set to uuid4()) in 1-2 major releases. # 2. Override __str__ or generic solution in prompts Overriding __str__ as a simple way to avoid changing user code that relies on default str(document) in prompts. I considered rolling out a more general solution in prompts (https://github.com/langchain-ai/langchain/pull/8685), but to do that we need to: 1. Make things serializable 2. The more general solution would likely need to be backwards compatible as well 3. It's unclear that one wants to format a List[int] in the same way as List[Document]. The former should be `,` seperated (likely), the latter should be `---` separated (likely). Proposal Start with __str__ override and focus on the vectorstore APIs, we generalize prompts later	2024-06-27 12:15:58 -04:00
ccurme	5bfcb898ad	openai[patch]: bump sdk version (#23592 ) Tests failing with `TypeError: Completions.create() got an unexpected keyword argument 'parallel_tool_calls'`	2024-06-27 11:57:24 -04:00
Jacob Lee	60fc15a56b	docs[patch]: Update docs introduction and README (#23558 ) CC @hwchase17 @baskaryan	2024-06-27 08:51:43 -07:00
panwg3	2445b997ee	Correction of incorrect words (#23557 ) 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" - [ ] 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! - [ ] Add tests and docs: If you're adding a new integration, please include 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. - [ ] Lint and test: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. See contribution guidelines for more: https://python.langchain.com/docs/contributing/ Additional guidelines: - 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.	2024-06-27 15:13:15 +00:00
Aditya	6721b991ab	docs: realigned sections for langchain-google-vertexai (#23584 ) - Description: Re-aligned sections in documentation of Vertex AI LLMs - Issue: NA - Dependencies: NA - Twitter handle:NA --------- Co-authored-by: adityarane@google.com <adityarane@google.com> Co-authored-by: ccurme <chester.curme@gmail.com>	2024-06-27 10:42:32 -04:00
mackong	daf733b52e	langchain[minor]: fix comment typo (#23564 ) Description: fix typo of comment Issue: N/A Dependencies: N/A	2024-06-27 10:09:18 -04:00
Jacob Lee	47f69fe0d8	docs[patch]: Add ReAct agent conceptual guide, improve search (#23554 ) @baskaryan	2024-06-26 19:02:03 -07:00
Jacob Lee	672fcbb8dc	docs[patch]: Fix bad link format (#23553 )	2024-06-26 16:43:26 -07:00
Jacob Lee	13254715a2	docs[patch]: Update installation guide with diagram (#23548 ) CC @baskaryan	2024-06-26 15:10:22 -07:00
Leonid Ganeline	2c9b84c3a8	core[patch]: docstrings `agents` (#23502 ) Added missed docstrings. Formatted docstrings to the consistent form.	2024-06-26 17:50:48 -04:00
Jacob Lee	79d8556c22	docs[patch]: Address feedback from docs users (#23550 ) - Updates chat few shot prompt tutorial to show off a more cohesive example - Fix async Chromium loader guide - Fix Excel loader install instructions - Reformat Html2Text page - Add install instructions to Azure OpenAI embeddings page - Add missing dep install to SQL QA tutorial @baskaryan	2024-06-26 14:47:01 -07:00
Leonid Ganeline	2a5d59b3d7	core[patch]: `callbacks` docstrings (#23375 ) Added missed docstrings. Formatted docstrings to the consistent form.	2024-06-26 17:11:06 -04:00
Leonid Ganeline	1141b08eb8	core: docstrings `example_selectors` (#23542 ) Added missed docstrings. Formatted docstrings to the consistent form.	2024-06-26 17:10:40 -04:00
wenngong	3bf1d98dbf	langchain[patch]: update agent and chains modules root_validators (#23256 ) Description: update agent and chains modules Pydantic root_validators. Issue: the issue #22819 --------- Co-authored-by: gongwn1 <gongwn1@lenovo.com> Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com> Co-authored-by: Eugene Yurtsev <eugene@langchain.dev>	2024-06-26 17:09:50 -04:00
Bagatur	a7ab93479b	anthropic[patch]: Release 0.1.16 (#23549 )	2024-06-26 20:49:13 +00:00
Jib	c0fcf76e93	LangChain-MongoDB: [Experimental] Driver-side index creation helper (#19359 ) ## Description Created a helper method to make vector search indexes via client-side pymongo. Recent Update -- Removed error suppressing/overwriting layer in favor of letting the original exception provide information. ## ToDo's - [x] Make _wait_untils for integration test delete index functionalities. - [x] Add documentation for its use. Highlight it's experimental - [x] Post Integration Test Results in a screenshot - [x] Get review from MongoDB internal team (@shaneharvey, @blink1073 , @NoahStapp , @caseyclements) - [x] Add tests and docs: If you're adding a new integration, please include 1. Added new integration tests. Not eligible for unit testing since the operation is Atlas Cloud specific. 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. ![image](https://github.com/langchain-ai/langchain/assets/2887713/a3fc8ee1-e04c-4976-accc-fea0eeae028a) - [x] 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/	2024-06-26 15:07:28 -04:00
Jacob Lee	b1dfb8ea1e	docs[patch]: Update contribution guides (#23382 ) CC @vbarda @hwchase17	2024-06-26 11:12:41 -07:00
maang-h	5070004e8a	docs: Update Tongyi ChatModel docstring (#23540 ) - Description: Update Tongyi ChatModel rich docstring - Issue: the issue #22296	2024-06-26 13:07:13 -04:00
Nuradil	2f976c5174	community: fix code example in ZenGuard docs (#23541 ) Thank you for contributing to LangChain! - [X] PR title: "community: fix code example in ZenGuard docs" - [X] PR message: - Description: corrected the docs by indicating in the code example that the tool accepts a list of prompts instead of just one - [X] 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/ Thank you for review --------- Co-authored-by: Baur <baur.krykpayev@gmail.com>	2024-06-26 13:05:59 -04:00
yonarw	6d0ebbca1e	community: SAP HANA Vector Engine fix for latest HANA release (#23516 ) - Description: This PR fixes an issue with SAP HANA Cloud QRC03 version. In that version the number to indicate no length being set for a vector column changed from -1 to 0. The change in this PR support both behaviours (old/new). - Dependencies: No dependencies have been introduced. - Tests: The change is covered by previous unit tests.	2024-06-26 13:15:51 +00:00
Roman Solomatin	1e3e05b0c3	openai[patch]: add support for extra_body (#23404 ) Description: Add support passing extra_body parameter Some OpenAI compatible API's have additional parameters (for example [vLLM](https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html#extra-parameters)) that can be passed thought `extra_body`. Same question in https://github.com/openai/openai-python/issues/767 <!-- If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17. -->	2024-06-26 13:11:59 +00:00
Alireza Kashani	c39521b70d	Update grobid.py (#23399 ) fixed potential `IndexError: list index out of range` in case there is no title 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" - [ ] 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! - [ ] Add tests and docs: If you're adding a new integration, please include 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. - [ ] Lint and test: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. See contribution guidelines for more: https://python.langchain.com/docs/contributing/ Additional guidelines: - 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.	2024-06-26 09:11:02 -04:00
Qingchuan Hao	ee282a1d2e	community: add missing link (#23526 )	2024-06-26 09:06:28 -04:00
Lincoln Stein	c314222796	Add a conversation memory that combines a (optionally persistent) vectorstore history with a token buffer (#22155 ) langchain: ConversationVectorStoreTokenBufferMemory -Description: This PR adds ConversationVectorStoreTokenBufferMemory. It is similar in concept to ConversationSummaryBufferMemory. It maintains an in-memory buffer of messages up to a preset token limit. After the limit is hit timestamped messages are written into a vectorstore retriever rather than into a summary. The user's prompt is then used to retrieve relevant fragments of the previous conversation. By persisting the vectorstore, one can maintain memory from session to session. -Issue: n/a -Dependencies: none -Twitter handle: Please no!!! - [X] Add tests and docs: I looked to see how the unit tests were written for the other ConversationMemory modules, but couldn't find anything other than a test for successful import. I need to know whether you are using pytest.mock or another fixture to simulate the LLM and vectorstore. In addition, I would like guidance on where to place the documentation. Should it be a notebook file in docs/docs? - [X] Lint and test: I am seeing some linting errors from a couple of modules unrelated to this PR. If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17. --------- Co-authored-by: Lincoln Stein <lstein@gmail.com> Co-authored-by: isaac hershenson <ihershenson@hmc.edu>	2024-06-25 20:17:10 -07:00
Bagatur	32f8f39974	core[patch]: use args_schema doc for tool description (#23503 )	2024-06-25 15:26:35 -07:00
ccurme	6f7fe82830	text-splitters: release 0.2.2 (#23508 )	2024-06-25 18:26:05 -04:00