cli: release 0.0.30 (#25672)

Added missed provider pages and links.

.github/scripts/check_diff.py

@@ -1,7 +1,6 @@
 import glob
 import json
 import os
-import re
 import sys
 import tomllib
 from collections import defaultdict
@@ -69,6 +68,13 @@ def dependents_graph() -> dict:
 
                     if "langchain" in dep:
                         dependents[dep].add(pkg_dir)
+
+    # remove huggingface from dependents because of CI instability
+    # specifically in huggingface jobs
+    # https://github.com/langchain-ai/langchain/issues/25558
+    for k in dependents:
+        if "libs/partners/huggingface" in dependents[k]:
+            dependents[k].remove("libs/partners/huggingface")
     return dependents
 
 
@@ -86,6 +92,11 @@ def add_dependents(dirs_to_eval: Set[str], dependents: dict) -> List[str]:
 
 
 def _get_configs_for_single_dir(job: str, dir_: str) -> List[Dict[str, str]]:
+    if dir_ == "libs/core":
+        return [
+            {"working-directory": dir_, "python-version": f"3.{v}"}
+            for v in range(8, 13)
+        ]
     min_python = "3.8"
     max_python = "3.12"
 
@@ -95,6 +106,15 @@ def _get_configs_for_single_dir(job: str, dir_: str) -> List[Dict[str, str]]:
         # declare deps in funny way
         max_python = "3.11"
 
+    if dir_ in ["libs/community", "libs/langchain"] and job == "extended-tests":
+        # community extended test resolution in 3.12 is slow
+        # even in uv
+        max_python = "3.11"
+
+    if dir_ == "libs/community" and job == "compile-integration-tests":
+        # community integration deps are slow in 3.12
+        max_python = "3.11"
+
     return [
         {"working-directory": dir_, "python-version": min_python},
         {"working-directory": dir_, "python-version": max_python},

.github/scripts/get_min_versions.py

@@ -1,6 +1,11 @@
 import sys
 
-import tomllib
+if sys.version_info >= (3, 11):
+    import tomllib
+else:
+    # for python 3.10 and below, which doesnt have stdlib tomllib
+    import tomli as tomllib
+
 from packaging.version import parse as parse_version
 import re
 
@@ -12,6 +17,8 @@ MIN_VERSION_LIBS = [
     "SQLAlchemy",
 ]
 
+SKIP_IF_PULL_REQUEST = ["langchain-core"]
+
 
 def get_min_version(version: str) -> str:
     # base regex for x.x.x with cases for rc/post/etc
@@ -38,7 +45,7 @@ def get_min_version(version: str) -> str:
     raise ValueError(f"Unrecognized version format: {version}")
 
 
-def get_min_version_from_toml(toml_path: str):
+def get_min_version_from_toml(toml_path: str, versions_for: str):
     # Parse the TOML file
     with open(toml_path, "rb") as file:
         toml_data = tomllib.load(file)
@@ -51,6 +58,10 @@ def get_min_version_from_toml(toml_path: str):
 
     # Iterate over the libs in MIN_VERSION_LIBS
     for lib in MIN_VERSION_LIBS:
+        if versions_for == "pull_request" and lib in SKIP_IF_PULL_REQUEST:
+            # some libs only get checked on release because of simultaneous
+            # changes
+            continue
         # Check if the lib is present in the dependencies
         if lib in dependencies:
             # Get the version string
@@ -71,8 +82,10 @@ def get_min_version_from_toml(toml_path: str):
 if __name__ == "__main__":
     # Get the TOML file path from the command line argument
     toml_file = sys.argv[1]
+    versions_for = sys.argv[2]
+    assert versions_for in ["release", "pull_request"]
 
     # Call the function to get the minimum versions
-    min_versions = get_min_version_from_toml(toml_file)
+    min_versions = get_min_version_from_toml(toml_file, versions_for)
 
     print(" ".join([f"{lib}=={version}" for lib, version in min_versions.items()]))

.github/workflows/_release.yml

@@ -189,7 +189,7 @@ jobs:
             --extra-index-url https://test.pypi.org/simple/ \
             "$PKG_NAME==$VERSION" || \
           ( \
-            sleep 5 && \
+            sleep 15 && \
             poetry run pip install \
               --extra-index-url https://test.pypi.org/simple/ \
               "$PKG_NAME==$VERSION" \
@@ -231,7 +231,7 @@ jobs:
         id: min-version
         run: |
           poetry run pip install packaging
-          min_versions="$(poetry run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml)"
+          min_versions="$(poetry run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml release)"
           echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"
           echo "min-versions=$min_versions"
 
@@ -290,6 +290,7 @@ jobs:
           VOYAGE_API_KEY: ${{ secrets.VOYAGE_API_KEY }}
           UPSTAGE_API_KEY: ${{ secrets.UPSTAGE_API_KEY }}
           FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
+          UNSTRUCTURED_API_KEY: ${{ secrets.UNSTRUCTURED_API_KEY }}
         run: make integration_tests
         working-directory: ${{ inputs.working-directory }}
 

.github/workflows/_test.yml

@@ -65,3 +65,22 @@ jobs:
           # grep will exit non-zero if the target message isn't found,
           # and `set -e` above will cause the step to fail.
           echo "$STATUS" | grep 'nothing to commit, working tree clean'
+          
+      - name: Get minimum versions
+        working-directory: ${{ inputs.working-directory }}
+        id: min-version
+        run: |
+          poetry run pip install packaging tomli
+          min_versions="$(poetry run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml pull_request)"
+          echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"
+          echo "min-versions=$min_versions"
+
+# Temporarily disabled until we can get the minimum versions working
+#      - name: Run unit tests with minimum dependency versions
+#        if: ${{ steps.min-version.outputs.min-versions != '' }}
+#        env:
+#          MIN_VERSIONS: ${{ steps.min-version.outputs.min-versions }}
+#        run: |
+#          poetry run pip install --force-reinstall $MIN_VERSIONS --editable .
+#          make tests
+#        working-directory: ${{ inputs.working-directory }}

.gitignore

@@ -172,6 +172,8 @@ docs/api_reference/*/
 !docs/api_reference/_static/
 !docs/api_reference/templates/
 !docs/api_reference/themes/
+!docs/api_reference/_extensions/
+!docs/api_reference/scripts/
 docs/docs/build
 docs/docs/node_modules
 docs/docs/yarn.lock

MIGRATE.md

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

Makefile

@@ -31,6 +31,7 @@ docs_linkcheck:
 api_docs_build:
 	poetry run python docs/api_reference/create_api_rst.py
 	cd docs/api_reference && poetry run make html
+	poetry run python docs/api_reference/scripts/custom_formatter.py docs/api_reference/_build/html/
 
 API_PKG ?= text-splitters
 
@@ -38,12 +39,14 @@ api_docs_quick_preview:
 	poetry run pip install "pydantic<2"
 	poetry run python docs/api_reference/create_api_rst.py $(API_PKG)
 	cd docs/api_reference && poetry run make html
-	open docs/api_reference/_build/html/$(shell echo $(API_PKG) | sed 's/-/_/g')_api_reference.html
+	poetry run python docs/api_reference/scripts/custom_formatter.py docs/api_reference/_build/html/
+	open docs/api_reference/_build/html/reference.html
 
 ## api_docs_clean: Clean the API Reference documentation build artifacts.
 api_docs_clean:
 	find ./docs/api_reference -name '*_api_reference.rst' -delete
 	git clean -fdX ./docs/api_reference
+	rm docs/api_reference/index.md
 	
 
 ## api_docs_linkcheck: Run linkchecker on the API Reference documentation.

README.md

@@ -7,7 +7,6 @@
 [![PyPI - License](https://img.shields.io/pypi/l/langchain-core?style=flat-square)](https://opensource.org/licenses/MIT)
 [![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-core?style=flat-square)](https://pypistats.org/packages/langchain-core)
 [![GitHub star chart](https://img.shields.io/github/stars/langchain-ai/langchain?style=flat-square)](https://star-history.com/#langchain-ai/langchain)
-[![Dependency Status](https://img.shields.io/librariesio/github/langchain-ai/langchain?style=flat-square)](https://libraries.io/github/langchain-ai/langchain)
 [![Open Issues](https://img.shields.io/github/issues-raw/langchain-ai/langchain?style=flat-square)](https://github.com/langchain-ai/langchain/issues)
 [![Open in Dev Containers](https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode&style=flat-square)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langchain-ai/langchain)
 [![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/langchain-ai/langchain)
@@ -15,18 +14,20 @@
 
 Looking for the JS/TS library? Check out [LangChain.js](https://github.com/langchain-ai/langchainjs).
 
-To help you ship LangChain apps to production faster, check out [LangSmith](https://smith.langchain.com). 
-[LangSmith](https://smith.langchain.com) is a unified developer platform for building, testing, and monitoring LLM applications. 
+To help you ship LangChain apps to production faster, check out [LangSmith](https://smith.langchain.com).
+[LangSmith](https://smith.langchain.com) is a unified developer platform for building, testing, and monitoring LLM applications.
 Fill out [this form](https://www.langchain.com/contact-sales) to speak with our sales team.
 
 ## Quick Install
 
 With pip:
+
 ```bash
 pip install langchain
 ```
 
 With conda:
+
 ```bash
 conda install langchain -c conda-forge
 ```
@@ -37,12 +38,13 @@ conda install langchain -c conda-forge
 
 For these applications, LangChain simplifies the entire application lifecycle:
 
-- **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.
+- **Open-source libraries**: Build your applications using LangChain's open-source [building blocks](https://python.langchain.com/v0.2/docs/concepts#langchain-expression-language-lcel), [components](https://python.langchain.com/v0.2/docs/concepts), and [third-party integrations](https://python.langchain.com/v0.2/docs/integrations/platforms/).
+  Use [LangGraph](/docs/concepts/#langgraph) to build stateful agents with first-class streaming and human-in-the-loop support.
 - **Productionization**: Inspect, monitor, and evaluate your apps with [LangSmith](https://docs.smith.langchain.com/) so that you can constantly optimize and deploy with confidence.
 - **Deployment**: Turn your LangGraph applications into production-ready APIs and Assistants with [LangGraph Cloud](https://langchain-ai.github.io/langgraph/cloud/).
 
 ### 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`**.
@@ -50,9 +52,11 @@ Use [LangGraph](/docs/concepts/#langgraph) to build stateful agents with first-c
 - **[`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:
+
 - **[LangGraph Cloud](https://langchain-ai.github.io/langgraph/cloud/)**: Turn your LangGraph applications into production-ready APIs and Assistants.
 
 ![Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers.](docs/static/svg/langchain_stack_062024.svg "LangChain Architecture Overview")
@@ -77,15 +81,17 @@ Use [LangGraph](/docs/concepts/#langgraph) to build stateful agents with first-c
 And much more! Head to the [Tutorials](https://python.langchain.com/v0.2/docs/tutorials/) section of the docs for more.
 
 ## 🚀 How does LangChain help?
+
 The main value props of the LangChain libraries are:
+
 1. **Components**: composable building blocks, tools and integrations for working with language models. Components are modular and easy-to-use, whether you are using the rest of the LangChain framework or not
 2. **Off-the-shelf chains**: built-in assemblages of components for accomplishing higher-level tasks
 
-Off-the-shelf chains make it easy to get started. Components make it easy to customize existing chains and build new ones. 
+Off-the-shelf chains make it easy to get started. Components make it easy to customize existing chains and build new ones.
 
 ## LangChain Expression Language (LCEL)
 
-LCEL is the foundation of many of LangChain's components, and is a declarative way to compose chains. LCEL was designed from day 1 to support putting prototypes in production, with no code changes, from the simplest “prompt + LLM” chain to the most complex chains.
+LCEL is a key part of LangChain, allowing you to build and organize chains of processes in a straightforward, declarative manner. It was designed to support taking prototypes directly into production without needing to alter any code. This means you can use LCEL to set up everything from basic "prompt + LLM" setups to intricate, multi-step workflows.
 
 - **[Overview](https://python.langchain.com/v0.2/docs/concepts/#langchain-expression-language-lcel)**: LCEL and its benefits
 - **[Interface](https://python.langchain.com/v0.2/docs/concepts/#runnable-interface)**: The standard Runnable interface for LCEL objects
@@ -124,7 +130,6 @@ Please see [here](https://python.langchain.com) for full documentation, which in
 - [🦜🕸️ LangGraph](https://langchain-ai.github.io/langgraph/): Create stateful, multi-actor applications with LLMs. Integrates smoothly with LangChain, but can be used without it.
 - [🦜🏓 LangServe](https://python.langchain.com/docs/langserve): Deploy LangChain runnables and chains as REST APIs.
 
-
 ## 💁 Contributing
 
 As an open-source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of a new feature, improved infrastructure, or better documentation.

cookbook/Multi_modal_RAG.ipynb

@@ -64,7 +64,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install -U langchain openai chromadb langchain-experimental # (newest versions required for multi-modal)"
+    "! pip install -U langchain openai langchain-chroma langchain-experimental # (newest versions required for multi-modal)"
    ]
   },
   {
@@ -355,7 +355,7 @@
     "\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryStore\n",
-    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_core.documents import Document\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",

cookbook/Multi_modal_RAG_google.ipynb

@@ -37,7 +37,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install -U --quiet langchain langchain_community openai chromadb langchain-experimental\n",
+    "%pip install -U --quiet langchain langchain-chroma langchain-community openai langchain-experimental\n",
     "%pip install --quiet \"unstructured[all-docs]\" pypdf pillow pydantic lxml pillow matplotlib chromadb tiktoken"
    ]
   },
@@ -344,8 +344,8 @@
     "\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryStore\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_community.embeddings import VertexAIEmbeddings\n",
-    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_core.documents import Document\n",
     "\n",
     "\n",

cookbook/RAPTOR.ipynb

@@ -7,7 +7,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "pip install -U langchain umap-learn scikit-learn langchain_community tiktoken langchain-openai langchainhub chromadb langchain-anthropic"
+    "pip install -U langchain umap-learn scikit-learn langchain_community tiktoken langchain-openai langchainhub langchain-chroma langchain-anthropic"
    ]
   },
   {
@@ -645,7 +645,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_chroma import Chroma\n",
     "\n",
     "# Initialize all_texts with leaf_texts\n",
     "all_texts = leaf_texts.copy()\n",

cookbook/README.md

@@ -36,6 +36,7 @@ Notebook | Description
 [llm_symbolic_math.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/llm_symbolic_math.ipynb) | Solve algebraic equations with the help of llms (language learning models) and sympy, a python library for symbolic mathematics.
 [meta_prompt.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/meta_prompt.ipynb) | Implement the meta-prompt concept, which is a method for building self-improving agents that reflect on their own performance and modify their instructions accordingly.
 [multi_modal_output_agent.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multi_modal_output_agent.ipynb) | Generate multi-modal outputs, specifically images and text.
+[multi_modal_RAG_vdms.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multi_modal_RAG_vdms.ipynb) | Perform retrieval-augmented generation (rag) on documents including text and images, using unstructured for parsing, Intel's Visual Data Management System (VDMS) as the vectorstore, and chains.
 [multi_player_dnd.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multi_player_dnd.ipynb) | Simulate multi-player dungeons & dragons games, with a custom function determining the speaking schedule of the agents.
 [multiagent_authoritarian.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multiagent_authoritarian.ipynb) | Implement a multi-agent simulation where a privileged agent controls the conversation, including deciding who speaks and when the conversation ends, in the context of a simulated news network.
 [multiagent_bidding.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multiagent_bidding.ipynb) | Implement a multi-agent simulation where agents bid to speak, with the highest bidder speaking next, demonstrated through a fictitious presidential debate example.
@@ -58,4 +59,5 @@ Notebook | Description
 [two_player_dnd.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/two_player_dnd.ipynb) | Simulate a two-player dungeons & dragons game, where a dialogue simulator class is used to coordinate the dialogue between the protagonist and the dungeon master.
 [wikibase_agent.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/wikibase_agent.ipynb) | Create a simple wikibase agent that utilizes sparql generation, with testing done on http://wikidata.org.
 [oracleai_demo.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/oracleai_demo.ipynb) | This guide outlines how to utilize Oracle AI Vector Search alongside Langchain for an end-to-end RAG pipeline, providing step-by-step examples. The process includes loading documents from various sources using OracleDocLoader, summarizing them either within or outside the database with OracleSummary, and generating embeddings similarly through OracleEmbeddings. It also covers chunking documents according to specific requirements using Advanced Oracle Capabilities from OracleTextSplitter, and finally, storing and indexing these documents in a Vector Store for querying with OracleVS.
-[rag-locally-on-intel-cpu.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/rag-locally-on-intel-cpu.ipynb) | Perform Retrieval-Augmented-Generation (RAG) on locally downloaded open-source models using langchain and open source tools and execute it on Intel Xeon CPU. We showed an example of how to apply RAG on Llama 2 model and enable it to answer the queries related to Intel Q1 2024 earnings release.
+[rag-locally-on-intel-cpu.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/rag-locally-on-intel-cpu.ipynb) | Perform Retrieval-Augmented-Generation (RAG) on locally downloaded open-source models using langchain and open source tools and execute it on Intel Xeon CPU. We showed an example of how to apply RAG on Llama 2 model and enable it to answer the queries related to Intel Q1 2024 earnings release.
+[visual_RAG_vdms.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/visual_RAG_vdms.ipynb) | Performs Visual Retrieval-Augmented-Generation (RAG) using videos and scene descriptions generated by open source models.

cookbook/Semi_Structured_RAG.ipynb

@@ -39,7 +39,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain unstructured[all-docs] pydantic lxml langchainhub"
+    "! pip install langchain langchain-chroma \"unstructured[all-docs]\" pydantic lxml langchainhub"
    ]
   },
   {
@@ -320,7 +320,7 @@
     "\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryStore\n",
-    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_core.documents import Document\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",

cookbook/Semi_structured_and_multi_modal_RAG.ipynb

@@ -59,7 +59,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain unstructured[all-docs] pydantic lxml"
+    "! pip install langchain langchain-chroma \"unstructured[all-docs]\" pydantic lxml"
    ]
   },
   {
@@ -375,7 +375,7 @@
     "\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryStore\n",
-    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_core.documents import Document\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",

cookbook/Semi_structured_multi_modal_RAG_LLaMA2.ipynb

@@ -59,7 +59,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain unstructured[all-docs] pydantic lxml"
+    "! pip install langchain langchain-chroma \"unstructured[all-docs]\" pydantic lxml"
    ]
   },
   {
@@ -378,8 +378,8 @@
     "\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryStore\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_community.embeddings import GPT4AllEmbeddings\n",
-    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_core.documents import Document\n",
     "\n",
     "# The vectorstore to use to index the child chunks\n",

cookbook/advanced_rag_eval.ipynb

@@ -19,7 +19,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install -U langchain openai chromadb langchain-experimental # (newest versions required for multi-modal)"
+    "! pip install -U langchain openai langchain_chroma langchain-experimental # (newest versions required for multi-modal)"
    ]
   },
   {
@@ -132,7 +132,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
     "baseline = Chroma.from_texts(\n",

cookbook/agent_vectorstore.ipynb

@@ -28,7 +28,7 @@
    "outputs": [],
    "source": [
     "from langchain.chains import RetrievalQA\n",
-    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_openai import OpenAI, OpenAIEmbeddings\n",
     "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",

cookbook/airbyte_github.ipynb

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

cookbook/databricks_sql_db.ipynb

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

cookbook/docugami_xml_kg_rag.ipynb

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

cookbook/fireworks_rag.ipynb

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

cookbook/hypothetical_document_embeddings.ipynb

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

cookbook/langgraph_agentic_rag.ipynb

@@ -7,7 +7,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain_community tiktoken langchain-openai langchainhub chromadb langchain langgraph"
+    "! pip install langchain-chroma langchain_community tiktoken langchain-openai langchainhub langchain langgraph"
    ]
   },
   {
@@ -30,8 +30,8 @@
    "outputs": [],
    "source": [
     "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_community.document_loaders import WebBaseLoader\n",
-    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
     "urls = [\n",

cookbook/langgraph_crag.ipynb

@@ -7,7 +7,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain_community tiktoken langchain-openai langchainhub chromadb langchain langgraph tavily-python"
+    "! pip install langchain-chroma langchain_community tiktoken langchain-openai langchainhub langchain langgraph tavily-python"
    ]
   },
   {
@@ -77,8 +77,8 @@
    "outputs": [],
    "source": [
     "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_community.document_loaders import WebBaseLoader\n",
-    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
     "urls = [\n",
@@ -180,8 +180,8 @@
     "from langchain.output_parsers.openai_tools import PydanticToolsParser\n",
     "from langchain.prompts import PromptTemplate\n",
     "from langchain.schema import Document\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_community.tools.tavily_search import TavilySearchResults\n",
-    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_core.messages import BaseMessage, FunctionMessage\n",
     "from langchain_core.output_parsers import StrOutputParser\n",
     "from langchain_core.pydantic_v1 import BaseModel, Field\n",

cookbook/langgraph_self_rag.ipynb

@@ -7,7 +7,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain_community tiktoken langchain-openai langchainhub chromadb langchain langgraph"
+    "! pip install langchain-chroma langchain_community tiktoken langchain-openai langchainhub langchain langgraph"
    ]
   },
   {
@@ -86,8 +86,8 @@
    "outputs": [],
    "source": [
     "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_community.document_loaders import WebBaseLoader\n",
-    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
     "urls = [\n",
@@ -188,7 +188,7 @@
     "from langchain.output_parsers import PydanticOutputParser\n",
     "from langchain.output_parsers.openai_tools import PydanticToolsParser\n",
     "from langchain.prompts import PromptTemplate\n",
-    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_core.messages import BaseMessage, FunctionMessage\n",
     "from langchain_core.output_parsers import StrOutputParser\n",
     "from langchain_core.pydantic_v1 import BaseModel, Field\n",

cookbook/multi_modal_RAG_chroma.ipynb

@@ -58,7 +58,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install -U langchain openai chromadb langchain-experimental # (newest versions required for multi-modal)"
+    "! pip install -U langchain openai langchain-chroma langchain-experimental # (newest versions required for multi-modal)"
    ]
   },
   {
@@ -187,7 +187,7 @@
     "\n",
     "import chromadb\n",
     "import numpy as np\n",
-    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_experimental.open_clip import OpenCLIPEmbeddings\n",
     "from PIL import Image as _PILImage\n",
     "\n",

cookbook/multi_modal_RAG_vdms.ipynb

@@ -18,26 +18,7 @@
     "* Use of multimodal embeddings (such as [CLIP](https://openai.com/research/clip)) to embed images and text\n",
     "* Use of [VDMS](https://github.com/IntelLabs/vdms/blob/master/README.md) as a vector store with support for multi-modal\n",
     "* Retrieval of both images and text using similarity search\n",
-    "* Passing raw images and text chunks to a multimodal LLM for answer synthesis \n",
-    "\n",
-    "\n",
-    "## Packages\n",
-    "\n",
-    "For `unstructured`, you will also need `poppler` ([installation instructions](https://pdf2image.readthedocs.io/en/latest/installation.html)) and `tesseract` ([installation instructions](https://tesseract-ocr.github.io/tessdoc/Installation.html)) in your system."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "febbc459-ebba-4c1a-a52b-fed7731593f8",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# (newest versions required for multi-modal)\n",
-    "! pip install --quiet -U vdms langchain-experimental\n",
-    "\n",
-    "# lock to 0.10.19 due to a persistent bug in more recent versions\n",
-    "! pip install --quiet pdf2image \"unstructured[all-docs]==0.10.19\" pillow pydantic lxml open_clip_torch"
+    "* Passing raw images and text chunks to a multimodal LLM for answer synthesis "
    ]
   },
   {
@@ -53,7 +34,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 1,
    "id": "5f483872",
    "metadata": {},
    "outputs": [
@@ -61,8 +42,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "docker: Error response from daemon: Conflict. The container name \"/vdms_rag_nb\" is already in use by container \"0c19ed281463ac10d7efe07eb815643e3e534ddf24844357039453ad2b0c27e8\". You have to remove (or rename) that container to be able to reuse that name.\n",
-      "See 'docker run --help'.\n"
+      "a1b9206b08ef626e15b356bf9e031171f7c7eb8f956a2733f196f0109246fe2b\n"
      ]
     }
    ],
@@ -75,9 +55,32 @@
     "vdms_client = VDMS_Client(port=55559)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "2498a0a1",
+   "metadata": {},
+   "source": [
+    "## Packages\n",
+    "\n",
+    "For `unstructured`, you will also need `poppler` ([installation instructions](https://pdf2image.readthedocs.io/en/latest/installation.html)) and `tesseract` ([installation instructions](https://tesseract-ocr.github.io/tessdoc/Installation.html)) in your system."
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
+   "id": "febbc459-ebba-4c1a-a52b-fed7731593f8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "! pip install --quiet -U vdms langchain-experimental\n",
+    "\n",
+    "# lock to 0.10.19 due to a persistent bug in more recent versions\n",
+    "! pip install --quiet pdf2image \"unstructured[all-docs]==0.10.19\" pillow pydantic lxml open_clip_torch"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
    "id": "78ac6543",
    "metadata": {},
    "outputs": [],
@@ -95,14 +98,9 @@
     "\n",
     "### Partition PDF text and images\n",
     "  \n",
-    "Let's look at an example pdf containing interesting images.\n",
+    "Let's use famous photographs from the PDF version of Library of Congress Magazine in this example.\n",
     "\n",
-    "Famous photographs from library of congress:\n",
-    "\n",
-    "* https://www.loc.gov/lcm/pdf/LCM_2020_1112.pdf\n",
-    "* We'll use this as an example below\n",
-    "\n",
-    "We can use `partition_pdf` below from [Unstructured](https://unstructured-io.github.io/unstructured/introduction.html#key-concepts) to extract text and images."
+    "We can use `partition_pdf` from [Unstructured](https://unstructured-io.github.io/unstructured/introduction.html#key-concepts) to extract text and images."
    ]
   },
   {
@@ -116,8 +114,8 @@
     "\n",
     "import requests\n",
     "\n",
-    "# Folder with pdf and extracted images\n",
-    "datapath = Path(\"./multimodal_files\").resolve()\n",
+    "# Folder to store pdf and extracted images\n",
+    "datapath = Path(\"./data/multimodal_files\").resolve()\n",
     "datapath.mkdir(parents=True, exist_ok=True)\n",
     "\n",
     "pdf_url = \"https://www.loc.gov/lcm/pdf/LCM_2020_1112.pdf\"\n",
@@ -174,14 +172,8 @@
    "source": [
     "## Multi-modal embeddings with our document\n",
     "\n",
-    "We will use [OpenClip multimodal embeddings](https://python.langchain.com/docs/integrations/text_embedding/open_clip).\n",
-    "\n",
-    "We use a larger model for better performance (set in `langchain_experimental.open_clip.py`).\n",
-    "\n",
-    "```\n",
-    "model_name = \"ViT-g-14\"\n",
-    "checkpoint = \"laion2b_s34b_b88k\"\n",
-    "```"
+    "In this section, we initialize the VDMS vector store for both text and images. For better performance, we use model `ViT-g-14` from [OpenClip multimodal embeddings](https://python.langchain.com/docs/integrations/text_embedding/open_clip).\n",
+    "The images are stored as base64 encoded strings with `vectorstore.add_images`.\n"
    ]
   },
   {
@@ -200,9 +192,7 @@
     "vectorstore = VDMS(\n",
     "    client=vdms_client,\n",
     "    collection_name=\"mm_rag_clip_photos\",\n",
-    "    embedding_function=OpenCLIPEmbeddings(\n",
-    "        model_name=\"ViT-g-14\", checkpoint=\"laion2b_s34b_b88k\"\n",
-    "    ),\n",
+    "    embedding=OpenCLIPEmbeddings(model_name=\"ViT-g-14\", checkpoint=\"laion2b_s34b_b88k\"),\n",
     ")\n",
     "\n",
     "# Get image URIs with .jpg extension only\n",
@@ -233,7 +223,7 @@
    "source": [
     "## RAG\n",
     "\n",
-    "`vectorstore.add_images` will store / retrieve images as base64 encoded strings."
+    "Here we define helper functions for image results."
    ]
   },
   {
@@ -392,7 +382,8 @@
    "id": "1566096d-97c2-4ddc-ba4a-6ef88c525e4e",
    "metadata": {},
    "source": [
-    "## Test retrieval and run RAG"
+    "## Test retrieval and run RAG\n",
+    "Now let's query for a `woman with children` and retrieve the top results."
    ]
   },
   {
@@ -452,6 +443,14 @@
     "        print(doc.page_content)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "15e9b54d",
+   "metadata": {},
+   "source": [
+    "Now let's use the `multi_modal_rag_chain` to process the same query and display the response."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 11,
@@ -462,10 +461,10 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "1. Detailed description of the visual elements in the image: The image features a woman with children, likely a mother and her family, standing together outside. They appear to be poor or struggling financially, as indicated by their attire and surroundings.\n",
-      "2. Historical and cultural context of the image: The photo was taken in 1936 during the Great Depression, when many families struggled to make ends meet. Dorothea Lange, a renowned American photographer, took this iconic photograph that became an emblem of poverty and hardship experienced by many Americans at that time.\n",
-      "3. Interpretation of the image's symbolism and meaning: The image conveys a sense of unity and resilience despite adversity. The woman and her children are standing together, displaying their strength as a family unit in the face of economic challenges. The photograph also serves as a reminder of the importance of empathy and support for those who are struggling.\n",
-      "4. Connections between the image and the related text: The text provided offers additional context about the woman in the photo, her background, and her feelings towards the photograph. It highlights the historical backdrop of the Great Depression and emphasizes the significance of this particular image as a representation of that time period.\n"
+      " The image depicts a woman with several children. The woman appears to be of Cherokee heritage, as suggested by the text provided. The image is described as having been initially regretted by the subject, Florence Owens Thompson, due to her feeling that it did not accurately represent her leadership qualities.\n",
+      "The historical and cultural context of the image is tied to the Great Depression and the Dust Bowl, both of which affected the Cherokee people in Oklahoma. The photograph was taken during this period, and its subject, Florence Owens Thompson, was a leader within her community who worked tirelessly to help those affected by these crises.\n",
+      "The image's symbolism and meaning can be interpreted as a representation of resilience and strength in the face of adversity. The woman is depicted with multiple children, which could signify her role as a caregiver and protector during difficult times.\n",
+      "Connections between the image and the related text include Florence Owens Thompson's leadership qualities and her regretted feelings about the photograph. Additionally, the mention of Dorothea Lange, the photographer who took this photo, ties the image to its historical context and the broader narrative of the Great Depression and Dust Bowl in Oklahoma. \n"
      ]
     }
    ],
@@ -492,14 +491,6 @@
    "source": [
     "! docker kill vdms_rag_nb"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "8ba652da",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
@@ -518,7 +509,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.13"
+   "version": "3.11.9"
   }
  },
  "nbformat": 4,

cookbook/nomic_embedding_rag.ipynb

@@ -58,7 +58,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install -U langchain-nomic langchain_community tiktoken langchain-openai chromadb langchain"
+    "! pip install -U langchain-nomic langchain-chroma langchain-community tiktoken langchain-openai langchain"
    ]
   },
   {
@@ -167,7 +167,7 @@
    "source": [
     "import os\n",
     "\n",
-    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_core.output_parsers import StrOutputParser\n",
     "from langchain_core.runnables import RunnableLambda, RunnablePassthrough\n",
     "from langchain_nomic import NomicEmbeddings\n",

cookbook/nomic_multimodal_rag.ipynb

@@ -56,7 +56,7 @@
    },
    "outputs": [],
    "source": [
-    "! pip install -U langchain-nomic langchain_community tiktoken langchain-openai chromadb langchain # (newest versions required for multi-modal)"
+    "! pip install -U langchain-nomic langchain-chroma langchain-community tiktoken langchain-openai langchain # (newest versions required for multi-modal)"
    ]
   },
   {
@@ -194,7 +194,7 @@
     "\n",
     "import chromadb\n",
     "import numpy as np\n",
-    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_nomic import NomicEmbeddings\n",
     "from PIL import Image as _PILImage\n",
     "\n",

cookbook/openai_functions_retrieval_qa.ipynb

@@ -20,8 +20,8 @@
    "outputs": [],
    "source": [
     "from langchain.chains import RetrievalQA\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_community.document_loaders import TextLoader\n",
-    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "from langchain_text_splitters import CharacterTextSplitter"
    ]

cookbook/optimization.ipynb

@@ -80,7 +80,7 @@
    "outputs": [],
    "source": [
     "from langchain.schema import Document\n",
-    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
     "embeddings = OpenAIEmbeddings()"

cookbook/rag_with_quantized_embeddings.ipynb

@@ -36,10 +36,10 @@
     "from bs4 import BeautifulSoup as Soup\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryByteStore, LocalFileStore\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_community.document_loaders.recursive_url_loader import (\n",
     "    RecursiveUrlLoader,\n",
     ")\n",
-    "from langchain_community.vectorstores import Chroma\n",
     "\n",
     "# For our example, we'll load docs from the web\n",
     "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
@@ -370,13 +370,14 @@
    ],
    "source": [
     "import torch\n",
-    "from langchain.llms.huggingface_pipeline import HuggingFacePipeline\n",
-    "from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline\n",
+    "from langchain_huggingface.llms import HuggingFacePipeline\n",
+    "from optimum.intel.ipex import IPEXModelForCausalLM\n",
+    "from transformers import AutoTokenizer, pipeline\n",
     "\n",
     "model_id = \"Intel/neural-chat-7b-v3-3\"\n",
     "tokenizer = AutoTokenizer.from_pretrained(model_id)\n",
-    "model = AutoModelForCausalLM.from_pretrained(\n",
-    "    model_id, device_map=\"auto\", torch_dtype=torch.bfloat16\n",
+    "model = IPEXModelForCausalLM.from_pretrained(\n",
+    "    model_id, torch_dtype=torch.bfloat16, export=True\n",
     ")\n",
     "\n",
     "pipe = pipeline(\"text-generation\", model=model, tokenizer=tokenizer, max_new_tokens=100)\n",
@@ -581,7 +582,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.18"
+   "version": "3.10.14"
   }
  },
  "nbformat": 4,

cookbook/sql_db_qa.mdx

@@ -740,7 +740,7 @@ Even this relatively large model will most likely fail to generate more complica
 
 
 ```bash
-poetry run pip install pyyaml chromadb
+poetry run pip install pyyaml langchain_chroma
 import yaml
 ```
 
@@ -994,7 +994,7 @@ from langchain.prompts import FewShotPromptTemplate, PromptTemplate
 from langchain.chains.sql_database.prompt import _sqlite_prompt, PROMPT_SUFFIX
 from langchain_huggingface import HuggingFaceEmbeddings
 from langchain.prompts.example_selector.semantic_similarity import SemanticSimilarityExampleSelector
-from langchain_community.vectorstores import Chroma
+from langchain_chroma import Chroma
 
 example_prompt = PromptTemplate(
     input_variables=["table_info", "input", "sql_cmd", "sql_result", "answer"],

cookbook/together_ai.ipynb

@@ -22,7 +22,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install --quiet pypdf chromadb tiktoken openai langchain-together"
+    "! pip install --quiet pypdf tiktoken openai langchain-chroma langchain-together"
    ]
   },
   {
@@ -45,8 +45,8 @@
     "all_splits = text_splitter.split_documents(data)\n",
     "\n",
     "# Add to vectorDB\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_community.embeddings import OpenAIEmbeddings\n",
-    "from langchain_community.vectorstores import Chroma\n",
     "\n",
     "\"\"\"\n",
     "from langchain_together.embeddings import TogetherEmbeddings\n",

docs/Makefile

@@ -13,7 +13,12 @@ OUTPUT_NEW_DOCS_DIR = $(OUTPUT_NEW_DIR)/docs
 
 PYTHON = .venv/bin/python
 
-PARTNER_DEPS_LIST := $(shell find ../libs/partners -mindepth 1 -maxdepth 1 -type d -exec test -e "{}/pyproject.toml" \; -print | grep -vE "airbyte|ibm|couchbase" | tr '\n' ' ')
+PARTNER_DEPS_LIST := $(shell find ../libs/partners -mindepth 1 -maxdepth 1 -type d -exec sh -c ' \
+for dir; do \
+    if find "$$dir" -maxdepth 1 -type f \( -name "pyproject.toml" -o -name "setup.py" \) | grep -q .; then \
+        echo "$$dir"; \
+    fi \
+done' sh {} + | grep -vE "airbyte|ibm|couchbase|databricks" | tr '\n' ' ')
 
 PORT ?= 3001
 
@@ -36,9 +41,11 @@ generate-files:
 	cp -r $(SOURCE_DIR)/* $(INTERMEDIATE_DIR)
 	mkdir -p $(INTERMEDIATE_DIR)/templates
 
-	$(PYTHON) scripts/model_feat_table.py $(INTERMEDIATE_DIR)
+	$(PYTHON) scripts/tool_feat_table.py $(INTERMEDIATE_DIR)
 
-	$(PYTHON) scripts/document_loader_feat_table.py $(INTERMEDIATE_DIR)
+	$(PYTHON) scripts/kv_store_feat_table.py $(INTERMEDIATE_DIR)
+
+	$(PYTHON) scripts/partner_pkg_table.py $(INTERMEDIATE_DIR)
 
 	$(PYTHON) scripts/copy_templates.py $(INTERMEDIATE_DIR)
 
@@ -63,16 +70,23 @@ render:
 md-sync:
 	rsync -avm --include="*/" --include="*.mdx" --include="*.md" --include="*.png" --include="*/_category_.yml" --exclude="*" $(INTERMEDIATE_DIR)/ $(OUTPUT_NEW_DOCS_DIR)
 
+append-related:
+	$(PYTHON) scripts/append_related_links.py $(OUTPUT_NEW_DOCS_DIR)
+
 generate-references:
 	$(PYTHON) scripts/generate_api_reference_links.py --docs_dir $(OUTPUT_NEW_DOCS_DIR)
 
-build: install-py-deps generate-files copy-infra render md-sync
+build: install-py-deps generate-files copy-infra render md-sync append-related
 
 vercel-build: install-vercel-deps build generate-references
 	rm -rf docs
 	mv $(OUTPUT_NEW_DOCS_DIR) docs
 	rm -rf build
-	yarn run docusaurus build
+	mkdir static/api_reference
+	git clone --depth=1 https://github.com/baskaryan/langchain-api-docs-build.git
+	mv langchain-api-docs-build/api_reference_build/html/* static/api_reference/
+	rm -rf langchain-api-docs-build
+	NODE_OPTIONS="--max-old-space-size=5000" yarn run docusaurus build
 	mv build v0.2
 	mkdir build
 	mv v0.2 build

docs/api_reference/_extensions/gallery_directive.py

@@ -0,0 +1,144 @@
+"""A directive to generate a gallery of images from structured data.
+
+Generating a gallery of images that are all the same size is a common
+pattern in documentation, and this can be cumbersome if the gallery is
+generated programmatically. This directive wraps this particular use-case
+in a helper-directive to generate it with a single YAML configuration file.
+
+It currently exists for maintainers of the pydata-sphinx-theme,
+but might be abstracted into a standalone package if it proves useful.
+"""
+
+from pathlib import Path
+from typing import Any, ClassVar, Dict, List
+
+from docutils import nodes
+from docutils.parsers.rst import directives
+from sphinx.application import Sphinx
+from sphinx.util import logging
+from sphinx.util.docutils import SphinxDirective
+from yaml import safe_load
+
+logger = logging.getLogger(__name__)
+
+
+TEMPLATE_GRID = """
+`````{{grid}} {columns}
+{options}
+
+{content}
+
+`````
+"""
+
+GRID_CARD = """
+````{{grid-item-card}} {title}
+{options}
+
+{content}
+````
+"""
+
+
+class GalleryGridDirective(SphinxDirective):
+    """A directive to show a gallery of images and links in a Bootstrap grid.
+
+    The grid can be generated from a YAML file that contains a list of items, or
+    from the content of the directive (also formatted in YAML). Use the parameter
+    "class-card" to add an additional CSS class to all cards. When specifying the grid
+    items, you can use all parameters from "grid-item-card" directive to customize
+    individual cards + ["image", "header", "content", "title"].
+
+    Danger:
+        This directive can only be used in the context of a Myst documentation page as
+        the templates use Markdown flavored formatting.
+    """
+
+    name = "gallery-grid"
+    has_content = True
+    required_arguments = 0
+    optional_arguments = 1
+    final_argument_whitespace = True
+    option_spec: ClassVar[dict[str, Any]] = {
+        # A class to be added to the resulting container
+        "grid-columns": directives.unchanged,
+        "class-container": directives.unchanged,
+        "class-card": directives.unchanged,
+    }
+
+    def run(self) -> List[nodes.Node]:
+        """Create the gallery grid."""
+        if self.arguments:
+            # If an argument is given, assume it's a path to a YAML file
+            # Parse it and load it into the directive content
+            path_data_rel = Path(self.arguments[0])
+            path_doc, _ = self.get_source_info()
+            path_doc = Path(path_doc).parent
+            path_data = (path_doc / path_data_rel).resolve()
+            if not path_data.exists():
+                logger.info(f"Could not find grid data at {path_data}.")
+                nodes.text("No grid data found at {path_data}.")
+                return
+            yaml_string = path_data.read_text()
+        else:
+            yaml_string = "\n".join(self.content)
+
+        # Use all the element with an img-bottom key as sites to show
+        # and generate a card item for each of them
+        grid_items = []
+        for item in safe_load(yaml_string):
+            # remove parameters that are not needed for the card options
+            title = item.pop("title", "")
+
+            # build the content of the card using some extra parameters
+            header = f"{item.pop('header')}  \n^^^  \n" if "header" in item else ""
+            image = f"![image]({item.pop('image')})  \n" if "image" in item else ""
+            content = f"{item.pop('content')}  \n" if "content" in item else ""
+
+            # optional parameter that influence all cards
+            if "class-card" in self.options:
+                item["class-card"] = self.options["class-card"]
+
+            loc_options_str = "\n".join(f":{k}: {v}" for k, v in item.items()) + "  \n"
+
+            card = GRID_CARD.format(
+                options=loc_options_str, content=header + image + content, title=title
+            )
+            grid_items.append(card)
+
+        # Parse the template with Sphinx Design to create an output container
+        # Prep the options for the template grid
+        class_ = "gallery-directive" + f' {self.options.get("class-container", "")}'
+        options = {"gutter": 2, "class-container": class_}
+        options_str = "\n".join(f":{k}: {v}" for k, v in options.items())
+
+        # Create the directive string for the grid
+        grid_directive = TEMPLATE_GRID.format(
+            columns=self.options.get("grid-columns", "1 2 3 4"),
+            options=options_str,
+            content="\n".join(grid_items),
+        )
+
+        # Parse content as a directive so Sphinx Design processes it
+        container = nodes.container()
+        self.state.nested_parse([grid_directive], 0, container)
+
+        # Sphinx Design outputs a container too, so just use that
+        return [container.children[0]]
+
+
+def setup(app: Sphinx) -> Dict[str, Any]:
+    """Add custom configuration to sphinx app.
+
+    Args:
+        app: the Sphinx application
+
+    Returns:
+        the 2 parallel parameters set to ``True``.
+    """
+    app.add_directive("gallery-grid", GalleryGridDirective)
+
+    return {
+        "parallel_read_safe": True,
+        "parallel_write_safe": True,
+    }

docs/api_reference/_static/css/custom.css

@@ -1,26 +1,411 @@
-pre {
-  white-space: break-spaces;
+@import url('https://fonts.googleapis.com/css2?family=Inter:wght@400;700&display=swap');
+
+/*******************************************************************************
+* master color map. Only the colors that actually differ between light and dark
+* themes are specified separately.
+*
+* To see the full list of colors see https://www.figma.com/file/rUrrHGhUBBIAAjQ82x6pz9/PyData-Design-system---proposal-for-implementation-(2)?node-id=1234%3A765&t=ifcFT1JtnrSshGfi-1
+*/
+/**
+* Function to get items from nested maps
+*/
+/* Assign base colors for the PyData theme */
+:root {
+  --pst-teal-50: #f4fbfc;
+  --pst-teal-100: #e9f6f8;
+  --pst-teal-200: #d0ecf1;
+  --pst-teal-300: #abdde6;
+  --pst-teal-400: #3fb1c5;
+  --pst-teal-500: #0a7d91;
+  --pst-teal-600: #085d6c;
+  --pst-teal-700: #064752;
+  --pst-teal-800: #042c33;
+  --pst-teal-900: #021b1f;
+  --pst-violet-50: #f4eefb;
+  --pst-violet-100: #e0c7ff;
+  --pst-violet-200: #d5b4fd;
+  --pst-violet-300: #b780ff;
+  --pst-violet-400: #9c5ffd;
+  --pst-violet-500: #8045e5;
+  --pst-violet-600: #6432bd;
+  --pst-violet-700: #4b258f;
+  --pst-violet-800: #341a61;
+  --pst-violet-900: #1e0e39;
+  --pst-gray-50: #f9f9fa;
+  --pst-gray-100: #f3f4f5;
+  --pst-gray-200: #e5e7ea;
+  --pst-gray-300: #d1d5da;
+  --pst-gray-400: #9ca4af;
+  --pst-gray-500: #677384;
+  --pst-gray-600: #48566b;
+  --pst-gray-700: #29313d;
+  --pst-gray-800: #222832;
+  --pst-gray-900: #14181e;
+  --pst-pink-50: #fcf8fd;
+  --pst-pink-100: #fcf0fa;
+  --pst-pink-200: #f8dff5;
+  --pst-pink-300: #f3c7ee;
+  --pst-pink-400: #e47fd7;
+  --pst-pink-500: #c132af;
+  --pst-pink-600: #912583;
+  --pst-pink-700: #6e1c64;
+  --pst-pink-800: #46123f;
+  --pst-pink-900: #2b0b27;
+  --pst-foundation-white: #ffffff;
+  --pst-foundation-black: #14181e;
+  --pst-green-10: #f1fdfd;
+  --pst-green-50: #E0F7F6;
+  --pst-green-100: #B3E8E6;
+  --pst-green-200: #80D6D3;
+  --pst-green-300: #4DC4C0;
+  --pst-green-400: #4FB2AD;
+  --pst-green-500: #287977;
+  --pst-green-600: #246161;
+  --pst-green-700: #204F4F;
+  --pst-green-800: #1C3C3C;
+  --pst-green-900: #0D2427;
+  --pst-lilac-50: #f4eefb;
+  --pst-lilac-100: #DAD6FE;
+  --pst-lilac-200: #BCB2FD;
+  --pst-lilac-300: #9F8BFA;
+  --pst-lilac-400: #7F5CF6;
+  --pst-lilac-500: #6F3AED;
+  --pst-lilac-600: #6028D9;
+  --pst-lilac-700: #5021B6;
+  --pst-lilac-800: #431D95;
+  --pst-lilac-900: #1e0e39;
+  --pst-header-height: 2.5rem;
 }
 
-@media (min-width: 1200px) {
-  .container,
-  .container-lg,
-  .container-md,
-  .container-sm,
-  .container-xl {
-    max-width: 2560px !important;
-  }
+html {
+    --pst-font-family-base: 'Inter';
+    --pst-font-family-heading: 'Inter Tight', sans-serif;
 }
 
-#my-component-root *,
-#headlessui-portal-root * {
-  z-index: 10000;
+/*******************************************************************************
+* write the color rules for each theme (light/dark)
+*/
+/* NOTE:
+ * Mixins enable us to reuse the same definitions for the different modes
+ * https://sass-lang.com/documentation/at-rules/mixin
+ * something inserts a variable into a CSS selector or property name
+ * https://sass-lang.com/documentation/interpolation
+ */
+/* Defaults to light mode if data-theme is not set */
+html:not([data-theme]) {
+  --pst-color-primary: #287977;
+  --pst-color-primary-bg: #80D6D3;
+  --pst-color-secondary: #6F3AED;
+  --pst-color-secondary-bg: #DAD6FE;
+  --pst-color-accent: #c132af;
+  --pst-color-accent-bg: #f8dff5;
+  --pst-color-info: #276be9;
+  --pst-color-info-bg: #dce7fc;
+  --pst-color-warning: #f66a0a;
+  --pst-color-warning-bg: #f8e3d0;
+  --pst-color-success: #00843f;
+  --pst-color-success-bg: #d6ece1;
+  --pst-color-attention: var(--pst-color-warning);
+  --pst-color-attention-bg: var(--pst-color-warning-bg);
+  --pst-color-danger: #d72d47;
+  --pst-color-danger-bg: #f9e1e4;
+  --pst-color-text-base: #222832;
+  --pst-color-text-muted: #48566b;
+  --pst-color-heading-color: #ffffff;
+  --pst-color-shadow: rgba(0, 0, 0, 0.1);
+  --pst-color-border: #d1d5da;
+  --pst-color-border-muted: rgba(23, 23, 26, 0.2);
+  --pst-color-inline-code: #912583;
+  --pst-color-inline-code-links: #246161;
+  --pst-color-target: #f3cf95;
+  --pst-color-background: #ffffff;
+  --pst-color-on-background: #F4F9F8;
+  --pst-color-surface: #F4F9F8;
+  --pst-color-on-surface: #222832;
+}
+html:not([data-theme]) {
+  --pst-color-link: var(--pst-color-primary);
+  --pst-color-link-hover: var(--pst-color-secondary);
+}
+html:not([data-theme]) .only-dark,
+html:not([data-theme]) .only-dark ~ figcaption {
+  display: none !important;
 }
 
-table.longtable code {
-  white-space: normal;
+/* NOTE: @each {...} is like a for-loop
+ * https://sass-lang.com/documentation/at-rules/control/each
+ */
+html[data-theme=light] {
+  --pst-color-primary: #287977;
+  --pst-color-primary-bg: #80D6D3;
+  --pst-color-secondary: #6F3AED;
+  --pst-color-secondary-bg: #DAD6FE;
+  --pst-color-accent: #c132af;
+  --pst-color-accent-bg: #f8dff5;
+  --pst-color-info: #276be9;
+  --pst-color-info-bg: #dce7fc;
+  --pst-color-warning: #f66a0a;
+  --pst-color-warning-bg: #f8e3d0;
+  --pst-color-success: #00843f;
+  --pst-color-success-bg: #d6ece1;
+  --pst-color-attention: var(--pst-color-warning);
+  --pst-color-attention-bg: var(--pst-color-warning-bg);
+  --pst-color-danger: #d72d47;
+  --pst-color-danger-bg: #f9e1e4;
+  --pst-color-text-base: #222832;
+  --pst-color-text-muted: #48566b;
+  --pst-color-heading-color: #ffffff;
+  --pst-color-shadow: rgba(0, 0, 0, 0.1);
+  --pst-color-border: #d1d5da;
+  --pst-color-border-muted: rgba(23, 23, 26, 0.2);
+  --pst-color-inline-code: #912583;
+  --pst-color-inline-code-links: #246161;
+  --pst-color-target: #f3cf95;
+  --pst-color-background: #ffffff;
+  --pst-color-on-background: #F4F9F8;
+  --pst-color-surface: #F4F9F8;
+  --pst-color-on-surface: #222832;
+  color-scheme: light;
+}
+html[data-theme=light] {
+  --pst-color-link: var(--pst-color-primary);
+  --pst-color-link-hover: var(--pst-color-secondary);
+}
+html[data-theme=light] .only-dark,
+html[data-theme=light] .only-dark ~ figcaption {
+  display: none !important;
 }
 
-table.longtable td {
-  max-width: 600px;
+html[data-theme=dark] {
+  --pst-color-primary: #4FB2AD;
+  --pst-color-primary-bg: #1C3C3C;
+  --pst-color-secondary: #7F5CF6;
+  --pst-color-secondary-bg: #431D95;
+  --pst-color-accent: #e47fd7;
+  --pst-color-accent-bg: #46123f;
+  --pst-color-info: #79a3f2;
+  --pst-color-info-bg: #06245d;
+  --pst-color-warning: #ff9245;
+  --pst-color-warning-bg: #652a02;
+  --pst-color-success: #5fb488;
+  --pst-color-success-bg: #002f17;
+  --pst-color-attention: var(--pst-color-warning);
+  --pst-color-attention-bg: var(--pst-color-warning-bg);
+  --pst-color-danger: #e78894;
+  --pst-color-danger-bg: #4e111b;
+  --pst-color-text-base: #ced6dd;
+  --pst-color-text-muted: #9ca4af;
+  --pst-color-heading-color: #14181e;
+  --pst-color-shadow: rgba(0, 0, 0, 0.2);
+  --pst-color-border: #48566b;
+  --pst-color-border-muted: #29313d;
+  --pst-color-inline-code: #f3c7ee;
+  --pst-color-inline-code-links: #4FB2AD;
+  --pst-color-target: #675c04;
+  --pst-color-background: #14181e;
+  --pst-color-on-background: #222832;
+  --pst-color-surface: #29313d;
+  --pst-color-on-surface: #f3f4f5;
+  /* Adjust images in dark mode (unless they have class .only-dark or
+   * .dark-light, in which case assume they're already optimized for dark
+   * mode).
+   */
+  /* Give images a light background in dark mode in case they have
+  *  transparency and black text (unless they have class .only-dark or .dark-light, in
+  *  which case assume they're already optimized for dark mode).
+  */
+  color-scheme: dark;
 }
+html[data-theme=dark] {
+  --pst-color-link: var(--pst-color-primary);
+  --pst-color-link-hover: var(--pst-color-secondary);
+}
+html[data-theme=dark] .only-light,
+html[data-theme=dark] .only-light ~ figcaption {
+  display: none !important;
+}
+html[data-theme=dark] img:not(.only-dark):not(.dark-light) {
+  filter: brightness(0.8) contrast(1.2);
+}
+html[data-theme=dark] .bd-content img:not(.only-dark):not(.dark-light) {
+  background: rgb(255, 255, 255);
+  border-radius: 0.25rem;
+}
+html[data-theme=dark] .MathJax_SVG * {
+  fill: var(--pst-color-text-base);
+}
+
+.pst-color-primary {
+  color: var(--pst-color-primary);
+}
+
+.pst-color-secondary {
+  color: var(--pst-color-secondary);
+}
+
+.pst-color-accent {
+  color: var(--pst-color-accent);
+}
+
+.pst-color-info {
+  color: var(--pst-color-info);
+}
+
+.pst-color-warning {
+  color: var(--pst-color-warning);
+}
+
+.pst-color-success {
+  color: var(--pst-color-success);
+}
+
+.pst-color-attention {
+  color: var(--pst-color-attention);
+}
+
+.pst-color-danger {
+  color: var(--pst-color-danger);
+}
+
+.pst-color-text-base {
+  color: var(--pst-color-text-base);
+}
+
+.pst-color-text-muted {
+  color: var(--pst-color-text-muted);
+}
+
+.pst-color-heading-color {
+  color: var(--pst-color-heading-color);
+}
+
+.pst-color-shadow {
+  color: var(--pst-color-shadow);
+}
+
+.pst-color-border {
+  color: var(--pst-color-border);
+}
+
+.pst-color-border-muted {
+  color: var(--pst-color-border-muted);
+}
+
+.pst-color-inline-code {
+  color: var(--pst-color-inline-code);
+}
+
+.pst-color-inline-code-links {
+  color: var(--pst-color-inline-code-links);
+}
+
+.pst-color-target {
+  color: var(--pst-color-target);
+}
+
+.pst-color-background {
+  color: var(--pst-color-background);
+}
+
+.pst-color-on-background {
+  color: var(--pst-color-on-background);
+}
+
+.pst-color-surface {
+  color: var(--pst-color-surface);
+}
+
+.pst-color-on-surface {
+  color: var(--pst-color-on-surface);
+}
+
+
+
+/* Adjust the height of the navbar */
+.bd-header .bd-header__inner{
+    height: 52px; /* Adjust this value as needed */
+}
+
+.navbar-nav > li > a {
+    line-height: 52px; /* Vertically center the navbar links */
+}
+
+/* Make sure the navbar items align properly */
+.navbar-nav {
+    display: flex;
+}
+
+
+.bd-header .navbar-header-items__start{
+  margin-left: 0rem
+}
+
+.bd-header button.primary-toggle {
+  margin-right: 0rem;
+}
+
+.bd-header ul.navbar-nav .dropdown .dropdown-menu {
+  overflow-y: auto; /* Enable vertical scrolling */
+  max-height: 80vh
+}
+
+.bd-sidebar-primary {
+    width: 22%;  /* Adjust this value to your preference */
+    line-height: 1.4;
+}
+
+.bd-sidebar-secondary {
+    line-height: 1.4;
+}
+
+.toc-entry a.nav-link, .toc-entry a>code {  
+  background-color: transparent;
+  border-color: transparent;
+}
+
+.bd-sidebar-primary code{
+  background-color: transparent;
+  border-color: transparent;
+}
+
+
+.toctree-wrapper li[class^=toctree-l1]>a {
+  font-size: 1.3em
+}
+
+.toctree-wrapper li[class^=toctree-l1] {
+  margin-bottom: 2em;
+}
+
+.toctree-wrapper li[class^=toctree-l]>ul {
+  margin-top: 0.5em;
+  font-size: 0.9em;
+}
+
+*, :after, :before {
+  font-style: normal;
+}
+
+div.deprecated {
+  margin-top: 0.5em;
+  margin-bottom: 2em;
+}
+
+.admonition-beta.admonition, div.admonition-beta.admonition {
+  border-color: var(--pst-color-warning);
+  margin-top:0.5em;
+  margin-bottom: 2em;
+}
+
+.admonition-beta>.admonition-title, div.admonition-beta>.admonition-title {
+  background-color: var(--pst-color-warning-bg);
+}
+
+dl[class]:not(.option-list):not(.field-list):not(.footnote):not(.glossary):not(.simple) dd {
+  margin-left: 1rem;
+}
+
+p {
+  font-size: 0.9rem;
+  margin-bottom: 0.5rem;
+}

docs/api_reference/_static/wordmark-api-dark.svg

@@ -0,0 +1,11 @@
+<svg width="72" height="19" viewBox="0 0 72 19" fill="none" xmlns="http://www.w3.org/2000/svg">
+<g clip-path="url(#clip0_4019_2020)">
+<path d="M29.4038 5.84477C30.1256 6.56657 30.1256 7.74117 29.4038 8.46296L27.7869 10.0538L27.7704 9.96259C27.6524 9.30879 27.3415 8.71552 26.8723 8.24627C26.5189 7.8936 26.1012 7.63282 25.6305 7.47143C25.3383 7.76508 25.1777 8.14989 25.1777 8.55487C25.1777 8.63706 25.1851 8.72224 25.2001 8.80742C25.4593 8.90082 25.6887 9.04503 25.8815 9.23781C26.6033 9.9596 26.6033 11.1342 25.8815 11.856L24.4738 13.2637C24.1129 13.6246 23.6392 13.8047 23.1647 13.8047C22.6902 13.8047 22.2165 13.6246 21.8556 13.2637C21.1338 12.5419 21.1338 11.3673 21.8556 10.6455L23.4725 9.05549L23.489 9.14665C23.6063 9.79896 23.9171 10.3922 24.3879 10.8622C24.742 11.2164 25.1343 11.4518 25.6043 11.6124L25.691 11.5257C25.954 11.2627 26.0982 10.913 26.0982 10.5402C26.0982 10.4572 26.0907 10.3743 26.0765 10.2929C25.8053 10.2032 25.5819 10.0754 25.3786 9.87218C25.0857 9.57928 24.9034 9.20493 24.8526 8.79024C24.8489 8.76035 24.8466 8.73121 24.8437 8.70132C24.8033 8.16109 24.9983 7.63357 25.3786 7.25399L26.7864 5.84627C27.1353 5.49733 27.6001 5.30455 28.0955 5.30455C28.5909 5.30455 29.0556 5.49658 29.4046 5.84627L29.4038 5.84477ZM36.7548 9.56583C36.7548 14.7163 32.5645 18.9058 27.4148 18.9058H9.34C4.1903 18.9058 0 14.7163 0 9.56583C0 4.41538 4.1903 0.22583 9.34 0.22583H27.4148C32.5652 0.22583 36.7548 4.41613 36.7548 9.56583ZM18 14.25C18.1472 14.0714 17.4673 13.5686 17.3283 13.384C17.0459 13.0777 17.0444 12.6368 16.8538 12.2789C16.3876 11.1985 15.8518 10.1262 15.1024 9.21166C14.3104 8.21116 13.333 7.38326 12.4745 6.44403C11.8371 5.78873 11.6668 4.85548 11.1041 4.15087C10.3285 3.00541 7.87624 2.69308 7.51683 4.31077C7.51833 4.36158 7.50264 4.39371 7.45855 4.42584C7.2598 4.57005 7.08271 4.73518 6.93402 4.93468C6.57013 5.44129 6.51409 6.30057 6.96839 6.75561C6.98333 6.51576 6.99155 6.28936 7.18134 6.1175C7.53252 6.41862 8.06304 6.52547 8.47026 6.30057C9.36989 7.585 9.14573 9.36184 9.86005 10.7457C10.0573 11.0729 10.2561 11.4069 10.5094 11.6939C10.7148 12.0137 11.4247 12.391 11.4665 12.6869C11.474 13.195 11.4142 13.7502 11.7475 14.1753C11.9044 14.4936 11.5188 14.8134 11.208 14.7738C10.8045 14.8291 10.3121 14.5026 9.95868 14.7036C9.8339 14.8388 9.58957 14.6894 9.48197 14.8769C9.44461 14.9741 9.24286 15.1108 9.36316 15.2042C9.49691 15.1026 9.62095 14.9965 9.80102 15.057C9.77412 15.2035 9.88994 15.2244 9.98184 15.267C9.97886 15.3663 9.92057 15.468 9.99679 15.5524C10.0857 15.4627 10.1388 15.3357 10.28 15.2983C10.7492 15.9238 11.2267 14.6655 12.2421 15.2318C12.0359 15.2214 11.8528 15.2475 11.7139 15.4172C11.6795 15.4553 11.6503 15.5001 11.7109 15.5494C12.2586 15.196 12.2556 15.6705 12.6112 15.5248C12.8847 15.382 13.1567 15.2035 13.4817 15.2543C13.1657 15.3454 13.153 15.5995 12.9677 15.8139C12.9363 15.8468 12.9213 15.8842 12.9579 15.9387C13.614 15.8834 13.6678 15.6652 14.1975 15.3977C14.5928 15.1564 14.9866 15.7414 15.3288 15.4082C15.4043 15.3357 15.5074 15.3604 15.6008 15.3507C15.4812 14.7133 14.1669 15.4672 14.1878 14.6124C14.6107 14.3247 14.5136 13.7741 14.542 13.3295C15.0284 13.5992 15.5694 13.7561 16.0461 14.0139C16.2867 14.4025 16.6641 14.9158 17.1669 14.8822C17.1804 14.8433 17.1923 14.8089 17.2065 14.7693C17.359 14.7955 17.5547 14.8964 17.6384 14.7036C17.8663 14.9419 18.201 14.93 18.4992 14.8687C18.7196 14.6894 18.0845 14.4338 17.9993 14.2493L18 14.25ZM31.3458 7.15387C31.3458 6.28413 31.0081 5.46744 30.3946 4.85399C29.7812 4.24054 28.9645 3.9028 28.094 3.9028C27.2235 3.9028 26.4068 4.24054 25.7933 4.85399L24.3856 6.26171C24.0569 6.59048 23.8073 6.97678 23.6436 7.40941L23.6339 7.43407L23.6085 7.44154C23.0974 7.5992 22.6469 7.86969 22.2696 8.24702L20.8618 9.65475C19.5938 10.9235 19.5938 12.9873 20.8618 14.2553C21.4753 14.8687 22.292 15.2064 23.1617 15.2064C24.0314 15.2064 24.8489 14.8687 25.4623 14.2553L26.8701 12.8475C27.1973 12.5203 27.4454 12.1355 27.609 11.7036L27.6188 11.6789L27.6442 11.6707C28.1463 11.5168 28.6095 11.2373 28.9854 10.8622L30.3931 9.4545C31.0066 8.84105 31.3443 8.02436 31.3443 7.15387H31.3458ZM12.8802 13.1972C12.7592 13.6695 12.7196 14.4742 12.1054 14.4974C12.0546 14.7701 12.2944 14.8724 12.5119 14.785C12.7278 14.6856 12.8302 14.8635 12.9026 15.0406C13.2359 15.0891 13.7291 14.9292 13.7477 14.5347C13.2501 14.2478 13.0962 13.7023 12.8795 13.1972H12.8802Z" fill="#F4F3FF"/>
+<path d="M43.5142 15.2258L47.1462 3.70583H49.9702L53.6022 15.2258H51.6182L48.3222 4.88983H48.7542L45.4982 15.2258H43.5142ZM45.5382 12.7298V10.9298H51.5862V12.7298H45.5382ZM55.0486 15.2258V3.70583H59.8086C59.9206 3.70583 60.0646 3.71116 60.2406 3.72183C60.4166 3.72716 60.5792 3.74316 60.7286 3.76983C61.3952 3.87116 61.9446 4.0925 62.3766 4.43383C62.8139 4.77516 63.1366 5.20716 63.3446 5.72983C63.5579 6.24716 63.6646 6.82316 63.6646 7.45783C63.6646 8.08716 63.5579 8.66316 63.3446 9.18583C63.1312 9.70316 62.8059 10.1325 62.3686 10.4738C61.9366 10.8152 61.3899 11.0365 60.7286 11.1378C60.5792 11.1592 60.4139 11.1752 60.2326 11.1858C60.0566 11.1965 59.9152 11.2018 59.8086 11.2018H56.9766V15.2258H55.0486ZM56.9766 9.40183H59.7286C59.8352 9.40183 59.9552 9.3965 60.0886 9.38583C60.2219 9.37516 60.3446 9.35383 60.4566 9.32183C60.7766 9.24183 61.0272 9.1005 61.2086 8.89783C61.3952 8.69516 61.5259 8.46583 61.6006 8.20983C61.6806 7.95383 61.7206 7.70316 61.7206 7.45783C61.7206 7.2125 61.6806 6.96183 61.6006 6.70583C61.5259 6.4445 61.3952 6.2125 61.2086 6.00983C61.0272 5.80716 60.7766 5.66583 60.4566 5.58583C60.3446 5.55383 60.2219 5.53516 60.0886 5.52983C59.9552 5.51916 59.8352 5.51383 59.7286 5.51383H56.9766V9.40183ZM65.4273 15.2258V3.70583H67.3553V15.2258H65.4273Z" fill="#F4F3FF"/>
+</g>
+<defs>
+<clipPath id="clip0_4019_2020">
+<rect width="71.0711" height="18.68" fill="white" transform="translate(0 0.22583)"/>
+</clipPath>
+</defs>
+</svg>

docs/api_reference/_static/wordmark-api.svg

@@ -0,0 +1,11 @@
+<svg width="72" height="20" viewBox="0 0 72 20" fill="none" xmlns="http://www.w3.org/2000/svg">
+<g clip-path="url(#clip0_4019_689)">
+<path d="M29.4038 5.97905C30.1256 6.70085 30.1256 7.87545 29.4038 8.59724L27.7869 10.188L27.7704 10.0969C27.6524 9.44307 27.3415 8.84979 26.8723 8.38055C26.5189 8.02787 26.1012 7.7671 25.6305 7.60571C25.3383 7.89936 25.1777 8.28416 25.1777 8.68915C25.1777 8.77134 25.1851 8.85652 25.2001 8.9417C25.4593 9.0351 25.6887 9.17931 25.8815 9.37209C26.6033 10.0939 26.6033 11.2685 25.8815 11.9903L24.4738 13.398C24.1129 13.7589 23.6392 13.939 23.1647 13.939C22.6902 13.939 22.2165 13.7589 21.8556 13.398C21.1338 12.6762 21.1338 11.5016 21.8556 10.7798L23.4725 9.18977L23.489 9.28093C23.6063 9.93323 23.9171 10.5265 24.3879 10.9965C24.742 11.3507 25.1343 11.586 25.6043 11.7467L25.691 11.66C25.954 11.397 26.0982 11.0473 26.0982 10.6745C26.0982 10.5915 26.0907 10.5086 26.0765 10.4271C25.8053 10.3375 25.5819 10.2097 25.3786 10.0065C25.0857 9.71356 24.9034 9.33921 24.8526 8.92451C24.8489 8.89463 24.8466 8.86549 24.8437 8.8356C24.8033 8.29537 24.9983 7.76785 25.3786 7.38827L26.7864 5.98055C27.1353 5.6316 27.6001 5.43883 28.0955 5.43883C28.5909 5.43883 29.0556 5.63086 29.4046 5.98055L29.4038 5.97905ZM36.7548 9.70011C36.7548 14.8506 32.5645 19.0401 27.4148 19.0401H9.34C4.1903 19.0401 0 14.8506 0 9.70011C0 4.54966 4.1903 0.360107 9.34 0.360107H27.4148C32.5652 0.360107 36.7548 4.55041 36.7548 9.70011ZM18 14.3843C18.1472 14.2057 17.4673 13.7029 17.3283 13.5183C17.0459 13.2119 17.0444 12.7711 16.8538 12.4132C16.3876 11.3327 15.8518 10.2605 15.1024 9.34594C14.3104 8.34543 13.333 7.51754 12.4745 6.57831C11.8371 5.92301 11.6668 4.98976 11.1041 4.28515C10.3285 3.13969 7.87624 2.82736 7.51683 4.44505C7.51833 4.49586 7.50264 4.52799 7.45855 4.56012C7.2598 4.70433 7.08271 4.86946 6.93402 5.06896C6.57013 5.57556 6.51409 6.43484 6.96839 6.88989C6.98333 6.65004 6.99155 6.42364 7.18134 6.25178C7.53252 6.5529 8.06304 6.65975 8.47026 6.43484C9.36989 7.71928 9.14573 9.49612 9.86005 10.8799C10.0573 11.2072 10.2561 11.5412 10.5094 11.8281C10.7148 12.1479 11.4247 12.5253 11.4665 12.8212C11.474 13.3293 11.4142 13.8844 11.7475 14.3096C11.9044 14.6279 11.5188 14.9477 11.208 14.9081C10.8045 14.9634 10.3121 14.6369 9.95868 14.8379C9.8339 14.9731 9.58957 14.8237 9.48197 15.0112C9.44461 15.1083 9.24286 15.2451 9.36316 15.3385C9.49691 15.2369 9.62095 15.1308 9.80102 15.1913C9.77412 15.3377 9.88994 15.3587 9.98184 15.4012C9.97886 15.5006 9.92057 15.6022 9.99679 15.6867C10.0857 15.597 10.1388 15.47 10.28 15.4326C10.7492 16.058 11.2267 14.7997 12.2421 15.3661C12.0359 15.3557 11.8528 15.3818 11.7139 15.5514C11.6795 15.5895 11.6503 15.6344 11.7109 15.6837C12.2586 15.3303 12.2556 15.8047 12.6112 15.659C12.8847 15.5163 13.1567 15.3377 13.4817 15.3885C13.1657 15.4797 13.153 15.7337 12.9677 15.9482C12.9363 15.9811 12.9213 16.0184 12.9579 16.073C13.614 16.0177 13.6678 15.7995 14.1975 15.532C14.5928 15.2907 14.9866 15.8757 15.3288 15.5425C15.4043 15.47 15.5074 15.4946 15.6008 15.4849C15.4812 14.8476 14.1669 15.6015 14.1878 14.7467C14.6107 14.459 14.5136 13.9083 14.542 13.4638C15.0284 13.7335 15.5694 13.8904 16.0461 14.1482C16.2867 14.5367 16.6641 15.0501 17.1669 15.0164C17.1804 14.9776 17.1923 14.9432 17.2065 14.9036C17.359 14.9298 17.5547 15.0306 17.6384 14.8379C17.8663 15.0762 18.201 15.0643 18.4992 15.003C18.7196 14.8237 18.0845 14.5681 17.9993 14.3836L18 14.3843ZM31.3458 7.28815C31.3458 6.41841 31.0081 5.60172 30.3946 4.98826C29.7812 4.37481 28.9645 4.03708 28.094 4.03708C27.2235 4.03708 26.4068 4.37481 25.7933 4.98826L24.3856 6.39599C24.0569 6.72476 23.8073 7.11106 23.6436 7.54369L23.6339 7.56835L23.6085 7.57582C23.0974 7.73348 22.6469 8.00396 22.2696 8.3813L20.8618 9.78902C19.5938 11.0578 19.5938 13.1215 20.8618 14.3895C21.4753 15.003 22.292 15.3407 23.1617 15.3407C24.0314 15.3407 24.8489 15.003 25.4623 14.3895L26.8701 12.9818C27.1973 12.6545 27.4454 12.2697 27.609 11.8378L27.6188 11.8132L27.6442 11.805C28.1463 11.651 28.6095 11.3716 28.9854 10.9965L30.3931 9.58878C31.0066 8.97532 31.3443 8.15863 31.3443 7.28815H31.3458ZM12.8802 13.3315C12.7592 13.8037 12.7196 14.6085 12.1054 14.6316C12.0546 14.9044 12.2944 15.0067 12.5119 14.9193C12.7278 14.8199 12.8302 14.9978 12.9026 15.1748C13.2359 15.2234 13.7291 15.0635 13.7477 14.669C13.2501 14.3821 13.0962 13.8366 12.8795 13.3315H12.8802Z" fill="#246161"/>
+<path d="M43.5142 15.3601L47.1462 3.84011H49.9702L53.6022 15.3601H51.6182L48.3222 5.02411H48.7542L45.4982 15.3601H43.5142ZM45.5382 12.8641V11.0641H51.5862V12.8641H45.5382ZM55.0486 15.3601V3.84011H59.8086C59.9206 3.84011 60.0646 3.84544 60.2406 3.85611C60.4166 3.86144 60.5792 3.87744 60.7286 3.90411C61.3952 4.00544 61.9446 4.22677 62.3766 4.56811C62.8139 4.90944 63.1366 5.34144 63.3446 5.86411C63.5579 6.38144 63.6646 6.95744 63.6646 7.59211C63.6646 8.22144 63.5579 8.79744 63.3446 9.32011C63.1312 9.83744 62.8059 10.2668 62.3686 10.6081C61.9366 10.9494 61.3899 11.1708 60.7286 11.2721C60.5792 11.2934 60.4139 11.3094 60.2326 11.3201C60.0566 11.3308 59.9152 11.3361 59.8086 11.3361H56.9766V15.3601H55.0486ZM56.9766 9.53611H59.7286C59.8352 9.53611 59.9552 9.53077 60.0886 9.52011C60.2219 9.50944 60.3446 9.48811 60.4566 9.45611C60.7766 9.37611 61.0272 9.23477 61.2086 9.03211C61.3952 8.82944 61.5259 8.60011 61.6006 8.34411C61.6806 8.08811 61.7206 7.83744 61.7206 7.59211C61.7206 7.34677 61.6806 7.09611 61.6006 6.84011C61.5259 6.57877 61.3952 6.34677 61.2086 6.14411C61.0272 5.94144 60.7766 5.80011 60.4566 5.72011C60.3446 5.68811 60.2219 5.66944 60.0886 5.66411C59.9552 5.65344 59.8352 5.64811 59.7286 5.64811H56.9766V9.53611ZM65.4273 15.3601V3.84011H67.3553V15.3601H65.4273Z" fill="#246161"/>
+</g>
+<defs>
+<clipPath id="clip0_4019_689">
+<rect width="71.0711" height="18.68" fill="white" transform="translate(0 0.360107)"/>
+</clipPath>
+</defs>
+</svg>

docs/api_reference/conf.py

@@ -15,6 +15,8 @@ from pathlib import Path
 
 import toml
 from docutils import nodes
+from docutils.parsers.rst.directives.admonitions import BaseAdmonition
+from docutils.statemachine import StringList
 from sphinx.util.docutils import SphinxDirective
 
 # If extensions (or modules to document with autodoc) are in another directory,
@@ -60,26 +62,41 @@ class ExampleLinksDirective(SphinxDirective):
             item_node.append(para_node)
             list_node.append(item_node)
         if list_node.children:
-            title_node = nodes.title()
+            title_node = nodes.rubric()
             title_node.append(nodes.Text(f"Examples using {class_or_func_name}"))
             return [title_node, list_node]
         return [list_node]
 
 
+class Beta(BaseAdmonition):
+    required_arguments = 0
+    node_class = nodes.admonition
+
+    def run(self):
+        self.content = self.content or StringList(
+            [
+                (
+                    "This feature is in beta. It is actively being worked on, so the "
+                    "API may change."
+                )
+            ]
+        )
+        self.arguments = self.arguments or ["Beta"]
+        return super().run()
+
+
 def setup(app):
     app.add_directive("example_links", ExampleLinksDirective)
+    app.add_directive("beta", Beta)
 
 
 # -- Project information -----------------------------------------------------
 
 project = "🦜🔗 LangChain"
-copyright = "2023, LangChain, Inc."
-author = "LangChain, Inc."
+copyright = "2023, LangChain Inc"
+author = "LangChain, Inc"
 
-version = data["tool"]["poetry"]["version"]
-release = version
-
-html_title = project + " " + version
+html_favicon = "_static/img/brand/favicon.png"
 html_last_updated_fmt = "%b %d, %Y"
 
 
@@ -95,11 +112,13 @@ extensions = [
     "sphinx.ext.napoleon",
     "sphinx.ext.viewcode",
     "sphinxcontrib.autodoc_pydantic",
-    "sphinx_copybutton",
-    "sphinx_panels",
     "IPython.sphinxext.ipython_console_highlighting",
+    "myst_parser",
+    "_extensions.gallery_directive",
+    "sphinx_design",
+    "sphinx_copybutton",
 ]
-source_suffix = [".rst"]
+source_suffix = [".rst", ".md"]
 
 # some autodoc pydantic options are repeated in the actual template.
 # potentially user error, but there may be bugs in the sphinx extension
@@ -131,23 +150,84 @@ exclude_patterns = ["_build", "Thumbs.db", ".DS_Store"]
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
 #
-html_theme = "scikit-learn-modern"
-html_theme_path = ["themes"]
+# The theme to use for HTML and HTML Help pages.
+html_theme = "pydata_sphinx_theme"
 
-# redirects dictionary maps from old links to new links
-html_additional_pages = {}
-redirects = {
-    "index": "langchain_api_reference",
+# Theme options are theme-specific and customize the look and feel of a theme
+# further.  For a list of options available for each theme, see the
+# documentation.
+html_theme_options = {
+    #     # -- General configuration ------------------------------------------------
+    "sidebar_includehidden": True,
+    "use_edit_page_button": False,
+    #     # "analytics": {
+    #     #     "plausible_analytics_domain": "scikit-learn.org",
+    #     #     "plausible_analytics_url": "https://views.scientific-python.org/js/script.js",
+    #     # },
+    #     # If "prev-next" is included in article_footer_items, then setting show_prev_next
+    #     # to True would repeat prev and next links. See
+    #     # https://github.com/pydata/pydata-sphinx-theme/blob/b731dc230bc26a3d1d1bb039c56c977a9b3d25d8/src/pydata_sphinx_theme/theme/pydata_sphinx_theme/layout.html#L118-L129
+    "show_prev_next": False,
+    "search_bar_text": "Search",
+    "navigation_with_keys": True,
+    "collapse_navigation": True,
+    "navigation_depth": 3,
+    "show_nav_level": 1,
+    "show_toc_level": 3,
+    "navbar_align": "left",
+    "header_links_before_dropdown": 5,
+    "header_dropdown_text": "Integrations",
+    "logo": {
+        "image_light": "_static/wordmark-api.svg",
+        "image_dark": "_static/wordmark-api-dark.svg",
+    },
+    "surface_warnings": True,
+    #     # -- Template placement in theme layouts ----------------------------------
+    "navbar_start": ["navbar-logo"],
+    #     # Note that the alignment of navbar_center is controlled by navbar_align
+    "navbar_center": ["navbar-nav"],
+    "navbar_end": ["langchain_docs", "theme-switcher", "navbar-icon-links"],
+    #     # navbar_persistent is persistent right (even when on mobiles)
+    "navbar_persistent": ["search-field"],
+    "article_header_start": ["breadcrumbs"],
+    "article_header_end": [],
+    "article_footer_items": [],
+    "content_footer_items": [],
+    #     # Use html_sidebars that map page patterns to list of sidebar templates
+    #     "primary_sidebar_end": [],
+    "footer_start": ["copyright"],
+    "footer_center": [],
+    "footer_end": [],
+    #     # When specified as a dictionary, the keys should follow glob-style patterns, as in
+    #     # https://www.sphinx-doc.org/en/master/usage/configuration.html#confval-exclude_patterns
+    #     # In particular, "**" specifies the default for all pages
+    #     # Use :html_theme.sidebar_secondary.remove: for file-wide removal
+    #     "secondary_sidebar_items": {"**": ["page-toc", "sourcelink"]},
+    #     "show_version_warning_banner": True,
+    #     "announcement": None,
+    "icon_links": [
+        {
+            # Label for this link
+            "name": "GitHub",
+            # URL where the link will redirect
+            "url": "https://github.com/langchain-ai/langchain",  # required
+            # Icon class (if "type": "fontawesome"), or path to local image (if "type": "local")
+            "icon": "fa-brands fa-square-github",
+            # The type of image to be used (see below for details)
+            "type": "fontawesome",
+        },
+        {
+            "name": "X / Twitter",
+            "url": "https://twitter.com/langchainai",
+            "icon": "fab fa-twitter-square",
+        },
+    ],
+    "icon_links_label": "Quick Links",
+    "external_links": [
+        {"name": "Legacy reference", "url": "https://api.python.langchain.com/"},
+    ],
 }
-for old_link in redirects:
-    html_additional_pages[old_link] = "redirects.html"
 
-partners_dir = Path(__file__).parent.parent.parent / "libs/partners"
-partners = [
-    (p.name, p.name.replace("-", "_") + "_api_reference")
-    for p in partners_dir.iterdir()
-]
-partners = sorted(partners)
 
 html_context = {
     "display_github": True,  # Integrate GitHub
@@ -155,8 +235,6 @@ html_context = {
     "github_repo": "langchain",  # Repo name
     "github_version": "master",  # Version
     "conf_py_path": "/docs/api_reference",  # Path in the checkout to the docs root
-    "redirects": redirects,
-    "partners": partners,
 }
 
 # Add any paths that contain custom static files (such as style sheets) here,
@@ -166,9 +244,7 @@ html_static_path = ["_static"]
 
 # These paths are either relative to html_static_path
 # or fully qualified paths (e.g. https://...)
-html_css_files = [
-    "css/custom.css",
-]
+html_css_files = ["css/custom.css"]
 html_use_index = False
 
 myst_enable_extensions = ["colon_fence"]
@@ -185,3 +261,5 @@ html_baseurl = os.environ.get("READTHEDOCS_CANONICAL_URL", "")
 # Tell Jinja2 templates the build is running on Read the Docs
 if os.environ.get("READTHEDOCS", "") == "True":
     html_context["READTHEDOCS"] = True
+
+master_doc = "index"

docs/api_reference/create_api_rst.py

@@ -38,6 +38,8 @@ class ClassInfo(TypedDict):
     """The kind of the class."""
     is_public: bool
     """Whether the class is public or not."""
+    is_deprecated: bool
+    """Whether the class is deprecated."""
 
 
 class FunctionInfo(TypedDict):
@@ -49,6 +51,8 @@ class FunctionInfo(TypedDict):
     """The fully qualified name of the function."""
     is_public: bool
     """Whether the function is public or not."""
+    is_deprecated: bool
+    """Whether the function is deprecated."""
 
 
 class ModuleMembers(TypedDict):
@@ -121,6 +125,7 @@ def _load_module_members(module_path: str, namespace: str) -> ModuleMembers:
                     qualified_name=f"{namespace}.{name}",
                     kind=kind,
                     is_public=not name.startswith("_"),
+                    is_deprecated=".. deprecated::" in (type_.__doc__ or ""),
                 )
             )
         elif inspect.isfunction(type_):
@@ -129,6 +134,7 @@ def _load_module_members(module_path: str, namespace: str) -> ModuleMembers:
                     name=name,
                     qualified_name=f"{namespace}.{name}",
                     is_public=not name.startswith("_"),
+                    is_deprecated=".. deprecated::" in (type_.__doc__ or ""),
                 )
             )
         else:
@@ -233,7 +239,7 @@ def _construct_doc(
     package_namespace: str,
     members_by_namespace: Dict[str, ModuleMembers],
     package_version: str,
-) -> str:
+) -> List[typing.Tuple[str, str]]:
     """Construct the contents of the reference.rst file for the given package.
 
     Args:
@@ -245,23 +251,62 @@ def _construct_doc(
     Returns:
         The contents of the reference.rst file.
     """
-    full_doc = f"""\
-=======================
-``{package_namespace}`` {package_version}
-=======================
+    docs = []
+    index_doc = f"""\
+:html_theme.sidebar_secondary.remove:
 
+.. currentmodule:: {package_namespace}
+
+.. _{package_namespace}:
+
+======================================
+{package_namespace.replace('_', '-')}: {package_version}
+======================================
+
+.. automodule:: {package_namespace}
+    :no-members:
+    :no-inherited-members:
+
+.. toctree::
+    :hidden:
+    :maxdepth: 2
+    
+"""
+    index_autosummary = """
 """
     namespaces = sorted(members_by_namespace)
 
     for module in namespaces:
+        index_doc += f"    {module}\n"
+        module_doc = f"""\
+.. currentmodule:: {package_namespace}
+
+.. _{package_namespace}_{module}:
+"""
         _members = members_by_namespace[module]
-        classes = [el for el in _members["classes_"] if el["is_public"]]
-        functions = [el for el in _members["functions"] if el["is_public"]]
+        classes = [
+            el
+            for el in _members["classes_"]
+            if el["is_public"] and not el["is_deprecated"]
+        ]
+        functions = [
+            el
+            for el in _members["functions"]
+            if el["is_public"] and not el["is_deprecated"]
+        ]
+        deprecated_classes = [
+            el for el in _members["classes_"] if el["is_public"] and el["is_deprecated"]
+        ]
+        deprecated_functions = [
+            el
+            for el in _members["functions"]
+            if el["is_public"] and el["is_deprecated"]
+        ]
         if not (classes or functions):
             continue
-        section = f":mod:`{package_namespace}.{module}`"
+        section = f":mod:`{module}`"
         underline = "=" * (len(section) + 1)
-        full_doc += f"""\
+        module_doc += f"""
 {section}
 {underline}
 
@@ -269,16 +314,26 @@ def _construct_doc(
     :no-members:
     :no-inherited-members:
 
+"""
+
+        index_autosummary += f"""
+:ref:`{package_namespace}_{module}`
+{'^' * (len(package_namespace) + len(module) + 8)}
 """
 
         if classes:
-            full_doc += f"""\
-Classes
---------------
+            module_doc += f"""\
+**Classes**
+
 .. currentmodule:: {package_namespace}
 
 .. autosummary::
     :toctree: {module}
+"""
+            index_autosummary += """
+**Classes**
+
+.. autosummary::
 """
 
             for class_ in sorted(classes, key=lambda c: c["qualified_name"]):
@@ -295,19 +350,22 @@ Classes
                 else:
                     template = "class.rst"
 
-                full_doc += f"""\
+                module_doc += f"""\
     :template: {template}
     
     {class_["qualified_name"]}
     
+"""
+                index_autosummary += f"""
+    {class_['qualified_name']}
 """
 
         if functions:
             _functions = [f["qualified_name"] for f in functions]
             fstring = "\n    ".join(sorted(_functions))
-            full_doc += f"""\
-Functions
---------------
+            module_doc += f"""\
+**Functions**
+
 .. currentmodule:: {package_namespace}
 
 .. autosummary::
@@ -317,7 +375,80 @@ Functions
     {fstring}
 
 """
-    return full_doc
+
+            index_autosummary += f"""
+**Functions**
+
+.. autosummary::
+
+    {fstring}
+"""
+        if deprecated_classes:
+            module_doc += f"""\
+**Deprecated classes**
+
+.. currentmodule:: {package_namespace}
+
+.. autosummary::
+    :toctree: {module}
+"""
+
+            index_autosummary += """
+**Deprecated classes**
+
+.. autosummary::
+"""
+
+            for class_ in sorted(deprecated_classes, key=lambda c: c["qualified_name"]):
+                if class_["kind"] == "TypedDict":
+                    template = "typeddict.rst"
+                elif class_["kind"] == "enum":
+                    template = "enum.rst"
+                elif class_["kind"] == "Pydantic":
+                    template = "pydantic.rst"
+                elif class_["kind"] == "RunnablePydantic":
+                    template = "runnable_pydantic.rst"
+                elif class_["kind"] == "RunnableNonPydantic":
+                    template = "runnable_non_pydantic.rst"
+                else:
+                    template = "class.rst"
+
+                module_doc += f"""\
+    :template: {template}
+
+    {class_["qualified_name"]}
+
+"""
+                index_autosummary += f"""
+    {class_['qualified_name']}
+"""
+
+        if deprecated_functions:
+            _functions = [f["qualified_name"] for f in deprecated_functions]
+            fstring = "\n    ".join(sorted(_functions))
+            module_doc += f"""\
+**Deprecated functions**
+
+.. currentmodule:: {package_namespace}
+
+.. autosummary::
+    :toctree: {module}
+    :template: function.rst
+
+    {fstring}
+
+"""
+            index_autosummary += f"""
+**Deprecated functions**
+
+.. autosummary::
+
+    {fstring}
+
+"""
+        docs.append((f"{module}.rst", module_doc))
+    docs.append(("index.rst", index_doc + index_autosummary))
+    return docs
 
 
 def _build_rst_file(package_name: str = "langchain") -> None:
@@ -329,13 +460,14 @@ def _build_rst_file(package_name: str = "langchain") -> None:
     package_dir = _package_dir(package_name)
     package_members = _load_package_modules(package_dir)
     package_version = _get_package_version(package_dir)
-    with open(_out_file_path(package_name), "w") as f:
-        f.write(
-            _doc_first_line(package_name)
-            + _construct_doc(
-                _package_namespace(package_name), package_members, package_version
-            )
-        )
+    output_dir = _out_file_path(package_name)
+    os.mkdir(output_dir)
+    rsts = _construct_doc(
+        _package_namespace(package_name), package_members, package_version
+    )
+    for name, rst in rsts:
+        with open(output_dir / name, "w") as f:
+            f.write(rst)
 
 
 def _package_namespace(package_name: str) -> str:
@@ -385,12 +517,119 @@ def _get_package_version(package_dir: Path) -> str:
 
 def _out_file_path(package_name: str) -> Path:
     """Return the path to the file containing the documentation."""
-    return HERE / f"{package_name.replace('-', '_')}_api_reference.rst"
+    return HERE / f"{package_name.replace('-', '_')}"
 
 
-def _doc_first_line(package_name: str) -> str:
-    """Return the path to the file containing the documentation."""
-    return f".. {package_name.replace('-', '_')}_api_reference:\n\n"
+def _build_index(dirs: List[str]) -> None:
+    custom_names = {
+        "airbyte": "Airbyte",
+        "aws": "AWS",
+        "ai21": "AI21",
+    }
+    ordered = ["core", "langchain", "text-splitters", "community", "experimental"]
+    main_ = [dir_ for dir_ in ordered if dir_ in dirs]
+    integrations = sorted(dir_ for dir_ in dirs if dir_ not in main_)
+    doc = """# LangChain Python API Reference
+
+Welcome to the LangChain Python API reference. This is a reference for all 
+`langchain-x` packages. 
+
+For user guides see [https://python.langchain.com](https://python.langchain.com).
+
+For the legacy API reference hosted on ReadTheDocs see [https://api.python.langchain.com/](https://api.python.langchain.com/).
+"""
+
+    if main_:
+        main_headers = [
+            " ".join(custom_names.get(x, x.title()) for x in dir_.split("-"))
+            for dir_ in main_
+        ]
+        main_tree = "\n".join(
+            f"{header_name}<{dir_.replace('-', '_')}/index>"
+            for header_name, dir_ in zip(main_headers, main_)
+        )
+        main_grid = "\n".join(
+            f'- header: "**{header_name}**"\n  content: "{_package_namespace(dir_).replace("_", "-")}: {_get_package_version(_package_dir(dir_))}"\n  link: {dir_.replace("-", "_")}/index.html'
+            for header_name, dir_ in zip(main_headers, main_)
+        )
+        doc += f"""## Base packages
+
+```{{gallery-grid}}
+:grid-columns: "1 2 2 3"
+
+{main_grid}
+```
+
+```{{toctree}}
+:maxdepth: 2
+:hidden:
+:caption: Base packages
+
+{main_tree}
+```
+"""
+    if integrations:
+        integration_headers = [
+            " ".join(
+                custom_names.get(x, x.title().replace("ai", "AI").replace("db", "DB"))
+                for x in dir_.split("-")
+            )
+            for dir_ in integrations
+        ]
+        integration_tree = "\n".join(
+            f"{header_name}<{dir_.replace('-', '_')}/index>"
+            for header_name, dir_ in zip(integration_headers, integrations)
+        )
+
+        integration_grid = ""
+        integrations_to_show = [
+            "openai",
+            "anthropic",
+            "google-vertexai",
+            "aws",
+            "huggingface",
+            "mistralai",
+        ]
+        for header_name, dir_ in sorted(
+            zip(integration_headers, integrations),
+            key=lambda h_d: integrations_to_show.index(h_d[1])
+            if h_d[1] in integrations_to_show
+            else len(integrations_to_show),
+        )[: len(integrations_to_show)]:
+            integration_grid += f'\n- header: "**{header_name}**"\n  content: {_package_namespace(dir_).replace("_", "-")} {_get_package_version(_package_dir(dir_))}\n  link: {dir_.replace("-", "_")}/index.html'
+        doc += f"""## Integrations
+
+```{{gallery-grid}}
+:grid-columns: "1 2 2 3"
+
+{integration_grid}
+```
+
+See the full list of integrations in the Section Navigation.
+
+```{{toctree}}
+:maxdepth: 2
+:hidden:
+:caption: Integrations
+
+{integration_tree}
+```
+"""
+    with open(HERE / "reference.md", "w") as f:
+        f.write(doc)
+
+    dummy_index = """\
+# API reference
+
+```{toctree}
+:maxdepth: 3
+:hidden:
+
+Reference<reference>
+```
+"""
+    with open(HERE / "index.md", "w") as f:
+        f.write(dummy_index)
 
 
 def main(dirs: Optional[list] = None) -> None:
@@ -418,6 +657,8 @@ def main(dirs: Optional[list] = None) -> None:
         else:
             print("Building package:", dir_)
             _build_rst_file(package_name=dir_)
+
+    _build_index(dirs)
     print("API reference files built.")
 
 

docs/api_reference/index.rst

@@ -1,8 +0,0 @@
-=============
-LangChain API
-=============
-
-.. toctree::
-    :maxdepth: 2
-
-    api_reference.rst

docs/api_reference/requirements.txt

@@ -1,17 +1,11 @@
--e libs/experimental
--e libs/langchain
--e libs/core
--e libs/community
-pydantic<2
-autodoc_pydantic==1.8.0
-myst_parser
-nbsphinx==0.8.9
-sphinx>=5
-sphinx-autobuild==2021.3.14
-sphinx_rtd_theme==1.0.0
-sphinx-typlog-theme==0.8.0
-sphinx-panels
-toml
-myst_nb
-sphinx_copybutton
-pydata-sphinx-theme==0.13.1
+autodoc_pydantic>=1,<2
+sphinx<=7
+myst-parser>=3
+sphinx-autobuild>=2024
+pydata-sphinx-theme>=0.15
+toml>=0.10.2
+myst-nb>=1.1.1
+pyyaml
+sphinx-design
+sphinx-copybutton
+beautifulsoup4

docs/api_reference/scripts/custom_formatter.py

@@ -0,0 +1,41 @@
+import sys
+from glob import glob
+from pathlib import Path
+
+from bs4 import BeautifulSoup
+
+CUR_DIR = Path(__file__).parents[1]
+
+
+def process_toc_h3_elements(html_content: str) -> str:
+    """Update Class.method() TOC headers to just method()."""
+    # Create a BeautifulSoup object
+    soup = BeautifulSoup(html_content, "html.parser")
+
+    # Find all <li> elements with class "toc-h3"
+    toc_h3_elements = soup.find_all("li", class_="toc-h3")
+
+    # Process each element
+    for element in toc_h3_elements:
+        element = element.a.code.span
+        # Get the text content of the element
+        content = element.get_text()
+
+        # Apply the regex substitution
+        modified_content = content.split(".")[-1]
+
+        # Update the element's content
+        element.string = modified_content
+
+    # Return the modified HTML
+    return str(soup)
+
+
+if __name__ == "__main__":
+    dir = sys.argv[1]
+    for fn in glob(str(f"{dir.rstrip('/')}/**/*.html"), recursive=True):
+        with open(fn, "r") as f:
+            html = f.read()
+        processed_html = process_toc_h3_elements(html)
+        with open(fn, "w") as f:
+            f.write(processed_html)

docs/api_reference/templates/class.rst

@@ -1,4 +1,4 @@
-:mod:`{{module}}`.{{objname}}
+{{ objname }}
 {{ underline }}==============
 
 .. currentmodule:: {{ module }}
@@ -11,7 +11,7 @@
 
    .. autosummary::
    {% for item in attributes %}
-      ~{{ name }}.{{ item }}
+      ~{{ item }}
    {%- endfor %}
    {% endif %}
    {% endblock %}
@@ -22,11 +22,11 @@
 
    .. autosummary::
    {% for item in methods %}
-      ~{{ name }}.{{ item }}
+      ~{{ item }}
    {%- endfor %}
 
    {% for item in methods %}
-   .. automethod:: {{ name }}.{{ item }}
+   .. automethod:: {{ item }}
    {%- endfor %}
 
    {% endif %}

docs/api_reference/templates/enum.rst

@@ -1,4 +1,4 @@
-:mod:`{{module}}`.{{objname}}
+{{ objname }}
 {{ underline }}==============
 
 .. currentmodule:: {{ module }}

docs/api_reference/templates/function.rst

@@ -1,4 +1,4 @@
-:mod:`{{module}}`.{{objname}}
+{{ objname }}
 {{ underline }}==============
 
 .. currentmodule:: {{ module }}

docs/api_reference/templates/langchain_docs.html

@@ -0,0 +1,12 @@
+<!-- This will display a link to LangChain docs -->
+<head>
+    <style>
+        .text-link {
+            text-decoration: none; /* Remove underline */
+            color: inherit;        /* Inherit color from parent element */
+        }
+    </style>
+</head>
+<body>
+<a href="https://python.langchain.com/" class='text-link'>Docs</a>
+</body>

docs/api_reference/templates/pydantic.rst

@@ -1,4 +1,4 @@
-:mod:`{{module}}`.{{objname}}
+{{ objname }}
 {{ underline }}==============
 
 .. currentmodule:: {{ module }}

docs/api_reference/templates/runnable_non_pydantic.rst

@@ -1,21 +1,21 @@
-:mod:`{{module}}`.{{objname}}
+{{ objname }}
 {{ underline }}==============
 
-.. NOTE:: {{objname}} implements the standard :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>`. 🏃
-
-    The :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>` has additional methods that are available on runnables, such as :py:meth:`with_types <langchain_core.runnables.base.Runnable.with_types>`, :py:meth:`with_retry <langchain_core.runnables.base.Runnable.with_retry>`, :py:meth:`assign <langchain_core.runnables.base.Runnable.assign>`, :py:meth:`bind <langchain_core.runnables.base.Runnable.bind>`, :py:meth:`get_graph <langchain_core.runnables.base.Runnable.get_graph>`, and more.
-
 .. currentmodule:: {{ module }}
 
 .. autoclass:: {{ objname }}
 
+.. NOTE:: {{objname}} implements the standard :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>`. 🏃
+
+    The :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>` has additional methods that are available on runnables, such as :py:meth:`with_types <langchain_core.runnables.base.Runnable.with_types>`, :py:meth:`with_retry <langchain_core.runnables.base.Runnable.with_retry>`, :py:meth:`assign <langchain_core.runnables.base.Runnable.assign>`, :py:meth:`bind <langchain_core.runnables.base.Runnable.bind>`, :py:meth:`get_graph <langchain_core.runnables.base.Runnable.get_graph>`, and more.
+
    {% block attributes %}
    {% if attributes %}
    .. rubric:: {{ _('Attributes') }}
 
    .. autosummary::
    {% for item in attributes %}
-      ~{{ name }}.{{ item }}
+      ~{{ item }}
    {%- endfor %}
    {% endif %}
    {% endblock %}
@@ -26,11 +26,11 @@
 
    .. autosummary::
    {% for item in methods %}
-      ~{{ name }}.{{ item }}
+      ~{{ item }}
    {%- endfor %}
 
    {% for item in methods %}
-   .. automethod:: {{ name }}.{{ item }}
+   .. automethod:: {{ item }}
    {%- endfor %}
 
    {% endif %}

docs/api_reference/templates/runnable_pydantic.rst

@@ -1,10 +1,6 @@
-:mod:`{{module}}`.{{objname}}
+{{ objname }}
 {{ underline }}==============
 
-.. NOTE:: {{objname}} implements the standard :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>`. 🏃
-
-    The :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>` has additional methods that are available on runnables, such as :py:meth:`with_types <langchain_core.runnables.base.Runnable.with_types>`, :py:meth:`with_retry <langchain_core.runnables.base.Runnable.with_retry>`, :py:meth:`assign <langchain_core.runnables.base.Runnable.assign>`, :py:meth:`bind <langchain_core.runnables.base.Runnable.bind>`, :py:meth:`get_graph <langchain_core.runnables.base.Runnable.get_graph>`, and more.
-
 .. currentmodule:: {{ module }}
 
 .. autopydantic_model:: {{ objname }}
@@ -19,6 +15,10 @@
     :member-order: groupwise
     :show-inheritance: True
     :special-members: __call__
-    :exclude-members: construct, copy, dict, from_orm, parse_file, parse_obj, parse_raw, schema, schema_json, update_forward_refs, validate, json, is_lc_serializable, to_json_not_implemented, lc_secrets, lc_attributes, lc_id, get_lc_namespace, astream_log, transform, atransform, get_output_schema, get_prompts, config_schema, map, pick, pipe, with_listeners, with_alisteners, with_config, with_fallbacks, with_types, with_retry, InputType, OutputType, config_specs, output_schema, get_input_schema, get_graph, get_name, input_schema, name, bind, assign
+    :exclude-members: construct, copy, dict, from_orm, parse_file, parse_obj, parse_raw, schema, schema_json, update_forward_refs, validate, json, is_lc_serializable, to_json_not_implemented, lc_secrets, lc_attributes, lc_id, get_lc_namespace, astream_log, transform, atransform, get_output_schema, get_prompts, config_schema, map, pick, pipe, with_listeners, with_alisteners, with_config, with_fallbacks, with_types, with_retry, InputType, OutputType, config_specs, output_schema, get_input_schema, get_graph, get_name, input_schema, name, bind, assign, as_tool
+
+    .. NOTE:: {{objname}} implements the standard :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>`. 🏃
+
+        The :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>` has additional methods that are available on runnables, such as :py:meth:`with_types <langchain_core.runnables.base.Runnable.with_types>`, :py:meth:`with_retry <langchain_core.runnables.base.Runnable.with_retry>`, :py:meth:`assign <langchain_core.runnables.base.Runnable.assign>`, :py:meth:`bind <langchain_core.runnables.base.Runnable.bind>`, :py:meth:`get_graph <langchain_core.runnables.base.Runnable.get_graph>`, and more.
 
 .. example_links:: {{ objname }}

docs/api_reference/templates/typeddict.rst

@@ -1,4 +1,4 @@
-:mod:`{{module}}`.{{objname}}
+{{ objname }}
 {{ underline }}==============
 
 .. currentmodule:: {{ module }}

docs/api_reference/themes/COPYRIGHT.txt

@@ -1,27 +0,0 @@
-Copyright (c) 2007-2023 The scikit-learn developers.
-All rights reserved.
-
-Redistribution and use in source and binary forms, with or without
-modification, are permitted provided that the following conditions are met:
-
-* Redistributions of source code must retain the above copyright notice, this
-  list of conditions and the following disclaimer.
-
-* Redistributions in binary form must reproduce the above copyright notice,
-  this list of conditions and the following disclaimer in the documentation
-  and/or other materials provided with the distribution.
-
-* Neither the name of the copyright holder nor the names of its
-  contributors may be used to endorse or promote products derived from
-  this software without specific prior written permission.
-
-THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
-AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
-IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
-DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
-FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
-DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
-SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
-CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
-OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
-OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

docs/api_reference/themes/scikit-learn-modern/javascript.html

@@ -1,67 +0,0 @@
-<script>
-$(document).ready(function() {
-    /* Add a [>>>] button on the top-right corner of code samples to hide
-     * the >>> and ... prompts and the output and thus make the code
-     * copyable. */
-    var div = $('.highlight-python .highlight,' +
-                '.highlight-python3 .highlight,' +
-                '.highlight-pycon .highlight,' +
-		'.highlight-default .highlight')
-    var pre = div.find('pre');
-
-    // get the styles from the current theme
-    pre.parent().parent().css('position', 'relative');
-    var hide_text = 'Hide prompts and outputs';
-    var show_text = 'Show prompts and outputs';
-
-    // create and add the button to all the code blocks that contain >>>
-    div.each(function(index) {
-        var jthis = $(this);
-        if (jthis.find('.gp').length > 0) {
-            var button = $('<span class="copybutton">&gt;&gt;&gt;</span>');
-            button.attr('title', hide_text);
-            button.data('hidden', 'false');
-            jthis.prepend(button);
-        }
-        // tracebacks (.gt) contain bare text elements that need to be
-        // wrapped in a span to work with .nextUntil() (see later)
-        jthis.find('pre:has(.gt)').contents().filter(function() {
-            return ((this.nodeType == 3) && (this.data.trim().length > 0));
-        }).wrap('<span>');
-    });
-
-    // define the behavior of the button when it's clicked
-    $('.copybutton').click(function(e){
-        e.preventDefault();
-        var button = $(this);
-        if (button.data('hidden') === 'false') {
-            // hide the code output
-            button.parent().find('.go, .gp, .gt').hide();
-            button.next('pre').find('.gt').nextUntil('.gp, .go').css('visibility', 'hidden');
-            button.css('text-decoration', 'line-through');
-            button.attr('title', show_text);
-            button.data('hidden', 'true');
-        } else {
-            // show the code output
-            button.parent().find('.go, .gp, .gt').show();
-            button.next('pre').find('.gt').nextUntil('.gp, .go').css('visibility', 'visible');
-            button.css('text-decoration', 'none');
-            button.attr('title', hide_text);
-            button.data('hidden', 'false');
-        }
-    });
-
-	/*** Add permalink buttons next to glossary terms ***/
-	$('dl.glossary > dt[id]').append(function() {
-		return ('<a class="headerlink" href="#' +
-			    this.getAttribute('id') +
-			    '" title="Permalink to this term">¶</a>');
-	});
-});
-
-</script>
-{%- if pagename != 'index' and pagename != 'documentation' %}
-    {% if theme_mathjax_path %}
-<script id="MathJax-script" async src="{{ theme_mathjax_path }}"></script>
-    {% endif %}
-{%- endif %}

docs/api_reference/themes/scikit-learn-modern/layout.html

@@ -1,132 +0,0 @@
-{# TEMPLATE VAR SETTINGS #}
-{%- set url_root = pathto('', 1) %}
-{%- if url_root == '#' %}{% set url_root = '' %}{% endif %}
-{%- if not embedded and docstitle %}
-    {%- set titlesuffix = " — "|safe + docstitle|e %}
-{%- else %}
-    {%- set titlesuffix = "" %}
-{%- endif %}
-{%- set lang_attr = 'en' %}
-
-<!DOCTYPE html>
-<!--[if IE 8]><html class="no-js lt-ie9" lang="{{ lang_attr }}" > <![endif]-->
-<!--[if gt IE 8]><!-->
-<html class="no-js" lang="{{ lang_attr }}"> <!--<![endif]-->
-<head>
-    <meta charset="utf-8">
-    {{ metatags }}
-    <meta name="viewport" content="width=device-width, initial-scale=1.0">
-
-    {% block htmltitle %}
-        <title>{{ title|striptags|e }}{{ titlesuffix }}</title>
-    {% endblock %}
-    <link rel="canonical"
-          href="https://api.python.langchain.com/en/latest/{{ pagename }}.html"/>
-
-    {% if favicon_url %}
-        <link rel="shortcut icon" href="{{ favicon_url|e }}"/>
-    {% endif %}
-
-    <link rel="stylesheet"
-          href="{{ pathto('_static/css/vendor/bootstrap.min.css', 1) }}"
-          type="text/css"/>
-    {%- for css in css_files %}
-        {%- if css|attr("rel") %}
-            <link rel="{{ css.rel }}" href="{{ pathto(css.filename, 1) }}"
-                  type="text/css"{% if css.title is not none %}
-                  title="{{ css.title }}"{% endif %} />
-        {%- else %}
-            <link rel="stylesheet" href="{{ pathto(css, 1) }}" type="text/css"/>
-        {%- endif %}
-    {%- endfor %}
-    <link rel="stylesheet" href="{{ pathto('_static/' + style, 1) }}" type="text/css"/>
-    <script id="documentation_options" data-url_root="{{ pathto('', 1) }}"
-            src="{{ pathto('_static/documentation_options.js', 1) }}"></script>
-    <script src="{{ pathto('_static/jquery.js', 1) }}"></script>
-    {%- block extrahead %} {% endblock %}
-</head>
-<body>
-{% include "nav.html" %}
-{%- block content %}
-    <div class="d-flex" id="sk-doc-wrapper">
-        <input type="checkbox" name="sk-toggle-checkbox" id="sk-toggle-checkbox">
-        <label id="sk-sidemenu-toggle" class="sk-btn-toggle-toc btn sk-btn-primary"
-               for="sk-toggle-checkbox">Toggle Menu</label>
-        <div id="sk-sidebar-wrapper" class="border-right">
-            <div class="sk-sidebar-toc-wrapper">
-                {%- if meta and meta['parenttoc']|tobool %}
-                    <div class="sk-sidebar-toc">
-                        {% set nav = get_nav_object(maxdepth=3, collapse=True, numbered=True) %}
-                        <ul>
-                            {% for main_nav_item in nav %}
-                                {% if main_nav_item.active %}
-                                    <li>
-                                        <a href="{{ main_nav_item.url }}"
-                                           class="sk-toc-active">{{ main_nav_item.title }}</a>
-                                    </li>
-                                    <ul>
-                                        {% for nav_item in main_nav_item.children %}
-                                            <li>
-                                                <a href="{{ nav_item.url }}"
-                                                   class="{% if nav_item.active %}sk-toc-active{% endif %}">{{ nav_item.title }}</a>
-                                                {% if nav_item.children %}
-                                                    <ul>
-                                                        {% for inner_child in nav_item.children %}
-                                                            <li class="sk-toctree-l3">
-                                                                <a href="{{ inner_child.url }}">{{ inner_child.title }}</a>
-                                                            </li>
-                                                        {% endfor %}
-                                                    </ul>
-                                                {% endif %}
-                                            </li>
-                                        {% endfor %}
-                                    </ul>
-                                {% endif %}
-                            {% endfor %}
-                        </ul>
-                    </div>
-                {%- elif meta and meta['globalsidebartoc']|tobool %}
-                    <div class="sk-sidebar-toc sk-sidebar-global-toc">
-                        {{ toctree(maxdepth=2, titles_only=True) }}
-                    </div>
-                {%- else %}
-                    <div class="sk-sidebar-toc">
-                        {{ toc }}
-                    </div>
-                {%- endif %}
-            </div>
-        </div>
-        <div id="sk-page-content-wrapper">
-            <div class="sk-page-content container-fluid body px-md-3" role="main">
-                {% block body %}{% endblock %}
-            </div>
-            <div class="container">
-                <footer class="sk-content-footer">
-                    {%- if pagename != 'index' %}
-                        {%- if show_copyright %}
-                            {%- if hasdoc('copyright') %}
-                                {% trans path=pathto('copyright'), copyright=copyright|e %}
-                                    &copy; {{ copyright }}.{% endtrans %}
-                            {%- else %}
-                                {% trans copyright=copyright|e %}&copy; {{ copyright }}
-                                    .{% endtrans %}
-                            {%- endif %}
-                        {%- endif %}
-                        {%- if last_updated %}
-                            {% trans last_updated=last_updated|e %}Last updated
-                                on {{ last_updated }}.{% endtrans %}
-                        {%- endif %}
-                        {%- if show_source and has_source and sourcename %}
-                            <a href="{{ pathto('_sources/' + sourcename, true)|e }}"
-                               rel="nofollow">{{ _('Show this page source') }}</a>
-                        {%- endif %}
-                    {%- endif %}
-                </footer>
-            </div>
-        </div>
-    </div>
-{%- endblock %}
-<script src="{{ pathto('_static/js/vendor/bootstrap.min.js', 1) }}"></script>
-{% include "javascript.html" %}
-</body>
-</html>

docs/api_reference/themes/scikit-learn-modern/nav.html

@@ -1,78 +0,0 @@
-{%- if pagename != 'index' and pagename != 'documentation' %}
-  {%- set nav_bar_class = "sk-docs-navbar" %}
-  {%- set top_container_cls = "sk-docs-container" %}
-{%- else %}
-  {%- set nav_bar_class = "sk-landing-navbar" %}
-  {%- set top_container_cls = "sk-landing-container" %}
-{%- endif %}
-
-<nav id="navbar" class="{{ nav_bar_class }} navbar navbar-expand-md navbar-light bg-light py-0">
-  <div class="container-fluid {{ top_container_cls }} px-0">
-    {%- if logo_url %}
-      <a class="navbar-brand py-0" href="{{ pathto('index') }}">
-        <img
-          class="sk-brand-img"
-          src="{{ logo_url|e }}"
-          alt="logo"/>
-      </a>
-    {%- endif %}
-    <button
-      id="sk-navbar-toggler"
-      class="navbar-toggler"
-      type="button"
-      data-toggle="collapse"
-      data-target="#navbarSupportedContent"
-      aria-controls="navbarSupportedContent"
-      aria-expanded="false"
-      aria-label="Toggle navigation"
-    >
-      <span class="navbar-toggler-icon"></span>
-    </button>
-
-    <div class="sk-navbar-collapse collapse navbar-collapse" id="navbarSupportedContent">
-      <ul class="navbar-nav mr-auto">
-        <li class="nav-item">
-          <a class="sk-nav-link nav-link" href="{{ pathto('langchain_api_reference') }}">LangChain</a>
-        </li>
-        <li class="nav-item">
-          <a class="sk-nav-link nav-link" href="{{ pathto('core_api_reference') }}">Core</a>
-        </li>
-        <li class="nav-item">
-          <a class="sk-nav-link nav-link" href="{{ pathto('community_api_reference') }}">Community</a>
-        </li>
-        <li class="nav-item">
-          <a class="sk-nav-link nav-link" href="{{ pathto('experimental_api_reference') }}">Experimental</a>
-        </li>
-        <li class="nav-item">
-          <a class="sk-nav-link nav-link" href="{{ pathto('text_splitters_api_reference') }}">Text splitters</a>
-        </li>
-        {%- for title, pathname in partners %}
-        <li class="nav-item">
-          <a class="sk-nav-link nav-link nav-more-item-mobile-items" href="{{ pathto(pathname) }}">{{ title }}</a>
-        </li>
-        {%- endfor %}
-        <li class="nav-item dropdown nav-more-item-dropdown">
-          <a class="sk-nav-link nav-link dropdown-toggle" href="#" id="navbarDropdown" role="button" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">Partner libs</a>
-          <div class="dropdown-menu" aria-labelledby="navbarDropdown">
-            {%- for title, pathname in partners %}
-              <a class="sk-nav-dropdown-item dropdown-item" href="{{ pathto(pathname) }}">{{ title }}</a>
-            {%- endfor %}
-          </div>
-        </li>
-        <li class="nav-item">
-          <a class="sk-nav-link nav-link" target="_blank" rel="noopener noreferrer" href="https://python.langchain.com/">Docs</a>
-        </li>
-      </ul>
-      {%- if pagename != "search"%}
-      <div id="searchbox" role="search">
-          <div class="searchformwrapper">
-          <form class="search" action="{{ pathto('search') }}" method="get">
-            <input class="sk-search-text-input" type="text" name="q" aria-labelledby="searchlabel" />
-            <input class="sk-search-text-btn" type="submit" value="{{ _('Go') }}" />
-          </form>
-          </div>
-      </div>
-      {%- endif %}
-    </div>
-  </div>
-</nav>

docs/api_reference/themes/scikit-learn-modern/search.html

@@ -1,16 +0,0 @@
-{%- extends "basic/search.html" %}
-{% block extrahead %}
-  <script type="text/javascript" src="{{ pathto('_static/underscore.js', 1) }}"></script>
-  <script type="text/javascript" src="{{ pathto('searchindex.js', 1) }}" defer></script>
-  <script type="text/javascript" src="{{ pathto('_static/doctools.js', 1) }}"></script>
-  <script type="text/javascript" src="{{ pathto('_static/language_data.js', 1) }}"></script>
-  <script type="text/javascript" src="{{ pathto('_static/searchtools.js', 1) }}"></script>
-  <script type="text/javascript" src="{{ pathto('_static/sphinx_highlight.js', 1) }}"></script>
-  <script type="text/javascript">
-    $(document).ready(function() {
-      if (!Search.out) {
-        Search.init();
-      }
-    });
-  </script>
-{% endblock %}

docs/api_reference/themes/scikit-learn-modern/theme.conf

@@ -1,8 +0,0 @@
-[theme]
-inherit = basic
-pygments_style = default
-stylesheet = css/theme.css
-
-[options]
-link_to_live_contributing_page = false
-mathjax_path =

docs/docs/additional_resources/arxiv_references.mdx

@@ -4,8 +4,11 @@ LangChain implements the latest research in the field of Natural Language Proces
 This page contains `arXiv` papers referenced in the LangChain Documentation, API Reference,
  Templates, and Cookbooks.
 
-From the opposite direction, scientists use LangChain in research and reference LangChain in the research papers. 
-Here you find [such papers](https://arxiv.org/search/?query=langchain&searchtype=all&source=header).
+From the opposite direction, scientists use `LangChain` in research and reference it in the research papers. 
+Here you find papers that reference:
+- [LangChain](https://arxiv.org/search/?query=langchain&searchtype=all&source=header)
+- [LangGraph](https://arxiv.org/search/?query=langgraph&searchtype=all&source=header)
+- [LangSmith](https://arxiv.org/search/?query=langsmith&searchtype=all&source=header)
 
 ## Summary
 
@@ -23,32 +26,30 @@ Here you find [such papers](https://arxiv.org/search/?query=langchain&searchtype
 | `2305.14283v3` [Query Rewriting for Retrieval-Augmented Large Language Models](http://arxiv.org/abs/2305.14283v3) | Xinbei Ma, Yeyun Gong, Pengcheng He,  et al. | 2023-05-23 | `Template:` [rewrite-retrieve-read](https://python.langchain.com/docs/templates/rewrite-retrieve-read), `Cookbook:` [rewrite](https://github.com/langchain-ai/langchain/blob/master/cookbook/rewrite.ipynb)
 | `2305.08291v1` [Large Language Model Guided Tree-of-Thought](http://arxiv.org/abs/2305.08291v1) | Jieyi Long | 2023-05-15 | `API:` [langchain_experimental.tot](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.tot), `Cookbook:` [tree_of_thought](https://github.com/langchain-ai/langchain/blob/master/cookbook/tree_of_thought.ipynb)
 | `2305.04091v3` [Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models](http://arxiv.org/abs/2305.04091v3) | Lei Wang, Wanyu Xu, Yihuai Lan,  et al. | 2023-05-06 | `Cookbook:` [plan_and_execute_agent](https://github.com/langchain-ai/langchain/blob/master/cookbook/plan_and_execute_agent.ipynb)
+| `2305.02156v1` [Zero-Shot Listwise Document Reranking with a Large Language Model](http://arxiv.org/abs/2305.02156v1) | Xueguang Ma, Xinyu Zhang, Ronak Pradeep,  et al. | 2023-05-03 | `API:` [langchain...LLMListwiseRerank](https://api.python.langchain.com/en/latest/retrievers/langchain.retrievers.document_compressors.listwise_rerank.LLMListwiseRerank.html#langchain.retrievers.document_compressors.listwise_rerank.LLMListwiseRerank)
 | `2304.08485v2` [Visual Instruction Tuning](http://arxiv.org/abs/2304.08485v2) | Haotian Liu, Chunyuan Li, Qingyang Wu,  et al. | 2023-04-17 | `Cookbook:` [Semi_structured_and_multi_modal_RAG](https://github.com/langchain-ai/langchain/blob/master/cookbook/Semi_structured_and_multi_modal_RAG.ipynb), [Semi_structured_multi_modal_RAG_LLaMA2](https://github.com/langchain-ai/langchain/blob/master/cookbook/Semi_structured_multi_modal_RAG_LLaMA2.ipynb)
 | `2304.03442v2` [Generative Agents: Interactive Simulacra of Human Behavior](http://arxiv.org/abs/2304.03442v2) | Joon Sung Park, Joseph C. O'Brien, Carrie J. Cai,  et al. | 2023-04-07 | `Cookbook:` [multiagent_bidding](https://github.com/langchain-ai/langchain/blob/master/cookbook/multiagent_bidding.ipynb), [generative_agents_interactive_simulacra_of_human_behavior](https://github.com/langchain-ai/langchain/blob/master/cookbook/generative_agents_interactive_simulacra_of_human_behavior.ipynb)
 | `2303.17760v2` [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](http://arxiv.org/abs/2303.17760v2) | Guohao Li, Hasan Abed Al Kader Hammoud, Hani Itani,  et al. | 2023-03-31 | `Cookbook:` [camel_role_playing](https://github.com/langchain-ai/langchain/blob/master/cookbook/camel_role_playing.ipynb)
 | `2303.17580v4` [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face](http://arxiv.org/abs/2303.17580v4) | Yongliang Shen, Kaitao Song, Xu Tan,  et al. | 2023-03-30 | `API:` [langchain_experimental.autonomous_agents](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.autonomous_agents), `Cookbook:` [hugginggpt](https://github.com/langchain-ai/langchain/blob/master/cookbook/hugginggpt.ipynb)
-| `2303.08774v6` [GPT-4 Technical Report](http://arxiv.org/abs/2303.08774v6) | OpenAI, Josh Achiam, Steven Adler,  et al. | 2023-03-15 | `Docs:` [docs/integrations/vectorstores/mongodb_atlas](https://python.langchain.com/docs/integrations/vectorstores/mongodb_atlas)
-| `2301.10226v4` [A Watermark for Large Language Models](http://arxiv.org/abs/2301.10226v4) | John Kirchenbauer, Jonas Geiping, Yuxin Wen,  et al. | 2023-01-24 | `API:` [langchain_community...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_huggingface...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community...OCIModelDeploymentTGI](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.oci_data_science_model_deployment_endpoint.OCIModelDeploymentTGI.html#langchain_community.llms.oci_data_science_model_deployment_endpoint.OCIModelDeploymentTGI), [langchain_community...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference)
+| `2301.10226v4` [A Watermark for Large Language Models](http://arxiv.org/abs/2301.10226v4) | John Kirchenbauer, Jonas Geiping, Yuxin Wen,  et al. | 2023-01-24 | `API:` [langchain_community...OCIModelDeploymentTGI](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.oci_data_science_model_deployment_endpoint.OCIModelDeploymentTGI.html#langchain_community.llms.oci_data_science_model_deployment_endpoint.OCIModelDeploymentTGI), [langchain_huggingface...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference)
 | `2212.10496v1` [Precise Zero-Shot Dense Retrieval without Relevance Labels](http://arxiv.org/abs/2212.10496v1) | Luyu Gao, Xueguang Ma, Jimmy Lin,  et al. | 2022-12-20 | `API:` [langchain...HypotheticalDocumentEmbedder](https://api.python.langchain.com/en/latest/chains/langchain.chains.hyde.base.HypotheticalDocumentEmbedder.html#langchain.chains.hyde.base.HypotheticalDocumentEmbedder), `Template:` [hyde](https://python.langchain.com/docs/templates/hyde), `Cookbook:` [hypothetical_document_embeddings](https://github.com/langchain-ai/langchain/blob/master/cookbook/hypothetical_document_embeddings.ipynb)
 | `2212.07425v3` [Robust and Explainable Identification of Logical Fallacies in Natural Language Arguments](http://arxiv.org/abs/2212.07425v3) | Zhivar Sourati, Vishnu Priya Prasanna Venkatesh, Darshan Deshpande,  et al. | 2022-12-12 | `API:` [langchain_experimental.fallacy_removal](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.fallacy_removal)
 | `2211.13892v2` [Complementary Explanations for Effective In-Context Learning](http://arxiv.org/abs/2211.13892v2) | Xi Ye, Srinivasan Iyer, Asli Celikyilmaz,  et al. | 2022-11-25 | `API:` [langchain_core...MaxMarginalRelevanceExampleSelector](https://api.python.langchain.com/en/latest/example_selectors/langchain_core.example_selectors.semantic_similarity.MaxMarginalRelevanceExampleSelector.html#langchain_core.example_selectors.semantic_similarity.MaxMarginalRelevanceExampleSelector)
-| `2211.10435v2` [PAL: Program-aided Language Models](http://arxiv.org/abs/2211.10435v2) | Luyu Gao, Aman Madaan, Shuyan Zhou,  et al. | 2022-11-18 | `API:` [langchain_experimental...PALChain](https://api.python.langchain.com/en/latest/pal_chain/langchain_experimental.pal_chain.base.PALChain.html#langchain_experimental.pal_chain.base.PALChain), [langchain_experimental.pal_chain](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.pal_chain), `Cookbook:` [program_aided_language_model](https://github.com/langchain-ai/langchain/blob/master/cookbook/program_aided_language_model.ipynb)
-| `2210.03629v3` [ReAct: Synergizing Reasoning and Acting in Language Models](http://arxiv.org/abs/2210.03629v3) | Shunyu Yao, Jeffrey Zhao, Dian Yu,  et al. | 2022-10-06 | `Docs:` [docs/integrations/providers/cohere](https://python.langchain.com/docs/integrations/providers/cohere), [docs/integrations/chat/huggingface](https://python.langchain.com/docs/integrations/chat/huggingface), [docs/integrations/tools/ionic_shopping](https://python.langchain.com/docs/integrations/tools/ionic_shopping), `API:` [langchain...create_react_agent](https://api.python.langchain.com/en/latest/agents/langchain.agents.react.agent.create_react_agent.html#langchain.agents.react.agent.create_react_agent), [langchain...TrajectoryEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.agents.trajectory_eval_chain.TrajectoryEvalChain.html#langchain.evaluation.agents.trajectory_eval_chain.TrajectoryEvalChain)
+| `2211.10435v2` [PAL: Program-aided Language Models](http://arxiv.org/abs/2211.10435v2) | Luyu Gao, Aman Madaan, Shuyan Zhou,  et al. | 2022-11-18 | `API:` [langchain_experimental.pal_chain](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.pal_chain), [langchain_experimental...PALChain](https://api.python.langchain.com/en/latest/pal_chain/langchain_experimental.pal_chain.base.PALChain.html#langchain_experimental.pal_chain.base.PALChain), `Cookbook:` [program_aided_language_model](https://github.com/langchain-ai/langchain/blob/master/cookbook/program_aided_language_model.ipynb)
+| `2210.03629v3` [ReAct: Synergizing Reasoning and Acting in Language Models](http://arxiv.org/abs/2210.03629v3) | Shunyu Yao, Jeffrey Zhao, Dian Yu,  et al. | 2022-10-06 | `Docs:` [docs/integrations/providers/cohere](https://python.langchain.com/docs/integrations/providers/cohere), [docs/integrations/tools/ionic_shopping](https://python.langchain.com/docs/integrations/tools/ionic_shopping), `API:` [langchain...TrajectoryEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.agents.trajectory_eval_chain.TrajectoryEvalChain.html#langchain.evaluation.agents.trajectory_eval_chain.TrajectoryEvalChain), [langchain...create_react_agent](https://api.python.langchain.com/en/latest/agents/langchain.agents.react.agent.create_react_agent.html#langchain.agents.react.agent.create_react_agent)
 | `2209.10785v2` [Deep Lake: a Lakehouse for Deep Learning](http://arxiv.org/abs/2209.10785v2) | Sasun Hambardzumyan, Abhinav Tuli, Levon Ghukasyan,  et al. | 2022-09-22 | `Docs:` [docs/integrations/providers/activeloop_deeplake](https://python.langchain.com/docs/integrations/providers/activeloop_deeplake)
+| `2205.13147v4` [Matryoshka Representation Learning](http://arxiv.org/abs/2205.13147v4) | Aditya Kusupati, Gantavya Bhatt, Aniket Rege,  et al. | 2022-05-26 | `Docs:` [docs/integrations/providers/snowflake](https://python.langchain.com/docs/integrations/providers/snowflake)
 | `2205.12654v1` [Bitext Mining Using Distilled Sentence Representations for Low-Resource Languages](http://arxiv.org/abs/2205.12654v1) | Kevin Heffernan, Onur Çelebi, Holger Schwenk | 2022-05-25 | `API:` [langchain_community...LaserEmbeddings](https://api.python.langchain.com/en/latest/embeddings/langchain_community.embeddings.laser.LaserEmbeddings.html#langchain_community.embeddings.laser.LaserEmbeddings)
-| `2204.00498v1` [Evaluating the Text-to-SQL Capabilities of Large Language Models](http://arxiv.org/abs/2204.00498v1) | Nitarshan Rajkumar, Raymond Li, Dzmitry Bahdanau | 2022-03-15 | `API:` [langchain_community...SparkSQL](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.spark_sql.SparkSQL.html#langchain_community.utilities.spark_sql.SparkSQL), [langchain_community...SQLDatabase](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.sql_database.SQLDatabase.html#langchain_community.utilities.sql_database.SQLDatabase)
-| `2202.00666v5` [Locally Typical Sampling](http://arxiv.org/abs/2202.00666v5) | Clara Meister, Tiago Pimentel, Gian Wiher,  et al. | 2022-02-01 | `API:` [langchain_community...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_huggingface...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference)
+| `2204.00498v1` [Evaluating the Text-to-SQL Capabilities of Large Language Models](http://arxiv.org/abs/2204.00498v1) | Nitarshan Rajkumar, Raymond Li, Dzmitry Bahdanau | 2022-03-15 | `API:` [langchain_community...SQLDatabase](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.sql_database.SQLDatabase.html#langchain_community.utilities.sql_database.SQLDatabase), [langchain_community...SparkSQL](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.spark_sql.SparkSQL.html#langchain_community.utilities.spark_sql.SparkSQL)
+| `2202.00666v5` [Locally Typical Sampling](http://arxiv.org/abs/2202.00666v5) | Clara Meister, Tiago Pimentel, Gian Wiher,  et al. | 2022-02-01 | `API:` [langchain_huggingface...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference)
 | `2103.00020v1` [Learning Transferable Visual Models From Natural Language Supervision](http://arxiv.org/abs/2103.00020v1) | Alec Radford, Jong Wook Kim, Chris Hallacy,  et al. | 2021-02-26 | `API:` [langchain_experimental.open_clip](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.open_clip)
-| `1909.05858v2` [CTRL: A Conditional Transformer Language Model for Controllable Generation](http://arxiv.org/abs/1909.05858v2) | Nitish Shirish Keskar, Bryan McCann, Lav R. Varshney,  et al. | 2019-09-11 | `API:` [langchain_community...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_huggingface...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference)
-| `1908.10084v1` [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](http://arxiv.org/abs/1908.10084v1) | Nils Reimers, Iryna Gurevych | 2019-08-27 | `Docs:` [docs/integrations/text_embedding/sentence_transformers](https://python.langchain.com/docs/integrations/text_embedding/sentence_transformers)
+| `1909.05858v2` [CTRL: A Conditional Transformer Language Model for Controllable Generation](http://arxiv.org/abs/1909.05858v2) | Nitish Shirish Keskar, Bryan McCann, Lav R. Varshney,  et al. | 2019-09-11 | `API:` [langchain_huggingface...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference)
 
 ## Self-Discover: Large Language Models Self-Compose Reasoning Structures
 
-- **arXiv id:** 2402.03620v1
+- **arXiv id:** [2402.03620v1](http://arxiv.org/abs/2402.03620v1)  **Published Date:** 2024-02-06
 - **Title:** Self-Discover: Large Language Models Self-Compose Reasoning Structures
 - **Authors:** Pei Zhou, Jay Pujara, Xiang Ren,  et al.
-- **Published Date:** 2024-02-06
-- **URL:** http://arxiv.org/abs/2402.03620v1
 - **LangChain:**
 
    - **Cookbook:** [self-discover](https://github.com/langchain-ai/langchain/blob/master/cookbook/self-discover.ipynb)
@@ -70,11 +71,9 @@ commonalities with human reasoning patterns.
                 
 ## RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
 
-- **arXiv id:** 2401.18059v1
+- **arXiv id:** [2401.18059v1](http://arxiv.org/abs/2401.18059v1)  **Published Date:** 2024-01-31
 - **Title:** RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
 - **Authors:** Parth Sarthi, Salman Abdullah, Aditi Tuli,  et al.
-- **Published Date:** 2024-01-31
-- **URL:** http://arxiv.org/abs/2401.18059v1
 - **LangChain:**
 
    - **Cookbook:** [RAPTOR](https://github.com/langchain-ai/langchain/blob/master/cookbook/RAPTOR.ipynb)
@@ -96,11 +95,9 @@ benchmark by 20% in absolute accuracy.
                 
 ## Corrective Retrieval Augmented Generation
 
-- **arXiv id:** 2401.15884v2
+- **arXiv id:** [2401.15884v2](http://arxiv.org/abs/2401.15884v2)  **Published Date:** 2024-01-29
 - **Title:** Corrective Retrieval Augmented Generation
 - **Authors:** Shi-Qi Yan, Jia-Chen Gu, Yun Zhu,  et al.
-- **Published Date:** 2024-01-29
-- **URL:** http://arxiv.org/abs/2401.15884v2
 - **LangChain:**
 
    - **Cookbook:** [langgraph_crag](https://github.com/langchain-ai/langchain/blob/master/cookbook/langgraph_crag.ipynb)
@@ -126,11 +123,9 @@ performance of RAG-based approaches.
                 
 ## Mixtral of Experts
 
-- **arXiv id:** 2401.04088v1
+- **arXiv id:** [2401.04088v1](http://arxiv.org/abs/2401.04088v1)  **Published Date:** 2024-01-08
 - **Title:** Mixtral of Experts
 - **Authors:** Albert Q. Jiang, Alexandre Sablayrolles, Antoine Roux,  et al.
-- **Published Date:** 2024-01-08
-- **URL:** http://arxiv.org/abs/2401.04088v1
 - **LangChain:**
 
    - **Cookbook:** [together_ai](https://github.com/langchain-ai/langchain/blob/master/cookbook/together_ai.ipynb)
@@ -152,11 +147,9 @@ the base and instruct models are released under the Apache 2.0 license.
                 
 ## Dense X Retrieval: What Retrieval Granularity Should We Use?
 
-- **arXiv id:** 2312.06648v2
+- **arXiv id:** [2312.06648v2](http://arxiv.org/abs/2312.06648v2)  **Published Date:** 2023-12-11
 - **Title:** Dense X Retrieval: What Retrieval Granularity Should We Use?
 - **Authors:** Tong Chen, Hongwei Wang, Sihao Chen,  et al.
-- **Published Date:** 2023-12-11
-- **URL:** http://arxiv.org/abs/2312.06648v2
 - **LangChain:**
 
    - **Template:** [propositional-retrieval](https://python.langchain.com/docs/templates/propositional-retrieval)
@@ -181,11 +174,9 @@ information.
                 
 ## Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models
 
-- **arXiv id:** 2311.09210v1
+- **arXiv id:** [2311.09210v1](http://arxiv.org/abs/2311.09210v1)  **Published Date:** 2023-11-15
 - **Title:** Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models
 - **Authors:** Wenhao Yu, Hongming Zhang, Xiaoman Pan,  et al.
-- **Published Date:** 2023-11-15
-- **URL:** http://arxiv.org/abs/2311.09210v1
 - **LangChain:**
 
    - **Template:** [chain-of-note-wiki](https://python.langchain.com/docs/templates/chain-of-note-wiki)
@@ -215,11 +206,9 @@ outside the pre-training knowledge scope.
                 
 ## Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
 
-- **arXiv id:** 2310.11511v1
+- **arXiv id:** [2310.11511v1](http://arxiv.org/abs/2310.11511v1)  **Published Date:** 2023-10-17
 - **Title:** Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
 - **Authors:** Akari Asai, Zeqiu Wu, Yizhong Wang,  et al.
-- **Published Date:** 2023-10-17
-- **URL:** http://arxiv.org/abs/2310.11511v1
 - **LangChain:**
 
    - **Cookbook:** [langgraph_self_rag](https://github.com/langchain-ai/langchain/blob/master/cookbook/langgraph_self_rag.ipynb)
@@ -248,11 +237,9 @@ to these models.
                 
 ## Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models
 
-- **arXiv id:** 2310.06117v2
+- **arXiv id:** [2310.06117v2](http://arxiv.org/abs/2310.06117v2)  **Published Date:** 2023-10-09
 - **Title:** Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models
 - **Authors:** Huaixiu Steven Zheng, Swaroop Mishra, Xinyun Chen,  et al.
-- **Published Date:** 2023-10-09
-- **URL:** http://arxiv.org/abs/2310.06117v2
 - **LangChain:**
 
    - **Template:** [stepback-qa-prompting](https://python.langchain.com/docs/templates/stepback-qa-prompting)
@@ -271,11 +258,9 @@ and 11% respectively, TimeQA by 27%, and MuSiQue by 7%.
                 
 ## Llama 2: Open Foundation and Fine-Tuned Chat Models
 
-- **arXiv id:** 2307.09288v2
+- **arXiv id:** [2307.09288v2](http://arxiv.org/abs/2307.09288v2)  **Published Date:** 2023-07-18
 - **Title:** Llama 2: Open Foundation and Fine-Tuned Chat Models
 - **Authors:** Hugo Touvron, Louis Martin, Kevin Stone,  et al.
-- **Published Date:** 2023-07-18
-- **URL:** http://arxiv.org/abs/2307.09288v2
 - **LangChain:**
 
    - **Cookbook:** [Semi_Structured_RAG](https://github.com/langchain-ai/langchain/blob/master/cookbook/Semi_Structured_RAG.ipynb)
@@ -292,11 +277,9 @@ contribute to the responsible development of LLMs.
                 
 ## Query Rewriting for Retrieval-Augmented Large Language Models
 
-- **arXiv id:** 2305.14283v3
+- **arXiv id:** [2305.14283v3](http://arxiv.org/abs/2305.14283v3)  **Published Date:** 2023-05-23
 - **Title:** Query Rewriting for Retrieval-Augmented Large Language Models
 - **Authors:** Xinbei Ma, Yeyun Gong, Pengcheng He,  et al.
-- **Published Date:** 2023-05-23
-- **URL:** http://arxiv.org/abs/2305.14283v3
 - **LangChain:**
 
    - **Template:** [rewrite-retrieve-read](https://python.langchain.com/docs/templates/rewrite-retrieve-read)
@@ -322,11 +305,9 @@ for retrieval-augmented LLM.
                 
 ## Large Language Model Guided Tree-of-Thought
 
-- **arXiv id:** 2305.08291v1
+- **arXiv id:** [2305.08291v1](http://arxiv.org/abs/2305.08291v1)  **Published Date:** 2023-05-15
 - **Title:** Large Language Model Guided Tree-of-Thought
 - **Authors:** Jieyi Long
-- **Published Date:** 2023-05-15
-- **URL:** http://arxiv.org/abs/2305.08291v1
 - **LangChain:**
 
    - **API Reference:** [langchain_experimental.tot](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.tot)
@@ -352,11 +333,9 @@ implementation of the ToT-based Sudoku solver is available on GitHub:
                 
 ## Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models
 
-- **arXiv id:** 2305.04091v3
+- **arXiv id:** [2305.04091v3](http://arxiv.org/abs/2305.04091v3)  **Published Date:** 2023-05-06
 - **Title:** Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models
 - **Authors:** Lei Wang, Wanyu Xu, Yihuai Lan,  et al.
-- **Published Date:** 2023-05-06
-- **URL:** http://arxiv.org/abs/2305.04091v3
 - **LangChain:**
 
    - **Cookbook:** [plan_and_execute_agent](https://github.com/langchain-ai/langchain/blob/master/cookbook/plan_and_execute_agent.ipynb)
@@ -383,13 +362,35 @@ Prompting, and has comparable performance with 8-shot CoT prompting on the math
 reasoning problem. The code can be found at
 https://github.com/AGI-Edgerunners/Plan-and-Solve-Prompting.
                 
+## Zero-Shot Listwise Document Reranking with a Large Language Model
+
+- **arXiv id:** [2305.02156v1](http://arxiv.org/abs/2305.02156v1)  **Published Date:** 2023-05-03
+- **Title:** Zero-Shot Listwise Document Reranking with a Large Language Model
+- **Authors:** Xueguang Ma, Xinyu Zhang, Ronak Pradeep,  et al.
+- **LangChain:**
+
+   - **API Reference:** [langchain...LLMListwiseRerank](https://api.python.langchain.com/en/latest/retrievers/langchain.retrievers.document_compressors.listwise_rerank.LLMListwiseRerank.html#langchain.retrievers.document_compressors.listwise_rerank.LLMListwiseRerank)
+
+**Abstract:** Supervised ranking methods based on bi-encoder or cross-encoder architectures
+have shown success in multi-stage text ranking tasks, but they require large
+amounts of relevance judgments as training data. In this work, we propose
+Listwise Reranker with a Large Language Model (LRL), which achieves strong
+reranking effectiveness without using any task-specific training data.
+Different from the existing pointwise ranking methods, where documents are
+scored independently and ranked according to the scores, LRL directly generates
+a reordered list of document identifiers given the candidate documents.
+Experiments on three TREC web search datasets demonstrate that LRL not only
+outperforms zero-shot pointwise methods when reranking first-stage retrieval
+results, but can also act as a final-stage reranker to improve the top-ranked
+results of a pointwise method for improved efficiency. Additionally, we apply
+our approach to subsets of MIRACL, a recent multilingual retrieval dataset,
+with results showing its potential to generalize across different languages.
+                
 ## Visual Instruction Tuning
 
-- **arXiv id:** 2304.08485v2
+- **arXiv id:** [2304.08485v2](http://arxiv.org/abs/2304.08485v2)  **Published Date:** 2023-04-17
 - **Title:** Visual Instruction Tuning
 - **Authors:** Haotian Liu, Chunyuan Li, Qingyang Wu,  et al.
-- **Published Date:** 2023-04-17
-- **URL:** http://arxiv.org/abs/2304.08485v2
 - **LangChain:**
 
    - **Cookbook:** [Semi_structured_and_multi_modal_RAG](https://github.com/langchain-ai/langchain/blob/master/cookbook/Semi_structured_and_multi_modal_RAG.ipynb), [Semi_structured_multi_modal_RAG_LLaMA2](https://github.com/langchain-ai/langchain/blob/master/cookbook/Semi_structured_multi_modal_RAG_LLaMA2.ipynb)
@@ -412,11 +413,9 @@ publicly available.
                 
 ## Generative Agents: Interactive Simulacra of Human Behavior
 
-- **arXiv id:** 2304.03442v2
+- **arXiv id:** [2304.03442v2](http://arxiv.org/abs/2304.03442v2)  **Published Date:** 2023-04-07
 - **Title:** Generative Agents: Interactive Simulacra of Human Behavior
 - **Authors:** Joon Sung Park, Joseph C. O'Brien, Carrie J. Cai,  et al.
-- **Published Date:** 2023-04-07
-- **URL:** http://arxiv.org/abs/2304.03442v2
 - **LangChain:**
 
    - **Cookbook:** [multiagent_bidding](https://github.com/langchain-ai/langchain/blob/master/cookbook/multiagent_bidding.ipynb), [generative_agents_interactive_simulacra_of_human_behavior](https://github.com/langchain-ai/langchain/blob/master/cookbook/generative_agents_interactive_simulacra_of_human_behavior.ipynb)
@@ -448,11 +447,9 @@ interaction patterns for enabling believable simulations of human behavior.
                 
 ## CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
 
-- **arXiv id:** 2303.17760v2
+- **arXiv id:** [2303.17760v2](http://arxiv.org/abs/2303.17760v2)  **Published Date:** 2023-03-31
 - **Title:** CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
 - **Authors:** Guohao Li, Hasan Abed Al Kader Hammoud, Hani Itani,  et al.
-- **Published Date:** 2023-03-31
-- **URL:** http://arxiv.org/abs/2303.17760v2
 - **LangChain:**
 
    - **Cookbook:** [camel_role_playing](https://github.com/langchain-ai/langchain/blob/master/cookbook/camel_role_playing.ipynb)
@@ -478,11 +475,9 @@ agents and beyond: https://github.com/camel-ai/camel.
                 
 ## HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face
 
-- **arXiv id:** 2303.17580v4
+- **arXiv id:** [2303.17580v4](http://arxiv.org/abs/2303.17580v4)  **Published Date:** 2023-03-30
 - **Title:** HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face
 - **Authors:** Yongliang Shen, Kaitao Song, Xu Tan,  et al.
-- **Published Date:** 2023-03-30
-- **URL:** http://arxiv.org/abs/2303.17580v4
 - **LangChain:**
 
    - **API Reference:** [langchain_experimental.autonomous_agents](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.autonomous_agents)
@@ -508,40 +503,14 @@ modalities and domains and achieve impressive results in language, vision,
 speech, and other challenging tasks, which paves a new way towards the
 realization of artificial general intelligence.
                 
-## GPT-4 Technical Report
-
-- **arXiv id:** 2303.08774v6
-- **Title:** GPT-4 Technical Report
-- **Authors:** OpenAI, Josh Achiam, Steven Adler,  et al.
-- **Published Date:** 2023-03-15
-- **URL:** http://arxiv.org/abs/2303.08774v6
-- **LangChain:**
-
-   - **Documentation:** [docs/integrations/vectorstores/mongodb_atlas](https://python.langchain.com/docs/integrations/vectorstores/mongodb_atlas)
-
-**Abstract:** We report the development of GPT-4, a large-scale, multimodal model which can
-accept image and text inputs and produce text outputs. While less capable than
-humans in many real-world scenarios, GPT-4 exhibits human-level performance on
-various professional and academic benchmarks, including passing a simulated bar
-exam with a score around the top 10% of test takers. GPT-4 is a
-Transformer-based model pre-trained to predict the next token in a document.
-The post-training alignment process results in improved performance on measures
-of factuality and adherence to desired behavior. A core component of this
-project was developing infrastructure and optimization methods that behave
-predictably across a wide range of scales. This allowed us to accurately
-predict some aspects of GPT-4's performance based on models trained with no
-more than 1/1,000th the compute of GPT-4.
-                
 ## A Watermark for Large Language Models
 
-- **arXiv id:** 2301.10226v4
+- **arXiv id:** [2301.10226v4](http://arxiv.org/abs/2301.10226v4)  **Published Date:** 2023-01-24
 - **Title:** A Watermark for Large Language Models
 - **Authors:** John Kirchenbauer, Jonas Geiping, Yuxin Wen,  et al.
-- **Published Date:** 2023-01-24
-- **URL:** http://arxiv.org/abs/2301.10226v4
 - **LangChain:**
 
-   - **API Reference:** [langchain_community...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_huggingface...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community...OCIModelDeploymentTGI](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.oci_data_science_model_deployment_endpoint.OCIModelDeploymentTGI.html#langchain_community.llms.oci_data_science_model_deployment_endpoint.OCIModelDeploymentTGI), [langchain_community...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference)
+   - **API Reference:** [langchain_community...OCIModelDeploymentTGI](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.oci_data_science_model_deployment_endpoint.OCIModelDeploymentTGI.html#langchain_community.llms.oci_data_science_model_deployment_endpoint.OCIModelDeploymentTGI), [langchain_huggingface...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference)
 
 **Abstract:** Potential harms of large language models can be mitigated by watermarking
 model output, i.e., embedding signals into generated text that are invisible to
@@ -559,11 +528,9 @@ family, and discuss robustness and security.
                 
 ## Precise Zero-Shot Dense Retrieval without Relevance Labels
 
-- **arXiv id:** 2212.10496v1
+- **arXiv id:** [2212.10496v1](http://arxiv.org/abs/2212.10496v1)  **Published Date:** 2022-12-20
 - **Title:** Precise Zero-Shot Dense Retrieval without Relevance Labels
 - **Authors:** Luyu Gao, Xueguang Ma, Jimmy Lin,  et al.
-- **Published Date:** 2022-12-20
-- **URL:** http://arxiv.org/abs/2212.10496v1
 - **LangChain:**
 
    - **API Reference:** [langchain...HypotheticalDocumentEmbedder](https://api.python.langchain.com/en/latest/chains/langchain.chains.hyde.base.HypotheticalDocumentEmbedder.html#langchain.chains.hyde.base.HypotheticalDocumentEmbedder)
@@ -590,11 +557,9 @@ search, QA, fact verification) and languages~(e.g. sw, ko, ja).
                 
 ## Robust and Explainable Identification of Logical Fallacies in Natural Language Arguments
 
-- **arXiv id:** 2212.07425v3
+- **arXiv id:** [2212.07425v3](http://arxiv.org/abs/2212.07425v3)  **Published Date:** 2022-12-12
 - **Title:** Robust and Explainable Identification of Logical Fallacies in Natural Language Arguments
 - **Authors:** Zhivar Sourati, Vishnu Priya Prasanna Venkatesh, Darshan Deshpande,  et al.
-- **Published Date:** 2022-12-12
-- **URL:** http://arxiv.org/abs/2212.07425v3
 - **LangChain:**
 
    - **API Reference:** [langchain_experimental.fallacy_removal](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.fallacy_removal)
@@ -623,11 +588,9 @@ further work on logical fallacy identification.
                 
 ## Complementary Explanations for Effective In-Context Learning
 
-- **arXiv id:** 2211.13892v2
+- **arXiv id:** [2211.13892v2](http://arxiv.org/abs/2211.13892v2)  **Published Date:** 2022-11-25
 - **Title:** Complementary Explanations for Effective In-Context Learning
 - **Authors:** Xi Ye, Srinivasan Iyer, Asli Celikyilmaz,  et al.
-- **Published Date:** 2022-11-25
-- **URL:** http://arxiv.org/abs/2211.13892v2
 - **LangChain:**
 
    - **API Reference:** [langchain_core...MaxMarginalRelevanceExampleSelector](https://api.python.langchain.com/en/latest/example_selectors/langchain_core.example_selectors.semantic_similarity.MaxMarginalRelevanceExampleSelector.html#langchain_core.example_selectors.semantic_similarity.MaxMarginalRelevanceExampleSelector)
@@ -651,14 +614,12 @@ performance across three real-world tasks on multiple LLMs.
                 
 ## PAL: Program-aided Language Models
 
-- **arXiv id:** 2211.10435v2
+- **arXiv id:** [2211.10435v2](http://arxiv.org/abs/2211.10435v2)  **Published Date:** 2022-11-18
 - **Title:** PAL: Program-aided Language Models
 - **Authors:** Luyu Gao, Aman Madaan, Shuyan Zhou,  et al.
-- **Published Date:** 2022-11-18
-- **URL:** http://arxiv.org/abs/2211.10435v2
 - **LangChain:**
 
-   - **API Reference:** [langchain_experimental...PALChain](https://api.python.langchain.com/en/latest/pal_chain/langchain_experimental.pal_chain.base.PALChain.html#langchain_experimental.pal_chain.base.PALChain), [langchain_experimental.pal_chain](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.pal_chain)
+   - **API Reference:** [langchain_experimental.pal_chain](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.pal_chain), [langchain_experimental...PALChain](https://api.python.langchain.com/en/latest/pal_chain/langchain_experimental.pal_chain.base.PALChain.html#langchain_experimental.pal_chain.base.PALChain)
    - **Cookbook:** [program_aided_language_model](https://github.com/langchain-ai/langchain/blob/master/cookbook/program_aided_language_model.ipynb)
 
 **Abstract:** Large language models (LLMs) have recently demonstrated an impressive ability
@@ -686,15 +647,13 @@ publicly available at http://reasonwithpal.com/ .
                 
 ## ReAct: Synergizing Reasoning and Acting in Language Models
 
-- **arXiv id:** 2210.03629v3
+- **arXiv id:** [2210.03629v3](http://arxiv.org/abs/2210.03629v3)  **Published Date:** 2022-10-06
 - **Title:** ReAct: Synergizing Reasoning and Acting in Language Models
 - **Authors:** Shunyu Yao, Jeffrey Zhao, Dian Yu,  et al.
-- **Published Date:** 2022-10-06
-- **URL:** http://arxiv.org/abs/2210.03629v3
 - **LangChain:**
 
-   - **Documentation:** [docs/integrations/providers/cohere](https://python.langchain.com/docs/integrations/providers/cohere), [docs/integrations/chat/huggingface](https://python.langchain.com/docs/integrations/chat/huggingface), [docs/integrations/tools/ionic_shopping](https://python.langchain.com/docs/integrations/tools/ionic_shopping)
-   - **API Reference:** [langchain...create_react_agent](https://api.python.langchain.com/en/latest/agents/langchain.agents.react.agent.create_react_agent.html#langchain.agents.react.agent.create_react_agent), [langchain...TrajectoryEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.agents.trajectory_eval_chain.TrajectoryEvalChain.html#langchain.evaluation.agents.trajectory_eval_chain.TrajectoryEvalChain)
+   - **Documentation:** [docs/integrations/providers/cohere](https://python.langchain.com/docs/integrations/providers/cohere), [docs/integrations/tools/ionic_shopping](https://python.langchain.com/docs/integrations/tools/ionic_shopping)
+   - **API Reference:** [langchain...TrajectoryEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.agents.trajectory_eval_chain.TrajectoryEvalChain.html#langchain.evaluation.agents.trajectory_eval_chain.TrajectoryEvalChain), [langchain...create_react_agent](https://api.python.langchain.com/en/latest/agents/langchain.agents.react.agent.create_react_agent.html#langchain.agents.react.agent.create_react_agent)
 
 **Abstract:** While large language models (LLMs) have demonstrated impressive capabilities
 across tasks in language understanding and interactive decision making, their
@@ -721,11 +680,9 @@ Project site with code: https://react-lm.github.io
                 
 ## Deep Lake: a Lakehouse for Deep Learning
 
-- **arXiv id:** 2209.10785v2
+- **arXiv id:** [2209.10785v2](http://arxiv.org/abs/2209.10785v2)  **Published Date:** 2022-09-22
 - **Title:** Deep Lake: a Lakehouse for Deep Learning
 - **Authors:** Sasun Hambardzumyan, Abhinav Tuli, Levon Ghukasyan,  et al.
-- **Published Date:** 2022-09-22
-- **URL:** http://arxiv.org/abs/2209.10785v2
 - **LangChain:**
 
    - **Documentation:** [docs/integrations/providers/activeloop_deeplake](https://python.langchain.com/docs/integrations/providers/activeloop_deeplake)
@@ -747,13 +704,43 @@ visualization engine, or (c) deep learning frameworks without sacrificing GPU
 utilization. Datasets stored in Deep Lake can be accessed from PyTorch,
 TensorFlow, JAX, and integrate with numerous MLOps tools.
                 
+## Matryoshka Representation Learning
+
+- **arXiv id:** [2205.13147v4](http://arxiv.org/abs/2205.13147v4)  **Published Date:** 2022-05-26
+- **Title:** Matryoshka Representation Learning
+- **Authors:** Aditya Kusupati, Gantavya Bhatt, Aniket Rege,  et al.
+- **LangChain:**
+
+   - **Documentation:** [docs/integrations/providers/snowflake](https://python.langchain.com/docs/integrations/providers/snowflake)
+
+**Abstract:** Learned representations are a central component in modern ML systems, serving
+a multitude of downstream tasks. When training such representations, it is
+often the case that computational and statistical constraints for each
+downstream task are unknown. In this context rigid, fixed capacity
+representations can be either over or under-accommodating to the task at hand.
+This leads us to ask: can we design a flexible representation that can adapt to
+multiple downstream tasks with varying computational resources? Our main
+contribution is Matryoshka Representation Learning (MRL) which encodes
+information at different granularities and allows a single embedding to adapt
+to the computational constraints of downstream tasks. MRL minimally modifies
+existing representation learning pipelines and imposes no additional cost
+during inference and deployment. MRL learns coarse-to-fine representations that
+are at least as accurate and rich as independently trained low-dimensional
+representations. The flexibility within the learned Matryoshka Representations
+offer: (a) up to 14x smaller embedding size for ImageNet-1K classification at
+the same level of accuracy; (b) up to 14x real-world speed-ups for large-scale
+retrieval on ImageNet-1K and 4K; and (c) up to 2% accuracy improvements for
+long-tail few-shot classification, all while being as robust as the original
+representations. Finally, we show that MRL extends seamlessly to web-scale
+datasets (ImageNet, JFT) across various modalities -- vision (ViT, ResNet),
+vision + language (ALIGN) and language (BERT). MRL code and pretrained models
+are open-sourced at https://github.com/RAIVNLab/MRL.
+                
 ## Bitext Mining Using Distilled Sentence Representations for Low-Resource Languages
 
-- **arXiv id:** 2205.12654v1
+- **arXiv id:** [2205.12654v1](http://arxiv.org/abs/2205.12654v1)  **Published Date:** 2022-05-25
 - **Title:** Bitext Mining Using Distilled Sentence Representations for Low-Resource Languages
 - **Authors:** Kevin Heffernan, Onur Çelebi, Holger Schwenk
-- **Published Date:** 2022-05-25
-- **URL:** http://arxiv.org/abs/2205.12654v1
 - **LangChain:**
 
    - **API Reference:** [langchain_community...LaserEmbeddings](https://api.python.langchain.com/en/latest/embeddings/langchain_community.embeddings.laser.LaserEmbeddings.html#langchain_community.embeddings.laser.LaserEmbeddings)
@@ -778,14 +765,12 @@ encoders, mine bitexts, and validate the bitexts by training NMT systems.
                 
 ## Evaluating the Text-to-SQL Capabilities of Large Language Models
 
-- **arXiv id:** 2204.00498v1
+- **arXiv id:** [2204.00498v1](http://arxiv.org/abs/2204.00498v1)  **Published Date:** 2022-03-15
 - **Title:** Evaluating the Text-to-SQL Capabilities of Large Language Models
 - **Authors:** Nitarshan Rajkumar, Raymond Li, Dzmitry Bahdanau
-- **Published Date:** 2022-03-15
-- **URL:** http://arxiv.org/abs/2204.00498v1
 - **LangChain:**
 
-   - **API Reference:** [langchain_community...SparkSQL](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.spark_sql.SparkSQL.html#langchain_community.utilities.spark_sql.SparkSQL), [langchain_community...SQLDatabase](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.sql_database.SQLDatabase.html#langchain_community.utilities.sql_database.SQLDatabase)
+   - **API Reference:** [langchain_community...SQLDatabase](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.sql_database.SQLDatabase.html#langchain_community.utilities.sql_database.SQLDatabase), [langchain_community...SparkSQL](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.spark_sql.SparkSQL.html#langchain_community.utilities.spark_sql.SparkSQL)
 
 **Abstract:** We perform an empirical evaluation of Text-to-SQL capabilities of the Codex
 language model. We find that, without any finetuning, Codex is a strong
@@ -797,14 +782,12 @@ few-shot examples.
                 
 ## Locally Typical Sampling
 
-- **arXiv id:** 2202.00666v5
+- **arXiv id:** [2202.00666v5](http://arxiv.org/abs/2202.00666v5)  **Published Date:** 2022-02-01
 - **Title:** Locally Typical Sampling
 - **Authors:** Clara Meister, Tiago Pimentel, Gian Wiher,  et al.
-- **Published Date:** 2022-02-01
-- **URL:** http://arxiv.org/abs/2202.00666v5
 - **LangChain:**
 
-   - **API Reference:** [langchain_community...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_huggingface...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference)
+   - **API Reference:** [langchain_huggingface...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference)
 
 **Abstract:** Today's probabilistic language generators fall short when it comes to
 producing coherent and fluent text despite the fact that the underlying models
@@ -829,11 +812,9 @@ reducing degenerate repetitions.
                 
 ## Learning Transferable Visual Models From Natural Language Supervision
 
-- **arXiv id:** 2103.00020v1
+- **arXiv id:** [2103.00020v1](http://arxiv.org/abs/2103.00020v1)  **Published Date:** 2021-02-26
 - **Title:** Learning Transferable Visual Models From Natural Language Supervision
 - **Authors:** Alec Radford, Jong Wook Kim, Chris Hallacy,  et al.
-- **Published Date:** 2021-02-26
-- **URL:** http://arxiv.org/abs/2103.00020v1
 - **LangChain:**
 
    - **API Reference:** [langchain_experimental.open_clip](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.open_clip)
@@ -861,14 +842,12 @@ https://github.com/OpenAI/CLIP.
                 
 ## CTRL: A Conditional Transformer Language Model for Controllable Generation
 
-- **arXiv id:** 1909.05858v2
+- **arXiv id:** [1909.05858v2](http://arxiv.org/abs/1909.05858v2)  **Published Date:** 2019-09-11
 - **Title:** CTRL: A Conditional Transformer Language Model for Controllable Generation
 - **Authors:** Nitish Shirish Keskar, Bryan McCann, Lav R. Varshney,  et al.
-- **Published Date:** 2019-09-11
-- **URL:** http://arxiv.org/abs/1909.05858v2
 - **LangChain:**
 
-   - **API Reference:** [langchain_community...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_huggingface...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference)
+   - **API Reference:** [langchain_huggingface...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference)
 
 **Abstract:** Large-scale language models show promising text generation capabilities, but
 users cannot easily control particular aspects of the generated text. We
@@ -881,32 +860,4 @@ codes also allow CTRL to predict which parts of the training data are most
 likely given a sequence. This provides a potential method for analyzing large
 amounts of data via model-based source attribution. We have released multiple
 full-sized, pretrained versions of CTRL at https://github.com/salesforce/ctrl.
-                
-## Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
-
-- **arXiv id:** 1908.10084v1
-- **Title:** Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
-- **Authors:** Nils Reimers, Iryna Gurevych
-- **Published Date:** 2019-08-27
-- **URL:** http://arxiv.org/abs/1908.10084v1
-- **LangChain:**
-
-   - **Documentation:** [docs/integrations/text_embedding/sentence_transformers](https://python.langchain.com/docs/integrations/text_embedding/sentence_transformers)
-
-**Abstract:** BERT (Devlin et al., 2018) and RoBERTa (Liu et al., 2019) has set a new
-state-of-the-art performance on sentence-pair regression tasks like semantic
-textual similarity (STS). However, it requires that both sentences are fed into
-the network, which causes a massive computational overhead: Finding the most
-similar pair in a collection of 10,000 sentences requires about 50 million
-inference computations (~65 hours) with BERT. The construction of BERT makes it
-unsuitable for semantic similarity search as well as for unsupervised tasks
-like clustering.
-  In this publication, we present Sentence-BERT (SBERT), a modification of the
-pretrained BERT network that use siamese and triplet network structures to
-derive semantically meaningful sentence embeddings that can be compared using
-cosine-similarity. This reduces the effort for finding the most similar pair
-from 65 hours with BERT / RoBERTa to about 5 seconds with SBERT, while
-maintaining the accuracy from BERT.
-  We evaluate SBERT and SRoBERTa on common STS tasks and transfer learning
-tasks, where it outperforms other state-of-the-art sentence embeddings methods.
                 

docs/docs/concepts.mdx

@@ -90,7 +90,7 @@ LCEL aims to provide consistency around behavior and customization over legacy s
 `ConversationalRetrievalChain`. Many of these legacy chains hide important details like prompts, and as a wider variety
 of viable models emerge, customization has become more and more important.
 
-If you are currently using one of these legacy chains, please see [this guide for guidance on how to migrate](/docs/how_to/migrate_chains/).
+If you are currently using one of these legacy chains, please see [this guide for guidance on how to migrate](/docs/versions/migrating_chains).
 
 For guides on how to do specific tasks with LCEL, check out [the relevant how-to guides](/docs/how_to/#langchain-expression-language-lcel).
 
@@ -165,7 +165,7 @@ Some important things to note:
 ChatModels also accept other parameters that are specific to that integration. To find all the parameters supported by a ChatModel head to the API reference for that model.
 
 :::important
-**Tool Calling** Some chat models have been fine-tuned for tool calling and provide a dedicated API for tool calling.
+Some chat models have been fine-tuned for **tool calling** and provide a dedicated API for it.
 Generally, such models are better at tool calling than non-fine-tuned models, and are recommended for use cases that require tool calling.
 Please see the [tool calling section](/docs/concepts/#functiontool-calling) for more information.
 :::
@@ -209,7 +209,7 @@ Some language models take a list of messages as input and return a message.
 There are a few different types of messages.
 All messages have a `role`, `content`, and `response_metadata` property.
 
-The `role` describes WHO is saying the message.
+The `role` describes WHO is saying the message. The standard roles are "user", "assistant", "system", and "tool".
 LangChain has different message classes for different roles.
 
 The `content` property describes the content of the message.
@@ -218,13 +218,16 @@ This can be a few different things:
 - A string (most models deal this type of content)
 - A List of dictionaries (this is used for multimodal input, where the dictionary contains information about that input type and that input location)
 
+Optionally, messages can have a `name` property which allows for differentiating between multiple speakers with the same role.
+For example, if there are two users in the chat history it can be useful to differentiate between them. Not all models support this.
+
 #### HumanMessage
 
-This represents a message from the user.
+This represents a message with role "user".
 
 #### AIMessage
 
-This represents a message from the model. In addition to the `content` property, these messages also have:
+This represents a message with role "assistant". In addition to the `content` property, these messages also have:
 
 **`response_metadata`**
 
@@ -236,7 +239,7 @@ This is where information like log-probs and token usage may be stored.
 These represent a decision from an language model to call a tool. They are included as part of an `AIMessage` output.
 They can be accessed from there with the `.tool_calls` property.
 
-This property returns a list of dictionaries. Each dictionary has the following keys:
+This property returns a list of `ToolCall`s. A `ToolCall` is a dictionary with the following arguments:
 
 - `name`: The name of the tool that should be called.
 - `args`: The arguments to that tool.
@@ -244,15 +247,20 @@ This property returns a list of dictionaries. Each dictionary has the following
 
 #### SystemMessage
 
-This represents a system message, which tells the model how to behave. Not every model provider supports this.
-
-#### FunctionMessage
-
-This represents the result of a function call. In addition to `role` and `content`, this message has a `name` parameter which conveys the name of the function that was called to produce this result.
+This represents a message with role "system", which tells the model how to behave. Not every model provider supports this.
 
 #### ToolMessage
 
-This represents the result of a tool call. This is distinct from a FunctionMessage in order to match OpenAI's `function` and `tool` message types. In addition to `role` and `content`, this message has a `tool_call_id` parameter which conveys the id of the call to the tool that was called to produce this result.
+This represents a message with role "tool", which contains the result of calling a tool. In addition to `role` and `content`, this message has:
+
+- a `tool_call_id` field which conveys the id of the call to the tool that was called to produce this result.
+- an `artifact` field which can be used to pass along arbitrary artifacts of the tool execution which are useful to track but which should not be sent to the model.
+
+#### (Legacy) FunctionMessage
+
+This is a legacy message type, corresponding to OpenAI's legacy function-calling API. `ToolMessage` should be used instead to correspond to the updated tool-calling API.
+
+This represents the result of a function call. In addition to `role` and `content`, this message has a `name` parameter which conveys the name of the function that was called to produce this result.
 
 
 ### Prompt templates
@@ -338,6 +346,7 @@ For specifics on how to use prompt templates, see the [relevant how-to guides he
 
 ### Example selectors
 One common prompting technique for achieving better performance is to include examples as part of the prompt.
+This is known as [few-shot prompting](/docs/concepts/#few-shot-prompting).
 This gives the language model concrete examples of how it should behave.
 Sometimes these examples are hardcoded into the prompt, but for more advanced situations it may be nice to dynamically select them.
 Example Selectors are classes responsible for selecting and then formatting examples into prompts.
@@ -493,38 +502,130 @@ Retrievers accept a string query as input and return a list of Document's as out
 
 For specifics on how to use retrievers, see the [relevant how-to guides here](/docs/how_to/#retrievers).
 
+### Key-value stores
+
+For some techniques, such as [indexing and retrieval with multiple vectors per document](/docs/how_to/multi_vector/) or
+[caching embeddings](/docs/how_to/caching_embeddings/), having a form of key-value (KV) storage is helpful.
+
+LangChain includes a [`BaseStore`](https://api.python.langchain.com/en/latest/stores/langchain_core.stores.BaseStore.html) interface,
+which allows for storage of arbitrary data. However, LangChain components that require KV-storage accept a
+more specific `BaseStore[str, bytes]` instance that stores binary data (referred to as a `ByteStore`), and internally take care of
+encoding and decoding data for their specific needs.
+
+This means that as a user, you only need to think about one type of store rather than different ones for different types of data.
+
+#### Interface
+
+All [`BaseStores`](https://api.python.langchain.com/en/latest/stores/langchain_core.stores.BaseStore.html) support the following interface. Note that the interface allows
+for modifying **multiple** key-value pairs at once:
+
+- `mget(key: Sequence[str]) -> List[Optional[bytes]]`: get the contents of multiple keys, returning `None` if the key does not exist
+- `mset(key_value_pairs: Sequence[Tuple[str, bytes]]) -> None`: set the contents of multiple keys
+- `mdelete(key: Sequence[str]) -> None`: delete multiple keys
+- `yield_keys(prefix: Optional[str] = None) -> Iterator[str]`: yield all keys in the store, optionally filtering by a prefix
+
+For key-value store implementations, see [this section](/docs/integrations/stores/).
+
 ### Tools
 <span data-heading-keywords="tool,tools"></span>
 
-Tools are interfaces that an agent, a chain, or a chat model / LLM can use to interact with the world.
+Tools are utilities designed to be called by a model: their inputs are designed to be generated by models, and their outputs are designed to be passed back to models.
+Tools are needed whenever you want a model to control parts of your code or call out to external APIs.
 
-A tool consists of the following components:
+A tool consists of:
 
-1. The name of the tool
-2. A description of what the tool does
-3. JSON schema of what the inputs to the tool are
-4. The function to call
-5. Whether the result of a tool should be returned directly to the user (only relevant for agents)
+1. The name of the tool.
+2. A description of what the tool does.
+3. A JSON schema defining the inputs to the tool.
+4. A function (and, optionally, an async variant of the function).
 
-The name, description and JSON schema are provided as context
-to the LLM, allowing the LLM to determine how to use the tool
-appropriately.
+When a tool is bound to a model, the name, description and JSON schema are provided as context to the model.
+Given a list of tools and a set of instructions, a model can request to call one or more tools with specific inputs.
+Typical usage may look like the following:
 
-Given a list of available tools and a prompt, an LLM can request
-that one or more tools be invoked with appropriate arguments.
+```python
+tools = [...] # Define a list of tools
+llm_with_tools = llm.bind_tools(tools)
+ai_msg = llm_with_tools.invoke("do xyz...")
+# -> AIMessage(tool_calls=[ToolCall(...), ...], ...)
+```
 
-Generally, when designing tools to be used by a chat model or LLM, it is important to keep in mind the following:
+The `AIMessage` returned from the model MAY have `tool_calls` associated with it.
+Read [this guide](/docs/concepts/#aimessage) for more information on what the response type may look like.
 
-- Chat models that have been fine-tuned for tool calling will be better at tool calling than non-fine-tuned models.
-- Non fine-tuned models may not be able to use tools at all, especially if the tools are complex or require multiple tool calls.
-- Models will perform better if the tools have well-chosen names, descriptions, and JSON schemas.
-- Simpler tools are generally easier for models to use than more complex tools.
+Once the chosen tools are invoked, the results can be passed back to the model so that it can complete whatever task
+it's performing.
+There are generally two different ways to invoke the tool and pass back the response:
 
-For specifics on how to use tools, see the [relevant how-to guides here](/docs/how_to/#tools).
+#### Invoke with just the arguments
 
-To use an existing pre-built tool, see [here](/docs/integrations/tools/) for a list of pre-built tools.
+When you invoke a tool with just the arguments, you will get back the raw tool output (usually a string).
+This generally looks like:
+
+```python
+# You will want to previously check that the LLM returned tool calls
+tool_call = ai_msg.tool_calls[0]
+# ToolCall(args={...}, id=..., ...)
+tool_output = tool.invoke(tool_call["args"])
+tool_message = ToolMessage(
+    content=tool_output,
+    tool_call_id=tool_call["id"],
+    name=tool_call["name"]
+)
+```
+
+Note that the `content` field will generally be passed back to the model.
+If you do not want the raw tool response to be passed to the model, but you still want to keep it around,
+you can transform the tool output but also pass it as an artifact (read more about [`ToolMessage.artifact` here](/docs/concepts/#toolmessage))
+
+```python
+... # Same code as above
+response_for_llm = transform(response)
+tool_message = ToolMessage(
+    content=response_for_llm,
+    tool_call_id=tool_call["id"],
+    name=tool_call["name"],
+    artifact=tool_output
+)
+```
+
+#### Invoke with `ToolCall`
+
+The other way to invoke a tool is to call it with the full `ToolCall` that was generated by the model.
+When you do this, the tool will return a ToolMessage.
+The benefits of this are that you don't have to write the logic yourself to transform the tool output into a ToolMessage.
+This generally looks like:
+
+```python
+tool_call = ai_msg.tool_calls[0]
+# -> ToolCall(args={...}, id=..., ...)
+tool_message = tool.invoke(tool_call)
+# -> ToolMessage(
+    content="tool result foobar...",
+    tool_call_id=...,
+    name="tool_name"
+)
+```
+
+If you are invoking the tool this way and want to include an [artifact](/docs/concepts/#toolmessage) for the ToolMessage, you will need to have the tool return two things.
+Read more about [defining tools that return artifacts here](/docs/how_to/tool_artifacts/).
+
+#### Best practices
+
+When designing tools to be used by a model, it is important to keep in mind that:
+
+- Chat models that have explicit [tool-calling APIs](/docs/concepts/#functiontool-calling) will be better at tool calling than non-fine-tuned models.
+- Models will perform better if the tools have well-chosen names, descriptions, and JSON schemas. This another form of prompt engineering.
+- Simple, narrowly scoped tools are easier for models to use than complex tools.
+
+#### Related
+
+For specifics on how to use tools, see the [tools how-to guides](/docs/how_to/#tools).
+
+To use a pre-built tool, see the [tool integration docs](/docs/integrations/tools/).
 
 ### Toolkits
+<span data-heading-keywords="toolkit,toolkits"></span>
 
 Toolkits are collections of tools that are designed to be used together for specific tasks. They have convenient loading methods.
 
@@ -769,6 +870,61 @@ units (like words or subwords) that carry meaning, rather than individual charac
 to learn and understand the structure of the language, including grammar and context.
 Furthermore, using tokens can also improve efficiency, since the model processes fewer units of text compared to character-level processing.
 
+### Function/tool calling
+
+:::info
+We use the term tool calling interchangeably with function calling. Although
+function calling is sometimes meant to refer to invocations of a single function,
+we treat all models as though they can return multiple tool or function calls in
+each message.
+:::
+
+Tool calling allows a [chat model](/docs/concepts/#chat-models) to respond to a given prompt by generating output that
+matches a user-defined schema.
+
+While the name implies that the model is performing
+some action, this is actually not the case! The model only generates the arguments to a tool, and actually running the tool (or not) is up to the user.
+One common example where you **wouldn't** want to call a function with the generated arguments
+is if you want to [extract structured output matching some schema](/docs/concepts/#structured-output)
+from unstructured text. You would give the model an "extraction" tool that takes
+parameters matching the desired schema, then treat the generated output as your final
+result.
+
+![Diagram of a tool call by a chat model](/img/tool_call.png)
+
+Tool calling is not universal, but is supported by many popular LLM providers, including [Anthropic](/docs/integrations/chat/anthropic/), 
+[Cohere](/docs/integrations/chat/cohere/), [Google](/docs/integrations/chat/google_vertex_ai_palm/), 
+[Mistral](/docs/integrations/chat/mistralai/), [OpenAI](/docs/integrations/chat/openai/), and even for locally-running models via [Ollama](/docs/integrations/chat/ollama/).
+
+LangChain provides a standardized interface for tool calling that is consistent across different models.
+
+The standard interface consists of:
+
+* `ChatModel.bind_tools()`: a method for specifying which tools are available for a model to call. This method accepts [LangChain tools](/docs/concepts/#tools) as well as [Pydantic](https://pydantic.dev/) objects.
+* `AIMessage.tool_calls`: an attribute on the `AIMessage` returned from the model for accessing the tool calls requested by the model.
+
+#### Tool usage
+
+After the model calls tools, you can use the tool by invoking it, then passing the arguments back to the model.
+LangChain provides the [`Tool`](/docs/concepts/#tools) abstraction to help you handle this.
+
+The general flow is this:
+
+1. Generate tool calls with a chat model in response to a query.
+2. Invoke the appropriate tools using the generated tool call as arguments.
+3. Format the result of the tool invocations as [`ToolMessages`](/docs/concepts/#toolmessage).
+4. Pass the entire list of messages back to the model so that it can generate a final answer (or call more tools).
+
+![Diagram of a complete tool calling flow](/img/tool_calling_flow.png)
+
+This is how tool calling [agents](/docs/concepts/#agents) perform tasks and answer queries.
+
+Check out some more focused guides below:
+
+- [How to use chat models to call tools](/docs/how_to/tool_calling/)
+- [How to pass tool outputs to chat models](/docs/how_to/tool_results_pass_to_model/)
+- [Building an agent with LangGraph](https://langchain-ai.github.io/langgraph/tutorials/introduction/)
+
 ### Structured output
 
 LLMs are capable of generating arbitrary text. This enables the model to respond appropriately to a wide
@@ -901,54 +1057,129 @@ chain.invoke({ "question": "What is the powerhouse of the cell?" })
 
 For a full list of model providers that support JSON mode, see [this table](/docs/integrations/chat/#advanced-features).
 
-#### Function/tool calling
+#### Tool calling {#structured-output-tool-calling}
 
-:::info
-We use the term tool calling interchangeably with function calling. Although
-function calling is sometimes meant to refer to invocations of a single function,
-we treat all models as though they can return multiple tool or function calls in
-each message
-:::
+For models that support it, [tool calling](/docs/concepts/#functiontool-calling) can be very convenient for structured output. It removes the
+guesswork around how best to prompt schemas in favor of a built-in model feature.
 
-Tool calling allows a model to respond to a given prompt by generating output that
-matches a user-defined schema. While the name implies that the model is performing
-some action, this is actually not the case! The model is coming up with the
-arguments to a tool, and actually running the tool (or not) is up to the user -
-for example, if you want to [extract output matching some schema](/docs/tutorials/extraction)
-from unstructured text, you could give the model an "extraction" tool that takes
-parameters matching the desired schema, then treat the generated output as your final
-result.
+It works by first binding the desired schema either directly or via a [LangChain tool](/docs/concepts/#tools) to a
+[chat model](/docs/concepts/#chat-models) using the `.bind_tools()` method. The model will then generate an `AIMessage` containing
+a `tool_calls` field containing `args` that match the desired shape.
 
-For models that support it, tool calling can be very convenient. It removes the
-guesswork around how best to prompt schemas in favor of a built-in model feature. It can also
-more naturally support agentic flows, since you can just pass multiple tool schemas instead
-of fiddling with enums or unions.
+There are several acceptable formats you can use to bind tools to a model in LangChain. Here's one example:
 
-Many LLM providers, including [Anthropic](https://www.anthropic.com/),
-[Cohere](https://cohere.com/), [Google](https://cloud.google.com/vertex-ai),
-[Mistral](https://mistral.ai/), [OpenAI](https://openai.com/), and others,
-support variants of a tool calling feature. These features typically allow requests
-to the LLM to include available tools and their schemas, and for responses to include
-calls to these tools. For instance, given a search engine tool, an LLM might handle a
-query by first issuing a call to the search engine. The system calling the LLM can
-receive the tool call, execute it, and return the output to the LLM to inform its
-response. LangChain includes a suite of [built-in tools](/docs/integrations/tools/)
-and supports several methods for defining your own [custom tools](/docs/how_to/custom_tools).
+```python
+from langchain_core.pydantic_v1 import BaseModel, Field
+from langchain_openai import ChatOpenAI
 
-LangChain provides a standardized interface for tool calling that is consistent across different models.
+class ResponseFormatter(BaseModel):
+    """Always use this tool to structure your response to the user."""
 
-The standard interface consists of:
+    answer: str = Field(description="The answer to the user's question")
+    followup_question: str = Field(description="A followup question the user could ask")
 
-* `ChatModel.bind_tools()`: a method for specifying which tools are available for a model to call. This method accepts [LangChain tools](/docs/concepts/#tools) here.
-* `AIMessage.tool_calls`: an attribute on the `AIMessage` returned from the model for accessing the tool calls requested by the model.
+model = ChatOpenAI(
+    model="gpt-4o",
+    temperature=0,
+)
 
-The following how-to guides are good practical resources for using function/tool calling:
+model_with_tools = model.bind_tools([ResponseFormatter])
+
+ai_msg = model_with_tools.invoke("What is the powerhouse of the cell?")
+
+ai_msg.tool_calls[0]["args"]
+```
+
+```
+{'answer': "The powerhouse of the cell is the mitochondrion. It generates most of the cell's supply of adenosine triphosphate (ATP), which is used as a source of chemical energy.",
+ 'followup_question': 'How do mitochondria generate ATP?'}
+```
+
+Tool calling is a generally consistent way to get a model to generate structured output, and is the default technique
+used for the [`.with_structured_output()`](/docs/concepts/#with_structured_output) method when a model supports it.
+
+The following how-to guides are good practical resources for using function/tool calling for structured output:
 
 - [How to return structured data from an LLM](/docs/how_to/structured_output/)
 - [How to use a model to call tools](/docs/how_to/tool_calling)
 
 For a full list of model providers that support tool calling, [see this table](/docs/integrations/chat/#advanced-features).
 
+### Few-shot prompting
+
+One of the most effective ways to improve model performance is to give a model examples of what you want it to do. The technique of adding example inputs and expected outputs to a model prompt is known as "few-shot prompting". There are a few things to think about when doing few-shot prompting:
+
+1. How are examples generated?
+2. How many examples are in each prompt?
+3. How are examples selected at runtime?
+4. How are examples formatted in the prompt?
+
+Here are the considerations for each.
+
+#### 1. Generating examples
+
+The first and most important step of few-shot prompting is coming up with a good dataset of examples. Good examples should be relevant at runtime, clear, informative, and provide information that was not already known to the model.
+
+At a high-level, the basic ways to generate examples are:
+- Manual: a person/people generates examples they think are useful.
+- Better model: a better (presumably more expensive/slower) model's responses are used as examples for a worse (presumably cheaper/faster) model.
+- User feedback: users (or labelers) leave feedback on interactions with the application and examples are generated based on that feedback (for example, all interactions with positive feedback could be turned into examples).
+- LLM feedback: same as user feedback but the process is automated by having models evaluate themselves.
+
+Which approach is best depends on your task. For tasks where a small number core principles need to be understood really well, it can be valuable hand-craft a few really good examples.
+For tasks where the space of correct behaviors is broader and more nuanced, it can be useful to generate many examples in a more automated fashion so that there's a higher likelihood of there being some highly relevant examples for any runtime input.
+
+**Single-turn v.s. multi-turn examples**
+
+Another dimension to think about when generating examples is what the example is actually showing.
+
+The simplest types of examples just have a user input and an expected model output. These are single-turn examples.
+
+One more complex type if example is where the example is an entire conversation, usually in which a model initially responds incorrectly and a user then tells the model how to correct its answer.
+This is called a multi-turn example. Multi-turn examples can be useful for more nuanced tasks where its useful to show common errors and spell out exactly why they're wrong and what should be done instead.
+
+#### 2. Number of examples
+
+Once we have a dataset of examples, we need to think about how many examples should be in each prompt.
+The key tradeoff is that more examples generally improve performance, but larger prompts increase costs and latency.
+And beyond some threshold having too many examples can start to confuse the model.
+Finding the right number of examples is highly dependent on the model, the task, the quality of the examples, and your cost and latency constraints.
+Anecdotally, the better the model is the fewer examples it needs to perform well and the more quickly you hit steeply diminishing returns on adding more examples.
+But, the best/only way to reliably answer this question is to run some experiments with different numbers of examples.
+
+#### 3. Selecting examples
+
+Assuming we are not adding our entire example dataset into each prompt, we need to have a way of selecting examples from our dataset based on a given input. We can do this:
+- Randomly
+- By (semantic or keyword-based) similarity of the inputs
+- Based on some other constraints, like token size
+
+LangChain has a number of [`ExampleSelectors`](/docs/concepts/#example-selectors) which make it easy to use any of these techniques.
+
+Generally, selecting by semantic similarity leads to the best model performance. But how important this is is again model and task specific, and is something worth experimenting with.
+
+#### 4. Formatting examples
+
+Most state-of-the-art models these days are chat models, so we'll focus on formatting examples for those. Our basic options are to insert the examples:
+- In the system prompt as a string
+- As their own messages
+
+If we insert our examples into the system prompt as a string, we'll need to make sure it's clear to the model where each example begins and which parts are the input versus output. Different models respond better to different syntaxes, like [ChatML](https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/chat-markup-language), XML, TypeScript, etc.
+
+If we insert our examples as messages, where each example is represented as a sequence of Human, AI messages, we might want to also assign [names](/docs/concepts/#messages) to our messages like `"example_user"` and `"example_assistant"` to make it clear that these messages correspond to different actors than the latest input message.
+
+**Formatting tool call examples**
+
+One area where formatting examples as messages can be tricky is when our example outputs have tool calls. This is because different models have different constraints on what types of message sequences are allowed when any tool calls are generated.
+- Some models require that any AIMessage with tool calls be immediately followed by ToolMessages for every tool call,
+- Some models additionally require that any ToolMessages be immediately followed by an AIMessage before the next HumanMessage,
+- Some models require that tools are passed in to the model if there are any tool calls / ToolMessages in the chat history.
+
+These requirements are model-specific and should be checked for the model you are using. If your model requires ToolMessages after tool calls and/or AIMessages after ToolMessages and your examples only include expected tool calls and not the actual tool outputs, you can try adding dummy ToolMessages / AIMessages to the end of each example with generic contents to satisfy the API constraints.
+In these cases it's especially worth experimenting with inserting your examples as strings versus messages, as having dummy messages can adversely affect certain models.
+
+You can see a case study of how Anthropic and OpenAI respond to different few-shot prompting techniques on two different tool calling benchmarks [here](https://blog.langchain.dev/few-shot-prompting-to-improve-tool-calling-performance/).
+
 ### Retrieval
 
 LLMs are trained on a large but fixed dataset, limiting their ability to reason over private or recent information. Fine-tuning an LLM with specific facts is one way to mitigate this, but is often [poorly suited for factual recall](https://www.anyscale.com/blog/fine-tuning-is-for-form-not-facts) and [can be costly](https://www.glean.com/blog/how-to-build-an-ai-assistant-for-the-enterprise). 

docs/docs/how_to/MultiQueryRetriever.ipynb

@@ -153,7 +153,7 @@
     "\n",
     "    def parse(self, text: str) -> List[str]:\n",
     "        lines = text.strip().split(\"\\n\")\n",
-    "        return lines\n",
+    "        return list(filter(None, lines))  # Remove empty lines\n",
     "\n",
     "\n",
     "output_parser = LineListOutputParser()\n",

docs/docs/how_to/chat_model_caching.ipynb

@@ -63,7 +63,7 @@
    "outputs": [],
    "source": [
     "# <!-- ruff: noqa: F821 -->\n",
-    "from langchain.globals import set_llm_cache"
+    "from langchain_core.globals import set_llm_cache"
    ]
   },
   {
@@ -103,7 +103,7 @@
    ],
    "source": [
     "%%time\n",
-    "from langchain.cache import InMemoryCache\n",
+    "from langchain_core.caches import InMemoryCache\n",
     "\n",
     "set_llm_cache(InMemoryCache())\n",
     "\n",

docs/docs/how_to/chat_model_rate_limiting.ipynb

@@ -0,0 +1,146 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "dcf87b32",
+   "metadata": {},
+   "source": [
+    "# How to handle rate limits\n",
+    "\n",
+    ":::info Prerequisites\n",
+    "\n",
+    "This guide assumes familiarity with the following concepts:\n",
+    "- [Chat models](/docs/concepts/#chat-models)\n",
+    "- [LLMs](/docs/concepts/#llms)\n",
+    ":::\n",
+    "\n",
+    "\n",
+    "You may find yourself in a situation where you are getting rate limited by the model provider API because you're making too many requests.\n",
+    "\n",
+    "For example, this might happen if you are running many parallel queries to benchmark the chat model on a test dataset.\n",
+    "\n",
+    "If you are facing such a situation, you can use a rate limiter to help match the rate at which you're making request to the rate allowed\n",
+    "by the API.\n",
+    "\n",
+    ":::info Requires ``langchain-core >= 0.2.24``\n",
+    "\n",
+    "This functionality was added in ``langchain-core == 0.2.24``. Please make sure your package is up to date.\n",
+    ":::"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cbc3c873-6109-4e03-b775-b73c1003faea",
+   "metadata": {},
+   "source": [
+    "## Initialize a rate limiter\n",
+    "\n",
+    "Langchain comes with a built-in in memory rate limiter. This rate limiter is thread safe and can be shared by multiple threads in the same process.\n",
+    "\n",
+    "The provided rate limiter can only limit the number of requests per unit time. It will not help if you need to also limited based on the size\n",
+    "of the requests."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "aa9c3c8c-0464-4190-a8c5-d69d173505a6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.rate_limiters import InMemoryRateLimiter\n",
+    "\n",
+    "rate_limiter = InMemoryRateLimiter(\n",
+    "    requests_per_second=0.1,  # <-- Super slow! We can only make a request once every 10 seconds!!\n",
+    "    check_every_n_seconds=0.1,  # Wake up every 100 ms to check whether allowed to make a request,\n",
+    "    max_bucket_size=10,  # Controls the maximum burst size.\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8e058bde-9413-4b08-8cc6-0c9cb638f19f",
+   "metadata": {},
+   "source": [
+    "## Choose a model\n",
+    "\n",
+    "Choose any model and pass to it the rate_limiter via the `rate_limiter` attribute."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "0f880a3a-c047-4e94-a323-fff2a4c0e96d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import time\n",
+    "from getpass import getpass\n",
+    "\n",
+    "if \"ANTHROPIC_API_KEY\" not in os.environ:\n",
+    "    os.environ[\"ANTHROPIC_API_KEY\"] = getpass()\n",
+    "\n",
+    "\n",
+    "from langchain_anthropic import ChatAnthropic\n",
+    "\n",
+    "model = ChatAnthropic(model_name=\"claude-3-opus-20240229\", rate_limiter=rate_limiter)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "80c9ab3a-299a-460f-985c-90280a046f52",
+   "metadata": {},
+   "source": [
+    "Let's confirm that the rate limiter works. We should only be able to invoke the model once per 10 seconds."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "d074265c-9f32-4c5f-b914-944148993c4d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "11.599073648452759\n",
+      "10.7502121925354\n",
+      "10.244257926940918\n",
+      "8.83088755607605\n",
+      "11.645203590393066\n"
+     ]
+    }
+   ],
+   "source": [
+    "for _ in range(5):\n",
+    "    tic = time.time()\n",
+    "    model.invoke(\"hello\")\n",
+    "    toc = time.time()\n",
+    "    print(toc - tic)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/how_to/chat_token_usage_tracking.ipynb

@@ -16,7 +16,7 @@
     "\n",
     "Tracking token usage to calculate cost is an important part of putting your app in production. This guide goes over how to obtain this information from your LangChain model calls.\n",
     "\n",
-    "This guide requires `langchain-openai >= 0.1.8`."
+    "This guide requires `langchain-openai >= 0.1.9`."
    ]
   },
   {
@@ -153,7 +153,7 @@
     "\n",
     "#### OpenAI\n",
     "\n",
-    "For example, OpenAI will return a message [chunk](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.ai.AIMessageChunk.html) at the end of a stream with token usage information. This behavior is supported by `langchain-openai >= 0.1.8` and can be enabled by setting `stream_usage=True`. This attribute can also be set when `ChatOpenAI` is instantiated.\n",
+    "For example, OpenAI will return a message [chunk](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.ai.AIMessageChunk.html) at the end of a stream with token usage information. This behavior is supported by `langchain-openai >= 0.1.9` and can be enabled by setting `stream_usage=True`. This attribute can also be set when `ChatOpenAI` is instantiated.\n",
     "\n",
     "```{=mdx}\n",
     ":::note\n",

docs/docs/how_to/code_splitter.ipynb

@@ -54,7 +54,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "9e4144de-d925-4d4c-91c3-685ef8baa57c",
+   "id": "2bb9c73f-9d00-4a19-a81f-cab2f0fd921a",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -63,7 +63,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 4,
    "id": "a9e37aa1",
    "metadata": {},
    "outputs": [],
@@ -718,8 +718,44 @@
     "php_splitter = RecursiveCharacterTextSplitter.from_language(\n",
     "    language=Language.PHP, chunk_size=50, chunk_overlap=0\n",
     ")\n",
-    "haskell_docs = php_splitter.create_documents([PHP_CODE])\n",
-    "haskell_docs"
+    "php_docs = php_splitter.create_documents([PHP_CODE])\n",
+    "php_docs"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e9fa62c1",
+   "metadata": {},
+   "source": [
+    "## PowerShell\n",
+    "Here's an example using the PowerShell text splitter:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7e6893ad",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "POWERSHELL_CODE = \"\"\"\n",
+    "$directoryPath = Get-Location\n",
+    "\n",
+    "$items = Get-ChildItem -Path $directoryPath\n",
+    "\n",
+    "$files = $items | Where-Object { -not $_.PSIsContainer }\n",
+    "\n",
+    "$sortedFiles = $files | Sort-Object LastWriteTime\n",
+    "\n",
+    "foreach ($file in $sortedFiles) {\n",
+    "    Write-Output (\"Name: \" + $file.Name + \" | Last Write Time: \" + $file.LastWriteTime)\n",
+    "}\n",
+    "\"\"\"\n",
+    "powershell_splitter = RecursiveCharacterTextSplitter.from_language(\n",
+    "    language=Language.POWERSHELL, chunk_size=100, chunk_overlap=0\n",
+    ")\n",
+    "powershell_docs = powershell_splitter.create_documents([POWERSHELL_CODE])\n",
+    "powershell_docs"
    ]
   }
  ],
@@ -739,7 +775,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.5"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/how_to/configure.ipynb

@@ -409,7 +409,7 @@
     "    # When configuring the end runnable, we can then use this id to configure this field\n",
     "    ConfigurableField(id=\"prompt\"),\n",
     "    # This sets a default_key.\n",
-    "    # If we specify this key, the default LLM (ChatAnthropic initialized above) will be used\n",
+    "    # If we specify this key, the default prompt (asking for a joke, as initialized above) will be used\n",
     "    default_key=\"joke\",\n",
     "    # This adds a new option, with name `poem`\n",
     "    poem=PromptTemplate.from_template(\"Write a short poem about {topic}\"),\n",
@@ -494,7 +494,7 @@
     "    # When configuring the end runnable, we can then use this id to configure this field\n",
     "    ConfigurableField(id=\"prompt\"),\n",
     "    # This sets a default_key.\n",
-    "    # If we specify this key, the default LLM (ChatAnthropic initialized above) will be used\n",
+    "    # If we specify this key, the default prompt (asking for a joke, as initialized above) will be used\n",
     "    default_key=\"joke\",\n",
     "    # This adds a new option, with name `poem`\n",
     "    poem=PromptTemplate.from_template(\"Write a short poem about {topic}\"),\n",

docs/docs/how_to/contextual_compression.ipynb

@@ -220,6 +220,57 @@
     "pretty_print_docs(compressed_docs)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "14002ec8-7ee5-4f91-9315-dd21c3808776",
+   "metadata": {},
+   "source": [
+    "### `LLMListwiseRerank`\n",
+    "\n",
+    "[LLMListwiseRerank](https://api.python.langchain.com/en/latest/retrievers/langchain.retrievers.document_compressors.listwise_rerank.LLMListwiseRerank.html) uses [zero-shot listwise document reranking](https://arxiv.org/pdf/2305.02156) and functions similarly to `LLMChainFilter` as a robust but more expensive option. It is recommended to use a more powerful LLM.\n",
+    "\n",
+    "Note that `LLMListwiseRerank` requires a model with the [with_structured_output](/docs/integrations/chat/) method implemented."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "4ab9ee9f-917e-4d6f-9344-eb7f01533228",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Document 1:\n",
+      "\n",
+      "Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
+      "\n",
+      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
+      "\n",
+      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
+      "\n",
+      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain.retrievers.document_compressors import LLMListwiseRerank\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n",
+    "\n",
+    "_filter = LLMListwiseRerank.from_llm(llm, top_n=1)\n",
+    "compression_retriever = ContextualCompressionRetriever(\n",
+    "    base_compressor=_filter, base_retriever=retriever\n",
+    ")\n",
+    "\n",
+    "compressed_docs = compression_retriever.invoke(\n",
+    "    \"What did the president say about Ketanji Jackson Brown\"\n",
+    ")\n",
+    "pretty_print_docs(compressed_docs)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "7194da42",
@@ -295,7 +346,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "id": "617a1756",
    "metadata": {},
    "outputs": [],

docs/docs/how_to/convert_runnable_to_tool.ipynb

@@ -5,7 +5,7 @@
    "id": "9a8bceb3-95bd-4496-bb9e-57655136e070",
    "metadata": {},
    "source": [
-    "# How to use Runnables as Tools\n",
+    "# How to convert Runnables as Tools\n",
     "\n",
     ":::info Prerequisites\n",
     "\n",
@@ -267,9 +267,9 @@
     "We first instantiate a chat model that supports [tool calling](/docs/how_to/tool_calling/):\n",
     "\n",
     "```{=mdx}\n",
-    "<ChatModelTabs\n",
-    "  customVarName=\"llm\"\n",
-    "/>\n",
+    "import ChatModelTabs from \"@theme/ChatModelTabs\";\n",
+    "\n",
+    "<ChatModelTabs customVarName=\"llm\" />\n",
     "```"
    ]
   },

docs/docs/how_to/custom_tools.ipynb

@@ -5,7 +5,7 @@
    "id": "5436020b",
    "metadata": {},
    "source": [
-    "# How to create custom tools\n",
+    "# How to create tools\n",
     "\n",
     "When constructing an agent, you will need to provide it with a list of `Tool`s that it can use. Besides the actual function that is called, the Tool consists of several components:\n",
     "\n",
@@ -270,7 +270,7 @@
    "source": [
     "### StructuredTool\n",
     "\n",
-    "The `StrurcturedTool.from_function` class method provides a bit more configurability than the `@tool` decorator, without requiring much additional code."
+    "The `StructuredTool.from_function` class method provides a bit more configurability than the `@tool` decorator, without requiring much additional code."
    ]
   },
   {

docs/docs/how_to/document_loader_custom.ipynb

@@ -63,7 +63,7 @@
     "* The `load` methods is a convenience method meant solely for prototyping work -- it just invokes `list(self.lazy_load())`.\n",
     "* The `alazy_load` has a default implementation that will delegate to `lazy_load`. If you're using async, we recommend overriding the default implementation and providing a native async implementation.\n",
     "\n",
-    "::: {.callout-important}\n",
+    ":::{.callout-important}\n",
     "When implementing a document loader do **NOT** provide parameters via the `lazy_load` or `alazy_load` methods.\n",
     "\n",
     "All configuration is expected to be passed through the initializer (__init__). This was a design choice made by LangChain to make sure that once a document loader has been instantiated it has all the information needed to load documents.\n",
@@ -235,7 +235,7 @@
    "id": "56cb443e-f987-4386-b4ec-975ee129adb2",
    "metadata": {},
    "source": [
-    "::: {.callout-tip}\n",
+    ":::{.callout-tip}\n",
     "\n",
     "`load()` can be helpful in an interactive environment such as a jupyter notebook.\n",
     "\n",
@@ -276,7 +276,7 @@
    "source": [
     "## Working with Files\n",
     "\n",
-    "Many document loaders invovle parsing files. The difference between such loaders usually stems from how the file is parsed rather than how the file is loaded. For example, you can use `open` to read the binary content of either a PDF or a markdown file, but you need different parsing logic to convert that binary data into text.\n",
+    "Many document loaders involve parsing files. The difference between such loaders usually stems from how the file is parsed, rather than how the file is loaded. For example, you can use `open` to read the binary content of either a PDF or a markdown file, but you need different parsing logic to convert that binary data into text.\n",
     "\n",
     "As a result, it can be helpful to decouple the parsing logic from the loading logic, which makes it easier to re-use a given parser regardless of how the data was loaded.\n",
     "\n",
@@ -355,7 +355,7 @@
    "id": "433bfb7c-7767-43bc-b71e-42413d7494a8",
    "metadata": {},
    "source": [
-    "Using the **blob** API also allows one to load content direclty from memory without having to read it from a file!"
+    "Using the **blob** API also allows one to load content directly from memory without having to read it from a file!"
    ]
   },
   {

docs/docs/how_to/document_loader_json.mdx

@@ -182,7 +182,7 @@ pprint(data)
 </CodeOutputBlock>
 
 
-Another option is set `jq_schema='.'` and provide `content_key`:
+Another option is to set `jq_schema='.'` and provide `content_key`:
 
 ```python
 loader = JSONLoader(

docs/docs/how_to/document_loader_markdown.ipynb

@@ -26,7 +26,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install \"unstructured[md]\""
+    "%pip install \"unstructured[md]\" nltk"
    ]
   },
   {

docs/docs/how_to/example_selectors_langsmith.ipynb

@@ -0,0 +1,353 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "4f7e423b",
+   "metadata": {},
+   "source": [
+    "# How to select examples from a LangSmith dataset\n",
+    "\n",
+    "import Prerequisites from \"@theme/Prerequisites\";\n",
+    "import Compatibility from \"@theme/Compatibility\";\n",
+    "\n",
+    "<Prerequisites titlesAndLinks={[\n",
+    "  [\"Chat models\", \"/docs/concepts/#chat-models\"],\n",
+    "  [\"Few-shot-prompting\", \"/docs/concepts/#few-shot-prompting\"],\n",
+    "  [\"LangSmith\", \"/docs/concepts/#langsmith\"],\n",
+    "]} />\n",
+    "\n",
+    "\n",
+    "<Compatibility packagesAndVersions={[\n",
+    "  [\"langsmith\", \"0.1.101\"],\n",
+    "  [\"langchain-core\", \"0.2.34\"],\n",
+    "]} />\n",
+    "\n",
+    "\n",
+    "LangSmith datasets have built-in support for similarity search, making them a great tool for building and querying few-shot examples.\n",
+    "\n",
+    "In this guide we'll see how to use an indexed LangSmith dataset as a few-shot example selector.\n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "Before getting started make sure you've [created a LangSmith account](https://smith.langchain.com/) and set your credentials:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "85445e0e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Set LangSmith API key:\n",
+      "\n",
+      "········\n"
+     ]
+    }
+   ],
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "if not os.environ.get(\"LANGSMITH_API_KEY\"):\n",
+    "    os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Set LangSmith API key:\\n\\n\")\n",
+    "\n",
+    "os.environ[\"LANGSMITH_TRACING\"] = \"true\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ca899e29",
+   "metadata": {},
+   "source": [
+    "We'll need to install the `langsmith` SDK. In this example we'll also make use of `langchain`, `langchain-openai`, and `langchain-benchmarks`:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b4fa7810",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU \"langsmith>=0.1.101\" \"langchain-core>=0.2.34\" langchain langchain-openai langchain-benchmarks"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fc716e12",
+   "metadata": {},
+   "source": [
+    "Now we'll clone a public dataset and turn on indexing for the dataset. We can also turn on indexing via the [LangSmith UI](https://docs.smith.langchain.com/how_to_guides/datasets/index_datasets_for_dynamic_few_shot_example_selection).\n",
+    "\n",
+    "We'll clone the [Multiverse math few shot example dataset](https://blog.langchain.dev/few-shot-prompting-to-improve-tool-calling-performance/).\n",
+    "\n",
+    "This enables searching over the dataset and will make sure that anytime we update/add examples they are also indexed."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cf53d280",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langsmith import Client as LangSmith\n",
+    "\n",
+    "ls_client = LangSmith()\n",
+    "\n",
+    "dataset_name = \"multiverse-math-few-shot-examples-v2\"\n",
+    "dataset_public_url = (\n",
+    "    \"https://smith.langchain.com/public/620596ee-570b-4d2b-8c8f-f828adbe5242/d\"\n",
+    ")\n",
+    "\n",
+    "ls_client.clone_public_dataset(dataset_public_url)\n",
+    "\n",
+    "dataset_id = ls_client.read_dataset(dataset_name=dataset_name).id\n",
+    "\n",
+    "ls_client.index_dataset(dataset_id=dataset_id)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5767d171",
+   "metadata": {},
+   "source": [
+    "## Querying dataset\n",
+    "\n",
+    "Indexing can take a few seconds. Once the dataset is indexed, we can search for similar examples. Note that the input to the `similar_examples` method must have the same schema as the examples inputs. In this case our example inputs are a dictionary with a \"question\" key:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "5013a56f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "3"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "examples = ls_client.similar_examples(\n",
+    "    {\"question\": \"whats the negation of the negation of the negation of 3\"},\n",
+    "    limit=3,\n",
+    "    dataset_id=dataset_id,\n",
+    ")\n",
+    "len(examples)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "a142db06",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'evaluate the negation of -100'"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "examples[0].inputs[\"question\"]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d2627125",
+   "metadata": {},
+   "source": [
+    "For this dataset, the outputs are the conversation that followed the question in OpenAI message format:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "af5b9191",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'role': 'assistant',\n",
+       "  'content': None,\n",
+       "  'tool_calls': [{'id': 'toolu_01HTpq4cYNUac6F7omUc2Wz3',\n",
+       "    'type': 'function',\n",
+       "    'function': {'name': 'negate', 'arguments': '{\"a\": -100}'}}]},\n",
+       " {'role': 'tool',\n",
+       "  'content': '-100.0',\n",
+       "  'tool_call_id': 'toolu_01HTpq4cYNUac6F7omUc2Wz3'},\n",
+       " {'role': 'assistant', 'content': 'So the answer is 100.'},\n",
+       " {'role': 'user',\n",
+       "  'content': '100 is incorrect. Please refer to the output of your tool call.'},\n",
+       " {'role': 'assistant',\n",
+       "  'content': [{'text': \"You're right, my previous answer was incorrect. Let me re-evaluate using the tool output:\",\n",
+       "    'type': 'text'}],\n",
+       "  'tool_calls': [{'id': 'toolu_01XsJQboYghGDygQpPjJkeRq',\n",
+       "    'type': 'function',\n",
+       "    'function': {'name': 'negate', 'arguments': '{\"a\": -100}'}}]},\n",
+       " {'role': 'tool',\n",
+       "  'content': '-100.0',\n",
+       "  'tool_call_id': 'toolu_01XsJQboYghGDygQpPjJkeRq'},\n",
+       " {'role': 'assistant', 'content': 'The answer is -100.0'},\n",
+       " {'role': 'user',\n",
+       "  'content': 'You have the correct numerical answer but are returning additional text. Please only respond with the numerical answer.'},\n",
+       " {'role': 'assistant', 'content': '-100.0'}]"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "examples[0].outputs[\"conversation\"]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e852c8ef",
+   "metadata": {},
+   "source": [
+    "## Creating dynamic few-shot prompts\n",
+    "\n",
+    "The search returns the examples whose inputs are most similar to the query input. We can use this for few-shot prompting a model like so:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "12cba1e1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chat_models import init_chat_model\n",
+    "from langchain_benchmarks.tool_usage.tasks.multiverse_math import (\n",
+    "    add,\n",
+    "    cos,\n",
+    "    divide,\n",
+    "    log,\n",
+    "    multiply,\n",
+    "    negate,\n",
+    "    pi,\n",
+    "    power,\n",
+    "    sin,\n",
+    "    subtract,\n",
+    ")\n",
+    "from langchain_core.runnables import RunnableLambda\n",
+    "from langsmith import AsyncClient as AsyncLangSmith\n",
+    "\n",
+    "async_ls_client = AsyncLangSmith()\n",
+    "\n",
+    "\n",
+    "def similar_examples(input_: dict) -> dict:\n",
+    "    examples = ls_client.similar_examples(input_, limit=5, dataset_id=dataset_id)\n",
+    "    return {**input_, \"examples\": examples}\n",
+    "\n",
+    "\n",
+    "async def asimilar_examples(input_: dict) -> dict:\n",
+    "    examples = await async_ls_client.similar_examples(\n",
+    "        input_, limit=5, dataset_id=dataset_id\n",
+    "    )\n",
+    "    return {**input_, \"examples\": examples}\n",
+    "\n",
+    "\n",
+    "def construct_prompt(input_: dict) -> list:\n",
+    "    instructions = \"\"\"You are great at using mathematical tools.\"\"\"\n",
+    "    examples = []\n",
+    "    for ex in input_[\"examples\"]:\n",
+    "        examples.append({\"role\": \"user\", \"content\": ex.inputs[\"question\"]})\n",
+    "        for msg in ex.outputs[\"conversation\"]:\n",
+    "            if msg[\"role\"] == \"assistant\":\n",
+    "                msg[\"name\"] = \"example_assistant\"\n",
+    "            if msg[\"role\"] == \"user\":\n",
+    "                msg[\"name\"] = \"example_user\"\n",
+    "            examples.append(msg)\n",
+    "    return [\n",
+    "        {\"role\": \"system\", \"content\": instructions},\n",
+    "        *examples,\n",
+    "        {\"role\": \"user\", \"content\": input_[\"question\"]},\n",
+    "    ]\n",
+    "\n",
+    "\n",
+    "tools = [add, cos, divide, log, multiply, negate, pi, power, sin, subtract]\n",
+    "llm = init_chat_model(\"gpt-4o-2024-08-06\")\n",
+    "llm_with_tools = llm.bind_tools(tools)\n",
+    "\n",
+    "example_selector = RunnableLambda(func=similar_examples, afunc=asimilar_examples)\n",
+    "\n",
+    "chain = example_selector | construct_prompt | llm_with_tools"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "c423b367",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'name': 'negate',\n",
+       "  'args': {'a': 3},\n",
+       "  'id': 'call_uMSdoTl6ehfHh5a6JQUb2NoZ',\n",
+       "  'type': 'tool_call'}]"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ai_msg = await chain.ainvoke({\"question\": \"whats the negation of the negation of 3\"})\n",
+    "ai_msg.tool_calls"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "94489b4a",
+   "metadata": {},
+   "source": [
+    "Looking at the LangSmith trace, we can see that relevant examples were pulled in in the `similar_examples` step and passed as messages to ChatOpenAI: https://smith.langchain.com/public/9585e30f-765a-4ed9-b964-2211420cd2f8/r/fdea98d6-e90f-49d4-ac22-dfd012e9e0d9."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "poetry-venv-311",
+   "language": "python",
+   "name": "poetry-venv-311"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/how_to/functions.ipynb

@@ -28,7 +28,7 @@
     "\n",
     "You can use arbitrary functions as [Runnables](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.Runnable.html#langchain_core.runnables.base.Runnable). This is useful for formatting or when you need functionality not provided by other LangChain components, and custom functions used as Runnables are called [`RunnableLambdas`](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.RunnableLambda.html).\n",
     "\n",
-    "Note that all inputs to these functions need to be a SINGLE argument. If you have a function that accepts multiple arguments, you should write a wrapper that accepts a single dict input and unpacks it into multiple argument.\n",
+    "Note that all inputs to these functions need to be a SINGLE argument. If you have a function that accepts multiple arguments, you should write a wrapper that accepts a single dict input and unpacks it into multiple arguments.\n",
     "\n",
     "This guide will cover:\n",
     "\n",

docs/docs/how_to/graph_mapping.ipynb

@@ -364,7 +364,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.chains.graph_qa.cypher_utils import CypherQueryCorrector, Schema\n",
+    "from langchain_community.chains.graph_qa.cypher_utils import (\n",
+    "    CypherQueryCorrector,\n",
+    "    Schema,\n",
+    ")\n",
     "\n",
     "# Cypher validation tool for relationship directions\n",
     "corrector_schema = [\n",

docs/docs/how_to/index.mdx

@@ -31,6 +31,8 @@ This highlights functionality that is core to using LangChain.
 
 [**LCEL cheatsheet**](/docs/how_to/lcel_cheatsheet/): For a quick overview of how to use the main LCEL primitives.
 
+[**Migration guide**](/docs/versions/migrating_chains): For migrating legacy chain abstractions to LCEL.
+
 - [How to: chain runnables](/docs/how_to/sequence)
 - [How to: stream runnables](/docs/how_to/streaming)
 - [How to: invoke runnables in parallel](/docs/how_to/parallel/)
@@ -43,7 +45,7 @@ This highlights functionality that is core to using LangChain.
 - [How to: create a dynamic (self-constructing) chain](/docs/how_to/dynamic_chain/)
 - [How to: inspect runnables](/docs/how_to/inspect)
 - [How to: add fallbacks to a runnable](/docs/how_to/fallbacks)
-- [How to: migrate chains to LCEL](/docs/how_to/migrate_chains)
+- [How to: pass runtime secrets to a runnable](/docs/how_to/runnable_runtime_secrets)
 
 ## Components
 
@@ -67,6 +69,7 @@ These are the core building blocks you can use when building applications.
 - [How to: select examples by semantic similarity](/docs/how_to/example_selectors_similarity)
 - [How to: select examples by semantic ngram overlap](/docs/how_to/example_selectors_ngram)
 - [How to: select examples by maximal marginal relevance](/docs/how_to/example_selectors_mmr)
+- [How to: select examples from LangSmith few-shot datasets](/docs/how_to/example_selectors_langsmith/)
 
 ### Chat models
 
@@ -80,12 +83,13 @@ These are the core building blocks you can use when building applications.
 - [How to: stream a response back](/docs/how_to/chat_streaming)
 - [How to: track token usage](/docs/how_to/chat_token_usage_tracking)
 - [How to: track response metadata across providers](/docs/how_to/response_metadata)
-- [How to: let your end users choose their model](/docs/how_to/chat_models_universal_init/)
 - [How to: use chat model to call tools](/docs/how_to/tool_calling)
 - [How to: stream tool calls](/docs/how_to/tool_streaming)
+- [How to: handle rate limits](/docs/how_to/chat_model_rate_limiting)
 - [How to: few shot prompt tool behavior](/docs/how_to/tools_few_shot)
 - [How to: bind model-specific formatted tools](/docs/how_to/tools_model_specific)
 - [How to: force a specific tool call](/docs/how_to/tool_choice)
+- [How to: work with local models](/docs/how_to/local_llms)
 - [How to: init any model in one line](/docs/how_to/chat_models_universal_init/)
 
 ### Messages
@@ -104,7 +108,7 @@ What LangChain calls [LLMs](/docs/concepts/#llms) are older forms of language mo
 - [How to: create a custom LLM class](/docs/how_to/custom_llm)
 - [How to: stream a response back](/docs/how_to/streaming_llm)
 - [How to: track token usage](/docs/how_to/llm_token_usage_tracking)
-- [How to: work with local LLMs](/docs/how_to/local_llms)
+- [How to: work with local models](/docs/how_to/local_llms)
 
 ### Output parsers
 
@@ -185,19 +189,21 @@ Indexing is the process of keeping your vectorstore in-sync with the underlying
 
 LangChain [Tools](/docs/concepts/#tools) contain a description of the tool (to pass to the language model) as well as the implementation of the function to call. Refer [here](/docs/integrations/tools/) for a list of pre-buit tools. 
 
-- [How to: create custom tools](/docs/how_to/custom_tools)
-- [How to: use built-in tools and built-in toolkits](/docs/how_to/tools_builtin)
-- [How to: convert Runnables to tools](/docs/how_to/convert_runnable_to_tool)
-- [How to: use chat model to call tools](/docs/how_to/tool_calling)
-- [How to: pass tool results back to model](/docs/how_to/tool_results_pass_to_model)
-- [How to: add ad-hoc tool calling capability to LLMs and chat models](/docs/how_to/tools_prompting)
+- [How to: create tools](/docs/how_to/custom_tools)
+- [How to: use built-in tools and toolkits](/docs/how_to/tools_builtin)
+- [How to: use chat models to call tools](/docs/how_to/tool_calling)
+- [How to: pass tool outputs to chat models](/docs/how_to/tool_results_pass_to_model)
 - [How to: pass run time values to tools](/docs/how_to/tool_runtime)
-- [How to: add a human in the loop to tool usage](/docs/how_to/tools_human)
-- [How to: handle errors when calling tools](/docs/how_to/tools_error)
-- [How to: disable parallel tool calling](/docs/how_to/tool_choice)
-- [How to: access the `RunnableConfig` object within a custom tool](/docs/how_to/tool_configure)
-- [How to: stream events from child runs within a custom tool](/docs/how_to/tool_stream_events)
-- [How to: return extra artifacts from a tool](/docs/how_to/tool_artifacts/)
+- [How to: add a human-in-the-loop for tools](/docs/how_to/tools_human)
+- [How to: handle tool errors](/docs/how_to/tools_error)
+- [How to: force models to call a tool](/docs/how_to/tool_choice)
+- [How to: disable parallel tool calling](/docs/how_to/tool_calling_parallel)
+- [How to: access the `RunnableConfig` from a tool](/docs/how_to/tool_configure)
+- [How to: stream events from a tool](/docs/how_to/tool_stream_events)
+- [How to: return artifacts from a tool](/docs/how_to/tool_artifacts/)
+- [How to: convert Runnables to tools](/docs/how_to/convert_runnable_to_tool)
+- [How to: add ad-hoc tool calling capability to models](/docs/how_to/tools_prompting)
+- [How to: pass in runtime secrets](/docs/how_to/runnable_runtime_secrets)
 
 ### Multimodal
 
@@ -310,6 +316,15 @@ For a high-level tutorial, check out [this guide](/docs/tutorials/graph/).
 - [How to: improve results with prompting](/docs/how_to/graph_prompting)
 - [How to: construct knowledge graphs](/docs/how_to/graph_constructing)
 
+### Summarization
+
+LLMs can summarize and otherwise distill desired information from text, including
+large volumes of text. For a high-level tutorial, check out [this guide](/docs/tutorials/summarization).
+
+- [How to: summarize text in a single LLM call](/docs/how_to/summarize_stuff)
+- [How to: summarize text through parallelization](/docs/how_to/summarize_map_reduce)
+- [How to: summarize text through iterative refinement](/docs/how_to/summarize_refine)
+
 ## [LangGraph](https://langchain-ai.github.io/langgraph)
 
 LangGraph is an extension of LangChain aimed at

docs/docs/how_to/indexing.ipynb

@@ -60,7 +60,7 @@
     "   * document addition by id (`add_documents` method with `ids` argument)\n",
     "   * delete by id (`delete` method with `ids` argument)\n",
     "\n",
-    "Compatible Vectorstores: `Aerospike`, `AnalyticDB`, `AstraDB`, `AwaDB`, `AzureCosmosDBNoSqlVectorSearch`, `AzureCosmosDBVectorSearch`, `Bagel`, `Cassandra`, `Chroma`, `CouchbaseVectorStore`, `DashVector`, `DatabricksVectorSearch`, `DeepLake`, `Dingo`, `ElasticVectorSearch`, `ElasticsearchStore`, `FAISS`, `HanaDB`, `Milvus`, `MyScale`, `OpenSearchVectorSearch`, `PGVector`, `Pinecone`, `Qdrant`, `Redis`, `Rockset`, `ScaNN`, `SingleStoreDB`, `SupabaseVectorStore`, `SurrealDBStore`, `TimescaleVector`, `Vald`, `VDMS`, `Vearch`, `VespaStore`, `Weaviate`, `Yellowbrick`, `ZepVectorStore`, `TencentVectorDB`, `OpenSearchVectorSearch`.\n",
+    "Compatible Vectorstores: `Aerospike`, `AnalyticDB`, `AstraDB`, `AwaDB`, `AzureCosmosDBNoSqlVectorSearch`, `AzureCosmosDBVectorSearch`, `Bagel`, `Cassandra`, `Chroma`, `CouchbaseVectorStore`, `DashVector`, `DatabricksVectorSearch`, `DeepLake`, `Dingo`, `ElasticVectorSearch`, `ElasticsearchStore`, `FAISS`, `HanaDB`, `Milvus`, `MongoDBAtlasVectorSearch`, `MyScale`, `OpenSearchVectorSearch`, `PGVector`, `Pinecone`, `Qdrant`, `Redis`, `Rockset`, `ScaNN`, `SingleStoreDB`, `SupabaseVectorStore`, `SurrealDBStore`, `TimescaleVector`, `Vald`, `VDMS`, `Vearch`, `VespaStore`, `Weaviate`, `Yellowbrick`, `ZepVectorStore`, `TencentVectorDB`, `OpenSearchVectorSearch`.\n",
     "  \n",
     "## Caution\n",
     "\n",

docs/docs/how_to/llm_caching.ipynb

@@ -15,21 +15,38 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
-   "id": "0aa6d335",
+   "execution_count": null,
+   "id": "25b0b0fa",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.globals import set_llm_cache\n",
-    "from langchain_openai import OpenAI\n",
+    "%pip install -qU langchain_openai langchain_community\n",
     "\n",
-    "# To make the caching really obvious, lets use a slower model.\n",
-    "llm = OpenAI(model_name=\"gpt-3.5-turbo-instruct\", n=2, best_of=2)"
+    "import os\n",
+    "from getpass import getpass\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = getpass()\n",
+    "# Please manually enter OpenAI Key"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 2,
+   "id": "0aa6d335",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.globals import set_llm_cache\n",
+    "from langchain_openai import OpenAI\n",
+    "\n",
+    "# To make the caching really obvious, lets use a slower and older model.\n",
+    "# Caching supports newer chat models as well.\n",
+    "llm = OpenAI(model=\"gpt-3.5-turbo-instruct\", n=2, best_of=2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
    "id": "f168ff0d",
    "metadata": {},
    "outputs": [
@@ -37,34 +54,34 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "CPU times: user 13.7 ms, sys: 6.54 ms, total: 20.2 ms\n",
-      "Wall time: 330 ms\n"
+      "CPU times: user 546 ms, sys: 379 ms, total: 925 ms\n",
+      "Wall time: 1.11 s\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "\"\\n\\nWhy couldn't the bicycle stand up by itself? Because it was two-tired!\""
+       "\"\\nWhy don't scientists trust atoms?\\n\\nBecause they make up everything!\""
       ]
      },
-     "execution_count": 12,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
     "%%time\n",
-    "from langchain.cache import InMemoryCache\n",
+    "from langchain_core.caches import InMemoryCache\n",
     "\n",
     "set_llm_cache(InMemoryCache())\n",
     "\n",
     "# The first time, it is not yet in cache, so it should take longer\n",
-    "llm.predict(\"Tell me a joke\")"
+    "llm.invoke(\"Tell me a joke\")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 4,
    "id": "ce7620fb",
    "metadata": {},
    "outputs": [
@@ -72,17 +89,17 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "CPU times: user 436 µs, sys: 921 µs, total: 1.36 ms\n",
-      "Wall time: 1.36 ms\n"
+      "CPU times: user 192 µs, sys: 77 µs, total: 269 µs\n",
+      "Wall time: 270 µs\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "\"\\n\\nWhy couldn't the bicycle stand up by itself? Because it was two-tired!\""
+       "\"\\nWhy don't scientists trust atoms?\\n\\nBecause they make up everything!\""
       ]
      },
-     "execution_count": 13,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -90,7 +107,7 @@
    "source": [
     "%%time\n",
     "# The second time it is, so it goes faster\n",
-    "llm.predict(\"Tell me a joke\")"
+    "llm.invoke(\"Tell me a joke\")"
    ]
   },
   {
@@ -103,7 +120,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 5,
    "id": "2e65de83",
    "metadata": {},
    "outputs": [],
@@ -113,7 +130,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 6,
    "id": "0be83715",
    "metadata": {},
    "outputs": [],
@@ -126,7 +143,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 7,
    "id": "9b427ce7",
    "metadata": {},
    "outputs": [
@@ -134,17 +151,17 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "CPU times: user 29.3 ms, sys: 17.3 ms, total: 46.7 ms\n",
-      "Wall time: 364 ms\n"
+      "CPU times: user 10.6 ms, sys: 4.21 ms, total: 14.8 ms\n",
+      "Wall time: 851 ms\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "'\\n\\nWhy did the tomato turn red?\\n\\nBecause it saw the salad dressing!'"
+       "\"\\n\\nWhy don't scientists trust atoms?\\n\\nBecause they make up everything!\""
       ]
      },
-     "execution_count": 10,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -152,12 +169,12 @@
    "source": [
     "%%time\n",
     "# The first time, it is not yet in cache, so it should take longer\n",
-    "llm.predict(\"Tell me a joke\")"
+    "llm.invoke(\"Tell me a joke\")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 8,
    "id": "87f52611",
    "metadata": {},
    "outputs": [
@@ -165,17 +182,17 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "CPU times: user 4.58 ms, sys: 2.23 ms, total: 6.8 ms\n",
-      "Wall time: 4.68 ms\n"
+      "CPU times: user 59.7 ms, sys: 63.6 ms, total: 123 ms\n",
+      "Wall time: 134 ms\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "'\\n\\nWhy did the tomato turn red?\\n\\nBecause it saw the salad dressing!'"
+       "\"\\n\\nWhy don't scientists trust atoms?\\n\\nBecause they make up everything!\""
       ]
      },
-     "execution_count": 11,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -183,7 +200,7 @@
    "source": [
     "%%time\n",
     "# The second time it is, so it goes faster\n",
-    "llm.predict(\"Tell me a joke\")"
+    "llm.invoke(\"Tell me a joke\")"
    ]
   },
   {
@@ -211,7 +228,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.1"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/how_to/local_llms.ipynb

@@ -5,11 +5,11 @@
    "id": "b8982428",
    "metadata": {},
    "source": [
-    "# Run LLMs locally\n",
+    "# Run models locally\n",
     "\n",
     "## Use case\n",
     "\n",
-    "The popularity of projects like [PrivateGPT](https://github.com/imartinez/privateGPT), [llama.cpp](https://github.com/ggerganov/llama.cpp), [Ollama](https://github.com/ollama/ollama), [GPT4All](https://github.com/nomic-ai/gpt4all), [llamafile](https://github.com/Mozilla-Ocho/llamafile), and others underscore the demand to run LLMs locally (on your own device).\n",
+    "The popularity of projects like [llama.cpp](https://github.com/ggerganov/llama.cpp), [Ollama](https://github.com/ollama/ollama), [GPT4All](https://github.com/nomic-ai/gpt4all), [llamafile](https://github.com/Mozilla-Ocho/llamafile), and others underscore the demand to run LLMs locally (on your own device).\n",
     "\n",
     "This has at least two important benefits:\n",
     "\n",
@@ -66,6 +66,12 @@
     "\n",
     "![Image description](../../static/img/llama_t_put.png)\n",
     "\n",
+    "### Formatting prompts\n",
+    "\n",
+    "Some providers have [chat model](/docs/concepts/#chat-models) wrappers that takes care of formatting your input prompt for the specific local model you're using. However, if you are prompting local models with a [text-in/text-out LLM](/docs/concepts/#llms) wrapper, you may need to use a prompt tailed for your specific model.\n",
+    "\n",
+    "This can [require the inclusion of special tokens](https://huggingface.co/blog/llama2#how-to-prompt-llama-2). [Here's an example for LLaMA 2](https://smith.langchain.com/hub/rlm/rag-prompt-llama).\n",
+    "\n",
     "## Quickstart\n",
     "\n",
     "[`Ollama`](https://ollama.ai/) is one way to easily run inference on macOS.\n",
@@ -73,10 +79,20 @@
     "The instructions [here](https://github.com/jmorganca/ollama?tab=readme-ov-file#ollama) provide details, which we summarize:\n",
     " \n",
     "* [Download and run](https://ollama.ai/download) the app\n",
-    "* From command line, fetch a model from this [list of options](https://github.com/jmorganca/ollama): e.g., `ollama pull llama2`\n",
+    "* From command line, fetch a model from this [list of options](https://github.com/jmorganca/ollama): e.g., `ollama pull llama3.1:8b`\n",
     "* When the app is running, all models are automatically served on `localhost:11434`\n"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "29450fc9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU langchain_ollama"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 2,
@@ -86,7 +102,7 @@
     {
      "data": {
       "text/plain": [
-       "' The first man on the moon was Neil Armstrong, who landed on the moon on July 20, 1969 as part of the Apollo 11 mission. obviously.'"
+       "'...Neil Armstrong!\\n\\nOn July 20, 1969, Neil Armstrong became the first person to set foot on the lunar surface, famously declaring \"That\\'s one small step for man, one giant leap for mankind\" as he stepped off the lunar module Eagle onto the Moon\\'s surface.\\n\\nWould you like to know more about the Apollo 11 mission or Neil Armstrong\\'s achievements?'"
       ]
      },
      "execution_count": 2,
@@ -95,51 +111,78 @@
     }
    ],
    "source": [
-    "from langchain_community.llms import Ollama\n",
+    "from langchain_ollama import OllamaLLM\n",
+    "\n",
+    "llm = OllamaLLM(model=\"llama3.1:8b\")\n",
     "\n",
-    "llm = Ollama(model=\"llama2\")\n",
     "llm.invoke(\"The first man on the moon was ...\")"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "343ab645",
+   "id": "674cc672",
    "metadata": {},
    "source": [
-    "Stream tokens as they are being generated."
+    "Stream tokens as they are being generated:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 40,
-   "id": "9cd83603",
+   "execution_count": 3,
+   "id": "1386a852",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " The first man to walk on the moon was Neil Armstrong, an American astronaut who was part of the Apollo 11 mission in 1969. февруари 20, 1969, Armstrong stepped out of the lunar module Eagle and onto the moon's surface, famously declaring \"That's one small step for man, one giant leap for mankind\" as he took his first steps. He was followed by fellow astronaut Edwin \"Buzz\" Aldrin, who also walked on the moon during the mission."
+      "...|"
      ]
     },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Neil| Armstrong|,| an| American| astronaut|.| He| stepped| out| of| the| lunar| module| Eagle| and| onto| the| surface| of| the| Moon| on| July| |20|,| |196|9|,| famously| declaring|:| \"|That|'s| one| small| step| for| man|,| one| giant| leap| for| mankind|.\"||"
+     ]
+    }
+   ],
+   "source": [
+    "for chunk in llm.stream(\"The first man on the moon was ...\"):\n",
+    "    print(chunk, end=\"|\", flush=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e5731060",
+   "metadata": {},
+   "source": [
+    "Ollama also includes a chat model wrapper that handles formatting conversation turns:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "f14a778a",
+   "metadata": {},
+   "outputs": [
     {
      "data": {
       "text/plain": [
-       "' The first man to walk on the moon was Neil Armstrong, an American astronaut who was part of the Apollo 11 mission in 1969. февруари 20, 1969, Armstrong stepped out of the lunar module Eagle and onto the moon\\'s surface, famously declaring \"That\\'s one small step for man, one giant leap for mankind\" as he took his first steps. He was followed by fellow astronaut Edwin \"Buzz\" Aldrin, who also walked on the moon during the mission.'"
+       "AIMessage(content='The answer is a historic one!\\n\\nThe first man to walk on the Moon was Neil Armstrong, an American astronaut and commander of the Apollo 11 mission. On July 20, 1969, Armstrong stepped out of the lunar module Eagle onto the surface of the Moon, famously declaring:\\n\\n\"That\\'s one small step for man, one giant leap for mankind.\"\\n\\nArmstrong was followed by fellow astronaut Edwin \"Buzz\" Aldrin, who also walked on the Moon during the mission. Michael Collins remained in orbit around the Moon in the command module Columbia.\\n\\nNeil Armstrong passed away on August 25, 2012, but his legacy as a pioneering astronaut and engineer continues to inspire people around the world!', response_metadata={'model': 'llama3.1:8b', 'created_at': '2024-08-01T00:38:29.176717Z', 'message': {'role': 'assistant', 'content': ''}, 'done_reason': 'stop', 'done': True, 'total_duration': 10681861417, 'load_duration': 34270292, 'prompt_eval_count': 19, 'prompt_eval_duration': 6209448000, 'eval_count': 141, 'eval_duration': 4432022000}, id='run-7bed57c5-7f54-4092-912c-ae49073dcd48-0', usage_metadata={'input_tokens': 19, 'output_tokens': 141, 'total_tokens': 160})"
       ]
      },
-     "execution_count": 40,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "from langchain_core.callbacks import CallbackManager, StreamingStdOutCallbackHandler\n",
+    "from langchain_ollama import ChatOllama\n",
     "\n",
-    "llm = Ollama(\n",
-    "    model=\"llama2\", callback_manager=CallbackManager([StreamingStdOutCallbackHandler()])\n",
-    ")\n",
-    "llm.invoke(\"The first man on the moon was ...\")"
+    "chat_model = ChatOllama(model=\"llama3.1:8b\")\n",
+    "\n",
+    "chat_model.invoke(\"Who was the first man on the moon?\")"
    ]
   },
   {
@@ -199,7 +242,7 @@
     "\n",
     "With [Ollama](https://github.com/jmorganca/ollama), fetch a model via `ollama pull <model family>:<tag>`:\n",
     "\n",
-    "* E.g., for Llama-7b: `ollama pull llama2` will download the most basic version of the model (e.g., smallest # parameters and 4 bit quantization)\n",
+    "* E.g., for Llama 2 7b: `ollama pull llama2` will download the most basic version of the model (e.g., smallest # parameters and 4 bit quantization)\n",
     "* We can also specify a particular version from the [model list](https://github.com/jmorganca/ollama?tab=readme-ov-file#model-library), e.g., `ollama pull llama2:13b`\n",
     "* See the full set of parameters on the [API reference page](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.ollama.Ollama.html)"
    ]
@@ -222,9 +265,7 @@
     }
    ],
    "source": [
-    "from langchain_community.llms import Ollama\n",
-    "\n",
-    "llm = Ollama(model=\"llama2:13b\")\n",
+    "llm = OllamaLLM(model=\"llama2:13b\")\n",
     "llm.invoke(\"The first man on the moon was ... think step by step\")"
    ]
   },
@@ -268,11 +309,7 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "5eba38dc",
-   "metadata": {
-    "vscode": {
-     "languageId": "plaintext"
-    }
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "%env CMAKE_ARGS=\"-DLLAMA_METAL=on\"\n",
@@ -542,7 +579,6 @@
     }
    ],
    "source": [
-    "from langchain.chains import LLMChain\n",
     "from langchain.chains.prompt_selector import ConditionalPromptSelector\n",
     "from langchain_core.prompts import PromptTemplate\n",
     "\n",
@@ -613,9 +649,9 @@
    ],
    "source": [
     "# Chain\n",
-    "llm_chain = LLMChain(prompt=prompt, llm=llm)\n",
+    "chain = prompt | llm\n",
     "question = \"What NFL team won the Super Bowl in the year that Justin Bieber was born?\"\n",
-    "llm_chain.run({\"question\": question})"
+    "chain.invoke({\"question\": question})"
    ]
   },
   {
@@ -666,7 +702,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.7"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/how_to/migrate_agent.ipynb

@@ -41,7 +41,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "id": "662fac50",
    "metadata": {},
    "outputs": [],
@@ -50,6 +50,26 @@
     "%pip install -U langgraph langchain langchain-openai"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "6f8ec38f",
+   "metadata": {},
+   "source": [
+    "Then, set your OpenAI API key."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "5fca87ef",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"sk-...\""
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "8e50635c-1671-46e6-be65-ce95f8167c2f",
@@ -62,7 +82,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "id": "1e425fea-2796-4b99-bee6-9a6ffe73f756",
    "metadata": {},
    "outputs": [],
@@ -95,7 +115,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "id": "03ea357c-9c36-4464-b2cc-27bd150e1554",
    "metadata": {},
    "outputs": [
@@ -106,7 +126,7 @@
        " 'output': 'The value of `magic_function(3)` is 5.'}"
       ]
      },
-     "execution_count": 2,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -142,7 +162,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "id": "53a3737a-d167-4255-89bf-20ac37f89a3e",
    "metadata": {},
    "outputs": [
@@ -153,7 +173,7 @@
        " 'output': 'The value of `magic_function(3)` is 5.'}"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -173,7 +193,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 5,
    "id": "74ecebe3-512e-409c-a661-bdd5b0a2b782",
    "metadata": {},
    "outputs": [
@@ -181,10 +201,10 @@
      "data": {
       "text/plain": [
        "{'input': 'Pardon?',\n",
-       " 'output': 'The result of applying `magic_function` to the input 3 is 5.'}"
+       " 'output': 'The value you get when you apply `magic_function` to the input 3 is 5.'}"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -223,7 +243,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "id": "a9a11ccd-75e2-4c11-844d-a34870b0ff91",
    "metadata": {},
    "outputs": [
@@ -234,7 +254,7 @@
        " 'output': 'El valor de `magic_function(3)` es 5.'}"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -263,19 +283,19 @@
    "source": [
     "Now, let's pass a custom system message to [react agent executor](https://langchain-ai.github.io/langgraph/reference/prebuilt/#create_react_agent).\n",
     "\n",
-    "LangGraph's prebuilt `create_react_agent` does not take a prompt template directly as a parameter, but instead takes a [`messages_modifier`](https://langchain-ai.github.io/langgraph/reference/prebuilt/#create_react_agent) parameter. This modifies messages before they are passed into the model, and can be one of four values:\n",
+    "LangGraph's prebuilt `create_react_agent` does not take a prompt template directly as a parameter, but instead takes a [`state_modifier`](https://langchain-ai.github.io/langgraph/reference/prebuilt/#create_react_agent) parameter. This modifies the graph state before the llm is called, and can be one of four values:\n",
     "\n",
     "- A `SystemMessage`, which is added to the beginning of the list of messages.\n",
     "- A `string`, which is converted to a `SystemMessage` and added to the beginning of the list of messages.\n",
-    "- A `Callable`, which should take in a list of messages. The output is then passed to the language model.\n",
-    "- Or a [`Runnable`](/docs/concepts/#langchain-expression-language-lcel), which should should take in a list of messages. The output is then passed to the language model.\n",
+    "- A `Callable`, which should take in full graph state. The output is then passed to the language model.\n",
+    "- Or a [`Runnable`](/docs/concepts/#langchain-expression-language-lcel), which should take in full graph state. The output is then passed to the language model.\n",
     "\n",
     "Here's how it looks in action:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "id": "a9486805-676a-4d19-a5c4-08b41b172989",
    "metadata": {},
    "outputs": [],
@@ -287,7 +307,7 @@
     "# This could also be a SystemMessage object\n",
     "# system_message = SystemMessage(content=\"You are a helpful assistant. Respond only in Spanish.\")\n",
     "\n",
-    "app = create_react_agent(model, tools, messages_modifier=system_message)\n",
+    "app = create_react_agent(model, tools, state_modifier=system_message)\n",
     "\n",
     "\n",
     "messages = app.invoke({\"messages\": [(\"user\", query)]})"
@@ -304,7 +324,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "id": "d369ab45-0c82-45f4-9d3e-8efb8dd47e2c",
    "metadata": {},
    "outputs": [
@@ -317,8 +337,8 @@
     }
    ],
    "source": [
-    "from langchain_core.messages import AnyMessage\n",
     "from langgraph.prebuilt import create_react_agent\n",
+    "from langgraph.prebuilt.chat_agent_executor import AgentState\n",
     "\n",
     "prompt = ChatPromptTemplate.from_messages(\n",
     "    [\n",
@@ -328,13 +348,13 @@
     ")\n",
     "\n",
     "\n",
-    "def _modify_messages(messages: list[AnyMessage]):\n",
-    "    return prompt.invoke({\"messages\": messages}).to_messages() + [\n",
+    "def _modify_state_messages(state: AgentState):\n",
+    "    return prompt.invoke({\"messages\": state[\"messages\"]}).to_messages() + [\n",
     "        (\"user\", \"Also say 'Pandamonium!' after the answer.\")\n",
     "    ]\n",
     "\n",
     "\n",
-    "app = create_react_agent(model, tools, messages_modifier=_modify_messages)\n",
+    "app = create_react_agent(model, tools, state_modifier=_modify_state_messages)\n",
     "\n",
     "\n",
     "messages = app.invoke({\"messages\": [(\"human\", query)]})\n",
@@ -366,8 +386,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
-   "id": "1fb52a2c",
+   "execution_count": 9,
+   "id": "b97beba5-8f74-430c-9399-91b77c8fa15c",
    "metadata": {},
    "outputs": [
     {
@@ -376,7 +396,7 @@
      "text": [
       "Hi Polly! The output of the magic function for the input 3 is 5.\n",
       "---\n",
-      "Yes, I remember your name, Polly! How can I assist you further?\n",
+      "Yes, your name is Polly!\n",
       "---\n",
       "The output of the magic function for the input 3 is 5.\n"
      ]
@@ -384,14 +404,14 @@
    ],
    "source": [
     "from langchain.agents import AgentExecutor, create_tool_calling_agent\n",
-    "from langchain_community.chat_message_histories import ChatMessageHistory\n",
+    "from langchain_core.chat_history import InMemoryChatMessageHistory\n",
     "from langchain_core.prompts import ChatPromptTemplate\n",
     "from langchain_core.runnables.history import RunnableWithMessageHistory\n",
     "from langchain_core.tools import tool\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
     "model = ChatOpenAI(model=\"gpt-4o\")\n",
-    "memory = ChatMessageHistory(session_id=\"test-session\")\n",
+    "memory = InMemoryChatMessageHistory(session_id=\"test-session\")\n",
     "prompt = ChatPromptTemplate.from_messages(\n",
     "    [\n",
     "        (\"system\", \"You are a helpful assistant.\"),\n",
@@ -456,24 +476,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
-   "id": "035e1253",
+   "execution_count": 10,
+   "id": "baca3dc6-678b-4509-9275-2fd653102898",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Hi Polly! The output of the magic_function for the input 3 is 5.\n",
+      "Hi Polly! The output of the magic_function for the input of 3 is 5.\n",
       "---\n",
       "Yes, your name is Polly!\n",
       "---\n",
-      "The output of the magic_function for the input 3 was 5.\n"
+      "The output of the magic_function for the input of 3 was 5.\n"
      ]
     }
    ],
    "source": [
-    "from langchain_core.messages import SystemMessage\n",
     "from langgraph.checkpoint import MemorySaver  # an in-memory checkpointer\n",
     "from langgraph.prebuilt import create_react_agent\n",
     "\n",
@@ -483,7 +502,7 @@
     "\n",
     "memory = MemorySaver()\n",
     "app = create_react_agent(\n",
-    "    model, tools, messages_modifier=system_message, checkpointer=memory\n",
+    "    model, tools, state_modifier=system_message, checkpointer=memory\n",
     ")\n",
     "\n",
     "config = {\"configurable\": {\"thread_id\": \"test-thread\"}}\n",
@@ -525,16 +544,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
-   "id": "d640feb3",
+   "execution_count": 11,
+   "id": "e62843c4-1107-41f0-a50b-aea256e28053",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'actions': [ToolAgentAction(tool='magic_function', tool_input={'input': 3}, log=\"\\nInvoking: `magic_function` with `{'input': 3}`\\n\\n\\n\", message_log=[AIMessageChunk(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_q9MgGFjqJbV2xSUX93WqxmOt', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls'}, id='run-c68fd76f-a3c3-4c3c-bfd7-748c171ed4b8', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_q9MgGFjqJbV2xSUX93WqxmOt'}], tool_call_chunks=[{'name': 'magic_function', 'args': '{\"input\":3}', 'id': 'call_q9MgGFjqJbV2xSUX93WqxmOt', 'index': 0}])], tool_call_id='call_q9MgGFjqJbV2xSUX93WqxmOt')], 'messages': [AIMessageChunk(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_q9MgGFjqJbV2xSUX93WqxmOt', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls'}, id='run-c68fd76f-a3c3-4c3c-bfd7-748c171ed4b8', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_q9MgGFjqJbV2xSUX93WqxmOt'}], tool_call_chunks=[{'name': 'magic_function', 'args': '{\"input\":3}', 'id': 'call_q9MgGFjqJbV2xSUX93WqxmOt', 'index': 0}])]}\n",
-      "{'steps': [AgentStep(action=ToolAgentAction(tool='magic_function', tool_input={'input': 3}, log=\"\\nInvoking: `magic_function` with `{'input': 3}`\\n\\n\\n\", message_log=[AIMessageChunk(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_q9MgGFjqJbV2xSUX93WqxmOt', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls'}, id='run-c68fd76f-a3c3-4c3c-bfd7-748c171ed4b8', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_q9MgGFjqJbV2xSUX93WqxmOt'}], tool_call_chunks=[{'name': 'magic_function', 'args': '{\"input\":3}', 'id': 'call_q9MgGFjqJbV2xSUX93WqxmOt', 'index': 0}])], tool_call_id='call_q9MgGFjqJbV2xSUX93WqxmOt'), observation=5)], 'messages': [FunctionMessage(content='5', name='magic_function')]}\n",
+      "{'actions': [ToolAgentAction(tool='magic_function', tool_input={'input': 3}, log=\"\\nInvoking: `magic_function` with `{'input': 3}`\\n\\n\\n\", message_log=[AIMessageChunk(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_1exy0rScfPmo4fy27FbQ5qJ2', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518'}, id='run-5664e138-7085-4da7-a49e-5656a87b8d78', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_1exy0rScfPmo4fy27FbQ5qJ2', 'type': 'tool_call'}], tool_call_chunks=[{'name': 'magic_function', 'args': '{\"input\":3}', 'id': 'call_1exy0rScfPmo4fy27FbQ5qJ2', 'index': 0, 'type': 'tool_call_chunk'}])], tool_call_id='call_1exy0rScfPmo4fy27FbQ5qJ2')], 'messages': [AIMessageChunk(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_1exy0rScfPmo4fy27FbQ5qJ2', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518'}, id='run-5664e138-7085-4da7-a49e-5656a87b8d78', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_1exy0rScfPmo4fy27FbQ5qJ2', 'type': 'tool_call'}], tool_call_chunks=[{'name': 'magic_function', 'args': '{\"input\":3}', 'id': 'call_1exy0rScfPmo4fy27FbQ5qJ2', 'index': 0, 'type': 'tool_call_chunk'}])]}\n",
+      "{'steps': [AgentStep(action=ToolAgentAction(tool='magic_function', tool_input={'input': 3}, log=\"\\nInvoking: `magic_function` with `{'input': 3}`\\n\\n\\n\", message_log=[AIMessageChunk(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_1exy0rScfPmo4fy27FbQ5qJ2', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518'}, id='run-5664e138-7085-4da7-a49e-5656a87b8d78', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_1exy0rScfPmo4fy27FbQ5qJ2', 'type': 'tool_call'}], tool_call_chunks=[{'name': 'magic_function', 'args': '{\"input\":3}', 'id': 'call_1exy0rScfPmo4fy27FbQ5qJ2', 'index': 0, 'type': 'tool_call_chunk'}])], tool_call_id='call_1exy0rScfPmo4fy27FbQ5qJ2'), observation=5)], 'messages': [FunctionMessage(content='5', name='magic_function')]}\n",
       "{'output': 'The value of `magic_function(3)` is 5.', 'messages': [AIMessage(content='The value of `magic_function(3)` is 5.')]}\n"
      ]
     }
@@ -585,23 +604,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
-   "id": "86abbe07",
+   "execution_count": 12,
+   "id": "076ebc85-f804-4093-a25a-a16334c9898e",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_yTjXXibj76tyFyPRa1soLo0S', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 70, 'total_tokens': 84}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-b275f314-c42e-4e77-9dec-5c23f7dbd53b-0', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_yTjXXibj76tyFyPRa1soLo0S'}])]}}\n",
-      "{'tools': {'messages': [ToolMessage(content='5', name='magic_function', id='41c5f227-528d-4483-a313-b03b23b1d327', tool_call_id='call_yTjXXibj76tyFyPRa1soLo0S')]}}\n",
-      "{'agent': {'messages': [AIMessage(content='The value of `magic_function(3)` is 5.', response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 93, 'total_tokens': 107}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'stop', 'logprobs': None}, id='run-0ef12b6e-415d-4758-9b62-5e5e1b350072-0')]}}\n"
+      "{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_my9rzFSKR4T1yYKwCsfbZB8A', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 61, 'total_tokens': 75}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_bc2a86f5f5', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-dd705555-8fae-4fb1-a033-5d99a23e3c22-0', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_my9rzFSKR4T1yYKwCsfbZB8A', 'type': 'tool_call'}], usage_metadata={'input_tokens': 61, 'output_tokens': 14, 'total_tokens': 75})]}}\n",
+      "{'tools': {'messages': [ToolMessage(content='5', name='magic_function', tool_call_id='call_my9rzFSKR4T1yYKwCsfbZB8A')]}}\n",
+      "{'agent': {'messages': [AIMessage(content='The value of `magic_function(3)` is 5.', response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 84, 'total_tokens': 98}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518', 'finish_reason': 'stop', 'logprobs': None}, id='run-698cad05-8cb2-4d08-8c2a-881e354f6cc7-0', usage_metadata={'input_tokens': 84, 'output_tokens': 14, 'total_tokens': 98})]}}\n"
      ]
     }
    ],
    "source": [
-    "from langchain_core.messages import AnyMessage\n",
     "from langgraph.prebuilt import create_react_agent\n",
+    "from langgraph.prebuilt.chat_agent_executor import AgentState\n",
     "\n",
     "prompt = ChatPromptTemplate.from_messages(\n",
     "    [\n",
@@ -611,12 +630,11 @@
     ")\n",
     "\n",
     "\n",
-    "def _modify_messages(messages: list[AnyMessage]):\n",
-    "    return prompt.invoke({\"messages\": messages}).to_messages()\n",
+    "def _modify_state_messages(state: AgentState):\n",
+    "    return prompt.invoke({\"messages\": state[\"messages\"]}).to_messages()\n",
     "\n",
     "\n",
-    "app = create_react_agent(model, tools, messages_modifier=_modify_messages)\n",
-    "\n",
+    "app = create_react_agent(model, tools, state_modifier=_modify_state_messages)\n",
     "\n",
     "for step in app.stream({\"messages\": [(\"human\", query)]}, stream_mode=\"updates\"):\n",
     "    print(step)"
@@ -637,14 +655,14 @@
   {
    "cell_type": "code",
    "execution_count": 12,
-   "id": "4eff44bc-a620-4c8a-97b1-268692a842bb",
+   "id": "a2f720f3-c121-4be2-b498-92c16bb44b0a",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[(ToolAgentAction(tool='magic_function', tool_input={'input': 3}, log=\"\\nInvoking: `magic_function` with `{'input': 3}`\\n\\n\\n\", message_log=[AIMessageChunk(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_ABI4hftfEdnVgKyfF6OzZbca', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls'}, id='run-837e794f-cfd8-40e0-8abc-4d98ced11b75', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_ABI4hftfEdnVgKyfF6OzZbca'}], tool_call_chunks=[{'name': 'magic_function', 'args': '{\"input\":3}', 'id': 'call_ABI4hftfEdnVgKyfF6OzZbca', 'index': 0}])], tool_call_id='call_ABI4hftfEdnVgKyfF6OzZbca'), 5)]\n"
+      "[(ToolAgentAction(tool='magic_function', tool_input={'input': 3}, log=\"\\nInvoking: `magic_function` with `{'input': 3}`\\n\\n\\n\", message_log=[AIMessageChunk(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_uPZ2D1Bo5mdED3gwgaeWURrf', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518'}, id='run-a792db4a-278d-4090-82ae-904a30eada93', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_uPZ2D1Bo5mdED3gwgaeWURrf', 'type': 'tool_call'}], tool_call_chunks=[{'name': 'magic_function', 'args': '{\"input\":3}', 'id': 'call_uPZ2D1Bo5mdED3gwgaeWURrf', 'index': 0, 'type': 'tool_call_chunk'}])], tool_call_id='call_uPZ2D1Bo5mdED3gwgaeWURrf'), 5)]\n"
      ]
     }
    ],
@@ -667,16 +685,16 @@
   {
    "cell_type": "code",
    "execution_count": 13,
-   "id": "4f4364ea-dffe-4d25-bdce-ef7d0020b880",
+   "id": "ef23117a-5ccb-42ce-80c3-ea49a9d3a942",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "{'messages': [HumanMessage(content='what is the value of magic_function(3)?', id='0f63e437-c4d8-4da9-b6f5-b293ebfe4a64'),\n",
-       "  AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_S96v28LlI6hNkQrNnIio0JPh', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 64, 'total_tokens': 78}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-ffef7898-14b1-4537-ad90-7c000a8a5d25-0', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_S96v28LlI6hNkQrNnIio0JPh'}]),\n",
-       "  ToolMessage(content='5', name='magic_function', id='fbd9df4e-1dda-4d3e-9044-b001f7875476', tool_call_id='call_S96v28LlI6hNkQrNnIio0JPh'),\n",
-       "  AIMessage(content='The value of `magic_function(3)` is 5.', response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 87, 'total_tokens': 101}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'stop', 'logprobs': None}, id='run-e5d94c54-d9f4-45cd-be8e-a9101a8d88d6-0')]}"
+       "{'messages': [HumanMessage(content='what is the value of magic_function(3)?', id='cd7d0f49-a0e0-425a-b2b0-603a716058ed'),\n",
+       "  AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_VfZ9287DuybOSrBsQH5X12xf', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 55, 'total_tokens': 69}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-a1e965cd-bf61-44f9-aec1-8aaecb80955f-0', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_VfZ9287DuybOSrBsQH5X12xf', 'type': 'tool_call'}], usage_metadata={'input_tokens': 55, 'output_tokens': 14, 'total_tokens': 69}),\n",
+       "  ToolMessage(content='5', name='magic_function', id='20d5c2fe-a5d8-47fa-9e04-5282642e2039', tool_call_id='call_VfZ9287DuybOSrBsQH5X12xf'),\n",
+       "  AIMessage(content='The value of `magic_function(3)` is 5.', response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 78, 'total_tokens': 92}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518', 'finish_reason': 'stop', 'logprobs': None}, id='run-abf9341c-ef41-4157-935d-a3be5dfa2f41-0', usage_metadata={'input_tokens': 78, 'output_tokens': 14, 'total_tokens': 92})]}"
       ]
      },
      "execution_count": 13,
@@ -708,7 +726,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 16,
    "id": "16f189a7-fc78-4cb5-aa16-a94ca06401a6",
    "metadata": {},
    "outputs": [],
@@ -724,7 +742,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 17,
    "id": "c96aefd7-6f6e-4670-aca6-1ac3d4e7871f",
    "metadata": {},
    "outputs": [
@@ -739,11 +757,7 @@
       "Invoking: `magic_function` with `{'input': '3'}`\n",
       "\n",
       "\n",
-      "\u001b[0m\u001b[36;1m\u001b[1;3mSorry, there was an error. Please try again.\u001b[0m\u001b[32;1m\u001b[1;3m\n",
-      "Invoking: `magic_function` with `{'input': '3'}`\n",
-      "responded: Parece que hubo un error al intentar obtener el valor de `magic_function(3)`. Permíteme intentarlo de nuevo.\n",
-      "\n",
-      "\u001b[0m\u001b[36;1m\u001b[1;3mSorry, there was an error. Please try again.\u001b[0m\u001b[32;1m\u001b[1;3mAún no puedo obtener el valor de `magic_function(3)`. ¿Hay algo más en lo que pueda ayudarte?\u001b[0m\n",
+      "\u001b[0m\u001b[36;1m\u001b[1;3mSorry, there was an error. Please try again.\u001b[0m\u001b[32;1m\u001b[1;3mParece que hubo un error al intentar calcular el valor de la función mágica. ¿Te gustaría que lo intente de nuevo?\u001b[0m\n",
       "\n",
       "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
@@ -752,10 +766,10 @@
      "data": {
       "text/plain": [
        "{'input': 'what is the value of magic_function(3)?',\n",
-       " 'output': 'Aún no puedo obtener el valor de `magic_function(3)`. ¿Hay algo más en lo que pueda ayudarte?'}"
+       " 'output': 'Parece que hubo un error al intentar calcular el valor de la función mágica. ¿Te gustaría que lo intente de nuevo?'}"
       ]
      },
-     "execution_count": 15,
+     "execution_count": 17,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -797,7 +811,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 18,
    "id": "b974a91f-6ae8-4644-83d9-73666258a6db",
    "metadata": {},
    "outputs": [
@@ -805,12 +819,12 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "('human', 'what is the value of magic_function(3)?')\n",
-      "content='' additional_kwargs={'tool_calls': [{'id': 'call_pFdKcCu5taDTtOOfX14vEDRp', 'function': {'arguments': '{\"input\":\"3\"}', 'name': 'magic_function'}, 'type': 'function'}]} response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 64, 'total_tokens': 78}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'tool_calls', 'logprobs': None} id='run-25836468-ba7e-43be-a7cf-76bba06a2a08-0' tool_calls=[{'name': 'magic_function', 'args': {'input': '3'}, 'id': 'call_pFdKcCu5taDTtOOfX14vEDRp'}]\n",
-      "content='Sorry, there was an error. Please try again.' name='magic_function' id='1a08b883-9c7b-4969-9e9b-67ce64cdcb5f' tool_call_id='call_pFdKcCu5taDTtOOfX14vEDRp'\n",
-      "content='It seems there was an error when trying to apply the magic function. Let me try again.' additional_kwargs={'tool_calls': [{'id': 'call_DA0lpDIkBFg2GHy4WsEcZG4K', 'function': {'arguments': '{\"input\":\"3\"}', 'name': 'magic_function'}, 'type': 'function'}]} response_metadata={'token_usage': {'completion_tokens': 34, 'prompt_tokens': 97, 'total_tokens': 131}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'tool_calls', 'logprobs': None} id='run-d571b774-0ea3-4e35-8b7d-f32932c3f3cc-0' tool_calls=[{'name': 'magic_function', 'args': {'input': '3'}, 'id': 'call_DA0lpDIkBFg2GHy4WsEcZG4K'}]\n",
-      "content='Sorry, there was an error. Please try again.' name='magic_function' id='0b45787b-c82a-487f-9a5a-de129c30460f' tool_call_id='call_DA0lpDIkBFg2GHy4WsEcZG4K'\n",
-      "content='It appears that there is a consistent issue when trying to apply the magic function to the input \"3.\" This could be due to various reasons, such as the input not being in the correct format or an internal error.\\n\\nIf you have any other questions or if there\\'s something else you\\'d like to try, please let me know!' response_metadata={'token_usage': {'completion_tokens': 66, 'prompt_tokens': 153, 'total_tokens': 219}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'stop', 'logprobs': None} id='run-50a962e6-21b7-4327-8dea-8e2304062627-0'\n"
+      "content='what is the value of magic_function(3)?' id='74e2d5e8-2b59-4820-979c-8d11ecfc14c2'\n",
+      "content='' additional_kwargs={'tool_calls': [{'id': 'call_ihtrH6IG95pDXpKluIwAgi3J', 'function': {'arguments': '{\"input\":\"3\"}', 'name': 'magic_function'}, 'type': 'function'}]} response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 55, 'total_tokens': 69}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518', 'finish_reason': 'tool_calls', 'logprobs': None} id='run-5a35e465-8a08-43dd-ac8b-4a76dcace305-0' tool_calls=[{'name': 'magic_function', 'args': {'input': '3'}, 'id': 'call_ihtrH6IG95pDXpKluIwAgi3J', 'type': 'tool_call'}] usage_metadata={'input_tokens': 55, 'output_tokens': 14, 'total_tokens': 69}\n",
+      "content='Sorry, there was an error. Please try again.' name='magic_function' id='8c37c19b-3586-46b1-aab9-a045786801a2' tool_call_id='call_ihtrH6IG95pDXpKluIwAgi3J'\n",
+      "content='It seems there was an error in processing the request. Let me try again.' additional_kwargs={'tool_calls': [{'id': 'call_iF0vYWAd6rfely0cXSqdMOnF', 'function': {'arguments': '{\"input\":\"3\"}', 'name': 'magic_function'}, 'type': 'function'}]} response_metadata={'token_usage': {'completion_tokens': 31, 'prompt_tokens': 88, 'total_tokens': 119}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518', 'finish_reason': 'tool_calls', 'logprobs': None} id='run-eb88ec77-d492-43a5-a5dd-4cefef9a6920-0' tool_calls=[{'name': 'magic_function', 'args': {'input': '3'}, 'id': 'call_iF0vYWAd6rfely0cXSqdMOnF', 'type': 'tool_call'}] usage_metadata={'input_tokens': 88, 'output_tokens': 31, 'total_tokens': 119}\n",
+      "content='Sorry, there was an error. Please try again.' name='magic_function' id='c9ff261f-a0f1-4c92-a9f2-cd749f62d911' tool_call_id='call_iF0vYWAd6rfely0cXSqdMOnF'\n",
+      "content='I am currently unable to process the request with the input \"3\" for the `magic_function`. If you have any other questions or need assistance with something else, please let me know!' response_metadata={'token_usage': {'completion_tokens': 39, 'prompt_tokens': 141, 'total_tokens': 180}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518', 'finish_reason': 'stop', 'logprobs': None} id='run-d42508aa-f286-4b57-80fb-f8a76736d470-0' usage_metadata={'input_tokens': 141, 'output_tokens': 39, 'total_tokens': 180}\n"
      ]
     }
    ],
@@ -847,7 +861,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 19,
    "id": "4b8498fc-a7af-4164-a401-d8714f082306",
    "metadata": {},
    "outputs": [
@@ -874,7 +888,7 @@
        " 'output': 'Agent stopped due to max iterations.'}"
       ]
      },
-     "execution_count": 17,
+     "execution_count": 19,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -917,7 +931,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 20,
    "id": "a2b29113-e6be-4f91-aa4c-5c63dea3e423",
    "metadata": {},
    "outputs": [
@@ -925,7 +939,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_HaQkeCwD5QskzJzFixCBacZ4', 'function': {'arguments': '{\"input\":\"3\"}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 64, 'total_tokens': 78}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-596c9200-771f-436d-8576-72fcb81620f1-0', tool_calls=[{'name': 'magic_function', 'args': {'input': '3'}, 'id': 'call_HaQkeCwD5QskzJzFixCBacZ4'}])]}}\n",
+      "{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_FKiTkTd0Ffd4rkYSzERprf1M', 'function': {'arguments': '{\"input\":\"3\"}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 55, 'total_tokens': 69}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-b842f7b6-ec10-40f8-8c0e-baa220b77e91-0', tool_calls=[{'name': 'magic_function', 'args': {'input': '3'}, 'id': 'call_FKiTkTd0Ffd4rkYSzERprf1M', 'type': 'tool_call'}], usage_metadata={'input_tokens': 55, 'output_tokens': 14, 'total_tokens': 69})]}}\n",
       "------\n",
       "{'input': 'what is the value of magic_function(3)?', 'output': 'Agent stopped due to max iterations.'}\n"
      ]
@@ -956,7 +970,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 21,
    "id": "e9eb55f4-a321-4bac-b52d-9e43b411cf92",
    "metadata": {},
    "outputs": [
@@ -964,7 +978,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_4agJXUHtmHrOOMogjF6ZuzAv', 'function': {'arguments': '{\"input\":\"3\"}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 64, 'total_tokens': 78}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-a1c77db7-405f-43d9-8d57-751f2ca1a58c-0', tool_calls=[{'name': 'magic_function', 'args': {'input': '3'}, 'id': 'call_4agJXUHtmHrOOMogjF6ZuzAv'}])]}}\n",
+      "{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_WoOB8juagB08xrP38twYlYKR', 'function': {'arguments': '{\"input\":\"3\"}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 55, 'total_tokens': 69}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-73dee47e-30ab-42c9-bb0c-6f227cac96cd-0', tool_calls=[{'name': 'magic_function', 'args': {'input': '3'}, 'id': 'call_WoOB8juagB08xrP38twYlYKR', 'type': 'tool_call'}], usage_metadata={'input_tokens': 55, 'output_tokens': 14, 'total_tokens': 69})]}}\n",
       "------\n",
       "Task Cancelled.\n"
      ]
@@ -1005,7 +1019,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 22,
    "id": "3f6e2cf2",
    "metadata": {},
    "outputs": [
@@ -1067,7 +1081,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 23,
    "id": "73cabbc4",
    "metadata": {},
    "outputs": [
@@ -1075,10 +1089,10 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "('human', 'what is the value of magic_function(3)?')\n",
-      "content='' additional_kwargs={'tool_calls': [{'id': 'call_bTURmOn9C8zslmn0kMFeykIn', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]} response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 64, 'total_tokens': 78}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'tool_calls', 'logprobs': None} id='run-0844a504-7e6b-4ea6-a069-7017e38121ee-0' tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_bTURmOn9C8zslmn0kMFeykIn'}]\n",
-      "content='Sorry there was an error, please try again.' name='magic_function' id='00d5386f-eb23-4628-9a29-d9ce6a7098cc' tool_call_id='call_bTURmOn9C8zslmn0kMFeykIn'\n",
-      "content='' additional_kwargs={'tool_calls': [{'id': 'call_JYqvvvWmXow2u012DuPoDHFV', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]} response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 96, 'total_tokens': 110}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'tool_calls', 'logprobs': None} id='run-b73b1b1c-c829-4348-98cd-60b315c85448-0' tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_JYqvvvWmXow2u012DuPoDHFV'}]\n",
+      "content='what is the value of magic_function(3)?' id='4fa7fbe5-758c-47a3-9268-717665d10680'\n",
+      "content='' additional_kwargs={'tool_calls': [{'id': 'call_ujE0IQBbIQnxcF9gsZXQfdhF', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]} response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 55, 'total_tokens': 69}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518', 'finish_reason': 'tool_calls', 'logprobs': None} id='run-65d689aa-baee-4342-a5d2-048feefab418-0' tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_ujE0IQBbIQnxcF9gsZXQfdhF', 'type': 'tool_call'}] usage_metadata={'input_tokens': 55, 'output_tokens': 14, 'total_tokens': 69}\n",
+      "content='Sorry there was an error, please try again.' name='magic_function' id='ef8ddf1d-9ad7-4ac0-b784-b673c4d94bbd' tool_call_id='call_ujE0IQBbIQnxcF9gsZXQfdhF'\n",
+      "content='It seems there was an issue with the previous attempt. Let me try that again.' additional_kwargs={'tool_calls': [{'id': 'call_GcsAfCFUHJ50BN2IOWnwTbQ7', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]} response_metadata={'token_usage': {'completion_tokens': 32, 'prompt_tokens': 87, 'total_tokens': 119}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518', 'finish_reason': 'tool_calls', 'logprobs': None} id='run-54527c4b-8ff0-4ee8-8abf-224886bd222e-0' tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_GcsAfCFUHJ50BN2IOWnwTbQ7', 'type': 'tool_call'}] usage_metadata={'input_tokens': 87, 'output_tokens': 32, 'total_tokens': 119}\n",
       "{'input': 'what is the value of magic_function(3)?', 'output': 'Agent stopped due to max iterations.'}\n"
      ]
     }
@@ -1118,7 +1132,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 24,
    "id": "b94bb169",
    "metadata": {},
    "outputs": [
@@ -1216,12 +1230,12 @@
    "source": [
     "### In LangGraph\n",
     "\n",
-    "We can use the [`messages_modifier`](https://langchain-ai.github.io/langgraph/reference/prebuilt/#create_react_agent) just as before when passing in [prompt templates](#prompt-templates)."
+    "We can use the [`state_modifier`](https://langchain-ai.github.io/langgraph/reference/prebuilt/#create_react_agent) just as before when passing in [prompt templates](#prompt-templates)."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 25,
    "id": "b309ba9a",
    "metadata": {},
    "outputs": [
@@ -1246,9 +1260,9 @@
     }
    ],
    "source": [
-    "from langchain_core.messages import AnyMessage\n",
     "from langgraph.errors import GraphRecursionError\n",
     "from langgraph.prebuilt import create_react_agent\n",
+    "from langgraph.prebuilt.chat_agent_executor import AgentState\n",
     "\n",
     "magic_step_num = 1\n",
     "\n",
@@ -1265,12 +1279,12 @@
     "tools = [magic_function]\n",
     "\n",
     "\n",
-    "def _modify_messages(messages: list[AnyMessage]):\n",
+    "def _modify_state_messages(state: AgentState):\n",
     "    # Give the agent amnesia, only keeping the original user query\n",
-    "    return [(\"system\", \"You are a helpful assistant\"), messages[0]]\n",
+    "    return [(\"system\", \"You are a helpful assistant\"), state[\"messages\"][0]]\n",
     "\n",
     "\n",
-    "app = create_react_agent(model, tools, messages_modifier=_modify_messages)\n",
+    "app = create_react_agent(model, tools, state_modifier=_modify_state_messages)\n",
     "\n",
     "try:\n",
     "    for step in app.stream({\"messages\": [(\"human\", query)]}, stream_mode=\"updates\"):\n",
@@ -1308,7 +1322,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.2"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/how_to/migrate_chains.ipynb

@@ -1,798 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "f331037f-be3f-4782-856f-d55dab952488",
-   "metadata": {},
-   "source": [
-    "# How to migrate chains to LCEL\n",
-    "\n",
-    ":::info Prerequisites\n",
-    "\n",
-    "This guide assumes familiarity with the following concepts:\n",
-    "- [LangChain Expression Language](/docs/concepts#langchain-expression-language-lcel)\n",
-    "\n",
-    ":::\n",
-    "\n",
-    "LCEL is designed to streamline the process of building useful apps with LLMs and combining related components. It does this by providing:\n",
-    "\n",
-    "1. **A unified interface**: Every LCEL object implements the `Runnable` interface, which defines a common set of invocation methods (`invoke`, `batch`, `stream`, `ainvoke`, ...). This makes it possible to also automatically and consistently support useful operations like streaming of intermediate steps and batching, since every chain composed of LCEL objects is itself an LCEL object.\n",
-    "2. **Composition primitives**: LCEL provides a number of primitives that make it easy to compose chains, parallelize components, add fallbacks, dynamically configure chain internals, and more.\n",
-    "\n",
-    "LangChain maintains a number of legacy abstractions. Many of these can be reimplemented via short combinations of LCEL primitives. Doing so confers some general advantages:\n",
-    "\n",
-    "- The resulting chains typically implement the full `Runnable` interface, including streaming and asynchronous support where appropriate;\n",
-    "- The chains may be more easily extended or modified;\n",
-    "- The parameters of the chain are typically surfaced for easier customization (e.g., prompts) over previous versions, which tended to be subclasses and had opaque parameters and internals.\n",
-    "\n",
-    "The LCEL implementations can be slightly more verbose, but there are significant benefits in transparency and customizability.\n",
-    "\n",
-    "In this guide we review LCEL implementations of common legacy abstractions. Where appropriate, we link out to separate guides with more detail."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "b99b47ec",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%pip install --upgrade --quiet langchain-community langchain langchain-openai faiss-cpu"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "717c8673",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "from getpass import getpass\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "e3621b62-a037-42b8-8faa-59575608bb8b",
-   "metadata": {},
-   "source": [
-    "## `LLMChain`\n",
-    "<span data-heading-keywords=\"llmchain\"></span>\n",
-    "\n",
-    "[`LLMChain`](https://api.python.langchain.com/en/latest/chains/langchain.chains.llm.LLMChain.html) combined a prompt template, LLM, and output parser into a class.\n",
-    "\n",
-    "Some advantages of switching to the LCEL implementation are:\n",
-    "\n",
-    "- Clarity around contents and parameters. The legacy `LLMChain` contains a default output parser and other options.\n",
-    "- Easier streaming. `LLMChain` only supports streaming via callbacks.\n",
-    "- Easier access to raw message outputs if desired. `LLMChain` only exposes these via a parameter or via callback.\n",
-    "\n",
-    "import { ColumnContainer, Column } from \"@theme/Columns\";\n",
-    "\n",
-    "<ColumnContainer>\n",
-    "\n",
-    "<Column>\n",
-    "\n",
-    "#### Legacy\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "e628905c-430e-4e4a-9d7c-c91d2f42052e",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'adjective': 'funny',\n",
-       " 'text': \"Why couldn't the bicycle find its way home?\\n\\nBecause it lost its bearings!\"}"
-      ]
-     },
-     "execution_count": 11,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain.chains import LLMChain\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [(\"user\", \"Tell me a {adjective} joke\")],\n",
-    ")\n",
-    "\n",
-    "chain = LLMChain(llm=ChatOpenAI(), prompt=prompt)\n",
-    "\n",
-    "chain({\"adjective\": \"funny\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "cdc3b527-c09e-4c77-9711-c3cc4506cd95",
-   "metadata": {},
-   "source": [
-    "\n",
-    "</Column>\n",
-    "\n",
-    "<Column>\n",
-    "\n",
-    "#### LCEL\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "0d2a7cf8-1bc7-405c-bb0d-f2ab2ba3b6ab",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\"Why couldn't the bicycle stand up by itself?\\n\\nBecause it was two tired!\""
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [(\"user\", \"Tell me a {adjective} joke\")],\n",
-    ")\n",
-    "\n",
-    "chain = prompt | ChatOpenAI() | StrOutputParser()\n",
-    "\n",
-    "chain.invoke({\"adjective\": \"funny\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "3c0b0513-77b8-4371-a20e-3e487cec7e7f",
-   "metadata": {},
-   "source": [
-    "\n",
-    "</Column>\n",
-    "</ColumnContainer>\n",
-    "\n",
-    "Note that `LLMChain` by default returns a `dict` containing both the input and the output. If this behavior is desired, we can replicate it using another LCEL primitive, [`RunnablePassthrough`](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.passthrough.RunnablePassthrough.html):"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "529206c5-abbe-4213-9e6c-3b8586c8000d",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'adjective': 'funny',\n",
-       " 'text': \"Why couldn't the bicycle stand up by itself?\\n\\nBecause it was two tired!\"}"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_core.runnables import RunnablePassthrough\n",
-    "\n",
-    "outer_chain = RunnablePassthrough().assign(text=chain)\n",
-    "\n",
-    "outer_chain.invoke({\"adjective\": \"funny\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "29d2e26c-2854-4971-9c2b-613450993921",
-   "metadata": {},
-   "source": [
-    "See [this tutorial](/docs/tutorials/llm_chain) for more detail on building with prompt templates, LLMs, and output parsers."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "00df631d-5121-4918-94aa-b88acce9b769",
-   "metadata": {},
-   "source": [
-    "## `ConversationChain`\n",
-    "<span data-heading-keywords=\"conversationchain\"></span>\n",
-    "\n",
-    "[`ConversationChain`](https://api.python.langchain.com/en/latest/chains/langchain.chains.conversation.base.ConversationChain.html) incorporates a memory of previous messages to sustain a stateful conversation.\n",
-    "\n",
-    "Some advantages of switching to the LCEL implementation are:\n",
-    "\n",
-    "- Innate support for threads/separate sessions. To make this work with `ConversationChain`, you'd need to instantiate a separate memory class outside the chain.\n",
-    "- More explicit parameters. `ConversationChain` contains a hidden default prompt, which can cause confusion.\n",
-    "- Streaming support. `ConversationChain` only supports streaming via callbacks.\n",
-    "\n",
-    "`RunnableWithMessageHistory` implements sessions via configuration parameters. It should be instantiated with a callable that returns a [chat message history](https://api.python.langchain.com/en/latest/chat_history/langchain_core.chat_history.BaseChatMessageHistory.html). By default, it expects this function to take a single argument `session_id`.\n",
-    "\n",
-    "<ColumnContainer>\n",
-    "<Column>\n",
-    "\n",
-    "#### Legacy\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "4f2cc6dc-d70a-4c13-9258-452f14290da6",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'input': 'how are you?',\n",
-       " 'history': '',\n",
-       " 'response': \"Arrr, I be doin' well, me matey! Just sailin' the high seas in search of treasure and adventure. How can I assist ye today?\"}"
-      ]
-     },
-     "execution_count": 15,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain.chains import ConversationChain\n",
-    "from langchain.memory import ConversationBufferMemory\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "template = \"\"\"\n",
-    "You are a pirate. Answer the following questions as best you can.\n",
-    "Chat history: {history}\n",
-    "Question: {input}\n",
-    "\"\"\"\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_template(template)\n",
-    "\n",
-    "memory = ConversationBufferMemory()\n",
-    "\n",
-    "chain = ConversationChain(\n",
-    "    llm=ChatOpenAI(),\n",
-    "    memory=memory,\n",
-    "    prompt=prompt,\n",
-    ")\n",
-    "\n",
-    "chain({\"input\": \"how are you?\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "f8e36b0e-c7dc-4130-a51b-189d4b756c7f",
-   "metadata": {},
-   "source": [
-    "</Column>\n",
-    "\n",
-    "<Column>\n",
-    "\n",
-    "#### LCEL\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "173e1a9c-2a18-4669-b0de-136f39197786",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\"Arr, matey! I be sailin' the high seas with me crew, searchin' for buried treasure and adventure! How be ye doin' on this fine day?\""
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_core.chat_history import InMemoryChatMessageHistory\n",
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_core.runnables.history import RunnableWithMessageHistory\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\"system\", \"You are a pirate. Answer the following questions as best you can.\"),\n",
-    "        (\"placeholder\", \"{chat_history}\"),\n",
-    "        (\"human\", \"{input}\"),\n",
-    "    ]\n",
-    ")\n",
-    "\n",
-    "history = InMemoryChatMessageHistory()\n",
-    "\n",
-    "chain = prompt | ChatOpenAI() | StrOutputParser()\n",
-    "\n",
-    "wrapped_chain = RunnableWithMessageHistory(chain, lambda x: history)\n",
-    "\n",
-    "wrapped_chain.invoke(\n",
-    "    {\"input\": \"how are you?\"},\n",
-    "    config={\"configurable\": {\"session_id\": \"42\"}},\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "6b386ce6-895e-442c-88f3-7bec0ab9f401",
-   "metadata": {},
-   "source": [
-    "\n",
-    "</Column>\n",
-    "</ColumnContainer>\n",
-    "\n",
-    "The above example uses the same `history` for all sessions. The example below shows how to use a different chat history for each session."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "4e05994f-1fbc-4699-bf2e-62cb0e4deeb8",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\"Ahoy there! What be ye wantin' from this old pirate?\", response_metadata={'token_usage': {'completion_tokens': 15, 'prompt_tokens': 29, 'total_tokens': 44}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-1846d5f5-0dda-43b6-bb49-864e541f9c29-0', usage_metadata={'input_tokens': 29, 'output_tokens': 15, 'total_tokens': 44})"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_core.chat_history import BaseChatMessageHistory\n",
-    "from langchain_core.runnables.history import RunnableWithMessageHistory\n",
-    "\n",
-    "store = {}\n",
-    "\n",
-    "\n",
-    "def get_session_history(session_id: str) -> BaseChatMessageHistory:\n",
-    "    if session_id not in store:\n",
-    "        store[session_id] = InMemoryChatMessageHistory()\n",
-    "    return store[session_id]\n",
-    "\n",
-    "\n",
-    "chain = prompt | ChatOpenAI() | StrOutputParser()\n",
-    "\n",
-    "wrapped_chain = RunnableWithMessageHistory(chain, get_session_history)\n",
-    "\n",
-    "wrapped_chain.invoke(\"Hello!\", config={\"configurable\": {\"session_id\": \"abc123\"}})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "c36ebecb",
-   "metadata": {},
-   "source": [
-    "See [this tutorial](/docs/tutorials/chatbot) for a more end-to-end guide on building with [`RunnableWithMessageHistory`](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.history.RunnableWithMessageHistory.html).\n",
-    "\n",
-    "## `RetrievalQA`\n",
-    "<span data-heading-keywords=\"retrievalqa\"></span>\n",
-    "\n",
-    "The [`RetrievalQA`](https://api.python.langchain.com/en/latest/chains/langchain.chains.retrieval_qa.base.RetrievalQA.html) chain performed natural-language question answering over a data source using retrieval-augmented generation.\n",
-    "\n",
-    "Some advantages of switching to the LCEL implementation are:\n",
-    "\n",
-    "- Easier customizability. Details such as the prompt and how documents are formatted are only configurable via specific parameters in the `RetrievalQA` chain.\n",
-    "- More easily return source documents.\n",
-    "- Support for runnable methods like streaming and async operations.\n",
-    "\n",
-    "Now let's look at them side-by-side. We'll use the same ingestion code to load a [blog post by Lilian Weng](https://lilianweng.github.io/posts/2023-06-23-agent/) on autonomous agents into a local vector store:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "1efbe16e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Load docs\n",
-    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
-    "from langchain_community.document_loaders import WebBaseLoader\n",
-    "from langchain_community.vectorstores import FAISS\n",
-    "from langchain_openai.chat_models import ChatOpenAI\n",
-    "from langchain_openai.embeddings import OpenAIEmbeddings\n",
-    "\n",
-    "loader = WebBaseLoader(\"https://lilianweng.github.io/posts/2023-06-23-agent/\")\n",
-    "data = loader.load()\n",
-    "\n",
-    "# Split\n",
-    "text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)\n",
-    "all_splits = text_splitter.split_documents(data)\n",
-    "\n",
-    "# Store splits\n",
-    "vectorstore = FAISS.from_documents(documents=all_splits, embedding=OpenAIEmbeddings())\n",
-    "\n",
-    "# LLM\n",
-    "llm = ChatOpenAI()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "c7e16438",
-   "metadata": {},
-   "source": [
-    "<ColumnContainer>\n",
-    "\n",
-    "<Column>\n",
-    "\n",
-    "#### Legacy"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "id": "43bf55a0",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'query': 'What are autonomous agents?',\n",
-       " 'result': 'Autonomous agents are LLM-empowered agents that handle autonomous design, planning, and performance of complex tasks, such as scientific experiments. These agents can browse the Internet, read documentation, execute code, call robotics experimentation APIs, and leverage other LLMs. They are capable of reasoning and planning ahead for complicated tasks by breaking them down into smaller steps.'}"
-      ]
-     },
-     "execution_count": 22,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain import hub\n",
-    "from langchain.chains import RetrievalQA\n",
-    "\n",
-    "# See full prompt at https://smith.langchain.com/hub/rlm/rag-prompt\n",
-    "prompt = hub.pull(\"rlm/rag-prompt\")\n",
-    "\n",
-    "qa_chain = RetrievalQA.from_llm(\n",
-    "    llm, retriever=vectorstore.as_retriever(), prompt=prompt\n",
-    ")\n",
-    "\n",
-    "qa_chain(\"What are autonomous agents?\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "081948e5",
-   "metadata": {},
-   "source": [
-    "</Column>\n",
-    "\n",
-    "<Column>\n",
-    "\n",
-    "#### LCEL\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "id": "9efcc931",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Autonomous agents are agents that can handle autonomous design, planning, and performance of complex tasks, such as scientific experiments. They can browse the Internet, read documentation, execute code, call robotics experimentation APIs, and leverage other language model models. These agents use reasoning steps to develop solutions to specific tasks, like creating a novel anticancer drug.'"
-      ]
-     },
-     "execution_count": 17,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain import hub\n",
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.runnables import RunnablePassthrough\n",
-    "\n",
-    "# See full prompt at https://smith.langchain.com/hub/rlm/rag-prompt\n",
-    "prompt = hub.pull(\"rlm/rag-prompt\")\n",
-    "\n",
-    "\n",
-    "def format_docs(docs):\n",
-    "    return \"\\n\\n\".join(doc.page_content for doc in docs)\n",
-    "\n",
-    "\n",
-    "qa_chain = (\n",
-    "    {\n",
-    "        \"context\": vectorstore.as_retriever() | format_docs,\n",
-    "        \"question\": RunnablePassthrough(),\n",
-    "    }\n",
-    "    | prompt\n",
-    "    | llm\n",
-    "    | StrOutputParser()\n",
-    ")\n",
-    "\n",
-    "qa_chain.invoke(\"What are autonomous agents?\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "d6f44fe8",
-   "metadata": {},
-   "source": [
-    "</Column>\n",
-    "</ColumnContainer>\n",
-    "\n",
-    "The LCEL implementation exposes the internals of what's happening around retrieving, formatting documents, and passing them through a prompt to the LLM, but it is more verbose. You can customize and wrap this composition logic in a helper function, or use the higher-level [`create_retrieval_chain`](https://api.python.langchain.com/en/latest/chains/langchain.chains.retrieval.create_retrieval_chain.html) and [`create_stuff_documents_chain`](https://api.python.langchain.com/en/latest/chains/langchain.chains.combine_documents.stuff.create_stuff_documents_chain.html) helper method:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 20,
-   "id": "5fe42761",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'input': 'What are autonomous agents?',\n",
-       " 'context': [Document(page_content='Boiko et al. (2023) also looked into LLM-empowered agents for scientific discovery, to handle autonomous design, planning, and performance of complex scientific experiments. This agent can use tools to browse the Internet, read documentation, execute code, call robotics experimentation APIs and leverage other LLMs.\\nFor example, when requested to \"develop a novel anticancer drug\", the model came up with the following reasoning steps:', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}),\n",
-       "  Document(page_content='Weng, Lilian. (Jun 2023). “LLM-powered Autonomous Agents”. Lil’Log. https://lilianweng.github.io/posts/2023-06-23-agent/.', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}),\n",
-       "  Document(page_content='Fig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}),\n",
-       "  Document(page_content=\"LLM Powered Autonomous Agents | Lil'Log\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\nLil'Log\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\nPosts\\n\\n\\n\\n\\nArchive\\n\\n\\n\\n\\nSearch\\n\\n\\n\\n\\nTags\\n\\n\\n\\n\\nFAQ\\n\\n\\n\\n\\nemojisearch.app\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n      LLM Powered Autonomous Agents\\n    \\nDate: June 23, 2023  |  Estimated Reading Time: 31 min  |  Author: Lilian Weng\\n\\n\\n \\n\\n\\nTable of Contents\\n\\n\\n\\nAgent System Overview\\n\\nComponent One: Planning\\n\\nTask Decomposition\\n\\nSelf-Reflection\\n\\n\\nComponent Two: Memory\\n\\nTypes of Memory\\n\\nMaximum Inner Product Search (MIPS)\", metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'})],\n",
-       " 'answer': 'Autonomous agents are entities that can operate independently, making decisions and taking actions without direct human intervention. These agents can perform tasks such as planning, executing complex experiments, and leveraging various tools and resources to achieve objectives. In the context provided, LLM-powered autonomous agents are specifically designed for scientific discovery, capable of handling tasks like designing novel anticancer drugs through reasoning steps.'}"
-      ]
-     },
-     "execution_count": 20,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain import hub\n",
-    "from langchain.chains import create_retrieval_chain\n",
-    "from langchain.chains.combine_documents import create_stuff_documents_chain\n",
-    "\n",
-    "# See full prompt at https://smith.langchain.com/hub/langchain-ai/retrieval-qa-chat\n",
-    "retrieval_qa_chat_prompt = hub.pull(\"langchain-ai/retrieval-qa-chat\")\n",
-    "\n",
-    "combine_docs_chain = create_stuff_documents_chain(llm, retrieval_qa_chat_prompt)\n",
-    "rag_chain = create_retrieval_chain(vectorstore.as_retriever(), combine_docs_chain)\n",
-    "\n",
-    "rag_chain.invoke({\"input\": \"What are autonomous agents?\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2772f4e9",
-   "metadata": {},
-   "source": [
-    "## `ConversationalRetrievalChain`\n",
-    "<span data-heading-keywords=\"conversationalretrievalchain\"></span>\n",
-    "\n",
-    "The [`ConversationalRetrievalChain`](https://api.python.langchain.com/en/latest/chains/langchain.chains.conversational_retrieval.base.ConversationalRetrievalChain.html) was an all-in one way that combined retrieval-augmented generation with chat history, allowing you to \"chat with\" your documents.\n",
-    "\n",
-    "Advantages of switching to the LCEL implementation are similar to the `RetrievalQA` section above:\n",
-    "\n",
-    "- Clearer internals. The `ConversationalRetrievalChain` chain hides an entire question rephrasing step which dereferences the initial query against the chat history.\n",
-    "  - This means the class contains two sets of configurable prompts, LLMs, etc.\n",
-    "- More easily return source documents.\n",
-    "- Support for runnable methods like streaming and async operations.\n",
-    "\n",
-    "Here are side-by-side implementations with custom prompts. We'll reuse the loaded documents and vector store from the previous section:"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "8bc06416",
-   "metadata": {},
-   "source": [
-    "<ColumnContainer>\n",
-    "\n",
-    "<Column>\n",
-    "\n",
-    "#### Legacy"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 31,
-   "id": "54eb9576",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'question': 'What are autonomous agents?',\n",
-       " 'chat_history': '',\n",
-       " 'answer': 'Autonomous agents are powered by Large Language Models (LLMs) to handle tasks like scientific discovery and complex experiments autonomously. These agents can browse the internet, read documentation, execute code, and leverage other LLMs to perform tasks. They can reason and plan ahead to decompose complicated tasks into manageable steps.'}"
-      ]
-     },
-     "execution_count": 31,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain.chains import ConversationalRetrievalChain\n",
-    "\n",
-    "condense_question_template = \"\"\"\n",
-    "Given the following conversation and a follow up question, rephrase the follow up question to be a standalone question.\n",
-    "\n",
-    "Chat History:\n",
-    "{chat_history}\n",
-    "Follow Up Input: {question}\n",
-    "Standalone question:\"\"\"\n",
-    "\n",
-    "condense_question_prompt = ChatPromptTemplate.from_template(condense_question_template)\n",
-    "\n",
-    "qa_template = \"\"\"\n",
-    "You are an assistant for question-answering tasks.\n",
-    "Use the following pieces of retrieved context to answer\n",
-    "the question. If you don't know the answer, say that you\n",
-    "don't know. Use three sentences maximum and keep the\n",
-    "answer concise.\n",
-    "\n",
-    "Chat History:\n",
-    "{chat_history}\n",
-    "\n",
-    "Other context:\n",
-    "{context}\n",
-    "\n",
-    "Question: {question}\n",
-    "\"\"\"\n",
-    "\n",
-    "qa_prompt = ChatPromptTemplate.from_template(qa_template)\n",
-    "\n",
-    "convo_qa_chain = ConversationalRetrievalChain.from_llm(\n",
-    "    llm,\n",
-    "    vectorstore.as_retriever(),\n",
-    "    condense_question_prompt=condense_question_prompt,\n",
-    "    combine_docs_chain_kwargs={\n",
-    "        \"prompt\": qa_prompt,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "convo_qa_chain(\n",
-    "    {\n",
-    "        \"question\": \"What are autonomous agents?\",\n",
-    "        \"chat_history\": \"\",\n",
-    "    }\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "43a8a23c",
-   "metadata": {},
-   "source": [
-    "</Column>\n",
-    "\n",
-    "<Column>\n",
-    "\n",
-    "#### LCEL\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 25,
-   "id": "c884b138",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'input': 'What are autonomous agents?',\n",
-       " 'chat_history': [],\n",
-       " 'context': [Document(page_content='Boiko et al. (2023) also looked into LLM-empowered agents for scientific discovery, to handle autonomous design, planning, and performance of complex scientific experiments. This agent can use tools to browse the Internet, read documentation, execute code, call robotics experimentation APIs and leverage other LLMs.\\nFor example, when requested to \"develop a novel anticancer drug\", the model came up with the following reasoning steps:', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}),\n",
-       "  Document(page_content='Weng, Lilian. (Jun 2023). “LLM-powered Autonomous Agents”. Lil’Log. https://lilianweng.github.io/posts/2023-06-23-agent/.', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}),\n",
-       "  Document(page_content='Fig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}),\n",
-       "  Document(page_content='Or\\n@article{weng2023agent,\\n  title   = \"LLM-powered Autonomous Agents\",\\n  author  = \"Weng, Lilian\",\\n  journal = \"lilianweng.github.io\",\\n  year    = \"2023\",\\n  month   = \"Jun\",\\n  url     = \"https://lilianweng.github.io/posts/2023-06-23-agent/\"\\n}\\nReferences#\\n[1] Wei et al. “Chain of thought prompting elicits reasoning in large language models.” NeurIPS 2022\\n[2] Yao et al. “Tree of Thoughts: Dliberate Problem Solving with Large Language Models.” arXiv preprint arXiv:2305.10601 (2023).', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'})],\n",
-       " 'answer': 'Autonomous agents are entities capable of acting independently, making decisions, and performing tasks without direct human intervention. These agents can interact with their environment, perceive information, and take actions based on their goals or objectives. They often use artificial intelligence techniques to navigate and accomplish tasks in complex or dynamic environments.'}"
-      ]
-     },
-     "execution_count": 25,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain.chains import create_history_aware_retriever, create_retrieval_chain\n",
-    "\n",
-    "condense_question_system_template = (\n",
-    "    \"Given a chat history and the latest user question \"\n",
-    "    \"which might reference context in the chat history, \"\n",
-    "    \"formulate a standalone question which can be understood \"\n",
-    "    \"without the chat history. Do NOT answer the question, \"\n",
-    "    \"just reformulate it if needed and otherwise return it as is.\"\n",
-    ")\n",
-    "\n",
-    "condense_question_prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\"system\", condense_question_system_template),\n",
-    "        (\"placeholder\", \"{chat_history}\"),\n",
-    "        (\"human\", \"{input}\"),\n",
-    "    ]\n",
-    ")\n",
-    "history_aware_retriever = create_history_aware_retriever(\n",
-    "    llm, vectorstore.as_retriever(), condense_question_prompt\n",
-    ")\n",
-    "\n",
-    "system_prompt = (\n",
-    "    \"You are an assistant for question-answering tasks. \"\n",
-    "    \"Use the following pieces of retrieved context to answer \"\n",
-    "    \"the question. If you don't know the answer, say that you \"\n",
-    "    \"don't know. Use three sentences maximum and keep the \"\n",
-    "    \"answer concise.\"\n",
-    "    \"\\n\\n\"\n",
-    "    \"{context}\"\n",
-    ")\n",
-    "\n",
-    "qa_prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\"system\", system_prompt),\n",
-    "        (\"placeholder\", \"{chat_history}\"),\n",
-    "        (\"human\", \"{input}\"),\n",
-    "    ]\n",
-    ")\n",
-    "qa_chain = create_stuff_documents_chain(llm, qa_prompt)\n",
-    "\n",
-    "convo_qa_chain = create_retrieval_chain(history_aware_retriever, qa_chain)\n",
-    "\n",
-    "convo_qa_chain.invoke(\n",
-    "    {\n",
-    "        \"input\": \"What are autonomous agents?\",\n",
-    "        \"chat_history\": [],\n",
-    "    }\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "b2717810",
-   "metadata": {},
-   "source": [
-    "</Column>\n",
-    "\n",
-    "</ColumnContainer>\n",
-    "\n",
-    "## Next steps\n",
-    "\n",
-    "You've now seen how to migrate existing usage of some legacy chains to LCEL.\n",
-    "\n",
-    "Next, check out the [LCEL conceptual docs](/docs/concepts/#langchain-expression-language-lcel) for more background information."
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.10.5"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/docs/how_to/pydantic_compatibility.md

@@ -1,27 +1,103 @@
 # How to use LangChain with different Pydantic versions
 
-- Pydantic v2 was released in June, 2023 (https://docs.pydantic.dev/2.0/blog/pydantic-v2-final/)
-- v2 contains has a number of breaking changes (https://docs.pydantic.dev/2.0/migration/)
-- Pydantic v2 and v1 are under the same package name, so both versions cannot be installed at the same time
+- Pydantic v2 was released in June, 2023 (https://docs.pydantic.dev/2.0/blog/pydantic-v2-final/).
+- v2 contains has a number of breaking changes (https://docs.pydantic.dev/2.0/migration/).
+- Pydantic 1 End of Life was in June 2024. LangChain will be dropping support for Pydantic 1 in the near future,
+and likely migrating internally to Pydantic 2. The timeline is tentatively September. This change will be accompanied by a minor version bump in the main langchain packages to version 0.3.x.
 
-## LangChain Pydantic migration plan
+As of `langchain>=0.0.267`, LangChain allows users to install either Pydantic V1 or V2.
 
-As of `langchain>=0.0.267`, LangChain will allow users to install either Pydantic V1 or V2. 
-   * Internally LangChain will continue to [use V1](https://docs.pydantic.dev/latest/migration/#continue-using-pydantic-v1-features).
-   * During this time, users can pin their pydantic version to v1 to avoid breaking changes, or start a partial
-   migration using pydantic v2 throughout their code, but avoiding mixing v1 and v2 code for LangChain (see below).
+Internally, LangChain continues to use the [Pydantic V1](https://docs.pydantic.dev/latest/migration/#continue-using-pydantic-v1-features) via
+the v1 namespace of Pydantic 2.
 
-User can either pin to pydantic v1, and upgrade their code in one go once LangChain has migrated to v2 internally, or they can start a partial migration to v2, but must avoid mixing v1 and v2 code for LangChain.
+Because Pydantic does not support mixing .v1 and .v2 objects, users should be aware of a number of issues
+when using LangChain with Pydantic.
+
+:::caution
+While LangChain supports Pydantic V2 objects in some APIs (listed below), it's suggested that users keep using Pydantic V1 objects until LangChain 0.3 is released.
+:::
+
+
+## 1. Passing Pydantic objects to LangChain APIs
+
+Most LangChain APIs for *tool usage* (see list below) have been updated to accept either Pydantic v1 or v2 objects.
+
+* Pydantic v1 objects correspond to subclasses of `pydantic.BaseModel` if `pydantic 1` is installed or subclasses of `pydantic.v1.BaseModel` if `pydantic 2` is installed.
+* Pydantic v2 objects correspond to subclasses of `pydantic.BaseModel` if `pydantic 2` is installed.
+
+
+| API                                    | Pydantic 1 | Pydantic 2                                                     |
+|----------------------------------------|------------|----------------------------------------------------------------|
+| `BaseChatModel.bind_tools`             | Yes        | langchain-core>=0.2.23, appropriate version of partner package |
+| `BaseChatModel.with_structured_output` | Yes        | langchain-core>=0.2.23, appropriate version of partner package |
+| `Tool.from_function`                   | Yes        | langchain-core>=0.2.23                                         |
+| `StructuredTool.from_function`         | Yes        | langchain-core>=0.2.23                                         |
+
+
+Partner packages that accept pydantic v2 objects via `bind_tools` or `with_structured_output` APIs:
+
+| Package Name        | pydantic v1 | pydantic v2 |
+|---------------------|-------------|-------------|
+| langchain-mistralai | Yes         | >=0.1.11    |
+| langchain-anthropic | Yes         | >=0.1.21    |
+| langchain-robocorp  | Yes         | >=0.0.10    |
+| langchain-openai    | Yes         | >=0.1.19    |
+| langchain-fireworks | Yes         | >=0.1.5     |
+| langchain-aws       | Yes         | >=0.1.15    |
+
+Additional partner packages will be updated to accept Pydantic v2 objects in the future.
+
+If you are still seeing issues with these APIs or other APIs that accept Pydantic objects, please open an issue, and we'll
+address it.
+
+Example:
+
+Prior to `langchain-core<0.2.23`, use Pydantic v1 objects when passing to LangChain APIs.
+
+
+```python
+from langchain_openai import ChatOpenAI
+from pydantic.v1 import BaseModel # <-- Note v1 namespace
+
+class Person(BaseModel):
+    """Personal information"""
+    name: str
+    
+model = ChatOpenAI()
+model = model.with_structured_output(Person)
+
+model.invoke('Bob is a person.')
+```
+
+After `langchain-core>=0.2.23`, use either Pydantic v1 or v2 objects when passing to LangChain APIs.
+
+```python
+from langchain_openai import ChatOpenAI
+from pydantic import BaseModel
+
+class Person(BaseModel):
+    """Personal information"""
+    name: str
+    
+    
+model = ChatOpenAI()
+model = model.with_structured_output(Person)
+
+model.invoke('Bob is a person.')
+```
+
+## 2. Sub-classing LangChain models
+
+Because LangChain internally uses Pydantic v1, if you are sub-classing LangChain models, you should use Pydantic v1
+primitives.
 
-Below are two examples of showing how to avoid mixing pydantic v1 and v2 code in
-the case of inheritance and in the case of passing objects to LangChain.
 
 **Example 1: Extending via inheritance**
 
 **YES** 
 
 ```python
-from pydantic.v1 import root_validator, validator
+from pydantic.v1 import validator
 from langchain_core.tools import BaseTool
 
 class CustomTool(BaseTool): # BaseTool is v1 code
@@ -70,38 +146,33 @@ CustomTool(
 )
 ```
 
-**Example 2: Passing objects to LangChain**
 
-**YES**
+## 3. Disable run-time validation for LangChain objects used inside Pydantic v2 models
+
+e.g.,
 
 ```python
-from langchain_core.tools import Tool
-from pydantic.v1 import BaseModel, Field # <-- Uses v1 namespace
+from typing import Annotated
 
-class CalculatorInput(BaseModel):
-    question: str = Field()
+from langchain_openai import ChatOpenAI # <-- ChatOpenAI uses pydantic v1
+from pydantic import BaseModel, SkipValidation
 
-Tool.from_function( # <-- tool uses v1 namespace
-    func=lambda question: 'hello',
-    name="Calculator",
-    description="useful for when you need to answer questions about math",
-    args_schema=CalculatorInput
-)
+
+class Foo(BaseModel): # <-- BaseModel is from Pydantic v2
+    model: Annotated[ChatOpenAI, SkipValidation()]
+
+Foo(model=ChatOpenAI(api_key="hello"))
 ```
 
-**NO**
+## 4: LangServe cannot generate OpenAPI docs if running Pydantic 2
 
-```python
-from langchain_core.tools import Tool
-from pydantic import BaseModel, Field # <-- Uses v2 namespace
+If you are using Pydantic 2, you will not be able to generate OpenAPI docs using LangServe.
 
-class CalculatorInput(BaseModel):
-    question: str = Field()
+If you need OpenAPI docs, your options are to either install Pydantic 1:
 
-Tool.from_function( # <-- tool uses v1 namespace
-    func=lambda question: 'hello',
-    name="Calculator",
-    description="useful for when you need to answer questions about math",
-    args_schema=CalculatorInput
-)
-```
+`pip install pydantic==1.10.17`
+
+or else to use the `APIHandler` object in LangChain to manually create the
+routes for your API.
+
+See: https://python.langchain.com/v0.2/docs/langserve/#pydantic

docs/docs/how_to/qa_chat_history_how_to.ipynb

@@ -42,7 +42,7 @@
    "outputs": [],
    "source": [
     "%%capture --no-stderr\n",
-    "%pip install --upgrade --quiet  langchain langchain-community langchain-chroma bs4"
+    "%pip install --upgrade --quiet  langchain langchain-community langchain-chroma beautifulsoup4"
    ]
   },
   {
@@ -721,9 +721,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langgraph.checkpoint.sqlite import SqliteSaver\n",
+    "from langgraph.checkpoint.memory import MemorySaver\n",
     "\n",
-    "memory = SqliteSaver.from_conn_string(\":memory:\")\n",
+    "memory = MemorySaver()\n",
     "\n",
     "agent_executor = create_react_agent(llm, tools, checkpointer=memory)"
    ]
@@ -890,9 +890,9 @@
     "from langchain_community.document_loaders import WebBaseLoader\n",
     "from langchain_openai import ChatOpenAI, OpenAIEmbeddings\n",
     "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
-    "from langgraph.checkpoint.sqlite import SqliteSaver\n",
+    "from langgraph.checkpoint.memory import MemorySaver\n",
     "\n",
-    "memory = SqliteSaver.from_conn_string(\":memory:\")\n",
+    "memory = MemorySaver()\n",
     "llm = ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0)\n",
     "\n",
     "\n",

docs/docs/how_to/qa_sources.ipynb

@@ -14,7 +14,9 @@
     "We will cover two approaches:\n",
     "\n",
     "1. Using the built-in [create_retrieval_chain](https://api.python.langchain.com/en/latest/chains/langchain.chains.retrieval.create_retrieval_chain.html), which returns sources by default;\n",
-    "2. Using a simple [LCEL](/docs/concepts#langchain-expression-language-lcel) implementation, to show the operating principle."
+    "2. Using a simple [LCEL](/docs/concepts#langchain-expression-language-lcel) implementation, to show the operating principle.\n",
+    "\n",
+    "We will also show how to structure sources into the model response, such that a model can report what specific sources it used in generating its answer."
    ]
   },
   {
@@ -38,7 +40,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet  langchain langchain-community langchainhub langchain-openai langchain-chroma bs4"
+    "%pip install --upgrade --quiet  langchain langchain-community langchainhub langchain-openai langchain-chroma beautifulsoup4"
    ]
   },
   {
@@ -130,8 +132,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
-   "id": "820244ae-74b4-4593-b392-822979dd91b8",
+   "execution_count": null,
+   "id": "24a69b8c-024e-4e34-b827-9c9de46512a3",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -211,11 +213,11 @@
      "data": {
       "text/plain": [
        "{'input': 'What is Task Decomposition?',\n",
-       " 'context': [Document(page_content='Fig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#\\nChain of thought (CoT; Wei et al. 2022) has become a standard prompting technique for enhancing model performance on complex tasks. The model is instructed to “think step by step” to utilize more test-time computation to decompose hard tasks into smaller and simpler steps. CoT transforms big tasks into multiple manageable tasks and shed lights into an interpretation of the model’s thinking process.', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'}),\n",
-       "  Document(page_content='Tree of Thoughts (Yao et al. 2023) extends CoT by exploring multiple reasoning possibilities at each step. It first decomposes the problem into multiple thought steps and generates multiple thoughts per step, creating a tree structure. The search process can be BFS (breadth-first search) or DFS (depth-first search) with each state evaluated by a classifier (via a prompt) or majority vote.\\nTask decomposition can be done (1) by LLM with simple prompting like \"Steps for XYZ.\\\\n1.\", \"What are the subgoals for achieving XYZ?\", (2) by using task-specific instructions; e.g. \"Write a story outline.\" for writing a novel, or (3) with human inputs.', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'}),\n",
-       "  Document(page_content='Resources:\\n1. Internet access for searches and information gathering.\\n2. Long Term memory management.\\n3. GPT-3.5 powered Agents for delegation of simple tasks.\\n4. File output.\\n\\nPerformance Evaluation:\\n1. Continuously review and analyze your actions to ensure you are performing to the best of your abilities.\\n2. Constructively self-criticize your big-picture behavior constantly.\\n3. Reflect on past decisions and strategies to refine your approach.\\n4. Every command has a cost, so be smart and efficient. Aim to complete tasks in the least number of steps.', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'}),\n",
-       "  Document(page_content=\"(3) Task execution: Expert models execute on the specific tasks and log results.\\nInstruction:\\n\\nWith the input and the inference results, the AI assistant needs to describe the process and results. The previous stages can be formed as - User Input: {{ User Input }}, Task Planning: {{ Tasks }}, Model Selection: {{ Model Assignment }}, Task Execution: {{ Predictions }}. You must first answer the user's request in a straightforward manner. Then describe the task process and show your analysis and model inference results to the user in the first person. If inference results contain a file path, must tell the user the complete file path.\", metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'})],\n",
-       " 'answer': 'Task decomposition involves breaking down a complex task into smaller and simpler steps. This process helps agents or models handle challenging tasks by dividing them into more manageable subtasks. Techniques like Chain of Thought and Tree of Thoughts are used to decompose tasks into multiple steps for better problem-solving.'}"
+       " 'context': [Document(metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'}, page_content='Fig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#\\nChain of thought (CoT; Wei et al. 2022) has become a standard prompting technique for enhancing model performance on complex tasks. The model is instructed to “think step by step” to utilize more test-time computation to decompose hard tasks into smaller and simpler steps. CoT transforms big tasks into multiple manageable tasks and shed lights into an interpretation of the model’s thinking process.'),\n",
+       "  Document(metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'}, page_content='Tree of Thoughts (Yao et al. 2023) extends CoT by exploring multiple reasoning possibilities at each step. It first decomposes the problem into multiple thought steps and generates multiple thoughts per step, creating a tree structure. The search process can be BFS (breadth-first search) or DFS (depth-first search) with each state evaluated by a classifier (via a prompt) or majority vote.\\nTask decomposition can be done (1) by LLM with simple prompting like \"Steps for XYZ.\\\\n1.\", \"What are the subgoals for achieving XYZ?\", (2) by using task-specific instructions; e.g. \"Write a story outline.\" for writing a novel, or (3) with human inputs.'),\n",
+       "  Document(metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'}, page_content='Resources:\\n1. Internet access for searches and information gathering.\\n2. Long Term memory management.\\n3. GPT-3.5 powered Agents for delegation of simple tasks.\\n4. File output.\\n\\nPerformance Evaluation:\\n1. Continuously review and analyze your actions to ensure you are performing to the best of your abilities.\\n2. Constructively self-criticize your big-picture behavior constantly.\\n3. Reflect on past decisions and strategies to refine your approach.\\n4. Every command has a cost, so be smart and efficient. Aim to complete tasks in the least number of steps.'),\n",
+       "  Document(metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'}, page_content=\"(3) Task execution: Expert models execute on the specific tasks and log results.\\nInstruction:\\n\\nWith the input and the inference results, the AI assistant needs to describe the process and results. The previous stages can be formed as - User Input: {{ User Input }}, Task Planning: {{ Tasks }}, Model Selection: {{ Model Assignment }}, Task Execution: {{ Predictions }}. You must first answer the user's request in a straightforward manner. Then describe the task process and show your analysis and model inference results to the user in the first person. If inference results contain a file path, must tell the user the complete file path.\")],\n",
+       " 'answer': 'Task decomposition involves breaking down a complex task into smaller and more manageable steps. This process helps agents or models tackle difficult tasks by dividing them into simpler subtasks or components. Task decomposition can be achieved through techniques like Chain of Thought or Tree of Thoughts, which guide the agent in breaking down tasks into sequential or branching steps.'}"
       ]
      },
      "execution_count": 5,
@@ -251,18 +253,18 @@
   {
    "cell_type": "code",
    "execution_count": 6,
-   "id": "22ea137c-1a7a-44dd-ac73-281213979957",
+   "id": "1950953a-e6f1-439d-b7b9-c3bd456e388d",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
        "{'input': 'What is Task Decomposition',\n",
-       " 'context': [Document(page_content='Fig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#\\nChain of thought (CoT; Wei et al. 2022) has become a standard prompting technique for enhancing model performance on complex tasks. The model is instructed to “think step by step” to utilize more test-time computation to decompose hard tasks into smaller and simpler steps. CoT transforms big tasks into multiple manageable tasks and shed lights into an interpretation of the model’s thinking process.', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'}),\n",
-       "  Document(page_content='Tree of Thoughts (Yao et al. 2023) extends CoT by exploring multiple reasoning possibilities at each step. It first decomposes the problem into multiple thought steps and generates multiple thoughts per step, creating a tree structure. The search process can be BFS (breadth-first search) or DFS (depth-first search) with each state evaluated by a classifier (via a prompt) or majority vote.\\nTask decomposition can be done (1) by LLM with simple prompting like \"Steps for XYZ.\\\\n1.\", \"What are the subgoals for achieving XYZ?\", (2) by using task-specific instructions; e.g. \"Write a story outline.\" for writing a novel, or (3) with human inputs.', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'}),\n",
-       "  Document(page_content='The AI assistant can parse user input to several tasks: [{\"task\": task, \"id\", task_id, \"dep\": dependency_task_ids, \"args\": {\"text\": text, \"image\": URL, \"audio\": URL, \"video\": URL}}]. The \"dep\" field denotes the id of the previous task which generates a new resource that the current task relies on. A special tag \"-task_id\" refers to the generated text image, audio and video in the dependency task with id as task_id. The task MUST be selected from the following options: {{ Available Task List }}. There is a logical relationship between tasks, please note their order. If the user input can\\'t be parsed, you need to reply empty JSON. Here are several cases for your reference: {{ Demonstrations }}. The chat history is recorded as {{ Chat History }}. From this chat history, you can find the path of the user-mentioned resources for your task planning.', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'}),\n",
-       "  Document(page_content='Fig. 11. Illustration of how HuggingGPT works. (Image source: Shen et al. 2023)\\nThe system comprises of 4 stages:\\n(1) Task planning: LLM works as the brain and parses the user requests into multiple tasks. There are four attributes associated with each task: task type, ID, dependencies, and arguments. They use few-shot examples to guide LLM to do task parsing and planning.\\nInstruction:', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'})],\n",
-       " 'answer': 'Task decomposition involves breaking down complex tasks into smaller and simpler steps to make them more manageable for autonomous agents or models. This process can be achieved by techniques like Chain of Thought (CoT) or Tree of Thoughts, which guide the model to think step by step or explore multiple reasoning possibilities at each step. Task decomposition can be done through simple prompting with language models, task-specific instructions, or human inputs.'}"
+       " 'context': [Document(metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'}, page_content='Fig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#\\nChain of thought (CoT; Wei et al. 2022) has become a standard prompting technique for enhancing model performance on complex tasks. The model is instructed to “think step by step” to utilize more test-time computation to decompose hard tasks into smaller and simpler steps. CoT transforms big tasks into multiple manageable tasks and shed lights into an interpretation of the model’s thinking process.'),\n",
+       "  Document(metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'}, page_content='Tree of Thoughts (Yao et al. 2023) extends CoT by exploring multiple reasoning possibilities at each step. It first decomposes the problem into multiple thought steps and generates multiple thoughts per step, creating a tree structure. The search process can be BFS (breadth-first search) or DFS (depth-first search) with each state evaluated by a classifier (via a prompt) or majority vote.\\nTask decomposition can be done (1) by LLM with simple prompting like \"Steps for XYZ.\\\\n1.\", \"What are the subgoals for achieving XYZ?\", (2) by using task-specific instructions; e.g. \"Write a story outline.\" for writing a novel, or (3) with human inputs.'),\n",
+       "  Document(metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'}, page_content='The AI assistant can parse user input to several tasks: [{\"task\": task, \"id\", task_id, \"dep\": dependency_task_ids, \"args\": {\"text\": text, \"image\": URL, \"audio\": URL, \"video\": URL}}]. The \"dep\" field denotes the id of the previous task which generates a new resource that the current task relies on. A special tag \"-task_id\" refers to the generated text image, audio and video in the dependency task with id as task_id. The task MUST be selected from the following options: {{ Available Task List }}. There is a logical relationship between tasks, please note their order. If the user input can\\'t be parsed, you need to reply empty JSON. Here are several cases for your reference: {{ Demonstrations }}. The chat history is recorded as {{ Chat History }}. From this chat history, you can find the path of the user-mentioned resources for your task planning.'),\n",
+       "  Document(metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'}, page_content='Fig. 11. Illustration of how HuggingGPT works. (Image source: Shen et al. 2023)\\nThe system comprises of 4 stages:\\n(1) Task planning: LLM works as the brain and parses the user requests into multiple tasks. There are four attributes associated with each task: task type, ID, dependencies, and arguments. They use few-shot examples to guide LLM to do task parsing and planning.\\nInstruction:')],\n",
+       " 'answer': 'Task decomposition is a technique used in artificial intelligence to break down complex tasks into smaller and more manageable subtasks. This approach helps agents or models to tackle difficult problems by dividing them into simpler steps, improving performance and interpretability. Different methods like Chain of Thought and Tree of Thoughts have been developed to enhance task decomposition in AI systems.'}"
       ]
      },
      "execution_count": 6,
@@ -279,15 +281,25 @@
     "    return \"\\n\\n\".join(doc.page_content for doc in docs)\n",
     "\n",
     "\n",
+    "# This Runnable takes a dict with keys 'input' and 'context',\n",
+    "# formats them into a prompt, and generates a response.\n",
     "rag_chain_from_docs = (\n",
-    "    RunnablePassthrough.assign(context=(lambda x: format_docs(x[\"context\"])))\n",
-    "    | prompt\n",
-    "    | llm\n",
-    "    | StrOutputParser()\n",
+    "    {\n",
+    "        \"input\": lambda x: x[\"input\"],  # input query\n",
+    "        \"context\": lambda x: format_docs(x[\"context\"]),  # context\n",
+    "    }\n",
+    "    | prompt  # format query and context into prompt\n",
+    "    | llm  # generate response\n",
+    "    | StrOutputParser()  # coerce to string\n",
     ")\n",
     "\n",
+    "# Pass input query to retriever\n",
     "retrieve_docs = (lambda x: x[\"input\"]) | retriever\n",
     "\n",
+    "# Below, we chain `.assign` calls. This takes a dict and successively\n",
+    "# adds keys-- \"context\" and \"answer\"-- where the value for each key\n",
+    "# is determined by a Runnable. The Runnable operates on all existing\n",
+    "# keys in the dict.\n",
     "chain = RunnablePassthrough.assign(context=retrieve_docs).assign(\n",
     "    answer=rag_chain_from_docs\n",
     ")\n",
@@ -302,7 +314,105 @@
    "source": [
     ":::{.callout-tip}\n",
     "\n",
-    "Check out the [LangSmith trace](https://smith.langchain.com/public/0cb42685-e29e-4280-a503-bef2014d7ba2/r)\n",
+    "Check out the [LangSmith trace](https://smith.langchain.com/public/1c055a3b-0236-4670-a3fb-023d418ba796/r)\n",
+    "\n",
+    ":::"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c1c17797-d965-4fd2-b8d4-d386f25dd352",
+   "metadata": {},
+   "source": [
+    "## Structure sources in model response\n",
+    "\n",
+    "Up to this point, we've simply propagated the documents returned from the retrieval step through to the final response. But this may not illustrate what subset of information the model relied on when generating its answer. Below, we show how to structure sources into the model response, allowing the model to report what specific context it relied on for its answer.\n",
+    "\n",
+    "Because the above LCEL implementation is composed of [Runnable](/docs/concepts/#runnable-interface) primitives, it is straightforward to extend. Below, we make a simple change:\n",
+    "\n",
+    "- We use the model's tool-calling features to generate [structured output](/docs/how_to/structured_output/), consisting of an answer and list of sources. The schema for the response is represented in the `AnswerWithSources` TypedDict, below.\n",
+    "- We remove the `StrOutputParser()`, as we expect `dict` output in this scenario."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "8f916b14-1b0a-4975-a62f-52f1353bde15",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from typing import List\n",
+    "\n",
+    "from langchain_core.runnables import RunnablePassthrough\n",
+    "from typing_extensions import Annotated, TypedDict\n",
+    "\n",
+    "\n",
+    "# Desired schema for response\n",
+    "class AnswerWithSources(TypedDict):\n",
+    "    \"\"\"An answer to the question, with sources.\"\"\"\n",
+    "\n",
+    "    answer: str\n",
+    "    sources: Annotated[\n",
+    "        List[str],\n",
+    "        ...,\n",
+    "        \"List of sources (author + year) used to answer the question\",\n",
+    "    ]\n",
+    "\n",
+    "\n",
+    "# Our rag_chain_from_docs has the following changes:\n",
+    "# - add `.with_structured_output` to the LLM;\n",
+    "# - remove the output parser\n",
+    "rag_chain_from_docs = (\n",
+    "    {\n",
+    "        \"input\": lambda x: x[\"input\"],\n",
+    "        \"context\": lambda x: format_docs(x[\"context\"]),\n",
+    "    }\n",
+    "    | prompt\n",
+    "    | llm.with_structured_output(AnswerWithSources)\n",
+    ")\n",
+    "\n",
+    "retrieve_docs = (lambda x: x[\"input\"]) | retriever\n",
+    "\n",
+    "chain = RunnablePassthrough.assign(context=retrieve_docs).assign(\n",
+    "    answer=rag_chain_from_docs\n",
+    ")\n",
+    "\n",
+    "response = chain.invoke({\"input\": \"What is Chain of Thought?\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "7a8fc0c5-afb3-4012-a467-3951996a6850",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{\n",
+      "  \"answer\": \"Chain of Thought (CoT) is a prompting technique that enhances model performance on complex tasks by instructing the model to \\\"think step by step\\\" to decompose hard tasks into smaller and simpler steps. It transforms big tasks into multiple manageable tasks and sheds light on the interpretation of the model's thinking process.\",\n",
+      "  \"sources\": [\n",
+      "    \"Wei et al. 2022\"\n",
+      "  ]\n",
+      "}\n"
+     ]
+    }
+   ],
+   "source": [
+    "import json\n",
+    "\n",
+    "print(json.dumps(response[\"answer\"], indent=2))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7440f785-29c5-4c6b-9656-0d9d5efbac05",
+   "metadata": {},
+   "source": [
+    ":::{.callout-tip}\n",
+    "\n",
+    "View [LangSmith trace](https://smith.langchain.com/public/0eeddf06-3a7b-4f27-974c-310ca8160f60/r)\n",
     "\n",
     ":::"
    ]

docs/docs/how_to/qa_streaming.ipynb

@@ -33,7 +33,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet  langchain langchain-community langchainhub langchain-openai langchain-chroma bs4"
+    "%pip install --upgrade --quiet  langchain langchain-community langchainhub langchain-openai langchain-chroma beautifulsoup4"
    ]
   },
   {

docs/docs/how_to/query_constructing_filters.ipynb

@@ -38,8 +38,8 @@
     "    Operator,\n",
     "    StructuredQuery,\n",
     ")\n",
-    "from langchain.retrievers.self_query.chroma import ChromaTranslator\n",
-    "from langchain.retrievers.self_query.elasticsearch import ElasticsearchTranslator\n",
+    "from langchain_community.query_constructors.chroma import ChromaTranslator\n",
+    "from langchain_community.query_constructors.elasticsearch import ElasticsearchTranslator\n",
     "from langchain_core.pydantic_v1 import BaseModel"
    ]
   },

docs/docs/how_to/runnable_runtime_secrets.ipynb

@@ -0,0 +1,78 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "6fcd2994-0092-4fa3-9bb1-c9c84babadc5",
+   "metadata": {},
+   "source": [
+    "# How to pass runtime secrets to runnables\n",
+    "\n",
+    ":::info Requires `langchain-core >= 0.2.22`\n",
+    "\n",
+    ":::\n",
+    "\n",
+    "We can pass in secrets to our runnables at runtime using the `RunnableConfig`. Specifically we can pass in secrets with a `__` prefix to the `configurable` field. This will ensure that these secrets aren't traced as part of the invocation:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "92e42e91-c277-49de-aa7a-dfb5c993c817",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "7"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_core.runnables import RunnableConfig\n",
+    "from langchain_core.tools import tool\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def foo(x: int, config: RunnableConfig) -> int:\n",
+    "    \"\"\"Sum x and a secret int\"\"\"\n",
+    "    return x + config[\"configurable\"][\"__top_secret_int\"]\n",
+    "\n",
+    "\n",
+    "foo.invoke({\"x\": 5}, {\"configurable\": {\"__top_secret_int\": 2, \"traced_key\": \"bar\"}})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ae3a4fb9-2ce7-46b2-b654-35dff0ae7197",
+   "metadata": {},
+   "source": [
+    "Looking at the LangSmith trace for this run, we can see that \"traced_key\" was recorded (as part of Metadata) while our secret int was not: https://smith.langchain.com/public/aa7e3289-49ca-422d-a408-f6b927210170/r"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "poetry-venv-311",
+   "language": "python",
+   "name": "poetry-venv-311"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/how_to/self_query.ipynb

@@ -512,7 +512,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.retrievers.self_query.chroma import ChromaTranslator\n",
+    "from langchain_community.query_constructors.chroma import ChromaTranslator\n",
     "\n",
     "retriever = SelfQueryRetriever(\n",
     "    query_constructor=query_constructor,\n",

docs/docs/how_to/semantic-chunker.ipynb

@@ -299,16 +299,16 @@
   },
   {
    "cell_type": "markdown",
+   "id": "423c6e099e94ca69",
+   "metadata": {
+    "collapsed": false
+   },
    "source": [
     "### Gradient\n",
     "\n",
     "In this method, the gradient of distance is used to split chunks along with the percentile method.\n",
     "This method is useful when chunks are highly correlated with each other or specific to a domain e.g. legal or medical. The idea is to apply anomaly detection on gradient array so that the distribution become wider and easy to identify boundaries in highly semantic data."
-   ],
-   "metadata": {
-    "collapsed": false
-   },
-   "id": "423c6e099e94ca69"
+   ]
   },
   {
    "cell_type": "code",
@@ -325,6 +325,8 @@
   {
    "cell_type": "code",
    "execution_count": 6,
+   "id": "e9f393d316ce1f6c",
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -337,13 +339,13 @@
    "source": [
     "docs = text_splitter.create_documents([state_of_the_union])\n",
     "print(docs[0].page_content)"
-   ],
-   "metadata": {},
-   "id": "e9f393d316ce1f6c"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 8,
+   "id": "a407cd57f02a0db4",
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -355,9 +357,7 @@
    ],
    "source": [
     "print(len(docs))"
-   ],
-   "metadata": {},
-   "id": "a407cd57f02a0db4"
+   ]
   }
  ],
  "metadata": {

docs/docs/how_to/sql_csv.ipynb

@@ -761,7 +761,7 @@
     "* [SQL tutorial](/docs/tutorials/sql_qa): Many of the challenges of working with SQL db's and CSV's are generic to any structured data type, so it's useful to read the SQL techniques even if you're using Pandas for CSV data analysis.\n",
     "* [Tool use](/docs/how_to/tool_calling): Guides on general best practices when working with chains and agents that invoke tools\n",
     "* [Agents](/docs/tutorials/agents): Understand the fundamentals of building LLM agents.\n",
-    "* Integrations: Sandboxed envs like [E2B](/docs/integrations/tools/e2b_data_analysis) and [Bearly](/docs/integrations/tools/bearly), utilities like [SQLDatabase](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.sql_database.SQLDatabase.html#langchain_community.utilities.sql_database.SQLDatabase), related agents like [Spark DataFrame agent](/docs/integrations/toolkits/spark)."
+    "* Integrations: Sandboxed envs like [E2B](/docs/integrations/tools/e2b_data_analysis) and [Bearly](/docs/integrations/tools/bearly), utilities like [SQLDatabase](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.sql_database.SQLDatabase.html#langchain_community.utilities.sql_database.SQLDatabase), related agents like [Spark DataFrame agent](/docs/integrations/tools/spark_sql)."
    ]
   }
  ],

docs/docs/how_to/streaming.ipynb

@@ -452,7 +452,7 @@
    "source": [
     "#### Generator Functions\n",
     "\n",
-    "Le'ts fix the streaming using a generator function that can operate on the **input stream**.\n",
+    "Let's fix the streaming using a generator function that can operate on the **input stream**.\n",
     "\n",
     ":::{.callout-tip}\n",
     "A generator function (a function that uses `yield`) allows writing code that operates on **input streams**\n",