core[patch]: use args_schema doc for tool description (#23503)

- rerun to remove warnings following
https://github.com/langchain-ai/langchain/pull/23363
- `raise` -> `return`

.devcontainer/README.md

@@ -10,7 +10,7 @@ You can use the dev container configuration in this folder to build and run the
 You may use the button above, or follow these steps to open this repo in a Codespace:
 1. Click the **Code** drop-down menu at the top of https://github.com/langchain-ai/langchain.
 1. Click on the **Codespaces** tab.
-1. Click **Create codespace on master** .
+1. Click **Create codespace on master**.
 
 For more info, check out the [GitHub documentation](https://docs.github.com/en/free-pro-team@latest/github/developing-online-with-codespaces/creating-a-codespace#creating-a-codespace).
   

.github/scripts/check_diff.py

@@ -1,7 +1,11 @@
 import json
 import sys
 import os
-from typing import Dict
+from typing import Dict, List, Set
+
+import tomllib
+from collections import defaultdict
+import glob
 
 LANGCHAIN_DIRS = [
     "libs/core",
@@ -11,6 +15,38 @@ LANGCHAIN_DIRS = [
     "libs/experimental",
 ]
 
+def all_package_dirs() -> Set[str]:
+    return {"/".join(path.split("/")[:-1]) for path in glob.glob("./libs/**/pyproject.toml", recursive=True)}
+
+
+def dependents_graph() -> dict:
+    dependents = defaultdict(set)
+
+    for path in glob.glob("./libs/**/pyproject.toml", recursive=True):
+        if "template" in path:
+            continue
+        with open(path, "rb") as f:
+            pyproject = tomllib.load(f)['tool']['poetry']
+        pkg_dir = "libs" + "/".join(path.split("libs")[1].split("/")[:-1])
+        for dep in pyproject['dependencies']:
+            if "langchain" in dep:
+                dependents[dep].add(pkg_dir)
+    return dependents
+
+
+def add_dependents(dirs_to_eval: Set[str], dependents: dict) -> List[str]:
+    updated = set()
+    for dir_ in dirs_to_eval:
+        # handle core manually because it has so many dependents
+        if "core" in dir_:
+            updated.add(dir_)
+            continue
+        pkg = "langchain-" + dir_.split("/")[-1]
+        updated.update(dependents[pkg])
+        updated.add(dir_)
+    return list(updated)
+
+
 if __name__ == "__main__":
     files = sys.argv[1:]
 
@@ -21,10 +57,11 @@ if __name__ == "__main__":
     }
     docs_edited = False
 
-    if len(files) == 300:
+    if len(files) >= 300:
         # max diff length is 300 files - there are likely files missing
-        raise ValueError("Max diff reached. Please manually run CI on changed libs.")
-
+        dirs_to_run["lint"] = all_package_dirs()
+        dirs_to_run["test"] = all_package_dirs()
+        dirs_to_run["extended-test"] = set(LANGCHAIN_DIRS)
     for file in files:
         if any(
             file.startswith(dir_)
@@ -81,11 +118,13 @@ if __name__ == "__main__":
                 docs_edited = True
             dirs_to_run["lint"].add(".")
 
+    dependents = dependents_graph()
+
     outputs = {
-        "dirs-to-lint": list(
-            dirs_to_run["lint"] | dirs_to_run["test"] | dirs_to_run["extended-test"]
+        "dirs-to-lint": add_dependents(
+            dirs_to_run["lint"] | dirs_to_run["test"] | dirs_to_run["extended-test"], dependents
         ),
-        "dirs-to-test": list(dirs_to_run["test"] | dirs_to_run["extended-test"]),
+        "dirs-to-test": add_dependents(dirs_to_run["test"] | dirs_to_run["extended-test"], dependents),
         "dirs-to-extended-test": list(dirs_to_run["extended-test"]),
         "docs-edited": "true" if docs_edited else "",
     }

.github/workflows/_compile_integration_test.yml

@@ -24,6 +24,7 @@ jobs:
           - "3.9"
           - "3.10"
           - "3.11"
+          - "3.12"
     name: "poetry run pytest -m compile tests/integration_tests #${{ matrix.python-version }}"
     steps:
       - uses: actions/checkout@v4

.github/workflows/_dependencies.yml

@@ -28,6 +28,7 @@ jobs:
           - "3.9"
           - "3.10"
           - "3.11"
+          - "3.12"
     name: dependency checks ${{ matrix.python-version }}
     steps:
       - uses: actions/checkout@v4

.github/workflows/_integration_test.yml

@@ -12,7 +12,6 @@ env:
 
 jobs:
   build:
-    environment: Scheduled testing
     defaults:
       run:
         working-directory: ${{ inputs.working-directory }}
@@ -53,8 +52,15 @@ jobs:
         shell: bash
         env:
           AI21_API_KEY: ${{ secrets.AI21_API_KEY }}
+          FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
           GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
           ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+          AZURE_OPENAI_API_VERSION: ${{ secrets.AZURE_OPENAI_API_VERSION }}
+          AZURE_OPENAI_API_BASE: ${{ secrets.AZURE_OPENAI_API_BASE }}
+          AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
+          AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_CHAT_DEPLOYMENT_NAME }}
+          AZURE_OPENAI_LLM_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LLM_DEPLOYMENT_NAME }}
+          AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME }}
           MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
           TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}

.github/workflows/_lint.yml

@@ -34,7 +34,7 @@ jobs:
         # so linting on fewer versions makes CI faster.
         python-version:
           - "3.8"
-          - "3.11"
+          - "3.12"
     steps:
       - uses: actions/checkout@v4
 

.github/workflows/_release.yml

@@ -202,7 +202,7 @@ jobs:
           poetry run python -c "import $IMPORT_NAME; print(dir($IMPORT_NAME))"
 
       - name: Import test dependencies
-        run: poetry install --with test,test_integration
+        run: poetry install --with test
         working-directory: ${{ inputs.working-directory }}
 
       # Overwrite the local version of the package with the test PyPI version.
@@ -245,6 +245,10 @@ jobs:
         with:
           credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
 
+      - name: Import integration test dependencies
+        run: poetry install --with test,test_integration
+        working-directory: ${{ inputs.working-directory }}
+
       - name: Run integration tests
         if: ${{ startsWith(inputs.working-directory, 'libs/partners/') }}
         env:

.github/workflows/_test.yml

@@ -28,6 +28,7 @@ jobs:
           - "3.9"
           - "3.10"
           - "3.11"
+          - "3.12"
     name: "make test #${{ matrix.python-version }}"
     steps:
       - uses: actions/checkout@v4

.github/workflows/_test_doc_imports.yml

@@ -12,7 +12,7 @@ jobs:
     strategy:
       matrix:
         python-version:
-          - "3.11"
+          - "3.12"
     name: "check doc imports #${{ matrix.python-version }}"
     steps:
       - uses: actions/checkout@v4

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

@@ -7,6 +7,7 @@ on:
 
 jobs:
   check-links:
+    if: github.repository_owner == 'langchain-ai'
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4

.github/workflows/check_diffs.yml

@@ -26,7 +26,7 @@ jobs:
       - uses: actions/checkout@v4
       - uses: actions/setup-python@v5
         with:
-          python-version: '3.10'
+          python-version: '3.11'
       - id: files
         uses: Ana06/get-changed-files@v2.2.0
       - id: set-matrix
@@ -104,6 +104,7 @@ jobs:
           - "3.9"
           - "3.10"
           - "3.11"
+          - "3.12"
     runs-on: ubuntu-latest
     defaults:
       run:
@@ -123,7 +124,9 @@ jobs:
         shell: bash
         run: |
           echo "Running extended tests, installing dependencies with poetry..."
-          poetry install -E extended_testing --with test
+          poetry install --with test
+          poetry run pip install uv
+          poetry run uv pip install -r extended_testing_deps.txt
 
       - name: Run extended tests
         run: make extended_tests

.github/workflows/check_new_docs.yml

@@ -0,0 +1,31 @@
+---
+name: Integration docs lint
+
+on:
+  push:
+    branches: [master]
+  pull_request:
+
+# If another push to the same PR or branch happens while this workflow is still running,
+# cancel the earlier run in favor of the next run.
+#
+# There's no point in testing an outdated version of the code. GitHub only allows
+# a limited number of job runners to be active at the same time, so it's better to cancel
+# pointless jobs early so that more useful jobs can run sooner.
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+      - id: files
+        uses: Ana06/get-changed-files@v2.2.0
+      - name: Check new docs
+        run: |
+          python docs/scripts/check_templates.py ${{ steps.files.outputs.added }}

.github/workflows/scheduled_test.yml

@@ -10,6 +10,8 @@ env:
 
 jobs:
   build:
+    if: github.repository_owner == 'langchain-ai'
+    name: Python ${{ matrix.python-version }} - ${{ matrix.working-directory }}
     runs-on: ubuntu-latest
     strategy:
       fail-fast: false
@@ -25,16 +27,45 @@ jobs:
           - "libs/partners/groq"
           - "libs/partners/mistralai"
           - "libs/partners/together"
-    name: Python ${{ matrix.python-version }} - ${{ matrix.working-directory }}
+          - "libs/partners/cohere"
+          - "libs/partners/google-vertexai"
+          - "libs/partners/google-genai"
+          - "libs/partners/aws"
+
     steps:
       - uses: actions/checkout@v4
+        with:
+          path: langchain
+      - uses: actions/checkout@v4
+        with:
+          repository: langchain-ai/langchain-google
+          path: langchain-google
+      - uses: actions/checkout@v4
+        with:
+          repository: langchain-ai/langchain-cohere
+          path: langchain-cohere
+      - uses: actions/checkout@v4
+        with:
+          repository: langchain-ai/langchain-aws
+          path: langchain-aws
+
+      - name: Move libs
+        run: |
+          rm -rf \
+            langchain/libs/partners/google-genai \
+            langchain/libs/partners/google-vertexai \
+            langchain/libs/partners/cohere
+          mv langchain-google/libs/genai langchain/libs/partners/google-genai
+          mv langchain-google/libs/vertexai langchain/libs/partners/google-vertexai
+          mv langchain-cohere/libs/cohere langchain/libs/partners/cohere
+          mv langchain-aws/libs/aws langchain/libs/partners/aws
 
       - name: Set up Python ${{ matrix.python-version }}
-        uses: "./.github/actions/poetry_setup"
+        uses: "./langchain/.github/actions/poetry_setup"
         with:
           python-version: ${{ matrix.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: ${{ matrix.working-directory }}
+          working-directory: langchain/${{ matrix.working-directory }}
           cache-key: scheduled
 
       - name: 'Authenticate to Google Cloud'
@@ -43,16 +74,20 @@ jobs:
         with:
           credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
 
+      - name: Configure AWS Credentials
+        uses: aws-actions/configure-aws-credentials@v4
+        with:
+          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+          aws-region: ${{ secrets.AWS_REGION }}
+
       - name: Install dependencies
-        working-directory: ${{ matrix.working-directory }}
-        shell: bash
         run: |
           echo "Running scheduled tests, installing dependencies with poetry..."
+          cd langchain/${{ matrix.working-directory }}
           poetry install --with=test_integration,test
 
       - name: Run integration tests
-        working-directory: ${{ matrix.working-directory }}
-        shell: bash
         env:
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
           ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
@@ -67,12 +102,25 @@ jobs:
           GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
           MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
           TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
+          COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
+          NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}
+          GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
+          GOOGLE_SEARCH_API_KEY: ${{ secrets.GOOGLE_SEARCH_API_KEY }}
+          GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
         run: |
-          make integration_test
+          cd langchain/${{ matrix.working-directory }}
+          make integration_tests
+
+      - name: Remove external libraries
+        run: | 
+          rm -rf \
+            langchain/libs/partners/google-genai \
+            langchain/libs/partners/google-vertexai \
+            langchain/libs/partners/cohere \
+            langchain/libs/partners/aws
 
       - name: Ensure the tests did not create any additional files
-        working-directory: ${{ matrix.working-directory }}
-        shell: bash
+        working-directory: langchain
         run: |
           set -eu
 

.gitignore

@@ -133,6 +133,7 @@ env.bak/
 
 # mypy
 .mypy_cache/
+.mypy_cache_test/
 .dmypy.json
 dmypy.json
 

Makefile

@@ -32,10 +32,13 @@ api_docs_build:
 	poetry run python docs/api_reference/create_api_rst.py
 	cd docs/api_reference && poetry run make html
 
+API_PKG ?= text-splitters
+
 api_docs_quick_preview:
-	poetry run python docs/api_reference/create_api_rst.py text-splitters
+	poetry run pip install "pydantic<2"
+	poetry run python docs/api_reference/create_api_rst.py $(API_PKG)
 	cd docs/api_reference && poetry run make html
-	open docs/api_reference/_build/html/text_splitters_api_reference.html
+	open docs/api_reference/_build/html/$(shell echo $(API_PKG) | sed 's/-/_/g')_api_reference.html
 
 ## api_docs_clean: Clean the API Reference documentation build artifacts.
 api_docs_clean:

README.md

@@ -2,17 +2,17 @@
 
 ⚡ Build context-aware reasoning applications ⚡
 
-[![Release Notes](https://img.shields.io/github/release/langchain-ai/langchain)](https://github.com/langchain-ai/langchain/releases)
+[![Release Notes](https://img.shields.io/github/release/langchain-ai/langchain?style=flat-square)](https://github.com/langchain-ai/langchain/releases)
 [![CI](https://github.com/langchain-ai/langchain/actions/workflows/check_diffs.yml/badge.svg)](https://github.com/langchain-ai/langchain/actions/workflows/check_diffs.yml)
-[![Downloads](https://static.pepy.tech/badge/langchain-core/month)](https://pepy.tech/project/langchain-core)
-[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-[![Twitter](https://img.shields.io/twitter/url/https/twitter.com/langchainai.svg?style=social&label=Follow%20%40LangChainAI)](https://twitter.com/langchainai)
-[![](https://dcbadge.vercel.app/api/server/6adMQxSpJS?compact=true&style=flat)](https://discord.gg/6adMQxSpJS)
-[![Open in Dev Containers](https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langchain-ai/langchain)
+[![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)
-[![GitHub star chart](https://img.shields.io/github/stars/langchain-ai/langchain?style=social)](https://star-history.com/#langchain-ai/langchain)
-[![Dependency Status](https://img.shields.io/librariesio/github/langchain-ai/langchain)](https://libraries.io/github/langchain-ai/langchain)
-[![Open Issues](https://img.shields.io/github/issues-raw/langchain-ai/langchain)](https://github.com/langchain-ai/langchain/issues)
+[![](https://dcbadge.vercel.app/api/server/6adMQxSpJS?compact=true&style=flat)](https://discord.gg/6adMQxSpJS)
+[![Twitter](https://img.shields.io/twitter/url/https/twitter.com/langchainai.svg?style=social&label=Follow%20%40LangChainAI)](https://twitter.com/langchainai)
 
 Looking for the JS/TS library? Check out [LangChain.js](https://github.com/langchain-ai/langchainjs).
 
@@ -38,22 +38,22 @@ conda install langchain -c conda-forge
 
 For these applications, LangChain simplifies the entire application lifecycle:
 
-- **Open-source libraries**: Build your applications using LangChain's [modular building blocks](https://python.langchain.com/docs/expression_language/) and [components](https://python.langchain.com/docs/modules/). Integrate with hundreds of [third-party providers](https://python.langchain.com/docs/integrations/platforms/).
-- **Productionization**: Inspect, monitor, and evaluate your apps with [LangSmith](https://python.langchain.com/docs/langsmith/) so that you can constantly optimize and deploy with confidence.
-- **Deployment**: Turn any chain into a REST API with [LangServe](https://python.langchain.com/docs/langserve).
+- **Open-source libraries**: Build your applications using LangChain's [modular building blocks](https://python.langchain.com/v0.2/docs/concepts/#langchain-expression-language-lcel) and [components](https://python.langchain.com/v0.2/docs/concepts/#components). Integrate with hundreds of [third-party providers](https://python.langchain.com/v0.2/docs/integrations/platforms/).
+- **Productionization**: Inspect, monitor, and evaluate your apps with [LangSmith](https://docs.smith.langchain.com/) so that you can constantly optimize and deploy with confidence.
+- **Deployment**: Turn any chain into a REST API with [LangServe](https://python.langchain.com/v0.2/docs/langserve/).
 
 ### Open-source libraries
 - **`langchain-core`**: Base abstractions and LangChain Expression Language.
 - **`langchain-community`**: Third party integrations.
   - Some integrations have been further split into **partner packages** that only rely on **`langchain-core`**. Examples include **`langchain_openai`** and **`langchain_anthropic`**.
 - **`langchain`**: Chains, agents, and retrieval strategies that make up an application's cognitive architecture.
-- **[`LangGraph`](https://python.langchain.com/docs/langgraph)**: A library for building robust and stateful multi-actor applications with LLMs by modeling steps as edges and nodes in a graph.
+- **[`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.
 
 ### Productionization:
-- **[LangSmith](https://python.langchain.com/docs/langsmith)**: A developer platform that lets you debug, test, evaluate, and monitor chains built on any LLM framework and seamlessly integrates with LangChain.
+- **[LangSmith](https://docs.smith.langchain.com/)**: A developer platform that lets you debug, test, evaluate, and monitor chains built on any LLM framework and seamlessly integrates with LangChain.
 
 ### Deployment:
-- **[LangServe](https://python.langchain.com/docs/langserve)**: A library for deploying LangChain chains as REST APIs.
+- **[LangServe](https://python.langchain.com/v0.2/docs/langserve/)**: A library for deploying LangChain chains as REST APIs.
 
 ![Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers.](docs/static/svg/langchain_stack.svg "LangChain Architecture Overview")
 
@@ -61,20 +61,20 @@ For these applications, LangChain simplifies the entire application lifecycle:
 
 **❓ Question answering with RAG**
 
-- [Documentation](https://python.langchain.com/docs/use_cases/question_answering/)
+- [Documentation](https://python.langchain.com/v0.2/docs/tutorials/rag/)
 - End-to-end Example: [Chat LangChain](https://chat.langchain.com) and [repo](https://github.com/langchain-ai/chat-langchain)
 
 **🧱 Extracting structured output**
 
-- [Documentation](https://python.langchain.com/docs/use_cases/extraction/)
+- [Documentation](https://python.langchain.com/v0.2/docs/tutorials/extraction/)
 - End-to-end Example: [SQL Llama2 Template](https://github.com/langchain-ai/langchain-extract/)
 
 **🤖 Chatbots**
 
-- [Documentation](https://python.langchain.com/docs/use_cases/chatbots)
+- [Documentation](https://python.langchain.com/v0.2/docs/tutorials/chatbot/)
 - End-to-end Example: [Web LangChain (web researcher chatbot)](https://weblangchain.vercel.app) and [repo](https://github.com/langchain-ai/weblangchain)
 
-And much more! Head to the [Use cases](https://python.langchain.com/docs/use_cases/) section of the docs for more.
+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:
@@ -87,49 +87,50 @@ Off-the-shelf chains make it easy to get started. Components make it easy to cus
 
 LCEL is the foundation of many of LangChain's components, and is a declarative way to compose chains. LCEL was designed from day 1 to support putting prototypes in production, with no code changes, from the simplest “prompt + LLM” chain to the most complex chains.
 
-- **[Overview](https://python.langchain.com/docs/expression_language/)**: LCEL and its benefits
-- **[Interface](https://python.langchain.com/docs/expression_language/interface)**: The standard interface for LCEL objects
-- **[Primitives](https://python.langchain.com/docs/expression_language/primitives)**: More on the primitives LCEL includes
+- **[Overview](https://python.langchain.com/v0.2/docs/concepts/#langchain-expression-language-lcel)**: LCEL and its benefits
+- **[Interface](https://python.langchain.com/v0.2/docs/concepts/#runnable-interface)**: The standard Runnable interface for LCEL objects
+- **[Primitives](https://python.langchain.com/v0.2/docs/how_to/#langchain-expression-language-lcel)**: More on the primitives LCEL includes
+- **[Cheatsheet](https://python.langchain.com/v0.2/docs/how_to/lcel_cheatsheet/)**: Quick overview of the most common usage patterns
 
 ## Components
 
 Components fall into the following **modules**:
 
-**📃 Model I/O:**
+**📃 Model I/O**
 
-This includes [prompt management](https://python.langchain.com/docs/modules/model_io/prompts/), [prompt optimization](https://python.langchain.com/docs/modules/model_io/prompts/example_selectors/), a generic interface for [chat models](https://python.langchain.com/docs/modules/model_io/chat/) and [LLMs](https://python.langchain.com/docs/modules/model_io/llms/), and common utilities for working with [model outputs](https://python.langchain.com/docs/modules/model_io/output_parsers/).
+This includes [prompt management](https://python.langchain.com/v0.2/docs/concepts/#prompt-templates), [prompt optimization](https://python.langchain.com/v0.2/docs/concepts/#example-selectors), a generic interface for [chat models](https://python.langchain.com/v0.2/docs/concepts/#chat-models) and [LLMs](https://python.langchain.com/v0.2/docs/concepts/#llms), and common utilities for working with [model outputs](https://python.langchain.com/v0.2/docs/concepts/#output-parsers).
 
-**📚 Retrieval:**
+**📚 Retrieval**
 
-Retrieval Augmented Generation involves [loading data](https://python.langchain.com/docs/modules/data_connection/document_loaders/) from a variety of sources, [preparing it](https://python.langchain.com/docs/modules/data_connection/document_loaders/), [then retrieving it](https://python.langchain.com/docs/modules/data_connection/retrievers/) for use in the generation step.
+Retrieval Augmented Generation involves [loading data](https://python.langchain.com/v0.2/docs/concepts/#document-loaders) from a variety of sources, [preparing it](https://python.langchain.com/v0.2/docs/concepts/#text-splitters), then [searching over (a.k.a. retrieving from)](https://python.langchain.com/v0.2/docs/concepts/#retrievers) it for use in the generation step.
 
-**🤖 Agents:**
+**🤖 Agents**
 
-Agents allow an LLM autonomy over how a task is accomplished. Agents make decisions about which Actions to take, then take that Action, observe the result, and repeat until the task is complete done. LangChain provides a [standard interface for agents](https://python.langchain.com/docs/modules/agents/), a [selection of agents](https://python.langchain.com/docs/modules/agents/agent_types/) to choose from, and examples of end-to-end agents.
+Agents allow an LLM autonomy over how a task is accomplished. Agents make decisions about which Actions to take, then take that Action, observe the result, and repeat until the task is complete. LangChain provides a [standard interface for agents](https://python.langchain.com/v0.2/docs/concepts/#agents) along with the [LangGraph](https://github.com/langchain-ai/langgraph) extension for building custom agents.
 
 ## 📖 Documentation
 
 Please see [here](https://python.langchain.com) for full documentation, which includes:
 
-- [Getting started](https://python.langchain.com/docs/get_started/introduction): installation, setting up the environment, simple examples
-- [Use case](https://python.langchain.com/docs/use_cases/) walkthroughs and best practice [guides](https://python.langchain.com/docs/guides/)
-- Overviews of the [interfaces](https://python.langchain.com/docs/expression_language/), [components](https://python.langchain.com/docs/modules/), and [integrations](https://python.langchain.com/docs/integrations/providers)
-
-You can also check out the full [API Reference docs](https://api.python.langchain.com).
+- [Introduction](https://python.langchain.com/v0.2/docs/introduction/): Overview of the framework and the structure of the docs.
+- [Tutorials](https://python.langchain.com/docs/use_cases/): If you're looking to build something specific or are more of a hands-on learner, check out our tutorials. This is the best place to get started.
+- [How-to guides](https://python.langchain.com/v0.2/docs/how_to/): Answers to “How do I….?” type questions. These guides are goal-oriented and concrete; they're meant to help you complete a specific task.
+- [Conceptual guide](https://python.langchain.com/v0.2/docs/concepts/): Conceptual explanations of the key parts of the framework.
+- [API Reference](https://api.python.langchain.com): Thorough documentation of every class and method.
 
 ## 🌐 Ecosystem
 
-- [🦜🛠️ LangSmith](https://python.langchain.com/docs/langsmith/): Tracing and evaluating your language model applications and intelligent agents to help you move from prototype to production.
-- [🦜🕸️ LangGraph](https://python.langchain.com/docs/langgraph): Creating stateful, multi-actor applications with LLMs, built on top of (and intended to be used with) LangChain primitives.
+- [🦜🛠️ LangSmith](https://docs.smith.langchain.com/): Tracing and evaluating your language model applications and intelligent agents to help you move from prototype to production.
+- [🦜🕸️ LangGraph](https://langchain-ai.github.io/langgraph/): Creating stateful, multi-actor applications with LLMs, built on top of (and intended to be used with) LangChain primitives.
 - [🦜🏓 LangServe](https://python.langchain.com/docs/langserve): Deploying LangChain runnables and chains as REST APIs.
-  - [LangChain Templates](https://python.langchain.com/docs/templates/): Example applications hosted with LangServe.
+- [LangChain Templates](https://python.langchain.com/v0.2/docs/templates/): Example applications hosted with LangServe.
 
 
 ## 💁 Contributing
 
 As an open-source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of a new feature, improved infrastructure, or better documentation.
 
-For detailed information on how to contribute, see [here](https://python.langchain.com/docs/contributing/).
+For detailed information on how to contribute, see [here](https://python.langchain.com/v0.2/docs/contributing/).
 
 ## 🌟 Contributors
 

cookbook/autogpt/marathon_times.ipynb

@@ -46,7 +46,7 @@
     "from langchain_experimental.autonomous_agents import AutoGPT\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "# Needed synce jupyter runs an async eventloop\n",
+    "# Needed since jupyter runs an async eventloop\n",
     "nest_asyncio.apply()"
    ]
   },

cookbook/nomic_multimodal_rag.ipynb

@@ -0,0 +1,497 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "9fc3897d-176f-4729-8fd1-cfb4add53abd",
+   "metadata": {},
+   "source": [
+    "## Nomic multi-modal RAG\n",
+    "\n",
+    "Many documents contain a mixture of content types, including text and images. \n",
+    "\n",
+    "Yet, information captured in images is lost in most RAG applications.\n",
+    "\n",
+    "With the emergence of multimodal LLMs, like [GPT-4V](https://openai.com/research/gpt-4v-system-card), it is worth considering how to utilize images in RAG:\n",
+    "\n",
+    "In this demo we\n",
+    "\n",
+    "* Use multimodal embeddings from Nomic Embed [Vision](https://huggingface.co/nomic-ai/nomic-embed-vision-v1.5) and [Text](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5) to embed images and text\n",
+    "* Retrieve both using similarity search\n",
+    "* Pass raw images and text chunks to a multimodal LLM for answer synthesis \n",
+    "\n",
+    "## Signup\n",
+    "\n",
+    "Get your API token, then run:\n",
+    "```\n",
+    "! nomic login\n",
+    "```\n",
+    "\n",
+    "Then run with your generated API token \n",
+    "```\n",
+    "! nomic login < token > \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": null,
+   "id": "54926b9b-75c2-4cd4-8f14-b3882a0d370b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "! nomic login token"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "febbc459-ebba-4c1a-a52b-fed7731593f8",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "! pip install -U langchain-nomic langchain_community tiktoken langchain-openai chromadb langchain # (newest versions required for multi-modal)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "acbdc603-39e2-4a5f-836c-2bbaecd46b0b",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "# lock to 0.10.19 due to a persistent bug in more recent versions\n",
+    "! pip install \"unstructured[all-docs]==0.10.19\" pillow pydantic lxml pillow matplotlib tiktoken"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1e94b3fb-8e3e-4736-be0a-ad881626c7bd",
+   "metadata": {},
+   "source": [
+    "## Data Loading\n",
+    "\n",
+    "### Partition PDF text and images\n",
+    "  \n",
+    "Let's look at an example pdfs containing interesting images.\n",
+    "\n",
+    "1/ Art from the J Paul Getty museum:\n",
+    "\n",
+    " * Here is a [zip file](https://drive.google.com/file/d/18kRKbq2dqAhhJ3DfZRnYcTBEUfYxe1YR/view?usp=sharing) with the PDF and the already extracted images. \n",
+    "* https://www.getty.edu/publications/resources/virtuallibrary/0892360224.pdf\n",
+    "\n",
+    "2/ 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.\n",
+    "\n",
+    "To supply this to extract the images:\n",
+    "```\n",
+    "extract_images_in_pdf=True\n",
+    "```\n",
+    "\n",
+    "\n",
+    "\n",
+    "If using this zip file, then you can simply process the text only with:\n",
+    "```\n",
+    "extract_images_in_pdf=False\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9646b524-71a7-4b2a-bdc8-0b81f77e968f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Folder with pdf and extracted images\n",
+    "from pathlib import Path\n",
+    "\n",
+    "# replace with actual path to images\n",
+    "path = Path(\"../art\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "77f096ab-a933-41d0-8f4e-1efc83998fc3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "path.resolve()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bc4839c0-8773-4a07-ba59-5364501269b2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Extract images, tables, and chunk text\n",
+    "from unstructured.partition.pdf import partition_pdf\n",
+    "\n",
+    "raw_pdf_elements = partition_pdf(\n",
+    "    filename=str(path.resolve()) + \"/getty.pdf\",\n",
+    "    extract_images_in_pdf=False,\n",
+    "    infer_table_structure=True,\n",
+    "    chunking_strategy=\"by_title\",\n",
+    "    max_characters=4000,\n",
+    "    new_after_n_chars=3800,\n",
+    "    combine_text_under_n_chars=2000,\n",
+    "    image_output_dir_path=path,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "969545ad",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Categorize text elements by type\n",
+    "tables = []\n",
+    "texts = []\n",
+    "for element in raw_pdf_elements:\n",
+    "    if \"unstructured.documents.elements.Table\" in str(type(element)):\n",
+    "        tables.append(str(element))\n",
+    "    elif \"unstructured.documents.elements.CompositeElement\" in str(type(element)):\n",
+    "        texts.append(str(element))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5d8e6349-1547-4cbf-9c6f-491d8610ec10",
+   "metadata": {},
+   "source": [
+    "## Multi-modal embeddings with our document\n",
+    "\n",
+    "We will use [nomic-embed-vision-v1.5](https://huggingface.co/nomic-ai/nomic-embed-vision-v1.5) embeddings. This model is aligned \n",
+    "to [nomic-embed-text-v1.5](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5) allowing for multimodal semantic search and Multimodal RAG!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4bc15842-cb95-4f84-9eb5-656b0282a800",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import uuid\n",
+    "\n",
+    "import chromadb\n",
+    "import numpy as np\n",
+    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_nomic import NomicEmbeddings\n",
+    "from PIL import Image as _PILImage\n",
+    "\n",
+    "# Create chroma\n",
+    "text_vectorstore = Chroma(\n",
+    "    collection_name=\"mm_rag_clip_photos_text\",\n",
+    "    embedding_function=NomicEmbeddings(\n",
+    "        vision_model=\"nomic-embed-vision-v1.5\", model=\"nomic-embed-text-v1.5\"\n",
+    "    ),\n",
+    ")\n",
+    "image_vectorstore = Chroma(\n",
+    "    collection_name=\"mm_rag_clip_photos_image\",\n",
+    "    embedding_function=NomicEmbeddings(\n",
+    "        vision_model=\"nomic-embed-vision-v1.5\", model=\"nomic-embed-text-v1.5\"\n",
+    "    ),\n",
+    ")\n",
+    "\n",
+    "# Get image URIs with .jpg extension only\n",
+    "image_uris = sorted(\n",
+    "    [\n",
+    "        os.path.join(path, image_name)\n",
+    "        for image_name in os.listdir(path)\n",
+    "        if image_name.endswith(\".jpg\")\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "# Add images\n",
+    "image_vectorstore.add_images(uris=image_uris)\n",
+    "\n",
+    "# Add documents\n",
+    "text_vectorstore.add_texts(texts=texts)\n",
+    "\n",
+    "# Make retriever\n",
+    "image_retriever = image_vectorstore.as_retriever()\n",
+    "text_retriever = text_vectorstore.as_retriever()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "02a186d0-27e0-4820-8092-63b5349dd25d",
+   "metadata": {},
+   "source": [
+    "## RAG\n",
+    "\n",
+    "`vectorstore.add_images` will store / retrieve images as base64 encoded strings.\n",
+    "\n",
+    "These can be passed to [GPT-4V](https://platform.openai.com/docs/guides/vision)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "344f56a8-0dc3-433e-851c-3f7600c7a72b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import base64\n",
+    "import io\n",
+    "from io import BytesIO\n",
+    "\n",
+    "import numpy as np\n",
+    "from PIL import Image\n",
+    "\n",
+    "\n",
+    "def resize_base64_image(base64_string, size=(128, 128)):\n",
+    "    \"\"\"\n",
+    "    Resize an image encoded as a Base64 string.\n",
+    "\n",
+    "    Args:\n",
+    "    base64_string (str): Base64 string of the original image.\n",
+    "    size (tuple): Desired size of the image as (width, height).\n",
+    "\n",
+    "    Returns:\n",
+    "    str: Base64 string of the resized image.\n",
+    "    \"\"\"\n",
+    "    # Decode the Base64 string\n",
+    "    img_data = base64.b64decode(base64_string)\n",
+    "    img = Image.open(io.BytesIO(img_data))\n",
+    "\n",
+    "    # Resize the image\n",
+    "    resized_img = img.resize(size, Image.LANCZOS)\n",
+    "\n",
+    "    # Save the resized image to a bytes buffer\n",
+    "    buffered = io.BytesIO()\n",
+    "    resized_img.save(buffered, format=img.format)\n",
+    "\n",
+    "    # Encode the resized image to Base64\n",
+    "    return base64.b64encode(buffered.getvalue()).decode(\"utf-8\")\n",
+    "\n",
+    "\n",
+    "def is_base64(s):\n",
+    "    \"\"\"Check if a string is Base64 encoded\"\"\"\n",
+    "    try:\n",
+    "        return base64.b64encode(base64.b64decode(s)) == s.encode()\n",
+    "    except Exception:\n",
+    "        return False\n",
+    "\n",
+    "\n",
+    "def split_image_text_types(docs):\n",
+    "    \"\"\"Split numpy array images and texts\"\"\"\n",
+    "    images = []\n",
+    "    text = []\n",
+    "    for doc in docs:\n",
+    "        doc = doc.page_content  # Extract Document contents\n",
+    "        if is_base64(doc):\n",
+    "            # Resize image to avoid OAI server error\n",
+    "            images.append(\n",
+    "                resize_base64_image(doc, size=(250, 250))\n",
+    "            )  # base64 encoded str\n",
+    "        else:\n",
+    "            text.append(doc)\n",
+    "    return {\"images\": images, \"texts\": text}"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "23a2c1d8-fea6-4152-b184-3172dd46c735",
+   "metadata": {},
+   "source": [
+    "Currently, we format the inputs using a `RunnableLambda` while we add image support to `ChatPromptTemplates`.\n",
+    "\n",
+    "Our runnable follows the classic RAG flow - \n",
+    "\n",
+    "* We first compute the context (both \"texts\" and \"images\" in this case) and the question (just a RunnablePassthrough here) \n",
+    "* Then we pass this into our prompt template, which is a custom function that formats the message for the gpt-4-vision-preview model. \n",
+    "* And finally we parse the output as a string."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5d8919dc-c238-4746-86ba-45d940a7d260",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4c93fab3-74c4-4f1d-958a-0bc4cdd0797e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from operator import itemgetter\n",
+    "\n",
+    "from langchain_core.messages import HumanMessage, SystemMessage\n",
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.runnables import RunnableLambda, RunnablePassthrough\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "\n",
+    "def prompt_func(data_dict):\n",
+    "    # Joining the context texts into a single string\n",
+    "    formatted_texts = \"\\n\".join(data_dict[\"text_context\"][\"texts\"])\n",
+    "    messages = []\n",
+    "\n",
+    "    # Adding image(s) to the messages if present\n",
+    "    if data_dict[\"image_context\"][\"images\"]:\n",
+    "        image_message = {\n",
+    "            \"type\": \"image_url\",\n",
+    "            \"image_url\": {\n",
+    "                \"url\": f\"data:image/jpeg;base64,{data_dict['image_context']['images'][0]}\"\n",
+    "            },\n",
+    "        }\n",
+    "        messages.append(image_message)\n",
+    "\n",
+    "    # Adding the text message for analysis\n",
+    "    text_message = {\n",
+    "        \"type\": \"text\",\n",
+    "        \"text\": (\n",
+    "            \"As an expert art critic and historian, your task is to analyze and interpret images, \"\n",
+    "            \"considering their historical and cultural significance. Alongside the images, you will be \"\n",
+    "            \"provided with related text to offer context. Both will be retrieved from a vectorstore based \"\n",
+    "            \"on user-input keywords. Please use your extensive knowledge and analytical skills to provide a \"\n",
+    "            \"comprehensive summary that includes:\\n\"\n",
+    "            \"- A detailed description of the visual elements in the image.\\n\"\n",
+    "            \"- The historical and cultural context of the image.\\n\"\n",
+    "            \"- An interpretation of the image's symbolism and meaning.\\n\"\n",
+    "            \"- Connections between the image and the related text.\\n\\n\"\n",
+    "            f\"User-provided keywords: {data_dict['question']}\\n\\n\"\n",
+    "            \"Text and / or tables:\\n\"\n",
+    "            f\"{formatted_texts}\"\n",
+    "        ),\n",
+    "    }\n",
+    "    messages.append(text_message)\n",
+    "\n",
+    "    return [HumanMessage(content=messages)]\n",
+    "\n",
+    "\n",
+    "model = ChatOpenAI(temperature=0, model=\"gpt-4-vision-preview\", max_tokens=1024)\n",
+    "\n",
+    "# RAG pipeline\n",
+    "chain = (\n",
+    "    {\n",
+    "        \"text_context\": text_retriever | RunnableLambda(split_image_text_types),\n",
+    "        \"image_context\": image_retriever | RunnableLambda(split_image_text_types),\n",
+    "        \"question\": RunnablePassthrough(),\n",
+    "    }\n",
+    "    | RunnableLambda(prompt_func)\n",
+    "    | model\n",
+    "    | StrOutputParser()\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1566096d-97c2-4ddc-ba4a-6ef88c525e4e",
+   "metadata": {},
+   "source": [
+    "## Test retrieval and run RAG"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "90121e56-674b-473b-871d-6e4753fd0c45",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from IPython.display import HTML, display\n",
+    "\n",
+    "\n",
+    "def plt_img_base64(img_base64):\n",
+    "    # Create an HTML img tag with the base64 string as the source\n",
+    "    image_html = f'<img src=\"data:image/jpeg;base64,{img_base64}\" />'\n",
+    "\n",
+    "    # Display the image by rendering the HTML\n",
+    "    display(HTML(image_html))\n",
+    "\n",
+    "\n",
+    "docs = text_retriever.invoke(\"Women with children\", k=5)\n",
+    "for doc in docs:\n",
+    "    if is_base64(doc.page_content):\n",
+    "        plt_img_base64(doc.page_content)\n",
+    "    else:\n",
+    "        print(doc.page_content)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "44eaa532-f035-4c04-b578-02339d42554c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "docs = image_retriever.invoke(\"Women with children\", k=5)\n",
+    "for doc in docs:\n",
+    "    if is_base64(doc.page_content):\n",
+    "        plt_img_base64(doc.page_content)\n",
+    "    else:\n",
+    "        print(doc.page_content)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "69fb15fd-76fc-49b4-806d-c4db2990027d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain.invoke(\"Women with children\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "227f08b8-e732-4089-b65c-6eb6f9e48f15",
+   "metadata": {},
+   "source": [
+    "We can see the images retrieved in the LangSmith trace:\n",
+    "\n",
+    "LangSmith [trace](https://smith.langchain.com/public/69c558a5-49dc-4c60-a49b-3adbb70f74c5/r/e872c2c8-528c-468f-aefd-8b5cd730a673)."
+   ]
+  }
+ ],
+ "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": "3.11.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

cookbook/oracleai_demo.ipynb

@@ -86,8 +86,7 @@
     "\n",
     "import oracledb\n",
     "\n",
-    "# please update with your username, password, hostname and service_name\n",
-    "# please make sure this user has sufficient privileges to perform all below\n",
+    "# Update with your username, password, hostname, and service_name\n",
     "username = \"\"\n",
     "password = \"\"\n",
     "dsn = \"\"\n",
@@ -97,40 +96,45 @@
     "    print(\"Connection successful!\")\n",
     "\n",
     "    cursor = conn.cursor()\n",
-    "    cursor.execute(\n",
-    "        \"\"\"\n",
-    "    begin\n",
-    "        -- drop user\n",
-    "        begin\n",
-    "            execute immediate 'drop user testuser cascade';\n",
-    "        exception\n",
-    "            when others then\n",
-    "                dbms_output.put_line('Error setting up user.');\n",
-    "        end;\n",
-    "        execute immediate 'create user testuser identified by testuser';\n",
-    "        execute immediate 'grant connect, unlimited tablespace, create credential, create procedure, create any index to testuser';\n",
-    "        execute immediate 'create or replace directory DEMO_PY_DIR as ''/scratch/hroy/view_storage/hroy_devstorage/demo/orachain''';\n",
-    "        execute immediate 'grant read, write on directory DEMO_PY_DIR to public';\n",
-    "        execute immediate 'grant create mining model to testuser';\n",
-    "\n",
-    "        -- network access\n",
-    "        begin\n",
-    "            DBMS_NETWORK_ACL_ADMIN.APPEND_HOST_ACE(\n",
-    "                host => '*',\n",
-    "                ace => xs$ace_type(privilege_list => xs$name_list('connect'),\n",
-    "                                principal_name => 'testuser',\n",
-    "                                principal_type => xs_acl.ptype_db));\n",
-    "        end;\n",
-    "    end;\n",
-    "    \"\"\"\n",
-    "    )\n",
-    "    print(\"User setup done!\")\n",
-    "    cursor.close()\n",
+    "    try:\n",
+    "        cursor.execute(\n",
+    "            \"\"\"\n",
+    "            begin\n",
+    "                -- Drop user\n",
+    "                begin\n",
+    "                    execute immediate 'drop user testuser cascade';\n",
+    "                exception\n",
+    "                    when others then\n",
+    "                        dbms_output.put_line('Error dropping user: ' || SQLERRM);\n",
+    "                end;\n",
+    "                \n",
+    "                -- Create user and grant privileges\n",
+    "                execute immediate 'create user testuser identified by testuser';\n",
+    "                execute immediate 'grant connect, unlimited tablespace, create credential, create procedure, create any index to testuser';\n",
+    "                execute immediate 'create or replace directory DEMO_PY_DIR as ''/scratch/hroy/view_storage/hroy_devstorage/demo/orachain''';\n",
+    "                execute immediate 'grant read, write on directory DEMO_PY_DIR to public';\n",
+    "                execute immediate 'grant create mining model to testuser';\n",
+    "                \n",
+    "                -- Network access\n",
+    "                begin\n",
+    "                    DBMS_NETWORK_ACL_ADMIN.APPEND_HOST_ACE(\n",
+    "                        host => '*',\n",
+    "                        ace => xs$ace_type(privilege_list => xs$name_list('connect'),\n",
+    "                                           principal_name => 'testuser',\n",
+    "                                           principal_type => xs_acl.ptype_db)\n",
+    "                    );\n",
+    "                end;\n",
+    "            end;\n",
+    "            \"\"\"\n",
+    "        )\n",
+    "        print(\"User setup done!\")\n",
+    "    except Exception as e:\n",
+    "        print(f\"User setup failed with error: {e}\")\n",
+    "    finally:\n",
+    "        cursor.close()\n",
     "    conn.close()\n",
     "except Exception as e:\n",
-    "    print(\"User setup failed!\")\n",
-    "    cursor.close()\n",
-    "    conn.close()\n",
+    "    print(f\"Connection failed with error: {e}\")\n",
     "    sys.exit(1)"
    ]
   },
@@ -526,8 +530,6 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "***Note:*** Currently, OracleEmbeddings processes each embedding generation request individually, without batching, by calling REST endpoints separately for each request. This method could potentially lead to exceeding the maximum request per minute quota set by some providers. However, we are actively working to enhance this process by implementing request batching, which will allow multiple embedding requests to be combined into fewer API calls, thereby optimizing our use of provider resources and adhering to their request limits. This update is expected to be rolled out soon, eliminating the current limitation.\n",
-    "\n",
     "***Note:*** Users may need to configure a proxy to utilize third-party embedding generation providers, excluding the 'database' provider that utilizes an ONNX model."
    ]
   },

docs/Makefile

@@ -31,15 +31,15 @@ install-py-deps:
 	$(PYTHON) -m uv pip install -r vercel_requirements.txt
 	$(PYTHON) -m uv pip install --editable $(PARTNER_DEPS_LIST)
 
-_generate-files-internal:
+generate-files:
 	mkdir -p $(INTERMEDIATE_DIR)
-	rsync -am --delete $(SOURCE_DIR) $(INTERMEDIATE_DIR)
-
-generate-files: _generate-files-internal
+	cp -r $(SOURCE_DIR)/* $(INTERMEDIATE_DIR)
 	mkdir -p $(INTERMEDIATE_DIR)/templates
 
 	$(PYTHON) scripts/model_feat_table.py $(INTERMEDIATE_DIR)
 
+	$(PYTHON) scripts/document_loader_feat_table.py $(INTERMEDIATE_DIR)
+
 	$(PYTHON) scripts/copy_templates.py $(INTERMEDIATE_DIR)
 
 	wget -q https://raw.githubusercontent.com/langchain-ai/langserve/main/README.md -O $(INTERMEDIATE_DIR)/langserve.md
@@ -61,23 +61,13 @@ render:
 	$(PYTHON) scripts/notebook_convert.py $(INTERMEDIATE_DIR) $(OUTPUT_NEW_DOCS_DIR)
 
 md-sync:
-	rsync -am --include="*/" --include="*.mdx" --include="*.md" --include="*.png" --exclude="*" $(INTERMEDIATE_DIR)/ $(OUTPUT_NEW_DOCS_DIR)
+	rsync -avm --include="*/" --include="*.mdx" --include="*.md" --include="*.png" --exclude="*" $(INTERMEDIATE_DIR)/ $(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
 
-generate-watch:
-	fswatch $(SOURCE_DIR) | xargs -I{} make _generate-files-internal 
-
-echo:
-	echo "hi"
-	echo x$(SOURCE_PATHS)x
-
-build-watch:
-	fswatch $(INTERMEDIATE_DIR) | grep -E --line-buffered "(?:.md|.mdx|.ipynb)$$" | xargs -I{} make render md-sync copy-infra SOURCE_PATHS={}
-
 vercel-build: install-vercel-deps build generate-references
 	rm -rf docs
 	mv $(OUTPUT_NEW_DOCS_DIR) docs

docs/README.md

@@ -1,14 +1,3 @@
 # LangChain Documentation
 
 For more information on contributing to our documentation, see the [Documentation Contributing Guide](https://python.langchain.com/docs/contributing/documentation)
-
-## Makefile
-
-The included Makefile coordinates all building of the documentation.
-There are 4 main steps to building the documentation:
-
-1. Installing dependencies
-2. Copying and downloading files into `build/intermediate`
-3. Rendering the files from `build/intermediate` to `build/output-new`
-4. Building `build/output-new` in docusaurus
-

docs/api_reference/create_api_rst.py

@@ -10,12 +10,21 @@ from pathlib import Path
 from typing import Dict, List, Literal, Optional, Sequence, TypedDict, Union
 
 import toml
+import typing_extensions
+from langchain_core.runnables import Runnable, RunnableSerializable
 from pydantic import BaseModel
 
 ROOT_DIR = Path(__file__).parents[2].absolute()
 HERE = Path(__file__).parent
 
-ClassKind = Literal["TypedDict", "Regular", "Pydantic", "enum"]
+ClassKind = Literal[
+    "TypedDict",
+    "Regular",
+    "Pydantic",
+    "enum",
+    "RunnablePydantic",
+    "RunnableNonPydantic",
+]
 
 
 class ClassInfo(TypedDict):
@@ -69,8 +78,36 @@ def _load_module_members(module_path: str, namespace: str) -> ModuleMembers:
             continue
 
         if inspect.isclass(type_):
-            if type(type_) == typing._TypedDictMeta:  # type: ignore
+            # The clasification of the class is used to select a template
+            # for the object when rendering the documentation.
+            # See `templates` directory for defined templates.
+            # This is a hacky solution to distinguish between different
+            # kinds of thing that we want to render.
+            if type(type_) is typing_extensions._TypedDictMeta:  # type: ignore
                 kind: ClassKind = "TypedDict"
+            elif type(type_) is typing._TypedDictMeta:  # type: ignore
+                kind: ClassKind = "TypedDict"
+            elif (
+                issubclass(type_, Runnable)
+                and issubclass(type_, BaseModel)
+                and type_ is not Runnable
+            ):
+                # RunnableSerializable subclasses from Pydantic which
+                # for which we use autodoc_pydantic for rendering.
+                # We need to distinguish these from regular Pydantic
+                # classes so we can hide inherited Runnable methods
+                # and provide a link to the Runnable interface from
+                # the template.
+                kind = "RunnablePydantic"
+            elif (
+                issubclass(type_, Runnable)
+                and not issubclass(type_, BaseModel)
+                and type_ is not Runnable
+            ):
+                # These are not pydantic classes but are Runnable.
+                # We'll hide all the inherited methods from Runnable
+                # but use a regular class template to render.
+                kind = "RunnableNonPydantic"
             elif issubclass(type_, Enum):
                 kind = "enum"
             elif issubclass(type_, BaseModel):
@@ -128,11 +165,11 @@ def _load_package_modules(
     of the modules/packages are part of the package vs. 3rd party or built-in.
 
     Parameters:
-        package_directory: Path to the package directory.
-        submodule: Optional name of submodule to load.
+        package_directory (Union[str, Path]): Path to the package directory.
+        submodule (Optional[str]): Optional name of submodule to load.
 
     Returns:
-        list: A list of loaded module objects.
+        Dict[str, ModuleMembers]: A dictionary where keys are module names and values are ModuleMembers objects.
     """
     package_path = (
         Path(package_directory)
@@ -251,6 +288,10 @@ Classes
                     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"
 

docs/api_reference/templates/class.rst

@@ -33,4 +33,4 @@
    {% endblock %}
 
 
-.. example_links:: {{ objname }}
+.. example_links:: {{ objname }}

docs/api_reference/templates/pydantic.rst

@@ -15,6 +15,8 @@
     :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, to_json_not_implemented, lc_secrets, lc_attributes, lc_id, get_lc_namespace
+
 
     {% block attributes %}
     {% endblock %}

docs/api_reference/templates/runnable_non_pydantic.rst

@@ -0,0 +1,39 @@
+:mod:`{{module}}`.{{objname}}
+{{ underline }}==============
+
+.. NOTE:: {{objname}} implements the standard :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>`. 🏃
+
+
+.. currentmodule:: {{ module }}
+
+.. autoclass:: {{ objname }}
+
+   {% block attributes %}
+   {% if attributes %}
+   .. rubric:: {{ _('Attributes') }}
+
+   .. autosummary::
+   {% for item in attributes %}
+      ~{{ name }}.{{ item }}
+   {%- endfor %}
+   {% endif %}
+   {% endblock %}
+
+   {% block methods %}
+   {% if methods %}
+   .. rubric:: {{ _('Methods') }}
+
+   .. autosummary::
+   {% for item in methods %}
+      ~{{ name }}.{{ item }}
+   {%- endfor %}
+
+   {% for item in methods %}
+   .. automethod:: {{ name }}.{{ item }}
+   {%- endfor %}
+
+   {% endif %}
+   {% endblock %}
+
+
+.. example_links:: {{ objname }}

docs/api_reference/templates/runnable_pydantic.rst

@@ -0,0 +1,22 @@
+:mod:`{{module}}`.{{objname}}
+{{ underline }}==============
+
+.. NOTE:: {{objname}} implements the standard :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>`. 🏃
+
+.. currentmodule:: {{ module }}
+
+.. autopydantic_model:: {{ objname }}
+    :model-show-json: False
+    :model-show-config-summary: False
+    :model-show-validator-members: False
+    :model-show-field-summary: False
+    :field-signature-prefix: param
+    :members:
+    :undoc-members:
+    :inherited-members:
+    :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, to_json_not_implemented, lc_secrets, lc_attributes, lc_id, get_lc_namespace, invoke, ainvoke, batch, abatch, batch_as_completed, abatch_as_completed, astream_log, stream, astream, astream_events, transform, atransform, get_output_schema, get_prompts, configurable_fields, configurable_alternatives, 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
+
+.. example_links:: {{ objname }}

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

@@ -2,132 +2,129 @@
 {%- set url_root = pathto('', 1) %}
 {%- if url_root == '#' %}{% set url_root = '' %}{% endif %}
 {%- if not embedded and docstitle %}
-  {%- set titlesuffix = " — "|safe + docstitle|e %}
+    {%- set titlesuffix = " — "|safe + docstitle|e %}
 {%- else %}
-  {%- set titlesuffix = "" %}
+    {%- 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]-->
+<!--[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">
+    <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" />
+    {% 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 %}
+    {% 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 %}
+    <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">
-        <div class="btn-group w-100 mb-2" role="group" aria-label="rellinks">
-          {%- if prev %}
-            <a href="{{ prev.link|e }}" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="{{ prev.title|striptags }}">Prev</a>
-          {%- else %}
-            <a href="#" role="button" class="btn sk-btn-rellink py-1 disabled"">Prev</a>
-          {%- endif %}
-          {%- if parents -%}
-            <a href="{{ parents[-1].link|e }}" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="{{ parents[-1].title|striptags }}">Up</a>
-          {%- else %}
-            <a href="#" role="button" class="btn sk-btn-rellink disabled py-1">Up</a>
-          {%- endif %}
-          {%- if next %}
-            <a href="{{ next.link|e }}" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="{{ next.title|striptags }}">Next</a>
-          {%- else %}
-            <a href="#" role="button" class="btn sk-btn-rellink py-1 disabled"">Next</a>
-          {%- endif %}
+    <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>
-            {%- 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 id="sk-page-content-wrapper">
+            <div class="sk-page-content container-fluid body px-md-3" role="main">
+                {% block body %}{% endblock %}
             </div>
-            {%- elif meta and meta['globalsidebartoc']|tobool %}
-            <div class="sk-sidebar-toc sk-sidebar-global-toc">
-              {{ toctree(maxdepth=2, titles_only=True) }}
+            <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>
-            {%- else %}
-            <div class="sk-sidebar-toc">
-              {{ toc }}
-            </div>
-            {%- endif %}
-      </div>
+        </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" %}

docs/docs/additional_resources/arxiv_references.mdx

@@ -4,6 +4,9 @@ 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).
+
 ## Summary
 
 | arXiv id / Title | Authors | Published date 🔻 | LangChain Documentation|
@@ -25,17 +28,18 @@ This page contains `arXiv` papers referenced in the LangChain Documentation, API
 | `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.llms...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community.llms...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), [langchain_huggingface.llms...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community.llms...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)
-| `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.chains...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)
+| `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)
+| `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.example_selectors...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.pal_chain](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.pal_chain), [langchain_experimental.pal_chain...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)
+| `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)
 | `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)
-| `2205.12654v1` [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.embeddings...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.utilities...SparkSQL](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.spark_sql.SparkSQL.html#langchain_community.utilities.spark_sql.SparkSQL), [langchain_community.utilities...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.llms...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community.llms...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), [langchain_huggingface.llms...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint)
+| `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)
 | `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.llms...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community.llms...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), [langchain_huggingface.llms...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint)
+| `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)
 
 ## Self-Discover: Large Language Models Self-Compose Reasoning Structures
@@ -537,7 +541,7 @@ more than 1/1,000th the compute of GPT-4.
 - **URL:** http://arxiv.org/abs/2301.10226v4
 - **LangChain:**
 
-   - **API Reference:** [langchain_community.llms...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community.llms...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), [langchain_huggingface.llms...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community.llms...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)
+   - **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)
 
 **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
@@ -562,7 +566,7 @@ family, and discuss robustness and security.
 - **URL:** http://arxiv.org/abs/2212.10496v1
 - **LangChain:**
 
-   - **API Reference:** [langchain.chains...HypotheticalDocumentEmbedder](https://api.python.langchain.com/en/latest/chains/langchain.chains.hyde.base.HypotheticalDocumentEmbedder.html#langchain.chains.hyde.base.HypotheticalDocumentEmbedder)
+   - **API Reference:** [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)
 
@@ -626,7 +630,7 @@ further work on logical fallacy identification.
 - **URL:** http://arxiv.org/abs/2211.13892v2
 - **LangChain:**
 
-   - **API Reference:** [langchain_core.example_selectors...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)
+   - **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)
 
 **Abstract:** Large language models (LLMs) have exhibited remarkable capabilities in
 learning from explanations in prompts, but there has been limited understanding
@@ -654,7 +658,7 @@ performance across three real-world tasks on multiple LLMs.
 - **URL:** http://arxiv.org/abs/2211.10435v2
 - **LangChain:**
 
-   - **API Reference:** [langchain_experimental.pal_chain](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.pal_chain), [langchain_experimental.pal_chain...PALChain](https://api.python.langchain.com/en/latest/pal_chain/langchain_experimental.pal_chain.base.PALChain.html#langchain_experimental.pal_chain.base.PALChain)
+   - **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)
    - **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
@@ -680,6 +684,41 @@ accuracy on the GSM8K benchmark of math word problems, surpassing PaLM-540B
 which uses chain-of-thought by absolute 15% top-1. Our code and data are
 publicly available at http://reasonwithpal.com/ .
                 
+## ReAct: Synergizing Reasoning and Acting in Language Models
+
+- **arXiv id:** 2210.03629v3
+- **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)
+
+**Abstract:** While large language models (LLMs) have demonstrated impressive capabilities
+across tasks in language understanding and interactive decision making, their
+abilities for reasoning (e.g. chain-of-thought prompting) and acting (e.g.
+action plan generation) have primarily been studied as separate topics. In this
+paper, we explore the use of LLMs to generate both reasoning traces and
+task-specific actions in an interleaved manner, allowing for greater synergy
+between the two: reasoning traces help the model induce, track, and update
+action plans as well as handle exceptions, while actions allow it to interface
+with external sources, such as knowledge bases or environments, to gather
+additional information. We apply our approach, named ReAct, to a diverse set of
+language and decision making tasks and demonstrate its effectiveness over
+state-of-the-art baselines, as well as improved human interpretability and
+trustworthiness over methods without reasoning or acting components.
+Concretely, on question answering (HotpotQA) and fact verification (Fever),
+ReAct overcomes issues of hallucination and error propagation prevalent in
+chain-of-thought reasoning by interacting with a simple Wikipedia API, and
+generates human-like task-solving trajectories that are more interpretable than
+baselines without reasoning traces. On two interactive decision making
+benchmarks (ALFWorld and WebShop), ReAct outperforms imitation and
+reinforcement learning methods by an absolute success rate of 34% and 10%
+respectively, while being prompted with only one or two in-context examples.
+Project site with code: https://react-lm.github.io
+                
 ## Deep Lake: a Lakehouse for Deep Learning
 
 - **arXiv id:** 2209.10785v2
@@ -717,7 +756,7 @@ TensorFlow, JAX, and integrate with numerous MLOps tools.
 - **URL:** http://arxiv.org/abs/2205.12654v1
 - **LangChain:**
 
-   - **API Reference:** [langchain_community.embeddings...LaserEmbeddings](https://api.python.langchain.com/en/latest/embeddings/langchain_community.embeddings.laser.LaserEmbeddings.html#langchain_community.embeddings.laser.LaserEmbeddings)
+   - **API Reference:** [langchain_community...LaserEmbeddings](https://api.python.langchain.com/en/latest/embeddings/langchain_community.embeddings.laser.LaserEmbeddings.html#langchain_community.embeddings.laser.LaserEmbeddings)
 
 **Abstract:** Scaling multilingual representation learning beyond the hundred most frequent
 languages is challenging, in particular to cover the long tail of low-resource
@@ -746,7 +785,7 @@ encoders, mine bitexts, and validate the bitexts by training NMT systems.
 - **URL:** http://arxiv.org/abs/2204.00498v1
 - **LangChain:**
 
-   - **API Reference:** [langchain_community.utilities...SparkSQL](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.spark_sql.SparkSQL.html#langchain_community.utilities.spark_sql.SparkSQL), [langchain_community.utilities...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...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)
 
 **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
@@ -765,7 +804,7 @@ few-shot examples.
 - **URL:** http://arxiv.org/abs/2202.00666v5
 - **LangChain:**
 
-   - **API Reference:** [langchain_community.llms...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community.llms...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), [langchain_huggingface.llms...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint)
+   - **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)
 
 **Abstract:** Today's probabilistic language generators fall short when it comes to
 producing coherent and fluent text despite the fact that the underlying models
@@ -829,7 +868,7 @@ https://github.com/OpenAI/CLIP.
 - **URL:** http://arxiv.org/abs/1909.05858v2
 - **LangChain:**
 
-   - **API Reference:** [langchain_community.llms...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community.llms...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), [langchain_huggingface.llms...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_huggingface.llms.huggingface_endpoint.HuggingFaceEndpoint)
+   - **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)
 
 **Abstract:** Large-scale language models show promising text generation capabilities, but
 users cannot easily control particular aspects of the generated text. We

docs/docs/additional_resources/tutorials.mdx

@@ -11,6 +11,7 @@
 ### [by Prompt Engineering](https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr)
 ### [by Mayo Oshin](https://www.youtube.com/@chatwithdata/search?query=langchain)
 ### [by 1 little Coder](https://www.youtube.com/playlist?list=PLpdmBGJ6ELUK-v0MK-t4wZmVEbxM5xk6L)
+### [by BobLin (Chinese language)](https://www.youtube.com/playlist?list=PLbd7ntv6PxC3QMFQvtWfk55p-Op_syO1C)
 
 ## Courses
 
@@ -45,7 +46,6 @@
 - [Generative AI with LangChain](https://www.amazon.com/Generative-AI-LangChain-language-ChatGPT/dp/1835083463/ref=sr_1_1?crid=1GMOMH0G7GLR&keywords=generative+ai+with+langchain&qid=1703247181&sprefix=%2Caps%2C298&sr=8-1) by [Ben Auffrath](https://www.amazon.com/stores/Ben-Auffarth/author/B08JQKSZ7D?ref=ap_rdr&store_ref=ap_rdr&isDramIntegrated=true&shoppingPortalEnabled=true), ©️ 2023 Packt Publishing
 - [LangChain AI Handbook](https://www.pinecone.io/learn/langchain/) By **James Briggs** and **Francisco Ingham**
 - [LangChain Cheatsheet](https://pub.towardsai.net/langchain-cheatsheet-all-secrets-on-a-single-page-8be26b721cde) by **Ivan Reznikov**
+- [Dive into Langchain (Chinese language)](https://langchain.boblin.app/)
 
 ---------------------
-
-

docs/docs/concepts.mdx

@@ -11,7 +11,7 @@ LangChain as a framework consists of a number of packages.
 
 ### `langchain-core`
 This package contains base abstractions of different components and ways to compose them together.
-The interfaces for core components like LLMs, vectorstores, retrievers and more are defined here.
+The interfaces for core components like LLMs, vector stores, retrievers and more are defined here.
 No third party integrations are defined here.
 The dependencies are kept purposefully very lightweight.
 
@@ -30,7 +30,7 @@ All chains, agents, and retrieval strategies here are NOT specific to any one in
 
 This package contains third party integrations that are maintained by the LangChain community.
 Key partner packages are separated out (see below).
-This contains all integrations for various components (LLMs, vectorstores, retrievers).
+This contains all integrations for various components (LLMs, vector stores, retrievers).
 All dependencies in this package are optional to keep the package as lightweight as possible.
 
 ### [`langgraph`](https://langchain-ai.github.io/langgraph)
@@ -38,7 +38,7 @@ All dependencies in this package are optional to keep the package as lightweight
 `langgraph` is an extension of `langchain` aimed at
 building robust and stateful multi-actor applications with LLMs by modeling steps as edges and nodes in a graph.
 
-LangGraph exposes high level interfaces for creating common types of agents, as well as a low-level API for constructing more contr
+LangGraph exposes high level interfaces for creating common types of agents, as well as a low-level API for composing custom flows.
 
 ### [`langserve`](/docs/langserve)
 
@@ -58,6 +58,7 @@ A developer platform that lets you debug, test, evaluate, and monitor LLM applic
 />
 
 ## LangChain Expression Language (LCEL)
+<span data-heading-keywords="lcel"></span>
 
 LangChain Expression Language, or LCEL, is a declarative way to chain LangChain components.
 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 (we’ve seen folks successfully run LCEL chains with 100s of steps in production). To highlight a few of the reasons you might want to use LCEL:
@@ -88,15 +89,16 @@ With LCEL, **all** steps are automatically logged to [LangSmith](https://docs.sm
 Any chain created with LCEL can be easily deployed using [LangServe](/docs/langserve).
 
 ### Runnable interface
+<span data-heading-keywords="invoke"></span>
 
 To make it as easy as possible to create custom chains, we've implemented a ["Runnable"](https://api.python.langchain.com/en/stable/runnables/langchain_core.runnables.base.Runnable.html#langchain_core.runnables.base.Runnable) protocol. Many LangChain components implement the `Runnable` protocol, including chat models, LLMs, output parsers, retrievers, prompt templates, and more. There are also several useful primitives for working with runnables, which you can read about below.
 
 This is a standard interface, which makes it easy to define custom chains as well as invoke them in a standard way.
 The standard interface includes:
 
-- [`stream`](#stream): stream back chunks of the response
-- [`invoke`](#invoke): call the chain on an input
-- [`batch`](#batch): call the chain on a list of inputs
+- `stream`: stream back chunks of the response
+- `invoke`: call the chain on an input
+- `batch`: call the chain on a list of inputs
 
 These also have corresponding async methods that should be used with [asyncio](https://docs.python.org/3/library/asyncio.html) `await` syntax for concurrency:
 
@@ -128,21 +130,33 @@ LangChain provides standard, extendable interfaces and external integrations for
 Some components LangChain implements, some components we rely on third-party integrations for, and others are a mix.
 
 ### Chat models
+<span data-heading-keywords="chat model,chat models"></span>
 
 Language models that use a sequence of messages as inputs and return chat messages as outputs (as opposed to using plain text).
-These are traditionally newer models (older models are generally `LLMs`, see above).
+These are traditionally newer models (older models are generally `LLMs`, see below).
 Chat models support the assignment of distinct roles to conversation messages, helping to distinguish messages from the AI, users, and instructions such as system messages.
 
 Although the underlying models are messages in, message out, the LangChain wrappers also allow these models to take a string as input. This means you can easily use chat models in place of LLMs.
 
-When a string is passed in as input, it is converted to a HumanMessage and then passed to the underlying model.
+When a string is passed in as input, it is converted to a `HumanMessage` and then passed to the underlying model.
 
-LangChain does not provide any ChatModels, rather we rely on third party integrations.
+LangChain does not host any Chat Models, rather we rely on third party integrations.
 
 We have some standardized parameters when constructing ChatModels:
 - `model`: the name of the model
+- `temperature`: the sampling temperature
+- `timeout`: request timeout
+- `max_tokens`: max tokens to generate
+- `stop`: default stop sequences
+- `max_retries`: max number of times to retry requests
+- `api_key`: API key for the model provider
+- `base_url`: endpoint to send requests to
 
-ChatModels also accept other parameters that are specific to that integration.
+Some important things to note:
+- standard params only apply to model providers that expose parameters with the intended functionality. For example, some providers do not expose a configuration for maximum output tokens, so max_tokens can't be supported on these.
+- standard params are currently only enforced on integrations that have their own integration packages (e.g. `langchain-openai`, `langchain-anthropic`, etc.), they're not enforced on models in ``langchain-community``.
+
+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.
@@ -150,16 +164,38 @@ Generally, such models are better at tool calling than non-fine-tuned models, an
 Please see the [tool calling section](/docs/concepts/#functiontool-calling) for more information.
 :::
 
+For specifics on how to use chat models, see the [relevant how-to guides here](/docs/how_to/#chat-models).
+
+#### Multimodality
+
+Some chat models are multimodal, accepting images, audio and even video as inputs. These are still less common, meaning model providers haven't standardized on the "best" way to define the API. Multimodal **outputs** are even less common. As such, we've kept our multimodal abstractions fairly light weight and plan to further solidify the multimodal APIs and interaction patterns as the field matures.
+
+In LangChain, most chat models that support multimodal inputs also accept those values in OpenAI's content blocks format. So far this is restricted to image inputs. For models like Gemini which support video and other bytes input, the APIs also support the native, model-specific representations.
+
+For specifics on how to use multimodal models, see the [relevant how-to guides here](/docs/how_to/#multimodal).
+
+For a full list of LangChain model providers with multimodal models, [check out this table](/docs/integrations/chat/#advanced-features).
+
 ### LLMs
+<span data-heading-keywords="llm,llms"></span>
+
+:::caution
+Pure text-in/text-out LLMs tend to be older or lower-level. Many popular models are best used as [chat completion models](/docs/concepts/#chat-models),
+even for non-chat use cases.
+
+You are probably looking for [the section above instead](/docs/concepts/#chat-models).
+:::
 
 Language models that takes a string as input and returns a string.
-These are traditionally older models (newer models generally are `ChatModels`, see below).
+These are traditionally older models (newer models generally are [Chat Models](/docs/concepts/#chat-models), see above).
 
 Although the underlying models are string in, string out, the LangChain wrappers also allow these models to take messages as input.
-This makes them interchangeable with ChatModels.
+This gives them the same interface as [Chat Models](/docs/concepts/#chat-models).
 When messages are passed in as input, they will be formatted into a string under the hood before being passed to the underlying model.
 
-LangChain does not provide any LLMs, rather we rely on third party integrations.
+LangChain does not host any LLMs, rather we rely on third party integrations.
+
+For specifics on how to use LLMs, see the [relevant how-to guides here](/docs/how_to/#llms).
 
 ### Messages
 
@@ -214,6 +250,8 @@ This represents the result of a tool call. This is distinct from a FunctionMessa
 
 
 ### Prompt templates
+<span data-heading-keywords="prompt,prompttemplate,chatprompttemplate"></span>
+
 Prompt templates help to translate user input and parameters into instructions for a language model.
 This can be used to guide a model's response, helping it understand the context and generate relevant and coherent language-based output.
 
@@ -222,7 +260,7 @@ Prompt Templates take as input a dictionary, where each key represents a variabl
 Prompt Templates output a PromptValue. This PromptValue can be passed to an LLM or a ChatModel, and can also be cast to a string or a list of messages.
 The reason this PromptValue exists is to make it easy to switch between strings and messages.
 
-There are a few different types of prompt templates
+There are a few different types of prompt templates:
 
 #### String PromptTemplates
 
@@ -258,6 +296,7 @@ The first is a system message, that has no variables to format.
 The second is a HumanMessage, and will be formatted by the `topic` variable the user passes in.
 
 #### MessagesPlaceholder
+<span data-heading-keywords="messagesplaceholder"></span>
 
 This prompt template is responsible for adding a list of messages in a particular place.
 In the above ChatPromptTemplate, we saw how we could format two messages, each one a string.
@@ -289,14 +328,18 @@ prompt_template = ChatPromptTemplate.from_messages([
 ])
 ```
 
+For specifics on how to use prompt templates, see the [relevant how-to guides here](/docs/how_to/#prompt-templates).
+
 ### Example selectors
 One common prompting technique for achieving better performance is to include examples as part of the prompt.
 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.
 
+For specifics on how to use example selectors, see the [relevant how-to guides here](/docs/how_to/#example-selectors).
 
 ### Output parsers
+<span data-heading-keywords="output parser"></span>
 
 :::note
 
@@ -340,16 +383,19 @@ LangChain has lots of different types of output parsers. This is a list of outpu
 | [Datetime](https://api.python.langchain.com/en/latest/output_parsers/langchain.output_parsers.datetime.DatetimeOutputParser.html#langchain.output_parsers.datetime.DatetimeOutputParser)        |                    | ✅                             |           | `str` \| `Message`                 | `datetime.datetime`  | Parses response into a datetime string.                                                                                                                                                                                                                  |
 | [Structured](https://api.python.langchain.com/en/latest/output_parsers/langchain.output_parsers.structured.StructuredOutputParser.html#langchain.output_parsers.structured.StructuredOutputParser)      |                    | ✅                             |           | `str` \| `Message`                 | `Dict[str, str]`     | An output parser that returns structured information. It is less powerful than other output parsers since it only allows for fields to be strings. This can be useful when you are working with smaller LLMs.                                            |
 
+For specifics on how to use output parsers, see the [relevant how-to guides here](/docs/how_to/#output-parsers).
+
 ### Chat history
 Most LLM applications have a conversational interface.
 An essential component of a conversation is being able to refer to information introduced earlier in the conversation.
 At bare minimum, a conversational system should be able to access some window of past messages directly.
 
 The concept of `ChatHistory` refers to a class in LangChain which can be used to wrap an arbitrary chain.
-This `ChatHistory` will keep track of inputs and outputs of the underlying chain, and append them as messages to a message database
+This `ChatHistory` will keep track of inputs and outputs of the underlying chain, and append them as messages to a message database.
 Future interactions will then load those messages and pass them into the chain as part of the input.
 
 ### Documents
+<span data-heading-keywords="document,documents"></span>
 
 A Document object in LangChain contains information about some data. It has two attributes:
 
@@ -357,6 +403,7 @@ A Document object in LangChain contains information about some data. It has two
 - `metadata: dict`: Arbitrary metadata associated with this document. Can track the document id, file name, etc.
 
 ### Document loaders
+<span data-heading-keywords="document loader,document loaders"></span>
 
 These classes load Document objects. LangChain has hundreds of integrations with various data sources to load data from: Slack, Notion, Google Drive, etc.
 
@@ -372,6 +419,8 @@ loader = CSVLoader(
 data = loader.load()
 ```
 
+For specifics on how to use document loaders, see the [relevant how-to guides here](/docs/how_to/#document-loaders).
+
 ### Text splitters
 
 Once you've loaded documents, you'll often want to transform them to better suit your application. The simplest example is you may want to split a long document into smaller chunks that can fit into your model's context window. LangChain has a number of built-in document transformers that make it easy to split, combine, filter, and otherwise manipulate documents.
@@ -389,18 +438,34 @@ That means there are two different axes along which you can customize your text
 1. How the text is split
 2. How the chunk size is measured
 
-### Embedding models
-The Embeddings class is a class designed for interfacing with text embedding models. There are lots of embedding model providers (OpenAI, Cohere, Hugging Face, etc) - this class is designed to provide a standard interface for all of them.
+For specifics on how to use text splitters, see the [relevant how-to guides here](/docs/how_to/#text-splitters).
 
-Embeddings create a vector representation of a piece of text. This is useful because it means we can think about text in the vector space, and do things like semantic search where we look for pieces of text that are most similar in the vector space.
+### Embedding models
+<span data-heading-keywords="embedding,embeddings"></span>
+
+Embedding models create a vector representation of a piece of text. You can think of a vector as an array of numbers that captures the semantic meaning of the text.
+By representing the text in this way, you can perform mathematical operations that allow you to do things like search for other pieces of text that are most similar in meaning.
+These natural language search capabilities underpin many types of [context retrieval](/docs/concepts/#retrieval),
+where we provide an LLM with the relevant data it needs to effectively respond to a query.
+
+![](/img/embeddings.png)
+
+The `Embeddings` class is a class designed for interfacing with text embedding models. There are many different embedding model providers (OpenAI, Cohere, Hugging Face, etc) and local models, and this class is designed to provide a standard interface for all of them.
 
 The base Embeddings class in LangChain provides two methods: one for embedding documents and one for embedding a query. The former takes as input multiple texts, while the latter takes a single text. The reason for having these as two separate methods is that some embedding providers have different embedding methods for documents (to be searched over) vs queries (the search query itself).
 
+For specifics on how to use embedding models, see the [relevant how-to guides here](/docs/how_to/#embedding-models).
+
 ### Vector stores
+<span data-heading-keywords="vector,vectorstore,vectorstores,vector store,vector stores"></span>
+
 One of the most common ways to store and search over unstructured data is to embed it and store the resulting embedding vectors,
 and then at query time to embed the unstructured query and retrieve the embedding vectors that are 'most similar' to the embedded query.
 A vector store takes care of storing embedded data and performing vector search for you.
 
+Most vector stores can also store metadata about embedded vectors and support filtering on that metadata before
+similarity search, allowing you more control over returned documents.
+
 Vector stores can be converted to the retriever interface by doing:
 
 ```python
@@ -408,15 +473,22 @@ vectorstore = MyVectorStore()
 retriever = vectorstore.as_retriever()
 ```
 
+For specifics on how to use vector stores, see the [relevant how-to guides here](/docs/how_to/#vector-stores).
+
 ### Retrievers
+<span data-heading-keywords="retriever,retrievers"></span>
+
 A retriever is an interface that returns documents given an unstructured query.
 It is more general than a vector store.
 A retriever does not need to be able to store documents, only to return (or retrieve) them.
-Retrievers can be created from vectorstores, but are also broad enough to include [Wikipedia search](/docs/integrations/retrievers/wikipedia/) and [Amazon Kendra](/docs/integrations/retrievers/amazon_kendra_retriever/).
+Retrievers can be created from vector stores, but are also broad enough to include [Wikipedia search](/docs/integrations/retrievers/wikipedia/) and [Amazon Kendra](/docs/integrations/retrievers/amazon_kendra_retriever/).
 
 Retrievers accept a string query as input and return a list of Document's as output.
 
+For specifics on how to use retrievers, see the [relevant how-to guides here](/docs/how_to/#retrievers).
+
 ### 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.
 
@@ -442,6 +514,8 @@ Generally, when designing tools to be used by a chat model or LLM, it is importa
 - 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.
 
+For specifics on how to use tools, see the [relevant how-to guides here](/docs/how_to/#tools).
+
 ### Toolkits
 
 Toolkits are collections of tools that are designed to be used together for specific tasks. They have convenient loading methods.
@@ -461,7 +535,7 @@ tools = toolkit.get_tools()
 
 By themselves, language models can't take actions - they just output text.
 A big use case for LangChain is creating **agents**.
-Agents are systems that use an LLM as a reasoning enginer to determine which actions to take and what the inputs to those actions should be.
+Agents are systems that use an LLM as a reasoning engine to determine which actions to take and what the inputs to those actions should be.
 The results of those actions can then be fed back into the agent and it determine whether more actions are needed, or whether it is okay to finish.
 
 [LangGraph](https://github.com/langchain-ai/langgraph) is an extension of LangChain specifically aimed at creating highly controllable and customizable agents.
@@ -474,13 +548,7 @@ In order to solve that we built LangGraph to be this flexible, highly-controllab
 
 If you are still using AgentExecutor, do not fear: we still have a guide on [how to use AgentExecutor](/docs/how_to/agent_executor).
 It is recommended, however, that you start to transition to LangGraph.
-In order to assist in this we have put together a [transition guide on how to do so](/docs/how_to/migrate_agent)
-
-### Multimodal
-
-Some models are multimodal, accepting images, audio and even video as inputs. These are still less common, meaning model providers haven't standardized on the "best" way to define the API. Multimodal **outputs** are even less common. As such, we've kept our multimodal abstractions fairly light weight and plan to further solidify the multimodal APIs and interaction patterns as the field matures.
-
-In LangChain, most chat models that support multimodal inputs also accept those values in OpenAI's content blocks format. So far this is restricted to image inputs. For models like Gemini which support video and other bytes input, the APIs also support the native, model-specific representations.
+In order to assist in this we have put together a [transition guide on how to do so](/docs/how_to/migrate_agent).
 
 ### Callbacks
 
@@ -552,15 +620,224 @@ This is a common reason why you may fail to see events being emitted from custom
 runnables or tools.
 :::
 
+For specifics on how to use callbacks, see the [relevant how-to guides here](/docs/how_to/#callbacks).
+
 ## Techniques
 
-### Function/tool calling
+### Streaming
+<span data-heading-keywords="stream,streaming"></span>
+
+Individual LLM calls often run for much longer than traditional resource requests.
+This compounds when you build more complex chains or agents that require multiple reasoning steps.
+
+Fortunately, LLMs generate output iteratively, which means it's possible to show sensible intermediate results
+before the final response is ready. Consuming output as soon as it becomes available has therefore become a vital part of the UX
+around building apps with LLMs to help alleviate latency issues, and LangChain aims to have first-class support for streaming.
+
+Below, we'll discuss some concepts and considerations around streaming in LangChain.
+
+#### `.stream()` and `.astream()`
+
+Most modules in LangChain include the `.stream()` method (and the equivalent `.astream()` method for [async](https://docs.python.org/3/library/asyncio.html) environments) as an ergonomic streaming interface.
+`.stream()` returns an iterator, which you can consume with a simple `for` loop. Here's an example with a chat model:
+
+```python
+from langchain_anthropic import ChatAnthropic
+
+model = ChatAnthropic(model="claude-3-sonnet-20240229")
+
+for chunk in model.stream("what color is the sky?"):
+    print(chunk.content, end="|", flush=True)
+```
+
+For models (or other components) that don't support streaming natively, this iterator would just yield a single chunk, but
+you could still use the same general pattern when calling them. Using `.stream()` will also automatically call the model in streaming mode
+without the need to provide additional config.
+
+The type of each outputted chunk depends on the type of component - for example, chat models yield [`AIMessageChunks`](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.ai.AIMessageChunk.html).
+Because this method is part of [LangChain Expression Language](/docs/concepts/#langchain-expression-language-lcel),
+you can handle formatting differences from different outputs using an [output parser](/docs/concepts/#output-parsers) to transform
+each yielded chunk.
+
+You can check out [this guide](/docs/how_to/streaming/#using-stream) for more detail on how to use `.stream()`.
+
+#### `.astream_events()`
+<span data-heading-keywords="astream_events,stream_events,stream events"></span>
+
+While the `.stream()` method is intuitive, it can only return the final generated value of your chain. This is fine for single LLM calls,
+but as you build more complex chains of several LLM calls together, you may want to use the intermediate values of
+the chain alongside the final output - for example, returning sources alongside the final generation when building a chat
+over documents app.
+
+There are ways to do this [using callbacks](/docs/concepts/#callbacks-1), or by constructing your chain in such a way that it passes intermediate
+values to the end with something like chained [`.assign()`](/docs/how_to/passthrough/) calls, but LangChain also includes an
+`.astream_events()` method that combines the flexibility of callbacks with the ergonomics of `.stream()`. When called, it returns an iterator
+which yields [various types of events](/docs/how_to/streaming/#event-reference) that you can filter and process according
+to the needs of your project.
+
+Here's one small example that prints just events containing streamed chat model output:
+
+```python
+from langchain_core.output_parsers import StrOutputParser
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_anthropic import ChatAnthropic
+
+model = ChatAnthropic(model="claude-3-sonnet-20240229")
+
+prompt = ChatPromptTemplate.from_template("tell me a joke about {topic}")
+parser = StrOutputParser()
+chain = prompt | model | parser
+
+async for event in chain.astream_events({"topic": "parrot"}, version="v2"):
+    kind = event["event"]
+    if kind == "on_chat_model_stream":
+        print(event, end="|", flush=True)
+```
+
+You can roughly think of it as an iterator over callback events (though the format differs) - and you can use it on almost all LangChain components!
+
+See [this guide](/docs/how_to/streaming/#using-stream-events) for more detailed information on how to use `.astream_events()`,
+including a table listing available events.
+
+#### Callbacks
+
+The lowest level way to stream outputs from LLMs in LangChain is via the [callbacks](/docs/concepts/#callbacks) system. You can pass a
+callback handler that handles the [`on_llm_new_token`](https://api.python.langchain.com/en/latest/callbacks/langchain.callbacks.streaming_aiter.AsyncIteratorCallbackHandler.html#langchain.callbacks.streaming_aiter.AsyncIteratorCallbackHandler.on_llm_new_token) event into LangChain components. When that component is invoked, any
+[LLM](/docs/concepts/#llms) or [chat model](/docs/concepts/#chat-models) contained in the component calls
+the callback with the generated token. Within the callback, you could pipe the tokens into some other destination, e.g. a HTTP response.
+You can also handle the [`on_llm_end`](https://api.python.langchain.com/en/latest/callbacks/langchain.callbacks.streaming_aiter.AsyncIteratorCallbackHandler.html#langchain.callbacks.streaming_aiter.AsyncIteratorCallbackHandler.on_llm_end) event to perform any necessary cleanup.
+
+You can see [this how-to section](/docs/how_to/#callbacks) for more specifics on using callbacks.
+
+Callbacks were the first technique for streaming introduced in LangChain. While powerful and generalizable,
+they can be unwieldy for developers. For example:
+
+- You need to explicitly initialize and manage some aggregator or other stream to collect results.
+- The execution order isn't explicitly guaranteed, and you could theoretically have a callback run after the `.invoke()` method finishes.
+- Providers would often make you pass an additional parameter to stream outputs instead of returning them all at once.
+- You would often ignore the result of the actual model call in favor of callback results.
+
+#### Tokens
+
+The unit that most model providers use to measure input and output is via a unit called a **token**.
+Tokens are the basic units that language models read and generate when processing or producing text.
+The exact definition of a token can vary depending on the specific way the model was trained -
+for instance, in English, a token could be a single word like "apple", or a part of a word like "app".
+
+When you send a model a prompt, the words and characters in the prompt are encoded into tokens using a **tokenizer**.
+The model then streams back generated output tokens, which the tokenizer decodes into human-readable text.
+The below example shows how OpenAI models tokenize `LangChain is cool!`:
+
+![](/img/tokenization.png)
+
+You can see that it gets split into 5 different tokens, and that the boundaries between tokens are not exactly the same as word boundaries.
+
+The reason language models use tokens rather than something more immediately intuitive like "characters"
+has to do with how they process and understand text. At a high-level, language models iteratively predict their next generated output based on
+the initial input and their previous generations. Training the model using tokens language models to handle linguistic
+units (like words or subwords) that carry meaning, rather than individual characters, which makes it easier for the model
+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.
+
+### Structured output
+
+LLMs are capable of generating arbitrary text. This enables the model to respond appropriately to a wide
+range of inputs, but for some use-cases, it can be useful to constrain the LLM's output
+to a specific format or structure. This is referred to as **structured output**.
+
+For example, if the output is to be stored in a relational database,
+it is much easier if the model generates output that adheres to a defined schema or format.
+[Extracting specific information](/docs/tutorials/extraction/) from unstructured text is another
+case where this is particularly useful. Most commonly, the output format will be JSON,
+though other formats such as [YAML](/docs/how_to/output_parser_yaml/) can be useful too. Below, we'll discuss
+a few ways to get structured output from models in LangChain.
+
+#### `.with_structured_output()`
+
+For convenience, some LangChain chat models support a `.with_structured_output()` method.
+This method only requires a schema as input, and returns a dict or Pydantic object.
+Generally, this method is only present on models that support one of the more advanced methods described below,
+and will use one of them under the hood. It takes care of importing a suitable output parser and
+formatting the schema in the right format for the model.
+
+For more information, check out this [how-to guide](/docs/how_to/structured_output/#the-with_structured_output-method).
+
+#### Raw prompting
+
+The most intuitive way to get a model to structure output is to ask nicely.
+In addition to your query, you can give instructions describing what kind of output you'd like, then
+parse the output using an [output parser](/docs/concepts/#output-parsers) to convert the raw
+model message or string output into something more easily manipulated.
+
+The biggest benefit to raw prompting is its flexibility:
+
+- Raw prompting does not require any special model features, only sufficient reasoning capability to understand
+the passed schema.
+- You can prompt for any format you'd like, not just JSON. This can be useful if the model you
+are using is more heavily trained on a certain type of data, such as XML or YAML.
+
+However, there are some drawbacks too:
+
+- LLMs are non-deterministic, and prompting a LLM to consistently output data in the exactly correct format
+for smooth parsing can be surprisingly difficult and model-specific.
+- Individual models have quirks depending on the data they were trained on, and optimizing prompts can be quite difficult.
+Some may be better at interpreting [JSON schema](https://json-schema.org/), others may be best with TypeScript definitions,
+and still others may prefer XML.
+
+While we'll next go over some ways that you can take advantage of features offered by
+model providers to increase reliability, prompting techniques remain important for tuning your
+results no matter what method you choose.
+
+#### JSON mode
+<span data-heading-keywords="json mode"></span>
+
+Some models, such as [Mistral](/docs/integrations/chat/mistralai/), [OpenAI](/docs/integrations/chat/openai/),
+[Together AI](/docs/integrations/chat/together/) and [Ollama](/docs/integrations/chat/ollama/),
+support a feature called **JSON mode**, usually enabled via config.
+
+When enabled, JSON mode will constrain the model's output to always be some sort of valid JSON.
+Often they require some custom prompting, but it's usually much less burdensome and along the lines of,
+`"you must always return JSON"`, and the [output is easier to parse](/docs/how_to/output_parser_json/).
+
+It's also generally simpler and more commonly available than tool calling.
+
+Here's an example:
+
+```python
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_openai import ChatOpenAI
+from langchain.output_parsers.json import SimpleJsonOutputParser
+
+model = ChatOpenAI(
+    model="gpt-4o",
+    model_kwargs={ "response_format": { "type": "json_object" } },
+)
+
+prompt = ChatPromptTemplate.from_template(
+    "Answer the user's question to the best of your ability."
+    'You must always output a JSON object with an "answer" key and a "followup_question" key.'
+    "{question}"
+)
+
+chain = prompt | model | SimpleJsonOutputParser()
+
+chain.invoke({ "question": "What is the powerhouse of the cell?" })
+```
+
+```
+{'answer': 'The powerhouse of the cell is the mitochondrion. It is responsible for producing energy in the form of ATP through cellular respiration.',
+ 'followup_question': 'Would you like to know more about how mitochondria produce energy?'}
+```
+
+For a full list of model providers that support JSON mode, see [this table](/docs/integrations/chat/#advanced-features).
+
+#### 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.
+each message
 :::
 
 Tool calling allows a model to respond to a given prompt by generating output that
@@ -572,8 +849,10 @@ 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.
 
-A tool call includes a name, arguments dict, and an optional identifier. The
-arguments dict is structured `{argument_name: argument_value}`.
+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.
 
 Many LLM providers, including [Anthropic](https://www.anthropic.com/),
 [Cohere](https://cohere.com/), [Google](https://cloud.google.com/vertex-ai),
@@ -590,39 +869,174 @@ LangChain provides a standardized interface for tool calling that is consistent
 
 The standard interface consists of:
 
-* `ChatModel.bind_tools()`: a method for specifying which tools are available for a model to call.
+* `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.
 
-There are two main use cases for function/tool calling:
+The following how-to guides are good practical resources for using function/tool calling:
 
 - [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/)
+- [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).
 
 ### Retrieval
 
-LangChain provides several advanced retrieval types. A full list is below, along with the following information:
+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). 
+Retrieval is the process of providing relevant information to an LLM to improve its response for a given input. Retrieval augmented generation (RAG) is the process of grounding the LLM generation (output) using the retrieved information.
 
-**Name**: Name of the retrieval algorithm.
+:::tip
 
-**Index Type**: Which index type (if any) this relies on.
+* See our RAG from Scratch [code](https://github.com/langchain-ai/rag-from-scratch) and [video series](https://youtube.com/playlist?list=PLfaIDFEXuae2LXbO1_PKyVJiQ23ZztA0x&feature=shared).
+* For a high-level guide on retrieval, see this [tutorial on RAG](/docs/tutorials/rag/).
 
-**Uses an LLM**: Whether this retrieval method uses an LLM.
+:::
 
-**When to Use**: Our commentary on when you should considering using this retrieval method.
+RAG is only as good as the retrieved documents’ relevance and quality. Fortunately, an emerging set of techniques can be employed to design and improve RAG systems. We've focused on taxonomizing and summarizing many of these techniques (see below figure) and will share some high-level strategic guidance in the following sections.
+You can and should experiment with using different pieces together. You might also find [this LangSmith guide](https://docs.smith.langchain.com/how_to_guides/evaluation/evaluate_llm_application) useful for showing how to evaluate different iterations of your app.
 
-**Description**: Description of what this retrieval algorithm is doing.
+![](/img/rag_landscape.png)
+
+#### Query Translation
+
+First, consider the user input(s) to your RAG system. Ideally, a RAG system can handle a wide range of inputs, from poorly worded questions to complex multi-part queries.
+**Using an LLM to review and optionally modify the input is the central idea behind query translation.** This serves as a general buffer, optimizing raw user inputs for your retrieval system. 
+For example, this can be as simple as extracting keywords or as complex as generating multiple sub-questions for a complex query.
+
+| Name          | When to use | Description |
+|---------------|-------------|-------------|
+| [Multi-query](/docs/how_to/MultiQueryRetriever/)   | When you need to cover multiple perspectives of a question. | Rewrite the user question from multiple perspectives, retrieve documents for each rewritten question, return the unique documents for all queries. |
+| [Decomposition](https://github.com/langchain-ai/rag-from-scratch/blob/main/rag_from_scratch_5_to_9.ipynb) | When a question can be broken down into smaller subproblems. | Decompose a question into a set of subproblems / questions, which can either be solved sequentially (use the answer from first + retrieval to answer the second) or in parallel (consolidate each answer into final answer). |
+| [Step-back](https://github.com/langchain-ai/rag-from-scratch/blob/main/rag_from_scratch_5_to_9.ipynb)     | When a higher-level conceptual understanding is required. | First prompt the LLM to ask a generic step-back question about higher-level concepts or principles, and retrieve relevant facts about them. Use this grounding to help answer the user question. |
+| [HyDE](https://github.com/langchain-ai/rag-from-scratch/blob/main/rag_from_scratch_5_to_9.ipynb)          | If you have challenges retrieving relevant documents using the raw user inputs. | Use an LLM to convert questions into hypothetical documents that answer the question. Use the embedded hypothetical documents to retrieve real documents with the premise that doc-doc similarity search can produce more relevant matches. |
+
+:::tip
+
+See our RAG from Scratch videos for a few different specific approaches:
+- [Multi-query](https://youtu.be/JChPi0CRnDY?feature=shared)
+- [Decomposition](https://youtu.be/h0OPWlEOank?feature=shared)
+- [Step-back](https://youtu.be/xn1jEjRyJ2U?feature=shared)
+- [HyDE](https://youtu.be/SaDzIVkYqyY?feature=shared)
+
+:::
+
+#### Routing
+
+Second, consider the data sources available to your RAG system. You want to query across more than one database or across structured and unstructured data sources. **Using an LLM to review the input and route it to the appropriate data source is a simple and effective approach for querying across sources.**
+
+| Name             | When to use                                | Description |
+|------------------|--------------------------------------------|-------------|
+| [Logical routing](/docs/how_to/routing/)  | When you can prompt an LLM with rules to decide where to route the input. | Logical routing can use an LLM to reason about the query and choose which datastore is most appropriate. |
+| [Semantic routing](/docs/how_to/routing/#routing-by-semantic-similarity) | When semantic similarity is an effective way to determine where to route the input. | Semantic routing embeds both query and, typically a set of prompts. It then chooses the appropriate prompt based upon similarity. |
+
+:::tip
+
+See our RAG from Scratch video on [routing](https://youtu.be/pfpIndq7Fi8?feature=shared).  
+
+:::
+
+#### Query Construction
+
+Third, consider whether any of your data sources require specific query formats. Many structured databases use SQL. Vector stores often have specific syntax for applying keyword filters to document metadata. **Using an LLM to convert a natural language query into a query syntax is a popular and powerful approach.**
+In particular, [text-to-SQL](/docs/tutorials/sql_qa/), [text-to-Cypher](/docs/tutorials/graph/), and [query analysis for metadata filters](/docs/tutorials/query_analysis/#query-analysis) are useful ways to interact with structured, graph, and vector databases respectively. 
+
+| Name                                        | When to Use                                                                                                                                   | Description                                                                                                                                                                                                                                                                                      |
+|---------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| [Text to SQL](/docs/tutorials/sql_qa/)      | If users are asking questions that require information housed in a relational database, accessible via SQL.                                   | This uses an LLM to transform user input into a SQL query.                                             |
+| [Text-to-Cypher](/docs/tutorials/graph/)    | If users are asking questions that require information housed in a graph database, accessible via Cypher.                                     | This uses an LLM to transform user input into a Cypher query.                                              |
+| [Self Query](/docs/how_to/self_query/)      | If users are asking questions that are better answered by fetching documents based on metadata rather than similarity with the text.          | This uses an LLM to transform user input into two things: (1) a string to look up semantically, (2) a metadata filter to go along with it. This is useful because oftentimes questions are about the METADATA of documents (not the content itself).                                              |
+
+:::tip
+
+See our [blog post overview](https://blog.langchain.dev/query-construction/) and RAG from Scratch video on [query construction](https://youtu.be/kl6NwWYxvbM?feature=shared), the process of text-to-DSL where DSL is a domain specific language required to interact with a given database. This converts user questions into structured queries. 
+
+:::
+
+#### Indexing
+
+Fouth, consider the design of your document index. A simple and powerful idea is to **decouple the documents that you index for retrieval from the documents that you pass to the LLM for generation.** Indexing frequently uses embedding models with vector stores, which [compress the semantic information in documents to fixed-size vectors](/docs/concepts/#embedding-models).
+
+Many RAG approaches focus on splitting documents into chunks and retrieving some number based on similarity to an input question for the LLM. But chunk size and chunk number can be difficult to set and affect results if they do not provide full context for the LLM to answer a question. Furthermore, LLMs are increasingly capable of processing millions of tokens. 
+
+Two approaches can address this tension: (1) [Multi Vector](/docs/how_to/multi_vector/) retriever using an LLM to translate documents into any form (e.g., often into a summary) that is well-suited for indexing, but returns full documents to the LLM for generation. (2) [ParentDocument](/docs/how_to/parent_document_retriever/) retriever embeds document chunks, but also returns full documents. The idea is to get the best of both worlds: use concise representations (summaries or chunks) for retrieval, but use the full documents for answer generation.
 
 | Name                      | Index Type                   | Uses an LLM               | When to Use                                                                                                                                   | Description                                                                                                                                                                                                                                                                                      |
 |---------------------------|------------------------------|---------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| [Vectorstore](/docs/how_to/vectorstore_retriever/)               | Vectorstore                  | No                        | If you are just getting started and looking for something quick and easy.                                                                     | This is the simplest method and the one that is easiest to get started with. It involves creating embeddings for each piece of text.                                                                                                                                                             |
-| [ParentDocument](/docs/how_to/parent_document_retriever/)            | Vectorstore + Document Store | No                        | If your pages have lots of smaller pieces of distinct information that are best indexed by themselves, but best retrieved all together.       | This involves indexing multiple chunks for each document. Then you find the chunks that are most similar in embedding space, but you retrieve the whole parent document and return that (rather than individual chunks).                                                                         |
-| [Multi Vector](/docs/how_to/multi_vector/)              | Vectorstore + Document Store | Sometimes during indexing | If you are able to extract information from documents that you think is more relevant to index than the text itself.                          | This involves creating multiple vectors for each document. Each vector could be created in a myriad of ways - examples include summaries of the text and hypothetical questions.                                                                                                                 |
-| [Self Query](/docs/how_to/self_query/)               | Vectorstore                  | Yes                       | If users are asking questions that are better answered by fetching documents based on metadata rather than similarity with the text.          | This uses an LLM to transform user input into two things: (1) a string to look up semantically, (2) a metadata filer to go along with it. This is useful because oftentimes questions are about the METADATA of documents (not the content itself).                                              |
-| [Contextual Compression](/docs/how_to/contextual_compression/)    | Any                          | Sometimes                 | If you are finding that your retrieved documents contain too much irrelevant information and are distracting the LLM.                         | This puts a post-processing step on top of another retriever and extracts only the most relevant information from retrieved documents. This can be done with embeddings or an LLM.                                                                                                               |
-| [Time-Weighted Vectorstore](/docs/how_to/time_weighted_vectorstore/) | Vectorstore                  | No                        | If you have timestamps associated with your documents, and you want to retrieve the most recent ones                                          | This fetches documents based on a combination of semantic similarity (as in normal vector retrieval) and recency (looking at timestamps of indexed documents)                                                                                                                                    |
-| [Multi-Query Retriever](/docs/how_to/MultiQueryRetriever/)     | Any                          | Yes                       | If users are asking questions that are complex and require multiple pieces of distinct information to respond                                 | This uses an LLM to generate multiple queries from the original one. This is useful when the original query needs pieces of information about multiple topics to be properly answered. By generating multiple queries, we can then fetch documents for each of them.                             |
-| [Ensemble](/docs/how_to/ensemble_retriever/)                  | Any                          | No                        | If you have multiple retrieval methods and want to try combining them.                                                                        | This fetches documents from multiple retrievers and then combines them.                                                                                                                                                                                                                          |
+| [Vector store](/docs/how_to/vectorstore_retriever/)               | Vector store                  | No                        | If you are just getting started and looking for something quick and easy.                                                                     | This is the simplest method and the one that is easiest to get started with. It involves creating embeddings for each piece of text.                                                                                                                                                             |
+| [ParentDocument](/docs/how_to/parent_document_retriever/)            | Vector store + Document Store | No                        | If your pages have lots of smaller pieces of distinct information that are best indexed by themselves, but best retrieved all together.       | This involves indexing multiple chunks for each document. Then you find the chunks that are most similar in embedding space, but you retrieve the whole parent document and return that (rather than individual chunks).                                                                         |
+| [Multi Vector](/docs/how_to/multi_vector/)              | Vector store + Document Store | Sometimes during indexing | If you are able to extract information from documents that you think is more relevant to index than the text itself.                          | This involves creating multiple vectors for each document. Each vector could be created in a myriad of ways - examples include summaries of the text and hypothetical questions.                                                                                                                 |
+| [Time-Weighted Vector store](/docs/how_to/time_weighted_vectorstore/) | Vector store                  | No                        | If you have timestamps associated with your documents, and you want to retrieve the most recent ones                                          | This fetches documents based on a combination of semantic similarity (as in normal vector retrieval) and recency (looking at timestamps of indexed documents)                                                                                                                                    |
 
+:::tip
+
+- See our RAG from Scratch video on [indexing fundamentals](https://youtu.be/bjb_EMsTDKI?feature=shared)
+- See our RAG from Scratch video on [multi vector retriever](https://youtu.be/gTCU9I6QqCE?feature=shared)
+
+:::
+
+Fifth, consider ways to improve the quality of your similarity search itself. Embedding models compress text into fixed-length (vector) representations that capture the semantic content of the document. This compression is useful for search / retrieval, but puts a heavy burden on that single vector representation to capture the semantic nuance / detail of the document. In some cases, irrelevant or redundant content can dilute the semantic usefulness of the embedding.
+
+[ColBERT](https://docs.google.com/presentation/d/1IRhAdGjIevrrotdplHNcc4aXgIYyKamUKTWtB3m3aMU/edit?usp=sharing) is an interesting approach to address this with a higher granularity embeddings: (1) produce a contextually influenced embedding for each token in the document and query, (2) score similarity between each query token and all document tokens, (3) take the max, (4) do this for all query tokens, and (5) take the sum of the max scores (in step 3) for all query tokens to get a query-document similarity score; this token-wise scoring can yield strong results. 
+
+![](/img/colbert.png)
+
+There are some additional tricks to improve the quality of your retrieval. Embeddings excel at capturing semantic information, but may struggle with keyword-based queries. Many [vector stores](/docs/integrations/retrievers/pinecone_hybrid_search/) offer built-in [hybrid-search](https://docs.pinecone.io/guides/data/understanding-hybrid-search) to combine keyword and semantic similarity, which marries the benefits of both approaches. Furthermore, many vector stores have [maximal marginal relevance](https://python.langchain.com/v0.1/docs/modules/model_io/prompts/example_selectors/mmr/), which attempts to diversify the results of a search to avoid returning similar and redundant documents. 
+
+| Name              | When to use                                              | Description |
+|-------------------|----------------------------------------------------------|-------------|
+| [ColBERT](/docs/integrations/providers/ragatouille/#using-colbert-as-a-reranker)           | When higher granularity embeddings are needed.           | ColBERT uses contextually influenced embeddings for each token in the document and query to get a granular query-document similarity score. |
+| [Hybrid search](/docs/integrations/retrievers/pinecone_hybrid_search/)     | When combining keyword-based and semantic similarity.    | Hybrid search combines keyword and semantic similarity, marrying the benefits of both approaches. |
+| [Maximal Marginal Relevance (MMR)](/docs/integrations/vectorstores/pinecone/#maximal-marginal-relevance-searches) | When needing to diversify search results. | MMR attempts to diversify the results of a search to avoid returning similar and redundant documents. |
+
+:::tip
+
+See our RAG from Scratch video on [ColBERT](https://youtu.be/cN6S0Ehm7_8?feature=shared>).
+
+:::
+
+#### Post-processing
+
+Sixth, consider ways to filter or rank retrieved documents. This is very useful if you are [combining documents returned from multiple sources](/docs/integrations/retrievers/cohere-reranker/#doing-reranking-with-coherererank), since it can can down-rank less relevant documents and / or [compress similar documents](/docs/how_to/contextual_compression/#more-built-in-compressors-filters). 
+
+| Name                      | Index Type                   | Uses an LLM               | When to Use                                                                                                                                   | Description                                                                                                                                                                                                                                                                                      |
+|---------------------------|------------------------------|---------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| [Contextual Compression](/docs/how_to/contextual_compression/)    | Any                          | Sometimes                 | If you are finding that your retrieved documents contain too much irrelevant information and are distracting the LLM.                         | This puts a post-processing step on top of another retriever and extracts only the most relevant information from retrieved documents. This can be done with embeddings or an LLM.                                                                                                               |
+| [Ensemble](/docs/how_to/ensemble_retriever/)                  | Any                          | No                        | If you have multiple retrieval methods and want to try combining them.                                                                        | This fetches documents from multiple retrievers and then combines them.                                                                                                                                                                                                                          |
+| [Re-ranking](/docs/integrations/retrievers/cohere-reranker/)                  | Any                          | Yes                        |  If you want to rank retrieved documents based upon relevance, especially if you want to combine results from multiple retrieval methods .                                                                         | Given a query and a list of documents, Rerank indexes the documents from most to least semantically relevant to the query.                                                                                                                                                                                                                         |
+
+:::tip
+
+See our RAG from Scratch video on [RAG-Fusion](https://youtu.be/77qELPbNgxA?feature=shared), on approach for post-processing across multiple queries:  Rewrite the user question from multiple perspectives, retrieve documents for each rewritten question, and combine the ranks of multiple search result lists to produce a single, unified ranking with [Reciprocal Rank Fusion (RRF)](https://towardsdatascience.com/forget-rag-the-future-is-rag-fusion-1147298d8ad1).
+
+:::
+
+#### Generation
+
+**Finally, consider ways to build self-correction into your RAG system.** RAG systems can suffer from low quality retrieval (e.g., if a user question is out of the domain for the index) and / or hallucinations in generation. A naive retrieve-generate pipeline has no ability to detect or self-correct from these kinds of errors. The concept of ["flow engineering"](https://x.com/karpathy/status/1748043513156272416) has been introduced [in the context of code generation](https://arxiv.org/abs/2401.08500): iteratively build an answer to a code question with unit tests to check and self-correct errors. Several works have applied this RAG, such as Self-RAG and Corrective-RAG. In both cases, checks for document relevance, hallucinations, and / or answer quality are performed in the RAG answer generation flow.
+
+We've found that graphs are a great way to reliably express logical flows and have implemented ideas from several of these papers [using LangGraph](https://github.com/langchain-ai/langgraph/tree/main/examples/rag), as shown in the figure below (red - routing, blue - fallback, green - self-correction):
+- **Routing:** Adaptive RAG ([paper](https://arxiv.org/abs/2403.14403)). Route questions to different retrieval approaches, as discussed above 
+- **Fallback:** Corrective RAG ([paper](https://arxiv.org/pdf/2401.15884.pdf)). Fallback to web search if docs are not relevant to query
+- **Self-correction:** Self-RAG ([paper](https://arxiv.org/abs/2310.11511)). Fix answers w/ hallucinations or don’t address question
+
+![](/img/langgraph_rag.png)
+
+| Name              | When to use                                               | Description |
+|-------------------|-----------------------------------------------------------|-------------|
+| Self-RAG          | When needing to fix answers with hallucinations or irrelevant content. | Self-RAG performs checks for document relevance, hallucinations, and answer quality during the RAG answer generation flow, iteratively building an answer and self-correcting errors. |
+| Corrective-RAG    | When needing a fallback mechanism for low relevance docs. | Corrective-RAG includes a fallback (e.g., to web search) if the retrieved documents are not relevant to the query, ensuring higher quality and more relevant retrieval. |
+
+:::tip
+
+See several videos and cookbooks showcasing RAG with LangGraph: 
+- [LangGraph Corrective RAG](https://www.youtube.com/watch?v=E2shqsYwxck)
+- [LangGraph combining Adaptive, Self-RAG, and Corrective RAG](https://www.youtube.com/watch?v=-ROS6gfYIts) 
+- [Cookbooks for RAG using LangGraph](https://github.com/langchain-ai/langgraph/tree/main/examples/rag)
+
+See our LangGraph RAG recipes with partners:
+- [Meta](https://github.com/meta-llama/llama-recipes/tree/main/recipes/use_cases/agents/langchain) 
+- [Mistral](https://github.com/mistralai/cookbook/tree/main/third_party/langchain)
+
+:::
 
 ### Text splitting
 
@@ -649,6 +1063,19 @@ Table columns:
 | Semantic Chunker (Experimental) | [SemanticChunker](/docs/how_to/semantic-chunker/)                                                                                                                             | Sentences                                                                                                       |               | First splits on sentences. Then combines ones next to each other if they are semantically similar enough. Taken from [Greg Kamradt](https://github.com/FullStackRetrieval-com/RetrievalTutorials/blob/main/tutorials/LevelsOfTextSplitting/5_Levels_Of_Text_Splitting.ipynb) |
 | Integration: AI21 Semantic | [AI21SemanticTextSplitter](/docs/integrations/document_transformers/ai21_semantic_text_splitter/)                                                                                                                    |    ✅           | Identifies distinct topics that form coherent pieces of text and splits along those.                                                                                                                                                                                         |
 
+### Evaluation
+<span data-heading-keywords="evaluation,evaluate"></span>
 
+Evaluation is the process of assessing the performance and effectiveness of your LLM-powered applications.
+It involves testing the model's responses against a set of predefined criteria or benchmarks to ensure it meets the desired quality standards and fulfills the intended purpose.
+This process is vital for building reliable applications.
 
+![](/img/langsmith_evaluate.png)
 
+[LangSmith](https://docs.smith.langchain.com/) helps with this process in a few ways:
+
+- It makes it easier to create and curate datasets via its tracing and annotation features
+- It provides an evaluation framework that helps you define metrics and run your app against your dataset
+- It allows you to track results over time and automatically run your evaluators on a schedule or as part of CI/Code
+
+To learn more, check out [this LangSmith guide](https://docs.smith.langchain.com/concepts/evaluation).

docs/docs/contributing/code.mdx

@@ -206,9 +206,7 @@ ignore-words-list = 'momento,collison,ned,foor,reworkd,parth,whats,aapply,mysogy
 
 `langchain-core` and partner packages **do not use** optional dependencies in this way.
 
-You only need to add a new dependency if a **unit test** relies on the package.
-If your package is only required for **integration tests**, then you can skip these
-steps and leave all pyproject.toml and poetry.lock files alone.
+You'll notice that `pyproject.toml` and `poetry.lock` are **not** touched when you add optional dependencies below.
 
 If you're adding a new dependency to Langchain, assume that it will be an optional dependency, and
 that most users won't have it installed.
@@ -216,20 +214,12 @@ that most users won't have it installed.
 Users who do not have the dependency installed should be able to **import** your code without
 any side effects (no warnings, no errors, no exceptions).
 
-To introduce the dependency to the pyproject.toml file correctly, please do the following:
+To introduce the dependency to a library, please do the following:
 
-1. Add the dependency to the main group as an optional dependency
-  ```bash
-  poetry add --optional [package_name]
-  ```
-2. Open pyproject.toml and add the dependency to the `extended_testing` extra
-3. Relock the poetry file to update the extra.
-  ```bash
-  poetry lock --no-update
-  ```
-4. Add a unit test that the very least attempts to import the new code. Ideally, the unit
+1. Open extended_testing_deps.txt and add the dependency
+2. Add a unit test that the very least attempts to import the new code. Ideally, the unit
 test makes use of lightweight fixtures to test the logic of the code.
-5. Please use the `@pytest.mark.requires(package_name)` decorator for any tests that require the dependency.
+3. Please use the `@pytest.mark.requires(package_name)` decorator for any unit tests that require the dependency.
 
 ## Adding a Jupyter Notebook
 

docs/docs/contributing/documentation/_category_.yml

@@ -0,0 +1,2 @@
+label: 'Documentation'
+position: 3

docs/docs/contributing/documentation/style_guide.mdx

@@ -55,7 +55,7 @@ The below sections are listed roughly in order of increasing level of abstractio
 
 ### Expression Language
 
-[LangChain Expression Language (LCEL)](/docs/concepts#langchain-expression-language) is the fundamental way that most LangChain components fit together, and this section is designed to teach
+[LangChain Expression Language (LCEL)](/docs/concepts#langchain-expression-language-lcel) is the fundamental way that most LangChain components fit together, and this section is designed to teach
 developers how to use it to build with LangChain's primitives effectively.
 
 This section should contains **Tutorials** that teach how to stream and use LCEL primitives for more abstract tasks, **Explanations** of specific behaviors,

docs/docs/contributing/how_to/index.mdx

@@ -1,35 +0,0 @@
----
-sidebar_class_name: hidden
----
-# Contributor how-to guides
-
-This section contains guides for contributors to the project. If you're looking to contribute to the project, this is a good place to start.
-
-This content is heavily inspired by scikit-learn's [contributing guide](https://scikit-learn.org/dev/developers/contributing.html).
-
-## Getting started
-
-- How to: create a minimal reproducible example
-- How to: find a package's source code
-- How to: set up the codebase
-- How to: lint and format documentation and code
-- [How to: run tests](./testing.mdx): Learn how to run tests in all of our packages
-- How to: open a pull request
-
-## Contributing documentation
-
-- How to: build the documentation locally
-- How to: edit markdown (.md, .mdx) documentation
-- How to: use code tabs in markdown
-- How to: edit Jupyter notebook (.ipynb) documentation
-- How to: add images to documentation
-
-## Contributing code
-
-- How to: find a bug to fix
-- How to: 
-
-## Old stuff
-- [Documentation](./documentation.mdx): Learn how to contribute to the documentation.
-- [Code](./code.mdx): Learn how to develop in the LangChain codebase.
-- [Integrations](./integrations.mdx): Learn how to contribute to third-party integrations to the LangChain ecosystem.

docs/docs/contributing/how_to/minimal_reproducer.mdx

@@ -1,19 +0,0 @@
----
-sidebar_label: Minimal Reproducible Examples
-sidebar_position: 0
----
-
-# How to craft a minimal reproducible example for LangChain
-
-:::info
-This guide is a LangChain-specific adaptation of sklearn's [minimal reproducer guide](https://scikit-learn.org/dev/developers/minimal_reproducer.html).
-:::
-
-Whether submitting a bug report, designing a suite of tests, or simply posting a question in the discussions, being able to craft minimal, reproducible examples (or minimal, workable examples) is the key to communicating effectively and efficiently with the community.
-
-There are very good guidelines on the internet such as this [StackOverflow document](https://stackoverflow.com/help/minimal-reproducible-example) or [this blogpost by Matthew Rocklin](https://matthewrocklin.com/minimal-bug-reports) on crafting Minimal Complete Verifiable Examples (referred below as MCVE). Our goal is not to be repetitive with those references but rather to provide a step-by-step guide on how to narrow down a bug until you have reached the shortest possible code to reproduce it.
-
-The first step before submitting a bug report to LangChain is to read the Issue template. It is already quite informative about the information you will be asked to provide.
-
-## Good practices
-

docs/docs/contributing/index.mdx

@@ -1,10 +1,54 @@
-# Contributing guide
+---
+sidebar_position: 0
+---
+# Welcome Contributors
 
-LangChain is an open-source project written by an amazing community of developers and maintained by the team at [LangChain AI](https://www.langchain.com).
+Hi there! Thank you for even being interested in contributing to LangChain.
+As an open-source project in a rapidly developing field, we are extremely open to contributions, whether they involve new features, improved infrastructure, better documentation, or bug fixes.
 
-There are many ways to contribute to LangChain, and please read this guide to learn how you can most effectively contribute to the project!
+## 🗺️ Guidelines
 
-For existing contributors, we have a [Contributor Cheat Sheet](./reference/cheat_sheet.mdx) as quick reference.
+### 👩‍💻 Ways to contribute
 
-## How to contribute
+There are many ways to contribute to LangChain. Here are some common ways people contribute:
 
+- [**Documentation**](/docs/contributing/documentation/style_guide): Help improve our docs, including this one!
+- [**Code**](./code.mdx): Help us write code, fix bugs, or improve our infrastructure.
+- [**Integrations**](integrations.mdx): Help us integrate with your favorite vendors and tools.
+- [**Discussions**](https://github.com/langchain-ai/langchain/discussions): Help answer usage questions and discuss issues with users.
+
+### 🚩 GitHub Issues
+
+Our [issues](https://github.com/langchain-ai/langchain/issues) page is kept up to date with bugs, improvements, and feature requests.
+
+There is a taxonomy of labels to help with sorting and discovery of issues of interest. Please use these to help organize issues.
+
+If you start working on an issue, please assign it to yourself.
+
+If you are adding an issue, please try to keep it focused on a single, modular bug/improvement/feature.
+If two issues are related, or blocking, please link them rather than combining them.
+
+We will try to keep these issues as up-to-date as possible, though
+with the rapid rate of development in this field some may get out of date.
+If you notice this happening, please let us know.
+
+### 💭 GitHub Discussions
+
+We have a [discussions](https://github.com/langchain-ai/langchain/discussions) page where users can ask usage questions, discuss design decisions, and propose new features.
+
+If you are able to help answer questions, please do so! This will allow the maintainers to spend more time focused on development and bug fixing.
+
+### 🙋 Getting Help
+
+Our goal is to have the simplest developer setup possible. Should you experience any difficulty getting setup, please
+contact a maintainer! Not only do we want to help get you unblocked, but we also want to make sure that the process is
+smooth for future contributors.
+
+In a similar vein, we do enforce certain linting, formatting, and documentation standards in the codebase.
+If you are finding these difficult (or even just annoying) to work with, feel free to contact a maintainer for help -
+we do not want these to get in the way of getting good code into the codebase.
+
+### 🌟 Recognition
+
+If your contribution has made its way into a release, we will want to give you credit on Twitter (only if you want though)!
+If you have a Twitter account you would like us to mention, please let us know in the PR or through another means.

docs/docs/contributing/reference/cheat_sheet.mdx

@@ -1,16 +0,0 @@
----
-sidebar_label: "Cheat sheet"
-sidebar_position: 1
----
-# Contributing cheat sheet
-
-## Pull request lifecycle
-
-1. Open a **draft** pull request
-2. Merge in latest master ("Update branch")
-3. Confirm that the CI checks pass
-4. Mark "Ready to review" to convert from draft to full PR
-5. Wait for a review. 
-6. Address review comments within 72 hours. In the event of no activity for 72 hours, the PR will be closed (but you can reopen).
-
-## 

docs/docs/contributing/reference/index.mdx

@@ -1,11 +0,0 @@
----
-sidebar_class_name: hidden
----
-# Contributor reference
-
-This section contains reference material for contributors to the project.
-
-- [Cheat sheet](./cheat_sheet.mdx): A quick reference for contributors.
-- [Repo structure](./repo_structure.mdx): Learn about the structure of the LangChain repository.
-- [Documentation style guide](./documentation_style_guide.mdx): Learn how to write documentation for LangChain.
-- [FAQ](./faq.mdx): Frequently asked questions about contributing to LangChain.

docs/docs/contributing/repo_structure.mdx

@@ -15,12 +15,22 @@ Here's the structure visualized as a tree:
 ├── cookbook # Tutorials and examples
 ├── docs # Contains content for the documentation here: https://python.langchain.com/
 ├── libs
-│   ├── langchain # Main package
+│   ├── langchain
+│   │   ├── langchain
 │   │   ├── tests/unit_tests # Unit tests (present in each package not shown for brevity)
 │   │   ├── tests/integration_tests # Integration tests (present in each package not shown for brevity)
-│   ├── langchain-community # Third-party integrations
-│   ├── langchain-core # Base interfaces for key abstractions
-│   ├── langchain-experimental # Experimental components and chains
+│   ├── community # Third-party integrations
+│   │   ├── langchain-community
+│   ├── core # Base interfaces for key abstractions
+│   │   ├── langchain-core
+│   ├── experimental # Experimental components and chains
+│   │   ├── langchain-experimental
+|   ├── cli # Command line interface
+│   │   ├── langchain-cli
+│   ├── text-splitters
+│   │   ├── langchain-text-splitters
+│   ├── standard-tests
+│   │   ├── langchain-standard-tests
 │   ├── partners
 │       ├── langchain-partner-1
 │       ├── langchain-partner-2
@@ -49,6 +59,6 @@ The `/libs` directory contains the code for the LangChain packages.
 
 To learn more about how to contribute code see the following guidelines:
 
-- [Code](../how_to/code.mdx) Learn how to develop in the LangChain codebase.
-- [Integrations](../how_to/integrations.mdx) to learn how to contribute to third-party integrations to langchain-community or to start a new partner package.
-- [Testing](../how_to/testing.mdx) guidelines to learn how to write tests for the packages.
+- [Code](./code.mdx) Learn how to develop in the LangChain codebase.
+- [Integrations](./integrations.mdx) to learn how to contribute to third-party integrations to langchain-community or to start a new partner package.
+- [Testing](./testing.mdx) guidelines to learn how to write tests for the packages.

docs/docs/how_to/agent_executor.ipynb

@@ -15,7 +15,11 @@
    "id": "f4c03f40-1328-412d-8a48-1db0cd481b77",
    "metadata": {},
    "source": [
-    "# Build an Agent\n",
+    "# Build an Agent with AgentExecutor (Legacy)\n",
+    "\n",
+    ":::{.callout-important}\n",
+    "This section will cover building with the legacy LangChain AgentExecutor. These are fine for getting started, but past a certain point, you will likely want flexibility and control that they do not offer. For working with more advanced agents, we'd recommend checking out [LangGraph Agents](/docs/concepts/#langgraph) or the [migration guide](/docs/how_to/migrate_agent/)\n",
+    ":::\n",
     "\n",
     "By themselves, language models can't take actions - they just output text.\n",
     "A big use case for LangChain is creating **agents**.\n",
@@ -24,10 +28,6 @@
     "\n",
     "In this tutorial, we will build an agent that can interact with multiple different tools: one being a local database, the other being a search engine. You will be able to ask this agent questions, watch it call tools, and have conversations with it.\n",
     "\n",
-    ":::{.callout-important}\n",
-    "This section will cover building with LangChain Agents. LangChain Agents are fine for getting started, but past a certain point, you will likely want flexibility and control that they do not offer. For working with more advanced agents, we'd reccommend checking out [LangGraph](/docs/concepts/#langgraph)\n",
-    ":::\n",
-    "\n",
     "## Concepts\n",
     "\n",
     "Concepts we will cover are:\n",

docs/docs/how_to/binding.ipynb

@@ -23,7 +23,7 @@
     "This guide assumes familiarity with the following concepts:\n",
     "- [LangChain Expression Language (LCEL)](/docs/concepts/#langchain-expression-language)\n",
     "- [Chaining runnables](/docs/how_to/sequence/)\n",
-    "- [Tool calling](/docs/how_to/tool_calling/)\n",
+    "- [Tool calling](/docs/how_to/tool_calling)\n",
     "\n",
     ":::\n",
     "\n",
@@ -142,7 +142,7 @@
     "\n",
     "## Attaching OpenAI tools\n",
     "\n",
-    "Another common use-case is tool calling. While you should generally use the [`.bind_tools()`](/docs/how_to/tool_calling/) method for tool-calling models, you can also bind provider-specific args directly if you want lower level control:"
+    "Another common use-case is tool calling. While you should generally use the [`.bind_tools()`](/docs/how_to/tool_calling) method for tool-calling models, you can also bind provider-specific args directly if you want lower level control:"
    ]
   },
   {

docs/docs/how_to/character_text_splitter.ipynb

@@ -1,5 +1,19 @@
 {
  "cells": [
+  {
+   "cell_type": "raw",
+   "id": "f781411d",
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
+   "source": [
+    "---\n",
+    "keywords: [charactertextsplitter]\n",
+    "---"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "c3ee8d00",

docs/docs/how_to/chat_models_universal_init.ipynb

@@ -0,0 +1,157 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "cfdf4f09-8125-4ed1-8063-6feed57da8a3",
+   "metadata": {},
+   "source": [
+    "# How to init any model in one line\n",
+    "\n",
+    "Many LLM applications let end users specify what model provider and model they want the application to be powered by. This requires writing some logic to initialize different ChatModels based on some user configuration. The `init_chat_model()` helper method makes it easy to initialize a number of different model integrations without having to worry about import paths and class names.\n",
+    "\n",
+    ":::tip Supported models\n",
+    "\n",
+    "See the [init_chat_model()](https://api.python.langchain.com/en/latest/chat_models/langchain.chat_models.base.init_chat_model.html) API reference for a full list of supported integrations.\n",
+    "\n",
+    "Make sure you have the integration packages installed for any model providers you want to support. E.g. you should have `langchain-openai` installed to init an OpenAI model.\n",
+    "\n",
+    ":::"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "165b0de6-9ae3-4e3d-aa98-4fc8a97c4a06",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU langchain langchain-openai langchain-anthropic langchain-google-vertexai"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ea2c9f57-a796-45f8-b6f4-3efd3f361a9b",
+   "metadata": {},
+   "source": [
+    "## Basic usage"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "79e14913-803c-4382-9009-5c6af3d75d35",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "GPT-4o: I'm an AI created by OpenAI, and I don't have a personal name. You can call me Assistant! How can I help you today?\n",
+      "\n",
+      "Claude Opus: My name is Claude. It's nice to meet you!\n",
+      "\n",
+      "Gemini 1.5: I am a large language model, trained by Google. I do not have a name. \n",
+      "\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain.chat_models import init_chat_model\n",
+    "\n",
+    "# Returns a langchain_openai.ChatOpenAI instance.\n",
+    "gpt_4o = init_chat_model(\"gpt-4o\", model_provider=\"openai\", temperature=0)\n",
+    "# Returns a langchain_anthropic.ChatAnthropic instance.\n",
+    "claude_opus = init_chat_model(\n",
+    "    \"claude-3-opus-20240229\", model_provider=\"anthropic\", temperature=0\n",
+    ")\n",
+    "# Returns a langchain_google_vertexai.ChatVertexAI instance.\n",
+    "gemini_15 = init_chat_model(\n",
+    "    \"gemini-1.5-pro\", model_provider=\"google_vertexai\", temperature=0\n",
+    ")\n",
+    "\n",
+    "# Since all model integrations implement the ChatModel interface, you can use them in the same way.\n",
+    "print(\"GPT-4o: \" + gpt_4o.invoke(\"what's your name\").content + \"\\n\")\n",
+    "print(\"Claude Opus: \" + claude_opus.invoke(\"what's your name\").content + \"\\n\")\n",
+    "print(\"Gemini 1.5: \" + gemini_15.invoke(\"what's your name\").content + \"\\n\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fff9a4c8-b6ee-4a1a-8d3d-0ecaa312d4ed",
+   "metadata": {},
+   "source": [
+    "## Simple config example"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "75c25d39-bf47-4b51-a6c6-64d9c572bfd6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "user_config = {\n",
+    "    \"model\": \"...user-specified...\",\n",
+    "    \"model_provider\": \"...user-specified...\",\n",
+    "    \"temperature\": 0,\n",
+    "    \"max_tokens\": 1000,\n",
+    "}\n",
+    "\n",
+    "llm = init_chat_model(**user_config)\n",
+    "llm.invoke(\"what's your name\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f811f219-5e78-4b62-b495-915d52a22532",
+   "metadata": {},
+   "source": [
+    "## Inferring model provider\n",
+    "\n",
+    "For common and distinct model names `init_chat_model()` will attempt to infer the model provider. See the [API reference](https://api.python.langchain.com/en/latest/chat_models/langchain.chat_models.base.init_chat_model.html) for a full list of inference behavior. E.g. any model that starts with `gpt-3...` or `gpt-4...` will be inferred as using model provider `openai`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "0378ccc6-95bc-4d50-be50-fccc193f0a71",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gpt_4o = init_chat_model(\"gpt-4o\", temperature=0)\n",
+    "claude_opus = init_chat_model(\"claude-3-opus-20240229\", temperature=0)\n",
+    "gemini_15 = init_chat_model(\"gemini-1.5-pro\", temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "da07b5c0-d2e6-42e4-bfcd-2efcfaae6221",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "poetry-venv-2",
+   "language": "python",
+   "name": "poetry-venv-2"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/how_to/chat_token_usage_tracking.ipynb

@@ -14,35 +14,51 @@
     "\n",
     ":::\n",
     "\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."
+    "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`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9c7d1338-dd1b-4d06-b33d-d5cffc49fd6a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade --quiet langchain langchain-openai"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "1a55e87a-3291-4e7f-8e8e-4c69b0854384",
+   "id": "598ae1e2-a52d-4459-81fd-cdc68b06742a",
    "metadata": {},
    "source": [
-    "## Using AIMessage.response_metadata\n",
+    "## Using LangSmith\n",
     "\n",
-    "A number of model providers return token usage information as part of the chat generation response. When available, this is included in the [`AIMessage.response_metadata`](/docs/how_to/response_metadata) field. Here's an example with OpenAI:"
+    "You can use [LangSmith](https://www.langchain.com/langsmith) to help track token usage in your LLM application. See the [LangSmith quick start guide](https://docs.smith.langchain.com/).\n",
+    "\n",
+    "## Using AIMessage.usage_metadata\n",
+    "\n",
+    "A number of model providers return token usage information as part of the chat generation response. When available, this information will be included on the `AIMessage` objects produced by the corresponding model.\n",
+    "\n",
+    "LangChain `AIMessage` objects include a [usage_metadata](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.ai.AIMessage.html#langchain_core.messages.ai.AIMessage.usage_metadata) attribute. When populated, this attribute will be a [UsageMetadata](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.ai.UsageMetadata.html) dictionary with standard keys (e.g., `\"input_tokens\"` and `\"output_tokens\"`).\n",
+    "\n",
+    "Examples:\n",
+    "\n",
+    "**OpenAI**:"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 1,
-   "id": "467ccdeb-6b62-45e5-816e-167cd24d2586",
+   "id": "b39bf807-4125-4db4-bbf7-28a46afff6b4",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "{'token_usage': {'completion_tokens': 225,\n",
-       "  'prompt_tokens': 17,\n",
-       "  'total_tokens': 242},\n",
-       " 'model_name': 'gpt-4-turbo',\n",
-       " 'system_fingerprint': 'fp_76f018034d',\n",
-       " 'finish_reason': 'stop',\n",
-       " 'logprobs': None}"
+       "{'input_tokens': 8, 'output_tokens': 9, 'total_tokens': 17}"
       ]
      },
      "execution_count": 1,
@@ -51,37 +67,33 @@
     }
    ],
    "source": [
-    "# !pip install -qU langchain-openai\n",
+    "# # !pip install -qU langchain-openai\n",
     "\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "llm = ChatOpenAI(model=\"gpt-4-turbo\")\n",
-    "msg = llm.invoke([(\"human\", \"What's the oldest known example of cuneiform\")])\n",
-    "msg.response_metadata"
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\")\n",
+    "openai_response = llm.invoke(\"hello\")\n",
+    "openai_response.usage_metadata"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "9d5026e9-3ad4-41e6-9946-9f1a26f4a21f",
+   "id": "2299c44a-2fe6-4d52-a6a2-99ff6d231c73",
    "metadata": {},
    "source": [
-    "And here's an example with Anthropic:"
+    "**Anthropic**:"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 2,
-   "id": "145404f1-e088-4824-b468-236c486a9903",
+   "id": "9c82ff80-ec4e-4049-b019-5f0bbd7df82a",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "{'id': 'msg_01P61rdHbapEo6h3fjpfpCQT',\n",
-       " 'model': 'claude-3-sonnet-20240229',\n",
-       " 'stop_reason': 'end_turn',\n",
-       " 'stop_sequence': None,\n",
-       " 'usage': {'input_tokens': 17, 'output_tokens': 306}}"
+       "{'input_tokens': 8, 'output_tokens': 12, 'total_tokens': 20}"
       ]
      },
      "execution_count": 2,
@@ -94,9 +106,222 @@
     "\n",
     "from langchain_anthropic import ChatAnthropic\n",
     "\n",
-    "llm = ChatAnthropic(model=\"claude-3-sonnet-20240229\")\n",
-    "msg = llm.invoke([(\"human\", \"What's the oldest known example of cuneiform\")])\n",
-    "msg.response_metadata"
+    "llm = ChatAnthropic(model=\"claude-3-haiku-20240307\")\n",
+    "anthropic_response = llm.invoke(\"hello\")\n",
+    "anthropic_response.usage_metadata"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6d4efc15-ba9f-4b3d-9278-8e01f99f263f",
+   "metadata": {},
+   "source": [
+    "### Using AIMessage.response_metadata\n",
+    "\n",
+    "Metadata from the model response is also included in the AIMessage [response_metadata](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.ai.AIMessage.html#langchain_core.messages.ai.AIMessage.response_metadata) attribute. These data are typically not standardized. Note that different providers adopt different conventions for representing token counts:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "f156f9da-21f2-4c81-a714-54cbf9ad393e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "OpenAI: {'completion_tokens': 9, 'prompt_tokens': 8, 'total_tokens': 17}\n",
+      "\n",
+      "Anthropic: {'input_tokens': 8, 'output_tokens': 12}\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(f'OpenAI: {openai_response.response_metadata[\"token_usage\"]}\\n')\n",
+    "print(f'Anthropic: {anthropic_response.response_metadata[\"usage\"]}')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b4ef2c43-0ff6-49eb-9782-e4070c9da8d7",
+   "metadata": {},
+   "source": [
+    "### Streaming\n",
+    "\n",
+    "Some providers support token count metadata in a streaming context.\n",
+    "\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_options={\"include_usage\": True}`.\n",
+    "\n",
+    "```{=mdx}\n",
+    ":::note\n",
+    "By default, the last message chunk in a stream will include a `\"finish_reason\"` in the message's `response_metadata` attribute. If we include token usage in streaming mode, an additional chunk containing usage metadata will be added to the end of the stream, such that `\"finish_reason\"` appears on the second to last message chunk.\n",
+    ":::\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "07f0c872-6b6c-4fed-a129-9b5a858505be",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "content='' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
+      "content='Hello' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
+      "content='!' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
+      "content=' How' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
+      "content=' can' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
+      "content=' I' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
+      "content=' assist' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
+      "content=' you' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
+      "content=' today' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
+      "content='?' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
+      "content='' response_metadata={'finish_reason': 'stop'} id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
+      "content='' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf' usage_metadata={'input_tokens': 8, 'output_tokens': 9, 'total_tokens': 17}\n"
+     ]
+    }
+   ],
+   "source": [
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\")\n",
+    "\n",
+    "aggregate = None\n",
+    "for chunk in llm.stream(\"hello\", stream_options={\"include_usage\": True}):\n",
+    "    print(chunk)\n",
+    "    aggregate = chunk if aggregate is None else aggregate + chunk"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "dd809ded-8b13-4d5f-be5e-277b79d51802",
+   "metadata": {},
+   "source": [
+    "Note that the usage metadata will be included in the sum of the individual message chunks:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "3db7bc03-a7d4-4704-92ab-f8ba92ef59ae",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Hello! How can I assist you today?\n",
+      "{'input_tokens': 8, 'output_tokens': 9, 'total_tokens': 17}\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(aggregate.content)\n",
+    "print(aggregate.usage_metadata)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7dba63e8-0ed7-4533-8f0f-78e19c38a25c",
+   "metadata": {},
+   "source": [
+    "To disable streaming token counts for OpenAI, set `\"include_usage\"` to False in `stream_options`, or omit it from the parameters:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "67117f2b-ce68-4c1e-9556-2d3849f90e1b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "content='' id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n",
+      "content='Hello' id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n",
+      "content='!' id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n",
+      "content=' How' id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n",
+      "content=' can' id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n",
+      "content=' I' id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n",
+      "content=' assist' id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n",
+      "content=' you' id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n",
+      "content=' today' id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n",
+      "content='?' id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n",
+      "content='' response_metadata={'finish_reason': 'stop'} id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n"
+     ]
+    }
+   ],
+   "source": [
+    "aggregate = None\n",
+    "for chunk in llm.stream(\"hello\"):\n",
+    "    print(chunk)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6a5d9617-be3a-419a-9276-de9c29fa50ae",
+   "metadata": {},
+   "source": [
+    "You can also enable streaming token usage by setting `model_kwargs` when instantiating the chat model. This can be useful when incorporating chat models into LangChain [chains](/docs/concepts#langchain-expression-language-lcel): usage metadata can be monitored when [streaming intermediate steps](/docs/how_to/streaming#using-stream-events) or using tracing software such as [LangSmith](https://docs.smith.langchain.com/).\n",
+    "\n",
+    "See the below example, where we return output structured to a desired schema, but can still observe token usage streamed from intermediate steps."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "57dec1fb-bd9c-4c98-8798-8fbbe67f6b2c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Token usage: {'input_tokens': 79, 'output_tokens': 23, 'total_tokens': 102}\n",
+      "\n",
+      "setup='Why was the math book sad?' punchline='Because it had too many problems.'\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
+    "\n",
+    "\n",
+    "class Joke(BaseModel):\n",
+    "    \"\"\"Joke to tell user.\"\"\"\n",
+    "\n",
+    "    setup: str = Field(description=\"question to set up a joke\")\n",
+    "    punchline: str = Field(description=\"answer to resolve the joke\")\n",
+    "\n",
+    "\n",
+    "llm = ChatOpenAI(\n",
+    "    model=\"gpt-3.5-turbo-0125\",\n",
+    "    model_kwargs={\"stream_options\": {\"include_usage\": True}},\n",
+    ")\n",
+    "# Under the hood, .with_structured_output binds tools to the\n",
+    "# chat model and appends a parser.\n",
+    "structured_llm = llm.with_structured_output(Joke)\n",
+    "\n",
+    "async for event in structured_llm.astream_events(\"Tell me a joke\", version=\"v2\"):\n",
+    "    if event[\"event\"] == \"on_chat_model_end\":\n",
+    "        print(f'Token usage: {event[\"data\"][\"output\"].usage_metadata}\\n')\n",
+    "    elif event[\"event\"] == \"on_chain_end\":\n",
+    "        print(event[\"data\"][\"output\"])\n",
+    "    else:\n",
+    "        pass"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2bc8d313-4bef-463e-89a5-236d8bb6ab2f",
+   "metadata": {},
+   "source": [
+    "Token usage is also visible in the corresponding [LangSmith trace](https://smith.langchain.com/public/fe6513d5-7212-4045-82e0-fefa28bc7656/r) in the payload from the chat model."
    ]
   },
   {
@@ -115,7 +340,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 9,
    "id": "31667d54",
    "metadata": {},
    "outputs": [
@@ -123,11 +348,11 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Tokens Used: 26\n",
+      "Tokens Used: 27\n",
       "\tPrompt Tokens: 11\n",
-      "\tCompletion Tokens: 15\n",
+      "\tCompletion Tokens: 16\n",
       "Successful Requests: 1\n",
-      "Total Cost (USD): $0.00056\n"
+      "Total Cost (USD): $2.95e-05\n"
      ]
     }
    ],
@@ -136,7 +361,7 @@
     "\n",
     "from langchain_community.callbacks.manager import get_openai_callback\n",
     "\n",
-    "llm = ChatOpenAI(model=\"gpt-4-turbo\", temperature=0)\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n",
     "\n",
     "with get_openai_callback() as cb:\n",
     "    result = llm.invoke(\"Tell me a joke\")\n",
@@ -153,7 +378,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 10,
    "id": "e09420f4",
    "metadata": {},
    "outputs": [
@@ -161,7 +386,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "52\n"
+      "55\n"
      ]
     }
    ],
@@ -172,6 +397,39 @@
     "    print(cb.total_tokens)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "9ac51188-c8f4-4230-90fd-3cd78cdd955d",
+   "metadata": {},
+   "source": [
+    "```{=mdx}\n",
+    ":::note\n",
+    "Cost information is currently not available in streaming mode. This is because model names are currently not propagated through chunks in streaming mode, and the model name is used to look up the correct pricing. Token counts however are available:\n",
+    ":::\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "b241069a-265d-4497-af34-b0a5f95ae67f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "28\n"
+     ]
+    }
+   ],
+   "source": [
+    "with get_openai_callback() as cb:\n",
+    "    for chunk in llm.stream(\"Tell me a joke\", stream_options={\"include_usage\": True}):\n",
+    "        pass\n",
+    "    print(cb.total_tokens)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "d8186e7b",
@@ -182,7 +440,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 12,
    "id": "5d1125c6",
    "metadata": {},
    "outputs": [],
@@ -211,15 +469,15 @@
    "source": [
     "```{=mdx}\n",
     ":::note\n",
-    "We have to set `stream_runnable=False` for token counting to work. By default the AgentExecutor will stream the underlying agent so that you can get the most granular results when streaming events via AgentExecutor.stream_events. However, OpenAI does not return token counts when streaming model responses, so we need to turn off the underlying streaming.\n",
+    "We have to set `stream_runnable=False` for cost information, as described above. By default the AgentExecutor will stream the underlying agent so that you can get the most granular results when streaming events via AgentExecutor.stream_events.\n",
     ":::\n",
     "```"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
-   "id": "2f98c536",
+   "execution_count": 13,
+   "id": "3950d88b-8bfb-4294-b75b-e6fd421e633c",
    "metadata": {},
    "outputs": [
     {
@@ -230,46 +488,51 @@
       "\n",
       "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
       "\u001b[32;1m\u001b[1;3m\n",
-      "Invoking: `wikipedia` with `Hummingbird`\n",
+      "Invoking: `wikipedia` with `{'query': 'hummingbird scientific name'}`\n",
       "\n",
       "\n",
       "\u001b[0m\u001b[36;1m\u001b[1;3mPage: Hummingbird\n",
-      "Summary: Hummingbirds are birds native to the Americas and comprise the biological family Trochilidae. With approximately 366 species and 113 genera, they occur from Alaska to Tierra del Fuego, but most species are found in Central and South America. As of 2024, 21 hummingbird species are listed as endangered or critically endangered, with numerous species declining in population.Hummingbirds have varied specialized characteristics to enable rapid, maneuverable flight: exceptional metabolic capacity, adaptations to high altitude, sensitive visual and communication abilities, and long-distance migration in some species. Among all birds, male hummingbirds have the widest diversity of plumage color, particularly in blues, greens, and purples. Hummingbirds are the smallest mature birds, measuring 7.5–13 cm (3–5 in) in length. The smallest is the 5 cm (2.0 in) bee hummingbird, which weighs less than 2.0 g (0.07 oz), and the largest is the 23 cm (9 in) giant hummingbird, weighing 18–24 grams (0.63–0.85 oz). Noted for long beaks, hummingbirds are specialized for feeding on flower nectar, but all species also consume small insects.\n",
+      "Summary: Hummingbirds are birds native to the Americas and comprise the biological family Trochilidae. With approximately 366 species and 113 genera, they occur from Alaska to Tierra del Fuego, but most species are found in Central and South America. As of 2024, 21 hummingbird species are listed as endangered or critically endangered, with numerous species declining in population.\n",
+      "Hummingbirds have varied specialized characteristics to enable rapid, maneuverable flight: exceptional metabolic capacity, adaptations to high altitude, sensitive visual and communication abilities, and long-distance migration in some species. Among all birds, male hummingbirds have the widest diversity of plumage color, particularly in blues, greens, and purples. Hummingbirds are the smallest mature birds, measuring 7.5–13 cm (3–5 in) in length. The smallest is the 5 cm (2.0 in) bee hummingbird, which weighs less than 2.0 g (0.07 oz), and the largest is the 23 cm (9 in) giant hummingbird, weighing 18–24 grams (0.63–0.85 oz). Noted for long beaks, hummingbirds are specialized for feeding on flower nectar, but all species also consume small insects.\n",
       "They are known as hummingbirds because of the humming sound created by their beating wings, which flap at high frequencies audible to other birds and humans. They hover at rapid wing-flapping rates, which vary from around 12 beats per second in the largest species to 80 per second in small hummingbirds.\n",
       "Hummingbirds have the highest mass-specific metabolic rate of any homeothermic animal. To conserve energy when food is scarce and at night when not foraging, they can enter torpor, a state similar to hibernation, and slow their metabolic rate to 1⁄15 of its normal rate. While most hummingbirds do not migrate, the rufous hummingbird has one of the longest migrations among birds, traveling twice per year between Alaska and Mexico, a distance of about 3,900 miles (6,300 km).\n",
       "Hummingbirds split from their sister group, the swifts and treeswifts, around 42 million years ago. The oldest known fossil hummingbird is Eurotrochilus, from the Rupelian Stage of Early Oligocene Europe.\n",
       "\n",
+      "Page: Rufous hummingbird\n",
+      "Summary: The rufous hummingbird (Selasphorus rufus) is a small hummingbird, about 8 cm (3.1 in) long with a long, straight and slender bill. These birds are known for their extraordinary flight skills, flying 2,000 mi (3,200 km) during their migratory transits. It is one of nine species in the genus Selasphorus.\n",
       "\n",
       "\n",
-      "Page: Bee hummingbird\n",
-      "Summary: The bee hummingbird, zunzuncito or Helena hummingbird (Mellisuga helenae) is a species of hummingbird, native to the island of Cuba in the Caribbean. It is the smallest known bird. The bee hummingbird feeds on nectar of flowers and bugs found in Cuba.\n",
       "\n",
-      "Page: Hummingbird cake\n",
-      "Summary: Hummingbird cake is a banana-pineapple spice cake originating in Jamaica and a popular dessert in the southern United States since the 1970s. Ingredients include flour, sugar, salt, vegetable oil, ripe banana, pineapple, cinnamon, pecans, vanilla extract, eggs, and leavening agent. It is often served with cream cheese frosting.\u001b[0m\u001b[32;1m\u001b[1;3m\n",
-      "Invoking: `wikipedia` with `Fastest bird`\n",
+      "Page: Anna's hummingbird\n",
+      "Summary: Anna's hummingbird (Calypte anna) is a North American species of hummingbird. It was named after Anna Masséna, Duchess of Rivoli.\n",
+      "It is native to western coastal regions of North America. In the early 20th century, Anna's hummingbirds bred only in northern Baja California and Southern California. The transplanting of exotic ornamental plants in residential areas throughout the Pacific coast and inland deserts provided expanded nectar and nesting sites, allowing the species to expand its breeding range. Year-round residence of Anna's hummingbirds in the Pacific Northwest is an example of ecological release dependent on acclimation to colder winter temperatures, introduced plants, and human provision of nectar feeders during winter.\n",
+      "These birds feed on nectar from flowers using a long extendable tongue. They also consume small insects and other arthropods caught in flight or gleaned from vegetation.\u001b[0m\u001b[32;1m\u001b[1;3m\n",
+      "Invoking: `wikipedia` with `{'query': 'fastest bird species'}`\n",
       "\n",
       "\n",
-      "\u001b[0m\u001b[36;1m\u001b[1;3mPage: Fastest animals\n",
+      "\u001b[0m\u001b[36;1m\u001b[1;3mPage: List of birds by flight speed\n",
+      "Summary: This is a list of the fastest flying birds in the world. A bird's velocity is necessarily variable; a hunting bird will reach much greater speeds while diving to catch prey than when flying horizontally. The bird that can achieve the greatest airspeed is the peregrine falcon (Falco peregrinus), able to exceed 320 km/h (200 mph) in its dives. A close relative of the common swift, the white-throated needletail (Hirundapus caudacutus), is commonly reported as the fastest bird in level flight with a reported top speed of 169 km/h (105 mph). This record remains unconfirmed as the measurement methods have never been published or verified. The record for the fastest confirmed level flight by a bird is 111.5 km/h (69.3 mph) held by the common swift.\n",
+      "\n",
+      "\n",
+      "\n",
+      "Page: Fastest animals\n",
       "Summary: This is a list of the fastest animals in the world, by types of animal.\n",
       "\n",
       "\n",
       "\n",
-      "Page: List of birds by flight speed\n",
-      "Summary: This is a list of the fastest flying birds in the world. A bird's velocity is necessarily variable; a hunting bird will reach much greater speeds while diving to catch prey than when flying horizontally. The bird that can achieve the greatest airspeed is the peregrine falcon, able to exceed 320 km/h (200 mph) in its dives. A close relative of the common swift, the white-throated needletail (Hirundapus caudacutus), is commonly reported as the fastest bird in level flight with a reported top speed of 169 km/h (105 mph). This record remains unconfirmed as the measurement methods have never been published or verified. The record for the fastest confirmed level flight by a bird is 111.5 km/h (69.3 mph) held by the common swift.\n",
-      "\n",
-      "Page: Ostrich\n",
-      "Summary: Ostriches are large flightless birds. They are the heaviest and largest living birds, with adult common ostriches weighing anywhere between 63.5 and 145 kilograms and laying the largest eggs of any living land animal. With the ability to run at 70 km/h (43.5 mph), they are the fastest birds on land. They are farmed worldwide, with significant industries in the Philippines and in Namibia. Ostrich leather is a lucrative commodity, and the large feathers are used as plumes for the decoration of ceremonial headgear. Ostrich eggs have been used by humans for millennia.\n",
-      "Ostriches are of the genus Struthio in the order Struthioniformes, part of the infra-class Palaeognathae, a diverse group of flightless birds also known as ratites that includes the emus, rheas, cassowaries, kiwis and the extinct elephant birds and moas. There are two living species of ostrich: the common ostrich, native to large areas of sub-Saharan Africa, and the Somali ostrich, native to the Horn of Africa.  The common ostrich was historically native to the Arabian Peninsula, and ostriches were present across Asia as far east as China and Mongolia during the Late Pleistocene and possibly into the Holocene.\u001b[0m\u001b[32;1m\u001b[1;3m### Hummingbird's Scientific Name\n",
-      "The scientific name for the bee hummingbird, which is the smallest known bird and a species of hummingbird, is **Mellisuga helenae**. It is native to Cuba.\n",
-      "\n",
-      "### Fastest Bird Species\n",
-      "The fastest bird in terms of airspeed is the **peregrine falcon**, which can exceed speeds of 320 km/h (200 mph) during its diving flight. In level flight, the fastest confirmed speed is held by the **common swift**, which can fly at 111.5 km/h (69.3 mph).\u001b[0m\n",
+      "Page: Falcon\n",
+      "Summary: Falcons () are birds of prey in the genus Falco, which includes about 40 species. Falcons are widely distributed on all continents of the world except Antarctica, though closely related raptors did occur there in the Eocene.\n",
+      "Adult falcons have thin, tapered wings, which enable them to fly at high speed and change direction rapidly. Fledgling falcons, in their first year of flying, have longer flight feathers, which make their configuration more like that of a general-purpose bird such as a broad wing. This makes flying easier while learning the exceptional skills required to be effective hunters as adults.\n",
+      "The falcons are the largest genus in the Falconinae subfamily of Falconidae, which itself also includes another subfamily comprising caracaras and a few other species. All these birds kill with their beaks, using a tomial \"tooth\" on the side of their beaks—unlike the hawks, eagles, and other birds of prey in the Accipitridae, which use their feet.\n",
+      "The largest falcon is the gyrfalcon at up to 65 cm in length.  The smallest falcon species is the pygmy falcon, which measures just 20 cm.  As with hawks and owls, falcons exhibit sexual dimorphism, with the females typically larger than the males, thus allowing a wider range of prey species.\n",
+      "Some small falcons with long, narrow wings are called \"hobbies\" and some which hover while hunting are called \"kestrels\".\n",
+      "As is the case with many birds of prey, falcons have exceptional powers of vision; the visual acuity of one species has been measured at 2.6 times that of a normal human. Peregrine falcons have been recorded diving at speeds of 320 km/h (200 mph), making them the fastest-moving creatures on Earth; the fastest recorded dive attained a vertical speed of 390 km/h (240 mph).\u001b[0m\u001b[32;1m\u001b[1;3mThe scientific name for a hummingbird is Trochilidae. The fastest bird species is the peregrine falcon (Falco peregrinus), which can exceed speeds of 320 km/h (200 mph) in its dives.\u001b[0m\n",
       "\n",
       "\u001b[1m> Finished chain.\u001b[0m\n",
-      "Total Tokens: 1583\n",
-      "Prompt Tokens: 1412\n",
-      "Completion Tokens: 171\n",
-      "Total Cost (USD): $0.019250000000000003\n"
+      "Total Tokens: 1787\n",
+      "Prompt Tokens: 1687\n",
+      "Completion Tokens: 100\n",
+      "Total Cost (USD): $0.0009935\n"
      ]
     }
    ],
@@ -298,19 +561,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
-   "id": "4a3eced5-2ff7-49a7-a48b-768af8658323",
+   "execution_count": 12,
+   "id": "1837c807-136a-49d8-9c33-060e58dc16d2",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Tokens Used: 0\n",
-      "\tPrompt Tokens: 0\n",
-      "\tCompletion Tokens: 0\n",
+      "Tokens Used: 96\n",
+      "\tPrompt Tokens: 26\n",
+      "\tCompletion Tokens: 70\n",
       "Successful Requests: 2\n",
-      "Total Cost (USD): $0.0\n"
+      "Total Cost (USD): $0.001888\n"
      ]
     }
    ],
@@ -364,7 +627,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/how_to/chatbots_memory.ipynb

@@ -71,13 +71,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "chat = ChatOpenAI(model=\"gpt-3.5-turbo-1106\")"
+    "chat = ChatOpenAI(model=\"gpt-3.5-turbo-0125\")"
    ]
   },
   {
@@ -95,19 +95,15 @@
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='I said \"J\\'adore la programmation,\" which means \"I love programming\" in French.')"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "I said \"J'adore la programmation,\" which means \"I love programming\" in French.\n"
+     ]
     }
    ],
    "source": [
-    "from langchain_core.messages import AIMessage, HumanMessage\n",
-    "from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
     "\n",
     "prompt = ChatPromptTemplate.from_messages(\n",
     "    [\n",
@@ -115,23 +111,25 @@
     "            \"system\",\n",
     "            \"You are a helpful assistant. Answer all questions to the best of your ability.\",\n",
     "        ),\n",
-    "        MessagesPlaceholder(variable_name=\"messages\"),\n",
+    "        (\"placeholder\", \"{messages}\"),\n",
     "    ]\n",
     ")\n",
     "\n",
     "chain = prompt | chat\n",
     "\n",
-    "chain.invoke(\n",
+    "ai_msg = chain.invoke(\n",
     "    {\n",
     "        \"messages\": [\n",
-    "            HumanMessage(\n",
-    "                content=\"Translate this sentence from English to French: I love programming.\"\n",
+    "            (\n",
+    "                \"human\",\n",
+    "                \"Translate this sentence from English to French: I love programming.\",\n",
     "            ),\n",
-    "            AIMessage(content=\"J'adore la programmation.\"),\n",
-    "            HumanMessage(content=\"What did you just say?\"),\n",
+    "            (\"ai\", \"J'adore la programmation.\"),\n",
+    "            (\"human\", \"What did you just say?\"),\n",
     "        ],\n",
     "    }\n",
-    ")"
+    ")\n",
+    "print(ai_msg.content)"
    ]
   },
   {
@@ -193,7 +191,7 @@
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='You asked me to translate the sentence \"I love programming\" from English to French.')"
+       "AIMessage(content='You just asked me to translate the sentence \"I love programming\" from English to French.', response_metadata={'token_usage': {'completion_tokens': 18, 'prompt_tokens': 61, 'total_tokens': 79}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-5cbb21c2-9c30-4031-8ea8-bfc497989535-0', usage_metadata={'input_tokens': 61, 'output_tokens': 18, 'total_tokens': 79})"
       ]
      },
      "execution_count": 5,
@@ -250,7 +248,7 @@
     "            \"system\",\n",
     "            \"You are a helpful assistant. Answer all questions to the best of your ability.\",\n",
     "        ),\n",
-    "        MessagesPlaceholder(variable_name=\"chat_history\"),\n",
+    "        (\"placeholder\", \"{chat_history}\"),\n",
     "        (\"human\", \"{input}\"),\n",
     "    ]\n",
     ")\n",
@@ -304,10 +302,17 @@
    "execution_count": 8,
    "metadata": {},
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Parent run dc4e2f79-4bcd-4a36-9506-55ace9040588 not found for run 34b5773e-3ced-46a6-8daf-4d464c15c940. Treating as a root run.\n"
+     ]
+    },
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='The translation of \"I love programming\" in French is \"J\\'adore la programmation.\"')"
+       "AIMessage(content='\"J\\'adore la programmation.\"', response_metadata={'token_usage': {'completion_tokens': 9, 'prompt_tokens': 39, 'total_tokens': 48}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-648b0822-b0bb-47a2-8e7d-7d34744be8f2-0', usage_metadata={'input_tokens': 39, 'output_tokens': 9, 'total_tokens': 48})"
       ]
      },
      "execution_count": 8,
@@ -327,10 +332,17 @@
    "execution_count": 9,
    "metadata": {},
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Parent run cc14b9d8-c59e-40db-a523-d6ab3fc2fa4f not found for run 5b75e25c-131e-46ee-9982-68569db04330. Treating as a root run.\n"
+     ]
+    },
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='You just asked me to translate the sentence \"I love programming\" from English to French.')"
+       "AIMessage(content='You asked me to translate the sentence \"I love programming\" from English to French.', response_metadata={'token_usage': {'completion_tokens': 17, 'prompt_tokens': 63, 'total_tokens': 80}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-5950435c-1dc2-43a6-836f-f989fd62c95e-0', usage_metadata={'input_tokens': 63, 'output_tokens': 17, 'total_tokens': 80})"
       ]
      },
      "execution_count": 9,
@@ -354,12 +366,12 @@
     "\n",
     "### Trimming messages\n",
     "\n",
-    "LLMs and chat models have limited context windows, and even if you're not directly hitting limits, you may want to limit the amount of distraction the model has to deal with. One solution is to only load and store the most recent `n` messages. Let's use an example history with some preloaded messages:"
+    "LLMs and chat models have limited context windows, and even if you're not directly hitting limits, you may want to limit the amount of distraction the model has to deal with. One solution is trim the historic messages before passing them to the model. Let's use an example history with some preloaded messages:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [
     {
@@ -371,7 +383,7 @@
        " AIMessage(content='Fine thanks!')]"
       ]
      },
-     "execution_count": 10,
+     "execution_count": 21,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -396,34 +408,28 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 22,
    "metadata": {},
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Parent run 7ff2d8ec-65e2-4f67-8961-e498e2c4a591 not found for run 3881e990-6596-4326-84f6-2b76949e0657. Treating as a root run.\n"
+     ]
+    },
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='Your name is Nemo.')"
+       "AIMessage(content='Your name is Nemo.', response_metadata={'token_usage': {'completion_tokens': 6, 'prompt_tokens': 66, 'total_tokens': 72}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-f8aabef8-631a-4238-a39b-701e881fbe47-0', usage_metadata={'input_tokens': 66, 'output_tokens': 6, 'total_tokens': 72})"
       ]
      },
-     "execution_count": 11,
+     "execution_count": 22,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\n",
-    "            \"system\",\n",
-    "            \"You are a helpful assistant. Answer all questions to the best of your ability.\",\n",
-    "        ),\n",
-    "        MessagesPlaceholder(variable_name=\"chat_history\"),\n",
-    "        (\"human\", \"{input}\"),\n",
-    "    ]\n",
-    ")\n",
-    "\n",
-    "chain = prompt | chat\n",
-    "\n",
     "chain_with_message_history = RunnableWithMessageHistory(\n",
     "    chain,\n",
     "    lambda session_id: demo_ephemeral_chat_history,\n",
@@ -443,34 +449,33 @@
    "source": [
     "We can see the chain remembers the preloaded name.\n",
     "\n",
-    "But let's say we have a very small context window, and we want to trim the number of messages passed to the chain to only the 2 most recent ones. We can use the `clear` method to remove messages and re-add them to the history. We don't have to, but let's put this method at the front of our chain to ensure it's always called:"
+    "But let's say we have a very small context window, and we want to trim the number of messages passed to the chain to only the 2 most recent ones. We can use the built in [trim_messages](/docs/how_to/trim_messages/) util to trim messages based on their token count before they reach our prompt. In this case we'll count each message as 1 \"token\" and keep only the last two messages:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [],
    "source": [
+    "from operator import itemgetter\n",
+    "\n",
+    "from langchain_core.messages import trim_messages\n",
     "from langchain_core.runnables import RunnablePassthrough\n",
     "\n",
-    "\n",
-    "def trim_messages(chain_input):\n",
-    "    stored_messages = demo_ephemeral_chat_history.messages\n",
-    "    if len(stored_messages) <= 2:\n",
-    "        return False\n",
-    "\n",
-    "    demo_ephemeral_chat_history.clear()\n",
-    "\n",
-    "    for message in stored_messages[-2:]:\n",
-    "        demo_ephemeral_chat_history.add_message(message)\n",
-    "\n",
-    "    return True\n",
-    "\n",
+    "trimmer = trim_messages(strategy=\"last\", max_tokens=2, token_counter=len)\n",
     "\n",
     "chain_with_trimming = (\n",
-    "    RunnablePassthrough.assign(messages_trimmed=trim_messages)\n",
-    "    | chain_with_message_history\n",
+    "    RunnablePassthrough.assign(chat_history=itemgetter(\"chat_history\") | trimmer)\n",
+    "    | prompt\n",
+    "    | chat\n",
+    ")\n",
+    "\n",
+    "chain_with_trimmed_history = RunnableWithMessageHistory(\n",
+    "    chain_with_trimming,\n",
+    "    lambda session_id: demo_ephemeral_chat_history,\n",
+    "    input_messages_key=\"input\",\n",
+    "    history_messages_key=\"chat_history\",\n",
     ")"
    ]
   },
@@ -483,22 +488,29 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 24,
    "metadata": {},
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Parent run 775cde65-8d22-4c44-80bb-f0b9811c32ca not found for run 5cf71d0e-4663-41cd-8dbe-e9752689cfac. Treating as a root run.\n"
+     ]
+    },
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"P. Sherman's address is 42 Wallaby Way, Sydney.\")"
+       "AIMessage(content='P. Sherman is a fictional character from the animated movie \"Finding Nemo\" who lives at 42 Wallaby Way, Sydney.', response_metadata={'token_usage': {'completion_tokens': 27, 'prompt_tokens': 53, 'total_tokens': 80}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-5642ef3a-fdbe-43cf-a575-d1785976a1b9-0', usage_metadata={'input_tokens': 53, 'output_tokens': 27, 'total_tokens': 80})"
       ]
      },
-     "execution_count": 13,
+     "execution_count": 24,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "chain_with_trimming.invoke(\n",
+    "chain_with_trimmed_history.invoke(\n",
     "    {\"input\": \"Where does P. Sherman live?\"},\n",
     "    {\"configurable\": {\"session_id\": \"unused\"}},\n",
     ")"
@@ -506,19 +518,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 25,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[HumanMessage(content=\"What's my name?\"),\n",
-       " AIMessage(content='Your name is Nemo.'),\n",
+       "[HumanMessage(content=\"Hey there! I'm Nemo.\"),\n",
+       " AIMessage(content='Hello!'),\n",
+       " HumanMessage(content='How are you today?'),\n",
+       " AIMessage(content='Fine thanks!'),\n",
+       " HumanMessage(content=\"What's my name?\"),\n",
+       " AIMessage(content='Your name is Nemo.', response_metadata={'token_usage': {'completion_tokens': 6, 'prompt_tokens': 66, 'total_tokens': 72}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-f8aabef8-631a-4238-a39b-701e881fbe47-0', usage_metadata={'input_tokens': 66, 'output_tokens': 6, 'total_tokens': 72}),\n",
        " HumanMessage(content='Where does P. Sherman live?'),\n",
-       " AIMessage(content=\"P. Sherman's address is 42 Wallaby Way, Sydney.\")]"
+       " AIMessage(content='P. Sherman is a fictional character from the animated movie \"Finding Nemo\" who lives at 42 Wallaby Way, Sydney.', response_metadata={'token_usage': {'completion_tokens': 27, 'prompt_tokens': 53, 'total_tokens': 80}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-5642ef3a-fdbe-43cf-a575-d1785976a1b9-0', usage_metadata={'input_tokens': 53, 'output_tokens': 27, 'total_tokens': 80})]"
       ]
      },
-     "execution_count": 14,
+     "execution_count": 25,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -536,48 +552,39 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 27,
    "metadata": {},
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Parent run fde7123f-6fd3-421a-a3fc-2fb37dead119 not found for run 061a4563-2394-470d-a3ed-9bf1388ca431. Treating as a root run.\n"
+     ]
+    },
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"I'm sorry, I don't have access to your personal information.\")"
+       "AIMessage(content=\"I'm sorry, but I don't have access to your personal information, so I don't know your name. How else may I assist you today?\", response_metadata={'token_usage': {'completion_tokens': 31, 'prompt_tokens': 74, 'total_tokens': 105}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-0ab03495-1f7c-4151-9070-56d2d1c565ff-0', usage_metadata={'input_tokens': 74, 'output_tokens': 31, 'total_tokens': 105})"
       ]
      },
-     "execution_count": 15,
+     "execution_count": 27,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "chain_with_trimming.invoke(\n",
+    "chain_with_trimmed_history.invoke(\n",
     "    {\"input\": \"What is my name?\"},\n",
     "    {\"configurable\": {\"session_id\": \"unused\"}},\n",
     ")"
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 16,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[HumanMessage(content='Where does P. Sherman live?'),\n",
-       " AIMessage(content=\"P. Sherman's address is 42 Wallaby Way, Sydney.\"),\n",
-       " HumanMessage(content='What is my name?'),\n",
-       " AIMessage(content=\"I'm sorry, I don't have access to your personal information.\")]"
-      ]
-     },
-     "execution_count": 16,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
    "source": [
-    "demo_ephemeral_chat_history.messages"
+    "Check out our [how to guide on trimming messages](/docs/how_to/trim_messages/) for more."
    ]
   },
   {
@@ -638,7 +645,7 @@
     "            \"system\",\n",
     "            \"You are a helpful assistant. Answer all questions to the best of your ability. The provided chat history includes facts about the user you are speaking with.\",\n",
     "        ),\n",
-    "        MessagesPlaceholder(variable_name=\"chat_history\"),\n",
+    "        (\"placeholder\", \"{chat_history}\"),\n",
     "        (\"user\", \"{input}\"),\n",
     "    ]\n",
     ")\n",
@@ -672,7 +679,7 @@
     "        return False\n",
     "    summarization_prompt = ChatPromptTemplate.from_messages(\n",
     "        [\n",
-    "            MessagesPlaceholder(variable_name=\"chat_history\"),\n",
+    "            (\"placeholder\", \"{chat_history}\"),\n",
     "            (\n",
     "                \"user\",\n",
     "                \"Distill the above chat messages into a single summary message. Include as many specific details as you can.\",\n",
@@ -772,9 +779,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.1"
+   "version": "3.11.9"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

docs/docs/how_to/document_loader_pdf.ipynb

@@ -69,6 +69,17 @@
     "Once we have loaded PDFs into LangChain `Document` objects, we can index them (e.g., a RAG application) in the usual way:"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c3b932bb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install faiss-cpu \n",
+    "# use `pip install faiss-gpu` for CUDA GPU support"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,

docs/docs/how_to/dynamic_chain.ipynb

@@ -1,15 +1,5 @@
 {
  "cells": [
-  {
-   "cell_type": "raw",
-   "id": "77bf57fb-e990-45f2-8b5f-c76388b05966",
-   "metadata": {},
-   "source": [
-    "---\n",
-    "keywords: [LCEL]\n",
-    "---"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "50d57bf2-7104-4570-b3e5-90fd71e1bea1",

docs/docs/how_to/ensemble_retriever.ipynb

@@ -4,13 +4,17 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# How to create an Ensemble Retriever\n",
+    "# How to combine results from multiple retrievers\n",
     "\n",
-    "The `EnsembleRetriever` takes a list of retrievers as input and ensemble the results of their `get_relevant_documents()` methods and rerank the results based on the [Reciprocal Rank Fusion](https://plg.uwaterloo.ca/~gvcormac/cormacksigir09-rrf.pdf) algorithm.\n",
+    "The [EnsembleRetriever](https://api.python.langchain.com/en/latest/retrievers/langchain.retrievers.ensemble.EnsembleRetriever.html) supports ensembling of results from multiple retrievers. It is initialized with a list of [BaseRetriever](https://api.python.langchain.com/en/latest/retrievers/langchain_core.retrievers.BaseRetriever.html) objects. EnsembleRetrievers rerank the results of the constituent retrievers based on the [Reciprocal Rank Fusion](https://plg.uwaterloo.ca/~gvcormac/cormacksigir09-rrf.pdf) algorithm.\n",
     "\n",
     "By leveraging the strengths of different algorithms, the `EnsembleRetriever` can achieve better performance than any single algorithm. \n",
     "\n",
-    "The most common pattern is to combine a sparse retriever (like BM25) with a dense retriever (like embedding similarity), because their strengths are complementary. It is also known as \"hybrid search\". The sparse retriever is good at finding relevant documents based on keywords, while the dense retriever is good at finding relevant documents based on semantic similarity."
+    "The most common pattern is to combine a sparse retriever (like BM25) with a dense retriever (like embedding similarity), because their strengths are complementary. It is also known as \"hybrid search\". The sparse retriever is good at finding relevant documents based on keywords, while the dense retriever is good at finding relevant documents based on semantic similarity.\n",
+    "\n",
+    "## Basic usage\n",
+    "\n",
+    "Below we demonstrate ensembling of a [BM25Retriever](https://api.python.langchain.com/en/latest/retrievers/langchain_community.retrievers.bm25.BM25Retriever.html) with a retriever derived from the [FAISS vector store](https://api.python.langchain.com/en/latest/vectorstores/langchain_community.vectorstores.faiss.FAISS.html)."
    ]
   },
   {
@@ -24,22 +28,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
     "from langchain.retrievers import EnsembleRetriever\n",
     "from langchain_community.retrievers import BM25Retriever\n",
     "from langchain_community.vectorstores import FAISS\n",
-    "from langchain_openai import OpenAIEmbeddings"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "metadata": {},
-   "outputs": [],
-   "source": [
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "\n",
     "doc_list_1 = [\n",
     "    \"I like apples\",\n",
     "    \"I like oranges\",\n",
@@ -71,19 +68,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[Document(page_content='You like apples', metadata={'source': 2}),\n",
-       " Document(page_content='I like apples', metadata={'source': 1}),\n",
-       " Document(page_content='You like oranges', metadata={'source': 2}),\n",
-       " Document(page_content='Apples and oranges are fruits', metadata={'source': 1})]"
+       "[Document(page_content='I like apples', metadata={'source': 1}),\n",
+       " Document(page_content='You like apples', metadata={'source': 2}),\n",
+       " Document(page_content='Apples and oranges are fruits', metadata={'source': 1}),\n",
+       " Document(page_content='You like oranges', metadata={'source': 2})]"
       ]
      },
-     "execution_count": 15,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -99,24 +96,17 @@
    "source": [
     "## Runtime Configuration\n",
     "\n",
-    "We can also configure the retrievers at runtime. In order to do this, we need to mark the fields as configurable"
+    "We can also configure the individual retrievers at runtime using [configurable fields](/docs/how_to/configure). Below we update the \"top-k\" parameter for the FAISS retriever specifically:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.runnables import ConfigurableField"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
+    "from langchain_core.runnables import ConfigurableField\n",
+    "\n",
     "faiss_retriever = faiss_vectorstore.as_retriever(\n",
     "    search_kwargs={\"k\": 2}\n",
     ").configurable_fields(\n",
@@ -125,15 +115,8 @@
     "        name=\"Search Kwargs\",\n",
     "        description=\"The search kwargs to use\",\n",
     "    )\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "metadata": {},
-   "outputs": [],
-   "source": [
+    ")\n",
+    "\n",
     "ensemble_retriever = EnsembleRetriever(\n",
     "    retrievers=[bm25_retriever, faiss_retriever], weights=[0.5, 0.5]\n",
     ")"
@@ -141,9 +124,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 6,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='I like apples', metadata={'source': 1}),\n",
+       " Document(page_content='You like apples', metadata={'source': 2}),\n",
+       " Document(page_content='Apples and oranges are fruits', metadata={'source': 1})]"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "config = {\"configurable\": {\"search_kwargs_faiss\": {\"k\": 1}}}\n",
     "docs = ensemble_retriever.invoke(\"apples\", config=config)\n",
@@ -181,7 +177,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.1"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/how_to/example_selectors.ipynb

@@ -60,7 +60,7 @@
    "source": [
     "examples = [\n",
     "    {\"input\": \"hi\", \"output\": \"ciao\"},\n",
-    "    {\"input\": \"bye\", \"output\": \"arrivaderci\"},\n",
+    "    {\"input\": \"bye\", \"output\": \"arrivederci\"},\n",
     "    {\"input\": \"soccer\", \"output\": \"calcio\"},\n",
     "]"
    ]
@@ -133,7 +133,7 @@
     {
      "data": {
       "text/plain": [
-       "[{'input': 'bye', 'output': 'arrivaderci'}]"
+       "[{'input': 'bye', 'output': 'arrivederci'}]"
       ]
      },
      "execution_count": 39,
@@ -209,7 +209,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Translate the following words from English to Italain:\n",
+      "Translate the following words from English to Italian:\n",
       "\n",
       "Input: hand -> Output: mano\n",
       "\n",
@@ -222,7 +222,7 @@
     "    example_selector=example_selector,\n",
     "    example_prompt=example_prompt,\n",
     "    suffix=\"Input: {input} -> Output:\",\n",
-    "    prefix=\"Translate the following words from English to Italain:\",\n",
+    "    prefix=\"Translate the following words from English to Italian:\",\n",
     "    input_variables=[\"input\"],\n",
     ")\n",
     "\n",

docs/docs/how_to/extraction_examples.ipynb

@@ -128,7 +128,7 @@
     "    # Having a good description can help improve extraction results.\n",
     "    name: Optional[str] = Field(..., description=\"The name of the person\")\n",
     "    hair_color: Optional[str] = Field(\n",
-    "        ..., description=\"The color of the peron's eyes if known\"\n",
+    "        ..., description=\"The color of the person's hair if known\"\n",
     "    )\n",
     "    height_in_meters: Optional[str] = Field(..., description=\"Height in METERs\")\n",
     "\n",

docs/docs/how_to/filter_messages.ipynb

@@ -0,0 +1,203 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "e389175d-8a65-4f0d-891c-dbdfabb3c3ef",
+   "metadata": {},
+   "source": [
+    "# How to filter messages\n",
+    "\n",
+    "In more complex chains and agents we might track state with a list of messages. This list can start to accumulate messages from multiple different models, speakers, sub-chains, etc., and we may only want to pass subsets of this full list of messages to each model call in the chain/agent.\n",
+    "\n",
+    "The `filter_messages` utility makes it easy to filter messages by type, id, or name.\n",
+    "\n",
+    "## Basic usage"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "f4ad2fd3-3cab-40d4-a989-972115865b8b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[HumanMessage(content='example input', name='example_user', id='2'),\n",
+       " HumanMessage(content='real input', name='bob', id='4')]"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_core.messages import (\n",
+    "    AIMessage,\n",
+    "    HumanMessage,\n",
+    "    SystemMessage,\n",
+    "    filter_messages,\n",
+    ")\n",
+    "\n",
+    "messages = [\n",
+    "    SystemMessage(\"you are a good assistant\", id=\"1\"),\n",
+    "    HumanMessage(\"example input\", id=\"2\", name=\"example_user\"),\n",
+    "    AIMessage(\"example output\", id=\"3\", name=\"example_assistant\"),\n",
+    "    HumanMessage(\"real input\", id=\"4\", name=\"bob\"),\n",
+    "    AIMessage(\"real output\", id=\"5\", name=\"alice\"),\n",
+    "]\n",
+    "\n",
+    "filter_messages(messages, include_types=\"human\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "7b663a1e-a8ae-453e-a072-8dd75dfab460",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[SystemMessage(content='you are a good assistant', id='1'),\n",
+       " HumanMessage(content='real input', name='bob', id='4'),\n",
+       " AIMessage(content='real output', name='alice', id='5')]"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "filter_messages(messages, exclude_names=[\"example_user\", \"example_assistant\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "db170e46-03f8-4710-b967-23c70c3ac054",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[HumanMessage(content='example input', name='example_user', id='2'),\n",
+       " HumanMessage(content='real input', name='bob', id='4'),\n",
+       " AIMessage(content='real output', name='alice', id='5')]"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "filter_messages(messages, include_types=[HumanMessage, AIMessage], exclude_ids=[\"3\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b7c4e5ad-d1b4-4c18-b250-864adde8f0dd",
+   "metadata": {},
+   "source": [
+    "## Chaining\n",
+    "\n",
+    "`filter_messages` can be used in an imperatively (like above) or declaratively, making it easy to compose with other components in a chain:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "675f8f79-db39-401c-a582-1df2478cba30",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=[], response_metadata={'id': 'msg_01Wz7gBHahAwkZ1KCBNtXmwA', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 16, 'output_tokens': 3}}, id='run-b5d8a3fe-004f-4502-a071-a6c025031827-0', usage_metadata={'input_tokens': 16, 'output_tokens': 3, 'total_tokens': 19})"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# pip install -U langchain-anthropic\n",
+    "from langchain_anthropic import ChatAnthropic\n",
+    "\n",
+    "llm = ChatAnthropic(model=\"claude-3-sonnet-20240229\", temperature=0)\n",
+    "# Notice we don't pass in messages. This creates\n",
+    "# a RunnableLambda that takes messages as input\n",
+    "filter_ = filter_messages(exclude_names=[\"example_user\", \"example_assistant\"])\n",
+    "chain = filter_ | llm\n",
+    "chain.invoke(messages)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4133ab28-f49c-480f-be92-b51eb6559153",
+   "metadata": {},
+   "source": [
+    "Looking at the LangSmith trace we can see that before the messages are passed to the model they are filtered: https://smith.langchain.com/public/f808a724-e072-438e-9991-657cc9e7e253/r\n",
+    "\n",
+    "Looking at just the filter_, we can see that it's a Runnable object that can be invoked like all Runnables:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "c090116a-1fef-43f6-a178-7265dff9db00",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[HumanMessage(content='real input', name='bob', id='4'),\n",
+       " AIMessage(content='real output', name='alice', id='5')]"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "filter_.invoke(messages)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ff339066-d424-4042-8cca-cd4b007c1a8e",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For a complete description of all arguments head to the API reference: https://api.python.langchain.com/en/latest/messages/langchain_core.messages.utils.filter_messages.html"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "poetry-venv-2",
+   "language": "python",
+   "name": "poetry-venv-2"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/how_to/functions.ipynb

@@ -300,7 +300,11 @@
    "id": "922b48bd",
    "metadata": {},
    "source": [
-    "# Streaming\n",
+    "## Streaming\n",
+    "\n",
+    ":::{.callout-note}\n",
+    "[RunnableLambda](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.RunnableLambda.html) is best suited for code that does not need to support streaming. If you need to support streaming (i.e., be able to operate on chunks of inputs and yield chunks of outputs), use [RunnableGenerator](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.RunnableGenerator.html) instead as in the example below.\n",
+    ":::\n",
     "\n",
     "You can use generator functions (ie. functions that use the `yield` keyword, and behave like iterators) in a chain.\n",
     "\n",

docs/docs/how_to/index.mdx

@@ -14,13 +14,14 @@ For comprehensive descriptions of every class and function see the [API Referenc
 ## Installation
 
 - [How to: install LangChain packages](/docs/how_to/installation/)
+- [How to: use LangChain with different Pydantic versions](/docs/how_to/pydantic_compatibility)
 
 ## Key features
 
 This highlights functionality that is core to using LangChain.
 
 - [How to: return structured data from a model](/docs/how_to/structured_output/)
-- [How to: use a model to call tools](/docs/how_to/tool_calling/)
+- [How to: use a model to call tools](/docs/how_to/tool_calling)
 - [How to: stream runnables](/docs/how_to/streaming)
 - [How to: debug your LLM apps](/docs/how_to/debugging/)
 
@@ -49,7 +50,7 @@ These are the core building blocks you can use when building applications.
 
 ### Prompt templates
 
-Prompt Templates are responsible for formatting user input into a format that can be passed to a language model.
+[Prompt Templates](/docs/concepts/#prompt-templates) are responsible for formatting user input into a format that can be passed to a language model.
 
 - [How to: use few shot examples](/docs/how_to/few_shot_examples)
 - [How to: use few shot examples in chat models](/docs/how_to/few_shot_examples_chat/)
@@ -58,7 +59,7 @@ Prompt Templates are responsible for formatting user input into a format that ca
 
 ### Example selectors
 
-Example Selectors are responsible for selecting the correct few shot examples to pass to the prompt.
+[Example Selectors](/docs/concepts/#example-selectors) are responsible for selecting the correct few shot examples to pass to the prompt.
 
 - [How to: use example selectors](/docs/how_to/example_selectors)
 - [How to: select examples by length](/docs/how_to/example_selectors_length_based)
@@ -68,7 +69,7 @@ Example Selectors are responsible for selecting the correct few shot examples to
 
 ### Chat models
 
-Chat Models are newer forms of language models that take messages in and output a message.
+[Chat Models](/docs/concepts/#chat-models) are newer forms of language models that take messages in and output a message.
 
 - [How to: do function/tool calling](/docs/how_to/tool_calling)
 - [How to: get models to return structured output](/docs/how_to/structured_output)
@@ -78,10 +79,25 @@ Chat Models are newer forms of language models that take messages in and output
 - [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: few shot prompt tool behavior](/docs/how_to/tools_few_shot)
+- [How to: bind model-specific formated tools](/docs/how_to/tools_model_specific)
+- [How to: force specific tool call](/docs/how_to/tool_choice)
+- [How to: init any model in one line](/docs/how_to/chat_models_universal_init/)
+
+### Messages
+
+[Messages](/docs/concepts/#messages) are the input and output of chat models. They have some `content` and a `role`, which describes the source of the message.
+
+- [How to: trim messages](/docs/how_to/trim_messages/)
+- [How to: filter messages](/docs/how_to/filter_messages/)
+- [How to: merge consecutive messages of the same type](/docs/how_to/merge_message_runs/)
 
 ### LLMs
 
-What LangChain calls LLMs are older forms of language models that take a string in and output a string.
+What LangChain calls [LLMs](/docs/concepts/#llms) are older forms of language models that take a string in and output a string.
 
 - [How to: cache model responses](/docs/how_to/llm_caching)
 - [How to: create a custom LLM class](/docs/how_to/custom_llm)
@@ -91,7 +107,7 @@ What LangChain calls LLMs are older forms of language models that take a string
 
 ### Output parsers
 
-Output Parsers are responsible for taking the output of an LLM and parsing into more structured format.
+[Output Parsers](/docs/concepts/#output-parsers) are responsible for taking the output of an LLM and parsing into more structured format.
 
 - [How to: use output parsers to parse an LLM response into structured format](/docs/how_to/output_parser_structured)
 - [How to: parse JSON output](/docs/how_to/output_parser_json)
@@ -103,7 +119,7 @@ Output Parsers are responsible for taking the output of an LLM and parsing into
 
 ### Document loaders
 
-Document Loaders are responsible for loading documents from a variety of sources.
+[Document Loaders](/docs/concepts/#document-loaders) are responsible for loading documents from a variety of sources.
 
 - [How to: load CSV data](/docs/how_to/document_loader_csv)
 - [How to: load data from a directory](/docs/how_to/document_loader_directory)
@@ -116,7 +132,7 @@ Document Loaders are responsible for loading documents from a variety of sources
 
 ### Text splitters
 
-Text Splitters take a document and split into chunks that can be used for retrieval.
+[Text Splitters](/docs/concepts/#text-splitters) take a document and split into chunks that can be used for retrieval.
 
 - [How to: recursively split text](/docs/how_to/recursive_text_splitter)
 - [How to: split by HTML headers](/docs/how_to/HTML_header_metadata_splitter)
@@ -130,20 +146,20 @@ Text Splitters take a document and split into chunks that can be used for retrie
 
 ### Embedding models
 
-Embedding Models take a piece of text and create a numerical representation of it.
+[Embedding Models](/docs/concepts/#embedding-models) take a piece of text and create a numerical representation of it.
 
 - [How to: embed text data](/docs/how_to/embed_text)
 - [How to: cache embedding results](/docs/how_to/caching_embeddings)
 
 ### Vector stores
 
-Vector stores are databases that can efficiently store and retrieve embeddings.
+[Vector stores](/docs/concepts/#vector-stores) are databases that can efficiently store and retrieve embeddings.
 
 - [How to: use a vector store to retrieve data](/docs/how_to/vectorstores)
 
 ### Retrievers
 
-Retrievers are responsible for taking a query and returning relevant documents.
+[Retrievers](/docs/concepts/#retrievers) are responsible for taking a query and returning relevant documents.
 
 - [How to: use a vector store to retrieve data](/docs/how_to/vectorstore_retriever)
 - [How to: generate multiple queries to retrieve data for](/docs/how_to/MultiQueryRetriever)
@@ -151,7 +167,7 @@ Retrievers are responsible for taking a query and returning relevant documents.
 - [How to: write a custom retriever class](/docs/how_to/custom_retriever)
 - [How to: add similarity scores to retriever results](/docs/how_to/add_scores_retriever)
 - [How to: combine the results from multiple retrievers](/docs/how_to/ensemble_retriever)
-- [How to: reorder retrieved results to put most relevant documents not in the middle](/docs/how_to/long_context_reorder)
+- [How to: reorder retrieved results to mitigate the "lost in the middle" effect](/docs/how_to/long_context_reorder)
 - [How to: generate multiple embeddings per document](/docs/how_to/multi_vector)
 - [How to: retrieve the whole document for a chunk](/docs/how_to/parent_document_retriever)
 - [How to: generate metadata filters](/docs/how_to/self_query)
@@ -166,14 +182,17 @@ Indexing is the process of keeping your vectorstore in-sync with the underlying
 
 ### Tools
 
-LangChain Tools contain a description of the tool (to pass to the language model) as well as the implementation of the function to call).
+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.
 
 - [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: use a chat model to call tools](/docs/how_to/tool_calling/)
+- [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: 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)
 
 ### Multimodal
 
@@ -194,6 +213,8 @@ For in depth how-to guides for agents, please check out [LangGraph](https://gith
 
 ### Callbacks
 
+[Callbacks](/docs/concepts/#callbacks) allow you to hook into the various stages of your LLM application's execution.
+
 - [How to: pass in callbacks at runtime](/docs/how_to/callbacks_runtime)
 - [How to: attach callbacks to a module](/docs/how_to/callbacks_attach)
 - [How to: pass callbacks into a module constructor](/docs/how_to/callbacks_constructor)
@@ -212,6 +233,8 @@ All of LangChain components can easily be extended to support your own versions.
 - [How to: create custom callback handlers](/docs/how_to/custom_callbacks)
 - [How to: define a custom tool](/docs/how_to/custom_tools)
 
+### Serialization
+- [How to: save and load LangChain objects](/docs/how_to/serialization)
 
 ## Use cases
 
@@ -220,6 +243,7 @@ These guides cover use-case specific details.
 ### Q&A with RAG
 
 Retrieval Augmented Generation (RAG) is a way to connect LLMs to external sources of data.
+For a high-level tutorial on RAG, check out [this guide](/docs/tutorials/rag/).
 
 - [How to: add chat history](/docs/how_to/qa_chat_history_how_to/)
 - [How to: stream](/docs/how_to/qa_streaming/)
@@ -231,6 +255,7 @@ Retrieval Augmented Generation (RAG) is a way to connect LLMs to external source
 ### Extraction
 
 Extraction is when you use LLMs to extract structured information from unstructured text.
+For a high level tutorial on extraction, check out [this guide](/docs/tutorials/extraction/).
 
 - [How to: use reference examples](/docs/how_to/extraction_examples/)
 - [How to: handle long text](/docs/how_to/extraction_long_text/)
@@ -239,14 +264,17 @@ Extraction is when you use LLMs to extract structured information from unstructu
 ### Chatbots
 
 Chatbots involve using an LLM to have a conversation.
+For a high-level tutorial on building chatbots, check out [this guide](/docs/tutorials/chatbot/).
 
 - [How to: manage memory](/docs/how_to/chatbots_memory)
 - [How to: do retrieval](/docs/how_to/chatbots_retrieval)
 - [How to: use tools](/docs/how_to/chatbots_tools)
+- [How to: manage large chat history](/docs/how_to/trim_messages/)
 
 ### Query analysis
 
 Query Analysis is the task of using an LLM to generate a query to send to a retriever.
+For a high-level tutorial on query analysis, check out [this guide](/docs/tutorials/query_analysis/).
 
 - [How to: add examples to the prompt](/docs/how_to/query_few_shot)
 - [How to: handle cases where no queries are generated](/docs/how_to/query_no_queries)
@@ -258,6 +286,7 @@ Query Analysis is the task of using an LLM to generate a query to send to a retr
 ### Q&A over SQL + CSV
 
 You can use LLMs to do question answering over tabular data.
+For a high-level tutorial, check out [this guide](/docs/tutorials/sql_qa/).
 
 - [How to: use prompting to improve results](/docs/how_to/sql_prompting)
 - [How to: do query validation](/docs/how_to/sql_query_checking)
@@ -267,8 +296,33 @@ You can use LLMs to do question answering over tabular data.
 ### Q&A over graph databases
 
 You can use an LLM to do question answering over graph databases.
+For a high-level tutorial, check out [this guide](/docs/tutorials/graph/).
 
 - [How to: map values to a database](/docs/how_to/graph_mapping)
 - [How to: add a semantic layer over the database](/docs/how_to/graph_semantic)
 - [How to: improve results with prompting](/docs/how_to/graph_prompting)
 - [How to: construct knowledge graphs](/docs/how_to/graph_constructing)
+
+## [LangGraph](https://langchain-ai.github.io/langgraph)
+
+LangGraph is an extension of LangChain aimed at
+building robust and stateful multi-actor applications with LLMs by modeling steps as edges and nodes in a graph.
+
+LangGraph documentation is currently hosted on a separate site.
+You can peruse [LangGraph how-to guides here](https://langchain-ai.github.io/langgraph/how-tos/).
+
+## [LangSmith](https://docs.smith.langchain.com/)
+
+LangSmith allows you to closely trace, monitor and evaluate your LLM application.
+It seamlessly integrates with LangChain and LangGraph, and you can use it to inspect and debug individual steps of your chains and agents as you build.
+
+LangSmith documentation is hosted on a separate site.
+You can peruse [LangSmith how-to guides here](https://docs.smith.langchain.com/how_to_guides/).
+
+### Evaluation
+<span data-heading-keywords="evaluation,evaluate"></span>
+
+Evaluating performance is a vital part of building LLM-powered applications.
+LangSmith helps with every step of the process from creating a dataset to defining metrics to running evaluators.
+
+To learn more, check out the [LangSmith evaluation how-to guides](https://docs.smith.langchain.com/how_to_guides#evaluation).

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`, `Bagel`, `Cassandra`, `Chroma`, `CouchbaseVectorStore`, `DashVector`, `DatabricksVectorSearch`, `DeepLake`, `Dingo`, `ElasticVectorSearch`, `ElasticsearchStore`, `FAISS`, `HanaDB`, `Milvus`, `MyScale`, `OpenSearchVectorSearch`, `PGVector`, `Pinecone`, `Qdrant`, `Redis`, `Rockset`, `ScaNN`, `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`, `MyScale`, `OpenSearchVectorSearch`, `PGVector`, `Pinecone`, `Qdrant`, `Redis`, `Rockset`, `ScaNN`, `SupabaseVectorStore`, `SurrealDBStore`, `TimescaleVector`, `Vald`, `VDMS`, `Vearch`, `VespaStore`, `Weaviate`, `Yellowbrick`, `ZepVectorStore`, `TencentVectorDB`, `OpenSearchVectorSearch`.\n",
     "  \n",
     "## Caution\n",
     "\n",

docs/docs/how_to/llm_token_usage_tracking.ipynb

@@ -2,169 +2,226 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "e5715368",
+   "id": "90dff237-bc28-4185-a2c0-d5203bbdeacd",
    "metadata": {},
    "source": [
     "# How to track token usage for LLMs\n",
     "\n",
-    "This notebook goes over how to track your token usage for specific calls. It is currently only implemented for the OpenAI API.\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",
-    "Let's first look at an extremely simple example of tracking token usage for a single LLM call."
+    ":::info Prerequisites\n",
+    "\n",
+    "This guide assumes familiarity with the following concepts:\n",
+    "\n",
+    "- [LLMs](/docs/concepts/#llms)\n",
+    ":::\n",
+    "\n",
+    "## Using LangSmith\n",
+    "\n",
+    "You can use [LangSmith](https://www.langchain.com/langsmith) to help track token usage in your LLM application. See the [LangSmith quick start guide](https://docs.smith.langchain.com/).\n",
+    "\n",
+    "## Using callbacks\n",
+    "\n",
+    "There are some API-specific callback context managers that allow you to track token usage across multiple calls. You'll need to check whether such an integration is available for your particular model.\n",
+    "\n",
+    "If such an integration is not available for your model, you can create a custom callback manager by adapting the implementation of the [OpenAI callback manager](https://api.python.langchain.com/en/latest/_modules/langchain_community/callbacks/openai_info.html#OpenAICallbackHandler).\n",
+    "\n",
+    "### OpenAI\n",
+    "\n",
+    "Let's first look at an extremely simple example of tracking token usage for a single Chat model call.\n",
+    "\n",
+    ":::{.callout-danger}\n",
+    "\n",
+    "The callback handler does not currently support streaming token counts for legacy language models (e.g., `langchain_openai.OpenAI`). For support in a streaming context, refer to the corresponding guide for chat models [here](/docs/how_to/chat_token_usage_tracking).\n",
+    "\n",
+    ":::"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f790edd9-823e-4bc5-befa-e9529c7237a0",
+   "metadata": {},
+   "source": [
+    "### Single call"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 1,
-   "id": "9455db35",
+   "id": "2eebbee2-6ca1-4fa8-a3aa-0376888ceefb",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "Why don't scientists trust atoms?\n",
+      "\n",
+      "Because they make up everything.\n",
+      "---\n",
+      "\n",
+      "Total Tokens: 18\n",
+      "Prompt Tokens: 4\n",
+      "Completion Tokens: 14\n",
+      "Total Cost (USD): $3.4e-05\n"
+     ]
+    }
+   ],
    "source": [
     "from langchain_community.callbacks import get_openai_callback\n",
-    "from langchain_openai import OpenAI"
+    "from langchain_openai import OpenAI\n",
+    "\n",
+    "llm = OpenAI(model_name=\"gpt-3.5-turbo-instruct\")\n",
+    "\n",
+    "with get_openai_callback() as cb:\n",
+    "    result = llm.invoke(\"Tell me a joke\")\n",
+    "    print(result)\n",
+    "    print(\"---\")\n",
+    "print()\n",
+    "\n",
+    "print(f\"Total Tokens: {cb.total_tokens}\")\n",
+    "print(f\"Prompt Tokens: {cb.prompt_tokens}\")\n",
+    "print(f\"Completion Tokens: {cb.completion_tokens}\")\n",
+    "print(f\"Total Cost (USD): ${cb.total_cost}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7df3be35-dd97-4e3a-bd51-52434ab2249d",
+   "metadata": {},
+   "source": [
+    "### Multiple calls\n",
+    "\n",
+    "Anything inside the context manager will get tracked. Here's an example of using it to track multiple calls in sequence to a chain. This will also work for an agent which may use multiple steps."
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 2,
-   "id": "d1c55cc9",
+   "id": "3ec10419-294c-44bf-af85-86aabf457cb6",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "Why did the chicken go to the seance?\n",
+      "\n",
+      "To talk to the other side of the road!\n",
+      "--\n",
+      "\n",
+      "\n",
+      "Why did the fish need a lawyer?\n",
+      "\n",
+      "Because it got caught in a net!\n",
+      "\n",
+      "---\n",
+      "Total Tokens: 50\n",
+      "Prompt Tokens: 12\n",
+      "Completion Tokens: 38\n",
+      "Total Cost (USD): $9.400000000000001e-05\n"
+     ]
+    }
+   ],
    "source": [
-    "llm = OpenAI(model_name=\"gpt-3.5-turbo-instruct\", n=2, best_of=2)"
+    "from langchain_community.callbacks import get_openai_callback\n",
+    "from langchain_core.prompts import PromptTemplate\n",
+    "from langchain_openai import OpenAI\n",
+    "\n",
+    "llm = OpenAI(model_name=\"gpt-3.5-turbo-instruct\")\n",
+    "\n",
+    "template = PromptTemplate.from_template(\"Tell me a joke about {topic}\")\n",
+    "chain = template | llm\n",
+    "\n",
+    "with get_openai_callback() as cb:\n",
+    "    response = chain.invoke({\"topic\": \"birds\"})\n",
+    "    print(response)\n",
+    "    response = chain.invoke({\"topic\": \"fish\"})\n",
+    "    print(\"--\")\n",
+    "    print(response)\n",
+    "\n",
+    "\n",
+    "print()\n",
+    "print(\"---\")\n",
+    "print(f\"Total Tokens: {cb.total_tokens}\")\n",
+    "print(f\"Prompt Tokens: {cb.prompt_tokens}\")\n",
+    "print(f\"Completion Tokens: {cb.completion_tokens}\")\n",
+    "print(f\"Total Cost (USD): ${cb.total_cost}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ad7a3fba-9fac-4222-8f87-d1d276d27d6e",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "## Streaming\n",
+    "\n",
+    ":::{.callout-danger}\n",
+    "\n",
+    "`get_openai_callback` does not currently support streaming token counts for legacy language models (e.g., `langchain_openai.OpenAI`). If you want to count tokens correctly in a streaming context, there are a number of options:\n",
+    "\n",
+    "- Use chat models as described in [this guide](/docs/how_to/chat_token_usage_tracking);\n",
+    "- Implement a [custom callback handler](/docs/how_to/custom_callbacks/) that uses appropriate tokenizers to count the tokens;\n",
+    "- Use a monitoring platform such as [LangSmith](https://www.langchain.com/langsmith).\n",
+    ":::\n",
+    "\n",
+    "Note that when using legacy language models in a streaming context, token counts are not updated:"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 3,
-   "id": "31667d54",
-   "metadata": {},
+   "id": "cd61ed79-7858-49bb-afb5-d41291f597ba",
+   "metadata": {
+    "tags": []
+   },
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Tokens Used: 37\n",
-      "\tPrompt Tokens: 4\n",
-      "\tCompletion Tokens: 33\n",
-      "Successful Requests: 1\n",
-      "Total Cost (USD): $7.2e-05\n"
+      "\n",
+      "\n",
+      "Why don't scientists trust atoms?\n",
+      "\n",
+      "Because they make up everything!\n",
+      "\n",
+      "Why don't scientists trust atoms?\n",
+      "\n",
+      "Because they make up everything.\n",
+      "---\n",
+      "\n",
+      "Total Tokens: 0\n",
+      "Prompt Tokens: 0\n",
+      "Completion Tokens: 0\n",
+      "Total Cost (USD): $0.0\n"
      ]
     }
    ],
    "source": [
-    "with get_openai_callback() as cb:\n",
-    "    result = llm.invoke(\"Tell me a joke\")\n",
-    "    print(cb)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "c0ab6d27",
-   "metadata": {},
-   "source": [
-    "Anything inside the context manager will get tracked. Here's an example of using it to track multiple calls in sequence."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "e09420f4",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "72\n"
-     ]
-    }
-   ],
-   "source": [
-    "with get_openai_callback() as cb:\n",
-    "    result = llm.invoke(\"Tell me a joke\")\n",
-    "    result2 = llm.invoke(\"Tell me a joke\")\n",
-    "    print(cb.total_tokens)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "d8186e7b",
-   "metadata": {},
-   "source": [
-    "If a chain or agent with multiple steps in it is used, it will track all those steps."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "5d1125c6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.agents import AgentType, initialize_agent, load_tools\n",
+    "from langchain_community.callbacks import get_openai_callback\n",
     "from langchain_openai import OpenAI\n",
     "\n",
-    "llm = OpenAI(temperature=0)\n",
-    "tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm)\n",
-    "agent = initialize_agent(\n",
-    "    tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "2f98c536",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3m I need to find out who Olivia Wilde's boyfriend is and then calculate his age raised to the 0.23 power.\n",
-      "Action: Search\n",
-      "Action Input: \"Olivia Wilde boyfriend\"\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3m[\"Olivia Wilde and Harry Styles took fans by surprise with their whirlwind romance, which began when they met on the set of Don't Worry Darling.\", 'Olivia Wilde started dating Harry Styles after ending her years-long engagement to Jason Sudeikis — see their relationship timeline.', 'Olivia Wilde and Harry Styles were spotted early on in their relationship walking around London. (. Image ...', \"Looks like Olivia Wilde and Jason Sudeikis are starting 2023 on good terms. Amid their highly publicized custody battle – and the actress' ...\", 'The two started dating after Wilde split up with actor Jason Sudeikisin 2020. However, their relationship came to an end last November.', \"Olivia Wilde and Harry Styles started dating during the filming of Don't Worry Darling. While the movie got a lot of backlash because of the ...\", \"Here's what we know so far about Harry Styles and Olivia Wilde's relationship.\", 'Olivia and the Grammy winner kept their romance out of the spotlight as their relationship began just two months after her split from ex-fiancé ...', \"Harry Styles and Olivia Wilde first met on the set of Don't Worry Darling and stepped out as a couple in January 2021. Relive all their biggest relationship ...\"]\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m Harry Styles is Olivia Wilde's boyfriend.\n",
-      "Action: Search\n",
-      "Action Input: \"Harry Styles age\"\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3m29 years\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I need to calculate 29 raised to the 0.23 power.\n",
-      "Action: Calculator\n",
-      "Action Input: 29^0.23\u001b[0m\n",
-      "Observation: \u001b[33;1m\u001b[1;3mAnswer: 2.169459462491557\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
-      "Final Answer: Harry Styles is Olivia Wilde's boyfriend and his current age raised to the 0.23 power is 2.169459462491557.\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n",
-      "Total Tokens: 2205\n",
-      "Prompt Tokens: 2053\n",
-      "Completion Tokens: 152\n",
-      "Total Cost (USD): $0.0441\n"
-     ]
-    }
-   ],
-   "source": [
+    "llm = OpenAI(model_name=\"gpt-3.5-turbo-instruct\")\n",
+    "\n",
     "with get_openai_callback() as cb:\n",
-    "    response = agent.run(\n",
-    "        \"Who is Olivia Wilde's boyfriend? What is his current age raised to the 0.23 power?\"\n",
-    "    )\n",
-    "    print(f\"Total Tokens: {cb.total_tokens}\")\n",
-    "    print(f\"Prompt Tokens: {cb.prompt_tokens}\")\n",
-    "    print(f\"Completion Tokens: {cb.completion_tokens}\")\n",
-    "    print(f\"Total Cost (USD): ${cb.total_cost}\")"
+    "    for chunk in llm.stream(\"Tell me a joke\"):\n",
+    "        print(chunk, end=\"\", flush=True)\n",
+    "    print(result)\n",
+    "    print(\"---\")\n",
+    "print()\n",
+    "\n",
+    "print(f\"Total Tokens: {cb.total_tokens}\")\n",
+    "print(f\"Prompt Tokens: {cb.prompt_tokens}\")\n",
+    "print(f\"Completion Tokens: {cb.completion_tokens}\")\n",
+    "print(f\"Total Cost (USD): ${cb.total_cost}\")"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "80ca77a3",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
@@ -183,7 +240,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.1"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/how_to/long_context_reorder.ipynb

@@ -5,28 +5,38 @@
    "id": "fc0db1bc",
    "metadata": {},
    "source": [
-    "# How to reorder retrieved results to put most relevant documents not in the middle\n",
+    "# How to reorder retrieved results to mitigate the \"lost in the middle\" effect\n",
     "\n",
-    "No matter the architecture of your model, there is a substantial performance degradation when you include 10+ retrieved documents.\n",
-    "In brief: When models must access relevant information in the middle of long contexts, they tend to ignore the provided documents.\n",
-    "See: https://arxiv.org/abs/2307.03172\n",
+    "Substantial performance degradations in [RAG](/docs/tutorials/rag) applications have been [documented](https://arxiv.org/abs/2307.03172) as the number of retrieved documents grows (e.g., beyond ten). In brief: models are liable to miss relevant information in the middle of long contexts.\n",
     "\n",
-    "To avoid this issue you can re-order documents after retrieval to avoid performance degradation."
+    "By contrast, queries against vector stores will typically return documents in descending order of relevance (e.g., as measured by cosine similarity of [embeddings](/docs/concepts/#embedding-models)).\n",
+    "\n",
+    "To mitigate the [\"lost in the middle\"](https://arxiv.org/abs/2307.03172) effect, you can re-order documents after retrieval such that the most relevant documents are positioned at extrema (e.g., the first and last pieces of context), and the least relevant documents are positioned in the middle. In some cases this can help surface the most relevant information to LLMs.\n",
+    "\n",
+    "The [LongContextReorder](https://api.python.langchain.com/en/latest/document_transformers/langchain_community.document_transformers.long_context_reorder.LongContextReorder.html) document transformer implements this re-ordering procedure. Below we demonstrate an example."
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "74d1ebe8",
+   "id": "2074fdaa-edff-468a-970f-6f5f26e93d4a",
    "metadata": {},
    "outputs": [],
    "source": [
     "%pip install --upgrade --quiet  sentence-transformers langchain-chroma langchain langchain-openai langchain-huggingface > /dev/null"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "c97eaaf2-34b7-4770-9949-e1abc4ca5226",
+   "metadata": {},
+   "source": [
+    "First we embed some artificial documents and index them in an (in-memory) [Chroma](/docs/integrations/providers/chroma/) vector store. We will use [Hugging Face](/docs/integrations/text_embedding/huggingfacehub/) embeddings, but any LangChain vector store or embeddings model will suffice."
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "id": "49cbcd8e",
    "metadata": {},
    "outputs": [
@@ -45,20 +55,14 @@
        " Document(page_content='This is just a random text.')]"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "from langchain.chains import LLMChain, StuffDocumentsChain\n",
     "from langchain_chroma import Chroma\n",
-    "from langchain_community.document_transformers import (\n",
-    "    LongContextReorder,\n",
-    ")\n",
-    "from langchain_core.prompts import PromptTemplate\n",
     "from langchain_huggingface import HuggingFaceEmbeddings\n",
-    "from langchain_openai import OpenAI\n",
     "\n",
     "# Get embeddings.\n",
     "embeddings = HuggingFaceEmbeddings(model_name=\"all-MiniLM-L6-v2\")\n",
@@ -83,14 +87,22 @@
     "query = \"What can you tell me about the Celtics?\"\n",
     "\n",
     "# Get relevant documents ordered by relevance score\n",
-    "docs = retriever.get_relevant_documents(query)\n",
+    "docs = retriever.invoke(query)\n",
     "docs"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "175d031a-43fa-42f4-93c4-2ba52c3c3ee5",
+   "metadata": {},
+   "source": [
+    "Note that documents are returned in descending order of relevance to the query. The `LongContextReorder` document transformer will implement the re-ordering described above:"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 4,
-   "id": "34fb9d6e",
+   "execution_count": 3,
+   "id": "9a1181f2-a3dc-4614-9233-2196ab65939e",
    "metadata": {},
    "outputs": [
     {
@@ -108,12 +120,14 @@
        " Document(page_content='This is a document about the Boston Celtics')]"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
+    "from langchain_community.document_transformers import LongContextReorder\n",
+    "\n",
     "# Reorder the documents:\n",
     "# Less relevant document will be at the middle of the list and more\n",
     "# relevant elements at beginning / end.\n",
@@ -125,58 +139,54 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "ceccab87",
+   "cell_type": "markdown",
+   "id": "a8d2ef0c-c397-4d8d-8118-3f7acf86d241",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'\\n\\nThe Celtics are referenced in four of the nine text extracts. They are mentioned as the favorite team of the author, the winner of a basketball game, a team with one of the best players, and a team with a specific player. Additionally, the last extract states that the document is about the Boston Celtics. This suggests that the Celtics are a basketball team, possibly from Boston, that is well-known and has had successful players and games in the past. '"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
    "source": [
-    "# We prepare and run a custom Stuff chain with reordered docs as context.\n",
-    "\n",
-    "# Override prompts\n",
-    "document_prompt = PromptTemplate(\n",
-    "    input_variables=[\"page_content\"], template=\"{page_content}\"\n",
-    ")\n",
-    "document_variable_name = \"context\"\n",
-    "llm = OpenAI()\n",
-    "stuff_prompt_override = \"\"\"Given this text extracts:\n",
-    "-----\n",
-    "{context}\n",
-    "-----\n",
-    "Please answer the following question:\n",
-    "{query}\"\"\"\n",
-    "prompt = PromptTemplate(\n",
-    "    template=stuff_prompt_override, input_variables=[\"context\", \"query\"]\n",
-    ")\n",
-    "\n",
-    "# Instantiate the chain\n",
-    "llm_chain = LLMChain(llm=llm, prompt=prompt)\n",
-    "chain = StuffDocumentsChain(\n",
-    "    llm_chain=llm_chain,\n",
-    "    document_prompt=document_prompt,\n",
-    "    document_variable_name=document_variable_name,\n",
-    ")\n",
-    "chain.run(input_documents=reordered_docs, query=query)"
+    "Below, we show how to incorporate the re-ordered documents into a simple question-answering chain:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "d4696a97",
+   "execution_count": 5,
+   "id": "8bbea705-d5b9-4ed5-9957-e12547283622",
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "The Celtics are a professional basketball team and one of the most iconic franchises in the NBA. They are highly regarded and have a large fan base. The team has had many successful seasons and is often considered one of the top teams in the league. They have a strong history and have produced many great players, such as Larry Bird and L. Kornet. The team is based in Boston and is often referred to as the Boston Celtics.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain.chains.combine_documents import create_stuff_documents_chain\n",
+    "from langchain_core.prompts import PromptTemplate\n",
+    "from langchain_openai import OpenAI\n",
+    "\n",
+    "llm = OpenAI()\n",
+    "\n",
+    "prompt_template = \"\"\"\n",
+    "Given these texts:\n",
+    "-----\n",
+    "{context}\n",
+    "-----\n",
+    "Please answer the following question:\n",
+    "{query}\n",
+    "\"\"\"\n",
+    "\n",
+    "prompt = PromptTemplate(\n",
+    "    template=prompt_template,\n",
+    "    input_variables=[\"context\", \"query\"],\n",
+    ")\n",
+    "\n",
+    "# Create and invoke the chain:\n",
+    "chain = create_stuff_documents_chain(llm, prompt)\n",
+    "response = chain.invoke({\"context\": reordered_docs, \"query\": query})\n",
+    "print(response)"
+   ]
   }
  ],
  "metadata": {
@@ -195,7 +205,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.1"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/how_to/merge_message_runs.ipynb

@@ -0,0 +1,170 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "ac47bfab-0f4f-42ce-8bb6-898ef22a0338",
+   "metadata": {},
+   "source": [
+    "# How to merge consecutive messages of the same type\n",
+    "\n",
+    "Certain models do not support passing in consecutive messages of the same type (a.k.a. \"runs\" of the same message type).\n",
+    "\n",
+    "The `merge_message_runs` utility makes it easy to merge consecutive messages of the same type.\n",
+    "\n",
+    "## Basic usage"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "1a215bbb-c05c-40b0-a6fd-d94884d517df",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "SystemMessage(content=\"you're a good assistant.\\nyou always respond with a joke.\")\n",
+      "\n",
+      "HumanMessage(content=[{'type': 'text', 'text': \"i wonder why it's called langchain\"}, 'and who is harrison chasing anyways'])\n",
+      "\n",
+      "AIMessage(content='Well, I guess they thought \"WordRope\" and \"SentenceString\" just didn\\'t have the same ring to it!\\nWhy, he\\'s probably chasing after the last cup of coffee in the office!')\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain_core.messages import (\n",
+    "    AIMessage,\n",
+    "    HumanMessage,\n",
+    "    SystemMessage,\n",
+    "    merge_message_runs,\n",
+    ")\n",
+    "\n",
+    "messages = [\n",
+    "    SystemMessage(\"you're a good assistant.\"),\n",
+    "    SystemMessage(\"you always respond with a joke.\"),\n",
+    "    HumanMessage([{\"type\": \"text\", \"text\": \"i wonder why it's called langchain\"}]),\n",
+    "    HumanMessage(\"and who is harrison chasing anyways\"),\n",
+    "    AIMessage(\n",
+    "        'Well, I guess they thought \"WordRope\" and \"SentenceString\" just didn\\'t have the same ring to it!'\n",
+    "    ),\n",
+    "    AIMessage(\"Why, he's probably chasing after the last cup of coffee in the office!\"),\n",
+    "]\n",
+    "\n",
+    "merged = merge_message_runs(messages)\n",
+    "print(\"\\n\\n\".join([repr(x) for x in merged]))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0544c811-7112-4b76-8877-cc897407c738",
+   "metadata": {},
+   "source": [
+    "Notice that if the contents of one of the messages to merge is a list of content blocks then the merged message will have a list of content blocks. And if both messages to merge have string contents then those are concatenated with a newline character."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1b2eee74-71c8-4168-b968-bca580c25d18",
+   "metadata": {},
+   "source": [
+    "## Chaining\n",
+    "\n",
+    "`merge_message_runs` can be used in an imperatively (like above) or declaratively, making it easy to compose with other components in a chain:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "6d5a0283-11f8-435b-b27b-7b18f7693592",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=[], response_metadata={'id': 'msg_01D6R8Naum57q8qBau9vLBUX', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 84, 'output_tokens': 3}}, id='run-ac0c465b-b54f-4b8b-9295-e5951250d653-0', usage_metadata={'input_tokens': 84, 'output_tokens': 3, 'total_tokens': 87})"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# pip install -U langchain-anthropic\n",
+    "from langchain_anthropic import ChatAnthropic\n",
+    "\n",
+    "llm = ChatAnthropic(model=\"claude-3-sonnet-20240229\", temperature=0)\n",
+    "# Notice we don't pass in messages. This creates\n",
+    "# a RunnableLambda that takes messages as input\n",
+    "merger = merge_message_runs()\n",
+    "chain = merger | llm\n",
+    "chain.invoke(messages)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "72e90dce-693c-4842-9526-ce6460fe956b",
+   "metadata": {},
+   "source": [
+    "Looking at the LangSmith trace we can see that before the messages are passed to the model they are merged: https://smith.langchain.com/public/ab558677-cac9-4c59-9066-1ecce5bcd87c/r\n",
+    "\n",
+    "Looking at just the merger, we can see that it's a Runnable object that can be invoked like all Runnables:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "460817a6-c327-429d-958e-181a8c46059c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[SystemMessage(content=\"you're a good assistant.\\nyou always respond with a joke.\"),\n",
+       " HumanMessage(content=[{'type': 'text', 'text': \"i wonder why it's called langchain\"}, 'and who is harrison chasing anyways']),\n",
+       " AIMessage(content='Well, I guess they thought \"WordRope\" and \"SentenceString\" just didn\\'t have the same ring to it!\\nWhy, he\\'s probably chasing after the last cup of coffee in the office!')]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "merger.invoke(messages)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4548d916-ce21-4dc6-8f19-eedb8003ace6",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For a complete description of all arguments head to the API reference: https://api.python.langchain.com/en/latest/messages/langchain_core.messages.utils.merge_message_runs.html"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "poetry-venv-2",
+   "language": "python",
+   "name": "poetry-venv-2"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/how_to/multi_vector.ipynb

@@ -5,33 +5,36 @@
    "id": "d9172545",
    "metadata": {},
    "source": [
-    "# How to use the MultiVector Retriever\n",
+    "# How to retrieve using multiple vectors per document\n",
     "\n",
-    "It can often be beneficial to store multiple vectors per document. There are multiple use cases where this is beneficial. LangChain has a base `MultiVectorRetriever` which makes querying this type of setup easy. A lot of the complexity lies in how to create the multiple vectors per document. This notebook covers some of the common ways to create those vectors and use the `MultiVectorRetriever`.\n",
+    "It can often be useful to store multiple vectors per document. There are multiple use cases where this is beneficial. For example, we can embed multiple chunks of a document and associate those embeddings with the parent document, allowing retriever hits on the chunks to return the larger document.\n",
+    "\n",
+    "LangChain implements a base [MultiVectorRetriever](https://api.python.langchain.com/en/latest/retrievers/langchain.retrievers.multi_vector.MultiVectorRetriever.html), which simplifies this process. Much of the complexity lies in how to create the multiple vectors per document. This notebook covers some of the common ways to create those vectors and use the `MultiVectorRetriever`.\n",
     "\n",
     "The methods to create multiple vectors per document include:\n",
     "\n",
-    "- Smaller chunks: split a document into smaller chunks, and embed those (this is ParentDocumentRetriever).\n",
+    "- Smaller chunks: split a document into smaller chunks, and embed those (this is [ParentDocumentRetriever](https://api.python.langchain.com/en/latest/retrievers/langchain.retrievers.parent_document_retriever.ParentDocumentRetriever.html)).\n",
     "- Summary: create a summary for each document, embed that along with (or instead of) the document.\n",
     "- Hypothetical questions: create hypothetical questions that each document would be appropriate to answer, embed those along with (or instead of) the document.\n",
     "\n",
+    "Note that this also enables another method of adding embeddings - manually. This is useful because you can explicitly add questions or queries that should lead to a document being recovered, giving you more control.\n",
     "\n",
-    "Note that this also enables another method of adding embeddings - manually. This is great because you can explicitly add questions or queries that should lead to a document being recovered, giving you more control."
+    "Below we walk through an example. First we instantiate some documents. We will index them in an (in-memory) [Chroma](/docs/integrations/providers/chroma/) vector store using [OpenAI](https://python.langchain.com/v0.2/docs/integrations/text_embedding/openai/) embeddings, but any LangChain vector store or embeddings model will suffice."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "09cecd95-3499-465a-895a-944627ffb77f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade --quiet  langchain-chroma langchain langchain-openai > /dev/null"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 1,
-   "id": "eed469be",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.retrievers.multi_vector import MultiVectorRetriever"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
    "id": "18c1421a",
    "metadata": {},
    "outputs": [],
@@ -40,25 +43,22 @@
     "from langchain_chroma import Chroma\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_openai import OpenAIEmbeddings\n",
-    "from langchain_text_splitters import RecursiveCharacterTextSplitter"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "6d869496",
-   "metadata": {},
-   "outputs": [],
-   "source": [
+    "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
+    "\n",
     "loaders = [\n",
-    "    TextLoader(\"../../paul_graham_essay.txt\"),\n",
+    "    TextLoader(\"paul_graham_essay.txt\"),\n",
     "    TextLoader(\"state_of_the_union.txt\"),\n",
     "]\n",
     "docs = []\n",
     "for loader in loaders:\n",
     "    docs.extend(loader.load())\n",
     "text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000)\n",
-    "docs = text_splitter.split_documents(docs)"
+    "docs = text_splitter.split_documents(docs)\n",
+    "\n",
+    "# The vectorstore to use to index the child chunks\n",
+    "vectorstore = Chroma(\n",
+    "    collection_name=\"full_documents\", embedding_function=OpenAIEmbeddings()\n",
+    ")"
    ]
   },
   {
@@ -68,52 +68,54 @@
    "source": [
     "## Smaller chunks\n",
     "\n",
-    "Often times it can be useful to retrieve larger chunks of information, but embed smaller chunks. This allows for embeddings to capture the semantic meaning as closely as possible, but for as much context as possible to be passed downstream. Note that this is what the `ParentDocumentRetriever` does. Here we show what is going on under the hood."
+    "Often times it can be useful to retrieve larger chunks of information, but embed smaller chunks. This allows for embeddings to capture the semantic meaning as closely as possible, but for as much context as possible to be passed downstream. Note that this is what the [ParentDocumentRetriever](https://api.python.langchain.com/en/latest/retrievers/langchain.retrievers.parent_document_retriever.ParentDocumentRetriever.html) does. Here we show what is going on under the hood.\n",
+    "\n",
+    "We will make a distinction between the vector store, which indexes embeddings of the (sub) documents, and the document store, which houses the \"parent\" documents and associates them with an identifier."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 2,
    "id": "0e7b6b45",
    "metadata": {},
    "outputs": [],
    "source": [
-    "# The vectorstore to use to index the child chunks\n",
-    "vectorstore = Chroma(\n",
-    "    collection_name=\"full_documents\", embedding_function=OpenAIEmbeddings()\n",
-    ")\n",
+    "import uuid\n",
+    "\n",
+    "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
+    "\n",
     "# The storage layer for the parent documents\n",
     "store = InMemoryByteStore()\n",
     "id_key = \"doc_id\"\n",
+    "\n",
     "# The retriever (empty to start)\n",
     "retriever = MultiVectorRetriever(\n",
     "    vectorstore=vectorstore,\n",
     "    byte_store=store,\n",
     "    id_key=id_key,\n",
     ")\n",
-    "import uuid\n",
     "\n",
     "doc_ids = [str(uuid.uuid4()) for _ in docs]"
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "72a36491",
+   "cell_type": "markdown",
+   "id": "d4feded4-856a-4282-91c3-53aabc62e6ff",
    "metadata": {},
-   "outputs": [],
    "source": [
-    "# The splitter to use to create smaller chunks\n",
-    "child_text_splitter = RecursiveCharacterTextSplitter(chunk_size=400)"
+    "We next generate the \"sub\" documents by splitting the original documents. Note that we store the document identifier in the `metadata` of the corresponding [Document](https://api.python.langchain.com/en/latest/documents/langchain_core.documents.base.Document.html) object."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 3,
    "id": "5d23247d",
    "metadata": {},
    "outputs": [],
    "source": [
+    "# The splitter to use to create smaller chunks\n",
+    "child_text_splitter = RecursiveCharacterTextSplitter(chunk_size=400)\n",
+    "\n",
     "sub_docs = []\n",
     "for i, doc in enumerate(docs):\n",
     "    _id = doc_ids[i]\n",
@@ -123,9 +125,17 @@
     "    sub_docs.extend(_sub_docs)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "8e0634f8-90d5-4250-981a-5257c8a6d455",
+   "metadata": {},
+   "source": [
+    "Finally, we index the documents in our vector store and document store:"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 4,
    "id": "92ed5861",
    "metadata": {},
    "outputs": [],
@@ -134,31 +144,46 @@
     "retriever.docstore.mset(list(zip(doc_ids, docs)))"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "14c48c6d-850c-4317-9b6e-1ade92f2f710",
+   "metadata": {},
+   "source": [
+    "The vector store alone will retrieve small chunks:"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 5,
    "id": "8afed60c",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "Document(page_content='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\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court.', metadata={'doc_id': '2fd77862-9ed5-4fad-bf76-e487b747b333', 'source': 'state_of_the_union.txt'})"
+       "Document(page_content='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\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court.', metadata={'doc_id': '064eca46-a4c4-4789-8e3b-583f9597e54f', 'source': 'state_of_the_union.txt'})"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "# Vectorstore alone retrieves the small chunks\n",
     "retriever.vectorstore.similarity_search(\"justice breyer\")[0]"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "717097c7-61d9-4306-8625-ef8f1940c127",
+   "metadata": {},
+   "source": [
+    "Whereas the retriever will return the larger parent document:"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 6,
    "id": "3c9017f1",
    "metadata": {},
    "outputs": [
@@ -168,14 +193,13 @@
        "9875"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "# Retriever returns larger chunks\n",
-    "len(retriever.get_relevant_documents(\"justice breyer\")[0].page_content)"
+    "len(retriever.invoke(\"justice breyer\")[0].page_content)"
    ]
   },
   {
@@ -183,12 +207,12 @@
    "id": "cdef8339-f9fa-4b3b-955f-ad9dbdf2734f",
    "metadata": {},
    "source": [
-    "The default search type the retriever performs on the vector database is a similarity search. LangChain Vector Stores also support searching via [Max Marginal Relevance](https://api.python.langchain.com/en/latest/vectorstores/langchain_core.vectorstores.VectorStore.html#langchain_core.vectorstores.VectorStore.max_marginal_relevance_search) so if you want this instead you can just set the `search_type` property as follows:"
+    "The default search type the retriever performs on the vector database is a similarity search. LangChain vector stores also support searching via [Max Marginal Relevance](https://api.python.langchain.com/en/latest/vectorstores/langchain_core.vectorstores.VectorStore.html#langchain_core.vectorstores.VectorStore.max_marginal_relevance_search). This can be controlled via the `search_type` parameter of the retriever:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 7,
    "id": "36739460-a737-4a8e-b70f-50bf8c8eaae7",
    "metadata": {},
    "outputs": [
@@ -198,7 +222,7 @@
        "9875"
       ]
      },
-     "execution_count": 10,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -208,7 +232,7 @@
     "\n",
     "retriever.search_type = SearchType.mmr\n",
     "\n",
-    "len(retriever.get_relevant_documents(\"justice breyer\")[0].page_content)"
+    "len(retriever.invoke(\"justice breyer\")[0].page_content)"
    ]
   },
   {
@@ -216,14 +240,37 @@
    "id": "d6a7ae0d",
    "metadata": {},
    "source": [
-    "## Summary\n",
+    "## Associating summaries with a document for retrieval\n",
     "\n",
-    "Oftentimes a summary may be able to distill more accurately what a chunk is about, leading to better retrieval. Here we show how to create summaries, and then embed those."
+    "A summary may be able to distill more accurately what a chunk is about, leading to better retrieval. Here we show how to create summaries, and then embed those.\n",
+    "\n",
+    "We construct a simple [chain](/docs/how_to/sequence) that will receive an input [Document](https://api.python.langchain.com/en/latest/documents/langchain_core.documents.base.Document.html) object and generate a summary using a LLM.\n",
+    "\n",
+    "```{=mdx}\n",
+    "import ChatModelTabs from \"@theme/ChatModelTabs\";\n",
+    "\n",
+    "<ChatModelTabs customVarName=\"llm\" />\n",
+    "```"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 8,
+   "id": "6589291f-55bb-4e9a-b4ff-08f2506ed641",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# | output: false\n",
+    "# | echo: false\n",
+    "\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "llm = ChatOpenAI()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
    "id": "1433dff4",
    "metadata": {},
    "outputs": [],
@@ -233,27 +280,26 @@
     "from langchain_core.documents import Document\n",
     "from langchain_core.output_parsers import StrOutputParser\n",
     "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_openai import ChatOpenAI"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "35b30390",
-   "metadata": {},
-   "outputs": [],
-   "source": [
+    "\n",
     "chain = (\n",
     "    {\"doc\": lambda x: x.page_content}\n",
     "    | ChatPromptTemplate.from_template(\"Summarize the following document:\\n\\n{doc}\")\n",
-    "    | ChatOpenAI(max_retries=0)\n",
+    "    | llm\n",
     "    | StrOutputParser()\n",
     ")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "3faa9fde-1b09-4849-a815-8b2e89c30a02",
+   "metadata": {},
+   "source": [
+    "Note that we can [batch](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.Runnable.html#langchain_core.runnables.base.Runnable) the chain accross documents:"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 10,
    "id": "41a2a738",
    "metadata": {},
    "outputs": [],
@@ -261,9 +307,17 @@
     "summaries = chain.batch(docs, {\"max_concurrency\": 5})"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "73ef599e-140b-4905-8b62-6c52cdde1852",
+   "metadata": {},
+   "source": [
+    "We can then initialize a `MultiVectorRetriever` as before, indexing the summaries in our vector store, and retaining the original documents in our document store:"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 11,
    "id": "7ac5e4b1",
    "metadata": {},
    "outputs": [],
@@ -279,29 +333,13 @@
     "    byte_store=store,\n",
     "    id_key=id_key,\n",
     ")\n",
-    "doc_ids = [str(uuid.uuid4()) for _ in docs]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "0d93309f",
-   "metadata": {},
-   "outputs": [],
-   "source": [
+    "doc_ids = [str(uuid.uuid4()) for _ in docs]\n",
+    "\n",
     "summary_docs = [\n",
     "    Document(page_content=s, metadata={id_key: doc_ids[i]})\n",
     "    for i, s in enumerate(summaries)\n",
-    "]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "id": "6d5edf0d",
-   "metadata": {},
-   "outputs": [],
-   "source": [
+    "]\n",
+    "\n",
     "retriever.vectorstore.add_documents(summary_docs)\n",
     "retriever.docstore.mset(list(zip(doc_ids, docs)))"
    ]
@@ -320,50 +358,48 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 18,
-   "id": "299232d6",
+   "cell_type": "markdown",
+   "id": "f0274892-29c1-4616-9040-d23f9d537526",
    "metadata": {},
-   "outputs": [],
    "source": [
-    "sub_docs = vectorstore.similarity_search(\"justice breyer\")"
+    "Querying the vector store will return summaries:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
-   "id": "10e404c0",
+   "execution_count": 12,
+   "id": "299232d6",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "Document(page_content=\"The document is a speech given by President Biden addressing various issues and outlining his agenda for the nation. He highlights the importance of nominating a Supreme Court justice and introduces his nominee, Judge Ketanji Brown Jackson. He emphasizes the need to secure the border and reform the immigration system, including providing a pathway to citizenship for Dreamers and essential workers. The President also discusses the protection of women's rights, including access to healthcare and the right to choose. He calls for the passage of the Equality Act to protect LGBTQ+ rights. Additionally, President Biden discusses the need to address the opioid epidemic, improve mental health services, support veterans, and fight against cancer. He expresses optimism for the future of America and the strength of the American people.\", metadata={'doc_id': '56345bff-3ead-418c-a4ff-dff203f77474'})"
+       "Document(page_content=\"President Biden recently nominated Judge Ketanji Brown Jackson to serve on the United States Supreme Court, emphasizing her qualifications and broad support. The President also outlined a plan to secure the border, fix the immigration system, protect women's rights, support LGBTQ+ Americans, and advance mental health services. He highlighted the importance of bipartisan unity in passing legislation, such as the Violence Against Women Act. The President also addressed supporting veterans, particularly those impacted by exposure to burn pits, and announced plans to expand benefits for veterans with respiratory cancers. Additionally, he proposed a plan to end cancer as we know it through the Cancer Moonshot initiative. President Biden expressed optimism about the future of America and emphasized the strength of the American people in overcoming challenges.\", metadata={'doc_id': '84015b1b-980e-400a-94d8-cf95d7e079bd'})"
       ]
      },
-     "execution_count": 19,
+     "execution_count": 12,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
+    "sub_docs = retriever.vectorstore.similarity_search(\"justice breyer\")\n",
+    "\n",
     "sub_docs[0]"
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 20,
-   "id": "e4cce5c2",
+   "cell_type": "markdown",
+   "id": "e4f77ac5-2926-4f60-aad5-b2067900dff9",
    "metadata": {},
-   "outputs": [],
    "source": [
-    "retrieved_docs = retriever.get_relevant_documents(\"justice breyer\")"
+    "Whereas the retriever will return the larger source document:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
-   "id": "c8570dbb",
+   "execution_count": 13,
+   "id": "e4cce5c2",
    "metadata": {},
    "outputs": [
     {
@@ -372,12 +408,14 @@
        "9194"
       ]
      },
-     "execution_count": 21,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
+    "retrieved_docs = retriever.invoke(\"justice breyer\")\n",
+    "\n",
     "len(retrieved_docs[0].page_content)"
    ]
   },
@@ -388,42 +426,28 @@
    "source": [
     "## Hypothetical Queries\n",
     "\n",
-    "An LLM can also be used to generate a list of hypothetical questions that could be asked of a particular document. These questions can then be embedded"
+    "An LLM can also be used to generate a list of hypothetical questions that could be asked of a particular document, which might bear close semantic similarity to relevant queries in a [RAG](/docs/tutorials/rag) application. These questions can then be embedded and associated with the documents to improve retrieval.\n",
+    "\n",
+    "Below, we use the [with_structured_output](/docs/how_to/structured_output/) method to structure the LLM output into a list of strings."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
-   "id": "5219b085",
+   "execution_count": 16,
+   "id": "03d85234-c33a-4a43-861d-47328e1ec2ea",
    "metadata": {},
    "outputs": [],
    "source": [
-    "functions = [\n",
-    "    {\n",
-    "        \"name\": \"hypothetical_questions\",\n",
-    "        \"description\": \"Generate hypothetical questions\",\n",
-    "        \"parameters\": {\n",
-    "            \"type\": \"object\",\n",
-    "            \"properties\": {\n",
-    "                \"questions\": {\n",
-    "                    \"type\": \"array\",\n",
-    "                    \"items\": {\"type\": \"string\"},\n",
-    "                },\n",
-    "            },\n",
-    "            \"required\": [\"questions\"],\n",
-    "        },\n",
-    "    }\n",
-    "]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 23,
-   "id": "523deb92",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.output_parsers.openai_functions import JsonKeyOutputFunctionsParser\n",
+    "from typing import List\n",
+    "\n",
+    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
+    "\n",
+    "\n",
+    "class HypotheticalQuestions(BaseModel):\n",
+    "    \"\"\"Generate hypothetical questions.\"\"\"\n",
+    "\n",
+    "    questions: List[str] = Field(..., description=\"List of questions\")\n",
+    "\n",
     "\n",
     "chain = (\n",
     "    {\"doc\": lambda x: x.page_content}\n",
@@ -431,28 +455,36 @@
     "    | ChatPromptTemplate.from_template(\n",
     "        \"Generate a list of exactly 3 hypothetical questions that the below document could be used to answer:\\n\\n{doc}\"\n",
     "    )\n",
-    "    | ChatOpenAI(max_retries=0, model=\"gpt-4\").bind(\n",
-    "        functions=functions, function_call={\"name\": \"hypothetical_questions\"}\n",
+    "    | ChatOpenAI(max_retries=0, model=\"gpt-4o\").with_structured_output(\n",
+    "        HypotheticalQuestions\n",
     "    )\n",
-    "    | JsonKeyOutputFunctionsParser(key_name=\"questions\")\n",
+    "    | (lambda x: x.questions)\n",
     ")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "6dddc40f-62af-413c-b944-f94a5e1f2f4e",
+   "metadata": {},
+   "source": [
+    "Invoking the chain on a single document demonstrates that it outputs a list of questions:"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 17,
    "id": "11d30554",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[\"What was the author's first experience with programming like?\",\n",
-       " 'Why did the author switch their focus from AI to Lisp during their graduate studies?',\n",
-       " 'What led the author to contemplate a career in art instead of computer science?']"
+       "[\"What impact did the IBM 1401 have on the author's early programming experiences?\",\n",
+       " \"How did the transition from using the IBM 1401 to microcomputers influence the author's programming journey?\",\n",
+       " \"What role did Lisp play in shaping the author's understanding and approach to AI?\"]"
       ]
      },
-     "execution_count": 24,
+     "execution_count": 17,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -462,22 +494,24 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 25,
-   "id": "3eb2e48c",
+   "cell_type": "markdown",
+   "id": "dcffc572-7b20-4b77-857a-90ec360a8f7e",
    "metadata": {},
-   "outputs": [],
    "source": [
-    "hypothetical_questions = chain.batch(docs, {\"max_concurrency\": 5})"
+    "We can batch then batch the chain over all documents and assemble our vector store and document store as before:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 18,
    "id": "b2cd6e75",
    "metadata": {},
    "outputs": [],
    "source": [
+    "# Batch chain over documents to generate hypothetical questions\n",
+    "hypothetical_questions = chain.batch(docs, {\"max_concurrency\": 5})\n",
+    "\n",
+    "\n",
     "# The vectorstore to use to index the child chunks\n",
     "vectorstore = Chroma(\n",
     "    collection_name=\"hypo-questions\", embedding_function=OpenAIEmbeddings()\n",
@@ -491,82 +525,67 @@
     "    byte_store=store,\n",
     "    id_key=id_key,\n",
     ")\n",
-    "doc_ids = [str(uuid.uuid4()) for _ in docs]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 27,
-   "id": "18831b3b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
+    "doc_ids = [str(uuid.uuid4()) for _ in docs]\n",
+    "\n",
+    "\n",
+    "# Generate Document objects from hypothetical questions\n",
     "question_docs = []\n",
     "for i, question_list in enumerate(hypothetical_questions):\n",
     "    question_docs.extend(\n",
     "        [Document(page_content=s, metadata={id_key: doc_ids[i]}) for s in question_list]\n",
-    "    )"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 28,
-   "id": "224b24c5",
-   "metadata": {},
-   "outputs": [],
-   "source": [
+    "    )\n",
+    "\n",
+    "\n",
     "retriever.vectorstore.add_documents(question_docs)\n",
     "retriever.docstore.mset(list(zip(doc_ids, docs)))"
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 29,
-   "id": "7b442b90",
+   "cell_type": "markdown",
+   "id": "75cba8ab-a06f-4545-85fc-cf49d0204b5e",
    "metadata": {},
-   "outputs": [],
    "source": [
-    "sub_docs = vectorstore.similarity_search(\"justice breyer\")"
+    "Note that querying the underlying vector store will retrieve hypothetical questions that are semantically similar to the input query:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
-   "id": "089b5ad0",
+   "execution_count": 19,
+   "id": "7b442b90",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[Document(page_content='Who has been nominated to serve on the United States Supreme Court?', metadata={'doc_id': '0b3a349e-c936-4e77-9c40-0a39fc3e07f0'}),\n",
-       " Document(page_content=\"What was the context and content of Robert Morris' advice to the document's author in 2010?\", metadata={'doc_id': 'b2b2cdca-988a-4af1-ba47-46170770bc8c'}),\n",
-       " Document(page_content='How did personal circumstances influence the decision to pass on the leadership of Y Combinator?', metadata={'doc_id': 'b2b2cdca-988a-4af1-ba47-46170770bc8c'}),\n",
-       " Document(page_content='What were the reasons for the author leaving Yahoo in the summer of 1999?', metadata={'doc_id': 'ce4f4981-ca60-4f56-86f0-89466de62325'})]"
+       "[Document(page_content='What might be the potential benefits of nominating Circuit Court of Appeals Judge Ketanji Brown Jackson to the United States Supreme Court?', metadata={'doc_id': '43292b74-d1b8-4200-8a8b-ea0cb57fbcdb'}),\n",
+       " Document(page_content='How might the Bipartisan Infrastructure Law impact the economic competition between the U.S. and China?', metadata={'doc_id': '66174780-d00c-4166-9791-f0069846e734'}),\n",
+       " Document(page_content='What factors led to the creation of Y Combinator?', metadata={'doc_id': '72003c4e-4cc9-4f09-a787-0b541a65b38c'}),\n",
+       " Document(page_content='How did the ability to publish essays online change the landscape for writers and thinkers?', metadata={'doc_id': 'e8d2c648-f245-4bcc-b8d3-14e64a164b64'})]"
       ]
      },
-     "execution_count": 30,
+     "execution_count": 19,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
+    "sub_docs = retriever.vectorstore.similarity_search(\"justice breyer\")\n",
+    "\n",
     "sub_docs"
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 31,
-   "id": "7594b24e",
+   "cell_type": "markdown",
+   "id": "63c32e43-5f4a-463b-a0c2-2101986f70e6",
    "metadata": {},
-   "outputs": [],
    "source": [
-    "retrieved_docs = retriever.get_relevant_documents(\"justice breyer\")"
+    "And invoking the retriever will return the corresponding document:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
-   "id": "4c120c65",
+   "execution_count": 20,
+   "id": "7594b24e",
    "metadata": {},
    "outputs": [
     {
@@ -575,22 +594,15 @@
        "9194"
       ]
      },
-     "execution_count": 32,
+     "execution_count": 20,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
+    "retrieved_docs = retriever.invoke(\"justice breyer\")\n",
     "len(retrieved_docs[0].page_content)"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "005072b8",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
@@ -609,7 +621,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.1"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/how_to/multimodal_inputs.ipynb

@@ -220,7 +220,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.4"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/docs/how_to/multimodal_prompts.ipynb

@@ -52,7 +52,12 @@
     "        (\"system\", \"Describe the image provided\"),\n",
     "        (\n",
     "            \"user\",\n",
-    "            [{\"type\": \"image_url\", \"image_url\": \"data:image/jpeg;base64,{image_data}\"}],\n",
+    "            [\n",
+    "                {\n",
+    "                    \"type\": \"image_url\",\n",
+    "                    \"image_url\": {\"url\": \"data:image/jpeg;base64,{image_data}\"},\n",
+    "                }\n",
+    "            ],\n",
     "        ),\n",
     "    ]\n",
     ")"
@@ -110,11 +115,11 @@
     "            [\n",
     "                {\n",
     "                    \"type\": \"image_url\",\n",
-    "                    \"image_url\": \"data:image/jpeg;base64,{image_data1}\",\n",
+    "                    \"image_url\": {\"url\": \"data:image/jpeg;base64,{image_data1}\"},\n",
     "                },\n",
     "                {\n",
     "                    \"type\": \"image_url\",\n",
-    "                    \"image_url\": \"data:image/jpeg;base64,{image_data2}\",\n",
+    "                    \"image_url\": {\"url\": \"data:image/jpeg;base64,{image_data2}\"},\n",
     "                },\n",
     "            ],\n",
     "        ),\n",

docs/docs/how_to/output_parser_structured.ipynb

@@ -94,7 +94,7 @@
    "source": [
     "## LCEL\n",
     "\n",
-    "Output parsers implement the [Runnable interface](/docs/concepts#interface), the basic building block of the [LangChain Expression Language (LCEL)](/docs/concepts#langchain-expression-language). This means they support `invoke`, `ainvoke`, `stream`, `astream`, `batch`, `abatch`, `astream_log` calls.\n",
+    "Output parsers implement the [Runnable interface](/docs/concepts#interface), the basic building block of the [LangChain Expression Language (LCEL)](/docs/concepts#langchain-expression-language-lcel). This means they support `invoke`, `ainvoke`, `stream`, `astream`, `batch`, `abatch`, `astream_log` calls.\n",
     "\n",
     "Output parsers accept a string or `BaseMessage` as input and can return an arbitrary type."
    ]

docs/docs/how_to/pydantic_compatibility.md

@@ -0,0 +1,107 @@
+# 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
+
+## LangChain Pydantic migration plan
+
+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).
+
+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.
+
+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 langchain_core.tools import BaseTool
+
+class CustomTool(BaseTool): # BaseTool is v1 code
+    x: int = Field(default=1)
+
+    def _run(*args, **kwargs):
+        return "hello"
+
+    @validator('x') # v1 code
+    @classmethod
+    def validate_x(cls, x: int) -> int:
+        return 1
+    
+
+CustomTool(
+    name='custom_tool',
+    description="hello",
+    x=1,
+)
+```
+
+Mixing Pydantic v2 primitives with Pydantic v1 primitives can raise cryptic errors
+
+**NO** 
+
+```python
+from pydantic import Field, field_validator # pydantic v2
+from langchain_core.tools import BaseTool
+
+class CustomTool(BaseTool): # BaseTool is v1 code
+    x: int = Field(default=1)
+
+    def _run(*args, **kwargs):
+        return "hello"
+
+    @field_validator('x') # v2 code
+    @classmethod
+    def validate_x(cls, x: int) -> int:
+        return 1
+    
+
+CustomTool( 
+    name='custom_tool',
+    description="hello",
+    x=1,
+)
+```
+
+**Example 2: Passing objects to LangChain**
+
+**YES**
+
+```python
+from langchain_core.tools import Tool
+from pydantic.v1 import BaseModel, Field # <-- Uses v1 namespace
+
+class CalculatorInput(BaseModel):
+    question: str = Field()
+
+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
+)
+```
+
+**NO**
+
+```python
+from langchain_core.tools import Tool
+from pydantic import BaseModel, Field # <-- Uses v2 namespace
+
+class CalculatorInput(BaseModel):
+    question: str = Field()
+
+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
+)
+```

docs/docs/how_to/qa_chat_history_how_to.ipynb

@@ -36,12 +36,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "id": "ede7fdc0-ef31-483d-bd67-32e4b5c5d527",
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet  langchain langchain-community langchainhub langchain-chroma bs4"
+    "%%capture --no-stderr\n",
+    "%pip install --upgrade --quiet  langchain langchain-community langchain-chroma bs4"
    ]
   },
   {
@@ -54,7 +55,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "id": "143787ca-d8e6-4dc9-8281-4374f4d71720",
    "metadata": {},
    "outputs": [],
@@ -62,7 +63,8 @@
     "import getpass\n",
     "import os\n",
     "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass()\n",
+    "if not os.environ.get(\"OPENAI_API_KEY\"):\n",
+    "    os.environ[\"OPENAI_API_KEY\"] = getpass.getpass()\n",
     "\n",
     "# import dotenv\n",
     "\n",
@@ -83,13 +85,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "id": "07411adb-3722-4f65-ab7f-8f6f57663d11",
    "metadata": {},
    "outputs": [],
    "source": [
     "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass()"
+    "if not os.environ.get(\"LANGCHAIN_API_KEY\"):\n",
+    "    os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass()"
    ]
   },
   {
@@ -126,7 +129,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 4,
    "id": "cb58f273-2111-4a9b-8932-9b64c95030c8",
    "metadata": {},
    "outputs": [],
@@ -157,13 +160,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 5,
    "id": "820244ae-74b4-4593-b392-822979dd91b8",
    "metadata": {},
    "outputs": [],
    "source": [
     "import bs4\n",
-    "from langchain import hub\n",
     "from langchain.chains import create_retrieval_chain\n",
     "from langchain.chains.combine_documents import create_stuff_documents_chain\n",
     "from langchain_chroma import Chroma\n",
@@ -202,7 +204,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 6,
    "id": "2b685428-8b82-4af1-be4f-7232c5d55b73",
    "metadata": {},
    "outputs": [],
@@ -239,7 +241,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 7,
    "id": "4c4b1695-6217-4ee8-abaf-7cc26366d988",
    "metadata": {},
    "outputs": [],
@@ -265,7 +267,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 8,
    "id": "afef4385-f571-4874-8f52-3d475642f579",
    "metadata": {},
    "outputs": [],
@@ -314,7 +316,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 9,
    "id": "9c3fb176-8d6a-4dc7-8408-6a22c5f7cc72",
    "metadata": {},
    "outputs": [],
@@ -343,17 +345,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 10,
    "id": "1046c92f-21b3-4214-907d-92878d8cba23",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "'Task decomposition involves breaking down a complex task into smaller and simpler steps to make it more manageable and easier to accomplish. This process can be done using techniques like Chain of Thought (CoT) or Tree of Thoughts to guide the model in thinking step by step or exploring multiple reasoning possibilities at each step. Task decomposition can be facilitated by providing simple prompts to a language model, task-specific instructions, or human inputs.'"
+       "'Task decomposition involves breaking down a complex task into smaller and simpler steps to make it more manageable and easier to accomplish. This process can be done using techniques like Chain of Thought (CoT) or Tree of Thoughts to guide the model in breaking down tasks effectively. Task decomposition can be facilitated by providing simple prompts to a language model, task-specific instructions, or human inputs.'"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -369,17 +371,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 11,
    "id": "0e89c75f-7ad7-4331-a2fe-57579eb8f840",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "'Task decomposition can be achieved through various methods, including using techniques like Chain of Thought (CoT) or Tree of Thoughts to guide the model in breaking down complex tasks into smaller steps. Common ways of task decomposition include providing simple prompts to a language model, task-specific instructions tailored to the specific task at hand, or incorporating human inputs to guide the decomposition process effectively.'"
+       "'Task decomposition can be achieved through various methods, including using techniques like Chain of Thought (CoT) or Tree of Thoughts to guide the model in breaking down tasks effectively. Common ways of task decomposition include providing simple prompts to a language model, task-specific instructions, or human inputs to break down complex tasks into smaller and more manageable steps. Additionally, task decomposition can involve utilizing resources like internet access for information gathering, long-term memory management, and GPT-3.5 powered agents for delegation of simple tasks.'"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -401,7 +403,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 12,
    "id": "7686b874-3a85-499f-82b5-28a85c4c768c",
    "metadata": {},
    "outputs": [
@@ -411,11 +413,11 @@
      "text": [
       "User: What is Task Decomposition?\n",
       "\n",
-      "AI: Task decomposition involves breaking down a complex task into smaller and simpler steps to make it more manageable and easier to accomplish. This process can be done using techniques like Chain of Thought (CoT) or Tree of Thoughts to guide the model in thinking step by step or exploring multiple reasoning possibilities at each step. Task decomposition can be facilitated by providing simple prompts to a language model, task-specific instructions, or human inputs.\n",
+      "AI: Task decomposition involves breaking down a complex task into smaller and simpler steps to make it more manageable and easier to accomplish. This process can be done using techniques like Chain of Thought (CoT) or Tree of Thoughts to guide the model in breaking down tasks effectively. Task decomposition can be facilitated by providing simple prompts to a language model, task-specific instructions, or human inputs.\n",
       "\n",
       "User: What are common ways of doing it?\n",
       "\n",
-      "AI: Task decomposition can be achieved through various methods, including using techniques like Chain of Thought (CoT) or Tree of Thoughts to guide the model in breaking down complex tasks into smaller steps. Common ways of task decomposition include providing simple prompts to a language model, task-specific instructions tailored to the specific task at hand, or incorporating human inputs to guide the decomposition process effectively.\n",
+      "AI: Task decomposition can be achieved through various methods, including using techniques like Chain of Thought (CoT) or Tree of Thoughts to guide the model in breaking down tasks effectively. Common ways of task decomposition include providing simple prompts to a language model, task-specific instructions, or human inputs to break down complex tasks into smaller and more manageable steps. Additionally, task decomposition can involve utilizing resources like internet access for information gathering, long-term memory management, and GPT-3.5 powered agents for delegation of simple tasks.\n",
       "\n"
      ]
     }
@@ -452,7 +454,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 13,
    "id": "71c32048-1a41-465f-a9e2-c4affc332fd9",
    "metadata": {},
    "outputs": [],
@@ -552,17 +554,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 14,
    "id": "6d0a7a73-d151-47d9-9e99-b4f3291c0322",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "'Task decomposition involves breaking down a complex task into smaller and simpler steps to make it more manageable. This process helps agents or models tackle difficult tasks by dividing them into more easily achievable subgoals. Task decomposition can be done through techniques like Chain of Thought or Tree of Thoughts, which guide the model in thinking step by step or exploring multiple reasoning possibilities at each step.'"
+       "'Task decomposition involves breaking down a complex task into smaller and simpler steps to make it more manageable. Techniques like Chain of Thought (CoT) and Tree of Thoughts help in decomposing hard tasks into multiple manageable tasks by instructing models to think step by step and explore multiple reasoning possibilities at each step. Task decomposition can be achieved through various methods such as using prompting techniques, task-specific instructions, or human inputs.'"
       ]
      },
-     "execution_count": 2,
+     "execution_count": 14,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -578,17 +580,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 15,
    "id": "17021822-896a-4513-a17d-1d20b1c5381c",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "\"Common ways of task decomposition include using techniques like Chain of Thought (CoT) or Tree of Thoughts to guide models in breaking down complex tasks into smaller steps. This can be achieved through simple prompting with LLMs, task-specific instructions, or human inputs to help the model understand and navigate the task effectively. Task decomposition aims to enhance model performance on complex tasks by utilizing more test-time computation and shedding light on the model's thinking process.\""
+       "'Task decomposition can be done in common ways such as using prompting techniques like Chain of Thought (CoT) or Tree of Thoughts, which instruct models to think step by step and explore multiple reasoning possibilities at each step. Another way is to provide task-specific instructions, such as asking to \"Write a story outline\" for writing a novel, to guide the decomposition process. Additionally, task decomposition can also involve human inputs to break down complex tasks into smaller and simpler steps.'"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 15,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -618,7 +620,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 16,
    "id": "809cc747-2135-40a2-8e73-e4556343ee64",
    "metadata": {},
    "outputs": [],
@@ -646,14 +648,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 17,
    "id": "1726d151-4653-4c72-a187-a14840add526",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langgraph.prebuilt import chat_agent_executor\n",
+    "from langgraph.prebuilt import create_react_agent\n",
     "\n",
-    "agent_executor = chat_agent_executor.create_tool_calling_executor(llm, tools)"
+    "agent_executor = create_react_agent(llm, tools)"
    ]
   },
   {
@@ -666,19 +668,26 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 18,
    "id": "52ae46d9-43f7-481b-96d5-df750be3ad65",
    "metadata": {},
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Error in LangChainTracer.on_tool_end callback: TracerException(\"Found chain run at ID 5cd28d13-88dd-4eac-a465-3770ac27eff6, but expected {'tool'} run.\")\n"
+     ]
+    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_wxRrUmNbaNny8wh9JIb5uCRB', 'function': {'arguments': '{\"query\":\"Task Decomposition\"}', 'name': 'blog_post_retriever'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 19, 'prompt_tokens': 68, 'total_tokens': 87}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_3b956da36b', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-57ee0d12-6142-4957-a002-cce0093efe07-0', tool_calls=[{'name': 'blog_post_retriever', 'args': {'query': 'Task Decomposition'}, 'id': 'call_wxRrUmNbaNny8wh9JIb5uCRB'}])]}}\n",
+      "{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_TbhPPPN05GKi36HLeaN4QM90', 'function': {'arguments': '{\"query\":\"Task Decomposition\"}', 'name': 'blog_post_retriever'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 19, 'prompt_tokens': 68, 'total_tokens': 87}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': None, 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-2e60d910-879a-4a2a-b1e9-6a6c5c7d7ebc-0', tool_calls=[{'name': 'blog_post_retriever', 'args': {'query': 'Task Decomposition'}, 'id': 'call_TbhPPPN05GKi36HLeaN4QM90'}])]}}\n",
       "----\n",
-      "{'action': {'messages': [ToolMessage(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\\nTree 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\\n(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\\nFig. 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:', name='blog_post_retriever', id='9c3a17f7-653c-47fa-b4e4-fa3d8d24c85d', tool_call_id='call_wxRrUmNbaNny8wh9JIb5uCRB')]}}\n",
+      "{'tools': {'messages': [ToolMessage(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\\nFig. 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\\nTree 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\\nTree 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.', name='blog_post_retriever', tool_call_id='call_TbhPPPN05GKi36HLeaN4QM90')]}}\n",
       "----\n",
-      "{'agent': {'messages': [AIMessage(content='Task decomposition is a technique used to break down complex tasks into smaller and simpler steps. This approach helps agents in planning and executing tasks more effectively. One common method for task decomposition is the Chain of Thought (CoT) technique, where models are instructed to think step by step to decompose hard tasks into manageable steps. Another extension of CoT is the Tree of Thoughts, which explores multiple reasoning possibilities at each step by creating a tree structure of thought steps.\\n\\nTask decomposition can be achieved through various methods, such as using language models with simple prompting, task-specific instructions, or human inputs. By breaking down tasks into smaller components, agents can better plan and execute tasks efficiently.\\n\\nIf you would like more detailed information or examples on task decomposition, feel free to ask!', response_metadata={'token_usage': {'completion_tokens': 154, 'prompt_tokens': 588, 'total_tokens': 742}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_3b956da36b', 'finish_reason': 'stop', 'logprobs': None}, id='run-8991fa20-c527-4f9e-a058-fc6264fe6259-0')]}}\n",
+      "{'agent': {'messages': [AIMessage(content='Task decomposition is a technique used to break down complex tasks into smaller and simpler steps. This approach helps in transforming big tasks into multiple manageable tasks, making it easier for autonomous agents to handle and interpret the thinking process. One common method for task decomposition is the Chain of Thought (CoT) technique, where models are instructed to \"think step by step\" to decompose hard tasks. Another extension of CoT is the Tree of Thoughts, which explores multiple reasoning possibilities at each step by creating a tree structure of multiple thoughts per step. Task decomposition can be facilitated through various methods such as using simple prompts, task-specific instructions, or human inputs.', response_metadata={'token_usage': {'completion_tokens': 130, 'prompt_tokens': 636, 'total_tokens': 766}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-3ef17638-65df-4030-a7fe-795e6da91c69-0')]}}\n",
       "----\n"
      ]
     }
@@ -707,7 +716,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 19,
    "id": "837a401e-9757-4d0e-a0da-24fa097d887e",
    "metadata": {},
    "outputs": [],
@@ -716,9 +725,7 @@
     "\n",
     "memory = SqliteSaver.from_conn_string(\":memory:\")\n",
     "\n",
-    "agent_executor = chat_agent_executor.create_tool_calling_executor(\n",
-    "    llm, tools, checkpointer=memory\n",
-    ")"
+    "agent_executor = create_react_agent(llm, tools, checkpointer=memory)"
    ]
   },
   {
@@ -733,7 +740,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 20,
    "id": "d6d70833-b958-4cd7-9e27-29c1c08bb1b8",
    "metadata": {},
    "outputs": [
@@ -741,7 +748,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'agent': {'messages': [AIMessage(content='Hello Bob! How can I assist you today?', response_metadata={'token_usage': {'completion_tokens': 11, 'prompt_tokens': 67, 'total_tokens': 78}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_3b956da36b', 'finish_reason': 'stop', 'logprobs': None}, id='run-1451e59b-b135-4776-985d-4759338ffee5-0')]}}\n",
+      "{'agent': {'messages': [AIMessage(content='Hello Bob! How can I assist you today?', response_metadata={'token_usage': {'completion_tokens': 11, 'prompt_tokens': 67, 'total_tokens': 78}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-1cd17562-18aa-4839-b41b-403b17a0fc20-0')]}}\n",
       "----\n"
      ]
     }
@@ -766,19 +773,26 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 21,
    "id": "e2c570ae-dd91-402c-8693-ae746de63b16",
    "metadata": {},
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Error in LangChainTracer.on_tool_end callback: TracerException(\"Found chain run at ID c54381c0-c5d9-495a-91a0-aca4ae755663, but expected {'tool'} run.\")\n"
+     ]
+    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_ab2x4iUPSWDAHS5txL7PspSK', 'function': {'arguments': '{\"query\":\"Task Decomposition\"}', 'name': 'blog_post_retriever'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 19, 'prompt_tokens': 91, 'total_tokens': 110}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_3b956da36b', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-f76b5813-b41c-4d0d-9ed2-667b988d885e-0', tool_calls=[{'name': 'blog_post_retriever', 'args': {'query': 'Task Decomposition'}, 'id': 'call_ab2x4iUPSWDAHS5txL7PspSK'}])]}}\n",
+      "{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_rg7zKTE5e0ICxVSslJ1u9LMg', 'function': {'arguments': '{\"query\":\"Task Decomposition\"}', 'name': 'blog_post_retriever'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 19, 'prompt_tokens': 91, 'total_tokens': 110}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': None, 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-122bf097-7ff1-49aa-b430-e362b51354ad-0', tool_calls=[{'name': 'blog_post_retriever', 'args': {'query': 'Task Decomposition'}, 'id': 'call_rg7zKTE5e0ICxVSslJ1u9LMg'}])]}}\n",
       "----\n",
-      "{'action': {'messages': [ToolMessage(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\\nTree 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\\n(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\\nFig. 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:', name='blog_post_retriever', id='e0895fa5-5d41-4be0-98db-10a83d42fc2f', tool_call_id='call_ab2x4iUPSWDAHS5txL7PspSK')]}}\n",
+      "{'tools': {'messages': [ToolMessage(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\\nFig. 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\\nTree 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\\nTree 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.', name='blog_post_retriever', tool_call_id='call_rg7zKTE5e0ICxVSslJ1u9LMg')]}}\n",
       "----\n",
-      "{'agent': {'messages': [AIMessage(content='Task decomposition is a technique used in complex tasks where the task is broken down into smaller and simpler steps. This approach helps in managing and solving difficult tasks by dividing them into more manageable components. One common method for task decomposition is the Chain of Thought (CoT) technique, which prompts the model to think step by step and decompose hard tasks into smaller steps. Another extension of CoT is the Tree of Thoughts, which explores multiple reasoning possibilities at each step by creating a tree structure of thought steps.\\n\\nTask decomposition can be achieved through various methods, such as using language models with simple prompting, task-specific instructions, or human inputs. By breaking down tasks into smaller components, agents can better plan and execute complex tasks effectively.\\n\\nIf you would like more detailed information or examples related to task decomposition, feel free to ask!', response_metadata={'token_usage': {'completion_tokens': 165, 'prompt_tokens': 611, 'total_tokens': 776}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_3b956da36b', 'finish_reason': 'stop', 'logprobs': None}, id='run-13296566-8577-4d65-982b-a39718988ca3-0')]}}\n",
+      "{'agent': {'messages': [AIMessage(content='Task decomposition is a technique used to break down complex tasks into smaller and simpler steps. This approach helps in managing and solving intricate problems by dividing them into more manageable components. By decomposing tasks, agents or models can better understand the steps involved and plan their actions accordingly. Techniques like Chain of Thought (CoT) and Tree of Thoughts are examples of methods that enhance model performance on complex tasks by breaking them down into smaller steps.', response_metadata={'token_usage': {'completion_tokens': 87, 'prompt_tokens': 659, 'total_tokens': 746}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-b9166386-83e5-4b82-9a4b-590e5fa76671-0')]}}\n",
       "----\n"
      ]
     }
@@ -805,7 +819,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 22,
    "id": "570d8c68-136e-4ba5-969a-03ba195f6118",
    "metadata": {},
    "outputs": [
@@ -813,11 +827,24 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_KvoiamnLfGEzMeEMlV3u0TJ7', 'function': {'arguments': '{\"query\":\"common ways of task decomposition\"}', 'name': 'blog_post_retriever'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 21, 'prompt_tokens': 930, 'total_tokens': 951}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_3b956da36b', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-dd842071-6dbd-4b68-8657-892eaca58638-0', tool_calls=[{'name': 'blog_post_retriever', 'args': {'query': 'common ways of task decomposition'}, 'id': 'call_KvoiamnLfGEzMeEMlV3u0TJ7'}])]}}\n",
+      "{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_6kbxTU5CDWLmF9mrvR7bWSkI', 'function': {'arguments': '{\"query\":\"Common ways of task decomposition\"}', 'name': 'blog_post_retriever'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 21, 'prompt_tokens': 769, 'total_tokens': 790}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': None, 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-2d2c8327-35cd-484a-b8fd-52436657c2d8-0', tool_calls=[{'name': 'blog_post_retriever', 'args': {'query': 'Common ways of task decomposition'}, 'id': 'call_6kbxTU5CDWLmF9mrvR7bWSkI'}])]}}\n",
+      "----\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Error in LangChainTracer.on_tool_end callback: TracerException(\"Found chain run at ID 29553415-e0f4-41a9-8921-ba489e377f68, but expected {'tool'} run.\")\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'tools': {'messages': [ToolMessage(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\\nFig. 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\\nTree 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\\nTree 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.', name='blog_post_retriever', tool_call_id='call_6kbxTU5CDWLmF9mrvR7bWSkI')]}}\n",
       "----\n",
-      "{'action': {'messages': [ToolMessage(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\\nFig. 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\\nResources:\\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\\n(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.', name='blog_post_retriever', id='c749bb8e-c8e0-4fa3-bc11-3e2e0651880b', tool_call_id='call_KvoiamnLfGEzMeEMlV3u0TJ7')]}}\n",
-      "----\n",
-      "{'agent': {'messages': [AIMessage(content='According to the blog post, common ways of task decomposition include:\\n\\n1. Using language models with simple prompting like \"Steps for XYZ\" or \"What are the subgoals for achieving XYZ?\"\\n2. Utilizing task-specific instructions, for example, using \"Write a story outline\" for writing a novel.\\n3. Involving human inputs in the task decomposition process.\\n\\nThese methods help in breaking down complex tasks into smaller and more manageable steps, facilitating better planning and execution of the overall task.', response_metadata={'token_usage': {'completion_tokens': 100, 'prompt_tokens': 1475, 'total_tokens': 1575}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_3b956da36b', 'finish_reason': 'stop', 'logprobs': None}, id='run-98b765b3-f1a6-4c9a-ad0f-2db7950b900f-0')]}}\n",
+      "{'agent': {'messages': [AIMessage(content='Common ways of task decomposition include:\\n1. Using LLM with simple prompting like \"Steps for XYZ\" or \"What are the subgoals for achieving XYZ?\"\\n2. Using task-specific instructions, for example, \"Write a story outline\" for writing a novel.\\n3. Involving human inputs in the task decomposition process.', response_metadata={'token_usage': {'completion_tokens': 67, 'prompt_tokens': 1339, 'total_tokens': 1406}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-9ad14cde-ca75-4238-a868-f865e0fc50dd-0')]}}\n",
       "----\n"
      ]
     }
@@ -852,20 +879,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 23,
    "id": "b1d2b4d4-e604-497d-873d-d345b808578e",
    "metadata": {},
    "outputs": [],
    "source": [
     "import bs4\n",
-    "from langchain.agents import AgentExecutor, create_tool_calling_agent\n",
     "from langchain.tools.retriever import create_retriever_tool\n",
     "from langchain_chroma import Chroma\n",
-    "from langchain_community.chat_message_histories import ChatMessageHistory\n",
     "from langchain_community.document_loaders import WebBaseLoader\n",
-    "from langchain_core.chat_history import BaseChatMessageHistory\n",
-    "from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
-    "from langchain_core.runnables.history import RunnableWithMessageHistory\n",
     "from langchain_openai import ChatOpenAI, OpenAIEmbeddings\n",
     "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
     "from langgraph.checkpoint.sqlite import SqliteSaver\n",
@@ -900,9 +922,7 @@
     "tools = [tool]\n",
     "\n",
     "\n",
-    "agent_executor = chat_agent_executor.create_tool_calling_executor(\n",
-    "    llm, tools, checkpointer=memory\n",
-    ")"
+    "agent_executor = create_react_agent(llm, tools, checkpointer=memory)"
    ]
   },
   {
@@ -941,7 +961,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.11.2"
   }
  },
  "nbformat": 4,

docs/docs/how_to/qa_sources.ipynb

@@ -14,7 +14,7 @@
     "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) implementation, to show the operating principle."
+    "2. Using a simple [LCEL](/docs/concepts#langchain-expression-language-lcel) implementation, to show the operating principle."
    ]
   },
   {

docs/docs/how_to/recursive_text_splitter.ipynb

@@ -1,5 +1,19 @@
 {
  "cells": [
+  {
+   "cell_type": "raw",
+   "id": "52976910",
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
+   "source": [
+    "---\n",
+    "keywords: [recursivecharactertextsplitter]\n",
+    "---"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "a678d550",

docs/docs/how_to/routing.ipynb

@@ -323,7 +323,7 @@
    "id": "fa0f589d",
    "metadata": {},
    "source": [
-    "# Routing by semantic similarity\n",
+    "## Routing by semantic similarity\n",
     "\n",
     "One especially useful technique is to use embeddings to route a query to the most relevant prompt. Here's an example."
    ]
@@ -371,7 +371,7 @@
     "chain = (\n",
     "    {\"query\": RunnablePassthrough()}\n",
     "    | RunnableLambda(prompt_router)\n",
-    "    | ChatAnthropic(model_name=\"claude-3-haiku-20240307\")\n",
+    "    | ChatAnthropic(model=\"claude-3-haiku-20240307\")\n",
     "    | StrOutputParser()\n",
     ")"
    ]

docs/docs/how_to/semantic-chunker.ipynb

@@ -297,13 +297,67 @@
     "print(len(docs))"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "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",
    "execution_count": null,
    "id": "b1f65472",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "text_splitter = SemanticChunker(\n",
+    "    OpenAIEmbeddings(), breakpoint_threshold_type=\"gradient\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Madam Speaker, Madam Vice President, our First Lady and Second Gentleman.\n"
+     ]
+    }
+   ],
+   "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,
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "26\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(len(docs))"
+   ],
+   "metadata": {},
+   "id": "a407cd57f02a0db4"
   }
  ],
  "metadata": {

docs/docs/how_to/sequence.ipynb

@@ -2,11 +2,14 @@
  "cells": [
   {
    "cell_type": "raw",
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
    "source": [
     "---\n",
-    "sidebar_position: 0\n",
-    "keywords: [Runnable, Runnables, LCEL]\n",
+    "keywords: [Runnable, Runnables, RunnableSequence, LCEL, chain, chains, chaining]\n",
     "---"
    ]
   },
@@ -250,8 +253,7 @@
    "source": [
     "## Related\n",
     "\n",
-    "- [Streaming](/docs/how_to/streaming/): Check out the streaming guide to understand the streaming behavior of a chain\n",
-    "- "
+    "- [Streaming](/docs/how_to/streaming/): Check out the streaming guide to understand the streaming behavior of a chain\n"
    ]
   }
  ],

docs/docs/how_to/serialization.ipynb

@@ -0,0 +1,305 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "ab3dc782-321e-4503-96ee-ac88a15e4b5e",
+   "metadata": {},
+   "source": [
+    "# How to save and load LangChain objects\n",
+    "\n",
+    "LangChain classes implement standard methods for serialization. Serializing LangChain objects using these methods confer some advantages:\n",
+    "\n",
+    "- Secrets, such as API keys, are separated from other parameters and can be loaded back to the object on de-serialization;\n",
+    "- De-serialization is kept compatible across package versions, so objects that were serialized with one version of LangChain can be properly de-serialized with another.\n",
+    "\n",
+    "To save and load LangChain objects using this system, use the `dumpd`, `dumps`, `load`, and `loads` functions in the [load module](https://api.python.langchain.com/en/latest/core_api_reference.html#module-langchain_core.load) of `langchain-core`. These functions support JSON and JSON-serializable objects.\n",
+    "\n",
+    "All LangChain objects that inherit from [Serializable](https://api.python.langchain.com/en/latest/load/langchain_core.load.serializable.Serializable.html) are JSON-serializable. Examples include [messages](https://api.python.langchain.com/en/latest/core_api_reference.html#module-langchain_core.messages), [document objects](https://api.python.langchain.com/en/latest/documents/langchain_core.documents.base.Document.html) (e.g., as returned from [retrievers](/docs/concepts/#retrievers)), and most [Runnables](/docs/concepts/#langchain-expression-language-lcel), such as chat models, retrievers, and [chains](/docs/how_to/sequence) implemented with the LangChain Expression Language.\n",
+    "\n",
+    "Below we walk through an example with a simple [LLM chain](/docs/tutorials/llm_chain).\n",
+    "\n",
+    ":::{.callout-caution}\n",
+    "\n",
+    "De-serialization using `load` and `loads` can instantiate any serializable LangChain object. Only use this feature with trusted inputs!\n",
+    "\n",
+    "De-serialization is a beta feature and is subject to change.\n",
+    ":::"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "f85d9e51-2a36-4f69-83b1-c716cd43f790",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.load import dumpd, dumps, load, loads\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\"system\", \"Translate the following into {language}:\"),\n",
+    "        (\"user\", \"{text}\"),\n",
+    "    ],\n",
+    ")\n",
+    "\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", api_key=\"llm-api-key\")\n",
+    "\n",
+    "chain = prompt | llm"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "356ea99f-5cb5-4433-9a6c-2443d2be9ed3",
+   "metadata": {},
+   "source": [
+    "## Saving objects\n",
+    "\n",
+    "### To json"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "26516764-d46b-4357-a6c6-bd8315bfa530",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{\n",
+      "  \"lc\": 1,\n",
+      "  \"type\": \"constructor\",\n",
+      "  \"id\": [\n",
+      "    \"langchain\",\n",
+      "    \"schema\",\n",
+      "    \"runnable\",\n",
+      "    \"RunnableSequence\"\n",
+      "  ],\n",
+      "  \"kwargs\": {\n",
+      "    \"first\": {\n",
+      "      \"lc\": 1,\n",
+      "      \"type\": \"constructor\",\n",
+      "      \"id\": [\n",
+      "        \"langchain\",\n",
+      "        \"prompts\",\n",
+      "        \"chat\",\n",
+      "        \"ChatPromptTemplate\"\n",
+      "      ],\n",
+      "      \"kwargs\": {\n",
+      "        \"input_variables\": [\n",
+      "          \"language\",\n",
+      "          \"text\"\n",
+      "        ],\n",
+      "        \"messages\": [\n",
+      "          {\n",
+      "            \"lc\": 1,\n",
+      "            \"type\": \"constructor\",\n",
+      "         \n"
+     ]
+    }
+   ],
+   "source": [
+    "string_representation = dumps(chain, pretty=True)\n",
+    "print(string_representation[:500])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "bd425716-545d-466b-a4e5-dc9952cfd72a",
+   "metadata": {},
+   "source": [
+    "### To a json-serializable Python dict"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "6561a968-1741-4419-8c29-e705b9d0ef39",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'dict'>\n"
+     ]
+    }
+   ],
+   "source": [
+    "dict_representation = dumpd(chain)\n",
+    "\n",
+    "print(type(dict_representation))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "711e986e-dd24-4839-9e38-c57903378a5f",
+   "metadata": {},
+   "source": [
+    "### To disk"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "f818378b-f4d6-43a7-895b-76cf7359b157",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "\n",
+    "with open(\"/tmp/chain.json\", \"w\") as fp:\n",
+    "    json.dump(string_representation, fp)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1e621a32-ff5f-4627-ad59-88cacba73c6b",
+   "metadata": {},
+   "source": [
+    "Note that the API key is withheld from the serialized representations. Parameters that are considered secret are specified by the `.lc_secrets` attribute of the LangChain object:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "8225e150-000a-4fbc-9f3d-09568f4b560b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'openai_api_key': 'OPENAI_API_KEY'}"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.last.lc_secrets"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6d090177-eb1c-4bfb-8c13-29286afe17d9",
+   "metadata": {},
+   "source": [
+    "## Loading objects\n",
+    "\n",
+    "Specifying `secrets_map` in `load` and `loads` will load the corresponding secrets onto the de-serialized LangChain object.\n",
+    "\n",
+    "### From string"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "54a66267-5f3a-40a2-bfcc-8b44bb24c154",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = loads(string_representation, secrets_map={\"OPENAI_API_KEY\": \"llm-api-key\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5ed9aff1-92cc-44ba-b2ec-4d12f924fa03",
+   "metadata": {},
+   "source": [
+    "### From dict"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "76979932-13de-4427-9f88-040fb05a6778",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = load(dict_representation, secrets_map={\"OPENAI_API_KEY\": \"llm-api-key\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7dd81a2a-5163-414d-ab42-f1c35e30471b",
+   "metadata": {},
+   "source": [
+    "### From disk"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "033f62a7-3377-472a-be58-718baa6ab445",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open(\"/tmp/chain.json\", \"r\") as fp:\n",
+    "    chain = loads(json.load(fp), secrets_map={\"OPENAI_API_KEY\": \"llm-api-key\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "dc520fdb-035a-468f-a8a8-c3ffe8ed98eb",
+   "metadata": {},
+   "source": [
+    "Note that we recover the API key specified at the start of the guide:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "566b2475-d9b4-432b-8c3b-27c2f183624e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'llm-api-key'"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.last.openai_api_key.get_secret_value()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7b4cba53-e1d5-4979-927e-b5794a02afc3",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/how_to/sql_csv.ipynb

@@ -351,7 +351,7 @@
    "id": "ab1b2e7c-6ea8-4674-98eb-a43c69f5c19d",
    "metadata": {},
    "source": [
-    "To help enforce proper use of our Python tool, we'll using [tool calling](/docs/how_to/tool_calling/):"
+    "To help enforce proper use of our Python tool, we'll using [tool calling](/docs/how_to/tool_calling):"
    ]
   },
   {

docs/docs/how_to/sql_query_checking.ipynb

@@ -243,7 +243,7 @@
      "text": [
       "================================\u001b[1m System Message \u001b[0m================================\n",
       "\n",
-      "You are a \u001b[33;1m\u001b[1;3m{dialect}\u001b[0m expert. Given an input question, creat a syntactically correct \u001b[33;1m\u001b[1;3m{dialect}\u001b[0m query to run.\n",
+      "You are a \u001b[33;1m\u001b[1;3m{dialect}\u001b[0m expert. Given an input question, create a syntactically correct \u001b[33;1m\u001b[1;3m{dialect}\u001b[0m query to run.\n",
       "Unless the user specifies in the question a specific number of examples to obtain, query for at most \u001b[33;1m\u001b[1;3m{top_k}\u001b[0m results using the LIMIT clause as per \u001b[33;1m\u001b[1;3m{dialect}\u001b[0m. You can order the results to return the most informative data in the database.\n",
       "Never query for all columns from a table. You must query only the columns that are needed to answer the question. Wrap each column name in double quotes (\") to denote them as delimited identifiers.\n",
       "Pay attention to use only the column names you can see in the tables below. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.\n",
@@ -275,7 +275,7 @@
     }
    ],
    "source": [
-    "system = \"\"\"You are a {dialect} expert. Given an input question, creat a syntactically correct {dialect} query to run.\n",
+    "system = \"\"\"You are a {dialect} expert. Given an input question, create a syntactically correct {dialect} query to run.\n",
     "Unless the user specifies in the question a specific number of examples to obtain, query for at most {top_k} results using the LIMIT clause as per {dialect}. You can order the results to return the most informative data in the database.\n",
     "Never query for all columns from a table. You must query only the columns that are needed to answer the question. Wrap each column name in double quotes (\") to denote them as delimited identifiers.\n",
     "Pay attention to use only the column names you can see in the tables below. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.\n",

docs/docs/how_to/streaming.ipynb

@@ -3,10 +3,14 @@
   {
    "cell_type": "raw",
    "id": "0bdb3b97-4989-4237-b43b-5943dbbd8302",
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
    "source": [
     "---\n",
-    "sidebar_position: 1.5\n",
+    "keywords: [stream]\n",
     "---"
    ]
   },
@@ -37,6 +41,10 @@
     "\n",
     "Let's take a look at both approaches, and try to understand how to use them.\n",
     "\n",
+    ":::info\n",
+    "For a higher-level overview of streaming techniques in LangChain, see [this section of the conceptual guide](/docs/concepts/#streaming).\n",
+    ":::\n",
+    "\n",
     "## Using Stream\n",
     "\n",
     "All `Runnable` objects implement a sync method called `stream` and an async variant called `astream`. \n",
@@ -999,7 +1007,7 @@
    "id": "798ea891-997c-454c-bf60-43124f40ee1b",
    "metadata": {},
    "source": [
-    "Because both the model and the parser support streaming, we see sreaming events from both components in real time! Kind of cool isn't it? 🦜"
+    "Because both the model and the parser support streaming, we see streaming events from both components in real time! Kind of cool isn't it? 🦜"
    ]
   },
   {

docs/docs/how_to/structured_output.ipynb

@@ -3,10 +3,15 @@
   {
    "cell_type": "raw",
    "id": "27598444",
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
    "source": [
     "---\n",
     "sidebar_position: 3\n",
+    "keywords: [structured output, json, information extraction, with_structured_output]\n",
     "---"
    ]
   },
@@ -28,6 +33,8 @@
     "\n",
     "## The `.with_structured_output()` method\n",
     "\n",
+    "<span data-heading-keywords=\"with_structured_output\"></span>\n",
+    "\n",
     ":::info Supported models\n",
     "\n",
     "You can find a [list of models that support this method here](/docs/integrations/chat/).\n",
@@ -69,7 +76,7 @@
    "id": "a808a401-be1f-49f9-ad13-58dd68f7db5f",
    "metadata": {},
    "source": [
-    "If we want the model to return a Pydantic object, we just need to pass in desired the Pydantic class:"
+    "If we want the model to return a Pydantic object, we just need to pass in the desired Pydantic class:"
    ]
   },
   {
@@ -243,7 +250,7 @@
    "id": "e28c14d3",
    "metadata": {},
    "source": [
-    "Alternatively, you can use tool calling directly to allow the model to choose between options, if your [chosen model supports it](/docs/integrations/chat/). This involves a bit more parsing and setup but in some instances leads to better performance because you don't have to use nested schemas. See [this how-to guide](/docs/how_to/tool_calling/) for more details."
+    "Alternatively, you can use tool calling directly to allow the model to choose between options, if your [chosen model supports it](/docs/integrations/chat/). This involves a bit more parsing and setup but in some instances leads to better performance because you don't have to use nested schemas. See [this how-to guide](/docs/how_to/tool_calling) for more details."
    ]
   },
   {

docs/docs/how_to/tool_calling.ipynb

@@ -14,14 +14,20 @@
     "\n",
     ":::\n",
     "\n",
-    "```{=mdx}\n",
-    ":::info\n",
+    ":::info Tool calling vs function calling\n",
+    "\n",
     "We use the term tool calling interchangeably with function calling. Although\n",
     "function calling is sometimes meant to refer to invocations of a single function,\n",
     "we treat all models as though they can return multiple tool or function calls in \n",
     "each message.\n",
+    "\n",
+    ":::\n",
+    "\n",
+    ":::info Supported models\n",
+    "\n",
+    "You can find a [list of all models that support tool calling](/docs/integrations/chat/).\n",
+    "\n",
     ":::\n",
-    "```\n",
     "\n",
     "Tool calling allows a chat model to respond to a given prompt by \"calling a tool\".\n",
     "While the name implies that the model is performing \n",
@@ -46,8 +52,13 @@
     "support variants of a tool calling feature.\n",
     "\n",
     "LangChain implements standard interfaces for defining tools, passing them to LLMs, \n",
-    "and representing tool calls. This guide will show you how to use them.\n",
-    "\n",
+    "and representing tool calls. This guide and the other How-to pages in the Tool section will show you how to use tools with LangChain."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
     "## Passing tools to chat models\n",
     "\n",
     "Chat models that support tool calling features implement a `.bind_tools` method, which \n",
@@ -61,7 +72,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -92,7 +103,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -140,9 +151,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 9,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
    "source": [
     "# | output: false\n",
     "# | echo: false\n",
@@ -161,13 +180,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [],
    "source": [
     "llm_with_tools = llm.bind_tools(tools)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "As we can see, even though the prompt didn't really suggest a tool call, our LLM made one since it was forced to do so. You can look at the docs for [`bind_tool`](https://api.python.langchain.com/en/latest/chat_models/langchain_openai.chat_models.base.BaseChatOpenAI.html#langchain_openai.chat_models.base.BaseChatOpenAI.bind_tools) to learn about all the ways to customize how your LLM selects tools."
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -189,7 +215,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -203,9 +229,8 @@
        "  'id': 'call_Fl0hQi4IBTzlpaJYlM5kPQhE'}]"
       ]
      },
-     "execution_count": 5,
      "metadata": {},
-     "output_type": "execute_result"
+     "output_type": "display_data"
     }
    ],
    "source": [
@@ -231,7 +256,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -240,9 +265,8 @@
        "[Multiply(a=3, b=12), Add(a=11, b=49)]"
       ]
      },
-     "execution_count": 6,
      "metadata": {},
-     "output_type": "execute_result"
+     "output_type": "display_data"
     }
    ],
    "source": [
@@ -252,437 +276,21 @@
     "chain.invoke(query)"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Streaming\n",
-    "\n",
-    "When tools are called in a streaming context, \n",
-    "[message chunks](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.ai.AIMessageChunk.html#langchain_core.messages.ai.AIMessageChunk) \n",
-    "will be populated with [tool call chunk](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.tool.ToolCallChunk.html#langchain_core.messages.tool.ToolCallChunk) \n",
-    "objects in a list via the `.tool_call_chunks` attribute. A `ToolCallChunk` includes \n",
-    "optional string fields for the tool `name`, `args`, and `id`, and includes an optional \n",
-    "integer field `index` that can be used to join chunks together. Fields are optional \n",
-    "because portions of a tool call may be streamed across different chunks (e.g., a chunk \n",
-    "that includes a substring of the arguments may have null values for the tool name and id).\n",
-    "\n",
-    "Because message chunks inherit from their parent message class, an \n",
-    "[AIMessageChunk](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.ai.AIMessageChunk.html#langchain_core.messages.ai.AIMessageChunk) \n",
-    "with tool call chunks will also include `.tool_calls` and `.invalid_tool_calls` fields. \n",
-    "These fields are parsed best-effort from the message's tool call chunks.\n",
-    "\n",
-    "Note that not all providers currently support streaming for tool calls:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[]\n",
-      "[{'name': 'Multiply', 'args': '', 'id': 'call_3aQwTP9CYlFxwOvQZPHDu6wL', 'index': 0}]\n",
-      "[{'name': None, 'args': '{\"a\"', 'id': None, 'index': 0}]\n",
-      "[{'name': None, 'args': ': 3, ', 'id': None, 'index': 0}]\n",
-      "[{'name': None, 'args': '\"b\": 1', 'id': None, 'index': 0}]\n",
-      "[{'name': None, 'args': '2}', 'id': None, 'index': 0}]\n",
-      "[{'name': 'Add', 'args': '', 'id': 'call_SQUoSsJz2p9Kx2x73GOgN1ja', 'index': 1}]\n",
-      "[{'name': None, 'args': '{\"a\"', 'id': None, 'index': 1}]\n",
-      "[{'name': None, 'args': ': 11,', 'id': None, 'index': 1}]\n",
-      "[{'name': None, 'args': ' \"b\": ', 'id': None, 'index': 1}]\n",
-      "[{'name': None, 'args': '49}', 'id': None, 'index': 1}]\n",
-      "[]\n"
-     ]
-    }
-   ],
-   "source": [
-    "async for chunk in llm_with_tools.astream(query):\n",
-    "    print(chunk.tool_call_chunks)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Note that adding message chunks will merge their corresponding tool call chunks. This is the principle by which LangChain's various [tool output parsers](/docs/how_to/output_parser_structured) support streaming.\n",
-    "\n",
-    "For example, below we accumulate tool call chunks:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[]\n",
-      "[{'name': 'Multiply', 'args': '', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}]\n",
-      "[{'name': 'Multiply', 'args': '{\"a\"', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}]\n",
-      "[{'name': 'Multiply', 'args': '{\"a\": 3, ', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}]\n",
-      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 1', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}]\n",
-      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}]\n",
-      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}, {'name': 'Add', 'args': '', 'id': 'call_b4iMiB3chGNGqbt5SjqqD2Wh', 'index': 1}]\n",
-      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}, {'name': 'Add', 'args': '{\"a\"', 'id': 'call_b4iMiB3chGNGqbt5SjqqD2Wh', 'index': 1}]\n",
-      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}, {'name': 'Add', 'args': '{\"a\": 11,', 'id': 'call_b4iMiB3chGNGqbt5SjqqD2Wh', 'index': 1}]\n",
-      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}, {'name': 'Add', 'args': '{\"a\": 11, \"b\": ', 'id': 'call_b4iMiB3chGNGqbt5SjqqD2Wh', 'index': 1}]\n",
-      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}, {'name': 'Add', 'args': '{\"a\": 11, \"b\": 49}', 'id': 'call_b4iMiB3chGNGqbt5SjqqD2Wh', 'index': 1}]\n",
-      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}, {'name': 'Add', 'args': '{\"a\": 11, \"b\": 49}', 'id': 'call_b4iMiB3chGNGqbt5SjqqD2Wh', 'index': 1}]\n"
-     ]
-    }
-   ],
-   "source": [
-    "first = True\n",
-    "async for chunk in llm_with_tools.astream(query):\n",
-    "    if first:\n",
-    "        gathered = chunk\n",
-    "        first = False\n",
-    "    else:\n",
-    "        gathered = gathered + chunk\n",
-    "\n",
-    "    print(gathered.tool_call_chunks)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "<class 'str'>\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(type(gathered.tool_call_chunks[0][\"args\"]))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "And below we accumulate tool calls to demonstrate partial parsing:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[]\n",
-      "[]\n",
-      "[{'name': 'Multiply', 'args': {}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}]\n",
-      "[{'name': 'Multiply', 'args': {'a': 3}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}]\n",
-      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 1}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}]\n",
-      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}]\n",
-      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}]\n",
-      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}, {'name': 'Add', 'args': {}, 'id': 'call_54Hx3DGjZitFlEjgMe1DYonh'}]\n",
-      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}, {'name': 'Add', 'args': {'a': 11}, 'id': 'call_54Hx3DGjZitFlEjgMe1DYonh'}]\n",
-      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}, {'name': 'Add', 'args': {'a': 11}, 'id': 'call_54Hx3DGjZitFlEjgMe1DYonh'}]\n",
-      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}, {'name': 'Add', 'args': {'a': 11, 'b': 49}, 'id': 'call_54Hx3DGjZitFlEjgMe1DYonh'}]\n",
-      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}, {'name': 'Add', 'args': {'a': 11, 'b': 49}, 'id': 'call_54Hx3DGjZitFlEjgMe1DYonh'}]\n"
-     ]
-    }
-   ],
-   "source": [
-    "first = True\n",
-    "async for chunk in llm_with_tools.astream(query):\n",
-    "    if first:\n",
-    "        gathered = chunk\n",
-    "        first = False\n",
-    "    else:\n",
-    "        gathered = gathered + chunk\n",
-    "\n",
-    "    print(gathered.tool_calls)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "<class 'dict'>\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(type(gathered.tool_calls[0][\"args\"]))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Passing tool outputs to the model\n",
-    "\n",
-    "If we're using the model-generated tool invocations to actually call tools and want to pass the tool results back to the model, we can do so using `ToolMessage`s."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[HumanMessage(content='What is 3 * 12? Also, what is 11 + 49?'),\n",
-       " AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_svc2GLSxNFALbaCAbSjMI9J8', 'function': {'arguments': '{\"a\": 3, \"b\": 12}', 'name': 'Multiply'}, 'type': 'function'}, {'id': 'call_r8jxte3zW6h3MEGV3zH2qzFh', 'function': {'arguments': '{\"a\": 11, \"b\": 49}', 'name': 'Add'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 50, 'prompt_tokens': 105, 'total_tokens': 155}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_d9767fc5b9', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-a79ad1dd-95f1-4a46-b688-4c83f327a7b3-0', tool_calls=[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_svc2GLSxNFALbaCAbSjMI9J8'}, {'name': 'Add', 'args': {'a': 11, 'b': 49}, 'id': 'call_r8jxte3zW6h3MEGV3zH2qzFh'}]),\n",
-       " ToolMessage(content='36', tool_call_id='call_svc2GLSxNFALbaCAbSjMI9J8'),\n",
-       " ToolMessage(content='60', tool_call_id='call_r8jxte3zW6h3MEGV3zH2qzFh')]"
-      ]
-     },
-     "execution_count": 12,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_core.messages import HumanMessage, ToolMessage\n",
-    "\n",
-    "messages = [HumanMessage(query)]\n",
-    "ai_msg = llm_with_tools.invoke(messages)\n",
-    "messages.append(ai_msg)\n",
-    "for tool_call in ai_msg.tool_calls:\n",
-    "    selected_tool = {\"add\": add, \"multiply\": multiply}[tool_call[\"name\"].lower()]\n",
-    "    tool_output = selected_tool.invoke(tool_call[\"args\"])\n",
-    "    messages.append(ToolMessage(tool_output, tool_call_id=tool_call[\"id\"]))\n",
-    "messages"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='3 * 12 is 36 and 11 + 49 is 60.', response_metadata={'token_usage': {'completion_tokens': 18, 'prompt_tokens': 171, 'total_tokens': 189}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_d9767fc5b9', 'finish_reason': 'stop', 'logprobs': None}, id='run-20b52149-e00d-48ea-97cf-f8de7a255f8c-0')"
-      ]
-     },
-     "execution_count": 13,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "llm_with_tools.invoke(messages)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Note that we pass back the same `id` in the `ToolMessage` as the what we receive from the model in order to help the model match tool responses with tool calls.\n",
-    "\n",
-    "## Few-shot prompting\n",
-    "\n",
-    "For more complex tool use it's very useful to add few-shot examples to the prompt. We can do this by adding `AIMessage`s with `ToolCall`s and corresponding `ToolMessage`s to our prompt.\n",
-    "\n",
-    "For example, even with some special instructions our model can get tripped up by order of operations:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[{'name': 'Multiply',\n",
-       "  'args': {'a': 119, 'b': 8},\n",
-       "  'id': 'call_T88XN6ECucTgbXXkyDeC2CQj'},\n",
-       " {'name': 'Add',\n",
-       "  'args': {'a': 952, 'b': -20},\n",
-       "  'id': 'call_licdlmGsRqzup8rhqJSb1yZ4'}]"
-      ]
-     },
-     "execution_count": 14,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "llm_with_tools.invoke(\n",
-    "    \"Whats 119 times 8 minus 20. Don't do any math yourself, only use tools for math. Respect order of operations\"\n",
-    ").tool_calls"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The model shouldn't be trying to add anything yet, since it technically can't know the results of 119 * 8 yet.\n",
-    "\n",
-    "By adding a prompt with some examples we can correct this behavior:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[{'name': 'Multiply',\n",
-       "  'args': {'a': 119, 'b': 8},\n",
-       "  'id': 'call_9MvuwQqg7dlJupJcoTWiEsDo'}]"
-      ]
-     },
-     "execution_count": 15,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_core.messages import AIMessage\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_core.runnables import RunnablePassthrough\n",
-    "\n",
-    "examples = [\n",
-    "    HumanMessage(\n",
-    "        \"What's the product of 317253 and 128472 plus four\", name=\"example_user\"\n",
-    "    ),\n",
-    "    AIMessage(\n",
-    "        \"\",\n",
-    "        name=\"example_assistant\",\n",
-    "        tool_calls=[\n",
-    "            {\"name\": \"Multiply\", \"args\": {\"x\": 317253, \"y\": 128472}, \"id\": \"1\"}\n",
-    "        ],\n",
-    "    ),\n",
-    "    ToolMessage(\"16505054784\", tool_call_id=\"1\"),\n",
-    "    AIMessage(\n",
-    "        \"\",\n",
-    "        name=\"example_assistant\",\n",
-    "        tool_calls=[{\"name\": \"Add\", \"args\": {\"x\": 16505054784, \"y\": 4}, \"id\": \"2\"}],\n",
-    "    ),\n",
-    "    ToolMessage(\"16505054788\", tool_call_id=\"2\"),\n",
-    "    AIMessage(\n",
-    "        \"The product of 317253 and 128472 plus four is 16505054788\",\n",
-    "        name=\"example_assistant\",\n",
-    "    ),\n",
-    "]\n",
-    "\n",
-    "system = \"\"\"You are bad at math but are an expert at using a calculator. \n",
-    "\n",
-    "Use past tool usage as an example of how to correctly use the tools.\"\"\"\n",
-    "few_shot_prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\"system\", system),\n",
-    "        *examples,\n",
-    "        (\"human\", \"{query}\"),\n",
-    "    ]\n",
-    ")\n",
-    "\n",
-    "chain = {\"query\": RunnablePassthrough()} | few_shot_prompt | llm_with_tools\n",
-    "chain.invoke(\"Whats 119 times 8 minus 20\").tool_calls"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "And we get the correct output this time.\n",
-    "\n",
-    "Here's what the [LangSmith trace](https://smith.langchain.com/public/f70550a1-585f-4c9d-a643-13148ab1616f/r) looks like."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Binding model-specific formats (advanced)\n",
-    "\n",
-    "Providers adopt different conventions for formatting tool schemas. \n",
-    "For instance, OpenAI uses a format like this:\n",
-    "\n",
-    "- `type`: The type of the tool. At the time of writing, this is always `\"function\"`.\n",
-    "- `function`: An object containing tool parameters.\n",
-    "- `function.name`: The name of the schema to output.\n",
-    "- `function.description`: A high level description of the schema to output.\n",
-    "- `function.parameters`: The nested details of the schema you want to extract, formatted as a [JSON schema](https://json-schema.org/) dict.\n",
-    "\n",
-    "We can bind this model-specific format directly to the model as well if preferred. Here's an example:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_mn4ELw1NbuE0DFYhIeK0GrPe', 'function': {'arguments': '{\"a\":119,\"b\":8}', 'name': 'multiply'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 17, 'prompt_tokens': 62, 'total_tokens': 79}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_c2295e73ad', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-353e8a9a-7125-4f94-8c68-4f3da4c21120-0', tool_calls=[{'name': 'multiply', 'args': {'a': 119, 'b': 8}, 'id': 'call_mn4ELw1NbuE0DFYhIeK0GrPe'}])"
-      ]
-     },
-     "execution_count": 18,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "model = ChatOpenAI()\n",
-    "\n",
-    "model_with_tools = model.bind(\n",
-    "    tools=[\n",
-    "        {\n",
-    "            \"type\": \"function\",\n",
-    "            \"function\": {\n",
-    "                \"name\": \"multiply\",\n",
-    "                \"description\": \"Multiply two integers together.\",\n",
-    "                \"parameters\": {\n",
-    "                    \"type\": \"object\",\n",
-    "                    \"properties\": {\n",
-    "                        \"a\": {\"type\": \"number\", \"description\": \"First integer\"},\n",
-    "                        \"b\": {\"type\": \"number\", \"description\": \"Second integer\"},\n",
-    "                    },\n",
-    "                    \"required\": [\"a\", \"b\"],\n",
-    "                },\n",
-    "            },\n",
-    "        }\n",
-    "    ]\n",
-    ")\n",
-    "\n",
-    "model_with_tools.invoke(\"Whats 119 times 8?\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "This is functionally equivalent to the `bind_tools()` calls above."
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
     "## Next steps\n",
     "\n",
-    "Now you've learned how to bind tool schemas to a chat model and to call those tools. Next, check out some more specific uses of tool calling:\n",
+    "Now you've learned how to bind tool schemas to a chat model and to call those tools. Next, you can learn more about how to use tools:\n",
+    "\n",
+    "- Few shot promting [with tools](/docs/how_to/tools_few_shot/)\n",
+    "- Stream [tool calls](/docs/how_to/tool_streaming/)\n",
+    "- Bind [model-specific tools](/docs/how_to/tools_model_specific/)\n",
+    "- Pass [runtime values to tools](/docs/how_to/tool_runtime)\n",
+    "- Pass [tool results back to model](/docs/how_to/tool_results_pass_to_model)\n",
+    "\n",
+    "You can also check out some more specific uses of tool calling:\n",
     "\n",
     "- Building [tool-using chains and agents](/docs/how_to#tools)\n",
     "- Getting [structured outputs](/docs/how_to/structured_output/) from models"
@@ -690,24 +298,10 @@
   }
  ],
  "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"
+   "name": "python"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 4
+ "nbformat_minor": 2
 }

docs/docs/how_to/tool_calling_parallel.ipynb

@@ -0,0 +1,108 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Disabling parallel tool calling (OpenAI only)\n",
+    "\n",
+    "OpenAI tool calling performs tool calling in parallel by default. That means that if we ask a question like \"What is the weather in Tokyo, New York, and Chicago?\" and we have a tool for getting the weather, it will call the tool 3 times in parallel. We can force it to call only a single tool once by using the ``parallel_tool_call`` parameter."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "First let's set up our tools and model:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.tools import tool\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def add(a: int, b: int) -> int:\n",
+    "    \"\"\"Adds a and b.\"\"\"\n",
+    "    return a + b\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def multiply(a: int, b: int) -> int:\n",
+    "    \"\"\"Multiplies a and b.\"\"\"\n",
+    "    return a * b\n",
+    "\n",
+    "\n",
+    "tools = [add, multiply]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from getpass import getpass\n",
+    "\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = getpass()\n",
+    "\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Now let's show a quick example of how disabling parallel tool calls work:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'name': 'add',\n",
+       "  'args': {'a': 2, 'b': 2},\n",
+       "  'id': 'call_Hh4JOTCDM85Sm9Pr84VKrWu5'}]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "llm_with_tools = llm.bind_tools(tools, parallel_tool_calls=False)\n",
+    "llm_with_tools.invoke(\"Please call the first tool two times\").tool_calls"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "As we can see, even though we explicitly told the model to call a tool twice, by disabling parallel tool calls the model was constrained to only calling one."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/docs/how_to/tool_choice.ipynb

@@ -0,0 +1,126 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# How to force tool calling behavior\n",
+    "\n",
+    "In order to force our LLM to spelect a specific tool, we can use the `tool_choice` parameter to ensure certain behavior. First, let's define our model and tools:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.tools import tool\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def add(a: int, b: int) -> int:\n",
+    "    \"\"\"Adds a and b.\"\"\"\n",
+    "    return a + b\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def multiply(a: int, b: int) -> int:\n",
+    "    \"\"\"Multiplies a and b.\"\"\"\n",
+    "    return a * b\n",
+    "\n",
+    "\n",
+    "tools = [add, multiply]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# | output: false\n",
+    "# | echo: false\n",
+    "\n",
+    "%pip install -qU langchain langchain_openai\n",
+    "\n",
+    "import os\n",
+    "from getpass import getpass\n",
+    "\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = getpass()\n",
+    "\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "For example, we can force our tool to call the multiply tool by using the following code:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_9cViskmLvPnHjXk9tbVla5HA', 'function': {'arguments': '{\"a\":2,\"b\":4}', 'name': 'Multiply'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 9, 'prompt_tokens': 103, 'total_tokens': 112}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-095b827e-2bdd-43bb-8897-c843f4504883-0', tool_calls=[{'name': 'Multiply', 'args': {'a': 2, 'b': 4}, 'id': 'call_9cViskmLvPnHjXk9tbVla5HA'}], usage_metadata={'input_tokens': 103, 'output_tokens': 9, 'total_tokens': 112})"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "llm_forced_to_multiply = llm.bind_tools(tools, tool_choice=\"Multiply\")\n",
+    "llm_forced_to_multiply.invoke(\"what is 2 + 4\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Even if we pass it something that doesn't require multiplcation - it will still call the tool!"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We can also just force our tool to select at least one of our tools by passing in the \"any\" (or \"required\" which is OpenAI specific) keyword to the `tool_choice` parameter."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_mCSiJntCwHJUBfaHZVUB2D8W', 'function': {'arguments': '{\"a\":1,\"b\":2}', 'name': 'Add'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 15, 'prompt_tokens': 94, 'total_tokens': 109}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-28f75260-9900-4bed-8cd3-f1579abb65e5-0', tool_calls=[{'name': 'Add', 'args': {'a': 1, 'b': 2}, 'id': 'call_mCSiJntCwHJUBfaHZVUB2D8W'}], usage_metadata={'input_tokens': 94, 'output_tokens': 15, 'total_tokens': 109})"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "llm_forced_to_use_tool = llm.bind_tools(tools, tool_choice=\"any\")\n",
+    "llm_forced_to_use_tool.invoke(\"What day is today?\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/docs/how_to/tool_results_pass_to_model.ipynb

@@ -0,0 +1,127 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# How to pass tool outputs to the model\n",
+    "\n",
+    "If we're using the model-generated tool invocations to actually call tools and want to pass the tool results back to the model, we can do so using `ToolMessage`s. First, let's define our tools and our model."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.tools import tool\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def add(a: int, b: int) -> int:\n",
+    "    \"\"\"Adds a and b.\"\"\"\n",
+    "    return a + b\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def multiply(a: int, b: int) -> int:\n",
+    "    \"\"\"Multiplies a and b.\"\"\"\n",
+    "    return a * b\n",
+    "\n",
+    "\n",
+    "tools = [add, multiply]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from getpass import getpass\n",
+    "\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = getpass()\n",
+    "\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n",
+    "llm_with_tools = llm.bind_tools(tools)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Now we can use ``ToolMessage`` to pass back the output of the tool calls to the model."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[HumanMessage(content='What is 3 * 12? Also, what is 11 + 49?'),\n",
+       " AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_svc2GLSxNFALbaCAbSjMI9J8', 'function': {'arguments': '{\"a\": 3, \"b\": 12}', 'name': 'Multiply'}, 'type': 'function'}, {'id': 'call_r8jxte3zW6h3MEGV3zH2qzFh', 'function': {'arguments': '{\"a\": 11, \"b\": 49}', 'name': 'Add'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 50, 'prompt_tokens': 105, 'total_tokens': 155}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_d9767fc5b9', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-a79ad1dd-95f1-4a46-b688-4c83f327a7b3-0', tool_calls=[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_svc2GLSxNFALbaCAbSjMI9J8'}, {'name': 'Add', 'args': {'a': 11, 'b': 49}, 'id': 'call_r8jxte3zW6h3MEGV3zH2qzFh'}]),\n",
+       " ToolMessage(content='36', tool_call_id='call_svc2GLSxNFALbaCAbSjMI9J8'),\n",
+       " ToolMessage(content='60', tool_call_id='call_r8jxte3zW6h3MEGV3zH2qzFh')]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from langchain_core.messages import HumanMessage, ToolMessage\n",
+    "\n",
+    "query = \"What is 3 * 12? Also, what is 11 + 49?\"\n",
+    "\n",
+    "messages = [HumanMessage(query)]\n",
+    "ai_msg = llm_with_tools.invoke(messages)\n",
+    "messages.append(ai_msg)\n",
+    "for tool_call in ai_msg.tool_calls:\n",
+    "    selected_tool = {\"add\": add, \"multiply\": multiply}[tool_call[\"name\"].lower()]\n",
+    "    tool_output = selected_tool.invoke(tool_call[\"args\"])\n",
+    "    messages.append(ToolMessage(tool_output, tool_call_id=tool_call[\"id\"]))\n",
+    "messages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='3 * 12 is 36 and 11 + 49 is 60.', response_metadata={'token_usage': {'completion_tokens': 18, 'prompt_tokens': 171, 'total_tokens': 189}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_d9767fc5b9', 'finish_reason': 'stop', 'logprobs': None}, id='run-20b52149-e00d-48ea-97cf-f8de7a255f8c-0')"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "llm_with_tools.invoke(messages)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Note that we pass back the same `id` in the `ToolMessage` as the what we receive from the model in order to help the model match tool responses with tool calls."
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/docs/how_to/tool_runtime.ipynb

@@ -0,0 +1,256 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# How to pass run time values to a tool\n",
+    "\n",
+    ":::info Prerequisites\n",
+    "\n",
+    "This guide assumes familiarity with the following concepts:\n",
+    "- [Chat models](/docs/concepts/#chat-models)\n",
+    "- [LangChain Tools](/docs/concepts/#tools)\n",
+    "- [How to create tools](/docs/how_to/custom_tools)\n",
+    "- [How to use a model to call tools](https://python.langchain.com/v0.2/docs/how_to/tool_calling)\n",
+    ":::\n",
+    "\n",
+    ":::{.callout-info} Supported models\n",
+    "\n",
+    "This how-to guide uses models with native tool calling capability.\n",
+    "You can find a [list of all models that support tool calling](/docs/integrations/chat/).\n",
+    "\n",
+    ":::\n",
+    "\n",
+    ":::{.callout-info} Using with LangGraph\n",
+    "\n",
+    "If you're using LangGraph, please refer to [this how-to guide](https://langchain-ai.github.io/langgraph/how-tos/pass-run-time-values-to-tools/)\n",
+    "which shows how to create an agent that keeps track of a given user's favorite pets.\n",
+    ":::\n",
+    "\n",
+    "You may need to bind values to a tool that are only known at runtime. For example, the tool logic may require using the ID of the user who made the request.\n",
+    "\n",
+    "Most of the time, such values should not be controlled by the LLM. In fact, allowing the LLM to control the user ID may lead to a security risk.\n",
+    "\n",
+    "Instead, the LLM should only control the parameters of the tool that are meant to be controlled by the LLM, while other parameters (such as user ID) should be fixed by the application logic.\n",
+    "\n",
+    "This how-to guide shows a simple design pattern that creates the tool dynamically at run time and binds to them appropriate values."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We can bind them to chat models as follows:\n",
+    "\n",
+    "```{=mdx}\n",
+    "import ChatModelTabs from \"@theme/ChatModelTabs\";\n",
+    "\n",
+    "<ChatModelTabs\n",
+    "  customVarName=\"llm\"\n",
+    "  fireworksParams={`model=\"accounts/fireworks/models/firefunction-v1\", temperature=0`}\n",
+    "/>\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.2.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.0\u001b[0m\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpython -m pip install --upgrade pip\u001b[0m\n",
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# | output: false\n",
+    "# | echo: false\n",
+    "\n",
+    "%pip install -qU langchain langchain_openai\n",
+    "\n",
+    "import os\n",
+    "from getpass import getpass\n",
+    "\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "if \"OPENAI_API_KEY\" not in os.environ:\n",
+    "    os.environ[\"OPENAI_API_KEY\"] = getpass()\n",
+    "\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Passing request time information\n",
+    "\n",
+    "The idea is to create the tool dynamically at request time, and bind to it the appropriate information. For example,\n",
+    "this information may be the user ID as resolved from the request itself."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from typing import List\n",
+    "\n",
+    "from langchain_core.output_parsers import JsonOutputParser\n",
+    "from langchain_core.tools import BaseTool, tool"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "user_to_pets = {}\n",
+    "\n",
+    "\n",
+    "def generate_tools_for_user(user_id: str) -> List[BaseTool]:\n",
+    "    \"\"\"Generate a set of tools that have a user id associated with them.\"\"\"\n",
+    "\n",
+    "    @tool\n",
+    "    def update_favorite_pets(pets: List[str]) -> None:\n",
+    "        \"\"\"Add the list of favorite pets.\"\"\"\n",
+    "        user_to_pets[user_id] = pets\n",
+    "\n",
+    "    @tool\n",
+    "    def delete_favorite_pets() -> None:\n",
+    "        \"\"\"Delete the list of favorite pets.\"\"\"\n",
+    "        if user_id in user_to_pets:\n",
+    "            del user_to_pets[user_id]\n",
+    "\n",
+    "    @tool\n",
+    "    def list_favorite_pets() -> None:\n",
+    "        \"\"\"List favorite pets if any.\"\"\"\n",
+    "        return user_to_pets.get(user_id, [])\n",
+    "\n",
+    "    return [update_favorite_pets, delete_favorite_pets, list_favorite_pets]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Verify that the tools work correctly"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'eugene': ['cat', 'dog']}\n",
+      "['cat', 'dog']\n"
+     ]
+    }
+   ],
+   "source": [
+    "update_pets, delete_pets, list_pets = generate_tools_for_user(\"eugene\")\n",
+    "update_pets.invoke({\"pets\": [\"cat\", \"dog\"]})\n",
+    "print(user_to_pets)\n",
+    "print(list_pets.invoke({}))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "\n",
+    "\n",
+    "def handle_run_time_request(user_id: str, query: str):\n",
+    "    \"\"\"Handle run time request.\"\"\"\n",
+    "    tools = generate_tools_for_user(user_id)\n",
+    "    llm_with_tools = llm.bind_tools(tools)\n",
+    "    prompt = ChatPromptTemplate.from_messages(\n",
+    "        [(\"system\", \"You are a helpful assistant.\")],\n",
+    "    )\n",
+    "    chain = prompt | llm_with_tools\n",
+    "    return llm_with_tools.invoke(query)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "This code will allow the LLM to invoke the tools, but the LLM is **unaware** of the fact that a **user ID** even exists!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'name': 'update_favorite_pets',\n",
+       "  'args': {'pets': ['cats', 'parrots']},\n",
+       "  'id': 'call_jJvjPXsNbFO5MMgW0q84iqCN'}]"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ai_message = handle_run_time_request(\n",
+    "    \"eugene\", \"my favorite animals are cats and parrots.\"\n",
+    ")\n",
+    "ai_message.tool_calls"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    ":::{.callout-important}\n",
+    "\n",
+    "Chat models only output requests to invoke tools, they don't actually invoke the underlying tools.\n",
+    "\n",
+    "To see how to invoke the tools, please refer to [how to use a model to call tools](https://python.langchain.com/v0.2/docs/how_to/tool_calling).\n",
+    ":::"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

docs/docs/how_to/tool_streaming.ipynb

@@ -0,0 +1,235 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# How to stream tool calls\n",
+    "\n",
+    "When tools are called in a streaming context, \n",
+    "[message chunks](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.ai.AIMessageChunk.html#langchain_core.messages.ai.AIMessageChunk) \n",
+    "will be populated with [tool call chunk](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.tool.ToolCallChunk.html#langchain_core.messages.tool.ToolCallChunk) \n",
+    "objects in a list via the `.tool_call_chunks` attribute. A `ToolCallChunk` includes \n",
+    "optional string fields for the tool `name`, `args`, and `id`, and includes an optional \n",
+    "integer field `index` that can be used to join chunks together. Fields are optional \n",
+    "because portions of a tool call may be streamed across different chunks (e.g., a chunk \n",
+    "that includes a substring of the arguments may have null values for the tool name and id).\n",
+    "\n",
+    "Because message chunks inherit from their parent message class, an \n",
+    "[AIMessageChunk](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.ai.AIMessageChunk.html#langchain_core.messages.ai.AIMessageChunk) \n",
+    "with tool call chunks will also include `.tool_calls` and `.invalid_tool_calls` fields. \n",
+    "These fields are parsed best-effort from the message's tool call chunks.\n",
+    "\n",
+    "Note that not all providers currently support streaming for tool calls. Before we start let's define our tools and our model."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.tools import tool\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def add(a: int, b: int) -> int:\n",
+    "    \"\"\"Adds a and b.\"\"\"\n",
+    "    return a + b\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def multiply(a: int, b: int) -> int:\n",
+    "    \"\"\"Multiplies a and b.\"\"\"\n",
+    "    return a * b\n",
+    "\n",
+    "\n",
+    "tools = [add, multiply]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from getpass import getpass\n",
+    "\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = getpass()\n",
+    "\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n",
+    "llm_with_tools = llm.bind_tools(tools)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Now let's define our query and stream our output:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[]\n",
+      "[{'name': 'Multiply', 'args': '', 'id': 'call_3aQwTP9CYlFxwOvQZPHDu6wL', 'index': 0}]\n",
+      "[{'name': None, 'args': '{\"a\"', 'id': None, 'index': 0}]\n",
+      "[{'name': None, 'args': ': 3, ', 'id': None, 'index': 0}]\n",
+      "[{'name': None, 'args': '\"b\": 1', 'id': None, 'index': 0}]\n",
+      "[{'name': None, 'args': '2}', 'id': None, 'index': 0}]\n",
+      "[{'name': 'Add', 'args': '', 'id': 'call_SQUoSsJz2p9Kx2x73GOgN1ja', 'index': 1}]\n",
+      "[{'name': None, 'args': '{\"a\"', 'id': None, 'index': 1}]\n",
+      "[{'name': None, 'args': ': 11,', 'id': None, 'index': 1}]\n",
+      "[{'name': None, 'args': ' \"b\": ', 'id': None, 'index': 1}]\n",
+      "[{'name': None, 'args': '49}', 'id': None, 'index': 1}]\n",
+      "[]\n"
+     ]
+    }
+   ],
+   "source": [
+    "query = \"What is 3 * 12? Also, what is 11 + 49?\"\n",
+    "\n",
+    "async for chunk in llm_with_tools.astream(query):\n",
+    "    print(chunk.tool_call_chunks)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Note that adding message chunks will merge their corresponding tool call chunks. This is the principle by which LangChain's various [tool output parsers](/docs/how_to/output_parser_structured) support streaming.\n",
+    "\n",
+    "For example, below we accumulate tool call chunks:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[]\n",
+      "[{'name': 'Multiply', 'args': '', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}]\n",
+      "[{'name': 'Multiply', 'args': '{\"a\"', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}]\n",
+      "[{'name': 'Multiply', 'args': '{\"a\": 3, ', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}]\n",
+      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 1', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}]\n",
+      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}]\n",
+      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}, {'name': 'Add', 'args': '', 'id': 'call_b4iMiB3chGNGqbt5SjqqD2Wh', 'index': 1}]\n",
+      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}, {'name': 'Add', 'args': '{\"a\"', 'id': 'call_b4iMiB3chGNGqbt5SjqqD2Wh', 'index': 1}]\n",
+      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}, {'name': 'Add', 'args': '{\"a\": 11,', 'id': 'call_b4iMiB3chGNGqbt5SjqqD2Wh', 'index': 1}]\n",
+      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}, {'name': 'Add', 'args': '{\"a\": 11, \"b\": ', 'id': 'call_b4iMiB3chGNGqbt5SjqqD2Wh', 'index': 1}]\n",
+      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}, {'name': 'Add', 'args': '{\"a\": 11, \"b\": 49}', 'id': 'call_b4iMiB3chGNGqbt5SjqqD2Wh', 'index': 1}]\n",
+      "[{'name': 'Multiply', 'args': '{\"a\": 3, \"b\": 12}', 'id': 'call_AkL3dVeCjjiqvjv8ckLxL3gP', 'index': 0}, {'name': 'Add', 'args': '{\"a\": 11, \"b\": 49}', 'id': 'call_b4iMiB3chGNGqbt5SjqqD2Wh', 'index': 1}]\n"
+     ]
+    }
+   ],
+   "source": [
+    "first = True\n",
+    "async for chunk in llm_with_tools.astream(query):\n",
+    "    if first:\n",
+    "        gathered = chunk\n",
+    "        first = False\n",
+    "    else:\n",
+    "        gathered = gathered + chunk\n",
+    "\n",
+    "    print(gathered.tool_call_chunks)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'str'>\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(type(gathered.tool_call_chunks[0][\"args\"]))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "And below we accumulate tool calls to demonstrate partial parsing:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[]\n",
+      "[]\n",
+      "[{'name': 'Multiply', 'args': {}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}]\n",
+      "[{'name': 'Multiply', 'args': {'a': 3}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}]\n",
+      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 1}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}]\n",
+      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}]\n",
+      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}]\n",
+      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}, {'name': 'Add', 'args': {}, 'id': 'call_54Hx3DGjZitFlEjgMe1DYonh'}]\n",
+      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}, {'name': 'Add', 'args': {'a': 11}, 'id': 'call_54Hx3DGjZitFlEjgMe1DYonh'}]\n",
+      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}, {'name': 'Add', 'args': {'a': 11}, 'id': 'call_54Hx3DGjZitFlEjgMe1DYonh'}]\n",
+      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}, {'name': 'Add', 'args': {'a': 11, 'b': 49}, 'id': 'call_54Hx3DGjZitFlEjgMe1DYonh'}]\n",
+      "[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_4p0D4tHVXSiae9Mu0e8jlI1m'}, {'name': 'Add', 'args': {'a': 11, 'b': 49}, 'id': 'call_54Hx3DGjZitFlEjgMe1DYonh'}]\n"
+     ]
+    }
+   ],
+   "source": [
+    "first = True\n",
+    "async for chunk in llm_with_tools.astream(query):\n",
+    "    if first:\n",
+    "        gathered = chunk\n",
+    "        first = False\n",
+    "    else:\n",
+    "        gathered = gathered + chunk\n",
+    "\n",
+    "    print(gathered.tool_calls)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'dict'>\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(type(gathered.tool_calls[0][\"args\"]))"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/docs/how_to/tools_builtin.ipynb

@@ -36,7 +36,7 @@
     "\n",
     "When using 3rd party tools, make sure that you understand how the tool works, what permissions\n",
     "it has. Read over its documentation and check if anything is required from you\n",
-    "from a security point of view. Please see our [security](https://python.langchain.com/v0.1/docs/security/) \n",
+    "from a security point of view. Please see our [security](https://python.langchain.com/v0.2/docs/security/) \n",
     "guidelines for more information.\n",
     "\n",
     ":::\n",

docs/docs/how_to/tools_few_shot.ipynb

@@ -0,0 +1,175 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# How to use few-shot prompting with tool calling\n",
+    "\n",
+    "For more complex tool use it's very useful to add few-shot examples to the prompt. We can do this by adding `AIMessage`s with `ToolCall`s and corresponding `ToolMessage`s to our prompt.\n",
+    "\n",
+    "First let's define our tools and model."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.tools import tool\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def add(a: int, b: int) -> int:\n",
+    "    \"\"\"Adds a and b.\"\"\"\n",
+    "    return a + b\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def multiply(a: int, b: int) -> int:\n",
+    "    \"\"\"Multiplies a and b.\"\"\"\n",
+    "    return a * b\n",
+    "\n",
+    "\n",
+    "tools = [add, multiply]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from getpass import getpass\n",
+    "\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = getpass()\n",
+    "\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n",
+    "llm_with_tools = llm.bind_tools(tools)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Let's run our model where we can notice that even with some special instructions our model can get tripped up by order of operations. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'name': 'Multiply',\n",
+       "  'args': {'a': 119, 'b': 8},\n",
+       "  'id': 'call_T88XN6ECucTgbXXkyDeC2CQj'},\n",
+       " {'name': 'Add',\n",
+       "  'args': {'a': 952, 'b': -20},\n",
+       "  'id': 'call_licdlmGsRqzup8rhqJSb1yZ4'}]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "llm_with_tools.invoke(\n",
+    "    \"Whats 119 times 8 minus 20. Don't do any math yourself, only use tools for math. Respect order of operations\"\n",
+    ").tool_calls"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The model shouldn't be trying to add anything yet, since it technically can't know the results of 119 * 8 yet.\n",
+    "\n",
+    "By adding a prompt with some examples we can correct this behavior:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'name': 'Multiply',\n",
+       "  'args': {'a': 119, 'b': 8},\n",
+       "  'id': 'call_9MvuwQqg7dlJupJcoTWiEsDo'}]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from langchain_core.messages import AIMessage, HumanMessage, ToolMessage\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_core.runnables import RunnablePassthrough\n",
+    "\n",
+    "examples = [\n",
+    "    HumanMessage(\n",
+    "        \"What's the product of 317253 and 128472 plus four\", name=\"example_user\"\n",
+    "    ),\n",
+    "    AIMessage(\n",
+    "        \"\",\n",
+    "        name=\"example_assistant\",\n",
+    "        tool_calls=[\n",
+    "            {\"name\": \"Multiply\", \"args\": {\"x\": 317253, \"y\": 128472}, \"id\": \"1\"}\n",
+    "        ],\n",
+    "    ),\n",
+    "    ToolMessage(\"16505054784\", tool_call_id=\"1\"),\n",
+    "    AIMessage(\n",
+    "        \"\",\n",
+    "        name=\"example_assistant\",\n",
+    "        tool_calls=[{\"name\": \"Add\", \"args\": {\"x\": 16505054784, \"y\": 4}, \"id\": \"2\"}],\n",
+    "    ),\n",
+    "    ToolMessage(\"16505054788\", tool_call_id=\"2\"),\n",
+    "    AIMessage(\n",
+    "        \"The product of 317253 and 128472 plus four is 16505054788\",\n",
+    "        name=\"example_assistant\",\n",
+    "    ),\n",
+    "]\n",
+    "\n",
+    "system = \"\"\"You are bad at math but are an expert at using a calculator. \n",
+    "\n",
+    "Use past tool usage as an example of how to correctly use the tools.\"\"\"\n",
+    "few_shot_prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\"system\", system),\n",
+    "        *examples,\n",
+    "        (\"human\", \"{query}\"),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "chain = {\"query\": RunnablePassthrough()} | few_shot_prompt | llm_with_tools\n",
+    "chain.invoke(\"Whats 119 times 8 minus 20\").tool_calls"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "And we get the correct output this time.\n",
+    "\n",
+    "Here's what the [LangSmith trace](https://smith.langchain.com/public/f70550a1-585f-4c9d-a643-13148ab1616f/r) looks like."
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/docs/how_to/tools_model_specific.ipynb

@@ -0,0 +1,79 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# How to bind model-specific tools\n",
+    "\n",
+    "Providers adopt different conventions for formatting tool schemas. \n",
+    "For instance, OpenAI uses a format like this:\n",
+    "\n",
+    "- `type`: The type of the tool. At the time of writing, this is always `\"function\"`.\n",
+    "- `function`: An object containing tool parameters.\n",
+    "- `function.name`: The name of the schema to output.\n",
+    "- `function.description`: A high level description of the schema to output.\n",
+    "- `function.parameters`: The nested details of the schema you want to extract, formatted as a [JSON schema](https://json-schema.org/) dict.\n",
+    "\n",
+    "We can bind this model-specific format directly to the model as well if preferred. Here's an example:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_mn4ELw1NbuE0DFYhIeK0GrPe', 'function': {'arguments': '{\"a\":119,\"b\":8}', 'name': 'multiply'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 17, 'prompt_tokens': 62, 'total_tokens': 79}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_c2295e73ad', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-353e8a9a-7125-4f94-8c68-4f3da4c21120-0', tool_calls=[{'name': 'multiply', 'args': {'a': 119, 'b': 8}, 'id': 'call_mn4ELw1NbuE0DFYhIeK0GrPe'}])"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "model = ChatOpenAI()\n",
+    "\n",
+    "model_with_tools = model.bind(\n",
+    "    tools=[\n",
+    "        {\n",
+    "            \"type\": \"function\",\n",
+    "            \"function\": {\n",
+    "                \"name\": \"multiply\",\n",
+    "                \"description\": \"Multiply two integers together.\",\n",
+    "                \"parameters\": {\n",
+    "                    \"type\": \"object\",\n",
+    "                    \"properties\": {\n",
+    "                        \"a\": {\"type\": \"number\", \"description\": \"First integer\"},\n",
+    "                        \"b\": {\"type\": \"number\", \"description\": \"Second integer\"},\n",
+    "                    },\n",
+    "                    \"required\": [\"a\", \"b\"],\n",
+    "                },\n",
+    "            },\n",
+    "        }\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "model_with_tools.invoke(\"Whats 119 times 8?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "This is functionally equivalent to the `bind_tools()` method."
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/docs/how_to/tools_prompting.ipynb

@@ -19,7 +19,7 @@
     "\n",
     ":::{.callout-caution}\n",
     "\n",
-    "Some models have been fine-tuned for tool calling and provide a dedicated API for tool calling. 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 [how to use a chat model to call tools](/docs/how_to/tool_calling/) guide for more information.\n",
+    "Some models have been fine-tuned for tool calling and provide a dedicated API for tool calling. 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 [how to use a chat model to call tools](/docs/how_to/tool_calling) guide for more information.\n",
     "\n",
     ":::\n",
     "\n",
@@ -34,7 +34,7 @@
     "\n",
     ":::\n",
     "\n",
-    "In this guide, we'll see how to add **ad-hoc** tool calling support to a chat model. This is an alternative method to invoke tools if you're using a model that does not natively support [tool calling](/docs/how_to/tool_calling/).\n",
+    "In this guide, we'll see how to add **ad-hoc** tool calling support to a chat model. This is an alternative method to invoke tools if you're using a model that does not natively support [tool calling](/docs/how_to/tool_calling).\n",
     "\n",
     "We'll do this by simply writing a prompt that will get the model to invoke the appropriate tools. Here's a diagram of the logic:\n",
     "\n",
@@ -87,7 +87,7 @@
    "id": "7ec6409b-21e5-4d0a-8a46-c4ef0b055dd3",
    "metadata": {},
    "source": [
-    "You can select any of the given models for this how-to guide. Keep in mind that most of these models already [support native tool calling](/docs/integrations/chat/), so using the prompting strategy shown here doesn't make sense for these models, and instead you should follow the [how to use a chat model to call tools](/docs/how_to/tool_calling/) guide.\n",
+    "You can select any of the given models for this how-to guide. Keep in mind that most of these models already [support native tool calling](/docs/integrations/chat/), so using the prompting strategy shown here doesn't make sense for these models, and instead you should follow the [how to use a chat model to call tools](/docs/how_to/tool_calling) guide.\n",
     "\n",
     "```{=mdx}\n",
     "import ChatModelTabs from \"@theme/ChatModelTabs\";\n",

docs/docs/how_to/trim_messages.ipynb

@@ -0,0 +1,479 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "b5ee5b75-6876-4d62-9ade-5a7a808ae5a2",
+   "metadata": {},
+   "source": [
+    "# How to trim messages\n",
+    "\n",
+    ":::info Prerequisites\n",
+    "\n",
+    "This guide assumes familiarity with the following concepts:\n",
+    "\n",
+    "- [Messages](/docs/concepts/#messages)\n",
+    "- [Chat models](/docs/concepts/#chat-models)\n",
+    "- [Chaining](/docs/how_to/sequence/)\n",
+    "- [Chat history](/docs/concepts/#chat-history)\n",
+    "\n",
+    "The methods in this guide also require `langchain-core>=0.2.9`.\n",
+    "\n",
+    ":::\n",
+    "\n",
+    "All models have finite context windows, meaning there's a limit to how many tokens they can take as input. If you have very long messages or a chain/agent that accumulates a long message is history, you'll need to manage the length of the messages you're passing in to the model.\n",
+    "\n",
+    "The `trim_messages` util provides some basic strategies for trimming a list of messages to be of a certain token length.\n",
+    "\n",
+    "## Getting the last `max_tokens` tokens\n",
+    "\n",
+    "To get the last `max_tokens` in the list of Messages we can set `strategy=\"last\"`. Notice that for our `token_counter` we can pass in a function (more on that below) or a language model (since language models have a message token counting method). It makes sense to pass in a model when you're trimming your messages to fit into the context window of that specific model:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "c974633b-3bd0-4844-8a8f-85e3e25f13fe",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[AIMessage(content=\"Hmmm let me think.\\n\\nWhy, he's probably chasing after the last cup of coffee in the office!\"),\n",
+       " HumanMessage(content='what do you call a speechless parrot')]"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# pip install -U langchain-openai\n",
+    "from langchain_core.messages import (\n",
+    "    AIMessage,\n",
+    "    HumanMessage,\n",
+    "    SystemMessage,\n",
+    "    trim_messages,\n",
+    ")\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "messages = [\n",
+    "    SystemMessage(\"you're a good assistant, you always respond with a joke.\"),\n",
+    "    HumanMessage(\"i wonder why it's called langchain\"),\n",
+    "    AIMessage(\n",
+    "        'Well, I guess they thought \"WordRope\" and \"SentenceString\" just didn\\'t have the same ring to it!'\n",
+    "    ),\n",
+    "    HumanMessage(\"and who is harrison chasing anyways\"),\n",
+    "    AIMessage(\n",
+    "        \"Hmmm let me think.\\n\\nWhy, he's probably chasing after the last cup of coffee in the office!\"\n",
+    "    ),\n",
+    "    HumanMessage(\"what do you call a speechless parrot\"),\n",
+    "]\n",
+    "\n",
+    "trim_messages(\n",
+    "    messages,\n",
+    "    max_tokens=45,\n",
+    "    strategy=\"last\",\n",
+    "    token_counter=ChatOpenAI(model=\"gpt-4o\"),\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d3f46654-c4b2-4136-b995-91c3febe5bf9",
+   "metadata": {},
+   "source": [
+    "If we want to always keep the initial system message we can specify `include_system=True`:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "589b0223-3a73-44ec-8315-2dba3ee6117d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[SystemMessage(content=\"you're a good assistant, you always respond with a joke.\"),\n",
+       " HumanMessage(content='what do you call a speechless parrot')]"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "trim_messages(\n",
+    "    messages,\n",
+    "    max_tokens=45,\n",
+    "    strategy=\"last\",\n",
+    "    token_counter=ChatOpenAI(model=\"gpt-4o\"),\n",
+    "    include_system=True,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8a8b542c-04d1-4515-8d82-b999ea4fac4f",
+   "metadata": {},
+   "source": [
+    "If we want to allow splitting up the contents of a message we can specify `allow_partial=True`:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "8c46a209-dddd-4d01-81f6-f6ae55d3225c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[SystemMessage(content=\"you're a good assistant, you always respond with a joke.\"),\n",
+       " AIMessage(content=\"\\nWhy, he's probably chasing after the last cup of coffee in the office!\"),\n",
+       " HumanMessage(content='what do you call a speechless parrot')]"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "trim_messages(\n",
+    "    messages,\n",
+    "    max_tokens=56,\n",
+    "    strategy=\"last\",\n",
+    "    token_counter=ChatOpenAI(model=\"gpt-4o\"),\n",
+    "    include_system=True,\n",
+    "    allow_partial=True,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "306adf9c-41cd-495c-b4dc-e4f43dd7f8f8",
+   "metadata": {},
+   "source": [
+    "If we need to make sure that our first message (excluding the system message) is always of a specific type, we can specify `start_on`:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "878a730b-fe44-4e9d-ab65-7b8f7b069de8",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[SystemMessage(content=\"you're a good assistant, you always respond with a joke.\"),\n",
+       " HumanMessage(content='what do you call a speechless parrot')]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "trim_messages(\n",
+    "    messages,\n",
+    "    max_tokens=60,\n",
+    "    strategy=\"last\",\n",
+    "    token_counter=ChatOpenAI(model=\"gpt-4o\"),\n",
+    "    include_system=True,\n",
+    "    start_on=\"human\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7f5d391d-235b-4091-b2de-c22866b478f3",
+   "metadata": {},
+   "source": [
+    "## Getting the first `max_tokens` tokens\n",
+    "\n",
+    "We can perform the flipped operation of getting the *first* `max_tokens` by specifying `strategy=\"first\"`:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "5f56ae54-1a39-4019-9351-3b494c003d5b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[SystemMessage(content=\"you're a good assistant, you always respond with a joke.\"),\n",
+       " HumanMessage(content=\"i wonder why it's called langchain\")]"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "trim_messages(\n",
+    "    messages,\n",
+    "    max_tokens=45,\n",
+    "    strategy=\"first\",\n",
+    "    token_counter=ChatOpenAI(model=\"gpt-4o\"),\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ab70bf70-1e5a-4d51-b9b8-a823bf2cf532",
+   "metadata": {},
+   "source": [
+    "## Writing a custom token counter\n",
+    "\n",
+    "We can write a custom token counter function that takes in a list of messages and returns an int."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "1c1c3b1e-2ece-49e7-a3b6-e69877c1633b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[AIMessage(content=\"Hmmm let me think.\\n\\nWhy, he's probably chasing after the last cup of coffee in the office!\"),\n",
+       " HumanMessage(content='what do you call a speechless parrot')]"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from typing import List\n",
+    "\n",
+    "# pip install tiktoken\n",
+    "import tiktoken\n",
+    "from langchain_core.messages import BaseMessage, ToolMessage\n",
+    "\n",
+    "\n",
+    "def str_token_counter(text: str) -> int:\n",
+    "    enc = tiktoken.get_encoding(\"o200k_base\")\n",
+    "    return len(enc.encode(text))\n",
+    "\n",
+    "\n",
+    "def tiktoken_counter(messages: List[BaseMessage]) -> int:\n",
+    "    \"\"\"Approximately reproduce https://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb\n",
+    "\n",
+    "    For simplicity only supports str Message.contents.\n",
+    "    \"\"\"\n",
+    "    num_tokens = 3  # every reply is primed with <|start|>assistant<|message|>\n",
+    "    tokens_per_message = 3\n",
+    "    tokens_per_name = 1\n",
+    "    for msg in messages:\n",
+    "        if isinstance(msg, HumanMessage):\n",
+    "            role = \"user\"\n",
+    "        elif isinstance(msg, AIMessage):\n",
+    "            role = \"assistant\"\n",
+    "        elif isinstance(msg, ToolMessage):\n",
+    "            role = \"tool\"\n",
+    "        elif isinstance(msg, SystemMessage):\n",
+    "            role = \"system\"\n",
+    "        else:\n",
+    "            raise ValueError(f\"Unsupported messages type {msg.__class__}\")\n",
+    "        num_tokens += (\n",
+    "            tokens_per_message\n",
+    "            + str_token_counter(role)\n",
+    "            + str_token_counter(msg.content)\n",
+    "        )\n",
+    "        if msg.name:\n",
+    "            num_tokens += tokens_per_name + str_token_counter(msg.name)\n",
+    "    return num_tokens\n",
+    "\n",
+    "\n",
+    "trim_messages(\n",
+    "    messages,\n",
+    "    max_tokens=45,\n",
+    "    strategy=\"last\",\n",
+    "    token_counter=tiktoken_counter,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4b2a672b-c007-47c5-9105-617944dc0a6a",
+   "metadata": {},
+   "source": [
+    "## Chaining\n",
+    "\n",
+    "`trim_messages` can be used in an imperatively (like above) or declaratively, making it easy to compose with other components in a chain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "96aa29b2-01e0-437c-a1ab-02fb0141cb57",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='A: A \"Polly-gone\"!', response_metadata={'token_usage': {'completion_tokens': 9, 'prompt_tokens': 32, 'total_tokens': 41}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_66b29dffce', 'finish_reason': 'stop', 'logprobs': None}, id='run-83e96ddf-bcaa-4f63-824c-98b0f8a0d474-0', usage_metadata={'input_tokens': 32, 'output_tokens': 9, 'total_tokens': 41})"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "llm = ChatOpenAI(model=\"gpt-4o\")\n",
+    "\n",
+    "# Notice we don't pass in messages. This creates\n",
+    "# a RunnableLambda that takes messages as input\n",
+    "trimmer = trim_messages(\n",
+    "    max_tokens=45,\n",
+    "    strategy=\"last\",\n",
+    "    token_counter=llm,\n",
+    "    include_system=True,\n",
+    ")\n",
+    "\n",
+    "chain = trimmer | llm\n",
+    "chain.invoke(messages)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4d91d390-e7f7-467b-ad87-d100411d7a21",
+   "metadata": {},
+   "source": [
+    "Looking at the LangSmith trace we can see that before the messages are passed to the model they are first trimmed: https://smith.langchain.com/public/65af12c4-c24d-4824-90f0-6547566e59bb/r\n",
+    "\n",
+    "Looking at just the trimmer, we can see that it's a Runnable object that can be invoked like all Runnables:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "1ff02d0a-353d-4fac-a77c-7c2c5262abd9",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[SystemMessage(content=\"you're a good assistant, you always respond with a joke.\"),\n",
+       " HumanMessage(content='what do you call a speechless parrot')]"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "trimmer.invoke(messages)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "dc4720c8-4062-4ebc-9385-58411202ce6e",
+   "metadata": {},
+   "source": [
+    "## Using with ChatMessageHistory\n",
+    "\n",
+    "Trimming messages is especially useful when [working with chat histories](/docs/how_to/message_history/), which can get arbitrarily long:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "a9517858-fc2f-4dc3-898d-bf98a0e905a0",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='A \"polly-no-wanna-cracker\"!', response_metadata={'token_usage': {'completion_tokens': 10, 'prompt_tokens': 32, 'total_tokens': 42}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_5bf7397cd3', 'finish_reason': 'stop', 'logprobs': None}, id='run-054dd309-3497-4e7b-b22a-c1859f11d32e-0', usage_metadata={'input_tokens': 32, 'output_tokens': 10, 'total_tokens': 42})"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_core.chat_history import InMemoryChatMessageHistory\n",
+    "from langchain_core.runnables.history import RunnableWithMessageHistory\n",
+    "\n",
+    "chat_history = InMemoryChatMessageHistory(messages=messages[:-1])\n",
+    "\n",
+    "\n",
+    "def dummy_get_session_history(session_id):\n",
+    "    if session_id != \"1\":\n",
+    "        return InMemoryChatMessageHistory()\n",
+    "    return chat_history\n",
+    "\n",
+    "\n",
+    "llm = ChatOpenAI(model=\"gpt-4o\")\n",
+    "\n",
+    "trimmer = trim_messages(\n",
+    "    max_tokens=45,\n",
+    "    strategy=\"last\",\n",
+    "    token_counter=llm,\n",
+    "    include_system=True,\n",
+    ")\n",
+    "\n",
+    "chain = trimmer | llm\n",
+    "chain_with_history = RunnableWithMessageHistory(chain, dummy_get_session_history)\n",
+    "chain_with_history.invoke(\n",
+    "    [HumanMessage(\"what do you call a speechless parrot\")],\n",
+    "    config={\"configurable\": {\"session_id\": \"1\"}},\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "556b7b4c-43cb-41de-94fc-1a41f4ec4d2e",
+   "metadata": {},
+   "source": [
+    "Looking at the LangSmith trace we can see that we retrieve all of our messages but before the messages are passed to the model they are trimmed to be just the system message and last human message: https://smith.langchain.com/public/17dd700b-9994-44ca-930c-116e00997315/r"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "75dc7b84-b92f-44e7-8beb-ba22398e4efb",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For a complete description of all arguments head to the API reference: https://api.python.langchain.com/en/latest/messages/langchain_core.messages.utils.trim_messages.html"
+   ]
+  }
+ ],
+ "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": "3.10.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/integrations/callbacks/llmonitor.md

@@ -110,7 +110,7 @@ with identify("user-123"):
     llm.invoke("Tell me a joke")
 
 with identify("user-456", user_props={"email": "user456@test.com"}):
-    agen.run("Who is Leo DiCaprio's girlfriend?")
+    agent.run("Who is Leo DiCaprio's girlfriend?")
 ```
 ## Support
 

docs/docs/integrations/callbacks/upstash_ratelimit.ipynb

@@ -0,0 +1,245 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Upstash Ratelimit Callback\n",
+    "\n",
+    "In this guide, we will go over how to add rate limiting based on number of requests or the number of tokens using `UpstashRatelimitHandler`. This handler uses [ratelimit library of Upstash](https://github.com/upstash/ratelimit-py/), which utilizes [Upstash Redis](https://upstash.com/docs/redis/overall/getstarted).\n",
+    "\n",
+    "Upstash Ratelimit works by sending an HTTP request to Upstash Redis everytime the `limit` method is called. Remaining tokens/requests of the user are checked and updated. Based on the remaining tokens, we can stop the execution of costly operations like invoking an LLM or querying a vector store:\n",
+    "\n",
+    "```py\n",
+    "response = ratelimit.limit()\n",
+    "if response.allowed:\n",
+    "    execute_costly_operation()\n",
+    "```\n",
+    "\n",
+    "`UpstashRatelimitHandler` allows you to incorporate the ratelimit logic into your chain in a few minutes.\n",
+    "\n",
+    "First, you will need to go to [the Upstash Console](https://console.upstash.com/login) and create a redis database ([see our docs](https://upstash.com/docs/redis/overall/getstarted)). After creating a database, you will need to set the environment variables:\n",
+    "\n",
+    "```\n",
+    "UPSTASH_REDIS_REST_URL=\"****\"\n",
+    "UPSTASH_REDIS_REST_TOKEN=\"****\"\n",
+    "```\n",
+    "\n",
+    "Next, you will need to install Upstash Ratelimit and Redis library with:\n",
+    "\n",
+    "```\n",
+    "pip install upstash-ratelimit upstash-redis\n",
+    "```\n",
+    "\n",
+    "You are now ready to add rate limiting to your chain!\n",
+    "\n",
+    "## Ratelimiting Per Request\n",
+    "\n",
+    "Let's imagine that we want to allow our users to invoke our chain 10 times per minute. Achieving this is as simple as:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Error in UpstashRatelimitHandler.on_chain_start callback: UpstashRatelimitError('Request limit reached!')\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Handling ratelimit. <class 'langchain_community.callbacks.upstash_ratelimit_callback.UpstashRatelimitError'>\n"
+     ]
+    }
+   ],
+   "source": [
+    "# set env variables\n",
+    "import os\n",
+    "\n",
+    "os.environ[\"UPSTASH_REDIS_REST_URL\"] = \"****\"\n",
+    "os.environ[\"UPSTASH_REDIS_REST_TOKEN\"] = \"****\"\n",
+    "\n",
+    "from langchain_community.callbacks import UpstashRatelimitError, UpstashRatelimitHandler\n",
+    "from langchain_core.runnables import RunnableLambda\n",
+    "from upstash_ratelimit import FixedWindow, Ratelimit\n",
+    "from upstash_redis import Redis\n",
+    "\n",
+    "# create ratelimit\n",
+    "ratelimit = Ratelimit(\n",
+    "    redis=Redis.from_env(),\n",
+    "    # 10 requests per window, where window size is 60 seconds:\n",
+    "    limiter=FixedWindow(max_requests=10, window=60),\n",
+    ")\n",
+    "\n",
+    "# create handler\n",
+    "user_id = \"user_id\"  # should be a method which gets the user id\n",
+    "handler = UpstashRatelimitHandler(identifier=user_id, request_ratelimit=ratelimit)\n",
+    "\n",
+    "# create mock chain\n",
+    "chain = RunnableLambda(str)\n",
+    "\n",
+    "# invoke chain with handler:\n",
+    "try:\n",
+    "    result = chain.invoke(\"Hello world!\", config={\"callbacks\": [handler]})\n",
+    "except UpstashRatelimitError:\n",
+    "    print(\"Handling ratelimit.\", UpstashRatelimitError)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Note that we pass the handler to the `invoke` method instead of passing the handler when defining the chain.\n",
+    "\n",
+    "For rate limiting algorithms other than `FixedWindow`, see [upstash-ratelimit docs](https://github.com/upstash/ratelimit-py?tab=readme-ov-file#ratelimiting-algorithms).\n",
+    "\n",
+    "Before executing any steps in our pipeline, ratelimit will check whether the user has passed the request limit. If so, `UpstashRatelimitError` is raised.\n",
+    "\n",
+    "## Ratelimiting Per Token\n",
+    "\n",
+    "Another option is to rate limit chain invokations based on:\n",
+    "1. number of tokens in prompt\n",
+    "2. number of tokens in prompt and LLM completion\n",
+    "\n",
+    "This only works if you have an LLM in your chain. Another requirement is that the LLM you are using should return the token usage in it's `LLMOutput`.\n",
+    "\n",
+    "### How it works\n",
+    "\n",
+    "The handler will get the remaining tokens before calling the LLM. If the remaining tokens is more than 0, LLM will be called. Otherwise `UpstashRatelimitError` will be raised.\n",
+    "\n",
+    "After LLM is called, token usage information will be used to subtracted from the remaining tokens of the user. No error is raised at this stage of the chain.\n",
+    "\n",
+    "### Configuration\n",
+    "\n",
+    "For the first configuration, simply initialize the handler like this:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ratelimit = Ratelimit(\n",
+    "    redis=Redis.from_env(),\n",
+    "    # 1000 tokens per window, where window size is 60 seconds:\n",
+    "    limiter=FixedWindow(max_requests=1000, window=60),\n",
+    ")\n",
+    "\n",
+    "handler = UpstashRatelimitHandler(identifier=user_id, token_ratelimit=ratelimit)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "For the second configuration, here is how to initialize the handler:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ratelimit = Ratelimit(\n",
+    "    redis=Redis.from_env(),\n",
+    "    # 1000 tokens per window, where window size is 60 seconds:\n",
+    "    limiter=FixedWindow(max_requests=1000, window=60),\n",
+    ")\n",
+    "\n",
+    "handler = UpstashRatelimitHandler(\n",
+    "    identifier=user_id,\n",
+    "    token_ratelimit=ratelimit,\n",
+    "    include_output_tokens=True,  # set to True\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "You can also employ ratelimiting based on requests and tokens at the same time, simply by passing both `request_ratelimit` and `token_ratelimit` parameters.\n",
+    "\n",
+    "Here is an example with a chain utilizing an LLM:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Error in UpstashRatelimitHandler.on_llm_start callback: UpstashRatelimitError('Token limit reached!')\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Handling ratelimit. <class 'langchain_community.callbacks.upstash_ratelimit_callback.UpstashRatelimitError'>\n"
+     ]
+    }
+   ],
+   "source": [
+    "# set env variables\n",
+    "import os\n",
+    "\n",
+    "os.environ[\"UPSTASH_REDIS_REST_URL\"] = \"****\"\n",
+    "os.environ[\"UPSTASH_REDIS_REST_TOKEN\"] = \"****\"\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"****\"\n",
+    "\n",
+    "from langchain_community.callbacks import UpstashRatelimitError, UpstashRatelimitHandler\n",
+    "from langchain_core.runnables import RunnableLambda\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "from upstash_ratelimit import FixedWindow, Ratelimit\n",
+    "from upstash_redis import Redis\n",
+    "\n",
+    "# create ratelimit\n",
+    "ratelimit = Ratelimit(\n",
+    "    redis=Redis.from_env(),\n",
+    "    # 500 tokens per window, where window size is 60 seconds:\n",
+    "    limiter=FixedWindow(max_requests=500, window=60),\n",
+    ")\n",
+    "\n",
+    "# create handler\n",
+    "user_id = \"user_id\"  # should be a method which gets the user id\n",
+    "handler = UpstashRatelimitHandler(identifier=user_id, token_ratelimit=ratelimit)\n",
+    "\n",
+    "# create mock chain\n",
+    "as_str = RunnableLambda(str)\n",
+    "model = ChatOpenAI()\n",
+    "\n",
+    "chain = as_str | model\n",
+    "\n",
+    "# invoke chain with handler:\n",
+    "try:\n",
+    "    result = chain.invoke(\"Hello world!\", config={\"callbacks\": [handler]})\n",
+    "except UpstashRatelimitError:\n",
+    "    print(\"Handling ratelimit.\", UpstashRatelimitError)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "lc39",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python",
+   "version": "3.9.19"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/docs/integrations/chat/azure_chat_openai.ipynb

@@ -23,13 +23,11 @@
    ]
   },
   {
-   "cell_type": "raw",
+   "cell_type": "code",
+   "execution_count": null,
    "id": "d83ba7de",
-   "metadata": {
-    "vscode": {
-     "languageId": "raw"
-    }
-   },
+   "metadata": {},
+   "outputs": [],
    "source": [
     "%pip install -qU langchain-openai"
    ]

docs/docs/integrations/chat/bedrock.ipynb

@@ -137,6 +137,77 @@
     "for chunk in chat.stream(messages):\n",
     "    print(chunk.content, end=\"\", flush=True)"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c36575b3",
+   "metadata": {},
+   "source": [
+    "### LLM Caching with OpenSearch Semantic Cache\n",
+    "\n",
+    "Use OpenSearch as a semantic cache to cache prompts and responses and evaluate hits based on semantic similarity.\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "375d4e56",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.globals import set_llm_cache\n",
+    "from langchain_aws import BedrockEmbeddings, ChatBedrock\n",
+    "from langchain_community.cache import OpenSearchSemanticCache\n",
+    "from langchain_core.messages import HumanMessage\n",
+    "\n",
+    "bedrock_embeddings = BedrockEmbeddings(\n",
+    "    model_id=\"amazon.titan-embed-text-v1\", region_name=\"us-east-1\"\n",
+    ")\n",
+    "\n",
+    "chat = ChatBedrock(\n",
+    "    model_id=\"anthropic.claude-3-haiku-20240307-v1:0\", model_kwargs={\"temperature\": 0.5}\n",
+    ")\n",
+    "\n",
+    "# Enable LLM cache. Make sure OpenSearch is set up and running. Update URL accordingly.\n",
+    "set_llm_cache(\n",
+    "    OpenSearchSemanticCache(\n",
+    "        opensearch_url=\"http://localhost:9200\", embedding=bedrock_embeddings\n",
+    "    )\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bb5d25bb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%time\n",
+    "# The first time, it is not yet in cache, so it should take longer\n",
+    "messages = [HumanMessage(content=\"tell me about Amazon Bedrock\")]\n",
+    "response_text = chat.invoke(messages)\n",
+    "\n",
+    "print(response_text)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6cfb3086",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%time\n",
+    "# The second time, while not a direct hit, the question is semantically similar to the original question,\n",
+    "# so it uses the cached result!\n",
+    "\n",
+    "messages = [HumanMessage(content=\"what is amazon bedrock\")]\n",
+    "response_text = chat.invoke(messages)\n",
+    "\n",
+    "print(response_text)"
+   ]
   }
  ],
  "metadata": {

docs/docs/integrations/chat/cohere.ipynb

@@ -201,7 +201,7 @@
    "source": [
     "## Chaining\n",
     "\n",
-    "You can also easily combine with a prompt template for easy structuring of user input. We can do this using [LCEL](/docs/concepts#langchain-expression-language)"
+    "You can also easily combine with a prompt template for easy structuring of user input. We can do this using [LCEL](/docs/concepts#langchain-expression-language-lcel)"
    ]
   },
   {