Merge branch 'master' into wfh/is_error

Added missed docstrings. Formatted docstrings to the consistent form.

.github/actions/people/app/main.py

@@ -547,6 +547,7 @@ if __name__ == "__main__":
         "obi1kenobi",
         "langchain-infra",
         "jacoblee93",
+        "isahers1",
         "dqbd",
         "bracesproul",
         "akira",

.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/_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/_release.yml

@@ -135,6 +135,7 @@ jobs:
       - release-notes
     uses:
       ./.github/workflows/_test_release.yml
+    permissions: write-all
     with:
       working-directory: ${{ inputs.working-directory }}
       dangerous-nonmaster-release: ${{ inputs.dangerous-nonmaster-release }}
@@ -202,7 +203,7 @@ 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 +246,10 @@ 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/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

.github/workflows/check_new_docs.yml

@@ -26,6 +26,11 @@ jobs:
           python-version: '3.10'
       - id: files
         uses: Ana06/get-changed-files@v2.2.0
+        with:
+          filter: |
+            *.ipynb
+            *.md
+            *.mdx
       - name: Check new docs
         run: |
           python docs/scripts/check_templates.py ${{ steps.files.outputs.added }}

.github/workflows/people.yml

@@ -16,6 +16,7 @@ jobs:
   langchain-people:
     if: github.repository_owner == 'langchain-ai'
     runs-on: ubuntu-latest
+    permissions: write-all
     steps:
       - name: Dump GitHub context
         env:

.github/workflows/scheduled_test.yml

@@ -31,7 +31,6 @@ jobs:
           - "libs/partners/google-vertexai"
           - "libs/partners/google-genai"
           - "libs/partners/aws"
-          - "libs/partners/nvidia-ai-endpoints"
 
     steps:
       - uses: actions/checkout@v4
@@ -41,10 +40,6 @@ jobs:
         with:
           repository: langchain-ai/langchain-google
           path: langchain-google
-      - uses: actions/checkout@v4
-        with:
-          repository: langchain-ai/langchain-nvidia
-          path: langchain-nvidia
       - uses: actions/checkout@v4
         with:
           repository: langchain-ai/langchain-cohere
@@ -59,11 +54,9 @@ jobs:
           rm -rf \
             langchain/libs/partners/google-genai \
             langchain/libs/partners/google-vertexai \
-            langchain/libs/partners/nvidia-ai-endpoints \
             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-nvidia/libs/ai-endpoints langchain/libs/partners/nvidia-ai-endpoints
           mv langchain-cohere/libs/cohere langchain/libs/partners/cohere
           mv langchain-aws/libs/aws langchain/libs/partners/aws
 
@@ -123,7 +116,6 @@ jobs:
           rm -rf \
             langchain/libs/partners/google-genai \
             langchain/libs/partners/google-vertexai \
-            langchain/libs/partners/nvidia-ai-endpoints \
             langchain/libs/partners/cohere \
             langchain/libs/partners/aws
 

README.md

@@ -38,24 +38,25 @@ conda install langchain -c conda-forge
 
 For these applications, LangChain simplifies the entire application lifecycle:
 
-- **Open-source libraries**: Build your applications using LangChain's [modular building blocks](https://python.langchain.com/v0.2/docs/concepts/#langchain-expression-language-lcel) and [components](https://python.langchain.com/v0.2/docs/concepts/#components). Integrate with hundreds of [third-party providers](https://python.langchain.com/v0.2/docs/integrations/platforms/).
+- **Open-source libraries**:  Build your applications using LangChain's open-source [building blocks](https://python.langchain.com/v0.2/docs/concepts#langchain-expression-language-lcel), [components](https://python.langchain.com/v0.2/docs/concepts), and [third-party integrations](https://python.langchain.com/v0.2/docs/integrations/platforms/).
+Use [LangGraph](/docs/concepts/#langgraph) to build stateful agents with first-class streaming and human-in-the-loop support.
 - **Productionization**: Inspect, monitor, and evaluate your apps with [LangSmith](https://docs.smith.langchain.com/) so that you can constantly optimize and deploy with confidence.
-- **Deployment**: Turn any chain into a REST API with [LangServe](https://python.langchain.com/v0.2/docs/langserve/).
+- **Deployment**: Turn your LangGraph applications into production-ready APIs and Assistants with [LangGraph Cloud](https://langchain-ai.github.io/langgraph/cloud/).
 
 ### Open-source libraries
 - **`langchain-core`**: Base abstractions and LangChain Expression Language.
 - **`langchain-community`**: Third party integrations.
   - Some integrations have been further split into **partner packages** that only rely on **`langchain-core`**. Examples include **`langchain_openai`** and **`langchain_anthropic`**.
 - **`langchain`**: Chains, agents, and retrieval strategies that make up an application's cognitive architecture.
-- **[`LangGraph`](https://langchain-ai.github.io/langgraph/)**: A library for building robust and stateful multi-actor applications with LLMs by modeling steps as edges and nodes in a graph.
+- **[`LangGraph`](https://langchain-ai.github.io/langgraph/)**: A library for building robust and stateful multi-actor applications with LLMs by modeling steps as edges and nodes in a graph. Integrates smoothly with LangChain, but can be used without it.
 
 ### Productionization:
 - **[LangSmith](https://docs.smith.langchain.com/)**: A developer platform that lets you debug, test, evaluate, and monitor chains built on any LLM framework and seamlessly integrates with LangChain.
 
 ### Deployment:
-- **[LangServe](https://python.langchain.com/v0.2/docs/langserve/)**: A library for deploying LangChain chains as REST APIs.
+- **[LangGraph Cloud](https://langchain-ai.github.io/langgraph/cloud/)**: Turn your LangGraph applications into production-ready APIs and Assistants.
 
-![Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers.](docs/static/svg/langchain_stack.svg "LangChain Architecture Overview")
+![Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers.](docs/static/svg/langchain_stack_062024.svg "LangChain Architecture Overview")
 
 ## 🧱 What can you build with LangChain?
 
@@ -106,7 +107,7 @@ Retrieval Augmented Generation involves [loading data](https://python.langchain.
 
 **🤖 Agents**
 
-Agents allow an LLM autonomy over how a task is accomplished. Agents make decisions about which Actions to take, then take that Action, observe the result, and repeat until the task is complete. LangChain provides a [standard interface for agents](https://python.langchain.com/v0.2/docs/concepts/#agents) along with the [LangGraph](https://github.com/langchain-ai/langgraph) extension for building custom agents.
+Agents allow an LLM autonomy over how a task is accomplished. Agents make decisions about which Actions to take, then take that Action, observe the result, and repeat until the task is complete. LangChain provides a [standard interface for agents](https://python.langchain.com/v0.2/docs/concepts/#agents), along with [LangGraph](https://github.com/langchain-ai/langgraph) for building custom agents.
 
 ## 📖 Documentation
 
@@ -120,10 +121,9 @@ Please see [here](https://python.langchain.com) for full documentation, which in
 
 ## 🌐 Ecosystem
 
-- [🦜🛠️ LangSmith](https://docs.smith.langchain.com/): Tracing and evaluating your language model applications and intelligent agents to help you move from prototype to production.
-- [🦜🕸️ LangGraph](https://langchain-ai.github.io/langgraph/): Creating stateful, multi-actor applications with LLMs, built on top of (and intended to be used with) LangChain primitives.
-- [🦜🏓 LangServe](https://python.langchain.com/docs/langserve): Deploying LangChain runnables and chains as REST APIs.
-  - [LangChain Templates](https://python.langchain.com/v0.2/docs/templates/): Example applications hosted with LangServe.
+- [🦜🛠️ LangSmith](https://docs.smith.langchain.com/): Trace and evaluate your language model applications and intelligent agents to help you move from prototype to production.
+- [🦜🕸️ LangGraph](https://langchain-ai.github.io/langgraph/): Create stateful, multi-actor applications with LLMs. Integrates smoothly with LangChain, but can be used without it.
+- [🦜🏓 LangServe](https://python.langchain.com/docs/langserve): Deploy LangChain runnables and chains as REST APIs.
 
 
 ## 💁 Contributing

docs/Makefile

@@ -38,6 +38,8 @@ generate-files:
 
 	$(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
@@ -59,7 +61,7 @@ render:
 	$(PYTHON) scripts/notebook_convert.py $(INTERMEDIATE_DIR) $(OUTPUT_NEW_DOCS_DIR)
 
 md-sync:
-	rsync -avm --include="*/" --include="*.mdx" --include="*.md" --include="*.png" --exclude="*" $(INTERMEDIATE_DIR)/ $(OUTPUT_NEW_DOCS_DIR)
+	rsync -avm --include="*/" --include="*.mdx" --include="*.md" --include="*.png" --include="*/_category_.yml" --exclude="*" $(INTERMEDIATE_DIR)/ $(OUTPUT_NEW_DOCS_DIR)
 
 generate-references:
 	$(PYTHON) scripts/generate_api_reference_links.py --docs_dir $(OUTPUT_NEW_DOCS_DIR)

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):
@@ -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 +1,40 @@
+:mod:`{{module}}`.{{objname}}
+{{ underline }}==============
+
+.. NOTE:: {{objname}} implements the standard :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>`. 🏃
+
+    The :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>` has additional methods that are available on runnables, such as :py:meth:`with_types <langchain_core.runnables.base.Runnable.with_types>`, :py:meth:`with_retry <langchain_core.runnables.base.Runnable.with_retry>`, :py:meth:`assign <langchain_core.runnables.base.Runnable.assign>`, :py:meth:`bind <langchain_core.runnables.base.Runnable.bind>`, :py:meth:`get_graph <langchain_core.runnables.base.Runnable.get_graph>`, and more.
+
+.. currentmodule:: {{ module }}
+
+.. autoclass:: {{ objname }}
+
+   {% 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 +1,24 @@
+:mod:`{{module}}`.{{objname}}
+{{ underline }}==============
+
+.. NOTE:: {{objname}} implements the standard :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>`. 🏃
+
+    The :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>` has additional methods that are available on runnables, such as :py:meth:`with_types <langchain_core.runnables.base.Runnable.with_types>`, :py:meth:`with_retry <langchain_core.runnables.base.Runnable.with_retry>`, :py:meth:`assign <langchain_core.runnables.base.Runnable.assign>`, :py:meth:`bind <langchain_core.runnables.base.Runnable.bind>`, :py:meth:`get_graph <langchain_core.runnables.base.Runnable.get_graph>`, and more.
+
+.. currentmodule:: {{ module }}
+
+.. autopydantic_model:: {{ objname }}
+    :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_not_implemented, lc_secrets, lc_attributes, lc_id, get_lc_namespace, astream_log, transform, atransform, get_output_schema, get_prompts, config_schema, map, pick, pipe, with_listeners, with_alisteners, with_config, with_fallbacks, with_types, with_retry, InputType, OutputType, config_specs, output_schema, get_input_schema, get_graph, get_name, input_schema, name, bind, assign
+
+.. 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

@@ -24,21 +24,22 @@ Here you find [such papers](https://arxiv.org/search/?query=langchain&searchtype
 | `2305.08291v1` [Large Language Model Guided Tree-of-Thought](http://arxiv.org/abs/2305.08291v1) | Jieyi Long | 2023-05-15 | `API:` [langchain_experimental.tot](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.tot), `Cookbook:` [tree_of_thought](https://github.com/langchain-ai/langchain/blob/master/cookbook/tree_of_thought.ipynb)
 | `2305.04091v3` [Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models](http://arxiv.org/abs/2305.04091v3) | Lei Wang, Wanyu Xu, Yihuai Lan,  et al. | 2023-05-06 | `Cookbook:` [plan_and_execute_agent](https://github.com/langchain-ai/langchain/blob/master/cookbook/plan_and_execute_agent.ipynb)
 | `2304.08485v2` [Visual Instruction Tuning](http://arxiv.org/abs/2304.08485v2) | Haotian Liu, Chunyuan Li, Qingyang Wu,  et al. | 2023-04-17 | `Cookbook:` [Semi_structured_and_multi_modal_RAG](https://github.com/langchain-ai/langchain/blob/master/cookbook/Semi_structured_and_multi_modal_RAG.ipynb), [Semi_structured_multi_modal_RAG_LLaMA2](https://github.com/langchain-ai/langchain/blob/master/cookbook/Semi_structured_multi_modal_RAG_LLaMA2.ipynb)
-| `2304.03442v2` [Generative Agents: Interactive Simulacra of Human Behavior](http://arxiv.org/abs/2304.03442v2) | Joon Sung Park, Joseph C. O'Brien, Carrie J. Cai,  et al. | 2023-04-07 | `Cookbook:` [generative_agents_interactive_simulacra_of_human_behavior](https://github.com/langchain-ai/langchain/blob/master/cookbook/generative_agents_interactive_simulacra_of_human_behavior.ipynb), [multiagent_bidding](https://github.com/langchain-ai/langchain/blob/master/cookbook/multiagent_bidding.ipynb)
+| `2304.03442v2` [Generative Agents: Interactive Simulacra of Human Behavior](http://arxiv.org/abs/2304.03442v2) | Joon Sung Park, Joseph C. O'Brien, Carrie J. Cai,  et al. | 2023-04-07 | `Cookbook:` [multiagent_bidding](https://github.com/langchain-ai/langchain/blob/master/cookbook/multiagent_bidding.ipynb), [generative_agents_interactive_simulacra_of_human_behavior](https://github.com/langchain-ai/langchain/blob/master/cookbook/generative_agents_interactive_simulacra_of_human_behavior.ipynb)
 | `2303.17760v2` [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](http://arxiv.org/abs/2303.17760v2) | Guohao Li, Hasan Abed Al Kader Hammoud, Hani Itani,  et al. | 2023-03-31 | `Cookbook:` [camel_role_playing](https://github.com/langchain-ai/langchain/blob/master/cookbook/camel_role_playing.ipynb)
 | `2303.17580v4` [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face](http://arxiv.org/abs/2303.17580v4) | Yongliang Shen, Kaitao Song, Xu Tan,  et al. | 2023-03-30 | `API:` [langchain_experimental.autonomous_agents](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.autonomous_agents), `Cookbook:` [hugginggpt](https://github.com/langchain-ai/langchain/blob/master/cookbook/hugginggpt.ipynb)
 | `2303.08774v6` [GPT-4 Technical Report](http://arxiv.org/abs/2303.08774v6) | OpenAI, Josh Achiam, Steven Adler,  et al. | 2023-03-15 | `Docs:` [docs/integrations/vectorstores/mongodb_atlas](https://python.langchain.com/docs/integrations/vectorstores/mongodb_atlas)
-| `2301.10226v4` [A Watermark for Large Language Models](http://arxiv.org/abs/2301.10226v4) | John Kirchenbauer, Jonas Geiping, Yuxin Wen,  et al. | 2023-01-24 | `API:` [langchain_community...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_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...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)
+| `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...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...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...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_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)
+| `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...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_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)
+| `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
@@ -418,7 +419,7 @@ publicly available.
 - **URL:** http://arxiv.org/abs/2304.03442v2
 - **LangChain:**
 
-   - **Cookbook:** [generative_agents_interactive_simulacra_of_human_behavior](https://github.com/langchain-ai/langchain/blob/master/cookbook/generative_agents_interactive_simulacra_of_human_behavior.ipynb), [multiagent_bidding](https://github.com/langchain-ai/langchain/blob/master/cookbook/multiagent_bidding.ipynb)
+   - **Cookbook:** [multiagent_bidding](https://github.com/langchain-ai/langchain/blob/master/cookbook/multiagent_bidding.ipynb), [generative_agents_interactive_simulacra_of_human_behavior](https://github.com/langchain-ai/langchain/blob/master/cookbook/generative_agents_interactive_simulacra_of_human_behavior.ipynb)
 
 **Abstract:** Believable proxies of human behavior can empower interactive applications
 ranging from immersive environments to rehearsal spaces for interpersonal
@@ -540,7 +541,7 @@ more than 1/1,000th the compute of GPT-4.
 - **URL:** http://arxiv.org/abs/2301.10226v4
 - **LangChain:**
 
-   - **API Reference:** [langchain_community...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_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...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)
+   - **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
@@ -683,6 +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
@@ -768,7 +804,7 @@ few-shot examples.
 - **URL:** http://arxiv.org/abs/2202.00666v5
 - **LangChain:**
 
-   - **API Reference:** [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), [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)
+   - **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
@@ -832,7 +868,7 @@ https://github.com/OpenAI/CLIP.
 - **URL:** http://arxiv.org/abs/1909.05858v2
 - **LangChain:**
 
-   - **API Reference:** [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), [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)
+   - **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)
@@ -51,8 +51,8 @@ A developer platform that lets you debug, test, evaluate, and monitor LLM applic
 <ThemedImage
   alt="Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers."
   sources={{
-    light: useBaseUrl('/svg/langchain_stack.svg'),
-    dark: useBaseUrl('/svg/langchain_stack_dark.svg'),
+    light: useBaseUrl('/svg/langchain_stack_062024.svg'),
+    dark: useBaseUrl('/svg/langchain_stack_062024_dark.svg'),
   }}
   title="LangChain Framework Overview"
 />
@@ -89,7 +89,7 @@ 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>
+<span data-heading-keywords="invoke,runnable"></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.
 
@@ -144,8 +144,19 @@ LangChain does not host any Chat Models, rather we rely on third party integrati
 
 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.
@@ -168,8 +179,15 @@ For a full list of LangChain model providers with multimodal models, [check out
 ### 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 [Chat Models](/docs/concepts/#chat-models), 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 gives them the same interface as [Chat Models](/docs/concepts/#chat-models).
@@ -425,9 +443,14 @@ For specifics on how to use text splitters, see the [relevant how-to guides here
 ### Embedding models
 <span data-heading-keywords="embedding,embeddings"></span>
 
-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.
+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.
 
-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.
+![](/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).
 
@@ -440,6 +463,9 @@ One of the most common ways to store and search over unstructured data is to emb
 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
@@ -455,7 +481,7 @@ For specifics on how to use vector stores, see the [relevant how-to guides here]
 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.
 
@@ -524,6 +550,28 @@ If you are still using AgentExecutor, do not fear: we still have a guide on [how
 It is recommended, however, that you start to transition to LangGraph.
 In order to assist in this we have put together a [transition guide on how to do so](/docs/how_to/migrate_agent).
 
+#### ReAct agents
+<span data-heading-keywords="react,react agent"></span>
+
+One popular architecture for building agents is [**ReAct**](https://arxiv.org/abs/2210.03629).
+ReAct combines reasoning and acting in an iterative process - in fact the name "ReAct" stands for "Reason" and "Act".
+
+The general flow looks like this:
+
+- The model will "think" about what step to take in response to an input and any previous observations.
+- The model will then choose an action from available tools (or choose to respond to the user).
+- The model will generate arguments to that tool.
+- The agent runtime (executor) will parse out the chosen tool and call it with the generated arguments.
+- The executor will return the results of the tool call back to the model as an observation.
+- This process repeats until the agent chooses to respond.
+
+There are general prompting based implementations that do not require any model-specific features, but the most
+reliable implementations use features like [tool calling](/docs/how_to/tool_calling/) to reliably format outputs
+and reduce variance.
+
+Please see the [LangGraph documentation](https://langchain-ai.github.io/langgraph/) for more information,
+or [this how-to guide](/docs/how_to/migrate_agent/) for specific information on migrating to LangGraph.
+
 ### Callbacks
 
 LangChain provides a callbacks system that allows you to hook into the various stages of your LLM application. This is useful for logging, monitoring, streaming, and other tasks.
@@ -599,6 +647,7 @@ For specifics on how to use callbacks, see the [relevant how-to guides here](/do
 ## Techniques
 
 ### 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.
@@ -609,49 +658,9 @@ around building apps with LLMs to help alleviate latency issues, and LangChain a
 
 Below, we'll discuss some concepts and considerations around streaming in LangChain.
 
-#### 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.
-
-#### 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.
-
 #### `.stream()` and `.astream()`
 
-LangChain also includes the `.stream()` method (and the equivalent `.astream()` method for [async](https://docs.python.org/3/library/asyncio.html) environments) as a more ergonomic streaming interface.
+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
@@ -664,7 +673,7 @@ for chunk in model.stream("what color is the sky?"):
 ```
 
 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. Using `.stream()` will also automatically call the model in streaming mode
+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).
@@ -675,14 +684,15 @@ 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 easier to use than callbacks, it only returns one type of value. This is fine for single LLM calls,
+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 the aforementioned callbacks, or by constructing your chain in such a way that it passes intermediate
-values to the end with something like [`.assign()`](/docs/how_to/passthrough/), but LangChain also includes an
+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.
@@ -708,7 +718,48 @@ async for event in chain.astream_events({"topic": "parrot"}, version="v2"):
 
 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()`.
+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
 
@@ -725,14 +776,54 @@ 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.
+For convenience, some LangChain chat models support a [`.with_structured_output()`](/docs/how_to/structured_output/#the-with_structured_output-method)
+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.
 
+Here's an example:
+
+```python
+from typing import Optional
+
+from langchain_core.pydantic_v1 import BaseModel, Field
+
+
+class Joke(BaseModel):
+    """Joke to tell user."""
+
+    setup: str = Field(description="The setup of the joke")
+    punchline: str = Field(description="The punchline to the joke")
+    rating: Optional[int] = Field(description="How funny the joke is, from 1 to 10")
+
+structured_llm = llm.with_structured_output(Joke)
+
+structured_llm.invoke("Tell me a joke about cats")
+```
+
+```
+Joke(setup='Why was the cat sitting on the computer?', punchline='To keep an eye on the mouse!', rating=None)
+
+```
+
+We recommend this method as a starting point when working with structured output:
+
+- It uses other model-specific features under the hood, without the need to import an output parser.
+- For the models that use tool calling, no special prompting is needed.
+- If multiple underlying techniques are supported, you can supply a `method` parameter to
+[toggle which one is used](/docs/how_to/structured_output/#advanced-specifying-the-method-for-structuring-outputs).
+
+You may want or need to use other techiniques if:
+
+- The chat model you are using does not support tool calling.
+- You are working with very complex schemas and the model is having trouble generating outputs that conform.
+
 For more information, check out this [how-to guide](/docs/how_to/structured_output/#the-with_structured_output-method).
 
+You can also check out [this table](/docs/integrations/chat/#advanced-features) for a list of models that support
+`with_structured_output()`.
+
 #### Raw prompting
 
 The most intuitive way to get a model to structure output is to ask nicely.
@@ -755,9 +846,8 @@ for smooth parsing can be surprisingly difficult and model-specific.
 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.
+While features offered by model providers may increase reliability, prompting techniques remain important for tuning your
+results no matter which method you choose.
 
 #### JSON mode
 <span data-heading-keywords="json mode"></span>
@@ -767,10 +857,11 @@ Some models, such as [Mistral](/docs/integrations/chat/mistralai/), [OpenAI](/do
 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/).
+Often they require some custom prompting, but it's usually much less burdensome than completely raw prompting and
+more along the lines of, `"you must always return JSON"`. The [output also generally easier to parse](/docs/how_to/output_parser_json/).
 
-It's also generally simpler and more commonly available than tool calling.
+It's also generally simpler to use directly and more commonly available than tool calling, and can give
+more flexibility around prompting and shaping results than tool calling.
 
 Here's an example:
 
@@ -808,7 +899,7 @@ For a full list of model providers that support JSON mode, see [this table](/doc
 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
@@ -846,36 +937,168 @@ The standard interface consists of:
 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)                                                                                                                                    |
 
-For a high-level guide on retrieval, see this [tutorial on RAG](/docs/tutorials/rag/).
+:::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/3p_integrations/langchain)
+- [Mistral](https://github.com/mistralai/cookbook/tree/main/third_party/langchain)
+
+:::
 
 ### Text splitting
 
@@ -902,6 +1125,29 @@ 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).
+
+### Tracing
+<span data-heading-keywords="trace,tracing"></span>
+
+A trace is essentially a series of steps that your application takes to go from input to output.
+Traces contain individual steps called `runs`. These can be individual calls from a model, retriever,
+tool, or sub-chains.
+Tracing gives you observability inside your chains and agents, and is vital in diagnosing issues.
+
+For a deeper dive, check out [this LangSmith conceptual guide](https://docs.smith.langchain.com/concepts/tracing).

docs/docs/contributing/code/guidelines.mdx

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

docs/docs/contributing/code/index.mdx

@@ -0,0 +1,6 @@
+# Contribute Code
+
+If you would like to add a new feature or update an existing one, please read the resources below before getting started:
+
+- [General guidelines](/docs/contributing/code/guidelines/)
+- [Setup](/docs/contributing/code/setup/)

docs/docs/contributing/code/setup.mdx

@@ -1,36 +1,9 @@
----
-sidebar_position: 1
----
-# Contribute Code
+# Setup
 
-To contribute to this project, please follow the ["fork and pull request"](https://docs.github.com/en/get-started/quickstart/contributing-to-projects) workflow.
-Please do not try to push directly to this repo unless you are a maintainer.
-
-Please follow the checked-in pull request template when opening pull requests. Note related issues and tag relevant
-maintainers.
-
-Pull requests cannot land without passing the formatting, linting, and testing checks first. See [Testing](#testing) and
-[Formatting and Linting](#formatting-and-linting) for how to run these checks locally.
-
-It's essential that we maintain great documentation and testing. If you:
-- Fix a bug
-  - Add a relevant unit or integration test when possible. These live in `tests/unit_tests` and `tests/integration_tests`.
-- Make an improvement
-  - Update any affected example notebooks and documentation. These live in `docs`.
-  - Update unit and integration tests when relevant.
-- Add a feature
-  - Add a demo notebook in `docs/docs/`.
-  - Add unit and integration tests.
-
-We are a small, progress-oriented team. If there's something you'd like to add or change, opening a pull request is the
-best way to get our attention.
-
-## 🚀 Quick Start
-
-This quick start guide explains how to run the repository locally.
+This guide walks through how to run the repository locally and check in your first code.
 For a [development container](https://containers.dev/), see the [.devcontainer folder](https://github.com/langchain-ai/langchain/tree/master/.devcontainer).
 
-### Dependency Management: Poetry and other env/dependency managers
+## Dependency Management: Poetry and other env/dependency managers
 
 This project utilizes [Poetry](https://python-poetry.org/) v1.7.1+ as a dependency manager.
 
@@ -41,7 +14,7 @@ Install Poetry: **[documentation on how to install it](https://python-poetry.org
 ❗Note: If you use `Conda` or `Pyenv` as your environment/package manager, after installing Poetry,
 tell Poetry to use the virtualenv python environment (`poetry config virtualenvs.prefer-active-python true`)
 
-### Different packages
+## Different packages
 
 This repository contains multiple packages:
 - `langchain-core`: Base interfaces for key abstractions as well as logic for combining them in chains (LangChain Expression Language).
@@ -59,7 +32,7 @@ For this quickstart, start with langchain-community:
 cd libs/community
 ```
 
-### Local Development Dependencies
+## Local Development Dependencies
 
 Install langchain-community development requirements (for running langchain, running examples, linting, formatting, tests, and coverage):
 
@@ -79,9 +52,9 @@ If you are still seeing this bug on v1.6.1+, you may also try disabling "modern
 (`poetry config installer.modern-installation false`) and re-installing requirements.
 See [this `debugpy` issue](https://github.com/microsoft/debugpy/issues/1246) for more details.
 
-### Testing
+## Testing
 
-_In `langchain`, `langchain-community`, and `langchain-experimental`, some test dependencies are optional; see section about optional dependencies_.
+**Note:** In `langchain`, `langchain-community`, and `langchain-experimental`, some test dependencies are optional. See the following section about optional dependencies.
 
 Unit tests cover modular logic that does not require calls to outside APIs.
 If you add new logic, please add a unit test.
@@ -118,11 +91,11 @@ poetry install --with test
 make test
 ```
 
-### Formatting and Linting
+## Formatting and Linting
 
 Run these locally before submitting a PR; the CI system will check also.
 
-#### Code Formatting
+### Code Formatting
 
 Formatting for this project is done via [ruff](https://docs.astral.sh/ruff/rules/).
 
@@ -174,7 +147,7 @@ This can be very helpful when you've made changes to only certain parts of the p
 
 We recognize linting can be annoying - if you do not want to do it, please contact a project maintainer, and they can help you with it. We do not want this to be a blocker for good code getting contributed.
 
-#### Spellcheck
+### Spellcheck
 
 Spellchecking for this project is done via [codespell](https://github.com/codespell-project/codespell).
 Note that `codespell` finds common typos, so it could have false-positive (correctly spelled but rarely used) and false-negatives (not finding misspelled) words.

docs/docs/contributing/documentation/_category_.yml

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

docs/docs/contributing/documentation/index.mdx

@@ -0,0 +1,7 @@
+# Contribute Documentation
+
+Documentation is a vital part of LangChain. We welcome both new documentation for new features and 
+community improvements to our current documentation. Please read the resources below before getting started:
+
+- [Documentation style guide](/docs/contributing/documentation/style_guide/)
+- [Setup](/docs/contributing/documentation/setup/)

docs/docs/contributing/documentation/setup.mdx

@@ -1,4 +1,8 @@
-# Technical logistics
+---
+sidebar_class_name: "hidden"
+---
+
+# Setup
 
 LangChain documentation consists of two components:
 
@@ -12,8 +16,6 @@ used to generate the externally facing [API Reference](https://api.python.langch
 The content for the API reference is autogenerated by scanning the docstrings in the codebase. For this reason we ask that
 developers document their code well.
 
-The main documentation is built using [Quarto](https://quarto.org) and [Docusaurus 2](https://docusaurus.io/).
-
 The `API Reference` is largely autogenerated by [sphinx](https://www.sphinx-doc.org/en/master/)
 from the code and is hosted by [Read the Docs](https://readthedocs.org/).
 
@@ -29,7 +31,7 @@ The content for the main documentation is located in the `/docs` directory of th
 
 The documentation is written using a combination of ipython notebooks (`.ipynb` files)
 and markdown (`.mdx` files). The notebooks are converted to markdown
-using [Quarto](https://quarto.org) and then built using [Docusaurus 2](https://docusaurus.io/).
+and then built using [Docusaurus 2](https://docusaurus.io/).
 
 Feel free to make contributions to the main documentation! 🥰
 
@@ -48,10 +50,6 @@ locally to ensure that it looks good and is free of errors.
 If you're unable to build it locally that's okay as well, as you will be able to
 see a preview of the documentation on the pull request page.
 
-### Install dependencies
-
-- [Quarto](https://quarto.org) - package that converts Jupyter notebooks (`.ipynb` files) into mdx files for serving in Docusaurus. [Download link](https://quarto.org/docs/download/).
-
 From the **monorepo root**, run the following command to install the dependencies:
 
 ```bash
@@ -71,8 +69,6 @@ make docs_clean
 make api_docs_clean
 ```
 
-
-
 Next, you can build the documentation as outlined below:
 
 ```bash

docs/docs/contributing/documentation/style_guide.mdx

@@ -1,10 +1,8 @@
 ---
-sidebar_label: "Style guide"
+sidebar_class_name: "hidden"
 ---
 
-# LangChain Documentation Style Guide
-
-## Introduction
+# Documentation Style Guide
 
 As LangChain continues to grow, the surface area of documentation required to cover it continues to grow too.
 This page provides guidelines for anyone writing documentation for LangChain, as well as some of our philosophies around
@@ -12,116 +10,137 @@ organization and structure.
 
 ## Philosophy
 
-LangChain's documentation aspires to follow the [Diataxis framework](https://diataxis.fr).
-Under this framework, all documentation falls under one of four categories:
+LangChain's documentation follows the [Diataxis framework](https://diataxis.fr).
+Under this framework, all documentation falls under one of four categories: [Tutorials](/docs/contributing/documentation/style_guide/#tutorials),
+[How-to guides](/docs/contributing/documentation/style_guide/#how-to-guides),
+[References](/docs/contributing/documentation/style_guide/#references), and [Explanations](/docs/contributing/documentation/style_guide/#conceptual-guide).
 
-- **Tutorials**: Lessons that take the reader by the hand through a series of conceptual steps to complete a project.
-  - An example of this is our [LCEL streaming guide](/docs/how_to/streaming).
-  - Our guides on [custom components](/docs/how_to/custom_chat_model) is another one.
-- **How-to guides**: Guides that take the reader through the steps required to solve a real-world problem.
-  - The clearest examples of this are our [Use case](/docs/how_to#use-cases) quickstart pages.
-- **Reference**: Technical descriptions of the machinery and how to operate it.
-  - Our [Runnable interface](/docs/concepts#interface) page is an example of this.
-  - The [API reference pages](https://api.python.langchain.com/) are another.
-- **Explanation**: Explanations that clarify and illuminate a particular topic.
-  - The [LCEL primitives pages](/docs/how_to/sequence) are an example of this.
+### Tutorials
+
+Tutorials are lessons that take the reader through a practical activity. Their purpose is to help the user
+gain understanding of concepts and how they interact by showing one way to achieve some goal in a hands-on way. They should **avoid** giving
+multiple permutations of ways to achieve that goal in-depth. Instead, it should guide a new user through a recommended path to accomplishing the tutorial's goal. While the end result of a tutorial does not necessarily need to
+be completely production-ready, it should be useful and practically satisfy the the goal that you clearly stated in the tutorial's introduction. Information on how to address additional scenarios
+belongs in how-to guides.
+
+To quote the Diataxis website:
+
+> A tutorial serves the user’s *acquisition* of skills and knowledge - their study. Its purpose is not to help the user get something done, but to help them learn.
+
+In LangChain, these are often higher level guides that show off end-to-end use cases.
+
+Some examples include:
+
+- [Build a Simple LLM Application with LCEL](/docs/tutorials/llm_chain/)
+- [Build a Retrieval Augmented Generation (RAG) App](/docs/tutorials/rag/)
+  
+Here are some high-level tips on writing a good tutorial:
+
+- Focus on guiding the user to get something done, but keep in mind the end-goal is more to impart principles than to create a perfect production system.
+- Be specific, not abstract and follow one path.
+  - No need to go deeply into alternative approaches, but it’s ok to reference them, ideally with a link to an appropriate how-to guide.
+- Get "a point on the board" as soon as possible - something the user can run that outputs something.
+  - You can iterate and expand afterwards.
+  - Try to frequently checkpoint at given steps where the user can run code and see progress.
+- Focus on results, not technical explanation.
+  - Crosslink heavily to appropriate conceptual/reference pages.
+- The first time you mention a LangChain concept, use its full name (e.g. "LangChain Expression Language (LCEL)"), and link to its conceptual/other documentation page.
+  - It's also helpful to add a prerequisite callout that links to any pages with necessary background information.
+- End with a recap/next steps section summarizing what the tutorial covered and future reading, such as related how-to guides.
+  
+### How-to guides
+
+A how-to guide, as the name implies, demonstrates how to do something discrete and specific.
+It should assume that the user is already familiar with underlying concepts, and is trying to solve an immediate problem, but
+should still give some background or list the scenarios where the information contained within can be relevant.
+They can and should discuss alternatives if one approach may be better than another in certain cases.
+
+To quote the Diataxis website:
+
+> A how-to guide serves the work of the already-competent user, whom you can assume to know what they want to do, and to be able to follow your instructions correctly.
+
+Some examples include:
+
+- [How to: return structured data from a model](/docs/how_to/structured_output/)
+- [How to: write a custom chat model](/docs/how_to/custom_chat_model/)
+
+Here are some high-level tips on writing a good how-to guide:
+
+- Clearly explain what you are guiding the user through at the start.
+- Assume higher intent than a tutorial and show what the user needs to do to get that task done.
+- Assume familiarity of concepts, but explain why suggested actions are helpful.
+  - Crosslink heavily to conceptual/reference pages.
+- Discuss alternatives and responses to real-world tradeoffs that may arise when solving a problem.
+- Use lots of example code.
+  - Prefer full code blocks that the reader can copy and run.
+- End with a recap/next steps section summarizing what the tutorial covered and future reading, such as other related how-to guides.
+
+### Conceptual guide
+
+LangChain's conceptual guide falls under the **Explanation** quadrant of Diataxis. They should cover LangChain terms and concepts
+in a more abstract way than how-to guides or tutorials, and should be geared towards curious users interested in
+gaining a deeper understanding of the framework. Try to avoid excessively large code examples - the goal here is to
+impart perspective to the user rather than to finish a practical project. These guides should cover **why** things work they way they do.
+
+This guide on documentation style is meant to fall under this category.
+
+To quote the Diataxis website:
+
+> The perspective of explanation is higher and wider than that of the other types. It does not take the user’s eye-level view, as in a how-to guide, or a close-up view of the machinery, like reference material. Its scope in each case is a topic - “an area of knowledge”, that somehow has to be bounded in a reasonable, meaningful way.
+
+Some examples include:
+
+- [Retrieval conceptual docs](/docs/concepts/#retrieval)
+- [Chat model conceptual docs](/docs/concepts/#chat-models)
+
+Here are some high-level tips on writing a good conceptual guide:
+
+- Explain design decisions. Why does concept X exist and why was it designed this way?
+- Use analogies and reference other concepts and alternatives
+- Avoid blending in too much reference content
+- You can and should reference content covered in other guides, but make sure to link to them
+
+### References
+
+References contain detailed, low-level information that describes exactly what functionality exists and how to use it.
+In LangChain, this is mainly our API reference pages, which are populated from docstrings within code.
+References pages are generally not read end-to-end, but are consulted as necessary when a user needs to know
+how to use something specific.
+
+To quote the Diataxis website:
+
+> The only purpose of a reference guide is to describe, as succinctly as possible, and in an orderly way. Whereas the content of tutorials and how-to guides are led by needs of the user, reference material is led by the product it describes.
+
+Many of the reference pages in LangChain are automatically generated from code,
+but here are some high-level tips on writing a good docstring:
+
+- Be concise
+- Discuss special cases and deviations from a user's expectations
+- Go into detail on required inputs and outputs
+- Light details on when one might use the feature are fine, but in-depth details belong in other sections.
 
 Each category serves a distinct purpose and requires a specific approach to writing and structuring the content.
 
-## Taxonomy
-
-Keeping the above in mind, we have sorted LangChain's docs into categories. It is helpful to think in these terms
-when contributing new documentation:
-
-### Getting started
-
-The [getting started section](/docs/introduction) includes a high-level introduction to LangChain, a quickstart that
-tours LangChain's various features, and logistical instructions around installation and project setup.
-
-It contains elements of **How-to guides** and **Explanations**.
-
-### Use cases
-
-[Use cases](/docs/how_to#use-cases) are guides that are meant to show how to use LangChain to accomplish a specific task (RAG, information extraction, etc.).
-The quickstarts should be good entrypoints for first-time LangChain developers who prefer to learn by getting something practical prototyped,
-then taking the pieces apart retrospectively. These should mirror what LangChain is good at.
-
-The quickstart pages here should fit the **How-to guide** category, with the other pages intended to be **Explanations** of more
-in-depth concepts and strategies that accompany the main happy paths.
-
-:::note
-The below sections are listed roughly in order of increasing level of abstraction.
-:::
-
-### Expression Language
-
-[LangChain Expression Language (LCEL)](/docs/concepts#langchain-expression-language-lcel) is the fundamental way that most LangChain components fit together, and this section is designed to teach
-developers how to use it to build with LangChain's primitives effectively.
-
-This section should contains **Tutorials** that teach how to stream and use LCEL primitives for more abstract tasks, **Explanations** of specific behaviors,
-and some **References** for how to use different methods in the Runnable interface.
-
-### Components
-
-The [components section](/docs/concepts) covers concepts one level of abstraction higher than LCEL.
-Abstract base classes like `BaseChatModel` and `BaseRetriever` should be covered here, as well as core implementations of these base classes,
-such as `ChatPromptTemplate` and `RecursiveCharacterTextSplitter`. Customization guides belong here too.
-
-This section should contain mostly conceptual **Tutorials**, **References**, and **Explanations** of the components they cover.
-
-:::note
-As a general rule of thumb, everything covered in the `Expression Language` and `Components` sections (with the exception of the `Composition` section of components) should
-cover only components that exist in `langchain_core`.
-:::
-
-### Integrations
-
-The [integrations](/docs/integrations/platforms/) are specific implementations of components. These often involve third-party APIs and services.
-If this is the case, as a general rule, these are maintained by the third-party partner.
-
-This section should contain mostly **Explanations** and **References**, though the actual content here is more flexible than other sections and more at the
-discretion of the third-party provider.
-
-:::note
-Concepts covered in `Integrations` should generally exist in `langchain_community` or specific partner packages.
-:::
-
-### Guides and Ecosystem
-
-The [Guides](/docs/tutorials) and [Ecosystem](https://docs.smith.langchain.com/) sections should contain guides that address higher-level problems than the sections above.
-This includes, but is not limited to, considerations around productionization and development workflows.
-
-These should contain mostly **How-to guides**, **Explanations**, and **Tutorials**.
-
-### API references
-
-LangChain's API references. Should act as **References** (as the name implies) with some **Explanation**-focused content as well. 
-
-## Sample developer journey
-
-We have set up our docs to assist a new developer to LangChain. Let's walk through the intended path:
-
-- The developer lands on https://python.langchain.com, and reads through the introduction and the diagram.
-- If they are just curious, they may be drawn to the [Quickstart](/docs/tutorials/llm_chain) to get a high-level tour of what LangChain contains.
-- If they have a specific task in mind that they want to accomplish, they will be drawn to the Use-Case section. The use-case should provide a good, concrete hook that shows the value LangChain can provide them and be a good entrypoint to the framework.
-- They can then move to learn more about the fundamentals of LangChain through the Expression Language sections.
-- Next, they can learn about LangChain's various components and integrations.
-- Finally, they can get additional knowledge through the Guides.
-
-This is only an ideal of course - sections will inevitably reference lower or higher-level concepts that are documented in other sections.
-
-## Guidelines
+## General guidelines
 
 Here are some other guidelines you should think about when writing and organizing documentation.
 
-### Linking to other sections
+We generally do not merge new tutorials from outside contributors without an actue need.
+We welcome updates as well as new integration docs, how-tos, and references.
+
+### Avoid duplication
+
+Multiple pages that cover the same material in depth are difficult to maintain and cause confusion. There should
+be only one (very rarely two), canonical pages for a given concept or feature. Instead, you should link to other guides.
+
+### Link to other sections
 
 Because sections of the docs do not exist in a vacuum, it is important to link to other sections as often as possible
 to allow a developer to learn more about an unfamiliar topic inline.
 
 This includes linking to the API references as well as conceptual sections!
 
-### Conciseness
+### Be concise
 
 In general, take a less-is-more approach. If a section with a good explanation of a concept already exists, you should link to it rather than
 re-explain it, unless the concept you are documenting presents some new wrinkle.
@@ -130,9 +149,10 @@ Be concise, including in code samples.
 
 ### General style
 
-- Use active voice and present tense whenever possible.
-- Use examples and code snippets to illustrate concepts and usage.
-- Use appropriate header levels (`#`, `##`, `###`, etc.) to organize the content hierarchically.
-- Use bullet points and numbered lists to break down information into easily digestible chunks.
-- Use tables (especially for **Reference** sections) and diagrams often to present information visually.
-- Include the table of contents for longer documentation pages to help readers navigate the content, but hide it for shorter pages.
+- Use active voice and present tense whenever possible
+- Use examples and code snippets to illustrate concepts and usage
+- Use appropriate header levels (`#`, `##`, `###`, etc.) to organize the content hierarchically
+- Use fewer cells with more code to make copy/paste easier
+- Use bullet points and numbered lists to break down information into easily digestible chunks
+- Use tables (especially for **Reference** sections) and diagrams often to present information visually
+- Include the table of contents for longer documentation pages to help readers navigate the content, but hide it for shorter pages

docs/docs/contributing/index.mdx

@@ -12,8 +12,8 @@ As an open-source project in a rapidly developing field, we are extremely open t
 
 There are many ways to contribute to LangChain. Here are some common ways people contribute:
 
-- [**Documentation**](/docs/contributing/documentation/style_guide): Help improve our docs, including this one!
-- [**Code**](./code.mdx): Help us write code, fix bugs, or improve our infrastructure.
+- [**Documentation**](/docs/contributing/documentation/): Help improve our docs, including this one!
+- [**Code**](/docs/contributing/code/): Help us write code, fix bugs, or improve our infrastructure.
 - [**Integrations**](integrations.mdx): Help us integrate with your favorite vendors and tools.
 - [**Discussions**](https://github.com/langchain-ai/langchain/discussions): Help answer usage questions and discuss issues with users.
 

docs/docs/contributing/integrations.mdx

@@ -1,6 +1,7 @@
 ---
 sidebar_position: 5
 ---
+
 # Contribute Integrations
 
 To begin, make sure you have all the dependencies outlined in guide on [Contributing Code](/docs/contributing/code/).

docs/docs/contributing/repo_structure.mdx

@@ -7,6 +7,7 @@ If you plan on contributing to LangChain code or documentation, it can be useful
 to understand the high level structure of the repository.
 
 LangChain is organized as a [monorepo](https://en.wikipedia.org/wiki/Monorepo) that contains multiple packages.
+You can check out our [installation guide](/docs/how_to/installation/) for more on how they fit together.
 
 Here's the structure visualized as a tree:
 
@@ -51,7 +52,7 @@ There are other files in the root directory level, but their presence should be
 The `/docs` directory contains the content for the documentation that is shown
 at https://python.langchain.com/ and the associated API Reference https://api.python.langchain.com/en/latest/langchain_api_reference.html.
 
-See the [documentation](/docs/contributing/documentation/style_guide) guidelines to learn how to contribute to the documentation.
+See the [documentation](/docs/contributing/documentation/) guidelines to learn how to contribute to the documentation.
 
 ## Code
 
@@ -59,6 +60,6 @@ The `/libs` directory contains the code for the LangChain packages.
 
 To learn more about how to contribute code see the following guidelines:
 
-- [Code](./code.mdx) Learn how to develop in the LangChain codebase.
-- [Integrations](./integrations.mdx) to learn how to contribute to third-party integrations to langchain-community or to start a new partner package.
-- [Testing](./testing.mdx) guidelines to learn how to write tests for the packages.
+- [Code](/docs/contributing/code/): Learn how to develop in the LangChain codebase.
+- [Integrations](./integrations.mdx): Learn how to contribute to third-party integrations to `langchain-community` or to start a new partner package.
+- [Testing](./testing.mdx): Guidelines to learn how to write tests for the packages.

docs/docs/contributing/testing.mdx

@@ -1,5 +1,5 @@
 ---
-sidebar_position: 2
+sidebar_position: 6
 ---
 
 # Testing

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/chat_models_universal_init.ipynb

@@ -5,7 +5,7 @@
    "id": "cfdf4f09-8125-4ed1-8063-6feed57da8a3",
    "metadata": {},
    "source": [
-    "# How to let your end users choose their model\n",
+    "# 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",

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_html.ipynb

@@ -23,12 +23,12 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install \"unstructured[html]\""
+    "%pip install unstructured"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "id": "7d167ca3-c7c7-4ef0-b509-080629f0f482",
    "metadata": {},
    "outputs": [
@@ -36,14 +36,14 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[Document(page_content='My First Heading\\n\\nMy first paragraph.', metadata={'source': '../../../docs/integrations/document_loaders/example_data/fake-content.html'})]\n"
+      "[Document(page_content='My First Heading\\n\\nMy first paragraph.', metadata={'source': '../../docs/integrations/document_loaders/example_data/fake-content.html'})]\n"
      ]
     }
    ],
    "source": [
     "from langchain_community.document_loaders import UnstructuredHTMLLoader\n",
     "\n",
-    "file_path = \"../../../docs/integrations/document_loaders/example_data/fake-content.html\"\n",
+    "file_path = \"../../docs/integrations/document_loaders/example_data/fake-content.html\"\n",
     "\n",
     "loader = UnstructuredHTMLLoader(file_path)\n",
     "data = loader.load()\n",
@@ -73,7 +73,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 4,
    "id": "0a2050a8-6df6-4696-9889-ba367d6f9caa",
    "metadata": {},
    "outputs": [
@@ -81,7 +81,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[Document(page_content='\\nTest Title\\n\\n\\nMy First Heading\\nMy first paragraph.\\n\\n\\n', metadata={'source': '../../../docs/integrations/document_loaders/example_data/fake-content.html', 'title': 'Test Title'})]\n"
+      "[Document(page_content='\\nTest Title\\n\\n\\nMy First Heading\\nMy first paragraph.\\n\\n\\n', metadata={'source': '../../docs/integrations/document_loaders/example_data/fake-content.html', 'title': 'Test Title'})]\n"
      ]
     }
    ],
@@ -111,7 +111,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.4"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/how_to/document_loader_markdown.ipynb

@@ -21,12 +21,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": null,
    "id": "c8b147fb-6877-4f7a-b2ee-ee971c7bc662",
    "metadata": {},
    "outputs": [],
    "source": [
-    "# !pip install \"unstructured[md]\""
+    "%pip install \"unstructured[md]\""
    ]
   },
   {
@@ -39,7 +39,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 4,
    "id": "80c50cc4-7ce9-4418-81b9-29c52c7b3627",
    "metadata": {},
    "outputs": [
@@ -62,7 +62,7 @@
     "from langchain_community.document_loaders import UnstructuredMarkdownLoader\n",
     "from langchain_core.documents import Document\n",
     "\n",
-    "markdown_path = \"../../../../README.md\"\n",
+    "markdown_path = \"../../../README.md\"\n",
     "loader = UnstructuredMarkdownLoader(markdown_path)\n",
     "\n",
     "data = loader.load()\n",
@@ -84,7 +84,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 5,
    "id": "a986bbce-7fd3-41d1-bc47-49f9f57c7cd1",
    "metadata": {},
    "outputs": [
@@ -92,11 +92,11 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Number of documents: 65\n",
+      "Number of documents: 66\n",
       "\n",
-      "page_content='🦜️🔗 LangChain' metadata={'source': '../../../../README.md', 'last_modified': '2024-04-29T13:40:19', 'page_number': 1, 'languages': ['eng'], 'filetype': 'text/markdown', 'file_directory': '../../../..', 'filename': 'README.md', 'category': 'Title'}\n",
+      "page_content='🦜️🔗 LangChain' metadata={'source': '../../../README.md', 'category_depth': 0, 'last_modified': '2024-06-28T15:20:01', 'languages': ['eng'], 'filetype': 'text/markdown', 'file_directory': '../../..', 'filename': 'README.md', 'category': 'Title'}\n",
       "\n",
-      "page_content='⚡ Build context-aware reasoning applications ⚡' metadata={'source': '../../../../README.md', 'last_modified': '2024-04-29T13:40:19', 'page_number': 1, 'languages': ['eng'], 'parent_id': 'c3223b6f7100be08a78f1e8c0c28fde1', 'filetype': 'text/markdown', 'file_directory': '../../../..', 'filename': 'README.md', 'category': 'NarrativeText'}\n",
+      "page_content='⚡ Build context-aware reasoning applications ⚡' metadata={'source': '../../../README.md', 'last_modified': '2024-06-28T15:20:01', 'languages': ['eng'], 'parent_id': '200b8a7d0dd03f66e4f13456566d2b3a', 'filetype': 'text/markdown', 'file_directory': '../../..', 'filename': 'README.md', 'category': 'NarrativeText'}\n",
       "\n"
      ]
     }
@@ -121,7 +121,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 6,
    "id": "75abc139-3ded-4e8e-9f21-d0c8ec40fdfc",
    "metadata": {},
    "outputs": [
@@ -129,13 +129,21 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'Title', 'NarrativeText', 'ListItem'}\n"
+      "{'ListItem', 'NarrativeText', 'Title'}\n"
      ]
     }
    ],
    "source": [
     "print(set(document.metadata[\"category\"] for document in data))"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "223b4c11",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
@@ -154,7 +162,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.4"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/how_to/extraction_examples.ipynb

@@ -246,11 +246,11 @@
     "examples = [\n",
     "    (\n",
     "        \"The ocean is vast and blue. It's more than 20,000 feet deep. There are many fish in it.\",\n",
-    "        Person(name=None, height_in_meters=None, hair_color=None),\n",
+    "        Data(people=[]),\n",
     "    ),\n",
     "    (\n",
     "        \"Fiona traveled far from France to Spain.\",\n",
-    "        Person(name=\"Fiona\", height_in_meters=None, hair_color=None),\n",
+    "        Data(people=[Person(name=\"Fiona\", height_in_meters=None, hair_color=None)]),\n",
     "    ),\n",
     "]\n",
     "\n",

docs/docs/how_to/few_shot_examples.ipynb

@@ -23,7 +23,7 @@
     "- [Prompt templates](/docs/concepts/#prompt-templates)\n",
     "- [Example selectors](/docs/concepts/#example-selectors)\n",
     "- [LLMs](/docs/concepts/#llms)\n",
-    "- [Vectorstores](/docs/concepts/#vectorstores)\n",
+    "- [Vectorstores](/docs/concepts/#vector-stores)\n",
     "\n",
     ":::\n",
     "\n",

docs/docs/how_to/few_shot_examples_chat.ipynb

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

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

@@ -21,7 +21,7 @@ For comprehensive descriptions of every class and function see the [API Referenc
 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/)
 
@@ -80,6 +80,20 @@ These are the core building blocks you can use when building applications.
 - [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
 
@@ -168,15 +182,17 @@ Indexing is the process of keeping your vectorstore in-sync with the underlying
 
 ### Tools
 
-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).
+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
 
@@ -217,6 +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
 
@@ -251,6 +269,7 @@ For a high-level tutorial on building chatbots, check out [this guide](/docs/tut
 - [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
 
@@ -295,7 +314,26 @@ You can peruse [LangGraph how-to guides here](https://langchain-ai.github.io/lan
 ## [LangSmith](https://docs.smith.langchain.com/)
 
 LangSmith allows you to closely trace, monitor and evaluate your LLM application.
-It seamlessly integrates with LangChain, and you can use it to inspect and debug individual steps of your chains as you build.
+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/).
+You can peruse [LangSmith how-to guides here](https://docs.smith.langchain.com/how_to_guides/), but we'll highlight a few sections that are particularly
+relevant to LangChain below:
+
+### 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).
+
+### Tracing
+<span data-heading-keywords="trace,tracing"></span>
+
+Tracing gives you observability inside your chains and agents, and is vital in diagnosing issues.
+
+- [How to: trace with LangChain](https://docs.smith.langchain.com/how_to_guides/tracing/trace_with_langchain)
+- [How to: add metadata and tags to traces](https://docs.smith.langchain.com/how_to_guides/tracing/trace_with_langchain#add-metadata-and-tags-to-traces)
+
+You can see general tracing-related how-tos [in this section of the LangSmith docs](https://docs.smith.langchain.com/how_to_guides/tracing).

docs/docs/how_to/installation.mdx

@@ -2,11 +2,14 @@
 sidebar_position: 2
 ---
 
-# Installation
+# How to install LangChain packages
+
+The LangChain ecosystem is split into different packages, which allow you to choose exactly which pieces of
+functionality to install.
 
 ## Official release
 
-To install LangChain run:
+To install the main LangChain package, run:
 
 import Tabs from '@theme/Tabs';
 import TabItem from '@theme/TabItem';
@@ -21,11 +24,24 @@ import CodeBlock from "@theme/CodeBlock";
   </TabItem>
 </Tabs>
 
-This will install the bare minimum requirements of LangChain.
-A lot of the value of LangChain comes when integrating it with various model providers, datastores, etc.
+While this package acts as a sane starting point to using LangChain,
+much of the value of LangChain comes when integrating it with various model providers, datastores, etc.
 By default, the dependencies needed to do that are NOT installed. You will need to install the dependencies for specific integrations separately.
+We'll show how to do that in the next sections of this guide.
 
-## From source
+## Ecosystem packages
+
+With the exception of the `langsmith` SDK, all packages in the LangChain ecosystem depend on `langchain-core`, which contains base
+classes and abstractions that other packages use. The dependency graph below shows how the difference packages are related.
+A directed arrow indicates that the source package depends on the target package:
+
+![](/img/ecosystem_packages.png)
+
+When installing a package, you do not need to explicitly install that package's explicit dependencies (such as `langchain-core`).
+However, you may choose to if you are using a feature only available in a certain version of that dependency.
+If you do, you should make sure that the installed or pinned version is compatible with any other integration packages you use.
+
+### From source
 
 If you want to install from source, you can do so by cloning the repo and be sure that the directory is `PATH/TO/REPO/langchain/libs/langchain` running:
 
@@ -33,21 +49,21 @@ If you want to install from source, you can do so by cloning the repo and be sur
 pip install -e .
 ```
 
-## LangChain core
+### LangChain core
 The `langchain-core` package contains base abstractions that the rest of the LangChain ecosystem uses, along with the LangChain Expression Language. It is automatically installed by `langchain`, but can also be used separately. Install with:
 
 ```bash
 pip install langchain-core
 ```
 
-## LangChain community
+### LangChain community
 The `langchain-community` package contains third-party integrations. Install with:
 
 ```bash
 pip install langchain-community
 ```
 
-## LangChain experimental
+### LangChain experimental
 The `langchain-experimental` package holds experimental LangChain code, intended for research and experimental uses.
 Install with:
 
@@ -55,14 +71,15 @@ Install with:
 pip install langchain-experimental
 ```
 
-## LangGraph
-`langgraph` is a library for building stateful, multi-actor applications with LLMs, built on top of (and intended to be used with) LangChain.
+### LangGraph
+`langgraph` is a library for building stateful, multi-actor applications with LLMs. It integrates smoothly with LangChain, but can be used without it.
 Install with:
 
 ```bash
 pip install langgraph
 ```
-## LangServe
+
+### LangServe
 LangServe helps developers deploy LangChain runnables and chains as a REST API.
 LangServe is automatically installed by LangChain CLI.
 If not using LangChain CLI, install with:
@@ -80,9 +97,10 @@ Install with:
 pip install langchain-cli
 ```
 
-## LangSmith SDK
-The LangSmith SDK is automatically installed by LangChain.
-If not using LangChain, install with:
+### LangSmith SDK
+The LangSmith SDK is automatically installed by LangChain. However, it does not depend on
+`langchain-core`, and can be installed and used independently if desired.
+If you are not using LangChain, you can install it with:
 
 ```bash
 pip install langsmith

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/message_history.ipynb

@@ -129,7 +129,7 @@
    "id": "a531da5e",
    "metadata": {},
    "source": [
-    "## What is the runnable you are trying wrap?\n",
+    "## What is the runnable you are trying to wrap?\n",
     "\n",
     "`RunnableWithMessageHistory` can only wrap certain types of Runnables. Specifically, it can be used for any Runnable that takes as input one of:\n",
     "\n",
@@ -898,7 +898,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.1"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/docs/how_to/migrate_agent.ipynb

@@ -1,5 +1,19 @@
 {
  "cells": [
+  {
+   "cell_type": "raw",
+   "id": "adc7ee09",
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
+   "source": [
+    "---\n",
+    "keywords: [create_react_agent, create_react_agent()]\n",
+    "---"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "457cdc67-1893-4653-8b0c-b185a5947e74",
@@ -7,9 +21,18 @@
    "source": [
     "# How to migrate from legacy LangChain agents to LangGraph\n",
     "\n",
-    "Here we focus on how to move from legacy LangChain agents to LangGraph agents.\n",
+    ":::info Prerequisites\n",
+    "\n",
+    "This guide assumes familiarity with the following concepts:\n",
+    "- [Agents](/docs/concepts/#agents)\n",
+    "- [LangGraph](https://langchain-ai.github.io/langgraph/)\n",
+    "- [Tool calling](/docs/how_to/tool_calling/)\n",
+    "\n",
+    ":::\n",
+    "\n",
+    "Here we focus on how to move from legacy LangChain agents to more flexible [LangGraph](https://langchain-ai.github.io/langgraph/) agents.\n",
     "LangChain agents (the [AgentExecutor](https://api.python.langchain.com/en/latest/agents/langchain.agents.agent.AgentExecutor.html#langchain.agents.agent.AgentExecutor) in particular) have multiple configuration parameters.\n",
-    "In this notebook we will show how those parameters map to the LangGraph [react agent executor](https://langchain-ai.github.io/langgraph/reference/prebuilt/#create_react_agent).\n",
+    "In this notebook we will show how those parameters map to the LangGraph react agent executor using the [create_react_agent](https://langchain-ai.github.io/langgraph/reference/prebuilt/#create_react_agent) prebuilt helper method.\n",
     "\n",
     "#### Prerequisites\n",
     "\n",
@@ -195,7 +218,7 @@
     "\n",
     "Let's take a look at all of these below. We will pass in custom instructions to get the agent to respond in Spanish.\n",
     "\n",
-    "First up, using AgentExecutor:"
+    "First up, using `AgentExecutor`:"
    ]
   },
   {
@@ -238,7 +261,16 @@
    "id": "bd5f5500-5ae4-4000-a9fd-8c5a2cc6404d",
    "metadata": {},
    "source": [
-    "Now, let's pass a custom system message to [react agent executor](https://langchain-ai.github.io/langgraph/reference/prebuilt/#create_react_agent). This can either be a string or a LangChain SystemMessage."
+    "Now, let's pass a custom system message to [react agent executor](https://langchain-ai.github.io/langgraph/reference/prebuilt/#create_react_agent).\n",
+    "\n",
+    "LangGraph's prebuilt `create_react_agent` does not take a prompt template directly as a parameter, but instead takes a [`messages_modifier`](https://langchain-ai.github.io/langgraph/reference/prebuilt/#create_react_agent) parameter. This modifies messages before they are passed into the model, and can be one of four values:\n",
+    "\n",
+    "- A `SystemMessage`, which is added to the beginning of the list of messages.\n",
+    "- A `string`, which is converted to a `SystemMessage` and added to the beginning of the list of messages.\n",
+    "- A `Callable`, which should take in a list of messages. The output is then passed to the language model.\n",
+    "- Or a [`Runnable`](/docs/concepts/#langchain-expression-language-lcel), which should should take in a list of messages. The output is then passed to the language model.\n",
+    "\n",
+    "Here's how it looks in action:"
    ]
   },
   {
@@ -1212,6 +1244,18 @@
     "except GraphRecursionError as e:\n",
     "    print(\"Stopping agent prematurely due to triggering stop condition\")"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "41377eb8",
+   "metadata": {},
+   "source": [
+    "## Next steps\n",
+    "\n",
+    "You've now learned how to migrate your LangChain agent executors to LangGraph.\n",
+    "\n",
+    "Next, check out other [LangGraph how-to guides](https://langchain-ai.github.io/langgraph/how-tos/)."
+   ]
   }
  ],
  "metadata": {

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/pydantic_compatibility.md

@@ -22,6 +22,7 @@ the case of inheritance and in the case of passing objects to LangChain.
 
 ```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)
@@ -48,6 +49,7 @@ Mixing Pydantic v2 primitives with Pydantic v1 primitives can raise cryptic erro
 
 ```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)
@@ -102,4 +104,4 @@ Tool.from_function( # <-- tool uses v1 namespace
     description="useful for when you need to answer questions about math",
     args_schema=CalculatorInput
 )
-```
+```

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/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

@@ -41,6 +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",
@@ -1003,7 +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

@@ -58,7 +58,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "id": "6d55008f",
    "metadata": {},
    "outputs": [],
@@ -76,22 +76,22 @@
    "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:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": 3,
    "id": "070bf702",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "Joke(setup='Why was the cat sitting on the computer?', punchline='To keep an eye on the mouse!', rating=None)"
+       "Joke(setup='Why was the cat sitting on the computer?', punchline='Because it wanted to keep an eye on the mouse!', rating=8)"
       ]
      },
-     "execution_count": 38,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -250,7 +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."
    ]
   },
   {
@@ -514,12 +514,49 @@
     ")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "91e95aa2",
+   "metadata": {},
+   "source": [
+    "### (Advanced) Raw outputs\n",
+    "\n",
+    "LLMs aren't perfect at generating structured output, especially as schemas become complex. You can avoid raising exceptions and handle the raw output yourself by passing `include_raw=True`. This changes the output format to contain the raw message output, the `parsed` value (if successful), and any resulting errors:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "10ed2842",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'raw': AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_ASK4EmZeZ69Fi3p554Mb4rWy', 'function': {'arguments': '{\"setup\":\"Why was the cat sitting on the computer?\",\"punchline\":\"Because it wanted to keep an eye on the mouse!\"}', 'name': 'Joke'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 36, 'prompt_tokens': 107, 'total_tokens': 143}, 'model_name': 'gpt-4-0125-preview', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-6491d35b-9164-4656-b75c-d7882cfb76cb-0', tool_calls=[{'name': 'Joke', 'args': {'setup': 'Why was the cat sitting on the computer?', 'punchline': 'Because it wanted to keep an eye on the mouse!'}, 'id': 'call_ASK4EmZeZ69Fi3p554Mb4rWy'}], usage_metadata={'input_tokens': 107, 'output_tokens': 36, 'total_tokens': 143}),\n",
+       " 'parsed': Joke(setup='Why was the cat sitting on the computer?', punchline='Because it wanted to keep an eye on the mouse!', rating=None),\n",
+       " 'parsing_error': None}"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "structured_llm = llm.with_structured_output(Joke, include_raw=True)\n",
+    "\n",
+    "structured_llm.invoke(\n",
+    "    \"Tell me a joke about cats, respond in JSON with `setup` and `punchline` keys\"\n",
+    ")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "5e92a98a",
    "metadata": {},
    "source": [
-    "## Prompting and parsing model directly\n",
+    "## Prompting and parsing model outputs directly\n",
     "\n",
     "Not all models support `.with_structured_output()`, since not all models have tool calling or JSON mode support. For such models you'll need to directly prompt the model to use a specific format, and use an output parser to extract the structured response from the raw model output.\n",
     "\n",
@@ -787,9 +824,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "poetry-venv-2",
+   "display_name": "Python 3",
    "language": "python",
-   "name": "poetry-venv-2"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -801,7 +838,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/how_to/tool_calling.ipynb

@@ -1,5 +1,18 @@
 {
  "cells": [
+  {
+   "cell_type": "raw",
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
+   "source": [
+    "---\n",
+    "keywords: [tool calling, tool call]\n",
+    "---"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -11,6 +24,7 @@
     "This guide assumes familiarity with the following concepts:\n",
     "- [Chat models](/docs/concepts/#chat-models)\n",
     "- [LangChain Tools](/docs/concepts/#tools)\n",
+    "- [Output parsers](/docs/concepts/#output-parsers)\n",
     "\n",
     ":::\n",
     "\n",
@@ -38,6 +52,12 @@
     "parameters matching the desired schema, then treat the generated output as your final \n",
     "result.\n",
     "\n",
+    ":::note\n",
+    "\n",
+    "If you only need formatted values, try the [.with_structured_output()](/docs/how_to/structured_output/#the-with_structured_output-method) chat model method as a simpler entrypoint.\n",
+    "\n",
+    ":::\n",
+    "\n",
     "However, tool calling goes beyond [structured output](/docs/how_to/structured_output/)\n",
     "since you can pass responses from called tools back to the model to create longer interactions.\n",
     "For instance, given a search engine tool, an LLM might handle a \n",
@@ -52,8 +72,13 @@
     "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",
@@ -153,7 +178,7 @@
     "# | output: false\n",
     "# | echo: false\n",
     "\n",
-    "%pip install -qU langchain langchain_openai\n",
+    "%pip install -qU langchain_openai\n",
     "\n",
     "import os\n",
     "from getpass import getpass\n",
@@ -167,81 +192,33 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm_with_tools = llm.bind_tools(tools)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "We can also use the `tool_choice` parameter to ensure certain behavior. For example, we can force our tool to call the multiply tool by using the following code:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 4,
    "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})"
+       "AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_g4RuAijtDcSeM96jXyCuiLSN', 'function': {'arguments': '{\"a\":3,\"b\":12}', 'name': 'Multiply'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 18, 'prompt_tokens': 95, 'total_tokens': 113}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-5157d15a-7e0e-4ab1-af48-3d98010cd152-0', tool_calls=[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_g4RuAijtDcSeM96jXyCuiLSN'}], usage_metadata={'input_tokens': 95, 'output_tokens': 18, 'total_tokens': 113})"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "llm_forced_to_multiply = llm.bind_tools(tools, tool_choice=\"Multiply\")\n",
-    "llm_forced_to_multiply.invoke(\"what is 2 + 4\")"
+    "llm_with_tools = llm.bind_tools(tools)\n",
+    "\n",
+    "query = \"What is 3 * 12?\"\n",
+    "\n",
+    "llm_with_tools.invoke(query)"
    ]
   },
   {
    "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": 10,
-   "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})"
-      ]
-     },
-     "execution_count": 10,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "llm_forced_to_use_tool = llm.bind_tools(tools, tool_choice=\"any\")\n",
-    "llm_forced_to_use_tool.invoke(\"What day is today?\")"
-   ]
-  },
-  {
-   "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."
+    "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_tools()](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."
    ]
   },
   {
@@ -273,10 +250,10 @@
       "text/plain": [
        "[{'name': 'Multiply',\n",
        "  'args': {'a': 3, 'b': 12},\n",
-       "  'id': 'call_KquHA7mSbgtAkpkmRPaFnJKa'},\n",
+       "  'id': 'call_TnadLbWJu9HwDULRb51RNSMw'},\n",
        " {'name': 'Add',\n",
        "  'args': {'a': 11, 'b': 49},\n",
-       "  'id': 'call_Fl0hQi4IBTzlpaJYlM5kPQhE'}]"
+       "  'id': 'call_Q9vt1up05sOQScXvUYWzSpCg'}]"
       ]
      },
      "execution_count": 5,
@@ -302,7 +279,8 @@
     "a name, string arguments, identifier, and error message.\n",
     "\n",
     "If desired, [output parsers](/docs/how_to#output-parsers) can further \n",
-    "process the output. For example, we can convert back to the original Pydantic class:"
+    "process the output. For example, we can convert existing values populated on the `.tool_calls` attribute back to the original Pydantic class using the\n",
+    "[PydanticToolsParser](https://api.python.langchain.com/en/latest/output_parsers/langchain_core.output_parsers.openai_tools.PydanticToolsParser.html):"
    ]
   },
   {
@@ -322,443 +300,27 @@
     }
    ],
    "source": [
-    "from langchain_core.output_parsers.openai_tools import PydanticToolsParser\n",
+    "from langchain_core.output_parsers import PydanticToolsParser\n",
     "\n",
     "chain = llm_with_tools | PydanticToolsParser(tools=[Multiply, Add])\n",
     "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"
@@ -781,7 +343,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

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

@@ -12,7 +12,7 @@
     "- [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",
+    "- [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",
@@ -227,7 +227,7 @@
     "\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",
+    "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",
     ":::"
    ]
   }

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_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/chat/ai21.ipynb

@@ -18,7 +18,9 @@
     "# ChatAI21\n",
     "\n",
     "This notebook covers how to get started with AI21 chat models.\n",
-    "\n",
+    "Note that different chat models support different parameters. See the ",
+    "[AI21 documentation](https://docs.ai21.com/reference) to learn more about the parameters in your chosen model.\n",
+    "[See all AI21's LangChain components.](https://pypi.org/project/langchain-ai21/) \n",
     "## Installation"
    ]
   },
@@ -44,7 +46,8 @@
    "source": [
     "## Environment Setup\n",
     "\n",
-    "We'll need to get a [AI21 API key](https://docs.ai21.com/) and set the `AI21_API_KEY` environment variable:\n"
+    "We'll need to get an [AI21 API key](https://docs.ai21.com/) and set the ",
+    "`AI21_API_KEY` environment variable:\n"
    ]
   },
   {

docs/docs/integrations/chat/anthropic.ipynb

@@ -36,7 +36,7 @@
     "| [ChatAnthropic](https://api.python.langchain.com/en/latest/chat_models/langchain_anthropic.chat_models.ChatAnthropic.html) | [langchain-anthropic](https://api.python.langchain.com/en/latest/anthropic_api_reference.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-anthropic?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-anthropic?style=flat-square&label=%20) |\n",
     "\n",
     "### Model features\n",
-    "| [Tool calling](/docs/how_to/tool_calling/) | [Structured output](/docs/how_to/structured_output/) | JSON mode | [Image input](/docs/how_to/multimodal_inputs/) | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | Native async | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
+    "| [Tool calling](/docs/how_to/tool_calling) | [Structured output](/docs/how_to/structured_output/) | JSON mode | [Image input](/docs/how_to/multimodal_inputs/) | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | Native async | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
     "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
     "| ✅ | ✅ | ❌ | ✅ | ❌ | ❌ | ✅ | ✅ | ✅ | ❌ | \n",
     "\n",
@@ -51,7 +51,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "id": "433e8d2b-9519-4b49-b2c4-7ab65b046c94",
    "metadata": {},
    "outputs": [],
@@ -59,7 +59,7 @@
     "import getpass\n",
     "import os\n",
     "\n",
-    "os.environ[\"anthropic_API_KEY\"] = getpass.getpass(\"Enter your Anthropic API key: \")"
+    "os.environ[\"ANTHROPIC_API_KEY\"] = getpass.getpass(\"Enter your Anthropic API key: \")"
    ]
   },
   {
@@ -72,7 +72,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "id": "a15d341e-3e26-4ca3-830b-5aab30ed66de",
    "metadata": {},
    "outputs": [],
@@ -113,7 +113,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 4,
    "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
    "metadata": {},
    "outputs": [],
@@ -121,7 +121,7 @@
     "from langchain_anthropic import ChatAnthropic\n",
     "\n",
     "llm = ChatAnthropic(\n",
-    "    model=\"claude-3-sonnet-20240229\",\n",
+    "    model=\"claude-3-5-sonnet-20240620\",\n",
     "    temperature=0,\n",
     "    max_tokens=1024,\n",
     "    timeout=None,\n",
@@ -140,7 +140,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 5,
    "id": "62e0dbc3",
    "metadata": {
     "tags": []
@@ -149,10 +149,10 @@
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"Voici la traduction en français :\\n\\nJ'aime la programmation.\", response_metadata={'id': 'msg_013qztabaFADNnKsHR1rdrju', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 29, 'output_tokens': 21}}, id='run-a22ab30c-7e09-48f5-bc27-a08a9d8f7fa1-0', usage_metadata={'input_tokens': 29, 'output_tokens': 21, 'total_tokens': 50})"
+       "AIMessage(content=\"J'adore la programmation.\", response_metadata={'id': 'msg_018Nnu76krRPq8HvgKLW4F8T', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 29, 'output_tokens': 11}}, id='run-57e9295f-db8a-48dc-9619-babd2bedd891-0', usage_metadata={'input_tokens': 29, 'output_tokens': 11, 'total_tokens': 40})"
       ]
      },
-     "execution_count": 2,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -171,7 +171,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 6,
    "id": "d86145b3-bfef-46e8-b227-4dda5c9c2705",
    "metadata": {},
    "outputs": [
@@ -179,9 +179,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Voici la traduction en français :\n",
-      "\n",
-      "J'aime la programmation.\n"
+      "J'adore la programmation.\n"
      ]
     }
    ],
@@ -201,17 +199,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 7,
    "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='Ich liebe Programmieren.', response_metadata={'id': 'msg_01FWrA8w9HbjqYPTQ7VryUnp', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 23, 'output_tokens': 11}}, id='run-b749bf20-b46d-4d62-ac73-f59adab6dd7e-0', usage_metadata={'input_tokens': 23, 'output_tokens': 11, 'total_tokens': 34})"
+       "AIMessage(content=\"Here's the German translation:\\n\\nIch liebe Programmieren.\", response_metadata={'id': 'msg_01GhkRtQZUkA5Ge9hqmD8HGY', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 23, 'output_tokens': 18}}, id='run-da5906b4-b200-4e08-b81a-64d4453643b6-0', usage_metadata={'input_tokens': 23, 'output_tokens': 18, 'total_tokens': 41})"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -251,22 +249,26 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 8,
    "id": "4a374a24-2534-4e6f-825b-30fab7bbe0cb",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[{'text': \"Okay, let's use the GetWeather tool to check the current temperatures in Los Angeles and New York City.\",\n",
+       "[{'text': \"To answer this question, we'll need to check the current weather in both Los Angeles (LA) and New York (NY). I'll use the GetWeather function to retrieve this information for both cities.\",\n",
        "  'type': 'text'},\n",
-       " {'id': 'toolu_01Tnp5tL7LJZaVyQXKEjbqcC',\n",
+       " {'id': 'toolu_01Ddzj5PkuZkrjF4tafzu54A',\n",
        "  'input': {'location': 'Los Angeles, CA'},\n",
        "  'name': 'GetWeather',\n",
+       "  'type': 'tool_use'},\n",
+       " {'id': 'toolu_012kz4qHZQqD4qg8sFPeKqpP',\n",
+       "  'input': {'location': 'New York, NY'},\n",
+       "  'name': 'GetWeather',\n",
        "  'type': 'tool_use'}]"
       ]
      },
-     "execution_count": 10,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -288,7 +290,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 9,
    "id": "6b4a1ead-952c-489f-a8d4-355d3fb55f3f",
    "metadata": {},
    "outputs": [
@@ -297,10 +299,13 @@
       "text/plain": [
        "[{'name': 'GetWeather',\n",
        "  'args': {'location': 'Los Angeles, CA'},\n",
-       "  'id': 'toolu_01Tnp5tL7LJZaVyQXKEjbqcC'}]"
+       "  'id': 'toolu_01Ddzj5PkuZkrjF4tafzu54A'},\n",
+       " {'name': 'GetWeather',\n",
+       "  'args': {'location': 'New York, NY'},\n",
+       "  'id': 'toolu_012kz4qHZQqD4qg8sFPeKqpP'}]"
       ]
      },
-     "execution_count": 11,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -336,7 +341,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/azure_chat_openai.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "raw",
-   "id": "641f8cb0",
+   "id": "afaf8039",
    "metadata": {},
    "source": [
     "---\n",
@@ -12,20 +12,89 @@
   },
   {
    "cell_type": "markdown",
-   "id": "38f26d7a",
+   "id": "e49f1e0d",
    "metadata": {},
    "source": [
     "# AzureChatOpenAI\n",
     "\n",
-    ">[Azure OpenAI Service](https://learn.microsoft.com/en-us/azure/ai-services/openai/overview) provides REST API access to OpenAI's powerful language models including the GPT-4, GPT-3.5-Turbo, and Embeddings model series. These models can be easily adapted to your specific task including but not limited to content generation, summarization, semantic search, and natural language to code translation. Users can access the service through REST APIs, Python SDK, or a web-based interface in the Azure OpenAI Studio.\n",
+    "This guide will help you get started with AzureOpenAI [chat models](/docs/concepts/#chat-models). For detailed documentation of all AzureChatOpenAI features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/chat_models/langchain_openai.chat_models.azure.AzureChatOpenAI.html).\n",
     "\n",
-    "This notebook goes over how to connect to an Azure-hosted OpenAI endpoint. First, we need to install the `langchain-openai` package."
+    "Azure OpenAI has several chat models. You can find information about their latest models and their costs, context windows, and supported input types in the [Azure docs](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models).\n",
+    "\n",
+    ":::info Azure OpenAI vs OpenAI\n",
+    "\n",
+    "Azure OpenAI refers to OpenAI models hosted on the [Microsoft Azure platform](https://azure.microsoft.com/en-us/products/ai-services/openai-service). OpenAI also provides its own model APIs. To access OpenAI services directly, use the [ChatOpenAI integration](/docs/integrations/chat/openai/).\n",
+    "\n",
+    ":::\n",
+    "\n",
+    "## Overview\n",
+    "### Integration details\n",
+    "\n",
+    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/v0.2/docs/integrations/chat/azure) | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+    "| [AzureChatOpenAI](https://api.python.langchain.com/en/latest/chat_models/langchain_openai.chat_models.azure.AzureChatOpenAI.html) | [langchain-openai](https://api.python.langchain.com/en/latest/openai_api_reference.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-openai?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-openai?style=flat-square&label=%20) |\n",
+    "\n",
+    "### Model features\n",
+    "| [Tool calling](/docs/how_to/tool_calling) | [Structured output](/docs/how_to/structured_output/) | JSON mode | [Image input](/docs/how_to/multimodal_inputs/) | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | Native async | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
+    "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
+    "| ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | ✅ | ✅ | ✅ | ✅ | \n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "To access AzureOpenAI models you'll need to create an Azure account, create a deployment of an Azure OpenAI model, get the name and endpoint for your deployment, get an Azure OpenAI API key, and install the `langchain-openai` integration package.\n",
+    "\n",
+    "### Credentials\n",
+    "\n",
+    "Head to the [Azure docs](https://learn.microsoft.com/en-us/azure/ai-services/openai/chatgpt-quickstart?tabs=command-line%2Cpython-new&pivots=programming-language-python) to create your deployment and generate an API key. Once you've done this set the AZURE_OPENAI_API_KEY and AZURE_OPENAI_ENDPOINT environment variables:"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "d83ba7de",
+   "id": "433e8d2b-9519-4b49-b2c4-7ab65b046c94",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "os.environ[\"AZURE_OPENAI_API_KEY\"] = getpass.getpass(\"Enter your AzureOpenAI API key: \")\n",
+    "os.environ[\"AZURE_OPENAI_ENDPOINT\"] = \"https://YOUR-ENDPOINT.openai.azure.com/\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "72ee0c4b-9764-423a-9dbf-95129e185210",
+   "metadata": {},
+   "source": [
+    "If you want to get automated tracing of your model calls you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a15d341e-3e26-4ca3-830b-5aab30ed66de",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
+    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0730d6a1-c893-4840-9817-5e5251676d5d",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "The LangChain AzureOpenAI integration lives in the `langchain-openai` package:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -34,65 +103,56 @@
   },
   {
    "cell_type": "markdown",
-   "id": "e39133c8",
-   "metadata": {
-    "vscode": {
-     "languageId": "raw"
-    }
-   },
+   "id": "a38cde65-254d-4219-a441-068766c0d4b5",
+   "metadata": {},
    "source": [
-    "Next, let's set some environment variables to help us connect to the Azure OpenAI service. You can find these values in the Azure portal."
+    "## Instantiation\n",
+    "\n",
+    "Now we can instantiate our model object and generate chat completions.\n",
+    "- Replace `azure_deployment` with the name of your deployment,\n",
+    "- You can find the latest supported `api_version` here: https://learn.microsoft.com/en-us/azure/ai-services/openai/reference."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "1d8d73bd",
+   "execution_count": 1,
+   "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
    "metadata": {},
    "outputs": [],
    "source": [
-    "import os\n",
+    "from langchain_openai import AzureChatOpenAI\n",
     "\n",
-    "os.environ[\"AZURE_OPENAI_API_KEY\"] = \"...\"\n",
-    "os.environ[\"AZURE_OPENAI_ENDPOINT\"] = \"https://<your-endpoint>.openai.azure.com/\"\n",
-    "os.environ[\"AZURE_OPENAI_API_VERSION\"] = \"2023-06-01-preview\"\n",
-    "os.environ[\"AZURE_OPENAI_CHAT_DEPLOYMENT_NAME\"] = \"chat\""
+    "llm = AzureChatOpenAI(\n",
+    "    azure_deployment=\"YOUR-DEPLOYMENT\",\n",
+    "    api_version=\"2024-05-01-preview\",\n",
+    "    temperature=0,\n",
+    "    max_tokens=None,\n",
+    "    timeout=None,\n",
+    "    max_retries=2,\n",
+    "    # other params...\n",
+    ")"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "e7b160f8",
+   "id": "2b4f3e15",
    "metadata": {},
    "source": [
-    "Next, let's construct our model and chat with it:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "cbe4bb58-ba13-4355-8af9-cd990dc47a64",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "from langchain_openai import AzureChatOpenAI\n",
-    "\n",
-    "model = AzureChatOpenAI(\n",
-    "    openai_api_version=os.environ[\"AZURE_OPENAI_API_VERSION\"],\n",
-    "    azure_deployment=os.environ[\"AZURE_OPENAI_CHAT_DEPLOYMENT_NAME\"],\n",
-    ")"
+    "## Invocation"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 4,
-   "id": "99509140",
-   "metadata": {},
+   "id": "62e0dbc3",
+   "metadata": {
+    "tags": []
+   },
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"J'adore programmer.\", response_metadata={'token_usage': {'completion_tokens': 6, 'prompt_tokens': 19, 'total_tokens': 25}, 'model_name': 'gpt-35-turbo', 'system_fingerprint': None, 'prompt_filter_results': [{'prompt_index': 0, 'content_filter_results': {'hate': {'filtered': False, 'severity': 'safe'}, 'self_harm': {'filtered': False, 'severity': 'safe'}, 'sexual': {'filtered': False, 'severity': 'safe'}, 'violence': {'filtered': False, 'severity': 'safe'}}}], 'finish_reason': 'stop', 'logprobs': None, 'content_filter_results': {'hate': {'filtered': False, 'severity': 'safe'}, 'self_harm': {'filtered': False, 'severity': 'safe'}, 'sexual': {'filtered': False, 'severity': 'safe'}, 'violence': {'filtered': False, 'severity': 'safe'}}}, id='run-25ed88db-38f2-4b0c-a943-a03f217711a9-0')"
+       "AIMessage(content=\"J'adore la programmation.\", response_metadata={'token_usage': {'completion_tokens': 8, 'prompt_tokens': 31, 'total_tokens': 39}, 'model_name': 'gpt-35-turbo', 'system_fingerprint': None, 'prompt_filter_results': [{'prompt_index': 0, 'content_filter_results': {'hate': {'filtered': False, 'severity': 'safe'}, 'self_harm': {'filtered': False, 'severity': 'safe'}, 'sexual': {'filtered': False, 'severity': 'safe'}, 'violence': {'filtered': False, 'severity': 'safe'}}}], 'finish_reason': 'stop', 'logprobs': None, 'content_filter_results': {'hate': {'filtered': False, 'severity': 'safe'}, 'self_harm': {'filtered': False, 'severity': 'safe'}, 'sexual': {'filtered': False, 'severity': 'safe'}, 'violence': {'filtered': False, 'severity': 'safe'}}}, id='run-a6a732c2-cb02-4e50-9a9c-ab30eab034fc-0', usage_metadata={'input_tokens': 31, 'output_tokens': 8, 'total_tokens': 39})"
       ]
      },
      "execution_count": 4,
@@ -101,95 +161,165 @@
     }
    ],
    "source": [
-    "message = HumanMessage(\n",
-    "    content=\"Translate this sentence from English to French. I love programming.\"\n",
-    ")\n",
-    "model.invoke([message])"
+    "messages = [\n",
+    "    (\n",
+    "        \"system\",\n",
+    "        \"You are a helpful assistant that translates English to French. Translate the user sentence.\",\n",
+    "    ),\n",
+    "    (\"human\", \"I love programming.\"),\n",
+    "]\n",
+    "ai_msg = llm.invoke(messages)\n",
+    "ai_msg"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "d86145b3-bfef-46e8-b227-4dda5c9c2705",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "J'adore la programmation.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(ai_msg.content)"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "f27fa24d",
+   "id": "18e2bfc0-7e78-4528-a73f-499ac150dca8",
    "metadata": {},
    "source": [
-    "## Model Version\n",
-    "Azure OpenAI responses contain `model` property, which is name of the model used to generate the response. However unlike native OpenAI responses, it does not contain the version of the model, which is set on the deployment in Azure. This makes it tricky to know which version of the model was used to generate the response, which as result can lead to e.g. wrong total cost calculation with `OpenAICallbackHandler`.\n",
+    "## Chaining\n",
+    "\n",
+    "We can [chain](/docs/how_to/sequence/) our model with a prompt template like so:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='Ich liebe das Programmieren.', response_metadata={'token_usage': {'completion_tokens': 6, 'prompt_tokens': 26, 'total_tokens': 32}, 'model_name': 'gpt-35-turbo', 'system_fingerprint': None, 'prompt_filter_results': [{'prompt_index': 0, 'content_filter_results': {'hate': {'filtered': False, 'severity': 'safe'}, 'self_harm': {'filtered': False, 'severity': 'safe'}, 'sexual': {'filtered': False, 'severity': 'safe'}, 'violence': {'filtered': False, 'severity': 'safe'}}}], 'finish_reason': 'stop', 'logprobs': None, 'content_filter_results': {'hate': {'filtered': False, 'severity': 'safe'}, 'self_harm': {'filtered': False, 'severity': 'safe'}, 'sexual': {'filtered': False, 'severity': 'safe'}, 'violence': {'filtered': False, 'severity': 'safe'}}}, id='run-084967d7-06f2-441f-b5c1-477e2a9e9d03-0', usage_metadata={'input_tokens': 26, 'output_tokens': 6, 'total_tokens': 32})"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            \"You are a helpful assistant that translates {input_language} to {output_language}.\",\n",
+    "        ),\n",
+    "        (\"human\", \"{input}\"),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "chain = prompt | llm\n",
+    "chain.invoke(\n",
+    "    {\n",
+    "        \"input_language\": \"English\",\n",
+    "        \"output_language\": \"German\",\n",
+    "        \"input\": \"I love programming.\",\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d1ee55bc-ffc8-4cfa-801c-993953a08cfd",
+   "metadata": {},
+   "source": [
+    "## Specifying model version\n",
+    "\n",
+    "Azure OpenAI responses contain `model_name` response metadata property, which is name of the model used to generate the response. However unlike native OpenAI responses, it does not contain the specific version of the model, which is set on the deployment in Azure. E.g. it does not distinguish between `gpt-35-turbo-0125` and `gpt-35-turbo-0301`. This makes it tricky to know which version of the model was used to generate the response, which as result can lead to e.g. wrong total cost calculation with `OpenAICallbackHandler`.\n",
     "\n",
     "To solve this problem, you can pass `model_version` parameter to `AzureChatOpenAI` class, which will be added to the model name in the llm output. This way you can easily distinguish between different versions of the model."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
-   "id": "0531798a",
+   "execution_count": null,
+   "id": "04b36e75-e8b7-4721-899e-76301ac2ecd9",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.callbacks import get_openai_callback"
+    "%pip install -qU langchain-community"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
-   "id": "aceddb72",
-   "metadata": {
-    "scrolled": true
-   },
+   "execution_count": 5,
+   "id": "84c411b0-1790-4798-8bb7-47d8ece4c2dc",
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Total Cost (USD): $0.000041\n"
+      "Total Cost (USD): $0.000063\n"
      ]
     }
    ],
    "source": [
-    "model = AzureChatOpenAI(\n",
-    "    openai_api_version=os.environ[\"AZURE_OPENAI_API_VERSION\"],\n",
-    "    azure_deployment=os.environ[\n",
-    "        \"AZURE_OPENAI_CHAT_DEPLOYMENT_NAME\"\n",
-    "    ],  # in Azure, this deployment has version 0613 - input and output tokens are counted separately\n",
-    ")\n",
+    "from langchain_community.callbacks import get_openai_callback\n",
+    "\n",
     "with get_openai_callback() as cb:\n",
-    "    model.invoke([message])\n",
+    "    llm.invoke(messages)\n",
     "    print(\n",
     "        f\"Total Cost (USD): ${format(cb.total_cost, '.6f')}\"\n",
     "    )  # without specifying the model version, flat-rate 0.002 USD per 1k input and output tokens is used"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "2e61eefd",
-   "metadata": {},
-   "source": [
-    "We can provide the model version to `AzureChatOpenAI` constructor. It will get appended to the model name returned by Azure OpenAI and cost will be counted correctly."
-   ]
-  },
   {
    "cell_type": "code",
-   "execution_count": 11,
-   "id": "8d5e54e9",
+   "execution_count": 6,
+   "id": "21234693-d92b-4d69-8a7f-55aa062084bf",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Total Cost (USD): $0.000044\n"
+      "Total Cost (USD): $0.000078\n"
      ]
     }
    ],
    "source": [
-    "model0301 = AzureChatOpenAI(\n",
-    "    openai_api_version=os.environ[\"AZURE_OPENAI_API_VERSION\"],\n",
-    "    azure_deployment=os.environ[\"AZURE_OPENAI_CHAT_DEPLOYMENT_NAME\"],\n",
+    "llm_0301 = AzureChatOpenAI(\n",
+    "    azure_deployment=\"YOUR-DEPLOYMENT\",\n",
+    "    api_version=\"2024-05-01-preview\",\n",
     "    model_version=\"0301\",\n",
     ")\n",
     "with get_openai_callback() as cb:\n",
-    "    model0301.invoke([message])\n",
+    "    llm_0301.invoke(messages)\n",
     "    print(f\"Total Cost (USD): ${format(cb.total_cost, '.6f')}\")"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all AzureChatOpenAI features and configurations head to the API reference: https://api.python.langchain.com/en/latest/chat_models/langchain_openai.chat_models.azure.AzureChatOpenAI.html"
+   ]
   }
  ],
  "metadata": {
@@ -208,7 +338,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.11.9"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/bedrock.ipynb

@@ -2,86 +2,125 @@
  "cells": [
   {
    "cell_type": "raw",
-   "id": "fbc66410",
-   "metadata": {
-    "vscode": {
-     "languageId": "raw"
-    }
-   },
+   "id": "afaf8039",
+   "metadata": {},
    "source": [
     "---\n",
-    "sidebar_label: Bedrock\n",
+    "sidebar_label: AWS Bedrock\n",
     "---"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "bf733a38-db84-4363-89e2-de6735c37230",
+   "id": "e49f1e0d",
    "metadata": {},
    "source": [
     "# ChatBedrock\n",
     "\n",
-    ">[Amazon Bedrock](https://aws.amazon.com/bedrock/) is a fully managed service that offers a choice of \n",
-    "> high-performing foundation models (FMs) from leading AI companies like `AI21 Labs`, `Anthropic`, `Cohere`, \n",
-    "> `Meta`, `Stability AI`, and `Amazon` via a single API, along with a broad set of capabilities you need to \n",
-    "> build generative AI applications with security, privacy, and responsible AI. Using `Amazon Bedrock`, \n",
-    "> you can easily experiment with and evaluate top FMs for your use case, privately customize them with \n",
-    "> your data using techniques such as fine-tuning and `Retrieval Augmented Generation` (`RAG`), and build \n",
-    "> agents that execute tasks using your enterprise systems and data sources. Since `Amazon Bedrock` is \n",
-    "> serverless, you don't have to manage any infrastructure, and you can securely integrate and deploy \n",
-    "> generative AI capabilities into your applications using the AWS services you are already familiar with.\n"
+    "This doc will help you get started with AWS Bedrock [chat models](/docs/concepts/#chat-models). Amazon Bedrock is a fully managed service that offers a choice of high-performing foundation models (FMs) from leading AI companies like AI21 Labs, Anthropic, Cohere, Meta, Stability AI, and Amazon via a single API, along with a broad set of capabilities you need to build generative AI applications with security, privacy, and responsible AI. Using Amazon Bedrock, you can easily experiment with and evaluate top FMs for your use case, privately customize them with your data using techniques such as fine-tuning and Retrieval Augmented Generation (RAG), and build agents that execute tasks using your enterprise systems and data sources. Since Amazon Bedrock is serverless, you don't have to manage any infrastructure, and you can securely integrate and deploy generative AI capabilities into your applications using the AWS services you are already familiar with.\n",
+    "\n",
+    "For more information on which models are accessible via Bedrock, head to the [AWS docs](https://docs.aws.amazon.com/bedrock/latest/userguide/models-features.html).\n",
+    "\n",
+    "For detailed documentation of all ChatBedrock features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/chat_models/langchain_aws.chat_models.bedrock.ChatBedrock.html).\n",
+    "\n",
+    "## Overview\n",
+    "### Integration details\n",
+    "\n",
+    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/v0.2/docs/integrations/chat/bedrock) | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+    "| [ChatBedrock](https://api.python.langchain.com/en/latest/chat_models/langchain_aws.chat_models.bedrock.ChatBedrock.html) | [langchain-aws](https://api.python.langchain.com/en/latest/aws_api_reference.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-aws?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-aws?style=flat-square&label=%20) |\n",
+    "\n",
+    "### Model features\n",
+    "| [Tool calling](/docs/how_to/tool_calling) | [Structured output](/docs/how_to/structured_output/) | JSON mode | [Image input](/docs/how_to/multimodal_inputs/) | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | Native async | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
+    "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
+    "| ✅ | ✅ | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | ✅ | ❌ | \n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "To access Bedrock models you'll need to create an AWS account, set up the Bedrock API service, get an access key ID and secret key, and install the `langchain-aws` integration package.\n",
+    "\n",
+    "### Credentials\n",
+    "\n",
+    "Head to the [AWS docs](https://docs.aws.amazon.com/bedrock/latest/userguide/setting-up.html) to sign up to AWS and setup your credentials. You'll also need to turn on model access for your account, which you can do by following [these instructions](https://docs.aws.amazon.com/bedrock/latest/userguide/model-access.html)."
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "d51edc81",
+   "cell_type": "markdown",
+   "id": "72ee0c4b-9764-423a-9dbf-95129e185210",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Note: you may need to restart the kernel to use updated packages.\n"
-     ]
-    }
-   ],
    "source": [
-    "%pip install --upgrade --quiet  langchain-aws"
+    "If you want to get automated tracing of your model calls you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
-   "id": "d4a7c55d-b235-4ca4-a579-c90cc9570da9",
-   "metadata": {
-    "tags": []
-   },
+   "execution_count": null,
+   "id": "a15d341e-3e26-4ca3-830b-5aab30ed66de",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
+    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0730d6a1-c893-4840-9817-5e5251676d5d",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "The LangChain Bedrock integration lives in the `langchain-aws` package:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU langchain-aws"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a38cde65-254d-4219-a441-068766c0d4b5",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "Now we can instantiate our model object and generate chat completions:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
+   "metadata": {},
    "outputs": [],
    "source": [
     "from langchain_aws import ChatBedrock\n",
-    "from langchain_core.messages import HumanMessage"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "70cf04e8-423a-4ff6-8b09-f11fb711c817",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "chat = ChatBedrock(\n",
+    "\n",
+    "llm = ChatBedrock(\n",
     "    model_id=\"anthropic.claude-3-sonnet-20240229-v1:0\",\n",
-    "    model_kwargs={\"temperature\": 0.1},\n",
+    "    model_kwargs=dict(temperature=0),\n",
+    "    # other params...\n",
     ")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "2b4f3e15",
+   "metadata": {},
+   "source": [
+    "## Invocation"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 12,
-   "id": "8199ef8f-eb8b-4253-9ea0-6c24a013ca4c",
+   "execution_count": 5,
+   "id": "62e0dbc3",
    "metadata": {
     "tags": []
    },
@@ -89,38 +128,30 @@
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"Voici la traduction en français :\\n\\nJ'aime la programmation.\", additional_kwargs={'usage': {'prompt_tokens': 20, 'completion_tokens': 21, 'total_tokens': 41}}, response_metadata={'model_id': 'anthropic.claude-3-sonnet-20240229-v1:0', 'usage': {'prompt_tokens': 20, 'completion_tokens': 21, 'total_tokens': 41}}, id='run-994f0362-0e50-4524-afad-3c4f5bb11328-0')"
+       "AIMessage(content=\"Voici la traduction en français :\\n\\nJ'aime la programmation.\", additional_kwargs={'usage': {'prompt_tokens': 29, 'completion_tokens': 21, 'total_tokens': 50}, 'stop_reason': 'end_turn', 'model_id': 'anthropic.claude-3-sonnet-20240229-v1:0'}, response_metadata={'usage': {'prompt_tokens': 29, 'completion_tokens': 21, 'total_tokens': 50}, 'stop_reason': 'end_turn', 'model_id': 'anthropic.claude-3-sonnet-20240229-v1:0'}, id='run-fdb07dc3-ff72-430d-b22b-e7824b15c766-0', usage_metadata={'input_tokens': 29, 'output_tokens': 21, 'total_tokens': 50})"
       ]
      },
-     "execution_count": 12,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
     "messages = [\n",
-    "    HumanMessage(\n",
-    "        content=\"Translate this sentence from English to French. I love programming.\"\n",
-    "    )\n",
+    "    (\n",
+    "        \"system\",\n",
+    "        \"You are a helpful assistant that translates English to French. Translate the user sentence.\",\n",
+    "    ),\n",
+    "    (\"human\", \"I love programming.\"),\n",
     "]\n",
-    "chat.invoke(messages)"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "id": "a4a4f4d4",
-   "metadata": {},
-   "source": [
-    "### Streaming\n",
-    "\n",
-    "To stream responses, you can use the runnable `.stream()` method."
+    "ai_msg = llm.invoke(messages)\n",
+    "ai_msg"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
-   "id": "d9e52838",
+   "execution_count": 6,
+   "id": "d86145b3-bfef-46e8-b227-4dda5c9c2705",
    "metadata": {},
    "outputs": [
     {
@@ -129,84 +160,124 @@
      "text": [
       "Voici la traduction en français :\n",
       "\n",
-      "J'aime la programmation."
+      "J'aime la programmation.\n"
      ]
     }
    ],
    "source": [
-    "for chunk in chat.stream(messages):\n",
-    "    print(chunk.content, end=\"\", flush=True)"
+    "print(ai_msg.content)"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "c36575b3",
+   "id": "18e2bfc0-7e78-4528-a73f-499ac150dca8",
    "metadata": {},
    "source": [
-    "### LLM Caching with OpenSearch Semantic Cache\n",
+    "## Chaining\n",
     "\n",
-    "Use OpenSearch as a semantic cache to cache prompts and responses and evaluate hits based on semantic similarity.\n",
-    "\n"
+    "We can [chain](/docs/how_to/sequence/) our model with a prompt template like so:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "375d4e56",
+   "execution_count": 7,
+   "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='Ich liebe Programmieren.', additional_kwargs={'usage': {'prompt_tokens': 23, 'completion_tokens': 11, 'total_tokens': 34}, 'stop_reason': 'end_turn', 'model_id': 'anthropic.claude-3-sonnet-20240229-v1:0'}, response_metadata={'usage': {'prompt_tokens': 23, 'completion_tokens': 11, 'total_tokens': 34}, 'stop_reason': 'end_turn', 'model_id': 'anthropic.claude-3-sonnet-20240229-v1:0'}, id='run-5ad005ce-9f31-4670-baa0-9373d418698a-0', usage_metadata={'input_tokens': 23, 'output_tokens': 11, 'total_tokens': 34})"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "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",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
     "\n",
-    "bedrock_embeddings = BedrockEmbeddings(\n",
-    "    model_id=\"amazon.titan-embed-text-v1\", region_name=\"us-east-1\"\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            \"You are a helpful assistant that translates {input_language} to {output_language}.\",\n",
+    "        ),\n",
+    "        (\"human\", \"{input}\"),\n",
+    "    ]\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",
+    "chain = prompt | llm\n",
+    "chain.invoke(\n",
+    "    {\n",
+    "        \"input_language\": \"English\",\n",
+    "        \"output_language\": \"German\",\n",
+    "        \"input\": \"I love programming.\",\n",
+    "    }\n",
     ")"
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "bb5d25bb",
+   "cell_type": "markdown",
+   "id": "d1ee55bc-ffc8-4cfa-801c-993953a08cfd",
    "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",
+    "## ***Beta***: Bedrock Converse API\n",
     "\n",
-    "print(response_text)"
+    "AWS has recently recently the Bedrock Converse API which provides a unified conversational interface for Bedrock models. This API does not yet support custom models. You can see a list of all [models that are supported here](https://docs.aws.amazon.com/bedrock/latest/userguide/conversation-inference.html). To improve reliability the ChatBedrock integration will switch to using the Bedrock Converse API as soon as it has feature parity with the existing Bedrock API. Until then a separate [ChatBedrockConverse](https://api.python.langchain.com/en/latest/chat_models/langchain_aws.chat_models.bedrock_converse.ChatBedrockConverse.html#langchain_aws.chat_models.bedrock_converse.ChatBedrockConverse) integration has been released in beta for users who do not need to use custom models.\n",
+    "\n",
+    "You can use it like so:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "6cfb3086",
+   "execution_count": 8,
+   "id": "ae728e59-94d4-40cf-9d24-25ad8723fc59",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/bagatur/langchain/libs/core/langchain_core/_api/beta_decorator.py:87: LangChainBetaWarning: The class `ChatBedrockConverse` is in beta. It is actively being worked on, so the API may change.\n",
+      "  warn_beta(\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"Voici la traduction en français :\\n\\nJ'aime la programmation.\", response_metadata={'ResponseMetadata': {'RequestId': '122fb1c8-c3c5-4b06-941e-c95d210bfbc7', 'HTTPStatusCode': 200, 'HTTPHeaders': {'date': 'Mon, 01 Jul 2024 21:48:25 GMT', 'content-type': 'application/json', 'content-length': '243', 'connection': 'keep-alive', 'x-amzn-requestid': '122fb1c8-c3c5-4b06-941e-c95d210bfbc7'}, 'RetryAttempts': 0}, 'stopReason': 'end_turn', 'metrics': {'latencyMs': 830}}, id='run-0e3df22f-fcd8-4fbb-a4fb-565227e7e430-0', usage_metadata={'input_tokens': 29, 'output_tokens': 21, 'total_tokens': 50})"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "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",
+    "from langchain_aws import ChatBedrockConverse\n",
     "\n",
-    "messages = [HumanMessage(content=\"what is amazon bedrock\")]\n",
-    "response_text = chat.invoke(messages)\n",
+    "llm = ChatBedrockConverse(\n",
+    "    model=\"anthropic.claude-3-sonnet-20240229-v1:0\",\n",
+    "    temperature=0,\n",
+    "    max_tokens=None,\n",
+    "    # other params...\n",
+    ")\n",
     "\n",
-    "print(response_text)"
+    "llm.invoke(messages)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all ChatBedrock features and configurations head to the API reference: https://api.python.langchain.com/en/latest/chat_models/langchain_aws.chat_models.bedrock.ChatBedrock.html\n",
+    "\n",
+    "For detailed documentation of all ChatBedrockConverse features and configurations head to the API reference: https://api.python.langchain.com/en/latest/chat_models/langchain_aws.chat_models.bedrock_converse.ChatBedrockConverse.html"
    ]
   }
  ],
@@ -226,7 +297,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.11.9"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/cohere.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "raw",
-   "id": "53fbf15f",
+   "id": "afaf8039",
    "metadata": {},
    "source": [
     "---\n",
@@ -12,103 +12,129 @@
   },
   {
    "cell_type": "markdown",
-   "id": "bf733a38-db84-4363-89e2-de6735c37230",
+   "id": "e49f1e0d",
    "metadata": {},
    "source": [
-    "# Cohere\n",
+    "# ChatCohere\n",
     "\n",
-    "This notebook covers how to get started with [Cohere chat models](https://cohere.com/chat).\n",
+    "This doc will help you get started with Cohere [chat models](/docs/concepts/#chat-models). For detailed documentation of all ChatCohere features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/chat_models/langchain_cohere.chat_models.ChatCohere.html).\n",
+    "\n",
+    "For an overview of all Cohere models head to the [Cohere docs](https://docs.cohere.com/docs/models).\n",
+    "\n",
+    "## Overview\n",
+    "### Integration details\n",
+    "\n",
+    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/v0.2/docs/integrations/chat/cohere) | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+    "| [ChatCohere](https://api.python.langchain.com/en/latest/chat_models/langchain_cohere.chat_models.ChatCohere.html) | [langchain-cohere](https://api.python.langchain.com/en/latest/cohere_api_reference.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-cohere?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-cohere?style=flat-square&label=%20) |\n",
+    "\n",
+    "### Model features\n",
+    "| [Tool calling](/docs/how_to/tool_calling) | [Structured output](/docs/how_to/structured_output/) | JSON mode | [Image input](/docs/how_to/multimodal_inputs/) | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | Native async | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
+    "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
+    "| ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | \n",
     "\n",
-    "Head to the [API reference](https://api.python.langchain.com/en/latest/chat_models/langchain_community.chat_models.cohere.ChatCohere.html) for detailed documentation of all attributes and methods."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "3607d67e-e56c-4102-bbba-df2edc0e109e",
-   "metadata": {},
-   "source": [
     "## Setup\n",
     "\n",
-    "The integration lives in the `langchain-cohere` package. We can install these with:\n",
+    "To access Cohere models you'll need to create a Cohere account, get an API key, and install the `langchain-cohere` integration package.\n",
     "\n",
-    "```bash\n",
-    "pip install -U langchain-cohere\n",
-    "```\n",
+    "### Credentials\n",
     "\n",
-    "We'll also need to get a [Cohere API key](https://cohere.com/) and set the `COHERE_API_KEY` environment variable:"
+    "Head to https://dashboard.cohere.com/welcome/login to sign up to Cohere and generate an API key. Once you've done this set the COHERE_API_KEY environment variable:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
-   "id": "2108b517-1e8d-473d-92fa-4f930e8072a7",
+   "execution_count": null,
+   "id": "433e8d2b-9519-4b49-b2c4-7ab65b046c94",
    "metadata": {},
    "outputs": [],
    "source": [
     "import getpass\n",
     "import os\n",
     "\n",
-    "os.environ[\"COHERE_API_KEY\"] = getpass.getpass()"
+    "os.environ[\"COHERE_API_KEY\"] = getpass.getpass(\"Enter your Cohere API key: \")"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "cf690fbb",
+   "id": "72ee0c4b-9764-423a-9dbf-95129e185210",
    "metadata": {},
    "source": [
-    "It's also helpful (but not needed) to set up [LangSmith](https://smith.langchain.com/) for best-in-class observability"
+    "If you want to get automated tracing of your model calls you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
-   "id": "7f11de02",
+   "execution_count": null,
+   "id": "a15d341e-3e26-4ca3-830b-5aab30ed66de",
    "metadata": {},
    "outputs": [],
    "source": [
-    "# os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "# os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass()"
+    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
+    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "4c26754b-b3c9-4d93-8f36-43049bd943bf",
+   "id": "0730d6a1-c893-4840-9817-5e5251676d5d",
    "metadata": {},
    "source": [
-    "## Usage\n",
+    "### Installation\n",
     "\n",
-    "ChatCohere supports all [ChatModel](/docs/how_to#chat-models) functionality:"
+    "The LangChain Cohere integration lives in the `langchain-cohere` package:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
-   "id": "d4a7c55d-b235-4ca4-a579-c90cc9570da9",
-   "metadata": {
-    "tags": []
-   },
+   "execution_count": null,
+   "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU langchain-cohere"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a38cde65-254d-4219-a441-068766c0d4b5",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "Now we can instantiate our model object and generate chat completions:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
+   "metadata": {},
    "outputs": [],
    "source": [
     "from langchain_cohere import ChatCohere\n",
-    "from langchain_core.messages import HumanMessage"
+    "\n",
+    "llm = ChatCohere(\n",
+    "    model=\"command-r-plus\",\n",
+    "    temperature=0,\n",
+    "    max_tokens=None,\n",
+    "    timeout=None,\n",
+    "    max_retries=2,\n",
+    "    # other params...\n",
+    ")"
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "70cf04e8-423a-4ff6-8b09-f11fb711c817",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
+   "cell_type": "markdown",
+   "id": "2b4f3e15",
+   "metadata": {},
    "source": [
-    "chat = ChatCohere(model=\"command\")"
+    "## Invocation"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
-   "id": "8199ef8f-eb8b-4253-9ea0-6c24a013ca4c",
+   "execution_count": 2,
+   "id": "62e0dbc3",
    "metadata": {
     "tags": []
    },
@@ -116,134 +142,110 @@
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='4 && 5 \\n6 || 7 \\n\\nWould you like to play a game of odds and evens?', additional_kwargs={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '2076b614-52b3-4082-a259-cc92cd3d9fea', 'token_count': {'prompt_tokens': 68, 'response_tokens': 23, 'total_tokens': 91, 'billed_tokens': 77}}, response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '2076b614-52b3-4082-a259-cc92cd3d9fea', 'token_count': {'prompt_tokens': 68, 'response_tokens': 23, 'total_tokens': 91, 'billed_tokens': 77}}, id='run-3475e0c8-c89b-4937-9300-e07d652455e1-0')"
+       "AIMessage(content=\"J'adore programmer.\", additional_kwargs={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': 'd84f80f3-4611-46e6-aed0-9d8665a20a11', 'token_count': {'input_tokens': 89, 'output_tokens': 5}}, response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': 'd84f80f3-4611-46e6-aed0-9d8665a20a11', 'token_count': {'input_tokens': 89, 'output_tokens': 5}}, id='run-514ab516-ed7e-48ac-b132-2598fb80ebef-0')"
       ]
      },
-     "execution_count": 15,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "messages = [HumanMessage(content=\"1\"), HumanMessage(content=\"2 3\")]\n",
-    "chat.invoke(messages)"
+    "messages = [\n",
+    "    (\n",
+    "        \"system\",\n",
+    "        \"You are a helpful assistant that translates English to French. Translate the user sentence.\",\n",
+    "    ),\n",
+    "    (\"human\", \"I love programming.\"),\n",
+    "]\n",
+    "ai_msg = llm.invoke(messages)\n",
+    "ai_msg"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
-   "id": "c5fac0e9-05a4-4fc1-a3b3-e5bbb24b971b",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='4 && 5', additional_kwargs={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': 'f0708a92-f874-46ee-9b93-334d616ad92e', 'token_count': {'prompt_tokens': 68, 'response_tokens': 3, 'total_tokens': 71, 'billed_tokens': 57}}, response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': 'f0708a92-f874-46ee-9b93-334d616ad92e', 'token_count': {'prompt_tokens': 68, 'response_tokens': 3, 'total_tokens': 71, 'billed_tokens': 57}}, id='run-1635e63e-2994-4e7f-986e-152ddfc95777-0')"
-      ]
-     },
-     "execution_count": 16,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "await chat.ainvoke(messages)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "id": "025be980-e50d-4a68-93dc-c9c7b500ce34",
-   "metadata": {
-    "tags": []
-   },
+   "execution_count": 3,
+   "id": "d86145b3-bfef-46e8-b227-4dda5c9c2705",
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "4 && 5"
+      "J'adore programmer.\n"
      ]
     }
    ],
    "source": [
-    "for chunk in chat.stream(messages):\n",
-    "    print(chunk.content, end=\"\", flush=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "id": "064288e4-f184-4496-9427-bcf148fa055e",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[AIMessage(content='4 && 5', additional_kwargs={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '6770ca86-f6c3-4ba3-a285-c4772160612f', 'token_count': {'prompt_tokens': 68, 'response_tokens': 3, 'total_tokens': 71, 'billed_tokens': 57}}, response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '6770ca86-f6c3-4ba3-a285-c4772160612f', 'token_count': {'prompt_tokens': 68, 'response_tokens': 3, 'total_tokens': 71, 'billed_tokens': 57}}, id='run-8d6fade2-1b39-4e31-ab23-4be622dd0027-0')]"
-      ]
-     },
-     "execution_count": 18,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chat.batch([messages])"
+    "print(ai_msg.content)"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "f1c56460",
+   "id": "18e2bfc0-7e78-4528-a73f-499ac150dca8",
    "metadata": {},
    "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-lcel)"
+    "We can [chain](/docs/how_to/sequence/) our model with a prompt template like so:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
-   "id": "0851b103",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_template(\"Tell me a joke about {topic}\")\n",
-    "chain = prompt | chat"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 20,
-   "id": "ae950c0f-1691-47f1-b609-273033cae707",
+   "execution_count": 4,
+   "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='What color socks do bears wear?\\n\\nThey don’t wear socks, they have bear feet. \\n\\nHope you laughed! If not, maybe this will help: laughter is the best medicine, and a good sense of humor is infectious!', additional_kwargs={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '6edccf44-9bc8-4139-b30e-13b368f3563c', 'token_count': {'prompt_tokens': 68, 'response_tokens': 51, 'total_tokens': 119, 'billed_tokens': 108}}, response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '6edccf44-9bc8-4139-b30e-13b368f3563c', 'token_count': {'prompt_tokens': 68, 'response_tokens': 51, 'total_tokens': 119, 'billed_tokens': 108}}, id='run-ef7f9789-0d4d-43bf-a4f7-f2a0e27a5320-0')"
+       "AIMessage(content='Ich liebe Programmierung.', additional_kwargs={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '053bebde-4e1d-4d06-8ee6-3446e7afa25e', 'token_count': {'input_tokens': 84, 'output_tokens': 6}}, response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '053bebde-4e1d-4d06-8ee6-3446e7afa25e', 'token_count': {'input_tokens': 84, 'output_tokens': 6}}, id='run-53700708-b7fb-417b-af36-1a6fcde38e7d-0')"
       ]
      },
-     "execution_count": 20,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "chain.invoke({\"topic\": \"bears\"})"
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            \"You are a helpful assistant that translates {input_language} to {output_language}.\",\n",
+    "        ),\n",
+    "        (\"human\", \"{input}\"),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "chain = prompt | llm\n",
+    "chain.invoke(\n",
+    "    {\n",
+    "        \"input_language\": \"English\",\n",
+    "        \"output_language\": \"German\",\n",
+    "        \"input\": \"I love programming.\",\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all ChatCohere features and configurations head to the API reference: https://api.python.langchain.com/en/latest/chat_models/langchain_cohere.chat_models.ChatCohere.html"
    ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "poetry-venv-2",
    "language": "python",
-   "name": "python3"
+   "name": "poetry-venv-2"
   },
   "language_info": {
    "codemirror_mode": {
@@ -255,7 +257,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.7"
+   "version": "3.11.9"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/databricks.ipynb

@@ -0,0 +1,429 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
+   "source": [
+    "---\n",
+    "sidebar_label: Databricks\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# ChatDatabricks\n",
+    "\n",
+    "> [Databricks](https://www.databricks.com/) Lakehouse Platform unifies data, analytics, and AI on one platform. \n",
+    "\n",
+    "This notebook provides a quick overview for getting started with Databricks [chat models](/docs/concepts/#chat-models). For detailed documentation of all ChatDatabricks features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/chat_models/langchain_community.chat_models.databricks.ChatDatabricks.html).\n",
+    "\n",
+    "## Overview\n",
+    "\n",
+    "`ChatDatabricks` class wraps a chat model endpoint hosted on [Databricks Model Serving](https://docs.databricks.com/en/machine-learning/model-serving/index.html). This example notebook shows how to wrap your serving endpoint and use it as a chat model in your LangChain application.\n",
+    "\n",
+    "### Integration details\n",
+    "\n",
+    "| Class | Package | Local | Serializable | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |  :---: | :---: |\n",
+    "| [ChatDatabricks](https://api.python.langchain.com/en/latest/chat_models/langchain_community.chat_models.databricks.ChatDatabricks.html) | [langchain-community](https://api.python.langchain.com/en/latest/community_api_reference.html) | ❌ | beta | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-community?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-community?style=flat-square&label=%20) |\n",
+    "\n",
+    "### Model features\n",
+    "| [Tool calling](/docs/how_to/tool_calling/) | [Structured output](/docs/how_to/structured_output/) | JSON mode | [Image input](/docs/how_to/multimodal_inputs/) | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | Native async | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
+    "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
+    "| ❌ | ❌ | ❌ | ❌ | ❌ | ❌ |  ✅ | ✅ | ✅ | ❌ | \n",
+    "\n",
+    "### Supported Methods\n",
+    "\n",
+    "`ChatDatabricks` supports all methods of `ChatModel` including async APIs.\n",
+    "\n",
+    "\n",
+    "### Endpoint Requirement\n",
+    "\n",
+    "The serving endpoint `ChatDatabricks` wraps must have OpenAI-compatible chat input/output format ([reference](https://mlflow.org/docs/latest/llms/deployments/index.html#chat)). As long as the input format is compatible, `ChatDatabricks` can be used for any endpoint type hosted on [Databricks Model Serving](https://docs.databricks.com/en/machine-learning/model-serving/index.html):\n",
+    "\n",
+    "1. Foundation Models - Curated list of state-of-the-art foundation models such as DRBX, Llama3, Mixtral-8x7B, and etc. These endpoint are ready to use in your Databricks workspace without any set up.\n",
+    "2. Custom Models - You can also deploy custom models to a serving endpoint via MLflow with\n",
+    "your choice of framework such as LangChain, Pytorch, Transformers, etc.\n",
+    "3. External Models - Databricks endpoints can serve models that are hosted outside Databricks as a proxy, such as proprietary model service like OpenAI GPT4.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "source": [
+    "## Setup\n",
+    "\n",
+    "To access Databricks models you'll need to create a Databricks account, set up credentials (only if you are outside Databricks workspace), and install required packages.\n",
+    "\n",
+    "### Credentials (only if you are outside Databricks)\n",
+    "\n",
+    "If you are running LangChain app inside Databricks, you can skip this step.\n",
+    "\n",
+    "Otherwise, you need manually set the Databricks workspace hostname and personal access token to `DATABRICKS_HOST` and `DATABRICKS_TOKEN` environment variables, respectively. See [Authentication Documentation](https://docs.databricks.com/en/dev-tools/auth/index.html#databricks-personal-access-tokens) for how to get an access token."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Enter your Databricks access token:  ········\n"
+     ]
+    }
+   ],
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "os.environ[\"DATABRICKS_HOST\"] = \"https://your-workspace.cloud.databricks.com\"\n",
+    "os.environ[\"DATABRICKS_TOKEN\"] = getpass.getpass(\"Enter your Databricks access token: \")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "The LangChain Databricks integration lives in the `langchain-community` package. Also, `mlflow >= 2.9 ` is required to run the code in this notebook."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU langchain-community mlflow>=2.9.0"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We first demonstrates how to query DBRX-instruct model hosted as Foundation Models endpoint with `ChatDatabricks`.\n",
+    "\n",
+    "For other type of endpoints, there are some difference in how to set up the endpoint itself, however, once the endpoint is ready, there is no difference in how to query it with `ChatDatabricks`. Please refer to the bottom of this notebook for the examples with other type of endpoints."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.chat_models import ChatDatabricks\n",
+    "\n",
+    "chat_model = ChatDatabricks(\n",
+    "    endpoint=\"databricks-dbrx-instruct\",\n",
+    "    temperature=0.1,\n",
+    "    max_tokens=256,\n",
+    "    # See https://api.python.langchain.com/en/latest/chat_models/langchain_community.chat_models.databricks.ChatDatabricks.html for other supported parameters\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Invocation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='MLflow is an open-source platform for managing end-to-end machine learning workflows. It was introduced by Databricks in 2018. MLflow provides tools for tracking experiments, packaging and sharing code, and deploying models. It is designed to work with any machine learning library and can be used in a variety of environments, including local machines, virtual machines, and cloud-based clusters. MLflow aims to streamline the machine learning development lifecycle, making it easier for data scientists and engineers to collaborate and deploy models into production.', response_metadata={'prompt_tokens': 229, 'completion_tokens': 104, 'total_tokens': 333}, id='run-d3fb4d06-3e10-4471-83c9-c282cc62b74d-0')"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chat_model.invoke(\"What is MLflow?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='Databricks Model Serving is a feature of the Databricks platform that allows data scientists and engineers to easily deploy machine learning models into production. With Model Serving, you can host, manage, and serve machine learning models as APIs, making it easy to integrate them into applications and business processes. It supports a variety of popular machine learning frameworks, including TensorFlow, PyTorch, and scikit-learn, and provides tools for monitoring and managing the performance of deployed models. Model Serving is designed to be scalable, secure, and easy to use, making it a great choice for organizations that want to quickly and efficiently deploy machine learning models into production.', response_metadata={'prompt_tokens': 35, 'completion_tokens': 130, 'total_tokens': 165}, id='run-b3feea21-223e-4105-8627-41d647d5ccab-0')"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# You can also pass a list of messages\n",
+    "messages = [\n",
+    "    (\"system\", \"You are a chatbot that can answer questions about Databricks.\"),\n",
+    "    (\"user\", \"What is Databricks Model Serving?\"),\n",
+    "]\n",
+    "chat_model.invoke(messages)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Chaining\n",
+    "Similar to other chat models, `ChatDatabricks` can be used as a part of a complex chain."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"Unity Catalog is a new data catalog feature in Databricks that allows you to discover, manage, and govern all your data assets across your data landscape, including data lakes, data warehouses, and data marts. It provides a centralized repository for storing and managing metadata, data lineage, and access controls for all your data assets. Unity Catalog enables data teams to easily discover and access the data they need, while ensuring compliance with data privacy and security regulations. It is designed to work seamlessly with Databricks' Lakehouse platform, providing a unified experience for managing and analyzing all your data.\", response_metadata={'prompt_tokens': 32, 'completion_tokens': 118, 'total_tokens': 150}, id='run-82d72624-f8df-4c0d-a976-919feec09a55-0')"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            \"You are a chatbot that can answer questions about {topic}.\",\n",
+    "        ),\n",
+    "        (\"user\", \"{question}\"),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "chain = prompt | chat_model\n",
+    "chain.invoke(\n",
+    "    {\n",
+    "        \"topic\": \"Databricks\",\n",
+    "        \"question\": \"What is Unity Catalog?\",\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Invocation (streaming)\n",
+    "\n",
+    "`ChatDatabricks` supports streaming response by `stream` method since `langchain-community>=0.2.1`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "I|'m| an| AI| and| don|'t| have| feelings|,| but| I|'m| here| and| ready| to| assist| you|.| How| can| I| help| you| today|?||"
+     ]
+    }
+   ],
+   "source": [
+    "for chunk in chat_model.stream(\"How are you?\"):\n",
+    "    print(chunk.content, end=\"|\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Async Invocation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import asyncio\n",
+    "\n",
+    "country = [\"Japan\", \"Italy\", \"Australia\"]\n",
+    "futures = [chat_model.ainvoke(f\"Where is the capital of {c}?\") for c in country]\n",
+    "await asyncio.gather(*futures)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Wrapping Custom Model Endpoint\n",
+    "\n",
+    "Prerequisites:\n",
+    "\n",
+    "* An LLM was registered and deployed to [a Databricks serving endpoint](https://docs.databricks.com/machine-learning/model-serving/index.html) via MLflow. The endpoint must have OpenAI-compatible chat input/output format ([reference](https://mlflow.org/docs/latest/llms/deployments/index.html#chat))\n",
+    "* You have [\"Can Query\" permission](https://docs.databricks.com/security/auth-authz/access-control/serving-endpoint-acl.html) to the endpoint.\n",
+    "\n",
+    "Once the endpoint is ready, the usage pattern is completely same as Foundation Models."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chat_model_custom = ChatDatabricks(\n",
+    "    endpoint=\"YOUR_ENDPOINT_NAME\",\n",
+    "    temperature=0.1,\n",
+    "    max_tokens=256,\n",
+    ")\n",
+    "\n",
+    "chat_model_custom.invoke(\"How are you?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Wrapping External Models"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Prerequisite: Create Proxy Endpoint\n",
+    "\n",
+    "First, create a new Databricks serving endpoint that proxies requests to the target external model. The endpoint creation should be fairy quick for proxying external models.\n",
+    "\n",
+    "This requires registering OpenAI API Key in Databricks secret manager with the following comment:\n",
+    "```sh\n",
+    "# Replace `<scope>` with your scope\n",
+    "databricks secrets create-scope <scope>\n",
+    "databricks secrets put-secret <scope> openai-api-key --string-value $OPENAI_API_KEY\n",
+    "```\n",
+    "\n",
+    "For how to set up Databricks CLI and manage secrets, please refer to https://docs.databricks.com/en/security/secrets/secrets.html"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from mlflow.deployments import get_deploy_client\n",
+    "\n",
+    "client = get_deploy_client(\"databricks\")\n",
+    "\n",
+    "secret = \"secrets/<scope>/openai-api-key\"  # replace `<scope>` with your scope\n",
+    "endpoint_name = \"my-chat\"  # rename this if my-chat already exists\n",
+    "client.create_endpoint(\n",
+    "    name=endpoint_name,\n",
+    "    config={\n",
+    "        \"served_entities\": [\n",
+    "            {\n",
+    "                \"name\": \"my-chat\",\n",
+    "                \"external_model\": {\n",
+    "                    \"name\": \"gpt-3.5-turbo\",\n",
+    "                    \"provider\": \"openai\",\n",
+    "                    \"task\": \"llm/v1/chat\",\n",
+    "                    \"openai_config\": {\n",
+    "                        \"openai_api_key\": \"{{\" + secret + \"}}\",\n",
+    "                    },\n",
+    "                },\n",
+    "            }\n",
+    "        ],\n",
+    "    },\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Once the endpoint status has become \"Ready\", you can query the endpoint in the same way as other types of endpoints."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chat_model_external = ChatDatabricks(\n",
+    "    endpoint=endpoint_name,\n",
+    "    temperature=0.1,\n",
+    "    max_tokens=256,\n",
+    ")\n",
+    "chat_model_external.invoke(\"How to use Databricks?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all ChatDatabricks features and configurations head to the API reference: https://api.python.langchain.com/en/latest/chat_models/langchain_community.chat_models.ChatDatabricks.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": "3.10.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

docs/docs/integrations/chat/deepinfra.ipynb

@@ -98,6 +98,78 @@
     ")\n",
     "chat.invoke(messages)"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "466c3cb41ace1410",
+   "metadata": {},
+   "source": [
+    "# Tool Calling\n",
+    "\n",
+    "DeepInfra currently supports only invoke and async invoke tool calling.\n",
+    "\n",
+    "For a complete list of models that support tool calling, please refer to our [tool calling documentation](https://deepinfra.com/docs/advanced/function_calling)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ddc4f4299763651c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import asyncio\n",
+    "\n",
+    "from dotenv import find_dotenv, load_dotenv\n",
+    "from langchain_community.chat_models import ChatDeepInfra\n",
+    "from langchain_core.messages import HumanMessage\n",
+    "from langchain_core.pydantic_v1 import BaseModel\n",
+    "from langchain_core.tools import tool\n",
+    "\n",
+    "model_name = \"meta-llama/Meta-Llama-3-70B-Instruct\"\n",
+    "\n",
+    "_ = load_dotenv(find_dotenv())\n",
+    "\n",
+    "\n",
+    "# Langchain tool\n",
+    "@tool\n",
+    "def foo(something):\n",
+    "    \"\"\"\n",
+    "    Called when foo\n",
+    "    \"\"\"\n",
+    "    pass\n",
+    "\n",
+    "\n",
+    "# Pydantic class\n",
+    "class Bar(BaseModel):\n",
+    "    \"\"\"\n",
+    "    Called when Bar\n",
+    "    \"\"\"\n",
+    "\n",
+    "    pass\n",
+    "\n",
+    "\n",
+    "llm = ChatDeepInfra(model=model_name)\n",
+    "tools = [foo, Bar]\n",
+    "llm_with_tools = llm.bind_tools(tools)\n",
+    "messages = [\n",
+    "    HumanMessage(\"Foo and bar, please.\"),\n",
+    "]\n",
+    "\n",
+    "response = llm_with_tools.invoke(messages)\n",
+    "print(response.tool_calls)\n",
+    "# [{'name': 'foo', 'args': {'something': None}, 'id': 'call_Mi4N4wAtW89OlbizFE1aDxDj'}, {'name': 'Bar', 'args': {}, 'id': 'call_daiE0mW454j2O1KVbmET4s2r'}]\n",
+    "\n",
+    "\n",
+    "async def call_ainvoke():\n",
+    "    result = await llm_with_tools.ainvoke(messages)\n",
+    "    print(result.tool_calls)\n",
+    "\n",
+    "\n",
+    "# Async call\n",
+    "asyncio.run(call_ainvoke())\n",
+    "# [{'name': 'foo', 'args': {'something': None}, 'id': 'call_ZH7FetmgSot4LHcMU6CEb8tI'}, {'name': 'Bar', 'args': {}, 'id': 'call_2MQhDifAJVoijZEvH8PeFSVB'}]"
+   ]
   }
  ],
  "metadata": {

docs/docs/integrations/chat/fireworks.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "raw",
-   "id": "529aeba9",
+   "id": "afaf8039",
    "metadata": {},
    "source": [
     "---\n",
@@ -11,190 +11,236 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
-   "id": "642fd21c-600a-47a1-be96-6e1438b421a9",
+   "id": "e49f1e0d",
    "metadata": {},
    "source": [
     "# ChatFireworks\n",
     "\n",
-    ">[Fireworks](https://app.fireworks.ai/) accelerates product development on generative AI by creating an innovative AI experiment and production platform. \n",
+    "This doc help you get started with Fireworks AI [chat models](/docs/concepts/#chat-models). For detailed documentation of all ChatFireworks features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/chat_models/langchain_fireworks.chat_models.ChatFireworks.html).\n",
     "\n",
-    "This example goes over how to use LangChain to interact with `ChatFireworks` models."
-   ]
-  },
-  {
-   "cell_type": "raw",
-   "id": "4a7c795e",
-   "metadata": {},
-   "source": [
-    "%pip install langchain-fireworks"
+    "Fireworks AI is an AI inference platform to run and customize models. For a list of all models served by Fireworks see the [Fireworks docs](https://fireworks.ai/models).\n",
+    "\n",
+    "## Overview\n",
+    "### Integration details\n",
+    "\n",
+    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/v0.2/docs/integrations/chat/fireworks) | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+    "| [ChatFireworks](https://api.python.langchain.com/en/latest/chat_models/langchain_fireworks.chat_models.ChatFireworks.html) | [langchain-fireworks](https://api.python.langchain.com/en/latest/fireworks_api_reference.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-fireworks?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-fireworks?style=flat-square&label=%20) |\n",
+    "\n",
+    "### Model features\n",
+    "| [Tool calling](/docs/how_to/tool_calling) | [Structured output](/docs/how_to/structured_output/) | JSON mode | [Image input](/docs/how_to/multimodal_inputs/) | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | Native async | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
+    "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
+    "| ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | ✅ | ✅ | ✅ | \n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "To access Fireworks models you'll need to create a Fireworks account, get an API key, and install the `langchain-fireworks` integration package.\n",
+    "\n",
+    "### Credentials\n",
+    "\n",
+    "Head to (ttps://fireworks.ai/login to sign up to Fireworks and generate an API key. Once you've done this set the FIREWORKS_API_KEY environment variable:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
-   "id": "d00d850917865298",
-   "metadata": {
-    "collapsed": false,
-    "jupyter": {
-     "outputs_hidden": false
-    }
-   },
-   "outputs": [],
-   "source": [
-    "from langchain_core.messages import HumanMessage, SystemMessage\n",
-    "from langchain_fireworks import ChatFireworks"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "f28ebf8b-f14f-46c7-9962-8b8dc42e31be",
-   "metadata": {},
-   "source": [
-    "# Setup\n",
-    "\n",
-    "1. Make sure the `langchain-fireworks` package is installed in your environment.\n",
-    "2. Sign in to [Fireworks AI](http://fireworks.ai) for the an API Key to access our models, and make sure it is set as the `FIREWORKS_API_KEY` environment variable.\n",
-    "3. Set up your model using a model id. If the model is not set, the default model is fireworks-llama-v2-7b-chat. See the full, most up-to-date model list on [app.fireworks.ai](https://app.fireworks.ai)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "d096fb14-8acc-4047-9cd0-c842430c3a1d",
+   "execution_count": null,
+   "id": "433e8d2b-9519-4b49-b2c4-7ab65b046c94",
    "metadata": {},
    "outputs": [],
    "source": [
     "import getpass\n",
     "import os\n",
     "\n",
-    "if \"FIREWORKS_API_KEY\" not in os.environ:\n",
-    "    os.environ[\"FIREWORKS_API_KEY\"] = getpass.getpass(\"Fireworks API Key:\")\n",
-    "\n",
-    "# Initialize a Fireworks chat model\n",
-    "chat = ChatFireworks(model=\"accounts/fireworks/models/mixtral-8x7b-instruct\")"
+    "os.environ[\"FIREWORKS_API_KEY\"] = getpass.getpass(\"Enter your Fireworks API key: \")"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "d8f13144-37cf-47a5-b5a0-e3cdf76d9a72",
+   "id": "72ee0c4b-9764-423a-9dbf-95129e185210",
    "metadata": {},
    "source": [
-    "# Calling the Model Directly\n",
+    "If you want to get automated tracing of your model calls you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a15d341e-3e26-4ca3-830b-5aab30ed66de",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
+    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0730d6a1-c893-4840-9817-5e5251676d5d",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
     "\n",
-    "You can call the model directly with a system and human message to get answers."
+    "The LangChain Fireworks integration lives in the `langchain-fireworks` package:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU langchain-fireworks"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a38cde65-254d-4219-a441-068766c0d4b5",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "Now we can instantiate our model object and generate chat completions:\n",
+    "\n",
+    "- TODO: Update model instantiation with relevant params."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_fireworks import ChatFireworks\n",
+    "\n",
+    "llm = ChatFireworks(\n",
+    "    model=\"accounts/fireworks/models/llama-v3-70b-instruct\",\n",
+    "    temperature=0,\n",
+    "    max_tokens=None,\n",
+    "    timeout=None,\n",
+    "    max_retries=2,\n",
+    "    # other params...\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2b4f3e15",
+   "metadata": {},
+   "source": [
+    "## Invocation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "62e0dbc3",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"J'adore la programmation.\", response_metadata={'token_usage': {'prompt_tokens': 35, 'total_tokens': 44, 'completion_tokens': 9}, 'model_name': 'accounts/fireworks/models/llama-v3-70b-instruct', 'system_fingerprint': '', 'finish_reason': 'stop', 'logprobs': None}, id='run-df28e69a-ff30-457e-a743-06eb14d01cb0-0', usage_metadata={'input_tokens': 35, 'output_tokens': 9, 'total_tokens': 44})"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "messages = [\n",
+    "    (\n",
+    "        \"system\",\n",
+    "        \"You are a helpful assistant that translates English to French. Translate the user sentence.\",\n",
+    "    ),\n",
+    "    (\"human\", \"I love programming.\"),\n",
+    "]\n",
+    "ai_msg = llm.invoke(messages)\n",
+    "ai_msg"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 3,
-   "id": "72340871-ae2f-415f-b399-0777d32dc379",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\"Hello! I'm an AI language model, a helpful assistant designed to chat and assist you with any questions or information you might need. I'm here to make your experience as smooth and enjoyable as possible. How can I assist you today?\")"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# ChatFireworks Wrapper\n",
-    "system_message = SystemMessage(content=\"You are to chat with the user.\")\n",
-    "human_message = HumanMessage(content=\"Who are you?\")\n",
-    "\n",
-    "chat.invoke([system_message, human_message])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "68c6b1fa-2ff7-4a63-8d88-3cec302180b8",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\"I'm an AI and do not have the ability to experience the weather firsthand. However,\")"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Setting additional parameters: temperature, max_tokens, top_p\n",
-    "chat = ChatFireworks(\n",
-    "    model=\"accounts/fireworks/models/mixtral-8x7b-instruct\",\n",
-    "    temperature=1,\n",
-    "    max_tokens=20,\n",
-    ")\n",
-    "system_message = SystemMessage(content=\"You are to chat with the user.\")\n",
-    "human_message = HumanMessage(content=\"How's the weather today?\")\n",
-    "chat.invoke([system_message, human_message])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "8c44cb36",
-   "metadata": {},
-   "source": [
-    "# Tool Calling\n",
-    "\n",
-    "Fireworks offers the [`FireFunction-v1` tool calling model](https://fireworks.ai/blog/firefunction-v1-gpt-4-level-function-calling). You can use it for structured output and function calling use cases:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "ee2db682",
+   "id": "d86145b3-bfef-46e8-b227-4dda5c9c2705",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'function': {'arguments': '{\"name\": \"Erick\", \"age\": 27}',\n",
-      "              'name': 'ExtractFields'},\n",
-      " 'id': 'call_J0WYP2TLenaFw3UeVU0UnWqx',\n",
-      " 'index': 0,\n",
-      " 'type': 'function'}\n"
+      "J'adore la programmation.\n"
      ]
     }
    ],
    "source": [
-    "from pprint import pprint\n",
+    "print(ai_msg.content)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "18e2bfc0-7e78-4528-a73f-499ac150dca8",
+   "metadata": {},
+   "source": [
+    "## Chaining\n",
     "\n",
-    "from langchain_core.pydantic_v1 import BaseModel\n",
-    "\n",
-    "\n",
-    "class ExtractFields(BaseModel):\n",
-    "    name: str\n",
-    "    age: int\n",
-    "\n",
-    "\n",
-    "chat = ChatFireworks(\n",
-    "    model=\"accounts/fireworks/models/firefunction-v1\",\n",
-    ").bind_tools([ExtractFields])\n",
-    "\n",
-    "result = chat.invoke(\"I am a 27 year old named Erick\")\n",
-    "\n",
-    "pprint(result.additional_kwargs[\"tool_calls\"][0])"
+    "We can [chain](/docs/how_to/sequence/) our model with a prompt template like so:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "2321a4e6",
+   "execution_count": 4,
+   "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='Ich liebe das Programmieren.', response_metadata={'token_usage': {'prompt_tokens': 30, 'total_tokens': 37, 'completion_tokens': 7}, 'model_name': 'accounts/fireworks/models/llama-v3-70b-instruct', 'system_fingerprint': '', 'finish_reason': 'stop', 'logprobs': None}, id='run-ff3f91ad-ed81-4acf-9f59-7490dc8d8f48-0', usage_metadata={'input_tokens': 30, 'output_tokens': 7, 'total_tokens': 37})"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            \"You are a helpful assistant that translates {input_language} to {output_language}.\",\n",
+    "        ),\n",
+    "        (\"human\", \"{input}\"),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "chain = prompt | llm\n",
+    "chain.invoke(\n",
+    "    {\n",
+    "        \"input_language\": \"English\",\n",
+    "        \"output_language\": \"German\",\n",
+    "        \"input\": \"I love programming.\",\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all ChatFireworks features and configurations head to the API reference: https://api.python.langchain.com/en/latest/chat_models/langchain_fireworks.chat_models.ChatFireworks.html"
+   ]
   }
  ],
  "metadata": {
@@ -213,7 +259,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.11.9"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/google_vertex_ai_palm.ipynb

@@ -35,7 +35,7 @@
     "| [ChatVertexAI](https://api.python.langchain.com/en/latest/chat_models/langchain_google_vertexai.chat_models.ChatVertexAI.html) | [langchain-google-vertexai](https://api.python.langchain.com/en/latest/google_vertexai_api_reference.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-google-vertexai?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-google-vertexai?style=flat-square&label=%20) |\n",
     "\n",
     "### Model features\n",
-    "| [Tool calling](/docs/how_to/tool_calling/) | [Structured output](/docs/how_to/structured_output/) | JSON mode | [Image input](/docs/how_to/multimodal_inputs/) | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | Native async | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
+    "| [Tool calling](/docs/how_to/tool_calling) | [Structured output](/docs/how_to/structured_output/) | JSON mode | [Image input](/docs/how_to/multimodal_inputs/) | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | Native async | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
     "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
     "| ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | \n",
     "\n",

docs/docs/integrations/chat/groq.ipynb

@@ -91,7 +91,7 @@
     "\n",
     "## Tool calling\n",
     "\n",
-    "Groq chat models support [tool calling](/docs/how_to/tool_calling/) to generate output matching a specific schema. The model may choose to call multiple tools or the same tool multiple times if appropriate.\n",
+    "Groq chat models support [tool calling](/docs/how_to/tool_calling) to generate output matching a specific schema. The model may choose to call multiple tools or the same tool multiple times if appropriate.\n",
     "\n",
     "Here's an example:"
    ]

docs/docs/integrations/chat/huggingface.ipynb

@@ -315,7 +315,11 @@
    "source": [
     "## 4. Take it for a spin as an agent!\n",
     "\n",
-    "Here we'll test out `Zephyr-7B-beta` as a zero-shot `ReAct` Agent. The example below is taken from [here](https://python.langchain.com/v0.1/docs/modules/agents/agent_types/react/#using-chat-models).\n",
+    "Here we'll test out `Zephyr-7B-beta` as a zero-shot `ReAct` Agent. \n",
+    "\n",
+    "The agent is based on the paper [ReAct: Synergizing Reasoning and Acting in Language Models](https://arxiv.org/abs/2210.03629)\n",
+    "\n",
+    "The example below is taken from [here](https://python.langchain.com/v0.1/docs/modules/agents/agent_types/react/#using-chat-models).\n",
     "\n",
     "> Note: To run this section, you'll need to have a [SerpAPI Token](https://serpapi.com/) saved as an environment variable: `SERPAPI_API_KEY`"
    ]

docs/docs/integrations/chat/ibm_watsonx.ipynb

@@ -0,0 +1,585 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "id": "1c95cd76",
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
+   "source": [
+    "---\n",
+    "sidebar_label: IBM watsonx.ai\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "70996d8a",
+   "metadata": {},
+   "source": [
+    "# ChatWatsonx\n",
+    "\n",
+    ">ChatWatsonx is a wrapper for IBM [watsonx.ai](https://www.ibm.com/products/watsonx-ai) foundation models.\n",
+    "\n",
+    "The aim of these examples is to show how to communicate with `watsonx.ai` models using `LangChain` LLMs API."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ef7b088a",
+   "metadata": {},
+   "source": [
+    "## Overview\n",
+    "\n",
+    "### Integration details\n",
+    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/v0.2/docs/integrations/chat/openai) | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+    "| [ChatWatsonx](https://api.python.langchain.com/en/latest/ibm_api_reference.html) | [langchain-ibm](https://api.python.langchain.com/en/latest/ibm_api_reference.html) | ❌ | ❌ | ❌ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-ibm?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-ibm?style=flat-square&label=%20) |\n",
+    "\n",
+    "### Model features\n",
+    "| [Tool calling](/docs/how_to/tool_calling/) | [Structured output](/docs/how_to/structured_output/) | JSON mode | Image input | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | Native async | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
+    "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
+    "| ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ | ✅ | ❌ | "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f406e092",
+   "metadata": {},
+   "source": [
+    "## Setup\n",
+    "\n",
+    "To access IBM watsonx.ai models you'll need to create an IBM watsonx.ai account, get an API key, and install the `langchain-ibm` integration package.\n",
+    "\n",
+    "### Credentials\n",
+    "\n",
+    "The cell below defines the credentials required to work with watsonx Foundation Model inferencing.\n",
+    "\n",
+    "**Action:** Provide the IBM Cloud user API key. For details, see\n",
+    "[Managing user API keys](https://cloud.ibm.com/docs/account?topic=account-userapikey&interface=ui)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "11d572a1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from getpass import getpass\n",
+    "\n",
+    "watsonx_api_key = getpass()\n",
+    "os.environ[\"WATSONX_APIKEY\"] = watsonx_api_key"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c59782a7",
+   "metadata": {},
+   "source": [
+    "Additionally you are able to pass additional secrets as an environment variable. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f98c573c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"WATSONX_URL\"] = \"your service instance url\"\n",
+    "os.environ[\"WATSONX_TOKEN\"] = \"your token for accessing the CPD cluster\"\n",
+    "os.environ[\"WATSONX_PASSWORD\"] = \"your password for accessing the CPD cluster\"\n",
+    "os.environ[\"WATSONX_USERNAME\"] = \"your username for accessing the CPD cluster\"\n",
+    "os.environ[\"WATSONX_INSTANCE_ID\"] = \"your instance_id for accessing the CPD cluster\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b3dc9176",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "The LangChain IBM integration lives in the `langchain-ibm` package:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "387eda86",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install -qU langchain-ibm"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e36acbef",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "You might need to adjust model `parameters` for different models or tasks. For details, refer to [Available MetaNames](https://ibm.github.io/watsonx-ai-python-sdk/fm_model.html#metanames.GenTextParamsMetaNames)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "407cd500",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "parameters = {\n",
+    "    \"decoding_method\": \"sample\",\n",
+    "    \"max_new_tokens\": 100,\n",
+    "    \"min_new_tokens\": 1,\n",
+    "    \"stop_sequences\": [\".\"],\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2b586538",
+   "metadata": {},
+   "source": [
+    "Initialize the `WatsonxLLM` class with the previously set parameters.\n",
+    "\n",
+    "\n",
+    "**Note**: \n",
+    "\n",
+    "- To provide context for the API call, you must pass the `project_id` or `space_id`. To get your project or space ID, open your project or space, go to the **Manage** tab, and click **General**. For more information see: [Project documentation](https://www.ibm.com/docs/en/watsonx-as-a-service?topic=projects) or [Deployment space documentation](https://www.ibm.com/docs/en/watsonx/saas?topic=spaces-creating-deployment).\n",
+    "- Depending on the region of your provisioned service instance, use one of the urls listed in [watsonx.ai API Authentication](https://ibm.github.io/watsonx-ai-python-sdk/setup_cloud.html#authentication).\n",
+    "\n",
+    "In this example, we’ll use the `project_id` and Dallas URL.\n",
+    "\n",
+    "\n",
+    "You need to specify the `model_id` that will be used for inferencing. You can find the list of all the available models in [Supported foundation models](https://ibm.github.io/watsonx-ai-python-sdk/fm_model.html#ibm_watsonx_ai.foundation_models.utils.enums.ModelTypes)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "98371396",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_ibm import ChatWatsonx\n",
+    "\n",
+    "chat = ChatWatsonx(\n",
+    "    model_id=\"ibm/granite-13b-chat-v2\",\n",
+    "    url=\"https://us-south.ml.cloud.ibm.com\",\n",
+    "    project_id=\"PASTE YOUR PROJECT_ID HERE\",\n",
+    "    params=parameters,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2202f4e0",
+   "metadata": {},
+   "source": [
+    "Alternatively, you can use Cloud Pak for Data credentials. For details, see [watsonx.ai software setup](https://ibm.github.io/watsonx-ai-python-sdk/setup_cpd.html).  "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "243ecccb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chat = ChatWatsonx(\n",
+    "    model_id=\"ibm/granite-13b-chat-v2\",\n",
+    "    url=\"PASTE YOUR URL HERE\",\n",
+    "    username=\"PASTE YOUR USERNAME HERE\",\n",
+    "    password=\"PASTE YOUR PASSWORD HERE\",\n",
+    "    instance_id=\"openshift\",\n",
+    "    version=\"4.8\",\n",
+    "    project_id=\"PASTE YOUR PROJECT_ID HERE\",\n",
+    "    params=parameters,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "96ed13d4",
+   "metadata": {},
+   "source": [
+    "Instead of `model_id`, you can also pass the `deployment_id` of the previously tuned model. The entire model tuning workflow is described in [Working with TuneExperiment and PromptTuner](https://ibm.github.io/watsonx-ai-python-sdk/pt_working_with_class_and_prompt_tuner.html)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "08e66c88",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chat = ChatWatsonx(\n",
+    "    deployment_id=\"PASTE YOUR DEPLOYMENT_ID HERE\",\n",
+    "    url=\"https://us-south.ml.cloud.ibm.com\",\n",
+    "    project_id=\"PASTE YOUR PROJECT_ID HERE\",\n",
+    "    params=parameters,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f571001d",
+   "metadata": {},
+   "source": [
+    "## Invocation\n",
+    "\n",
+    "To obtain completions, you can call the model directly using a string prompt."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "beea2b5b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"Je t'aime pour écouter la Rock.\", response_metadata={'token_usage': {'generated_token_count': 12, 'input_token_count': 28}, 'model_name': 'ibm/granite-13b-chat-v2', 'system_fingerprint': '', 'finish_reason': 'stop_sequence'}, id='run-05b305ce-5401-4a10-b557-41a4b15c7f6f-0')"
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Invocation\n",
+    "\n",
+    "messages = [\n",
+    "    (\"system\", \"You are a helpful assistant that translates English to French.\"),\n",
+    "    (\n",
+    "        \"human\",\n",
+    "        \"I love you for listening to Rock.\",\n",
+    "    ),\n",
+    "]\n",
+    "\n",
+    "chat.invoke(messages)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "id": "8ab1a25a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='Sure, I can help you with that! Horses are large, powerful mammals that belong to the family Equidae.', response_metadata={'token_usage': {'generated_token_count': 24, 'input_token_count': 24}, 'model_name': 'ibm/granite-13b-chat-v2', 'system_fingerprint': '', 'finish_reason': 'stop_sequence'}, id='run-391776ff-3b38-4768-91e8-ff64177149e5-0')"
+      ]
+     },
+     "execution_count": 41,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Invocation multiple chat\n",
+    "from langchain_core.messages import (\n",
+    "    HumanMessage,\n",
+    "    SystemMessage,\n",
+    ")\n",
+    "\n",
+    "system_message = SystemMessage(\n",
+    "    content=\"You are a helpful assistant which telling short-info about provided topic.\"\n",
+    ")\n",
+    "human_message = HumanMessage(content=\"horse\")\n",
+    "\n",
+    "chat.invoke([system_message, human_message])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "20e4b568",
+   "metadata": {},
+   "source": [
+    "## Chaining\n",
+    "Create `ChatPromptTemplate` objects which will be responsible for creating a random question."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "dd919925",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "\n",
+    "system = (\n",
+    "    \"You are a helpful assistant that translates {input_language} to {output_language}.\"\n",
+    ")\n",
+    "human = \"{input}\"\n",
+    "prompt = ChatPromptTemplate.from_messages([(\"system\", system), (\"human\", human)])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1a013a53",
+   "metadata": {},
+   "source": [
+    "Provide a inputs and run the chain."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "68160377",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='Ich liebe Python.', response_metadata={'token_usage': {'generated_token_count': 5, 'input_token_count': 23}, 'model_name': 'ibm/granite-13b-chat-v2', 'system_fingerprint': '', 'finish_reason': 'stop_sequence'}, id='run-1b1ccf5d-0e33-46f2-a087-e2a136ba1fb7-0')"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain = prompt | chat\n",
+    "chain.invoke(\n",
+    "    {\n",
+    "        \"input_language\": \"English\",\n",
+    "        \"output_language\": \"German\",\n",
+    "        \"input\": \"I love Python\",\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d2c9da33",
+   "metadata": {},
+   "source": [
+    "## Streaming the Model output \n",
+    "\n",
+    "You can stream the model output."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "3f63166a",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The moon is a natural satellite of the Earth, and it has been a source of fascination for humans for centuries."
+     ]
+    }
+   ],
+   "source": [
+    "system_message = SystemMessage(\n",
+    "    content=\"You are a helpful assistant which telling short-info about provided topic.\"\n",
+    ")\n",
+    "human_message = HumanMessage(content=\"moon\")\n",
+    "\n",
+    "for chunk in chat.stream([system_message, human_message]):\n",
+    "    print(chunk.content, end=\"\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5a7a2aa1",
+   "metadata": {},
+   "source": [
+    "## Batch the Model output \n",
+    "\n",
+    "You can batch the model output."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "id": "9e948729",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[AIMessage(content='Cats are domestic animals that belong to the Felidae family.', response_metadata={'token_usage': {'generated_token_count': 13, 'input_token_count': 24}, 'model_name': 'ibm/granite-13b-chat-v2', 'system_fingerprint': '', 'finish_reason': 'stop_sequence'}, id='run-71a8bd7a-a1aa-497b-9bdd-a4d6fe1d471a-0'),\n",
+       " AIMessage(content='Dogs are domesticated mammals of the family Canidae, characterized by their adaptability to various environments and social structures.', response_metadata={'token_usage': {'generated_token_count': 24, 'input_token_count': 24}, 'model_name': 'ibm/granite-13b-chat-v2', 'system_fingerprint': '', 'finish_reason': 'stop_sequence'}, id='run-22b7a0cb-e44a-4b68-9921-872f82dcd82b-0')]"
+      ]
+     },
+     "execution_count": 32,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "message_1 = [\n",
+    "    SystemMessage(\n",
+    "        content=\"You are a helpful assistant which telling short-info about provided topic.\"\n",
+    "    ),\n",
+    "    HumanMessage(content=\"cat\"),\n",
+    "]\n",
+    "message_2 = [\n",
+    "    SystemMessage(\n",
+    "        content=\"You are a helpful assistant which telling short-info about provided topic.\"\n",
+    "    ),\n",
+    "    HumanMessage(content=\"dog\"),\n",
+    "]\n",
+    "\n",
+    "chat.batch([message_1, message_2])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c739e1fe",
+   "metadata": {},
+   "source": [
+    "## Tool calling\n",
+    "\n",
+    "### ChatWatsonx.bind_tools()\n",
+    "\n",
+    "Please note that `ChatWatsonx.bind_tools` is on beta state, so right now we only support `mistralai/mixtral-8x7b-instruct-v01` model.\n",
+    "\n",
+    "You should also redefine `max_new_tokens` parameter to get the entire model response. By default `max_new_tokens` is set ot 20."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "328fce76",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_ibm import ChatWatsonx\n",
+    "\n",
+    "parameters = {\"max_new_tokens\": 200}\n",
+    "\n",
+    "chat = ChatWatsonx(\n",
+    "    model_id=\"mistralai/mixtral-8x7b-instruct-v01\",\n",
+    "    url=\"https://us-south.ml.cloud.ibm.com\",\n",
+    "    project_id=\"PASTE YOUR PROJECT_ID HERE\",\n",
+    "    params=parameters,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "e1633a73",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
+    "\n",
+    "\n",
+    "class GetWeather(BaseModel):\n",
+    "    \"\"\"Get the current weather in a given location\"\"\"\n",
+    "\n",
+    "    location: str = Field(..., description=\"The city and state, e.g. San Francisco, CA\")\n",
+    "\n",
+    "\n",
+    "llm_with_tools = chat.bind_tools([GetWeather])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "3bf9b8ab",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='', additional_kwargs={'function_call': {'type': 'function'}, 'tool_calls': [{'type': 'function', 'function': {'name': 'GetWeather', 'arguments': '{\"location\": \"Los Angeles\"}'}, 'id': None}, {'type': 'function', 'function': {'name': 'GetWeather', 'arguments': '{\"location\": \"New York\"}'}, 'id': None}]}, response_metadata={'token_usage': {'generated_token_count': 99, 'input_token_count': 320}, 'model_name': 'mistralai/mixtral-8x7b-instruct-v01', 'system_fingerprint': '', 'finish_reason': 'eos_token'}, id='run-38627104-f2ac-4edb-8390-d5425fb65979-0', tool_calls=[{'name': 'GetWeather', 'args': {'location': 'Los Angeles'}, 'id': None}, {'name': 'GetWeather', 'args': {'location': 'New York'}, 'id': None}])"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ai_msg = llm_with_tools.invoke(\n",
+    "    \"Which city is hotter today: LA or NY?\",\n",
+    ")\n",
+    "ai_msg"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ba03dbf4",
+   "metadata": {},
+   "source": [
+    "### AIMessage.tool_calls\n",
+    "Notice that the AIMessage has a `tool_calls` attribute. This contains in a standardized ToolCall format that is model-provider agnostic."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "38f10ba7",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'name': 'GetWeather', 'args': {'location': 'Los Angeles'}, 'id': None},\n",
+       " {'name': 'GetWeather', 'args': {'location': 'New York'}, 'id': None}]"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ai_msg.tool_calls"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9ee72a59",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all IBM watsonx.ai features and configurations head to the API reference: https://api.python.langchain.com/en/latest/ibm_api_reference.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": "3.10.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/integrations/chat/llamacpp.ipynb

@@ -0,0 +1,418 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# ChatLlamaCpp\n",
+    "\n",
+    "This notebook provides a quick overview for getting started with chat model intergrated with [llama cpp python](https://github.com/abetlen/llama-cpp-python)."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Overview\n",
+    "\n",
+    "### Integration details\n",
+    "| Class | Package | Local | Serializable | JS support |\n",
+    "| :--- | :--- | :---: | :---: |  :---: |\n",
+    "| [ChatLlamaCpp](https://api.python.langchain.com/en/latest/chat_models/langchain_community.chat_models.llamacpp.ChatLlamaCpp.html) | [langchain-community](https://api.python.langchain.com/en/latest/community_api_reference.html) | ✅ | ❌ | ❌ |\n",
+    "\n",
+    "### Model features\n",
+    "| [Tool calling](/docs/how_to/tool_calling) | [Structured output](/docs/how_to/structured_output/) | JSON mode | Image input | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | Native async | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
+    "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
+    "| ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ✅ | \n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "To get started and use **all** the features show below, we reccomend using a model that has been fine-tuned for tool-calling.\n",
+    "\n",
+    "We will use [\n",
+    "Hermes-2-Pro-Llama-3-8B-GGUF](https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF) from NousResearch. \n",
+    "\n",
+    "> Hermes 2 Pro is an upgraded version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house. This new version of Hermes maintains its excellent general task and conversation capabilities - but also excels at Function Calling\n",
+    "\n",
+    "See our guides on local models to go deeper:\n",
+    "\n",
+    "* [Run LLMs locally](https://python.langchain.com/v0.1/docs/guides/development/local_llms/)\n",
+    "* [Using local models with RAG](https://python.langchain.com/v0.1/docs/use_cases/question_answering/local_retrieval_qa/)\n",
+    "\n",
+    "### Installation\n",
+    "\n",
+    "The LangChain OpenAI integration lives in the `langchain-community` and `llama-cpp-python` packages:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU langchain-community llama-cpp-python"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "Now we can instantiate our model object and generate chat completions:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Path to your model weights\n",
+    "local_model = \"local/path/to/Hermes-2-Pro-Llama-3-8B-Q8_0.gguf\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import multiprocessing\n",
+    "\n",
+    "from langchain_community.chat_models import ChatLlamaCpp\n",
+    "\n",
+    "llm = ChatLlamaCpp(\n",
+    "    temperature=0.5,\n",
+    "    model_path=local_model,\n",
+    "    n_ctx=10000,\n",
+    "    n_gpu_layers=8,\n",
+    "    n_batch=300,  # Should be between 1 and n_ctx, consider the amount of VRAM in your GPU.\n",
+    "    max_tokens=512,\n",
+    "    n_threads=multiprocessing.cpu_count() - 1,\n",
+    "    repeat_penalty=1.5,\n",
+    "    top_p=0.5,\n",
+    "    verbose=True,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Invocation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "messages = [\n",
+    "    (\n",
+    "        \"system\",\n",
+    "        \"You are a helpful assistant that translates English to French. Translate the user sentence.\",\n",
+    "    ),\n",
+    "    (\"human\", \"I love programming.\"),\n",
+    "]\n",
+    "\n",
+    "ai_msg = llm.invoke(messages)\n",
+    "ai_msg"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "J'aime programmer. (In France, \"programming\" is often used in its original sense of scheduling or organizing events.) \n",
+      "\n",
+      "If you meant computer-programming: \n",
+      "Je suis amoureux de la programmation informatique.\n",
+      "\n",
+      "(You might also say simply 'programmation', which would be understood as both meanings - depending on context).\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(ai_msg.content)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Chaining\n",
+    "\n",
+    "We can [chain](/docs/how_to/sequence/) our model with a prompt template like so:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            \"You are a helpful assistant that translates {input_language} to {output_language}.\",\n",
+    "        ),\n",
+    "        (\"human\", \"{input}\"),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "chain = prompt | llm\n",
+    "chain.invoke(\n",
+    "    {\n",
+    "        \"input_language\": \"English\",\n",
+    "        \"output_language\": \"German\",\n",
+    "        \"input\": \"I love programming.\",\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Tool calling\n",
+    "\n",
+    "Firstly, it works mostly the same as OpenAI Function Calling\n",
+    "\n",
+    "OpenAI has a [tool calling](https://platform.openai.com/docs/guides/function-calling) (we use \"tool calling\" and \"function calling\" interchangeably here) API that lets you describe tools and their arguments, and have the model return a JSON object with a tool to invoke and the inputs to that tool. tool-calling is extremely useful for building tool-using chains and agents, and for getting structured outputs from models more generally.\n",
+    "\n",
+    "With `ChatLlamaCpp.bind_tools`, we can easily pass in Pydantic classes, dict schemas, LangChain tools, or even functions as tools to the model. Under the hood these are converted to an OpenAI tool schemas, which looks like:\n",
+    "```\n",
+    "{\n",
+    "    \"name\": \"...\",\n",
+    "    \"description\": \"...\",\n",
+    "    \"parameters\": {...}  # JSONSchema\n",
+    "}\n",
+    "```\n",
+    "and passed in every model invocation.\n",
+    "\n",
+    "\n",
+    "However, it cannot automatically trigger a function/tool, we need to force it by specifying the 'tool choice' parameter. This parameter is typically formatted as described below.\n",
+    "\n",
+    "```{\"type\": \"function\", \"function\": {\"name\": <<tool_name>>}}.```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.tools import tool\n",
+    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
+    "\n",
+    "\n",
+    "class WeatherInput(BaseModel):\n",
+    "    location: str = Field(description=\"The city and state, e.g. San Francisco, CA\")\n",
+    "    unit: str = Field(enum=[\"celsius\", \"fahrenheit\"])\n",
+    "\n",
+    "\n",
+    "@tool(\"get_current_weather\", args_schema=WeatherInput)\n",
+    "def get_weather(location: str, unit: str):\n",
+    "    \"\"\"Get the current weather in a given location\"\"\"\n",
+    "    return f\"Now the weather in {location} is 22 {unit}\"\n",
+    "\n",
+    "\n",
+    "llm_with_tools = llm.bind_tools(\n",
+    "    tools=[get_weather],\n",
+    "    tool_choice={\"type\": \"function\", \"function\": {\"name\": \"get_current_weather\"}},\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ai_msg = llm_with_tools.invoke(\n",
+    "    \"what is the weather like in HCMC in celsius\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'name': 'get_current_weather',\n",
+       "  'args': {'location': 'Ho Chi Minh City', 'unit': 'celsius'},\n",
+       "  'id': 'call__0_get_current_weather_cmpl-394d9943-0a1f-425b-8139-d2826c1431f2'}]"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ai_msg.tool_calls"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class MagicFunctionInput(BaseModel):\n",
+    "    magic_function_input: int = Field(description=\"The input value for magic function\")\n",
+    "\n",
+    "\n",
+    "@tool(\"get_magic_function\", args_schema=MagicFunctionInput)\n",
+    "def magic_function(magic_function_input: int):\n",
+    "    \"\"\"Get the value of magic function for an input.\"\"\"\n",
+    "    return magic_function_input + 2\n",
+    "\n",
+    "\n",
+    "llm_with_tools = llm.bind_tools(\n",
+    "    tools=[magic_function],\n",
+    "    tool_choice={\"type\": \"function\", \"function\": {\"name\": \"get_magic_function\"}},\n",
+    ")\n",
+    "\n",
+    "ai_msg = llm_with_tools.invoke(\n",
+    "    \"What is magic function of 3?\",\n",
+    ")\n",
+    "\n",
+    "ai_msg"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'name': 'get_magic_function',\n",
+       "  'args': {'magic_function_input': 3},\n",
+       "  'id': 'call__0_get_magic_function_cmpl-cd83a994-b820-4428-957c-48076c68335a'}]"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ai_msg.tool_calls"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Structured output"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.pydantic_v1 import BaseModel\n",
+    "from langchain_core.utils.function_calling import convert_to_openai_tool\n",
+    "\n",
+    "\n",
+    "class Joke(BaseModel):\n",
+    "    \"\"\"A setup to a joke and the punchline.\"\"\"\n",
+    "\n",
+    "    setup: str\n",
+    "    punchline: str\n",
+    "\n",
+    "\n",
+    "dict_schema = convert_to_openai_tool(Joke)\n",
+    "structured_llm = llm.with_structured_output(dict_schema)\n",
+    "result = structured_llm.invoke(\"Tell me a joke about birds\")\n",
+    "result"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'setup': '- Why did the chicken cross the playground?',\n",
+       " 'punchline': '\\n\\n- To get to its gilded cage on the other side!'}"
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "result"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Streaming\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for chunk in llm.stream(\"what is 25x5\"):\n",
+    "    print(chunk.content, end=\"\\n\", flush=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all ChatLlamaCpp features and configurations head to the API reference: https://api.python.langchain.com/en/latest/chat_models/langchain_community.chat_models.llamacpp.ChatLlamaCpp.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": "3.11.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

docs/docs/integrations/chat/nvidia_ai_endpoints.ipynb

@@ -134,7 +134,7 @@
     "from langchain_nvidia_ai_endpoints import ChatNVIDIA\n",
     "\n",
     "# connect to an embedding NIM running at localhost:8000, specifying a specific model\n",
-    "llm = ChatNVIDIA(base_url=\"http://localhost:8000/v1\", model=\"meta-llama3-8b-instruct\")"
+    "llm = ChatNVIDIA(base_url=\"http://localhost:8000/v1\", model=\"meta/llama3-8b-instruct\")"
    ]
   },
   {
@@ -658,7 +658,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.13"
+   "version": "3.10.2"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/oci_generative_ai.ipynb

@@ -0,0 +1,190 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "id": "afaf8039",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_label: OCIGenAI\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e49f1e0d",
+   "metadata": {},
+   "source": [
+    "# ChatOCIGenAI\n",
+    "\n",
+    "This notebook provides a quick overview for getting started with OCIGenAI [chat models](/docs/concepts/#chat-models). For detailed documentation of all ChatOCIGenAI features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/chat_models/langchain_community.chat_models.oci_generative_ai.ChatOCIGenAI.html).\n",
+    "\n",
+    "Oracle Cloud Infrastructure (OCI) Generative AI is a fully managed service that provides a set of state-of-the-art, customizable large language models (LLMs) that cover a wide range of use cases, and which is available through a single API.\n",
+    "Using the OCI Generative AI service you can access ready-to-use pretrained models, or create and host your own fine-tuned custom models based on your own data on dedicated AI clusters. Detailed documentation of the service and API is available __[here](https://docs.oracle.com/en-us/iaas/Content/generative-ai/home.htm)__ and __[here](https://docs.oracle.com/en-us/iaas/api/#/en/generative-ai/20231130/)__.\n",
+    "\n",
+    "\n",
+    "## Overview\n",
+    "### Integration details\n",
+    "\n",
+    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/v0.2/docs/integrations/chat/oci_generative_ai) | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+    "| [ChatOCIGenAI](https://api.python.langchain.com/en/latest/chat_models/langchain_community.chat_models.oci_generative_ai.ChatOCIGenAI.html) | [langchain-community](https://api.python.langchain.com/en/latest/community_api_reference.html) | ❌ | ❌ | ❌ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-oci-generative-ai?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-oci-generative-ai?style=flat-square&label=%20) |\n",
+    "\n",
+    "### Model features\n",
+    "| [Tool calling](/docs/how_to/tool_calling/) | [Structured output](/docs/how_to/structured_output/) | JSON mode | [Image input](/docs/how_to/multimodal_inputs/) | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | Native async | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
+    "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
+    "| ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ | ✅ | ❌ | \n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "To access OCIGenAI models you'll need to install the `oci` and `langchain-community` packages.\n",
+    "\n",
+    "### Credentials\n",
+    "\n",
+    "The credentials and authentication methods supported for this integration are equivalent to those used with other OCI services and follow the __[standard SDK authentication](https://docs.oracle.com/en-us/iaas/Content/API/Concepts/sdk_authentication_methods.htm)__ methods, specifically API Key, session token, instance principal, and resource principal.\n",
+    "\n",
+    "API key is the default authentication method used in the examples above. The following example demonstrates how to use a different authentication method (session token)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0730d6a1-c893-4840-9817-5e5251676d5d",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "The LangChain OCIGenAI integration lives in the `langchain-community` package and you will also need to install the `oci` package:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU langchain-community oci"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a38cde65-254d-4219-a441-068766c0d4b5",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "Now we can instantiate our model object and generate chat completions:\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.chat_models.oci_generative_ai import ChatOCIGenAI\n",
+    "from langchain_core.messages import AIMessage, HumanMessage, SystemMessage\n",
+    "\n",
+    "chat = ChatOCIGenAI(\n",
+    "    model_id=\"cohere.command-r-16k\",\n",
+    "    service_endpoint=\"https://inference.generativeai.us-chicago-1.oci.oraclecloud.com\",\n",
+    "    compartment_id=\"MY_OCID\",\n",
+    "    model_kwargs={\"temperature\": 0.7, \"max_tokens\": 500},\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2b4f3e15",
+   "metadata": {},
+   "source": [
+    "## Invocation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "62e0dbc3",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "messages = [\n",
+    "    SystemMessage(content=\"your are an AI assistant.\"),\n",
+    "    AIMessage(content=\"Hi there human!\"),\n",
+    "    HumanMessage(content=\"tell me a joke.\"),\n",
+    "]\n",
+    "response = chat.invoke(messages)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d86145b3-bfef-46e8-b227-4dda5c9c2705",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(response.content)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "18e2bfc0-7e78-4528-a73f-499ac150dca8",
+   "metadata": {},
+   "source": [
+    "## Chaining\n",
+    "\n",
+    "We can [chain](/docs/how_to/sequence/) our model with a prompt template like so:\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_template(\"Tell me a joke about {topic}\")\n",
+    "chain = prompt | chat\n",
+    "\n",
+    "response = chain.invoke({\"topic\": \"dogs\"})\n",
+    "print(response.content)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all ChatOCIGenAI features and configurations head to the API reference: https://api.python.langchain.com/en/latest/chat_models/langchain_community.chat_models.oci_generative_ai.ChatOCIGenAI.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": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/integrations/chat/ollama_functions.ipynb

@@ -15,85 +15,85 @@
    "source": [
     "# OllamaFunctions\n",
     "\n",
-    "This notebook shows how to use an experimental wrapper around Ollama that gives it the same API as OpenAI Functions.\n",
+    "This notebook shows how to use an experimental wrapper around Ollama that gives it [tool calling capabilities](https://python.langchain.com/v0.2/docs/concepts/#functiontool-calling).\n",
     "\n",
     "Note that more powerful and capable models will perform better with complex schema and/or multiple functions. The examples below use llama3 and phi3 models.\n",
     "For a complete list of supported models and model variants, see the [Ollama model library](https://ollama.ai/library).\n",
     "\n",
+    ":::warning\n",
+    "\n",
+    "This is an experimental wrapper that attempts to bolt-on tool calling support to models that do not natively support it. Use with caution.\n",
+    "\n",
+    ":::\n",
+    "## Overview\n",
+    "\n",
+    "### Integration details\n",
+    "\n",
+    "|                                                                Class                                                                | Package | Local | Serializable | JS support | Package downloads | Package latest |\n",
+    "|:-----------------------------------------------------------------------------------------------------------------------------------:|:-------:|:-----:|:------------:|:----------:|:-----------------:|:--------------:|\n",
+    "| [OllamaFunctions](https://api.python.langchain.com/en/latest/llms/langchain_experimental.llms.ollama_function.OllamaFunctions.html) | [langchain-experimental](https://api.python.langchain.com/en/latest/openai_api_reference.html) | ✅ | ❌ | ❌ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-experimental?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-experimental?style=flat-square&label=%20) |\n",
+    "\n",
+    "### Model features\n",
+    "\n",
+    "| [Tool calling](/docs/how_to/tool_calling/) | [Structured output](/docs/how_to/structured_output/) | JSON mode | Image input | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | Native async | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
+    "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
+    "| ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ |\n",
+    "\n",
     "## Setup\n",
     "\n",
-    "Follow [these instructions](https://github.com/jmorganca/ollama) to set up and run a local Ollama instance.\n",
+    "To access `OllamaFunctions` you will need to install `langchain-experimental` integration package.\n",
+    "Follow [these instructions](https://github.com/jmorganca/ollama) to set up and run a local Ollama instance as well as download and serve [supported models](https://ollama.com/library).\n",
     "\n",
-    "## Usage\n",
+    "### Credentials\n",
     "\n",
-    "You can initialize OllamaFunctions in a similar way to how you'd initialize a standard ChatOllama instance:"
+    "Credentials support is not present at this time.\n",
+    "\n",
+    "### Installation\n",
+    "\n",
+    "The `OllamaFunctions` class lives in the `langchain-experimental` package:\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU langchain-experimental"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "`OllamaFunctions` takes the same init parameters as `ChatOllama`. \n",
+    "\n",
+    "In order to use tool calling, you must also specify `format=\"json\"`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-04-28T00:53:25.276543Z",
-     "start_time": "2024-04-28T00:53:24.881202Z"
-    },
-    "scrolled": true
+     "end_time": "2024-06-23T15:20:21.818089Z",
+     "start_time": "2024-06-23T15:20:21.815759Z"
+    }
    },
    "outputs": [],
    "source": [
     "from langchain_experimental.llms.ollama_functions import OllamaFunctions\n",
     "\n",
-    "model = OllamaFunctions(model=\"llama3\", format=\"json\")"
+    "llm = OllamaFunctions(model=\"phi3\")"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "You can then bind functions defined with JSON Schema parameters and a `function_call` parameter to force the model to call the given function:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2024-04-26T04:59:17.270931Z",
-     "start_time": "2024-04-26T04:59:17.263347Z"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "model = model.bind_tools(\n",
-    "    tools=[\n",
-    "        {\n",
-    "            \"name\": \"get_current_weather\",\n",
-    "            \"description\": \"Get the current weather in a given location\",\n",
-    "            \"parameters\": {\n",
-    "                \"type\": \"object\",\n",
-    "                \"properties\": {\n",
-    "                    \"location\": {\n",
-    "                        \"type\": \"string\",\n",
-    "                        \"description\": \"The city and state, \" \"e.g. San Francisco, CA\",\n",
-    "                    },\n",
-    "                    \"unit\": {\n",
-    "                        \"type\": \"string\",\n",
-    "                        \"enum\": [\"celsius\", \"fahrenheit\"],\n",
-    "                    },\n",
-    "                },\n",
-    "                \"required\": [\"location\"],\n",
-    "            },\n",
-    "        }\n",
-    "    ],\n",
-    "    function_call={\"name\": \"get_current_weather\"},\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Calling a function with this model then results in JSON output matching the provided schema:"
+    "## Invocation"
    ]
   },
   {
@@ -101,15 +101,15 @@
    "execution_count": 3,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-04-26T04:59:26.092428Z",
-     "start_time": "2024-04-26T04:59:17.272627Z"
+     "end_time": "2024-06-23T15:20:46.794689Z",
+     "start_time": "2024-06-23T15:20:44.982632Z"
     }
    },
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='', additional_kwargs={'function_call': {'name': 'get_current_weather', 'arguments': '{\"location\": \"Boston, MA\"}'}}, id='run-1791f9fe-95ad-4ca4-bdf7-9f73eab31e6f-0')"
+       "AIMessage(content=\"J'adore programmer.\", id='run-94815fcf-ae11-438a-ba3f-00819328b5cd-0')"
       ]
      },
      "execution_count": 3,
@@ -118,79 +118,55 @@
     }
    ],
    "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "model.invoke(\"what is the weather in Boston?\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Structured Output\n",
-    "\n",
-    "One useful thing you can do with function calling using `with_structured_output()` function is extracting properties from a given input in a structured format:"
+    "messages = [\n",
+    "    (\n",
+    "        \"system\",\n",
+    "        \"You are a helpful assistant that translates English to French. Translate the user sentence.\",\n",
+    "    ),\n",
+    "    (\"human\", \"I love programming.\"),\n",
+    "]\n",
+    "ai_msg = llm.invoke(messages)\n",
+    "ai_msg"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 4,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2024-04-26T04:59:26.098828Z",
-     "start_time": "2024-04-26T04:59:26.094021Z"
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"J'adore programmer.\""
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
     }
-   },
-   "outputs": [],
+   ],
    "source": [
-    "from langchain_core.prompts import PromptTemplate\n",
-    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
-    "\n",
-    "\n",
-    "# Schema for structured response\n",
-    "class Person(BaseModel):\n",
-    "    name: str = Field(description=\"The person's name\", required=True)\n",
-    "    height: float = Field(description=\"The person's height\", required=True)\n",
-    "    hair_color: str = Field(description=\"The person's hair color\")\n",
-    "\n",
-    "\n",
-    "# Prompt template\n",
-    "prompt = PromptTemplate.from_template(\n",
-    "    \"\"\"Alex is 5 feet tall. \n",
-    "Claudia is 1 feet taller than Alex and jumps higher than him. \n",
-    "Claudia is a brunette and Alex is blonde.\n",
-    "\n",
-    "Human: {question}\n",
-    "AI: \"\"\"\n",
-    ")\n",
-    "\n",
-    "# Chain\n",
-    "llm = OllamaFunctions(model=\"phi3\", format=\"json\", temperature=0)\n",
-    "structured_llm = llm.with_structured_output(Person)\n",
-    "chain = prompt | structured_llm"
+    "ai_msg.content"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Extracting data about Alex"
+    "## Chaining\n",
+    "\n",
+    "We can [chain](https://python.langchain.com/v0.2/docs/how_to/sequence/) our model with a prompt template like so:"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 5,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2024-04-26T04:59:30.164955Z",
-     "start_time": "2024-04-26T04:59:26.099790Z"
-    }
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "Person(name='Alex', height=5.0, hair_color='blonde')"
+       "AIMessage(content='Programmieren ist sehr verrückt! Es freut mich, dass Sie auf Programmierung so positiv eingestellt sind.', id='run-ee99be5e-4d48-4ab6-b602-35415f0bdbde-0')"
       ]
      },
      "execution_count": 5,
@@ -199,41 +175,123 @@
     }
    ],
    "source": [
-    "alex = chain.invoke(\"Describe Alex\")\n",
-    "alex"
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            \"You are a helpful assistant that translates {input_language} to {output_language}.\",\n",
+    "        ),\n",
+    "        (\"human\", \"{input}\"),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "chain = prompt | llm\n",
+    "chain.invoke(\n",
+    "    {\n",
+    "        \"input_language\": \"English\",\n",
+    "        \"output_language\": \"German\",\n",
+    "        \"input\": \"I love programming.\",\n",
+    "    }\n",
+    ")"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Extracting data about Claudia"
+    "## Tool Calling\n",
+    "\n",
+    "### OllamaFunctions.bind_tools()\n",
+    "\n",
+    "With `OllamaFunctions.bind_tools`, we can easily pass in Pydantic classes, dict schemas, LangChain tools, or even functions as tools to the model. Under the hood these are converted to a tool definition schemas, which looks like:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2024-04-26T04:59:31.509846Z",
-     "start_time": "2024-04-26T04:59:30.165662Z"
-    }
-   },
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
+    "\n",
+    "\n",
+    "class GetWeather(BaseModel):\n",
+    "    \"\"\"Get the current weather in a given location\"\"\"\n",
+    "\n",
+    "    location: str = Field(..., description=\"The city and state, e.g. San Francisco, CA\")\n",
+    "\n",
+    "\n",
+    "llm_with_tools = llm.bind_tools([GetWeather])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "Person(name='Claudia', height=6.0, hair_color='brunette')"
+       "AIMessage(content='', id='run-b9769435-ec6a-4cb8-8545-5a5035fc19bd-0', tool_calls=[{'name': 'GetWeather', 'args': {'location': 'San Francisco, CA'}, 'id': 'call_064c4e1cb27e4adb9e4e7ed60362ecc9'}])"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "claudia = chain.invoke(\"Describe Claudia\")\n",
-    "claudia"
+    "ai_msg = llm_with_tools.invoke(\n",
+    "    \"what is the weather like in San Francisco\",\n",
+    ")\n",
+    "ai_msg"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### AIMessage.tool_calls\n",
+    "\n",
+    "Notice that the AIMessage has a `tool_calls` attribute. This contains in a standardized `ToolCall` format that is model-provider agnostic."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'name': 'GetWeather',\n",
+       "  'args': {'location': 'San Francisco, CA'},\n",
+       "  'id': 'call_064c4e1cb27e4adb9e4e7ed60362ecc9'}]"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ai_msg.tool_calls"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": "For more on binding tools and tool call outputs, head to the [tool calling](docs/how_to/function_calling) docs."
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all ToolCallingLLM features and configurations head to the API reference: https://api.python.langchain.com/en/latest/llms/langchain_experimental.llms.ollama_functions.OllamaFunctions.html\n"
    ]
   }
  ],
@@ -253,7 +311,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/openai.ipynb

@@ -41,7 +41,7 @@
     "| [ChatOpenAI](https://api.python.langchain.com/en/latest/chat_models/langchain_openai.chat_models.base.ChatOpenAI.html) | [langchain-openai](https://api.python.langchain.com/en/latest/openai_api_reference.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-openai?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-openai?style=flat-square&label=%20) |\n",
     "\n",
     "### Model features\n",
-    "| [Tool calling](/docs/how_to/tool_calling/) | [Structured output](/docs/how_to/structured_output/) | JSON mode | Image input | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | Native async | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
+    "| [Tool calling](/docs/how_to/tool_calling) | [Structured output](/docs/how_to/structured_output/) | JSON mode | Image input | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | Native async | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
     "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
     "| ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | ✅ | ✅ | ✅ | ✅ | \n",
     "\n",
@@ -426,7 +426,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.11.9"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/perplexity.ipynb

@@ -45,7 +45,7 @@
     "The code provided assumes that your PPLX_API_KEY is set in your environment variables. If you would like to manually specify your API key and also choose a different model, you can use the following code:\n",
     "\n",
     "```python\n",
-    "chat = ChatPerplexity(temperature=0, pplx_api_key=\"YOUR_API_KEY\", model=\"pplx-70b-online\")\n",
+    "chat = ChatPerplexity(temperature=0, pplx_api_key=\"YOUR_API_KEY\", model=\"llama-3-sonar-small-32k-online\")\n",
     "```\n",
     "\n",
     "You can check a list of available models [here](https://docs.perplexity.ai/docs/model-cards). For reproducibility, we can set the API key dynamically by taking it as an input in this notebook."
@@ -78,7 +78,7 @@
    },
    "outputs": [],
    "source": [
-    "chat = ChatPerplexity(temperature=0, model=\"pplx-70b-online\")"
+    "chat = ChatPerplexity(temperature=0, model=\"llama-3-sonar-small-32k-online\")"
    ]
   },
   {
@@ -146,7 +146,7 @@
     }
    ],
    "source": [
-    "chat = ChatPerplexity(temperature=0, model=\"pplx-70b-online\")\n",
+    "chat = ChatPerplexity(temperature=0, model=\"llama-3-sonar-small-32k-online\")\n",
     "prompt = ChatPromptTemplate.from_messages([(\"human\", \"Tell me a joke about {topic}\")])\n",
     "chain = prompt | chat\n",
     "response = chain.invoke({\"topic\": \"cats\"})\n",
@@ -195,7 +195,7 @@
     }
    ],
    "source": [
-    "chat = ChatPerplexity(temperature=0.7, model=\"pplx-70b-online\")\n",
+    "chat = ChatPerplexity(temperature=0.7, model=\"llama-3-sonar-small-32k-online\")\n",
     "prompt = ChatPromptTemplate.from_messages(\n",
     "    [(\"human\", \"Give me a list of famous tourist attractions in Pakistan\")]\n",
     ")\n",

docs/docs/integrations/chat/premai.ipynb

@@ -238,6 +238,67 @@
     "> Ideally, you do not need to connect Repository IDs here to get Retrieval Augmented Generations. You can still get the same result if you have connected the repositories in prem platform. "
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Prem Templates\n",
+    "\n",
+    "Writing Prompt Templates can be super messy. Prompt templates are long, hard to manage, and must be continuously tweaked to improve and keep the same throughout the application. \n",
+    "\n",
+    "With **Prem**, writing and managing prompts can be super easy. The **_Templates_** tab inside the [launchpad](https://docs.premai.io/get-started/launchpad) helps you write as many prompts you need and use it inside the SDK to make your application running using those prompts. You can read more about Prompt Templates [here](https://docs.premai.io/get-started/prem-templates). \n",
+    "\n",
+    "To use Prem Templates natively with LangChain, you need to pass an id the `HumanMessage`. This id should be the name the variable of your prompt template. the `content` in `HumanMessage` should be the value of that variable. \n",
+    "\n",
+    "let's say for example, if your prompt template was this:\n",
+    "\n",
+    "```text\n",
+    "Say hello to my name and say a feel-good quote\n",
+    "from my age. My name is: {name} and age is {age}\n",
+    "```\n",
+    "\n",
+    "So now your human_messages should look like:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "human_messages = [\n",
+    "    HumanMessage(content=\"Shawn\", id=\"name\"),\n",
+    "    HumanMessage(content=\"22\", id=\"age\"),\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "\n",
+    "Pass this `human_messages` to ChatPremAI Client. Please note: Do not forget to\n",
+    "pass the additional `template_id` to invoke generation with Prem Templates. If you are not aware of `template_id` you can learn more about that [in our docs](https://docs.premai.io/get-started/prem-templates). Here is an example:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "template_id = \"78069ce8-xxxxx-xxxxx-xxxx-xxx\"\n",
+    "response = chat.invoke([human_message], template_id=template_id)\n",
+    "print(response.content)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Prem Template feature is available in streaming too. "
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},

docs/docs/integrations/chat/snowflake.ipynb

@@ -0,0 +1,180 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Snowflake Cortex\n",
+    "\n",
+    "[Snowflake Cortex](https://docs.snowflake.com/en/user-guide/snowflake-cortex/llm-functions) gives you instant access to industry-leading large language models (LLMs) trained by researchers at companies like Mistral, Reka, Meta, and Google, including [Snowflake Arctic](https://www.snowflake.com/en/data-cloud/arctic/), an open enterprise-grade model developed by Snowflake.\n",
+    "\n",
+    "This example goes over how to use LangChain to interact with Snowflake Cortex."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Installation and setup\n",
+    "\n",
+    "We start by installing the `snowflake-snowpark-python` library, using the command below. Then we configure the credentials for connecting to Snowflake, as environment variables or pass them directly."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
+   "source": [
+    "%pip install --upgrade --quiet snowflake-snowpark-python"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "# First step is to set up the environment variables, to connect to Snowflake,\n",
+    "# you can also pass these snowflake credentials while instantiating the model\n",
+    "\n",
+    "if os.environ.get(\"SNOWFLAKE_ACCOUNT\") is None:\n",
+    "    os.environ[\"SNOWFLAKE_ACCOUNT\"] = getpass.getpass(\"Account: \")\n",
+    "\n",
+    "if os.environ.get(\"SNOWFLAKE_USERNAME\") is None:\n",
+    "    os.environ[\"SNOWFLAKE_USERNAME\"] = getpass.getpass(\"Username: \")\n",
+    "\n",
+    "if os.environ.get(\"SNOWFLAKE_PASSWORD\") is None:\n",
+    "    os.environ[\"SNOWFLAKE_PASSWORD\"] = getpass.getpass(\"Password: \")\n",
+    "\n",
+    "if os.environ.get(\"SNOWFLAKE_DATABASE\") is None:\n",
+    "    os.environ[\"SNOWFLAKE_DATABASE\"] = getpass.getpass(\"Database: \")\n",
+    "\n",
+    "if os.environ.get(\"SNOWFLAKE_SCHEMA\") is None:\n",
+    "    os.environ[\"SNOWFLAKE_SCHEMA\"] = getpass.getpass(\"Schema: \")\n",
+    "\n",
+    "if os.environ.get(\"SNOWFLAKE_WAREHOUSE\") is None:\n",
+    "    os.environ[\"SNOWFLAKE_WAREHOUSE\"] = getpass.getpass(\"Warehouse: \")\n",
+    "\n",
+    "if os.environ.get(\"SNOWFLAKE_ROLE\") is None:\n",
+    "    os.environ[\"SNOWFLAKE_ROLE\"] = getpass.getpass(\"Role: \")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.chat_models import ChatSnowflakeCortex\n",
+    "from langchain_core.messages import HumanMessage, SystemMessage\n",
+    "\n",
+    "# By default, we'll be using the cortex provided model: `snowflake-arctic`, with function: `complete`\n",
+    "chat = ChatSnowflakeCortex()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The above cell assumes that your Snowflake credentials are set in your environment variables. If you would rather manually specify them, use the following code:\n",
+    "\n",
+    "```python\n",
+    "chat = ChatSnowflakeCortex(\n",
+    "    # change default cortex model and function\n",
+    "    model=\"snowflake-arctic\",\n",
+    "    cortex_function=\"complete\",\n",
+    "\n",
+    "    # change default generation parameters\n",
+    "    temperature=0,\n",
+    "    max_tokens=10,\n",
+    "    top_p=0.95,\n",
+    "\n",
+    "    # specify snowflake credentials\n",
+    "    account=\"YOUR_SNOWFLAKE_ACCOUNT\",\n",
+    "    username=\"YOUR_SNOWFLAKE_USERNAME\",\n",
+    "    password=\"YOUR_SNOWFLAKE_PASSWORD\",\n",
+    "    database=\"YOUR_SNOWFLAKE_DATABASE\",\n",
+    "    schema=\"YOUR_SNOWFLAKE_SCHEMA\",\n",
+    "    role=\"YOUR_SNOWFLAKE_ROLE\",\n",
+    "    warehouse=\"YOUR_SNOWFLAKE_WAREHOUSE\"\n",
+    ")\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Calling the model\n",
+    "We can now call the model using the `invoke` or `generate` method.\n",
+    "\n",
+    "#### Generation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\" Large language models are artificial intelligence systems designed to understand, generate, and manipulate human language. These models are typically based on deep learning techniques and are trained on vast amounts of text data to learn patterns and structures in language. They can perform a wide range of language-related tasks, such as language translation, text generation, sentiment analysis, and answering questions. Some well-known large language models include Google's BERT, OpenAI's GPT series, and Facebook's RoBERTa. These models have shown remarkable performance in various natural language processing tasks, and their applications continue to expand as research in AI progresses.\", response_metadata={'completion_tokens': 131, 'prompt_tokens': 29, 'total_tokens': 160}, id='run-5435bd0a-83fd-4295-b237-66cbd1b5c0f3-0')"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "messages = [\n",
+    "    SystemMessage(content=\"You are a friendly assistant.\"),\n",
+    "    HumanMessage(content=\"What are large language models?\"),\n",
+    "]\n",
+    "chat.invoke(messages)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Streaming\n",
+    "`ChatSnowflakeCortex` doesn't support streaming as of now. Support for streaming will be coming in the later versions!"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/docs/integrations/document_loaders/async_chromium.ipynb

@@ -13,7 +13,7 @@
     "\n",
     "Headless mode means that the browser is running without a graphical user interface.\n",
     "\n",
-    "`AsyncChromiumLoader` loads the page, and then we use `Html2TextTransformer` to transform to text."
+    "In the below example we'll use the `AsyncChromiumLoader` to loads the page, and then the [`Html2TextTransformer`](/docs/integrations/document_transformers/html2text/) to strip out the HTML tags and other semantic information."
    ]
   },
   {
@@ -23,48 +23,22 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet  playwright beautifulsoup4\n",
+    "%pip install --upgrade --quiet playwright beautifulsoup4 html2text\n",
     "!playwright install"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "dd2cdea7",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'<!DOCTYPE html><html lang=\"en\"><head><script src=\"https://s0.2mdn.net/instream/video/client.js\" asyn'"
-      ]
-     },
-     "execution_count": 2,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_community.document_loaders import AsyncChromiumLoader\n",
-    "\n",
-    "urls = [\"https://www.wsj.com\"]\n",
-    "loader = AsyncChromiumLoader(urls, user_agent=\"MyAppUserAgent\")\n",
-    "docs = loader.load()\n",
-    "docs[0].page_content[0:100]"
-   ]
-  },
   {
    "cell_type": "markdown",
-   "id": "c64e7df9",
+   "id": "00487c0f",
    "metadata": {},
    "source": [
-    "If you are using Jupyter notebooks, you might need to apply `nest_asyncio` before loading the documents."
+    "**Note:** If you are using Jupyter notebooks, you might also need to install and apply `nest_asyncio` before loading the documents like this:"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "5f2fe3c0",
+   "id": "d374eef4",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -74,6 +48,40 @@
     "nest_asyncio.apply()"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "dd2cdea7",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'<!DOCTYPE html><html lang=\"en\" dir=\"ltr\" class=\"docs-wrapper docs-doc-page docs-version-2.0 plugin-d'"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_community.document_loaders import AsyncChromiumLoader\n",
+    "\n",
+    "urls = [\"https://docs.smith.langchain.com/\"]\n",
+    "loader = AsyncChromiumLoader(urls, user_agent=\"MyAppUserAgent\")\n",
+    "docs = loader.load()\n",
+    "docs[0].page_content[0:100]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7eb5e6aa",
+   "metadata": {},
+   "source": [
+    "Now let's transform the documents into a more readable syntax using the transformer:"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 6,
@@ -83,7 +91,7 @@
     {
      "data": {
       "text/plain": [
-       "\"Skip to Main ContentSkip to SearchSkip to... Select * Top News * What's News *\\nFeatured Stories * Retirement * Life & Arts * Hip-Hop * Sports * Video *\\nEconomy * Real Estate * Sports * CMO * CIO * CFO * Risk & Compliance *\\nLogistics Report * Sustainable Business * Heard on the Street * Barron’s *\\nMarketWatch * Mansion Global * Penta * Opinion * Journal Reports * Sponsored\\nOffers Explore Our Brands * WSJ * * * * * Barron's * * * * * MarketWatch * * *\\n* * IBD # The Wall Street Journal SubscribeSig\""
+       "'Skip to main content\\n\\nGo to API Docs\\n\\nSearch`⌘``K`\\n\\nGo to App\\n\\n  * Quick start\\n  * Tutorials\\n\\n  * How-to guides\\n\\n  * Concepts\\n\\n  * Reference\\n\\n  * Pricing\\n  * Self-hosting\\n\\n  * LangGraph Cloud\\n\\n  *   * Quick start\\n\\nOn this page\\n\\n# Get started with LangSmith\\n\\n**LangSmith** is a platform for building production-grade LLM applications. It\\nallows you to closely monitor and evaluate your application, so you can ship\\nquickly and with confidence. Use of LangChain is not necessary - LangSmith\\nworks on it'"
       ]
      },
      "execution_count": 6,
@@ -116,7 +124,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.16"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/integrations/document_loaders/email.ipynb

@@ -7,7 +7,9 @@
    "source": [
     "# Email\n",
     "\n",
-    "This notebook shows how to load email (`.eml`) or `Microsoft Outlook` (`.msg`) files."
+    "This notebook shows how to load email (`.eml`) or `Microsoft Outlook` (`.msg`) files.\n",
+    "\n",
+    "Please see [this guide](/docs/integrations/providers/unstructured/) for more instructions on setting up Unstructured locally, including setting up required system dependencies."
    ]
   },
   {
@@ -27,49 +29,13 @@
    },
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet  unstructured"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "40cd9806",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain_community.document_loaders import UnstructuredEmailLoader"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "2d20b852",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "loader = UnstructuredEmailLoader(\"example_data/fake-email.eml\")"
+    "%pip install --upgrade --quiet unstructured"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 3,
-   "id": "579fa702",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "data = loader.load()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "90c1d899",
+   "id": "2d20b852",
    "metadata": {
     "tags": []
    },
@@ -77,15 +43,21 @@
     {
      "data": {
       "text/plain": [
-       "[Document(page_content='This is a test email to use for unit tests.\\n\\nImportant points:\\n\\nRoses are red\\n\\nViolets are blue', metadata={'source': 'example_data/fake-email.eml'})]"
+       "[Document(page_content='This is a test email to use for unit tests.\\n\\nImportant points:\\n\\nRoses are red\\n\\nViolets are blue', metadata={'source': './example_data/fake-email.eml'})]"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
+    "from langchain_community.document_loaders import UnstructuredEmailLoader\n",
+    "\n",
+    "loader = UnstructuredEmailLoader(\"./example_data/fake-email.eml\")\n",
+    "\n",
+    "data = loader.load()\n",
+    "\n",
     "data"
    ]
   },
@@ -101,42 +73,26 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "id": "b9592eaf",
    "metadata": {},
-   "outputs": [],
-   "source": [
-    "loader = UnstructuredEmailLoader(\"example_data/fake-email.eml\", mode=\"elements\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "0b16d03f",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "data = loader.load()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "d7bdc5e5",
-   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "Document(page_content='This is a test email to use for unit tests.', metadata={'source': 'example_data/fake-email.eml', 'filename': 'fake-email.eml', 'file_directory': 'example_data', 'date': '2022-12-16T17:04:16-05:00', 'filetype': 'message/rfc822', 'sent_from': ['Matthew Robinson <mrobinson@unstructured.io>'], 'sent_to': ['Matthew Robinson <mrobinson@unstructured.io>'], 'subject': 'Test Email', 'category': 'NarrativeText'})"
+       "Document(page_content='This is a test email to use for unit tests.', metadata={'source': 'example_data/fake-email.eml', 'file_directory': 'example_data', 'filename': 'fake-email.eml', 'last_modified': '2022-12-16T17:04:16-05:00', 'sent_from': ['Matthew Robinson <mrobinson@unstructured.io>'], 'sent_to': ['Matthew Robinson <mrobinson@unstructured.io>'], 'subject': 'Test Email', 'languages': ['eng'], 'filetype': 'message/rfc822', 'category': 'NarrativeText'})"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
+    "loader = UnstructuredEmailLoader(\"example_data/fake-email.eml\", mode=\"elements\")\n",
+    "\n",
+    "data = loader.load()\n",
+    "\n",
     "data[0]"
    ]
   },
@@ -152,46 +108,30 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 5,
    "id": "6539f166",
    "metadata": {},
-   "outputs": [],
-   "source": [
-    "loader = UnstructuredEmailLoader(\n",
-    "    \"example_data/fake-email.eml\",\n",
-    "    mode=\"elements\",\n",
-    "    process_attachments=True,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "aebead38",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "data = loader.load()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "ddeb60f4",
-   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "Document(page_content='This is a test email to use for unit tests.', metadata={'source': 'example_data/fake-email.eml', 'filename': 'fake-email.eml', 'file_directory': 'example_data', 'date': '2022-12-16T17:04:16-05:00', 'filetype': 'message/rfc822', 'sent_from': ['Matthew Robinson <mrobinson@unstructured.io>'], 'sent_to': ['Matthew Robinson <mrobinson@unstructured.io>'], 'subject': 'Test Email', 'category': 'NarrativeText'})"
+       "Document(page_content='This is a test email to use for unit tests.', metadata={'source': 'example_data/fake-email.eml', 'file_directory': 'example_data', 'filename': 'fake-email.eml', 'last_modified': '2022-12-16T17:04:16-05:00', 'sent_from': ['Matthew Robinson <mrobinson@unstructured.io>'], 'sent_to': ['Matthew Robinson <mrobinson@unstructured.io>'], 'subject': 'Test Email', 'languages': ['eng'], 'filetype': 'message/rfc822', 'category': 'NarrativeText'})"
       ]
      },
-     "execution_count": 10,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
+    "loader = UnstructuredEmailLoader(\n",
+    "    \"example_data/fake-email.eml\",\n",
+    "    mode=\"elements\",\n",
+    "    process_attachments=True,\n",
+    ")\n",
+    "\n",
+    "data = loader.load()\n",
+    "\n",
     "data[0]"
    ]
   },
@@ -210,57 +150,33 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet  extract_msg"
+    "%pip install --upgrade --quiet extract_msg"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 7,
    "id": "1e7a8444",
    "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_community.document_loaders import OutlookMessageLoader"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "77a055e6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "loader = OutlookMessageLoader(\"example_data/fake-email.msg\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "789882de",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "data = loader.load()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "46aa0632",
-   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "Document(page_content='This is a test email to experiment with the MS Outlook MSG Extractor\\r\\n\\r\\n\\r\\n-- \\r\\n\\r\\n\\r\\nKind regards\\r\\n\\r\\n\\r\\n\\r\\n\\r\\nBrian Zhou\\r\\n\\r\\n', metadata={'subject': 'Test for TIF files', 'sender': 'Brian Zhou <brizhou@gmail.com>', 'date': 'Mon, 18 Nov 2013 16:26:24 +0800'})"
+       "Document(page_content='This is a test email to experiment with the MS Outlook MSG Extractor\\r\\n\\r\\n\\r\\n-- \\r\\n\\r\\n\\r\\nKind regards\\r\\n\\r\\n\\r\\n\\r\\n\\r\\nBrian Zhou\\r\\n\\r\\n', metadata={'source': 'example_data/fake-email.msg', 'subject': 'Test for TIF files', 'sender': 'Brian Zhou <brizhou@gmail.com>', 'date': datetime.datetime(2013, 11, 18, 0, 26, 24, tzinfo=zoneinfo.ZoneInfo(key='America/Los_Angeles'))})"
       ]
      },
-     "execution_count": 11,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
+    "from langchain_community.document_loaders import OutlookMessageLoader\n",
+    "\n",
+    "loader = OutlookMessageLoader(\"example_data/fake-email.msg\")\n",
+    "\n",
+    "data = loader.load()\n",
+    "\n",
     "data[0]"
    ]
   },
@@ -289,7 +205,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.13"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/integrations/document_loaders/example_data/state_of_the_union.txt

@@ -0,0 +1,723 @@
+Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans.  
+
+Last year COVID-19 kept us apart. This year we are finally together again. 
+
+Tonight, we meet as Democrats Republicans and Independents. But most importantly as Americans. 
+
+With a duty to one another to the American people to the Constitution. 
+
+And with an unwavering resolve that freedom will always triumph over tyranny. 
+
+Six days ago, Russia’s Vladimir Putin sought to shake the foundations of the free world thinking he could make it bend to his menacing ways. But he badly miscalculated. 
+
+He thought he could roll into Ukraine and the world would roll over. Instead he met a wall of strength he never imagined. 
+
+He met the Ukrainian people. 
+
+From President Zelenskyy to every Ukrainian, their fearlessness, their courage, their determination, inspires the world. 
+
+Groups of citizens blocking tanks with their bodies. Everyone from students to retirees teachers turned soldiers defending their homeland. 
+
+In this struggle as President Zelenskyy said in his speech to the European Parliament “Light will win over darkness.” The Ukrainian Ambassador to the United States is here tonight. 
+
+Let each of us here tonight in this Chamber send an unmistakable signal to Ukraine and to the world. 
+
+Please rise if you are able and show that, Yes, we the United States of America stand with the Ukrainian people. 
+
+Throughout our history we’ve learned this lesson when dictators do not pay a price for their aggression they cause more chaos.   
+
+They keep moving.   
+
+And the costs and the threats to America and the world keep rising.   
+
+That’s why the NATO Alliance was created to secure peace and stability in Europe after World War 2. 
+
+The United States is a member along with 29 other nations. 
+
+It matters. American diplomacy matters. American resolve matters. 
+
+Putin’s latest attack on Ukraine was premeditated and unprovoked. 
+
+He rejected repeated efforts at diplomacy. 
+
+He thought the West and NATO wouldn’t respond. And he thought he could divide us at home. Putin was wrong. We were ready.  Here is what we did.   
+
+We prepared extensively and carefully. 
+
+We spent months building a coalition of other freedom-loving nations from Europe and the Americas to Asia and Africa to confront Putin. 
+
+I spent countless hours unifying our European allies. We shared with the world in advance what we knew Putin was planning and precisely how he would try to falsely justify his aggression.  
+
+We countered Russia’s lies with truth.   
+
+And now that he has acted the free world is holding him accountable. 
+
+Along with twenty-seven members of the European Union including France, Germany, Italy, as well as countries like the United Kingdom, Canada, Japan, Korea, Australia, New Zealand, and many others, even Switzerland. 
+
+We are inflicting pain on Russia and supporting the people of Ukraine. Putin is now isolated from the world more than ever. 
+
+Together with our allies –we are right now enforcing powerful economic sanctions. 
+
+We are cutting off Russia’s largest banks from the international financial system.  
+
+Preventing Russia’s central bank from defending the Russian Ruble making Putin’s $630 Billion “war fund” worthless.   
+
+We are choking off Russia’s access to technology that will sap its economic strength and weaken its military for years to come.  
+
+Tonight I say to the Russian oligarchs and corrupt leaders who have bilked billions of dollars off this violent regime no more. 
+
+The U.S. Department of Justice is assembling a dedicated task force to go after the crimes of Russian oligarchs.  
+
+We are joining with our European allies to find and seize your yachts your luxury apartments your private jets. We are coming for your ill-begotten gains. 
+
+And tonight I am announcing that we will join our allies in closing off American air space to all Russian flights – further isolating Russia – and adding an additional squeeze –on their economy. The Ruble has lost 30% of its value. 
+
+The Russian stock market has lost 40% of its value and trading remains suspended. Russia’s economy is reeling and Putin alone is to blame. 
+
+Together with our allies we are providing support to the Ukrainians in their fight for freedom. Military assistance. Economic assistance. Humanitarian assistance. 
+
+We are giving more than $1 Billion in direct assistance to Ukraine. 
+
+And we will continue to aid the Ukrainian people as they defend their country and to help ease their suffering.  
+
+Let me be clear, our forces are not engaged and will not engage in conflict with Russian forces in Ukraine.  
+
+Our forces are not going to Europe to fight in Ukraine, but to defend our NATO Allies – in the event that Putin decides to keep moving west.  
+
+For that purpose we’ve mobilized American ground forces, air squadrons, and ship deployments to protect NATO countries including Poland, Romania, Latvia, Lithuania, and Estonia. 
+
+As I have made crystal clear the United States and our Allies will defend every inch of territory of NATO countries with the full force of our collective power.  
+
+And we remain clear-eyed. The Ukrainians are fighting back with pure courage. But the next few days weeks, months, will be hard on them.  
+
+Putin has unleashed violence and chaos.  But while he may make gains on the battlefield – he will pay a continuing high price over the long run. 
+
+And a proud Ukrainian people, who have known 30 years  of independence, have repeatedly shown that they will not tolerate anyone who tries to take their country backwards.  
+
+To all Americans, I will be honest with you, as I’ve always promised. A Russian dictator, invading a foreign country, has costs around the world. 
+
+And I’m taking robust action to make sure the pain of our sanctions  is targeted at Russia’s economy. And I will use every tool at our disposal to protect American businesses and consumers. 
+
+Tonight, I can announce that the United States has worked with 30 other countries to release 60 Million barrels of oil from reserves around the world.  
+
+America will lead that effort, releasing 30 Million barrels from our own Strategic Petroleum Reserve. And we stand ready to do more if necessary, unified with our allies.  
+
+These steps will help blunt gas prices here at home. And I know the news about what’s happening can seem alarming. 
+
+But I want you to know that we are going to be okay. 
+
+When the history of this era is written Putin’s war on Ukraine will have left Russia weaker and the rest of the world stronger. 
+
+While it shouldn’t have taken something so terrible for people around the world to see what’s at stake now everyone sees it clearly. 
+
+We see the unity among leaders of nations and a more unified Europe a more unified West. And we see unity among the people who are gathering in cities in large crowds around the world even in Russia to demonstrate their support for Ukraine.  
+
+In the battle between democracy and autocracy, democracies are rising to the moment, and the world is clearly choosing the side of peace and security. 
+
+This is a real test. It’s going to take time. So let us continue to draw inspiration from the iron will of the Ukrainian people. 
+
+To our fellow Ukrainian Americans who forge a deep bond that connects our two nations we stand with you. 
+
+Putin may circle Kyiv with tanks, but he will never gain the hearts and souls of the Ukrainian people. 
+
+He will never extinguish their love of freedom. He will never weaken the resolve of the free world. 
+
+We meet tonight in an America that has lived through two of the hardest years this nation has ever faced. 
+
+The pandemic has been punishing. 
+
+And so many families are living paycheck to paycheck, struggling to keep up with the rising cost of food, gas, housing, and so much more. 
+
+I understand. 
+
+I remember when my Dad had to leave our home in Scranton, Pennsylvania to find work. I grew up in a family where if the price of food went up, you felt it. 
+
+That’s why one of the first things I did as President was fight to pass the American Rescue Plan.  
+
+Because people were hurting. We needed to act, and we did. 
+
+Few pieces of legislation have done more in a critical moment in our history to lift us out of crisis. 
+
+It fueled our efforts to vaccinate the nation and combat COVID-19. It delivered immediate economic relief for tens of millions of Americans.  
+
+Helped put food on their table, keep a roof over their heads, and cut the cost of health insurance. 
+
+And as my Dad used to say, it gave people a little breathing room. 
+
+And unlike the $2 Trillion tax cut passed in the previous administration that benefitted the top 1% of Americans, the American Rescue Plan helped working people—and left no one behind. 
+
+And it worked. It created jobs. Lots of jobs. 
+
+In fact—our economy created over 6.5 Million new jobs just last year, more jobs created in one year  
+than ever before in the history of America. 
+
+Our economy grew at a rate of 5.7% last year, the strongest growth in nearly 40 years, the first step in bringing fundamental change to an economy that hasn’t worked for the working people of this nation for too long.  
+
+For the past 40 years we were told that if we gave tax breaks to those at the very top, the benefits would trickle down to everyone else. 
+
+But that trickle-down theory led to weaker economic growth, lower wages, bigger deficits, and the widest gap between those at the top and everyone else in nearly a century. 
+
+Vice President Harris and I ran for office with a new economic vision for America. 
+
+Invest in America. Educate Americans. Grow the workforce. Build the economy from the bottom up  
+and the middle out, not from the top down.  
+
+Because we know that when the middle class grows, the poor have a ladder up and the wealthy do very well. 
+
+America used to have the best roads, bridges, and airports on Earth. 
+
+Now our infrastructure is ranked 13th in the world. 
+
+We won’t be able to compete for the jobs of the 21st Century if we don’t fix that. 
+
+That’s why it was so important to pass the Bipartisan Infrastructure Law—the most sweeping investment to rebuild America in history. 
+
+This was a bipartisan effort, and I want to thank the members of both parties who worked to make it happen. 
+
+We’re done talking about infrastructure weeks. 
+
+We’re going to have an infrastructure decade. 
+
+It is going to transform America and put us on a path to win the economic competition of the 21st Century that we face with the rest of the world—particularly with China.  
+
+As I’ve told Xi Jinping, it is never a good bet to bet against the American people. 
+
+We’ll create good jobs for millions of Americans, modernizing roads, airports, ports, and waterways all across America. 
+
+And we’ll do it all to withstand the devastating effects of the climate crisis and promote environmental justice. 
+
+We’ll build a national network of 500,000 electric vehicle charging stations, begin to replace poisonous lead pipes—so every child—and every American—has clean water to drink at home and at school, provide affordable high-speed internet for every American—urban, suburban, rural, and tribal communities. 
+
+4,000 projects have already been announced. 
+
+And tonight, I’m announcing that this year we will start fixing over 65,000 miles of highway and 1,500 bridges in disrepair. 
+
+When we use taxpayer dollars to rebuild America – we are going to Buy American: buy American products to support American jobs. 
+
+The federal government spends about $600 Billion a year to keep the country safe and secure. 
+
+There’s been a law on the books for almost a century 
+to make sure taxpayers’ dollars support American jobs and businesses. 
+
+Every Administration says they’ll do it, but we are actually doing it. 
+
+We will buy American to make sure everything from the deck of an aircraft carrier to the steel on highway guardrails are made in America. 
+
+But to compete for the best jobs of the future, we also need to level the playing field with China and other competitors. 
+
+That’s why it is so important to pass the Bipartisan Innovation Act sitting in Congress that will make record investments in emerging technologies and American manufacturing. 
+
+Let me give you one example of why it’s so important to pass it. 
+
+If you travel 20 miles east of Columbus, Ohio, you’ll find 1,000 empty acres of land. 
+
+It won’t look like much, but if you stop and look closely, you’ll see a “Field of dreams,” the ground on which America’s future will be built. 
+
+This is where Intel, the American company that helped build Silicon Valley, is going to build its $20 billion semiconductor “mega site”. 
+
+Up to eight state-of-the-art factories in one place. 10,000 new good-paying jobs. 
+
+Some of the most sophisticated manufacturing in the world to make computer chips the size of a fingertip that power the world and our everyday lives. 
+
+Smartphones. The Internet. Technology we have yet to invent. 
+
+But that’s just the beginning. 
+
+Intel’s CEO, Pat Gelsinger, who is here tonight, told me they are ready to increase their investment from  
+$20 billion to $100 billion. 
+
+That would be one of the biggest investments in manufacturing in American history. 
+
+And all they’re waiting for is for you to pass this bill. 
+
+So let’s not wait any longer. Send it to my desk. I’ll sign it.  
+
+And we will really take off. 
+
+And Intel is not alone. 
+
+There’s something happening in America. 
+
+Just look around and you’ll see an amazing story. 
+
+The rebirth of the pride that comes from stamping products “Made In America.” The revitalization of American manufacturing.   
+
+Companies are choosing to build new factories here, when just a few years ago, they would have built them overseas. 
+
+That’s what is happening. Ford is investing $11 billion to build electric vehicles, creating 11,000 jobs across the country. 
+
+GM is making the largest investment in its history—$7 billion to build electric vehicles, creating 4,000 jobs in Michigan. 
+
+All told, we created 369,000 new manufacturing jobs in America just last year. 
+
+Powered by people I’ve met like JoJo Burgess, from generations of union steelworkers from Pittsburgh, who’s here with us tonight. 
+
+As Ohio Senator Sherrod Brown says, “It’s time to bury the label “Rust Belt.” 
+
+It’s time. 
+
+But with all the bright spots in our economy, record job growth and higher wages, too many families are struggling to keep up with the bills.  
+
+Inflation is robbing them of the gains they might otherwise feel. 
+
+I get it. That’s why my top priority is getting prices under control. 
+
+Look, our economy roared back faster than most predicted, but the pandemic meant that businesses had a hard time hiring enough workers to keep up production in their factories. 
+
+The pandemic also disrupted global supply chains. 
+
+When factories close, it takes longer to make goods and get them from the warehouse to the store, and prices go up. 
+
+Look at cars. 
+
+Last year, there weren’t enough semiconductors to make all the cars that people wanted to buy. 
+
+And guess what, prices of automobiles went up. 
+
+So—we have a choice. 
+
+One way to fight inflation is to drive down wages and make Americans poorer.  
+
+I have a better plan to fight inflation. 
+
+Lower your costs, not your wages. 
+
+Make more cars and semiconductors in America. 
+
+More infrastructure and innovation in America. 
+
+More goods moving faster and cheaper in America. 
+
+More jobs where you can earn a good living in America. 
+
+And instead of relying on foreign supply chains, let’s make it in America. 
+
+Economists call it “increasing the productive capacity of our economy.” 
+
+I call it building a better America. 
+
+My plan to fight inflation will lower your costs and lower the deficit. 
+
+17 Nobel laureates in economics say my plan will ease long-term inflationary pressures. Top business leaders and most Americans support my plan. And here’s the plan: 
+
+First – cut the cost of prescription drugs. Just look at insulin. One in ten Americans has diabetes. In Virginia, I met a 13-year-old boy named Joshua Davis.  
+
+He and his Dad both have Type 1 diabetes, which means they need insulin every day. Insulin costs about $10 a vial to make.  
+
+But drug companies charge families like Joshua and his Dad up to 30 times more. I spoke with Joshua’s mom. 
+
+Imagine what it’s like to look at your child who needs insulin and have no idea how you’re going to pay for it.  
+
+What it does to your dignity, your ability to look your child in the eye, to be the parent you expect to be. 
+
+Joshua is here with us tonight. Yesterday was his birthday. Happy birthday, buddy.  
+
+For Joshua, and for the 200,000 other young people with Type 1 diabetes, let’s cap the cost of insulin at $35 a month so everyone can afford it.  
+
+Drug companies will still do very well. And while we’re at it let Medicare negotiate lower prices for prescription drugs, like the VA already does. 
+
+Look, the American Rescue Plan is helping millions of families on Affordable Care Act plans save $2,400 a year on their health care premiums. Let’s close the coverage gap and make those savings permanent. 
+
+Second – cut energy costs for families an average of $500 a year by combatting climate change.  
+
+Let’s provide investments and tax credits to weatherize your homes and businesses to be energy efficient and you get a tax credit; double America’s clean energy production in solar, wind, and so much more;  lower the price of electric vehicles, saving you another $80 a month because you’ll never have to pay at the gas pump again. 
+
+Third – cut the cost of child care. Many families pay up to $14,000 a year for child care per child.  
+
+Middle-class and working families shouldn’t have to pay more than 7% of their income for care of young children.  
+
+My plan will cut the cost in half for most families and help parents, including millions of women, who left the workforce during the pandemic because they couldn’t afford child care, to be able to get back to work. 
+
+My plan doesn’t stop there. It also includes home and long-term care. More affordable housing. And Pre-K for every 3- and 4-year-old.  
+
+All of these will lower costs. 
+
+And under my plan, nobody earning less than $400,000 a year will pay an additional penny in new taxes. Nobody.  
+
+The one thing all Americans agree on is that the tax system is not fair. We have to fix it.  
+
+I’m not looking to punish anyone. But let’s make sure corporations and the wealthiest Americans start paying their fair share. 
+
+Just last year, 55 Fortune 500 corporations earned $40 billion in profits and paid zero dollars in federal income tax.  
+
+That’s simply not fair. That’s why I’ve proposed a 15% minimum tax rate for corporations. 
+
+We got more than 130 countries to agree on a global minimum tax rate so companies can’t get out of paying their taxes at home by shipping jobs and factories overseas. 
+
+That’s why I’ve proposed closing loopholes so the very wealthy don’t pay a lower tax rate than a teacher or a firefighter.  
+
+So that’s my plan. It will grow the economy and lower costs for families. 
+
+So what are we waiting for? Let’s get this done. And while you’re at it, confirm my nominees to the Federal Reserve, which plays a critical role in fighting inflation.  
+
+My plan will not only lower costs to give families a fair shot, it will lower the deficit. 
+
+The previous Administration not only ballooned the deficit with tax cuts for the very wealthy and corporations, it undermined the watchdogs whose job was to keep pandemic relief funds from being wasted. 
+
+But in my administration, the watchdogs have been welcomed back. 
+
+We’re going after the criminals who stole billions in relief money meant for small businesses and millions of Americans.  
+
+And tonight, I’m announcing that the Justice Department will name a chief prosecutor for pandemic fraud. 
+
+By the end of this year, the deficit will be down to less than half what it was before I took office.  
+
+The only president ever to cut the deficit by more than one trillion dollars in a single year. 
+
+Lowering your costs also means demanding more competition. 
+
+I’m a capitalist, but capitalism without competition isn’t capitalism. 
+
+It’s exploitation—and it drives up prices. 
+
+When corporations don’t have to compete, their profits go up, your prices go up, and small businesses and family farmers and ranchers go under. 
+
+We see it happening with ocean carriers moving goods in and out of America. 
+
+During the pandemic, these foreign-owned companies raised prices by as much as 1,000% and made record profits. 
+
+Tonight, I’m announcing a crackdown on these companies overcharging American businesses and consumers. 
+
+And as Wall Street firms take over more nursing homes, quality in those homes has gone down and costs have gone up.  
+
+That ends on my watch. 
+
+Medicare is going to set higher standards for nursing homes and make sure your loved ones get the care they deserve and expect. 
+
+We’ll also cut costs and keep the economy going strong by giving workers a fair shot, provide more training and apprenticeships, hire them based on their skills not degrees. 
+
+Let’s pass the Paycheck Fairness Act and paid leave.  
+
+Raise the minimum wage to $15 an hour and extend the Child Tax Credit, so no one has to raise a family in poverty. 
+
+Let’s increase Pell Grants and increase our historic support of HBCUs, and invest in what Jill—our First Lady who teaches full-time—calls America’s best-kept secret: community colleges. 
+
+And let’s pass the PRO Act when a majority of workers want to form a union—they shouldn’t be stopped.  
+
+When we invest in our workers, when we build the economy from the bottom up and the middle out together, we can do something we haven’t done in a long time: build a better America. 
+
+For more than two years, COVID-19 has impacted every decision in our lives and the life of the nation. 
+
+And I know you’re tired, frustrated, and exhausted. 
+
+But I also know this. 
+
+Because of the progress we’ve made, because of your resilience and the tools we have, tonight I can say  
+we are moving forward safely, back to more normal routines.  
+
+We’ve reached a new moment in the fight against COVID-19, with severe cases down to a level not seen since last July.  
+
+Just a few days ago, the Centers for Disease Control and Prevention—the CDC—issued new mask guidelines. 
+
+Under these new guidelines, most Americans in most of the country can now be mask free.   
+
+And based on the projections, more of the country will reach that point across the next couple of weeks. 
+
+Thanks to the progress we have made this past year, COVID-19 need no longer control our lives.  
+
+I know some are talking about “living with COVID-19”. Tonight – I say that we will never just accept living with COVID-19. 
+
+We will continue to combat the virus as we do other diseases. And because this is a virus that mutates and spreads, we will stay on guard. 
+
+Here are four common sense steps as we move forward safely.  
+
+First, stay protected with vaccines and treatments. We know how incredibly effective vaccines are. If you’re vaccinated and boosted you have the highest degree of protection. 
+
+We will never give up on vaccinating more Americans. Now, I know parents with kids under 5 are eager to see a vaccine authorized for their children. 
+
+The scientists are working hard to get that done and we’ll be ready with plenty of vaccines when they do. 
+
+We’re also ready with anti-viral treatments. If you get COVID-19, the Pfizer pill reduces your chances of ending up in the hospital by 90%.  
+
+We’ve ordered more of these pills than anyone in the world. And Pfizer is working overtime to get us 1 Million pills this month and more than double that next month.  
+
+And we’re launching the “Test to Treat” initiative so people can get tested at a pharmacy, and if they’re positive, receive antiviral pills on the spot at no cost.  
+
+If you’re immunocompromised or have some other vulnerability, we have treatments and free high-quality masks. 
+
+We’re leaving no one behind or ignoring anyone’s needs as we move forward. 
+
+And on testing, we have made hundreds of millions of tests available for you to order for free.   
+
+Even if you already ordered free tests tonight, I am announcing that you can order more from covidtests.gov starting next week. 
+
+Second – we must prepare for new variants. Over the past year, we’ve gotten much better at detecting new variants. 
+
+If necessary, we’ll be able to deploy new vaccines within 100 days instead of many more months or years.  
+
+And, if Congress provides the funds we need, we’ll have new stockpiles of tests, masks, and pills ready if needed. 
+
+I cannot promise a new variant won’t come. But I can promise you we’ll do everything within our power to be ready if it does.  
+
+Third – we can end the shutdown of schools and businesses. We have the tools we need. 
+
+It’s time for Americans to get back to work and fill our great downtowns again.  People working from home can feel safe to begin to return to the office.   
+
+We’re doing that here in the federal government. The vast majority of federal workers will once again work in person. 
+
+Our schools are open. Let’s keep it that way. Our kids need to be in school. 
+
+And with 75% of adult Americans fully vaccinated and hospitalizations down by 77%, most Americans can remove their masks, return to work, stay in the classroom, and move forward safely. 
+
+We achieved this because we provided free vaccines, treatments, tests, and masks. 
+
+Of course, continuing this costs money. 
+
+I will soon send Congress a request. 
+
+The vast majority of Americans have used these tools and may want to again, so I expect Congress to pass it quickly.   
+
+Fourth, we will continue vaccinating the world.     
+
+We’ve sent 475 Million vaccine doses to 112 countries, more than any other nation. 
+
+And we won’t stop. 
+
+We have lost so much to COVID-19. Time with one another. And worst of all, so much loss of life. 
+
+Let’s use this moment to reset. Let’s stop looking at COVID-19 as a partisan dividing line and see it for what it is: A God-awful disease.  
+
+Let’s stop seeing each other as enemies, and start seeing each other for who we really are: Fellow Americans.  
+
+We can’t change how divided we’ve been. But we can change how we move forward—on COVID-19 and other issues we must face together. 
+
+I recently visited the New York City Police Department days after the funerals of Officer Wilbert Mora and his partner, Officer Jason Rivera. 
+
+They were responding to a 9-1-1 call when a man shot and killed them with a stolen gun. 
+
+Officer Mora was 27 years old. 
+
+Officer Rivera was 22. 
+
+Both Dominican Americans who’d grown up on the same streets they later chose to patrol as police officers. 
+
+I spoke with their families and told them that we are forever in debt for their sacrifice, and we will carry on their mission to restore the trust and safety every community deserves. 
+
+I’ve worked on these issues a long time. 
+
+I know what works: Investing in crime prevention and community police officers who’ll walk the beat, who’ll know the neighborhood, and who can restore trust and safety. 
+
+So let’s not abandon our streets. Or choose between safety and equal justice. 
+
+Let’s come together to protect our communities, restore trust, and hold law enforcement accountable. 
+
+That’s why the Justice Department required body cameras, banned chokeholds, and restricted no-knock warrants for its officers. 
+
+That’s why the American Rescue Plan provided $350 Billion that cities, states, and counties can use to hire more police and invest in proven strategies like community violence interruption—trusted messengers breaking the cycle of violence and trauma and giving young people hope.  
+
+We should all agree: The answer is not to Defund the police. The answer is to FUND the police with the resources and training they need to protect our communities. 
+
+I ask Democrats and Republicans alike: Pass my budget and keep our neighborhoods safe.  
+
+And I will keep doing everything in my power to crack down on gun trafficking and ghost guns you can buy online and make at home—they have no serial numbers and can’t be traced. 
+
+And I ask Congress to pass proven measures to reduce gun violence. Pass universal background checks. Why should anyone on a terrorist list be able to purchase a weapon? 
+
+Ban assault weapons and high-capacity magazines. 
+
+Repeal the liability shield that makes gun manufacturers the only industry in America that can’t be sued. 
+
+These laws don’t infringe on the Second Amendment. They save lives. 
+
+The most fundamental right in America is the right to vote – and to have it counted. And it’s under assault. 
+
+In state after state, new laws have been passed, not only to suppress the vote, but to subvert entire elections. 
+
+We cannot let this happen. 
+
+Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. 
+
+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. 
+
+One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. 
+
+And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence. 
+
+A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. 
+
+And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. 
+
+We can do both. At our border, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling.  
+
+We’ve set up joint patrols with Mexico and Guatemala to catch more human traffickers.  
+
+We’re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. 
+
+We’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders. 
+
+We can do all this while keeping lit the torch of liberty that has led generations of immigrants to this land—my forefathers and so many of yours. 
+
+Provide a pathway to citizenship for Dreamers, those on temporary status, farm workers, and essential workers. 
+
+Revise our laws so businesses have the workers they need and families don’t wait decades to reunite. 
+
+It’s not only the right thing to do—it’s the economically smart thing to do. 
+
+That’s why immigration reform is supported by everyone from labor unions to religious leaders to the U.S. Chamber of Commerce. 
+
+Let’s get it done once and for all. 
+
+Advancing liberty and justice also requires protecting the rights of women. 
+
+The constitutional right affirmed in Roe v. Wade—standing precedent for half a century—is under attack as never before. 
+
+If we want to go forward—not backward—we must protect access to health care. Preserve a woman’s right to choose. And let’s continue to advance maternal health care in America. 
+
+And for our LGBTQ+ Americans, let’s finally get the bipartisan Equality Act to my desk. The onslaught of state laws targeting transgender Americans and their families is wrong. 
+
+As I said last year, especially to our younger transgender Americans, I will always have your back as your President, so you can be yourself and reach your God-given potential. 
+
+While it often appears that we never agree, that isn’t true. I signed 80 bipartisan bills into law last year. From preventing government shutdowns to protecting Asian-Americans from still-too-common hate crimes to reforming military justice. 
+
+And soon, we’ll strengthen the Violence Against Women Act that I first wrote three decades ago. It is important for us to show the nation that we can come together and do big things. 
+
+So tonight I’m offering a Unity Agenda for the Nation. Four big things we can do together.  
+
+First, beat the opioid epidemic. 
+
+There is so much we can do. Increase funding for prevention, treatment, harm reduction, and recovery.  
+
+Get rid of outdated rules that stop doctors from prescribing treatments. And stop the flow of illicit drugs by working with state and local law enforcement to go after traffickers. 
+
+If you’re suffering from addiction, know you are not alone. I believe in recovery, and I celebrate the 23 million Americans in recovery. 
+
+Second, let’s take on mental health. Especially among our children, whose lives and education have been turned upside down.  
+
+The American Rescue Plan gave schools money to hire teachers and help students make up for lost learning.  
+
+I urge every parent to make sure your school does just that. And we can all play a part—sign up to be a tutor or a mentor. 
+
+Children were also struggling before the pandemic. Bullying, violence, trauma, and the harms of social media. 
+
+As Frances Haugen, who is here with us tonight, has shown, we must hold social media platforms accountable for the national experiment they’re conducting on our children for profit. 
+
+It’s time to strengthen privacy protections, ban targeted advertising to children, demand tech companies stop collecting personal data on our children. 
+
+And let’s get all Americans the mental health services they need. More people they can turn to for help, and full parity between physical and mental health care. 
+
+Third, support our veterans. 
+
+Veterans are the best of us. 
+
+I’ve always believed that we have a sacred obligation to equip all those we send to war and care for them and their families when they come home. 
+
+My administration is providing assistance with job training and housing, and now helping lower-income veterans get VA care debt-free.  
+
+Our troops in Iraq and Afghanistan faced many dangers. 
+
+One was stationed at bases and breathing in toxic smoke from “burn pits” that incinerated wastes of war—medical and hazard material, jet fuel, and more. 
+
+When they came home, many of the world’s fittest and best trained warriors were never the same. 
+
+Headaches. Numbness. Dizziness. 
+
+A cancer that would put them in a flag-draped coffin. 
+
+I know. 
+
+One of those soldiers was my son Major Beau Biden. 
+
+We don’t know for sure if a burn pit was the cause of his brain cancer, or the diseases of so many of our troops. 
+
+But I’m committed to finding out everything we can. 
+
+Committed to military families like Danielle Robinson from Ohio. 
+
+The widow of Sergeant First Class Heath Robinson.  
+
+He was born a soldier. Army National Guard. Combat medic in Kosovo and Iraq. 
+
+Stationed near Baghdad, just yards from burn pits the size of football fields. 
+
+Heath’s widow Danielle is here with us tonight. They loved going to Ohio State football games. He loved building Legos with their daughter. 
+
+But cancer from prolonged exposure to burn pits ravaged Heath’s lungs and body. 
+
+Danielle says Heath was a fighter to the very end. 
+
+He didn’t know how to stop fighting, and neither did she. 
+
+Through her pain she found purpose to demand we do better. 
+
+Tonight, Danielle—we are. 
+
+The VA is pioneering new ways of linking toxic exposures to diseases, already helping more veterans get benefits. 
+
+And tonight, I’m announcing we’re expanding eligibility to veterans suffering from nine respiratory cancers. 
+
+I’m also calling on Congress: pass a law to make sure veterans devastated by toxic exposures in Iraq and Afghanistan finally get the benefits and comprehensive health care they deserve. 
+
+And fourth, let’s end cancer as we know it. 
+
+This is personal to me and Jill, to Kamala, and to so many of you. 
+
+Cancer is the #2 cause of death in America–second only to heart disease. 
+
+Last month, I announced our plan to supercharge  
+the Cancer Moonshot that President Obama asked me to lead six years ago. 
+
+Our goal is to cut the cancer death rate by at least 50% over the next 25 years, turn more cancers from death sentences into treatable diseases.  
+
+More support for patients and families. 
+
+To get there, I call on Congress to fund ARPA-H, the Advanced Research Projects Agency for Health. 
+
+It’s based on DARPA—the Defense Department project that led to the Internet, GPS, and so much more.  
+
+ARPA-H will have a singular purpose—to drive breakthroughs in cancer, Alzheimer’s, diabetes, and more. 
+
+A unity agenda for the nation. 
+
+We can do this. 
+
+My fellow Americans—tonight , we have gathered in a sacred space—the citadel of our democracy. 
+
+In this Capitol, generation after generation, Americans have debated great questions amid great strife, and have done great things. 
+
+We have fought for freedom, expanded liberty, defeated totalitarianism and terror. 
+
+And built the strongest, freest, and most prosperous nation the world has ever known. 
+
+Now is the hour. 
+
+Our moment of responsibility. 
+
+Our test of resolve and conscience, of history itself. 
+
+It is in this moment that our character is formed. Our purpose is found. Our future is forged. 
+
+Well I know this nation.  
+
+We will meet the test. 
+
+To protect freedom and liberty, to expand fairness and opportunity. 
+
+We will save democracy. 
+
+As hard as these times have been, I am more optimistic about America today than I have been my whole life. 
+
+Because I see the future that is within our grasp. 
+
+Because I know there is simply nothing beyond our capacity. 
+
+We are the only nation on Earth that has always turned every crisis we have faced into an opportunity. 
+
+The only nation that can be defined by a single word: possibilities. 
+
+So on this night, in our 245th year as a nation, I have come to report on the State of the Union. 
+
+And my report is this: the State of the Union is strong—because you, the American people, are strong. 
+
+We are stronger today than we were a year ago. 
+
+And we will be stronger a year from now than we are today. 
+
+Now is our moment to meet and overcome the challenges of our time. 
+
+And we will, as one people. 
+
+One America. 
+
+The United States of America. 
+
+May God bless you all. May God protect our troops.

docs/docs/integrations/document_loaders/image.ipynb

@@ -7,7 +7,9 @@
    "source": [
     "# Images\n",
     "\n",
-    "This covers how to load images such as `JPG` or `PNG` into a document format that we can use downstream."
+    "This covers how to load images into a document format that we can use downstream with other LangChain modules.\n",
+    "\n",
+    "It uses [Unstructured](https://unstructured.io/) to handle a wide variety of image formats, such as `.jpg` and `.png`. Please see [this guide](/docs/integrations/providers/unstructured/) for more instructions on setting up Unstructured locally, including setting up required system dependencies."
    ]
   },
   {
@@ -27,63 +29,35 @@
    },
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet  pdfminer"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "0cc0cd42",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain_community.document_loaders.image import UnstructuredImageLoader"
+    "%pip install --upgrade --quiet \"unstructured[all-docs]\""
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 2,
-   "id": "082d557c",
+   "id": "0cc0cd42",
    "metadata": {
     "tags": []
    },
-   "outputs": [],
-   "source": [
-    "loader = UnstructuredImageLoader(\"layout-parser-paper-fast.jpg\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "df11c953",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "data = loader.load()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "4284d44c",
-   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "Document(page_content=\"LayoutParser: A Unified Toolkit for Deep\\nLearning Based Document Image Analysis\\n\\n\\n‘Zxjiang Shen' (F3}, Ruochen Zhang”, Melissa Dell*, Benjamin Charles Germain\\nLeet, Jacob Carlson, and Weining LiF\\n\\n\\nsugehen\\n\\nshangthrows, et\\n\\n“Abstract. Recent advanocs in document image analysis (DIA) have been\\n‘pimarliy driven bythe application of neural networks dell roar\\n{uteomer could be aly deployed in production and extended fo farther\\n[nvetigtion. However, various factory ke lcely organize codebanee\\nsnd sophisticated modal cnigurations compat the ey ree of\\n‘erin! innovation by wide sence, Though there have been sng\\n‘Hors to improve reuablty and simplify deep lees (DL) mode\\n‘aon, sone of them ae optimized for challenge inthe demain of DIA,\\nThis roprscte a major gap in the extng fol, sw DIA i eal to\\nscademic research acon wie range of dpi in the social ssencee\\n[rary for streamlining the sage of DL in DIA research and appicn\\n‘tons The core LayoutFaraer brary comes with a sch of simple and\\nIntative interfaee or applying and eutomiing DI. odel fr Inyo de\\npltfom for sharing both protrined modes an fal document dist\\n{ation pipeline We demonutate that LayootPareer shea fr both\\nlightweight and lrgeseledgtieation pipelines in eal-word uae ces\\nThe leary pblely smal at Btspe://layost-pareergsthab So\\n\\n\\n\\n‘Keywords: Document Image Analysis» Deep Learning Layout Analysis\\n‘Character Renguition - Open Serres dary « Tol\\n\\n\\nIntroduction\\n\\n\\n‘Deep Learning(DL)-based approaches are the state-of-the-art for a wide range of\\ndoctiment image analysis (DIA) tea including document image clasiffeation [I]\\n\", lookup_str='', metadata={'source': 'layout-parser-paper-fast.jpg'}, lookup_index=0)"
+       "Document(page_content='2021\\n\\n2103.15348v2 [cs.CV] 21 Jun\\n\\narXiv\\n\\nLayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis\\n\\nZejiang Shen! (&4), Ruochen Zhang?, Melissa Dell?, Benjamin Charles Germain Lee*, Jacob Carlson?, and Weining Li?\\n\\n1\\n\\nAllen Institute for AI shannons@allenai.org ? Brown University ruochen_zhang@brown. edu 3 Harvard University {melissadell, jacob_carlson}@fas.harvard.edu 4 University of Washington begl@cs.washington.edu 5 University of Waterloo w4221i@uwaterloo.ca\\n\\nAbstract. Recent advances in document image analysis (DIA) have been primarily driven by the application of neural networks. Ideally, research outcomes could be easily deployed in production and extended for further investigation. However, various factors like loosely organized codebases and sophisticated model configurations complicate the easy reuse of im- portant innovations by a wide audience. Though there have been on-going efforts to improve reusability and simplify deep learning (DL) model development in disciplines like natural language processing and computer vision, none of them are optimized for challenges in the domain of DIA. This represents a major gap in the existing toolkit, as DIA is central to academic research across a wide range of disciplines in the social sciences and humanities. This paper introduces LayoutParser, an open-source library for streamlining the usage of DL in DIA research and applica- tions. The core LayoutParser library comes with a set of simple and intuitive interfaces for applying and customizing DL models for layout de- tection, character recognition, and many other document processing tasks. To promote extensibility, LayoutParser also incorporates a community platform for sharing both pre-trained models and full document digiti- zation pipelines. We demonstrate that LayoutParser is helpful for both lightweight and large-scale digitization pipelines in real-word use cases. The library is publicly available at https: //layout-parser.github. io.\\n\\nKeywords: Document Image Analysis - Deep Learning - Layout Analysis - Character Recognition - Open Source library - Toolkit.\\n\\n1 Introduction\\n\\nDeep Learning(DL)-based approaches are the state-of-the-art for a wide range of document image analysis (DIA) tasks including document image classification [11,', metadata={'source': './example_data/layout-parser-paper-screenshot.png'})"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
+    "from langchain_community.document_loaders.image import UnstructuredImageLoader\n",
+    "\n",
+    "loader = UnstructuredImageLoader(\"./example_data/layout-parser-paper-screenshot.png\")\n",
+    "\n",
+    "data = loader.load()\n",
+    "\n",
     "data[0]"
    ]
   },
@@ -94,47 +68,33 @@
    "source": [
     "### Retain Elements\n",
     "\n",
-    "Under the hood, Unstructured creates different \"elements\" for different chunks of text. By default we combine those together, but you can easily keep that separation by specifying `mode=\"elements\"`."
+    "Under the hood, Unstructured creates different \"elements\" for different chunks of text. By default we combine those together, but you can keep that separation by specifying `mode=\"elements\"`."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 3,
    "id": "0fab833b",
    "metadata": {},
-   "outputs": [],
-   "source": [
-    "loader = UnstructuredImageLoader(\"layout-parser-paper-fast.jpg\", mode=\"elements\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "c3e8ff1b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "data = loader.load()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "43c23d2d",
-   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "Document(page_content='LayoutParser: A Unified Toolkit for Deep\\nLearning Based Document Image Analysis\\n', lookup_str='', metadata={'source': 'layout-parser-paper-fast.jpg', 'filename': 'layout-parser-paper-fast.jpg', 'page_number': 1, 'category': 'Title'}, lookup_index=0)"
+       "Document(page_content='2021', metadata={'source': './example_data/layout-parser-paper-screenshot.png', 'coordinates': {'points': ((47.0, 492.0), (47.0, 591.0), (83.0, 591.0), (83.0, 492.0)), 'system': 'PixelSpace', 'layout_width': 1624, 'layout_height': 1920}, 'last_modified': '2024-07-01T10:38:29', 'filetype': 'PNG', 'languages': ['eng'], 'page_number': 1, 'file_directory': './example_data', 'filename': 'layout-parser-paper-screenshot.png', 'category': 'UncategorizedText'})"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
+    "loader = UnstructuredImageLoader(\n",
+    "    \"./example_data/layout-parser-paper-screenshot.png\", mode=\"elements\"\n",
+    ")\n",
+    "\n",
+    "data = loader.load()\n",
+    "\n",
     "data[0]"
    ]
   }
@@ -155,7 +115,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.6"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/integrations/document_loaders/image_captions.ipynb

@@ -83,7 +83,7 @@
    },
    "outputs": [],
    "source": [
-    "loader = ImageCaptionLoader(path_images=list_image_urls)\n",
+    "loader = ImageCaptionLoader(images=list_image_urls)\n",
     "list_docs = loader.load()\n",
     "list_docs"
    ]

docs/docs/integrations/document_loaders/microsoft_excel.ipynb

@@ -7,17 +7,19 @@
    "source": [
     "# Microsoft Excel\n",
     "\n",
-    "The `UnstructuredExcelLoader` is used to load `Microsoft Excel` files. The loader works with both `.xlsx` and `.xls` files. The page content will be the raw text of the Excel file. If you use the loader in `\"elements\"` mode, an HTML representation of the Excel file will be available in the document metadata under the `text_as_html` key."
+    "The `UnstructuredExcelLoader` is used to load `Microsoft Excel` files. The loader works with both `.xlsx` and `.xls` files. The page content will be the raw text of the Excel file. If you use the loader in `\"elements\"` mode, an HTML representation of the Excel file will be available in the document metadata under the `text_as_html` key.\n",
+    "\n",
+    "Please see [this guide](/docs/integrations/providers/unstructured/) for more instructions on setting up Unstructured locally, including setting up required system dependencies."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
-   "id": "e6616e3a",
+   "execution_count": null,
+   "id": "0b01ee46",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.document_loaders import UnstructuredExcelLoader"
+    "%pip install --upgrade --quiet langchain-community unstructured openpyxl"
    ]
   },
   {
@@ -26,10 +28,20 @@
    "id": "a654e4d9",
    "metadata": {},
    "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "4\n"
+     ]
+    },
     {
      "data": {
       "text/plain": [
-       "Document(page_content='\\n  \\n    \\n      Team\\n      Location\\n      Stanley Cups\\n    \\n    \\n      Blues\\n      STL\\n      1\\n    \\n    \\n      Flyers\\n      PHI\\n      2\\n    \\n    \\n      Maple Leafs\\n      TOR\\n      13\\n    \\n  \\n', metadata={'source': 'example_data/stanley-cups.xlsx', 'filename': 'stanley-cups.xlsx', 'file_directory': 'example_data', 'filetype': 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet', 'page_number': 1, 'page_name': 'Stanley Cups', 'text_as_html': '<table border=\"1\" class=\"dataframe\">\\n  <tbody>\\n    <tr>\\n      <td>Team</td>\\n      <td>Location</td>\\n      <td>Stanley Cups</td>\\n    </tr>\\n    <tr>\\n      <td>Blues</td>\\n      <td>STL</td>\\n      <td>1</td>\\n    </tr>\\n    <tr>\\n      <td>Flyers</td>\\n      <td>PHI</td>\\n      <td>2</td>\\n    </tr>\\n    <tr>\\n      <td>Maple Leafs</td>\\n      <td>TOR</td>\\n      <td>13</td>\\n    </tr>\\n  </tbody>\\n</table>', 'category': 'Table'})"
+       "[Document(page_content='Stanley Cups', metadata={'source': './example_data/stanley-cups.xlsx', 'file_directory': './example_data', 'filename': 'stanley-cups.xlsx', 'last_modified': '2023-12-19T13:42:18', 'page_name': 'Stanley Cups', 'page_number': 1, 'languages': ['eng'], 'filetype': 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet', 'category': 'Title'}),\n",
+       " Document(page_content='\\n\\n\\nTeam\\nLocation\\nStanley Cups\\n\\n\\nBlues\\nSTL\\n1\\n\\n\\nFlyers\\nPHI\\n2\\n\\n\\nMaple Leafs\\nTOR\\n13\\n\\n\\n', metadata={'source': './example_data/stanley-cups.xlsx', 'file_directory': './example_data', 'filename': 'stanley-cups.xlsx', 'last_modified': '2023-12-19T13:42:18', 'page_name': 'Stanley Cups', 'page_number': 1, 'text_as_html': '<table border=\"1\" class=\"dataframe\">\\n  <tbody>\\n    <tr>\\n      <td>Team</td>\\n      <td>Location</td>\\n      <td>Stanley Cups</td>\\n    </tr>\\n    <tr>\\n      <td>Blues</td>\\n      <td>STL</td>\\n      <td>1</td>\\n    </tr>\\n    <tr>\\n      <td>Flyers</td>\\n      <td>PHI</td>\\n      <td>2</td>\\n    </tr>\\n    <tr>\\n      <td>Maple Leafs</td>\\n      <td>TOR</td>\\n      <td>13</td>\\n    </tr>\\n  </tbody>\\n</table>', 'languages': ['eng'], 'parent_id': '17e9a90f9616f2abed8cf32b5bd3810d', 'filetype': 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet', 'category': 'Table'}),\n",
+       " Document(page_content='Stanley Cups Since 67', metadata={'source': './example_data/stanley-cups.xlsx', 'file_directory': './example_data', 'filename': 'stanley-cups.xlsx', 'last_modified': '2023-12-19T13:42:18', 'page_name': 'Stanley Cups Since 67', 'page_number': 2, 'languages': ['eng'], 'filetype': 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet', 'category': 'Title'}),\n",
+       " Document(page_content='\\n\\n\\nTeam\\nLocation\\nStanley Cups\\n\\n\\nBlues\\nSTL\\n1\\n\\n\\nFlyers\\nPHI\\n2\\n\\n\\nMaple Leafs\\nTOR\\n0\\n\\n\\n', metadata={'source': './example_data/stanley-cups.xlsx', 'file_directory': './example_data', 'filename': 'stanley-cups.xlsx', 'last_modified': '2023-12-19T13:42:18', 'page_name': 'Stanley Cups Since 67', 'page_number': 2, 'text_as_html': '<table border=\"1\" class=\"dataframe\">\\n  <tbody>\\n    <tr>\\n      <td>Team</td>\\n      <td>Location</td>\\n      <td>Stanley Cups</td>\\n    </tr>\\n    <tr>\\n      <td>Blues</td>\\n      <td>STL</td>\\n      <td>1</td>\\n    </tr>\\n    <tr>\\n      <td>Flyers</td>\\n      <td>PHI</td>\\n      <td>2</td>\\n    </tr>\\n    <tr>\\n      <td>Maple Leafs</td>\\n      <td>TOR</td>\\n      <td>0</td>\\n    </tr>\\n  </tbody>\\n</table>', 'languages': ['eng'], 'parent_id': 'ee34bd8c186b57e3530d5443ffa58122', 'filetype': 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet', 'category': 'Table'})]"
       ]
      },
      "execution_count": 2,
@@ -38,9 +50,14 @@
     }
    ],
    "source": [
-    "loader = UnstructuredExcelLoader(\"example_data/stanley-cups.xlsx\", mode=\"elements\")\n",
+    "from langchain_community.document_loaders import UnstructuredExcelLoader\n",
+    "\n",
+    "loader = UnstructuredExcelLoader(\"./example_data/stanley-cups.xlsx\", mode=\"elements\")\n",
     "docs = loader.load()\n",
-    "docs[0]"
+    "\n",
+    "print(len(docs))\n",
+    "\n",
+    "docs"
    ]
   },
   {
@@ -76,7 +93,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet  langchain langchain-community azure-ai-documentintelligence"
+    "%pip install --upgrade --quiet langchain langchain-community azure-ai-documentintelligence"
    ]
   },
   {
@@ -115,7 +132,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.13"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,