implement in core

These are covered by standard tests.

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -29,14 +29,14 @@ body:
       options:
         - label: I added a very descriptive title to this issue.
           required: true
-        - label: I searched the LangChain documentation with the integrated search.
-          required: true
         - label: I used the GitHub search to find a similar question and didn't find it.
           required: true
         - label: I am sure that this is a bug in LangChain rather than my code.
           required: true
         - label: The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).
           required: true
+        - label: I posted a self-contained, minimal, reproducible example. A maintainer can copy it and run it AS IS.
+          required: true
   - type: textarea
     id: reproduction
     validations:

.github/workflows/_integration_test.yml

@@ -76,6 +76,7 @@ jobs:
           COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
           UPSTAGE_API_KEY: ${{ secrets.UPSTAGE_API_KEY }}
           XAI_API_KEY: ${{ secrets.XAI_API_KEY }}
+          PPLX_API_KEY: ${{ secrets.PPLX_API_KEY }}
         run: |
           make integration_tests
 

.github/workflows/_release.yml

@@ -327,6 +327,7 @@ jobs:
           FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
           XAI_API_KEY: ${{ secrets.XAI_API_KEY }}
           DEEPSEEK_API_KEY: ${{ secrets.DEEPSEEK_API_KEY }}
+          PPLX_API_KEY: ${{ secrets.PPLX_API_KEY }}
         run: make integration_tests
         working-directory: ${{ inputs.working-directory }}
 
@@ -394,8 +395,11 @@ jobs:
 
           # Checkout the latest package files
           rm -rf $GITHUB_WORKSPACE/libs/partners/${{ matrix.partner }}/*
-          cd $GITHUB_WORKSPACE/libs/partners/${{ matrix.partner }}
-          git checkout "$LATEST_PACKAGE_TAG" -- .
+          rm -rf $GITHUB_WORKSPACE/libs/standard-tests/*
+          cd $GITHUB_WORKSPACE/libs/
+          git checkout "$LATEST_PACKAGE_TAG" -- standard-tests/
+          git checkout "$LATEST_PACKAGE_TAG" -- partners/${{ matrix.partner }}/
+          cd partners/${{ matrix.partner }}
 
           # Print as a sanity check
           echo "Version number from pyproject.toml: "

.github/workflows/check_core_versions.yml

@@ -0,0 +1,29 @@
+name: Check `langchain-core` version equality
+
+on:
+  pull_request:
+    paths:
+      - 'libs/core/pyproject.toml'
+      - 'libs/core/langchain_core/version.py'
+
+jobs:
+  check_version_equality:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Check version equality
+        run: |
+          PYPROJECT_VERSION=$(grep -Po '(?<=^version = ")[^"]*' libs/core/pyproject.toml)
+          VERSION_PY_VERSION=$(grep -Po '(?<=^VERSION = ")[^"]*' libs/core/langchain_core/version.py)
+
+          # Compare the two versions
+          if [ "$PYPROJECT_VERSION" != "$VERSION_PY_VERSION" ]; then
+            echo "langchain-core versions in pyproject.toml and version.py do not match!"
+            echo "pyproject.toml version: $PYPROJECT_VERSION"
+            echo "version.py version: $VERSION_PY_VERSION"
+            exit 1
+          else
+            echo "Versions match: $PYPROJECT_VERSION"
+          fi

.github/workflows/codspeed.yml

@@ -0,0 +1,44 @@
+name: CodSpeed
+
+on:
+  push:
+    branches:
+        - master
+  pull_request:
+    paths:
+      - 'libs/core/**'
+  # `workflow_dispatch` allows CodSpeed to trigger backtest
+  # performance analysis in order to generate initial data.
+  workflow_dispatch:
+
+jobs:
+  codspeed:
+    name: Run benchmarks
+    if: (github.event_name == 'pull_request' && contains(github.event.pull_request.labels.*.name, 'run-codspeed-benchmarks')) || github.event_name == 'workflow_dispatch' || github.event_name == 'push'
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      # We have to use 3.12, 3.13 is not yet supported
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+        with:
+          python-version: "3.12"
+
+      # Using this action is still necessary for CodSpeed to work
+      - uses: actions/setup-python@v3
+        with:
+          python-version: "3.12"
+
+      - name: install deps
+        run: uv sync --group test
+        working-directory: ./libs/core
+
+      - name: Run benchmarks
+        uses: CodSpeedHQ/action@v3
+        with:
+          token: ${{ secrets.CODSPEED_TOKEN }}
+          run: |
+            cd libs/core
+            uv run --no-sync pytest ./tests/benchmarks --codspeed
+          mode: walltime

.github/workflows/people.yml

@@ -6,11 +6,6 @@ on:
   push:
     branches: [jacob/people]
   workflow_dispatch:
-    inputs:
-      debug_enabled:
-        description: 'Run the build with tmate debugging enabled (https://github.com/marketplace/actions/debugging-with-tmate)'
-        required: false
-        default: 'false'
 
 jobs:
   langchain-people:
@@ -26,12 +21,6 @@ jobs:
       # Ref: https://github.com/actions/runner/issues/2033
       - name: Fix git safe.directory in container
         run: mkdir -p /home/runner/work/_temp/_github_home && printf "[safe]\n\tdirectory = /github/workspace" > /home/runner/work/_temp/_github_home/.gitconfig
-      # Allow debugging with tmate
-      - name: Setup tmate session
-        uses: mxschmitt/action-tmate@v3
-        if: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.debug_enabled == 'true' }}
-        with:
-          limit-access-to-actor: true
       - uses: ./.github/actions/people
         with:
           token: ${{ secrets.LANGCHAIN_PEOPLE_GITHUB_TOKEN }}

.github/workflows/run_notebooks.yml

@@ -61,6 +61,7 @@ jobs:
         env:
           ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
           FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
+          GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
           GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
           MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}

.github/workflows/scheduled_test.yml

@@ -145,6 +145,7 @@ jobs:
           GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
           GOOGLE_SEARCH_API_KEY: ${{ secrets.GOOGLE_SEARCH_API_KEY }}
           GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
+          PPLX_API_KEY: ${{ secrets.PPLX_API_KEY }}
         run: |
           cd langchain/${{ matrix.working-directory }}
           make integration_tests

.gitignore

@@ -59,6 +59,7 @@ coverage.xml
 *.py,cover
 .hypothesis/
 .pytest_cache/
+.codspeed/
 
 # Translations
 *.mo

README.md

@@ -15,8 +15,9 @@
 [![GitHub star chart](https://img.shields.io/github/stars/langchain-ai/langchain?style=flat-square)](https://star-history.com/#langchain-ai/langchain)
 [![Open Issues](https://img.shields.io/github/issues-raw/langchain-ai/langchain?style=flat-square)](https://github.com/langchain-ai/langchain/issues)
 [![Open in Dev Containers](https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode&style=flat-square)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langchain-ai/langchain)
-[![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/langchain-ai/langchain)
+[<img src="https://github.com/codespaces/badge.svg" title="Open in Github Codespace" width="150" height="20">](https://codespaces.new/langchain-ai/langchain)
 [![Twitter](https://img.shields.io/twitter/url/https/twitter.com/langchainai.svg?style=social&label=Follow%20%40LangChainAI)](https://twitter.com/langchainai)
+[![CodSpeed Badge](https://img.shields.io/endpoint?url=https://codspeed.io/badge.json)](https://codspeed.io/langchain-ai/langchain)
 
 > [!NOTE]
 > Looking for the JS/TS library? Check out [LangChain.js](https://github.com/langchain-ai/langchainjs).

cookbook/advanced_rag_eval.ipynb

@@ -30,7 +30,7 @@
    "outputs": [],
    "source": [
     "# lock to 0.10.19 due to a persistent bug in more recent versions\n",
-    "! pip install \"unstructured[all-docs]==0.10.19\" pillow pydantic lxml pillow matplotlib tiktoken open_clip_torch torch"
+    "! pip install \"unstructured[all-docs]==0.10.19\" pillow pydantic lxml matplotlib tiktoken open_clip_torch torch"
    ]
   },
   {
@@ -409,7 +409,7 @@
     "    table_summaries,\n",
     "    tables,\n",
     "    image_summaries,\n",
-    "    image_summaries,\n",
+    "    img_base64_list,\n",
     ")"
    ]
   },

cookbook/img-to_img-search_CLIP_ChromaDB.ipynb

@@ -358,7 +358,7 @@
    "id": "6e5cd014-db86-4d6b-8399-25cae3da5570",
    "metadata": {},
    "source": [
-    "## Helper function to plot retrived similar images"
+    "## Helper function to plot retrieved similar images"
    ]
   },
   {

docs/api_reference/conf.py

@@ -11,6 +11,7 @@
 import json
 import os
 import sys
+from datetime import datetime
 from pathlib import Path
 
 import toml
@@ -104,7 +105,7 @@ def skip_private_members(app, what, name, obj, skip, options):
 # -- Project information -----------------------------------------------------
 
 project = "🦜🔗 LangChain"
-copyright = "2023, LangChain Inc"
+copyright = f"{datetime.now().year}, LangChain Inc"
 author = "LangChain, Inc"
 
 html_favicon = "_static/img/brand/favicon.png"
@@ -275,3 +276,7 @@ if os.environ.get("READTHEDOCS", "") == "True":
     html_context["READTHEDOCS"] = True
 
 master_doc = "index"
+
+# If a signature’s length in characters exceeds 60,
+# each parameter within the signature will be displayed on an individual logical line
+maximum_signature_line_length = 60

docs/api_reference/templates/runnable_non_pydantic.rst

@@ -7,7 +7,7 @@
 
 .. 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.
+    The :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>` has additional methods that are available on runnables, such as :py:meth:`with_config <langchain_core.runnables.base.Runnable.with_config>`, :py:meth:`with_types <langchain_core.runnables.base.Runnable.with_types>`, :py:meth:`with_retry <langchain_core.runnables.base.Runnable.with_retry>`, :py:meth:`assign <langchain_core.runnables.base.Runnable.assign>`, :py:meth:`bind <langchain_core.runnables.base.Runnable.bind>`, :py:meth:`get_graph <langchain_core.runnables.base.Runnable.get_graph>`, and more.
 
    {% block attributes %}
    {% if attributes %}

docs/api_reference/templates/runnable_pydantic.rst

@@ -19,6 +19,6 @@
 
     .. 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.
+        The :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>` has additional methods that are available on runnables, such as :py:meth:`with_config <langchain_core.runnables.base.Runnable.with_config>`, :py:meth:`with_types <langchain_core.runnables.base.Runnable.with_types>`, :py:meth:`with_retry <langchain_core.runnables.base.Runnable.with_retry>`, :py:meth:`assign <langchain_core.runnables.base.Runnable.assign>`, :py:meth:`bind <langchain_core.runnables.base.Runnable.bind>`, :py:meth:`get_graph <langchain_core.runnables.base.Runnable.get_graph>`, and more.
 
 .. example_links:: {{ objname }}

docs/cassettes/chat_token_usage_tracking_05f22a1d-b021-490f-8840-f628a07459f2.msgpack.zlib

@@ -1 +0,0 @@
-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

docs/cassettes/chat_token_usage_tracking_07f0c872-6b6c-4fed-a129-9b5a858505be.msgpack.zlib

@@ -1 +1 @@
-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

docs/cassettes/chat_token_usage_tracking_0b1523d8-127e-4314-82fa-bd97aca37f9a.msgpack.zlib

@@ -1 +1 @@
-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

docs/cassettes/chat_token_usage_tracking_1837c807-136a-49d8-9c33-060e58dc16d2.msgpack.zlib

@@ -1 +0,0 @@
-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

docs/cassettes/chat_token_usage_tracking_4728f55a-24e1-48cd-a195-09d037821b1e.msgpack.zlib

@@ -0,0 +1 @@
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

docs/cassettes/chat_token_usage_tracking_67117f2b-ce68-4c1e-9556-2d3849f90e1b.msgpack.zlib

@@ -1 +1 @@
-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

docs/cassettes/chat_token_usage_tracking_9c82ff80-ec4e-4049-b019-5f0bbd7df82a.msgpack.zlib

@@ -1 +1 @@
-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

docs/cassettes/chat_token_usage_tracking_b04a4486-72fd-48ce-8f9e-5d281b441195.msgpack.zlib

@@ -1 +1 @@
-eNqdVXtsU9cZT5qtDRVqR1WVtgxxZ1HRh8/1vX5fZ2ZKYhKiYJzaDiRBNDq+99i+8X3lPhI7lD3CJDatr1sQLYVCWzt2m6RAQqCUNqjvBoa6jU1rXa2ok0bY1oKGEF27bmHHjjMSwV+7f9zX+c73/b7v9/2+M1joQ6rGy1L1KC/pSIWsjj80c7Cgol4DafrP8yLSkzKXawtFollD5YsPJnVd0Xw2G1R4UlaQBHmSlUVbH21jk1C34XdFQGU3uZjMZYrKFouINA0mkGbxbdpiYWUcSdItPksUCQIhIgISPXIKWawWVRYQ/m9oSLVs3Wy1iDKHBPwjoejAKQORl3hspekqgqLFF4eChqwWHYkKRq4bKt5LkdTWQhJBDqf1ZC4pa7p5YCHQg5BlEfaHJFbmeClhvpoY4BUrwaG4AHU0jOFJqFwGcziFkAKgwPeh/Owu8xBUFIFnYWnd1qPJ0mglHaBnFHT98nApF4Bzl3RzIoRB1LfY2jK4ohJBk26apA+lgaZDXhJwiYAAMZ68Ul5/Y/6CAtkUdgIqbJn52c0H5tvImjkUhGwossAlVNmkOQRV0e08PP+/akg6LyKz0Nh2fbjK4rVwDpK2k96xBY61jMSaQ2USXluwGelqBrAy9mG+SB2Yq4+ApISeNLM0bX9ZRZqC+wNty+NtuqEN5jAX6PRUodIoL4Va50g8W7U0F8C8mJMbEWclKBfRhGKEnbK78M3ncvucXqI5GB1trISJ3pCGsagKJS2OqVgzR3uBTRpSCnHDjTckfLJEOM6mBB+3JUBpRdYQqKAyRztAeFYhoCVweLa7gKwmoMQPlMOak2Xm+wfS/RxrcFyyr1+kmAGng48hg41PVLYoqlwKgwEBUTOzDOM9UFmZq/0wzpUCNAUo+nga4D5HAi/yuJ7le0WmmplzURR17HoDHSsLC7rgpMrXifkWKhIxaaXY19w4GYZ588ZGc64c2ITxMMcXWmloPhraLmrHrjeouHiJ0kbTc9aA58ziSvzRDTnG4XAih9PjgN64K+amXSwd57ysnXNDxsm+jpXPs9hLiUxFVnWgIRbPJD1jFq0iTJd05nfQLocbZ1pH8BIrGByKGLGAXMpBqyMUFQky5A6yccBCNonAbP+ZhUDn+vpgS+NwBINslOUUj57+tLqmu5uNd8dE/7o1VHOID7X3hqk1XeudKY3NeGLd4ZBmGC1xJRBq6TEeHpC0tSovA9rj8Hq8DEV5AU1SJFYpcDEpb5ILrW00WtJNVKC1IRTs9darQW8kJnUE6Hi/t51R1DUBt0RFpai7K6FCUW/qc3Kcm2v3BrsMkmwWtCZBbpd7Okl7Z1v3OjvVj7OBetJvqyNwb/K4vv6KQgBWCCjpg/bZ5/RRR3DlGvjJhdOwjliLx3lIEjJ1RKRUTISfUEQRXkf+9bKEijtxDYw+nvNT9UxnbzoQbWXCSTfk0qlA2Ej2t1MsGWxIe5L1altTfVci3GNXEvOK4KY9gKrUwU05veUuvAb9/0R1tAPMFzwIKbPnVkGSNYmPx/MRpGIBmcOsIBscHuwqyjc2gXB9pznBUJyLjdspDrkYbxzGQQMemXPe/jcecqVToQAF3GN9rHk46fBbfE6nw1JHiNDvdWM5lU+3n+VLPSkl3q9+Z8WvaqvKV81j4bef+D31vcnzD928f9nOXeTfvhr8fPA7Ny0ia8dGpo6sOml9Qizu0DeOzNSpZ8TxmHns63+cPX15i+Pys9W1Z2K3Nxx5uv18cGbmxOvLVs8Iz01v+f7Z20Z/8aM9D927evmJrd88uOGVd5dfbLsU+Th1zic/dbL4yw3V97Hhzc/IfecuHr//lPnXvU07Pr33N9/88dzyzlOe9+N7lqITZ59/Y1PzrdlP3j24uOrz3kd3hEYuPfLlix3+Hyz/4P5ld37buuSntR+tDEzd/cD4hHWD45W9aCJ7ZcWFmuSZt0BD1P7CrRdrm8cJMJVd/K/PHp8cW9F2crVlorb5nrev7A24ijdPNbQu6WnIdoOfLOr458P53FHP9GP7yaOPpx5Vtqenbengrtim7+78XZGjxy/HuNA9b13w7pvpjP152xc/3Pjlj7PBwS+urFw1PWSd+mw39+GZ019PD1wZ7Boy79t97O6DbeEjL5//KLN0/OO/3BU4OvXv13Y/M1H4E7fnqrl/0dBvHX8/dcsfcvtu2ffrm/I7/rOxiD7IwiX04tyh2DtPffXC2K7J3be1vLd96pN2jHLb7c7NkQsj6rbjO7ePvHpH8YFva6qqrl6tqbq0btXWTfj9v/DeoiM=
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

docs/cassettes/chat_token_usage_tracking_b39bf807-4125-4db4-bbf7-28a46afff6b4.msgpack.zlib

@@ -1 +1 @@
-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

docs/cassettes/chat_token_usage_tracking_c00c9158-7bb4-4279-88e6-ea70f46e6ac2.msgpack.zlib

@@ -1 +0,0 @@
-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

docs/cassettes/chat_token_usage_tracking_fe945078-ee2d-43ba-8cdf-afb2f2f4ecef.msgpack.zlib

@@ -0,0 +1 @@
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

docs/cassettes/multimodal_inputs_0f68cce7-350b-4cde-bc40-d3a169551fc3.msgpack.zlib

@@ -0,0 +1 @@
+eNqVVnlwE9cZtzkSh1JKmmYgmTGoGwYS4pV2dUuOGx/CxgRbxhb4Koin3Sdppb28h2TZ9UyBkskE0mYHSBNKpg22ZXANBkw54zQUCMz0dtzO2FCTpslASupp66QZmkD6Vge2Y//THY32Pb3v+H3f+33fp+09MSjJjMDn9jG8AiVAKWgja9t7JNiiQln5QZKDSligu2q8db5OVWJGVocVRZTdJhMQGaMgQh4wRkrgTDHSRIWBYkJrkYUpM10BgU6MzilsxzgoyyAEZczd3I5RAnLFK6m1khAh5sYU2KpgBemXG/NAmZKYADQoYWiIQ4BekoHh0ZaRDQyHDLmxjoL7yqlf/KrEIguTa3c7lnphWbyqyAqANsaZKMNBmgFGQQqZ9J2o73TcHMJsUsIqFzDRJpo2VQRFPM7ICK/M8DgHaEYWeByhwXmgqBLEAwKQ6Dhgo8aIGDKZbXZCbMX/Py2so2NzASYJrB6JKkMJ0/ecQEMde0hUcKuRRIHJigQBh7mDgJUhypQgsPLUDAZVPnV3SPT+EqWAB5x+mkmiX1dDEnQqwWJaaNZ0IyERSEgZkULWDYkSumtJYWBql5VCS8irCFYzJqs8n0BqFCuotL6QAIN+QMFkEKIIGF6PFx0hcjESpHW9rKlJQSEQgZSCBDs2d/SEIaARhLGcxV1hQVa0o9Np1w8oCqIkQZ4SaGReOxJqY8QCAw2DLFBgL7oFHqayofVGIRRxwDIxmExraceAKLIMBfRzUwRdU1+Gm7gOZeZxr35BOGIYr2gnvQhESaWpJoHqgzeQRgdhJI614rKC4mYR33EWIDxJMXV+fuqBCKgoMoJnak9LppWPTpURZK27ClDeumkmgUSFtW4gcXbrwNTfJZVXEKu1nrKame4yh/fd9ViMJIk+x6dZlhM8pXWn6HV6mjZUpAROCciI9gaRpAQhykBtNPdBv58K+gNcUZ3fEvNbAhFPzMFyld6AnWcb1Von79vokNpCzFpbiTGyaf26al+8CicdVqvLaXcRZpw0EkaEArdXcrF4bcOGhMjzmzzlDRTXsq6lPFASLfFz3tKm0rWkTfFtiK6vMEf9PlaqdoQ50OJItFRG1pWysKKkwZMI0eIGX4uDV8iGoLVGoBWy1Ot0rPfVVjdWEy22RiHibamzSaFCA4Ksxhi6iKvdaC8JcYlgIF6/NlaxRoow6yo3EZsIm9PjquQCpRba72+CSn1TaApmh43AiSxswuok9OdoljIs5ENKWOu0OchDEpRFVP9wRxIlUlHl7V2InvA3V3syjfCg97lJZj/W5UFU1QbLJabAQDoNJaJkMBNmm4G0ui02N2EzVFT5+soybnyzMvO4TwK8HETsXJOthB4qrPJRSPeWzVoDg3oNoPvV4aP2g8NWUZAhnkGl9TXgtekRgFd6BtIFh6OOCXimLeVWG0wVQ7ytNU5TKk2HY3GOcLVZLaiTqFTwZEYF9Q3dDQKEc7LWZbbbzEczR1k+9qJgCZxEuSXfasUllAuW4RiU0NQ3w4sq+tb7OioJm57yczOlMuMKedAlzswUUIQoRIMtmb60EWyqhAQ5xHYd4nRnVhd63ppdctKhLvXm7EJZpw6Xy2y2fsWSDL8SXCfJyedmykx6Is2cfGamQMZLl83JyX2tWXmcobWRFWjjt9sdpJ12WkiHy0zazRQBbAGCouwOGyRsdpfjrN6ZKWRHp5AoSAouQwqNeiWhjRRwoFVveEUW0maxo8wVokFMsSoN69SAR9ADlQsNogT12dpPBXEKUGjSpVmv9Xgaq0uqKstONeBT6Yt7xfTfjB5ekHkmGEzWQQmxQetNDQ/UuSWYLCvHa0satZMui9kKzRDaKcJqpUknXop6YtbafbJ36W2/B7AIe4zSBsKWIsxttVqwQgMHipx2K0Gk/oxsS6an0OXcL5bvystJPXN311UJ14iFg5/X5z2zaueecy3vN7ePLmo+PWeQfmrhmiRnO7HiFrV58Qe//MYrj1yrtGz9ztLty5bf+WTtMqz0+0tefnirTe37Y+C/nwxuudS/8e6/N+7/jDv+zs3lQ6tuDw+c9YIh8/B/8l8rHBh/NXKy+Mq+j7cGX3azA78bWtGIL/m586HizgXfwo8M8fuv/zY50XqPeGnPRwUuMnr5saarV/tfWFy66K83Invn39u2+9Keiaodfx5a8O3bO/JyOz3tc4eb+Px9i1bOvbpXebJ5ZOhr5JwDtVjI98Ib4mf55TcvPLnas+WZic//8rcrv/59/b+4R5/t45g/jT93uOLTc8Pt+fP2bTkx9rOHx26E6i/n5Vb+5O27xX+PWBNPT7zozaupu/NAd/QXF4H8w7HiU7m3u68L7+Ut6aKU21/YzZe2foQ/+tPXD9aurmi+cKH39CPSx+cxX/dLo6NPr977Xan55gOHv/6j/PZlr++c99B7ptEFo4fKz18/nP/8wYGRwFj3TjBe/s/357k/PLT03aEPPyh/583iisSt7z3L7j7x+K5thQvzP51f/4Th8cF7AweazxY+eKbv3qq7OcTzo0CL7pgf+rF32a8Wnmq/039s7KZhacH+GwfAuHP/qSfmvzK8i6feHj9ycaXpbN8fwhcvjhYfnvjH3W++u2Js5VOeK7dM6Jq//HJujrk3ea14Xk7O/wDBk1ep

docs/cassettes/multimodal_inputs_325fb4ca.msgpack.zlib

@@ -1 +1 @@
-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

docs/cassettes/multimodal_inputs_55e1d937-3b22-4deb-b9f0-9e688f0609dc.msgpack.zlib

@@ -0,0 +1 @@
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

docs/cassettes/multimodal_inputs_83593b9d-a8d3-4c99-9dac-64e0a9d397cb.msgpack.zlib

@@ -0,0 +1 @@
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

docs/cassettes/multimodal_inputs_99d27f8f-ae78-48bc-9bf2-3cef35213ec7.msgpack.zlib

@@ -0,0 +1 @@
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

docs/cassettes/multimodal_inputs_9bbf578e-794a-4dc0-a469-78c876ccd4a3.msgpack.zlib

@@ -0,0 +1 @@
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

docs/cassettes/multimodal_inputs_a8819cf3-5ddc-44f0-889a-19ca7b7fe77e.msgpack.zlib

@@ -1 +0,0 @@
-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

docs/cassettes/multimodal_inputs_cd22ea82-2f93-46f9-9f7a-6aaf479fcaa9.msgpack.zlib

@@ -1 +0,0 @@
-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

docs/cassettes/sql_qa_11.msgpack.zlib

@@ -1 +1 @@
-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

docs/cassettes/sql_qa_39.msgpack.zlib

@@ -1 +1 @@
-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

docs/docs/changes/changelog/core.mdx

@@ -6,5 +6,5 @@
 
 - `BaseChatModel` methods `__call__`, `call_as_llm`, `predict`, `predict_messages`. Will be removed in 0.2.0. Use `BaseChatModel.invoke` instead.
 - `BaseChatModel` methods `apredict`, `apredict_messages`. Will be removed in 0.2.0. Use `BaseChatModel.ainvoke` instead.
-- `BaseLLM` methods `__call__, `predict`, `predict_messages`. Will be removed in 0.2.0. Use `BaseLLM.invoke` instead.
+- `BaseLLM` methods `__call__`, `predict`, `predict_messages`. Will be removed in 0.2.0. Use `BaseLLM.invoke` instead.
 - `BaseLLM` methods `apredict`, `apredict_messages`. Will be removed in 0.2.0. Use `BaseLLM.ainvoke` instead.

docs/docs/concepts/multimodality.mdx

@@ -15,7 +15,10 @@
 * [Messages](/docs/concepts/messages)
 :::
  
-Multimodal support is still relatively new and less common, model providers have not yet standardized on the "best" way to define the API. As such, LangChain's multimodal abstractions are lightweight and flexible, designed to accommodate different model providers' APIs and interaction patterns, but are **not** standardized across models.
+LangChain supports multimodal data as input to chat models:
+
+1. Following provider-specific formats
+2. Adhering to a cross-provider standard (see [how-to guides](/docs/how_to/#multimodal) for detail)
 
 ### How to use multimodal models
 
@@ -26,38 +29,85 @@ Multimodal support is still relatively new and less common, model providers have
 
 #### Inputs
 
-Some models can accept multimodal inputs, such as images, audio, video, or files. The types of multimodal inputs supported depend on the model provider. For instance, [Google's Gemini](/docs/integrations/chat/google_generative_ai/) supports documents like PDFs as inputs.
+Some models can accept multimodal inputs, such as images, audio, video, or files.
+The types of multimodal inputs supported depend on the model provider. For instance,
+[OpenAI](/docs/integrations/chat/openai/),
+[Anthropic](/docs/integrations/chat/anthropic/), and
+[Google Gemini](/docs/integrations/chat/google_generative_ai/)
+support documents like PDFs as inputs.
 
-Most chat models that support **multimodal inputs** also accept those values in OpenAI's content blocks format. So far this is restricted to image inputs. For models like Gemini which support video and other bytes input, the APIs also support the native, model-specific representations.
-
-The gist of passing multimodal inputs to a chat model is to use content blocks that specify a type and corresponding data. For example, to pass an image to a chat model:
+The gist of passing multimodal inputs to a chat model is to use content blocks that
+specify a type and corresponding data. For example, to pass an image to a chat model
+as URL:
 
 ```python
 from langchain_core.messages import HumanMessage
 
 message = HumanMessage(
     content=[
-        {"type": "text", "text": "describe the weather in this image"},
+        {"type": "text", "text": "Describe the weather in this image:"},
+        {
+            "type": "image",
+            "source_type": "url",
+            "url": "https://...",
+        },
+    ],
+)
+response = model.invoke([message])
+```
+
+We can also pass the image as in-line data:
+
+```python
+from langchain_core.messages import HumanMessage
+
+message = HumanMessage(
+    content=[
+        {"type": "text", "text": "Describe the weather in this image:"},
+        {
+            "type": "image",
+            "source_type": "base64",
+            "data": "<base64 string>",
+            "mime_type": "image/jpeg",
+        },
+    ],
+)
+response = model.invoke([message])
+```
+
+To pass a PDF file as in-line data (or URL, as supported by providers such as
+Anthropic), just change `"type"` to `"file"` and `"mime_type"` to `"application/pdf"`.
+
+See the [how-to guides](/docs/how_to/#multimodal) for more detail.
+
+Most chat models that support multimodal **image** inputs also accept those values in
+OpenAI's [Chat Completions format](https://platform.openai.com/docs/guides/images?api-mode=chat):
+
+```python
+from langchain_core.messages import HumanMessage
+
+message = HumanMessage(
+    content=[
+        {"type": "text", "text": "Describe the weather in this image:"},
         {"type": "image_url", "image_url": {"url": image_url}},
     ],
 )
 response = model.invoke([message])
 ```
 
-:::caution
-The exact format of the content blocks may vary depending on the model provider. Please refer to the chat model's
-integration documentation for the correct format. Find the integration in the [chat model integration table](/docs/integrations/chat/).
-:::
+Otherwise, chat models will typically accept the native, provider-specific content
+block format. See [chat model integrations](/docs/integrations/chat/) for detail
+on specific providers.
+
 
 #### Outputs
 
-Virtually no popular chat models support multimodal outputs at the time of writing (October 2024). 
+Some chat models support multimodal outputs, such as images and audio. Multimodal
+outputs will appear as part of the [AIMessage](/docs/concepts/messages/#aimessage)
+response object. See for example:
 
-The only exception is OpenAI's chat model ([gpt-4o-audio-preview](/docs/integrations/chat/openai/)), which can generate audio outputs.
-
-Multimodal outputs will appear as part of the [AIMessage](/docs/concepts/messages/#aimessage) response object.
-
-Please see the [ChatOpenAI](/docs/integrations/chat/openai/) for more information on how to use multimodal outputs.
+- Generating [audio outputs](/docs/integrations/chat/openai/#audio-generation-preview) with OpenAI;
+- Generating [image outputs](/docs/integrations/chat/google_generative_ai/#image-generation) with Google Gemini.
 
 #### Tools
 

docs/docs/concepts/retrieval.mdx

@@ -92,7 +92,7 @@ structured_model = model.with_structured_output(Questions)
 
 # Define the system prompt
 system = """You are a helpful assistant that generates multiple sub-questions related to an input question. \n
-The goal is to break down the input into a set of sub-problems / sub-questions that can be answers in isolation. \n"""
+The goal is to break down the input into a set of sub-problems / sub-questions that can be answered independently. \n"""
 
 # Pass the question to the model
 question = """What are the main components of an LLM-powered autonomous agent system?"""

docs/docs/concepts/runnables.mdx

@@ -126,7 +126,7 @@ Please see the [Configurable Runnables](#configurable-runnables) section for mor
 LangChain will automatically try to infer the input and output types of a Runnable based on available information.
 
 Currently, this inference does not work well for more complex Runnables that are built using [LCEL](/docs/concepts/lcel) composition, and the inferred input and / or output types may be incorrect. In these cases, we recommend that users override the inferred input and output types using the `with_types` method ([API Reference](https://python.langchain.com/api_reference/core/runnables/langchain_core.runnables.base.Runnable.html#langchain_core.runnables.base.Runnable.with_types
-).
+)).
 
 ## RunnableConfig
 
@@ -194,7 +194,7 @@ In Python 3.11 and above, this works out of the box, and you do not need to do a
 In Python 3.9 and 3.10, if you are using **async code**, you need to manually pass the `RunnableConfig` through to the `Runnable` when invoking it. 
 
 This is due to a limitation in [asyncio's tasks](https://docs.python.org/3/library/asyncio-task.html#asyncio.create_task)  in Python 3.9 and 3.10 which did
-not accept a `context` argument).
+not accept a `context` argument.
 
 Propagating the `RunnableConfig` manually is done like so:
 

docs/docs/contributing/how_to/integrations/index.mdx

@@ -83,7 +83,6 @@ LinkedIn, where we highlight the best examples.
 
 Here are some heuristics for types of content we are excited to promote:
 
-- **Integration announcement:** Announcements of new integrations with a link to the LangChain documentation page.
 - **Educational content:** Blogs, YouTube videos and other media showcasing educational content. Note that we prefer content that is NOT framed as "here's how to use integration XYZ", but rather "here's how to do ABC", as we find that is more educational and helpful for developers.
 - **End-to-end applications:** End-to-end applications are great resources for developers looking to build. We prefer to highlight applications that are more complex/agentic in nature, and that use [LangGraph](https://github.com/langchain-ai/langgraph) as the orchestration framework. We get particularly excited about anything involving long-term memory, human-in-the-loop interaction patterns, or multi-agent architectures.
 - **Research:** We love highlighting novel research! Whether it is research built on top of LangChain or that integrates with it.

docs/docs/how_to/chat_token_usage_tracking.ipynb

@@ -16,7 +16,7 @@
     "\n",
     "Tracking [token](/docs/concepts/tokens/) usage to calculate cost is an important part of putting your app in production. This guide goes over how to obtain this information from your LangChain model calls.\n",
     "\n",
-    "This guide requires `langchain-anthropic` and `langchain-openai >= 0.1.9`."
+    "This guide requires `langchain-anthropic` and `langchain-openai >= 0.3.11`."
    ]
   },
   {
@@ -38,19 +38,9 @@
     "\n",
     "OpenAI's Chat Completions API does not stream token usage statistics by default (see API reference\n",
     "[here](https://platform.openai.com/docs/api-reference/completions/create#completions-create-stream_options)).\n",
-    "To recover token counts when streaming with `ChatOpenAI`, set `stream_usage=True` as\n",
+    "To recover token counts when streaming with `ChatOpenAI` or `AzureChatOpenAI`, set `stream_usage=True` as\n",
     "demonstrated in this guide.\n",
     "\n",
-    "For `AzureChatOpenAI`, set `stream_options={\"include_usage\": True}` when calling\n",
-    "`.(a)stream`, or initialize with:\n",
-    "\n",
-    "```python\n",
-    "AzureChatOpenAI(\n",
-    "    ...,\n",
-    "    model_kwargs={\"stream_options\": {\"include_usage\": True}},\n",
-    ")\n",
-    "```\n",
-    "\n",
     ":::"
    ]
   },
@@ -67,7 +57,7 @@
     "\n",
     "A number of model providers return token usage information as part of the chat generation response. When available, this information will be included on the `AIMessage` objects produced by the corresponding model.\n",
     "\n",
-    "LangChain `AIMessage` objects include a [usage_metadata](https://python.langchain.com/api_reference/core/messages/langchain_core.messages.ai.AIMessage.html#langchain_core.messages.ai.AIMessage.usage_metadata) attribute. When populated, this attribute will be a [UsageMetadata](https://python.langchain.com/api_reference/core/messages/langchain_core.messages.ai.UsageMetadata.html) dictionary with standard keys (e.g., `\"input_tokens\"` and `\"output_tokens\"`).\n",
+    "LangChain `AIMessage` objects include a [usage_metadata](https://python.langchain.com/api_reference/core/messages/langchain_core.messages.ai.AIMessage.html#langchain_core.messages.ai.AIMessage.usage_metadata) attribute. When populated, this attribute will be a [UsageMetadata](https://python.langchain.com/api_reference/core/messages/langchain_core.messages.ai.UsageMetadata.html) dictionary with standard keys (e.g., `\"input_tokens\"` and `\"output_tokens\"`). They will also include information on cached token usage and tokens from multi-modal data.\n",
     "\n",
     "Examples:\n",
     "\n",
@@ -92,9 +82,9 @@
     }
    ],
    "source": [
-    "from langchain_openai import ChatOpenAI\n",
+    "from langchain.chat_models import init_chat_model\n",
     "\n",
-    "llm = ChatOpenAI(model=\"gpt-4o-mini\")\n",
+    "llm = init_chat_model(model=\"gpt-4o-mini\")\n",
     "openai_response = llm.invoke(\"hello\")\n",
     "openai_response.usage_metadata"
    ]
@@ -132,37 +122,6 @@
     "anthropic_response.usage_metadata"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "6d4efc15-ba9f-4b3d-9278-8e01f99f263f",
-   "metadata": {},
-   "source": [
-    "### Using AIMessage.response_metadata\n",
-    "\n",
-    "Metadata from the model response is also included in the AIMessage [response_metadata](https://python.langchain.com/api_reference/core/messages/langchain_core.messages.ai.AIMessage.html#langchain_core.messages.ai.AIMessage.response_metadata) attribute. These data are typically not standardized. Note that different providers adopt different conventions for representing token counts:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "f156f9da-21f2-4c81-a714-54cbf9ad393e",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "OpenAI: {'completion_tokens': 9, 'prompt_tokens': 8, 'total_tokens': 17}\n",
-      "\n",
-      "Anthropic: {'input_tokens': 8, 'output_tokens': 12}\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(f'OpenAI: {openai_response.response_metadata[\"token_usage\"]}\\n')\n",
-    "print(f'Anthropic: {anthropic_response.response_metadata[\"usage\"]}')"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "b4ef2c43-0ff6-49eb-9782-e4070c9da8d7",
@@ -207,7 +166,7 @@
     }
    ],
    "source": [
-    "llm = ChatOpenAI(model=\"gpt-4o-mini\")\n",
+    "llm = init_chat_model(model=\"gpt-4o-mini\")\n",
     "\n",
     "aggregate = None\n",
     "for chunk in llm.stream(\"hello\", stream_usage=True):\n",
@@ -318,7 +277,7 @@
     "    punchline: str = Field(description=\"answer to resolve the joke\")\n",
     "\n",
     "\n",
-    "llm = ChatOpenAI(\n",
+    "llm = init_chat_model(\n",
     "    model=\"gpt-4o-mini\",\n",
     "    stream_usage=True,\n",
     ")\n",
@@ -326,10 +285,10 @@
     "# chat model and appends a parser.\n",
     "structured_llm = llm.with_structured_output(Joke)\n",
     "\n",
-    "async for event in structured_llm.astream_events(\"Tell me a joke\", version=\"v2\"):\n",
+    "async for event in structured_llm.astream_events(\"Tell me a joke\"):\n",
     "    if event[\"event\"] == \"on_chat_model_end\":\n",
     "        print(f'Token usage: {event[\"data\"][\"output\"].usage_metadata}\\n')\n",
-    "    elif event[\"event\"] == \"on_chain_end\":\n",
+    "    elif event[\"event\"] == \"on_chain_end\" and event[\"name\"] == \"RunnableSequence\":\n",
     "        print(event[\"data\"][\"output\"])\n",
     "    else:\n",
     "        pass"
@@ -350,17 +309,18 @@
    "source": [
     "## Using callbacks\n",
     "\n",
-    "There are also some API-specific callback context managers that allow you to track token usage across multiple calls. They are currently only implemented for the OpenAI API and Bedrock Anthropic API, and are available in `langchain-community`:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "64e52d21",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%pip install -qU langchain-community"
+    ":::info Requires ``langchain-core>=0.3.49``\n",
+    "\n",
+    ":::\n",
+    "\n",
+    "LangChain implements a callback handler and context manager that will track token usage across calls of any chat model that returns `usage_metadata`.\n",
+    "\n",
+    "There are also some API-specific callback context managers that maintain pricing for different models, allowing for cost estimation in real time. They are currently only implemented for the OpenAI API and Bedrock Anthropic API, and are available in `langchain-community`:\n",
+    "\n",
+    "- [get_openai_callback](https://python.langchain.com/api_reference/community/callbacks/langchain_community.callbacks.manager.get_openai_callback.html)\n",
+    "- [get_bedrock_anthropic_callback](https://python.langchain.com/api_reference/community/callbacks/langchain_community.callbacks.manager.get_bedrock_anthropic_callback.html)\n",
+    "\n",
+    "Below, we demonstrate the general-purpose usage metadata callback manager. We can track token usage through configuration or as a context manager."
    ]
   },
   {
@@ -368,41 +328,84 @@
    "id": "6f043cb9",
    "metadata": {},
    "source": [
-    "### OpenAI\n",
+    "### Tracking token usage through configuration\n",
     "\n",
-    "Let's first look at an extremely simple example of tracking token usage for a single Chat model call."
+    "To track token usage through configuration, instantiate a `UsageMetadataCallbackHandler` and pass it into the config:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 17,
    "id": "b04a4486-72fd-48ce-8f9e-5d281b441195",
    "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'gpt-4o-mini-2024-07-18': {'input_tokens': 8,\n",
+       "  'output_tokens': 10,\n",
+       "  'total_tokens': 18,\n",
+       "  'input_token_details': {'audio': 0, 'cache_read': 0},\n",
+       "  'output_token_details': {'audio': 0, 'reasoning': 0}},\n",
+       " 'claude-3-5-haiku-20241022': {'input_tokens': 8,\n",
+       "  'output_tokens': 21,\n",
+       "  'total_tokens': 29,\n",
+       "  'input_token_details': {'cache_read': 0, 'cache_creation': 0}}}"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain.chat_models import init_chat_model\n",
+    "from langchain_core.callbacks import UsageMetadataCallbackHandler\n",
+    "\n",
+    "llm_1 = init_chat_model(model=\"openai:gpt-4o-mini\")\n",
+    "llm_2 = init_chat_model(model=\"anthropic:claude-3-5-haiku-latest\")\n",
+    "\n",
+    "callback = UsageMetadataCallbackHandler()\n",
+    "result_1 = llm_1.invoke(\"Hello\", config={\"callbacks\": [callback]})\n",
+    "result_2 = llm_2.invoke(\"Hello\", config={\"callbacks\": [callback]})\n",
+    "callback.usage_metadata"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7a290085-e541-4233-afe4-637ec5032bfd",
+   "metadata": {},
+   "source": [
+    "### Tracking token usage using a context manager\n",
+    "\n",
+    "You can also use `get_usage_metadata_callback` to create a context manager and aggregate usage metadata there:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "4728f55a-24e1-48cd-a195-09d037821b1e",
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Tokens Used: 27\n",
-      "\tPrompt Tokens: 11\n",
-      "\tCompletion Tokens: 16\n",
-      "Successful Requests: 1\n",
-      "Total Cost (USD): $2.95e-05\n"
+      "{'gpt-4o-mini-2024-07-18': {'input_tokens': 8, 'output_tokens': 10, 'total_tokens': 18, 'input_token_details': {'audio': 0, 'cache_read': 0}, 'output_token_details': {'audio': 0, 'reasoning': 0}}, 'claude-3-5-haiku-20241022': {'input_tokens': 8, 'output_tokens': 21, 'total_tokens': 29, 'input_token_details': {'cache_read': 0, 'cache_creation': 0}}}\n"
      ]
     }
    ],
    "source": [
-    "from langchain_community.callbacks.manager import get_openai_callback\n",
+    "from langchain.chat_models import init_chat_model\n",
+    "from langchain_core.callbacks import get_usage_metadata_callback\n",
     "\n",
-    "llm = ChatOpenAI(\n",
-    "    model=\"gpt-4o-mini\",\n",
-    "    temperature=0,\n",
-    "    stream_usage=True,\n",
-    ")\n",
+    "llm_1 = init_chat_model(model=\"openai:gpt-4o-mini\")\n",
+    "llm_2 = init_chat_model(model=\"anthropic:claude-3-5-haiku-latest\")\n",
     "\n",
-    "with get_openai_callback() as cb:\n",
-    "    result = llm.invoke(\"Tell me a joke\")\n",
-    "    print(cb)"
+    "with get_usage_metadata_callback() as cb:\n",
+    "    llm_1.invoke(\"Hello\")\n",
+    "    llm_2.invoke(\"Hello\")\n",
+    "    print(cb.usage_metadata)"
    ]
   },
   {
@@ -410,61 +413,7 @@
    "id": "c0ab6d27",
    "metadata": {},
    "source": [
-    "Anything inside the context manager will get tracked. Here's an example of using it to track multiple calls in sequence."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "05f22a1d-b021-490f-8840-f628a07459f2",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "54\n"
-     ]
-    }
-   ],
-   "source": [
-    "with get_openai_callback() as cb:\n",
-    "    result = llm.invoke(\"Tell me a joke\")\n",
-    "    result2 = llm.invoke(\"Tell me a joke\")\n",
-    "    print(cb.total_tokens)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "c00c9158-7bb4-4279-88e6-ea70f46e6ac2",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Tokens Used: 27\n",
-      "\tPrompt Tokens: 11\n",
-      "\tCompletion Tokens: 16\n",
-      "Successful Requests: 1\n",
-      "Total Cost (USD): $2.95e-05\n"
-     ]
-    }
-   ],
-   "source": [
-    "with get_openai_callback() as cb:\n",
-    "    for chunk in llm.stream(\"Tell me a joke\"):\n",
-    "        pass\n",
-    "    print(cb)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "d8186e7b",
-   "metadata": {},
-   "source": [
-    "If a chain or agent with multiple steps in it is used, it will track all those steps."
+    "Either of these methods will aggregate token usage across multiple calls to each model. For example, you can use it in an [agent](https://python.langchain.com/docs/concepts/agents/) to track token usage across repeated calls to one model:"
    ]
   },
   {
@@ -474,138 +423,63 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install -qU langchain langchain-aws wikipedia"
+    "%pip install -qU langgraph"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
-   "id": "5d1125c6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.agents import AgentExecutor, create_tool_calling_agent, load_tools\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\"system\", \"You're a helpful assistant\"),\n",
-    "        (\"human\", \"{input}\"),\n",
-    "        (\"placeholder\", \"{agent_scratchpad}\"),\n",
-    "    ]\n",
-    ")\n",
-    "tools = load_tools([\"wikipedia\"])\n",
-    "agent = create_tool_calling_agent(llm, tools, prompt)\n",
-    "agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "3950d88b-8bfb-4294-b75b-e6fd421e633c",
+   "execution_count": 20,
+   "id": "fe945078-ee2d-43ba-8cdf-afb2f2f4ecef",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
+      "================================\u001b[1m Human Message \u001b[0m=================================\n",
       "\n",
+      "What's the weather in Boston?\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
+      "Tool Calls:\n",
+      "  get_weather (call_izMdhUYpp9Vhx7DTNAiybzGa)\n",
+      " Call ID: call_izMdhUYpp9Vhx7DTNAiybzGa\n",
+      "  Args:\n",
+      "    location: Boston\n",
+      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
+      "Name: get_weather\n",
       "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3m\n",
-      "Invoking: `wikipedia` with `{'query': 'hummingbird scientific name'}`\n",
+      "It's sunny.\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
       "\n",
+      "The weather in Boston is sunny.\n",
       "\n",
-      "\u001b[0m\u001b[36;1m\u001b[1;3mPage: Hummingbird\n",
-      "Summary: Hummingbirds are birds native to the Americas and comprise the biological family Trochilidae. With approximately 366 species and 113 genera, they occur from Alaska to Tierra del Fuego, but most species are found in Central and South America. As of 2024, 21 hummingbird species are listed as endangered or critically endangered, with numerous species declining in population.\n",
-      "Hummingbirds have varied specialized characteristics to enable rapid, maneuverable flight: exceptional metabolic capacity, adaptations to high altitude, sensitive visual and communication abilities, and long-distance migration in some species. Among all birds, male hummingbirds have the widest diversity of plumage color, particularly in blues, greens, and purples. Hummingbirds are the smallest mature birds, measuring 7.5–13 cm (3–5 in) in length. The smallest is the 5 cm (2.0 in) bee hummingbird, which weighs less than 2.0 g (0.07 oz), and the largest is the 23 cm (9 in) giant hummingbird, weighing 18–24 grams (0.63–0.85 oz). Noted for long beaks, hummingbirds are specialized for feeding on flower nectar, but all species also consume small insects.\n",
-      "They are known as hummingbirds because of the humming sound created by their beating wings, which flap at high frequencies audible to other birds and humans. They hover at rapid wing-flapping rates, which vary from around 12 beats per second in the largest species to 80 per second in small hummingbirds.\n",
-      "Hummingbirds have the highest mass-specific metabolic rate of any homeothermic animal. To conserve energy when food is scarce and at night when not foraging, they can enter torpor, a state similar to hibernation, and slow their metabolic rate to 1⁄15 of its normal rate. While most hummingbirds do not migrate, the rufous hummingbird has one of the longest migrations among birds, traveling twice per year between Alaska and Mexico, a distance of about 3,900 miles (6,300 km).\n",
-      "Hummingbirds split from their sister group, the swifts and treeswifts, around 42 million years ago. The oldest known fossil hummingbird is Eurotrochilus, from the Rupelian Stage of Early Oligocene Europe.\n",
-      "\n",
-      "Page: Rufous hummingbird\n",
-      "Summary: The rufous hummingbird (Selasphorus rufus) is a small hummingbird, about 8 cm (3.1 in) long with a long, straight and slender bill. These birds are known for their extraordinary flight skills, flying 2,000 mi (3,200 km) during their migratory transits. It is one of nine species in the genus Selasphorus.\n",
-      "\n",
-      "\n",
-      "\n",
-      "Page: Allen's hummingbird\n",
-      "Summary: Allen's hummingbird (Selasphorus sasin) is a species of hummingbird that breeds in the western United States. It is one of seven species in the genus Selasphorus.\u001b[0m\u001b[32;1m\u001b[1;3m\n",
-      "Invoking: `wikipedia` with `{'query': 'fastest bird species'}`\n",
-      "\n",
-      "\n",
-      "\u001b[0m\u001b[36;1m\u001b[1;3mPage: List of birds by flight speed\n",
-      "Summary: This is a list of the fastest flying birds in the world. A bird's velocity is necessarily variable; a hunting bird will reach much greater speeds while diving to catch prey than when flying horizontally. The bird that can achieve the greatest airspeed is the peregrine falcon (Falco peregrinus), able to exceed 320 km/h (200 mph) in its dives. A close relative of the common swift, the white-throated needletail (Hirundapus caudacutus), is commonly reported as the fastest bird in level flight with a reported top speed of 169 km/h (105 mph). This record remains unconfirmed as the measurement methods have never been published or verified. The record for the fastest confirmed level flight by a bird is 111.5 km/h (69.3 mph) held by the common swift.\n",
-      "\n",
-      "Page: Fastest animals\n",
-      "Summary: This is a list of the fastest animals in the world, by types of animal.\n",
-      "\n",
-      "Page: Falcon\n",
-      "Summary: Falcons () are birds of prey in the genus Falco, which includes about 40 species. Falcons are widely distributed on all continents of the world except Antarctica, though closely related raptors did occur there in the Eocene.\n",
-      "Adult falcons have thin, tapered wings, which enable them to fly at high speed and change direction rapidly. Fledgling falcons, in their first year of flying, have longer flight feathers, which make their configuration more like that of a general-purpose bird such as a broad wing. This makes flying easier while learning the exceptional skills required to be effective hunters as adults.\n",
-      "The falcons are the largest genus in the Falconinae subfamily of Falconidae, which itself also includes another subfamily comprising caracaras and a few other species. All these birds kill with their beaks, using a tomial \"tooth\" on the side of their beaks—unlike the hawks, eagles, and other birds of prey in the Accipitridae, which use their feet.\n",
-      "The largest falcon is the gyrfalcon at up to 65 cm in length.  The smallest falcon species is the pygmy falcon, which measures just 20 cm.  As with hawks and owls, falcons exhibit sexual dimorphism, with the females typically larger than the males, thus allowing a wider range of prey species.\n",
-      "Some small falcons with long, narrow wings are called \"hobbies\" and some which hover while hunting are called \"kestrels\".\n",
-      "As is the case with many birds of prey, falcons have exceptional powers of vision; the visual acuity of one species has been measured at 2.6 times that of a normal human. Peregrine falcons have been recorded diving at speeds of 320 km/h (200 mph), making them the fastest-moving creatures on Earth; the fastest recorded dive attained a vertical speed of 390 km/h (240 mph).\u001b[0m\u001b[32;1m\u001b[1;3mThe scientific name for a hummingbird is Trochilidae. The fastest bird species in level flight is the common swift, which holds the record for the fastest confirmed level flight by a bird at 111.5 km/h (69.3 mph). The peregrine falcon is known to exceed speeds of 320 km/h (200 mph) in its dives, making it the fastest bird in terms of diving speed.\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n",
-      "Total Tokens: 1675\n",
-      "Prompt Tokens: 1538\n",
-      "Completion Tokens: 137\n",
-      "Total Cost (USD): $0.0009745000000000001\n"
+      "Total usage: {'gpt-4o-mini-2024-07-18': {'input_token_details': {'audio': 0, 'cache_read': 0}, 'input_tokens': 125, 'total_tokens': 149, 'output_tokens': 24, 'output_token_details': {'audio': 0, 'reasoning': 0}}}\n"
      ]
     }
    ],
    "source": [
-    "with get_openai_callback() as cb:\n",
-    "    response = agent_executor.invoke(\n",
-    "        {\n",
-    "            \"input\": \"What's a hummingbird's scientific name and what's the fastest bird species?\"\n",
-    "        }\n",
-    "    )\n",
-    "    print(f\"Total Tokens: {cb.total_tokens}\")\n",
-    "    print(f\"Prompt Tokens: {cb.prompt_tokens}\")\n",
-    "    print(f\"Completion Tokens: {cb.completion_tokens}\")\n",
-    "    print(f\"Total Cost (USD): ${cb.total_cost}\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "ebc9122b-050b-4006-b763-264b0b26d9df",
-   "metadata": {},
-   "source": [
-    "### Bedrock Anthropic\n",
+    "from langgraph.prebuilt import create_react_agent\n",
     "\n",
-    "The `get_bedrock_anthropic_callback` works very similarly:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "1837c807-136a-49d8-9c33-060e58dc16d2",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Tokens Used: 96\n",
-      "\tPrompt Tokens: 26\n",
-      "\tCompletion Tokens: 70\n",
-      "Successful Requests: 2\n",
-      "Total Cost (USD): $0.001888\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_aws import ChatBedrock\n",
-    "from langchain_community.callbacks.manager import get_bedrock_anthropic_callback\n",
     "\n",
-    "llm = ChatBedrock(model_id=\"anthropic.claude-v2\")\n",
+    "# Create a tool\n",
+    "def get_weather(location: str) -> str:\n",
+    "    \"\"\"Get the weather at a location.\"\"\"\n",
+    "    return \"It's sunny.\"\n",
     "\n",
-    "with get_bedrock_anthropic_callback() as cb:\n",
-    "    result = llm.invoke(\"Tell me a joke\")\n",
-    "    result2 = llm.invoke(\"Tell me a joke\")\n",
-    "    print(cb)"
+    "\n",
+    "callback = UsageMetadataCallbackHandler()\n",
+    "\n",
+    "tools = [get_weather]\n",
+    "agent = create_react_agent(\"openai:gpt-4o-mini\", tools)\n",
+    "for step in agent.stream(\n",
+    "    {\"messages\": [{\"role\": \"user\", \"content\": \"What's the weather in Boston?\"}]},\n",
+    "    stream_mode=\"values\",\n",
+    "    config={\"callbacks\": [callback]},\n",
+    "):\n",
+    "    step[\"messages\"][-1].pretty_print()\n",
+    "\n",
+    "\n",
+    "print(f\"\\nTotal usage: {callback.usage_metadata}\")"
    ]
   },
   {

docs/docs/how_to/code_splitter.ipynb

@@ -40,7 +40,7 @@
     "\n",
     "To view the list of separators for a given language, pass a value from this enum into\n",
     "```python\n",
-    "RecursiveCharacterTextSplitter.get_separators_for_language`\n",
+    "RecursiveCharacterTextSplitter.get_separators_for_language\n",
     "```\n",
     "\n",
     "To instantiate a splitter that is tailored for a specific language, pass a value from the enum into\n",

docs/docs/how_to/index.mdx

@@ -50,6 +50,7 @@ See [supported integrations](/docs/integrations/chat/) for details on getting st
 - [How to: force a specific tool call](/docs/how_to/tool_choice)
 - [How to: work with local models](/docs/how_to/local_llms)
 - [How to: init any model in one line](/docs/how_to/chat_models_universal_init/)
+- [How to: pass multimodal data directly to models](/docs/how_to/multimodal_inputs/)
 
 ### Messages
 
@@ -67,6 +68,7 @@ See [supported integrations](/docs/integrations/chat/) for details on getting st
 - [How to: use few shot examples in chat models](/docs/how_to/few_shot_examples_chat/)
 - [How to: partially format prompt templates](/docs/how_to/prompts_partial)
 - [How to: compose prompts together](/docs/how_to/prompts_composition)
+- [How to: use multimodal prompts](/docs/how_to/multimodal_prompts/)
 
 ### Example selectors
 
@@ -170,7 +172,7 @@ 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. Refer [here](/docs/integrations/tools/) for a list of pre-buit 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. Refer [here](/docs/integrations/tools/) for a list of pre-built tools. 
 
 - [How to: create tools](/docs/how_to/custom_tools)
 - [How to: use built-in tools and toolkits](/docs/how_to/tools_builtin)
@@ -351,7 +353,7 @@ LangSmith allows you to closely trace, monitor and evaluate your LLM application
 It seamlessly integrates with LangChain and LangGraph, and you can use it to inspect and debug individual steps of your chains and agents as you build.
 
 LangSmith documentation is hosted on a separate site.
-You can peruse [LangSmith how-to guides here](https://docs.smith.langchain.com/how_to_guides/), but we'll highlight a few sections that are particularly
+You can peruse [LangSmith how-to guides here](https://docs.smith.langchain.com/), but we'll highlight a few sections that are particularly
 relevant to LangChain below:
 
 ### Evaluation

docs/docs/how_to/multimodal_inputs.ipynb

@@ -5,120 +5,165 @@
    "id": "4facdf7f-680e-4d28-908b-2b8408e2a741",
    "metadata": {},
    "source": [
-    "# How to pass multimodal data directly to models\n",
+    "# How to pass multimodal data to models\n",
     "\n",
-    "Here we demonstrate how to pass [multimodal](/docs/concepts/multimodality/) input directly to models. \n",
-    "We currently expect all input to be passed in the same format as [OpenAI expects](https://platform.openai.com/docs/guides/vision).\n",
-    "For other model providers that support multimodal input, we have added logic inside the class to convert to the expected format.\n",
+    "Here we demonstrate how to pass [multimodal](/docs/concepts/multimodality/) input directly to models.\n",
     "\n",
-    "In this example we will ask a [model](/docs/concepts/chat_models/#multimodality) to describe an image."
+    "LangChain supports multimodal data as input to chat models:\n",
+    "\n",
+    "1. Following provider-specific formats\n",
+    "2. Adhering to a cross-provider standard\n",
+    "\n",
+    "Below, we demonstrate the cross-provider standard. See [chat model integrations](/docs/integrations/chat/) for detail\n",
+    "on native formats for specific providers.\n",
+    "\n",
+    ":::note\n",
+    "\n",
+    "Most chat models that support multimodal **image** inputs also accept those values in\n",
+    "OpenAI's [Chat Completions format](https://platform.openai.com/docs/guides/images?api-mode=chat):\n",
+    "\n",
+    "```python\n",
+    "{\n",
+    "    \"type\": \"image_url\",\n",
+    "    \"image_url\": {\"url\": image_url},\n",
+    "}\n",
+    "```\n",
+    ":::"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e30a4ff0-ab38-41a7-858c-a93f99bb2f1b",
+   "metadata": {},
+   "source": [
+    "## Images\n",
+    "\n",
+    "Many providers will accept images passed in-line as base64 data. Some will additionally accept an image from a URL directly.\n",
+    "\n",
+    "### Images from base64 data\n",
+    "\n",
+    "To pass images in-line, format them as content blocks of the following form:\n",
+    "\n",
+    "```python\n",
+    "{\n",
+    "    \"type\": \"image\",\n",
+    "    \"source_type\": \"base64\",\n",
+    "    \"mime_type\": \"image/jpeg\",  # or image/png, etc.\n",
+    "    \"data\": \"<base64 data string>\",\n",
+    "}\n",
+    "```\n",
+    "\n",
+    "Example:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
-   "id": "0d9fd81a-b7f0-445a-8e3d-cfc2d31fdd59",
+   "execution_count": 10,
+   "id": "1fcf7b27-1cc3-420a-b920-0420b5892e20",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The image shows a beautiful clear day with bright blue skies and wispy cirrus clouds stretching across the horizon. The clouds are thin and streaky, creating elegant patterns against the blue backdrop. The lighting suggests it's during the day, possibly late afternoon given the warm, golden quality of the light on the grass. The weather appears calm with no signs of wind (the grass looks relatively still) and no indication of rain. It's the kind of perfect, mild weather that's ideal for walking along the wooden boardwalk through the marsh grass.\n"
+     ]
+    }
+   ],
    "source": [
-    "image_url = \"https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg\""
+    "import base64\n",
+    "\n",
+    "import httpx\n",
+    "from langchain.chat_models import init_chat_model\n",
+    "\n",
+    "# Fetch image data\n",
+    "image_url = \"https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg\"\n",
+    "image_data = base64.b64encode(httpx.get(image_url).content).decode(\"utf-8\")\n",
+    "\n",
+    "\n",
+    "# Pass to LLM\n",
+    "llm = init_chat_model(\"anthropic:claude-3-5-sonnet-latest\")\n",
+    "\n",
+    "message = {\n",
+    "    \"role\": \"user\",\n",
+    "    \"content\": [\n",
+    "        {\n",
+    "            \"type\": \"text\",\n",
+    "            \"text\": \"Describe the weather in this image:\",\n",
+    "        },\n",
+    "        # highlight-start\n",
+    "        {\n",
+    "            \"type\": \"image\",\n",
+    "            \"source_type\": \"base64\",\n",
+    "            \"data\": image_data,\n",
+    "            \"mime_type\": \"image/jpeg\",\n",
+    "        },\n",
+    "        # highlight-end\n",
+    "    ],\n",
+    "}\n",
+    "response = llm.invoke([message])\n",
+    "print(response.text())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ee2b678a-01dd-40c1-81ff-ddac22be21b7",
+   "metadata": {},
+   "source": [
+    "See [LangSmith trace](https://smith.langchain.com/public/eab05a31-54e8-4fc9-911f-56805da67bef/r) for more detail.\n",
+    "\n",
+    "### Images from a URL\n",
+    "\n",
+    "Some providers (including [OpenAI](/docs/integrations/chat/openai/),\n",
+    "[Anthropic](/docs/integrations/chat/anthropic/), and\n",
+    "[Google Gemini](/docs/integrations/chat/google_generative_ai/)) will also accept images from URLs directly.\n",
+    "\n",
+    "To pass images as URLs, format them as content blocks of the following form:\n",
+    "\n",
+    "```python\n",
+    "{\n",
+    "    \"type\": \"image\",\n",
+    "    \"source_type\": \"url\",\n",
+    "    \"url\": \"https://...\",\n",
+    "}\n",
+    "```\n",
+    "\n",
+    "Example:"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 2,
-   "id": "fb896ce9",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "model = ChatOpenAI(model=\"gpt-4o\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "4fca4da7",
-   "metadata": {},
-   "source": [
-    "The most commonly supported way to pass in images is to pass it in as a byte string.\n",
-    "This should work for most model integrations."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "9ca1040c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import base64\n",
-    "\n",
-    "import httpx\n",
-    "\n",
-    "image_data = base64.b64encode(httpx.get(image_url).content).decode(\"utf-8\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "ec680b6b",
+   "id": "99d27f8f-ae78-48bc-9bf2-3cef35213ec7",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "The weather in the image appears to be clear and pleasant. The sky is mostly blue with scattered, light clouds, suggesting a sunny day with minimal cloud cover. There is no indication of rain or strong winds, and the overall scene looks bright and calm. The lush green grass and clear visibility further indicate good weather conditions.\n"
+      "The weather in this image appears to be pleasant and clear. The sky is mostly blue with a few scattered, light clouds, and there is bright sunlight illuminating the green grass and plants. There are no signs of rain or stormy conditions, suggesting it is a calm, likely warm day—typical of spring or summer.\n"
      ]
     }
    ],
    "source": [
-    "message = HumanMessage(\n",
-    "    content=[\n",
-    "        {\"type\": \"text\", \"text\": \"describe the weather in this image\"},\n",
+    "message = {\n",
+    "    \"role\": \"user\",\n",
+    "    \"content\": [\n",
     "        {\n",
-    "            \"type\": \"image_url\",\n",
-    "            \"image_url\": {\"url\": f\"data:image/jpeg;base64,{image_data}\"},\n",
+    "            \"type\": \"text\",\n",
+    "            \"text\": \"Describe the weather in this image:\",\n",
+    "        },\n",
+    "        {\n",
+    "            \"type\": \"image\",\n",
+    "            # highlight-start\n",
+    "            \"source_type\": \"url\",\n",
+    "            \"url\": image_url,\n",
+    "            # highlight-end\n",
     "        },\n",
     "    ],\n",
-    ")\n",
-    "response = model.invoke([message])\n",
-    "print(response.content)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "8656018e-c56d-47d2-b2be-71e87827f90a",
-   "metadata": {},
-   "source": [
-    "We can feed the image URL directly in a content block of type \"image_url\". Note that only some model providers support this."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "a8819cf3-5ddc-44f0-889a-19ca7b7fe77e",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "The weather in the image appears to be clear and sunny. The sky is mostly blue with a few scattered clouds, suggesting good visibility and a likely pleasant temperature. The bright sunlight is casting distinct shadows on the grass and vegetation, indicating it is likely daytime, possibly late morning or early afternoon. The overall ambiance suggests a warm and inviting day, suitable for outdoor activities.\n"
-     ]
-    }
-   ],
-   "source": [
-    "message = HumanMessage(\n",
-    "    content=[\n",
-    "        {\"type\": \"text\", \"text\": \"describe the weather in this image\"},\n",
-    "        {\"type\": \"image_url\", \"image_url\": {\"url\": image_url}},\n",
-    "    ],\n",
-    ")\n",
-    "response = model.invoke([message])\n",
-    "print(response.content)"
+    "}\n",
+    "response = llm.invoke([message])\n",
+    "print(response.text())"
    ]
   },
   {
@@ -126,12 +171,12 @@
    "id": "1c470309",
    "metadata": {},
    "source": [
-    "We can also pass in multiple images."
+    "We can also pass in multiple images:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 4,
    "id": "325fb4ca",
    "metadata": {},
    "outputs": [
@@ -139,20 +184,460 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Yes, the two images are the same. They both depict a wooden boardwalk extending through a grassy field under a blue sky with light clouds. The scenery, lighting, and composition are identical.\n"
+      "Yes, these two images are the same. They depict a wooden boardwalk going through a grassy field under a blue sky with some clouds. The colors, composition, and elements in both images are identical.\n"
      ]
     }
    ],
    "source": [
-    "message = HumanMessage(\n",
-    "    content=[\n",
-    "        {\"type\": \"text\", \"text\": \"are these two images the same?\"},\n",
-    "        {\"type\": \"image_url\", \"image_url\": {\"url\": image_url}},\n",
-    "        {\"type\": \"image_url\", \"image_url\": {\"url\": image_url}},\n",
+    "message = {\n",
+    "    \"role\": \"user\",\n",
+    "    \"content\": [\n",
+    "        {\"type\": \"text\", \"text\": \"Are these two images the same?\"},\n",
+    "        {\"type\": \"image\", \"source_type\": \"url\", \"url\": image_url},\n",
+    "        {\"type\": \"image\", \"source_type\": \"url\", \"url\": image_url},\n",
     "    ],\n",
-    ")\n",
-    "response = model.invoke([message])\n",
-    "print(response.content)"
+    "}\n",
+    "response = llm.invoke([message])\n",
+    "print(response.text())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d72b83e6-8d21-448e-b5df-d5b556c3ccc8",
+   "metadata": {},
+   "source": [
+    "## Documents (PDF)\n",
+    "\n",
+    "Some providers (including [OpenAI](/docs/integrations/chat/openai/),\n",
+    "[Anthropic](/docs/integrations/chat/anthropic/), and\n",
+    "[Google Gemini](/docs/integrations/chat/google_generative_ai/)) will accept PDF documents.\n",
+    "\n",
+    "### Documents from base64 data\n",
+    "\n",
+    "To pass documents in-line, format them as content blocks of the following form:\n",
+    "\n",
+    "```python\n",
+    "{\n",
+    "    \"type\": \"file\",\n",
+    "    \"source_type\": \"base64\",\n",
+    "    \"mime_type\": \"application/pdf\",\n",
+    "    \"data\": \"<base64 data string>\",\n",
+    "}\n",
+    "```\n",
+    "\n",
+    "Example:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "6c1455a9-699a-4702-a7e0-7f6eaec76a21",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "This document appears to be a sample PDF file that contains Lorem ipsum placeholder text. It begins with a title \"Sample PDF\" followed by the subtitle \"This is a simple PDF file. Fun fun fun.\"\n",
+      "\n",
+      "The rest of the document consists of several paragraphs of Lorem ipsum text, which is a commonly used placeholder text in design and publishing. The text is formatted in a clean, readable layout with consistent paragraph spacing. The document appears to be a single page containing four main paragraphs of this placeholder text.\n",
+      "\n",
+      "The Lorem ipsum text, while appearing to be Latin, is actually scrambled Latin-like text that is used primarily to demonstrate the visual form of a document or typeface without the distraction of meaningful content. It's commonly used in publishing and graphic design when the actual content is not yet available but the layout needs to be demonstrated.\n",
+      "\n",
+      "The document has a professional, simple layout with generous margins and clear paragraph separation, making it an effective example of basic PDF formatting and structure.\n"
+     ]
+    }
+   ],
+   "source": [
+    "import base64\n",
+    "\n",
+    "import httpx\n",
+    "from langchain.chat_models import init_chat_model\n",
+    "\n",
+    "# Fetch PDF data\n",
+    "pdf_url = \"https://pdfobject.com/pdf/sample.pdf\"\n",
+    "pdf_data = base64.b64encode(httpx.get(pdf_url).content).decode(\"utf-8\")\n",
+    "\n",
+    "\n",
+    "# Pass to LLM\n",
+    "llm = init_chat_model(\"anthropic:claude-3-5-sonnet-latest\")\n",
+    "\n",
+    "message = {\n",
+    "    \"role\": \"user\",\n",
+    "    \"content\": [\n",
+    "        {\n",
+    "            \"type\": \"text\",\n",
+    "            \"text\": \"Describe the document:\",\n",
+    "        },\n",
+    "        # highlight-start\n",
+    "        {\n",
+    "            \"type\": \"file\",\n",
+    "            \"source_type\": \"base64\",\n",
+    "            \"data\": pdf_data,\n",
+    "            \"mime_type\": \"application/pdf\",\n",
+    "        },\n",
+    "        # highlight-end\n",
+    "    ],\n",
+    "}\n",
+    "response = llm.invoke([message])\n",
+    "print(response.text())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "efb271da-8fdd-41b5-9f29-be6f8c76f49b",
+   "metadata": {},
+   "source": [
+    "### Documents from a URL\n",
+    "\n",
+    "Some providers (specifically [Anthropic](/docs/integrations/chat/anthropic/))\n",
+    "will also accept documents from URLs directly.\n",
+    "\n",
+    "To pass documents as URLs, format them as content blocks of the following form:\n",
+    "\n",
+    "```python\n",
+    "{\n",
+    "    \"type\": \"file\",\n",
+    "    \"source_type\": \"url\",\n",
+    "    \"url\": \"https://...\",\n",
+    "}\n",
+    "```\n",
+    "\n",
+    "Example:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "55e1d937-3b22-4deb-b9f0-9e688f0609dc",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "This document appears to be a sample PDF file with both text and an image. It begins with a title \"Sample PDF\" followed by the text \"This is a simple PDF file. Fun fun fun.\" The rest of the document contains Lorem ipsum placeholder text arranged in several paragraphs. The content is shown both as text and as an image of the formatted PDF, with the same content displayed in a clean, formatted layout with consistent spacing and typography. The document consists of a single page containing this sample text.\n"
+     ]
+    }
+   ],
+   "source": [
+    "message = {\n",
+    "    \"role\": \"user\",\n",
+    "    \"content\": [\n",
+    "        {\n",
+    "            \"type\": \"text\",\n",
+    "            \"text\": \"Describe the document:\",\n",
+    "        },\n",
+    "        {\n",
+    "            \"type\": \"file\",\n",
+    "            # highlight-start\n",
+    "            \"source_type\": \"url\",\n",
+    "            \"url\": pdf_url,\n",
+    "            # highlight-end\n",
+    "        },\n",
+    "    ],\n",
+    "}\n",
+    "response = llm.invoke([message])\n",
+    "print(response.text())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1e661c26-e537-4721-8268-42c0861cb1e6",
+   "metadata": {},
+   "source": [
+    "## Audio\n",
+    "\n",
+    "Some providers (including [OpenAI](/docs/integrations/chat/openai/) and\n",
+    "[Google Gemini](/docs/integrations/chat/google_generative_ai/)) will accept audio inputs.\n",
+    "\n",
+    "### Audio from base64 data\n",
+    "\n",
+    "To pass audio in-line, format them as content blocks of the following form:\n",
+    "\n",
+    "```python\n",
+    "{\n",
+    "    \"type\": \"audio\",\n",
+    "    \"source_type\": \"base64\",\n",
+    "    \"mime_type\": \"audio/wav\",  # or appropriate mime-type\n",
+    "    \"data\": \"<base64 data string>\",\n",
+    "}\n",
+    "```\n",
+    "\n",
+    "Example:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "a0b91b29-dbd6-4c94-8f24-05471adc7598",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The audio appears to consist primarily of bird sounds, specifically bird vocalizations like chirping and possibly other bird songs.\n"
+     ]
+    }
+   ],
+   "source": [
+    "import base64\n",
+    "\n",
+    "import httpx\n",
+    "from langchain.chat_models import init_chat_model\n",
+    "\n",
+    "# Fetch audio data\n",
+    "audio_url = \"https://upload.wikimedia.org/wikipedia/commons/3/3d/Alcal%C3%A1_de_Henares_%28RPS_13-04-2024%29_canto_de_ruise%C3%B1or_%28Luscinia_megarhynchos%29_en_el_Soto_del_Henares.wav\"\n",
+    "audio_data = base64.b64encode(httpx.get(audio_url).content).decode(\"utf-8\")\n",
+    "\n",
+    "\n",
+    "# Pass to LLM\n",
+    "llm = init_chat_model(\"google_genai:gemini-2.0-flash-001\")\n",
+    "\n",
+    "message = {\n",
+    "    \"role\": \"user\",\n",
+    "    \"content\": [\n",
+    "        {\n",
+    "            \"type\": \"text\",\n",
+    "            \"text\": \"Describe this audio:\",\n",
+    "        },\n",
+    "        # highlight-start\n",
+    "        {\n",
+    "            \"type\": \"audio\",\n",
+    "            \"source_type\": \"base64\",\n",
+    "            \"data\": audio_data,\n",
+    "            \"mime_type\": \"audio/wav\",\n",
+    "        },\n",
+    "        # highlight-end\n",
+    "    ],\n",
+    "}\n",
+    "response = llm.invoke([message])\n",
+    "print(response.text())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "92f55a6c-2e4a-4175-8444-8b9aacd6a13e",
+   "metadata": {},
+   "source": [
+    "## Provider-specific parameters\n",
+    "\n",
+    "Some providers will support or require additional fields on content blocks containing multimodal data.\n",
+    "For example, Anthropic lets you specify [caching](/docs/integrations/chat/anthropic/#prompt-caching) of\n",
+    "specific content to reduce token consumption.\n",
+    "\n",
+    "To use these fields, you can:\n",
+    "\n",
+    "1. Store them on directly on the content block; or\n",
+    "2. Use the native format supported by each provider (see [chat model integrations](/docs/integrations/chat/) for detail).\n",
+    "\n",
+    "We show three examples below.\n",
+    "\n",
+    "### Example: Anthropic prompt caching"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "83593b9d-a8d3-4c99-9dac-64e0a9d397cb",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The image shows a beautiful, clear day with partly cloudy skies. The sky is a vibrant blue with wispy, white cirrus clouds stretching across it. The lighting suggests it's during daylight hours, possibly late afternoon or early evening given the warm, golden quality of the light on the grass. The weather appears calm with no signs of wind (the grass looks relatively still) and no threatening weather conditions. It's the kind of perfect weather you'd want for a walk along this wooden boardwalk through the marshland or grassland area.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "{'input_tokens': 1586,\n",
+       " 'output_tokens': 117,\n",
+       " 'total_tokens': 1703,\n",
+       " 'input_token_details': {'cache_read': 0, 'cache_creation': 1582}}"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "llm = init_chat_model(\"anthropic:claude-3-5-sonnet-latest\")\n",
+    "\n",
+    "message = {\n",
+    "    \"role\": \"user\",\n",
+    "    \"content\": [\n",
+    "        {\n",
+    "            \"type\": \"text\",\n",
+    "            \"text\": \"Describe the weather in this image:\",\n",
+    "        },\n",
+    "        {\n",
+    "            \"type\": \"image\",\n",
+    "            \"source_type\": \"url\",\n",
+    "            \"url\": image_url,\n",
+    "            # highlight-next-line\n",
+    "            \"cache_control\": {\"type\": \"ephemeral\"},\n",
+    "        },\n",
+    "    ],\n",
+    "}\n",
+    "response = llm.invoke([message])\n",
+    "print(response.text())\n",
+    "response.usage_metadata"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "9bbf578e-794a-4dc0-a469-78c876ccd4a3",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Clear blue skies, wispy clouds.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "{'input_tokens': 1716,\n",
+       " 'output_tokens': 12,\n",
+       " 'total_tokens': 1728,\n",
+       " 'input_token_details': {'cache_read': 1582, 'cache_creation': 0}}"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "next_message = {\n",
+    "    \"role\": \"user\",\n",
+    "    \"content\": [\n",
+    "        {\n",
+    "            \"type\": \"text\",\n",
+    "            \"text\": \"Summarize that in 5 words.\",\n",
+    "        }\n",
+    "    ],\n",
+    "}\n",
+    "response = llm.invoke([message, response, next_message])\n",
+    "print(response.text())\n",
+    "response.usage_metadata"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "915b9443-5964-43b8-bb08-691c1ba59065",
+   "metadata": {},
+   "source": [
+    "### Example: Anthropic citations"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "ea7707a1-5660-40a1-a10f-0df48a028689",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'citations': [{'cited_text': 'Sample PDF\\r\\nThis is a simple PDF file. Fun fun fun.\\r\\n',\n",
+       "    'document_index': 0,\n",
+       "    'document_title': None,\n",
+       "    'end_page_number': 2,\n",
+       "    'start_page_number': 1,\n",
+       "    'type': 'page_location'}],\n",
+       "  'text': 'Simple PDF file: fun fun',\n",
+       "  'type': 'text'}]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "message = {\n",
+    "    \"role\": \"user\",\n",
+    "    \"content\": [\n",
+    "        {\n",
+    "            \"type\": \"text\",\n",
+    "            \"text\": \"Generate a 5 word summary of this document.\",\n",
+    "        },\n",
+    "        {\n",
+    "            \"type\": \"file\",\n",
+    "            \"source_type\": \"base64\",\n",
+    "            \"data\": pdf_data,\n",
+    "            \"mime_type\": \"application/pdf\",\n",
+    "            # highlight-next-line\n",
+    "            \"citations\": {\"enabled\": True},\n",
+    "        },\n",
+    "    ],\n",
+    "}\n",
+    "response = llm.invoke([message])\n",
+    "response.content"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e26991eb-e769-41f4-b6e0-63d81f2c7d67",
+   "metadata": {},
+   "source": [
+    "### Example: OpenAI file names\n",
+    "\n",
+    "OpenAI requires that PDF documents be associated with file names:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "ae076c9b-ff8f-461d-9349-250f396c9a25",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The document is a sample PDF file containing placeholder text. It consists of one page, titled \"Sample PDF\". The content is a mixture of English and the commonly used filler text \"Lorem ipsum dolor sit amet...\" and its extensions, which are often used in publishing and web design as generic text to demonstrate font, layout, and other visual elements.\n",
+      "\n",
+      "**Key points about the document:**\n",
+      "- Length: 1 page\n",
+      "- Purpose: Demonstrative/sample content\n",
+      "- Content: No substantive or meaningful information, just demonstration text in paragraph form\n",
+      "- Language: English (with the Latin-like \"Lorem Ipsum\" text used for layout purposes)\n",
+      "\n",
+      "There are no charts, tables, diagrams, or images on the page—only plain text. The document serves as an example of what a PDF file looks like rather than providing actual, useful content.\n"
+     ]
+    }
+   ],
+   "source": [
+    "llm = init_chat_model(\"openai:gpt-4.1\")\n",
+    "\n",
+    "message = {\n",
+    "    \"role\": \"user\",\n",
+    "    \"content\": [\n",
+    "        {\n",
+    "            \"type\": \"text\",\n",
+    "            \"text\": \"Describe the document:\",\n",
+    "        },\n",
+    "        {\n",
+    "            \"type\": \"file\",\n",
+    "            \"source_type\": \"base64\",\n",
+    "            \"data\": pdf_data,\n",
+    "            \"mime_type\": \"application/pdf\",\n",
+    "            # highlight-next-line\n",
+    "            \"filename\": \"my-file\",\n",
+    "        },\n",
+    "    ],\n",
+    "}\n",
+    "response = llm.invoke([message])\n",
+    "print(response.text())"
    ]
   },
   {
@@ -167,16 +652,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
-   "id": "cd22ea82-2f93-46f9-9f7a-6aaf479fcaa9",
+   "execution_count": 4,
+   "id": "0f68cce7-350b-4cde-bc40-d3a169551fc3",
    "metadata": {},
    "outputs": [
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[{'name': 'weather_tool', 'args': {'weather': 'sunny'}, 'id': 'call_BSX4oq4SKnLlp2WlzDhToHBr'}]\n"
-     ]
+     "data": {
+      "text/plain": [
+       "[{'name': 'weather_tool',\n",
+       "  'args': {'weather': 'sunny'},\n",
+       "  'id': 'toolu_01G6JgdkhwggKcQKfhXZQPjf',\n",
+       "  'type': 'tool_call'}]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
     }
    ],
    "source": [
@@ -191,16 +682,17 @@
     "    pass\n",
     "\n",
     "\n",
-    "model_with_tools = model.bind_tools([weather_tool])\n",
+    "llm_with_tools = llm.bind_tools([weather_tool])\n",
     "\n",
-    "message = HumanMessage(\n",
-    "    content=[\n",
-    "        {\"type\": \"text\", \"text\": \"describe the weather in this image\"},\n",
-    "        {\"type\": \"image_url\", \"image_url\": {\"url\": image_url}},\n",
+    "message = {\n",
+    "    \"role\": \"user\",\n",
+    "    \"content\": [\n",
+    "        {\"type\": \"text\", \"text\": \"Describe the weather in this image:\"},\n",
+    "        {\"type\": \"image\", \"source_type\": \"url\", \"url\": image_url},\n",
     "    ],\n",
-    ")\n",
-    "response = model_with_tools.invoke([message])\n",
-    "print(response.tool_calls)"
+    "}\n",
+    "response = llm_with_tools.invoke([message])\n",
+    "response.tool_calls"
    ]
   }
  ],
@@ -220,7 +712,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/how_to/multimodal_prompts.ipynb

@@ -9,157 +9,148 @@
     "\n",
     "Here we demonstrate how to use prompt templates to format [multimodal](/docs/concepts/multimodality/) inputs to models. \n",
     "\n",
-    "In this example we will ask a [model](/docs/concepts/chat_models/#multimodality) to describe an image."
+    "To use prompt templates in the context of multimodal data, we can templatize elements of the corresponding content block.\n",
+    "For example, below we define a prompt that takes a URL for an image as a parameter:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
-   "id": "0d9fd81a-b7f0-445a-8e3d-cfc2d31fdd59",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import base64\n",
-    "\n",
-    "import httpx\n",
-    "\n",
-    "image_url = \"https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg\"\n",
-    "image_data = base64.b64encode(httpx.get(image_url).content).decode(\"utf-8\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 1,
    "id": "2671f995",
    "metadata": {},
    "outputs": [],
    "source": [
     "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "model = ChatOpenAI(model=\"gpt-4o\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "4ee35e4f",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "prompt = ChatPromptTemplate.from_messages(\n",
+    "# Define prompt\n",
+    "prompt = ChatPromptTemplate(\n",
     "    [\n",
-    "        (\"system\", \"Describe the image provided\"),\n",
-    "        (\n",
-    "            \"user\",\n",
-    "            [\n",
+    "        {\n",
+    "            \"role\": \"system\",\n",
+    "            \"content\": \"Describe the image provided.\",\n",
+    "        },\n",
+    "        {\n",
+    "            \"role\": \"user\",\n",
+    "            \"content\": [\n",
     "                {\n",
-    "                    \"type\": \"image_url\",\n",
-    "                    \"image_url\": {\"url\": \"data:image/jpeg;base64,{image_data}\"},\n",
-    "                }\n",
+    "                    \"type\": \"image\",\n",
+    "                    \"source_type\": \"url\",\n",
+    "                    # highlight-next-line\n",
+    "                    \"url\": \"{image_url}\",\n",
+    "                },\n",
     "            ],\n",
-    "        ),\n",
+    "        },\n",
     "    ]\n",
     ")"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "089f75c2",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "chain = prompt | model"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "02744b06",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "The image depicts a sunny day with a beautiful blue sky filled with scattered white clouds. The sky has varying shades of blue, ranging from a deeper hue near the horizon to a lighter, almost pale blue higher up. The white clouds are fluffy and scattered across the expanse of the sky, creating a peaceful and serene atmosphere. The lighting and cloud patterns suggest pleasant weather conditions, likely during the daytime hours on a mild, sunny day in an outdoor natural setting.\n"
-     ]
-    }
-   ],
-   "source": [
-    "response = chain.invoke({\"image_data\": image_data})\n",
-    "print(response.content)"
-   ]
-  },
   {
    "cell_type": "markdown",
-   "id": "e9b9ebf6",
+   "id": "f75d2e26-5b9a-4d5f-94a7-7f98f5666f6d",
    "metadata": {},
    "source": [
-    "We can also pass in multiple images."
+    "Let's use this prompt to pass an image to a [chat model](/docs/concepts/chat_models/#multimodality):"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
-   "id": "02190ee3",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\"system\", \"compare the two pictures provided\"),\n",
-    "        (\n",
-    "            \"user\",\n",
-    "            [\n",
-    "                {\n",
-    "                    \"type\": \"image_url\",\n",
-    "                    \"image_url\": {\"url\": \"data:image/jpeg;base64,{image_data1}\"},\n",
-    "                },\n",
-    "                {\n",
-    "                    \"type\": \"image_url\",\n",
-    "                    \"image_url\": {\"url\": \"data:image/jpeg;base64,{image_data2}\"},\n",
-    "                },\n",
-    "            ],\n",
-    "        ),\n",
-    "    ]\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "42af057b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "chain = prompt | model"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "id": "513abe00",
+   "execution_count": 2,
+   "id": "5df2e558-321d-4cf7-994e-2815ac37e704",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "The two images provided are identical. Both images feature a wooden boardwalk path extending through a lush green field under a bright blue sky with some clouds. The perspective, colors, and elements in both images are exactly the same.\n"
+      "This image shows a beautiful wooden boardwalk cutting through a lush green wetland or marsh area. The boardwalk extends straight ahead toward the horizon, creating a strong leading line through the composition. On either side, tall green grasses sway in what appears to be a summer or late spring setting. The sky is particularly striking, with wispy cirrus clouds streaking across a vibrant blue background. In the distance, you can see a tree line bordering the wetland area. The lighting suggests this may be during \"golden hour\" - either early morning or late afternoon - as there's a warm, gentle quality to the light that's illuminating the scene. The wooden planks of the boardwalk appear well-maintained and provide safe passage through what would otherwise be difficult terrain to traverse. It's the kind of scene you might find in a nature preserve or wildlife refuge designed to give visitors access to observe wetland ecosystems while protecting the natural environment.\n"
      ]
     }
    ],
    "source": [
-    "response = chain.invoke({\"image_data1\": image_data, \"image_data2\": image_data})\n",
-    "print(response.content)"
+    "from langchain.chat_models import init_chat_model\n",
+    "\n",
+    "llm = init_chat_model(\"anthropic:claude-3-5-sonnet-latest\")\n",
+    "\n",
+    "url = \"https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg\"\n",
+    "\n",
+    "chain = prompt | llm\n",
+    "response = chain.invoke({\"image_url\": url})\n",
+    "print(response.text())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f4cfdc50-4a9f-4888-93b4-af697366b0f3",
+   "metadata": {},
+   "source": [
+    "Note that we can templatize arbitrary elements of the content block:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "53c88ebb-dd57-40c8-8542-b2c916706653",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prompt = ChatPromptTemplate(\n",
+    "    [\n",
+    "        {\n",
+    "            \"role\": \"system\",\n",
+    "            \"content\": \"Describe the image provided.\",\n",
+    "        },\n",
+    "        {\n",
+    "            \"role\": \"user\",\n",
+    "            \"content\": [\n",
+    "                {\n",
+    "                    \"type\": \"image\",\n",
+    "                    \"source_type\": \"base64\",\n",
+    "                    \"mime_type\": \"{image_mime_type}\",\n",
+    "                    \"data\": \"{image_data}\",\n",
+    "                    \"cache_control\": {\"type\": \"{cache_type}\"},\n",
+    "                },\n",
+    "            ],\n",
+    "        },\n",
+    "    ]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "25e4829e-0073-49a8-9669-9f43e5778383",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "This image shows a beautiful wooden boardwalk cutting through a lush green marsh or wetland area. The boardwalk extends straight ahead toward the horizon, creating a strong leading line in the composition. The surrounding vegetation consists of tall grass and reeds in vibrant green hues, with some bushes and trees visible in the background. The sky is particularly striking, featuring a bright blue color with wispy white clouds streaked across it. The lighting suggests this photo was taken during the \"golden hour\" - either early morning or late afternoon - giving the scene a warm, peaceful quality. The raised wooden path provides accessible access through what would otherwise be difficult terrain to traverse, allowing visitors to experience and appreciate this natural environment.\n"
+     ]
+    }
+   ],
+   "source": [
+    "import base64\n",
+    "\n",
+    "import httpx\n",
+    "\n",
+    "image_data = base64.b64encode(httpx.get(url).content).decode(\"utf-8\")\n",
+    "\n",
+    "chain = prompt | llm\n",
+    "response = chain.invoke(\n",
+    "    {\n",
+    "        \"image_data\": image_data,\n",
+    "        \"image_mime_type\": \"image/jpeg\",\n",
+    "        \"cache_type\": \"ephemeral\",\n",
+    "    }\n",
+    ")\n",
+    "print(response.text())"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "ea8152c3",
+   "id": "424defe8-d85c-4e45-a88d-bf6f910d5ebb",
    "metadata": {},
    "outputs": [],
    "source": []
@@ -181,7 +172,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.1"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/how_to/qa_citations.ipynb

@@ -127,7 +127,7 @@
    "id": "c89e2045-9244-43e6-bf3f-59af22658529",
    "metadata": {},
    "source": [
-    "Now that we've got a [model](/docs/concepts/chat_models/), [retriver](/docs/concepts/retrievers/) and [prompt](/docs/concepts/prompt_templates/), let's chain them all together. Following the how-to guide on [adding citations](/docs/how_to/qa_citations) to a RAG application, we'll make it so our chain returns both the answer and the retrieved Documents. This uses the same [LangGraph](/docs/concepts/architecture/#langgraph) implementation as in the [RAG Tutorial](/docs/tutorials/rag)."
+    "Now that we've got a [model](/docs/concepts/chat_models/), [retriever](/docs/concepts/retrievers/) and [prompt](/docs/concepts/prompt_templates/), let's chain them all together. Following the how-to guide on [adding citations](/docs/how_to/qa_citations) to a RAG application, we'll make it so our chain returns both the answer and the retrieved Documents. This uses the same [LangGraph](/docs/concepts/architecture/#langgraph) implementation as in the [RAG Tutorial](/docs/tutorials/rag)."
    ]
   },
   {

docs/docs/how_to/query_multiple_queries.ipynb

@@ -270,7 +270,7 @@
    "source": [
     "## Retrieval with query analysis\n",
     "\n",
-    "So how would we include this in a chain? One thing that will make this a lot easier is if we call our retriever asyncronously - this will let us loop over the queries and not get blocked on the response time."
+    "So how would we include this in a chain? One thing that will make this a lot easier is if we call our retriever asynchronously - this will let us loop over the queries and not get blocked on the response time."
    ]
   },
   {

docs/docs/how_to/summarize_map_reduce.ipynb

@@ -24,7 +24,7 @@
     "\n",
     "Note that the map step is typically parallelized over the input documents. This strategy is especially effective when understanding of a sub-document does not rely on preceeding context. For example, when summarizing a corpus of many, shorter documents.\n",
     "\n",
-    "[LangGraph](https://langchain-ai.github.io/langgraph/), built on top of `langchain-core`, suports [map-reduce](https://langchain-ai.github.io/langgraph/how-tos/map-reduce/) workflows and is well-suited to this problem:\n",
+    "[LangGraph](https://langchain-ai.github.io/langgraph/), built on top of `langchain-core`, supports [map-reduce](https://langchain-ai.github.io/langgraph/how-tos/map-reduce/) workflows and is well-suited to this problem:\n",
     "\n",
     "- LangGraph allows for individual steps (such as successive summarizations) to be streamed, allowing for greater control of execution;\n",
     "- LangGraph's [checkpointing](https://langchain-ai.github.io/langgraph/how-tos/persistence/) supports error recovery, extending with human-in-the-loop workflows, and easier incorporation into conversational applications.\n",

docs/docs/how_to/tools_human.ipynb

@@ -15,7 +15,7 @@
     "\n",
     "To build a production application, you will need to do more work to keep track of application state appropriately.\n",
     "\n",
-    "We recommend using `langgraph` for powering such a capability. For more details, please see this [guide](https://langchain-ai.github.io/langgraph/how-tos/human-in-the-loop/).\n",
+    "We recommend using `langgraph` for powering such a capability. For more details, please see this [guide](https://langchain-ai.github.io/langgraph/concepts/human_in_the_loop/).\n",
     ":::\n"
    ]
   },
@@ -209,7 +209,7 @@
    "metadata": {},
    "outputs": [
     {
-     "name": "stdin",
+     "name": "stdout",
      "output_type": "stream",
      "text": [
       "Do you approve of the following tool invocations\n",
@@ -252,7 +252,7 @@
    "metadata": {},
    "outputs": [
     {
-     "name": "stdin",
+     "name": "stdout",
      "output_type": "stream",
      "text": [
       "Do you approve of the following tool invocations\n",

docs/docs/integrations/caches/singlestore_semantic_cache.ipynb

@@ -0,0 +1,118 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "e49f1e0d",
+   "metadata": {},
+   "source": [
+    "# SingleStoreSemanticCache\n",
+    "\n",
+    "This example demonstrates how to get started with the SingleStore semantic cache.\n",
+    "\n",
+    "### Integration Overview\n",
+    "\n",
+    "`SingleStoreSemanticCache` leverages `SingleStoreVectorStore` to cache LLM responses directly in a SingleStore database, enabling efficient semantic retrieval and reuse of results.\n",
+    "\n",
+    "### Integration details\n",
+    "\n",
+    "\n",
+    "\n",
+    "| Class | Package | JS support |\n",
+    "| :--- | :--- |  :---: |\n",
+    "| SingleStoreSemanticCache | langchain_singlestore | ❌ | "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0730d6a1-c893-4840-9817-5e5251676d5d",
+   "metadata": {},
+   "source": [
+    "## Installation\n",
+    "\n",
+    "This cache lives in the `langchain-singlestore` package:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU langchain-singlestore"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5c5f2839-4020-424e-9fc9-07777eede442",
+   "metadata": {},
+   "source": [
+    "## Usage"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "51a60dbe-9f2e-4e04-bb62-23968f17164a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.globals import set_llm_cache\n",
+    "from langchain_singlestore import SingleStoreSemanticCache\n",
+    "\n",
+    "set_llm_cache(\n",
+    "    SingleStoreSemanticCache(\n",
+    "        embedding=YourEmbeddings(),\n",
+    "        host=\"root:pass@localhost:3306/db\",\n",
+    "    )\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cddda8ef",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%time\n",
+    "# The first time, it is not yet in cache, so it should take longer\n",
+    "llm.invoke(\"Tell me a joke\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c474168f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%time\n",
+    "# The second time, while not a direct hit, the question is semantically similar to the original question,\n",
+    "# so it uses the cached result!\n",
+    "llm.invoke(\"Tell me one joke\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "langchain-singlestore-BD1RbQ07-py3.11",
+   "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": "3.11.11"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/integrations/chat/ai21.ipynb

@@ -1,318 +1,316 @@
 {
- "cells": [
-  {
-   "cell_type": "raw",
-   "id": "4cebeec0",
-   "metadata": {},
-   "source": [
-    "---\n",
-    "sidebar_label: AI21 Labs\n",
-    "---"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "e49f1e0d",
-   "metadata": {},
-   "source": [
-    "# ChatAI21\n",
-    "\n",
-    "## Overview\n",
-    "\n",
-    "This notebook covers how to get started with AI21 chat models.\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",
-    "\n",
-    "### Integration details\n",
-    "\n",
-    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/docs/integrations/chat/__package_name_short_snake__) | Package downloads | Package latest |\n",
-    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
-    "| [ChatAI21](https://python.langchain.com/api_reference/ai21/chat_models/langchain_ai21.chat_models.ChatAI21.html#langchain_ai21.chat_models.ChatAI21) | [langchain-ai21](https://python.langchain.com/api_reference/ai21/index.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-ai21?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-ai21?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",
-    "\n",
-    "## Setup"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2b4f3e15",
-   "metadata": {},
-   "source": [
-    "### Credentials\n",
-    "\n",
-    "We'll need to get an [AI21 API key](https://docs.ai21.com/) and set the `AI21_API_KEY` environment variable:\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "62e0dbc3",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "from getpass import getpass\n",
-    "\n",
-    "if \"AI21_API_KEY\" not in os.environ:\n",
-    "    os.environ[\"AI21_API_KEY\"] = getpass()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "f6844fff-3702-4489-ab74-732f69f3b9d7",
-   "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": "7c2e19d3-7c58-4470-9e1a-718b27a32056",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\"\n",
-    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "98e22f31-8acc-42d6-916d-415d1263c56e",
-   "metadata": {},
-   "source": [
-    "### Installation"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "f9699cd9-58f2-450e-aa64-799e66906c0f",
-   "metadata": {},
-   "source": [
-    "!pip install -qU langchain-ai21"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "4828829d3da430ce",
-   "metadata": {
-    "collapsed": false,
-    "jupyter": {
-     "outputs_hidden": false
+  "cells": [
+    {
+      "cell_type": "raw",
+      "id": "4cebeec0",
+      "metadata": {},
+      "source": [
+        "---\n",
+        "sidebar_label: AI21 Labs\n",
+        "---"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "e49f1e0d",
+      "metadata": {},
+      "source": [
+        "# ChatAI21\n",
+        "\n",
+        "## Overview\n",
+        "\n",
+        "This notebook covers how to get started with AI21 chat models.\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",
+        "\n",
+        "### Integration details\n",
+        "\n",
+        "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/docs/integrations/chat/__package_name_short_snake__) | Package downloads | Package latest |\n",
+        "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+        "| [ChatAI21](https://python.langchain.com/api_reference/ai21/chat_models/langchain_ai21.chat_models.ChatAI21.html#langchain_ai21.chat_models.ChatAI21) | [langchain-ai21](https://python.langchain.com/api_reference/ai21/index.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-ai21?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-ai21?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",
+        "\n",
+        "## Setup"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "2b4f3e15",
+      "metadata": {},
+      "source": [
+        "### Credentials\n",
+        "\n",
+        "We'll need to get an [AI21 API key](https://docs.ai21.com/) and set the `AI21_API_KEY` environment variable:\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "62e0dbc3",
+      "metadata": {
+        "tags": []
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "from getpass import getpass\n",
+        "\n",
+        "if \"AI21_API_KEY\" not in os.environ:\n",
+        "    os.environ[\"AI21_API_KEY\"] = getpass()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "f6844fff-3702-4489-ab74-732f69f3b9d7",
+      "metadata": {},
+      "source": "To enable automated tracing of your model calls, set your [LangSmith](https://docs.smith.langchain.com/) API key:"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "7c2e19d3-7c58-4470-9e1a-718b27a32056",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# os.environ[\"LANGSMITH_TRACING\"] = \"true\"\n",
+        "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "98e22f31-8acc-42d6-916d-415d1263c56e",
+      "metadata": {},
+      "source": [
+        "### Installation"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "f9699cd9-58f2-450e-aa64-799e66906c0f",
+      "metadata": {},
+      "source": [
+        "!pip install -qU langchain-ai21"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "4828829d3da430ce",
+      "metadata": {
+        "collapsed": false,
+        "jupyter": {
+          "outputs_hidden": false
+        }
+      },
+      "source": [
+        "## Instantiation\n",
+        "\n",
+        "Now we can instantiate our model object and generate chat completions:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "c40756fb-cbf8-4d44-a293-3989d707237e",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from langchain_ai21 import ChatAI21\n",
+        "\n",
+        "llm = ChatAI21(model=\"jamba-instruct\", temperature=0)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "2bdc5d68-2a19-495e-8c04-d11adc86d3ae",
+      "metadata": {},
+      "source": [
+        "## Invocation"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "46b982dc-5d8a-46da-a711-81c03ccd6adc",
+      "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",
+        "ai_msg = llm.invoke(messages)\n",
+        "ai_msg"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "10a30f84-b531-4fd5-8b5b-91512fbdc75b",
+      "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,
+      "id": "39353473fce5dd2e",
+      "metadata": {
+        "collapsed": false,
+        "jupyter": {
+          "outputs_hidden": false
+        }
+      },
+      "outputs": [],
+      "source": [
+        "from langchain_core.prompts import ChatPromptTemplate\n",
+        "\n",
+        "prompt = ChatPromptTemplate(\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": "39c0ccd229927eab",
+      "metadata": {},
+      "source": "# Tool Calls / Function Calling"
+    },
+    {
+      "cell_type": "markdown",
+      "id": "2bf6b40be07fe2d4",
+      "metadata": {},
+      "source": "This example shows how to use tool calling with AI21 models:"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "a181a28df77120fb",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "from getpass import getpass\n",
+        "\n",
+        "from langchain_ai21.chat_models import ChatAI21\n",
+        "from langchain_core.messages import HumanMessage, SystemMessage, ToolMessage\n",
+        "from langchain_core.tools import tool\n",
+        "from langchain_core.utils.function_calling import convert_to_openai_tool\n",
+        "\n",
+        "if \"AI21_API_KEY\" not in os.environ:\n",
+        "    os.environ[\"AI21_API_KEY\"] = getpass()\n",
+        "\n",
+        "\n",
+        "@tool\n",
+        "def get_weather(location: str, date: str) -> str:\n",
+        "    \"\"\"“Provide the weather for the specified location on the given date.”\"\"\"\n",
+        "    if location == \"New York\" and date == \"2024-12-05\":\n",
+        "        return \"25 celsius\"\n",
+        "    elif location == \"New York\" and date == \"2024-12-06\":\n",
+        "        return \"27 celsius\"\n",
+        "    elif location == \"London\" and date == \"2024-12-05\":\n",
+        "        return \"22 celsius\"\n",
+        "    return \"32 celsius\"\n",
+        "\n",
+        "\n",
+        "llm = ChatAI21(model=\"jamba-1.5-mini\")\n",
+        "\n",
+        "llm_with_tools = llm.bind_tools([convert_to_openai_tool(get_weather)])\n",
+        "\n",
+        "chat_messages = [\n",
+        "    SystemMessage(\n",
+        "        content=\"You are a helpful assistant. You can use the provided tools \"\n",
+        "        \"to assist with various tasks and provide accurate information\"\n",
+        "    )\n",
+        "]\n",
+        "\n",
+        "human_messages = [\n",
+        "    HumanMessage(\n",
+        "        content=\"What is the forecast for the weather in New York on December 5, 2024?\"\n",
+        "    ),\n",
+        "    HumanMessage(content=\"And what about the 2024-12-06?\"),\n",
+        "    HumanMessage(content=\"OK, thank you.\"),\n",
+        "    HumanMessage(content=\"What is the expected weather in London on December 5, 2024?\"),\n",
+        "]\n",
+        "\n",
+        "\n",
+        "for human_message in human_messages:\n",
+        "    print(f\"User: {human_message.content}\")\n",
+        "    chat_messages.append(human_message)\n",
+        "    response = llm_with_tools.invoke(chat_messages)\n",
+        "    chat_messages.append(response)\n",
+        "    if response.tool_calls:\n",
+        "        tool_call = response.tool_calls[0]\n",
+        "        if tool_call[\"name\"] == \"get_weather\":\n",
+        "            weather = get_weather.invoke(\n",
+        "                {\n",
+        "                    \"location\": tool_call[\"args\"][\"location\"],\n",
+        "                    \"date\": tool_call[\"args\"][\"date\"],\n",
+        "                }\n",
+        "            )\n",
+        "            chat_messages.append(\n",
+        "                ToolMessage(content=weather, tool_call_id=tool_call[\"id\"])\n",
+        "            )\n",
+        "            llm_answer = llm_with_tools.invoke(chat_messages)\n",
+        "            print(f\"Assistant: {llm_answer.content}\")\n",
+        "    else:\n",
+        "        print(f\"Assistant: {response.content}\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "e79de691-9dd6-4697-b57e-59a4a3cc073a",
+      "metadata": {},
+      "source": [
+        "## API reference\n",
+        "\n",
+        "For detailed documentation of all ChatAI21 features and configurations head to the API reference: https://python.langchain.com/api_reference/ai21/chat_models/langchain_ai21.chat_models.ChatAI21.html"
+      ]
     }
-   },
-   "source": [
-    "## Instantiation\n",
-    "\n",
-    "Now we can instantiate our model object and generate chat completions:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "c40756fb-cbf8-4d44-a293-3989d707237e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_ai21 import ChatAI21\n",
-    "\n",
-    "llm = ChatAI21(model=\"jamba-instruct\", temperature=0)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2bdc5d68-2a19-495e-8c04-d11adc86d3ae",
-   "metadata": {},
-   "source": [
-    "## Invocation"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "46b982dc-5d8a-46da-a711-81c03ccd6adc",
-   "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",
-    "ai_msg = llm.invoke(messages)\n",
-    "ai_msg"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "10a30f84-b531-4fd5-8b5b-91512fbdc75b",
-   "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,
-   "id": "39353473fce5dd2e",
-   "metadata": {
-    "collapsed": false,
-    "jupyter": {
-     "outputs_hidden": false
+  ],
+  "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"
     }
-   },
-   "outputs": [],
-   "source": [
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "\n",
-    "prompt = ChatPromptTemplate(\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": "39c0ccd229927eab",
-   "metadata": {},
-   "source": "# Tool Calls / Function Calling"
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2bf6b40be07fe2d4",
-   "metadata": {},
-   "source": "This example shows how to use tool calling with AI21 models:"
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "a181a28df77120fb",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "from getpass import getpass\n",
-    "\n",
-    "from langchain_ai21.chat_models import ChatAI21\n",
-    "from langchain_core.messages import HumanMessage, SystemMessage, ToolMessage\n",
-    "from langchain_core.tools import tool\n",
-    "from langchain_core.utils.function_calling import convert_to_openai_tool\n",
-    "\n",
-    "if \"AI21_API_KEY\" not in os.environ:\n",
-    "    os.environ[\"AI21_API_KEY\"] = getpass()\n",
-    "\n",
-    "\n",
-    "@tool\n",
-    "def get_weather(location: str, date: str) -> str:\n",
-    "    \"\"\"“Provide the weather for the specified location on the given date.”\"\"\"\n",
-    "    if location == \"New York\" and date == \"2024-12-05\":\n",
-    "        return \"25 celsius\"\n",
-    "    elif location == \"New York\" and date == \"2024-12-06\":\n",
-    "        return \"27 celsius\"\n",
-    "    elif location == \"London\" and date == \"2024-12-05\":\n",
-    "        return \"22 celsius\"\n",
-    "    return \"32 celsius\"\n",
-    "\n",
-    "\n",
-    "llm = ChatAI21(model=\"jamba-1.5-mini\")\n",
-    "\n",
-    "llm_with_tools = llm.bind_tools([convert_to_openai_tool(get_weather)])\n",
-    "\n",
-    "chat_messages = [\n",
-    "    SystemMessage(\n",
-    "        content=\"You are a helpful assistant. You can use the provided tools \"\n",
-    "        \"to assist with various tasks and provide accurate information\"\n",
-    "    )\n",
-    "]\n",
-    "\n",
-    "human_messages = [\n",
-    "    HumanMessage(\n",
-    "        content=\"What is the forecast for the weather in New York on December 5, 2024?\"\n",
-    "    ),\n",
-    "    HumanMessage(content=\"And what about the 2024-12-06?\"),\n",
-    "    HumanMessage(content=\"OK, thank you.\"),\n",
-    "    HumanMessage(content=\"What is the expected weather in London on December 5, 2024?\"),\n",
-    "]\n",
-    "\n",
-    "\n",
-    "for human_message in human_messages:\n",
-    "    print(f\"User: {human_message.content}\")\n",
-    "    chat_messages.append(human_message)\n",
-    "    response = llm_with_tools.invoke(chat_messages)\n",
-    "    chat_messages.append(response)\n",
-    "    if response.tool_calls:\n",
-    "        tool_call = response.tool_calls[0]\n",
-    "        if tool_call[\"name\"] == \"get_weather\":\n",
-    "            weather = get_weather.invoke(\n",
-    "                {\n",
-    "                    \"location\": tool_call[\"args\"][\"location\"],\n",
-    "                    \"date\": tool_call[\"args\"][\"date\"],\n",
-    "                }\n",
-    "            )\n",
-    "            chat_messages.append(\n",
-    "                ToolMessage(content=weather, tool_call_id=tool_call[\"id\"])\n",
-    "            )\n",
-    "            llm_answer = llm_with_tools.invoke(chat_messages)\n",
-    "            print(f\"Assistant: {llm_answer.content}\")\n",
-    "    else:\n",
-    "        print(f\"Assistant: {response.content}\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "e79de691-9dd6-4697-b57e-59a4a3cc073a",
-   "metadata": {},
-   "source": [
-    "## API reference\n",
-    "\n",
-    "For detailed documentation of all ChatAI21 features and configurations head to the API reference: https://python.langchain.com/api_reference/ai21/chat_models/langchain_ai21.chat_models.ChatAI21.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
+  "nbformat": 4,
+  "nbformat_minor": 5
 }

docs/docs/integrations/chat/azure_chat_openai.ipynb

@@ -1,349 +1,347 @@
 {
- "cells": [
-  {
-   "cell_type": "raw",
-   "id": "afaf8039",
-   "metadata": {},
-   "source": [
-    "---\n",
-    "sidebar_label: Azure OpenAI\n",
-    "---"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "e49f1e0d",
-   "metadata": {},
-   "source": [
-    "# AzureChatOpenAI\n",
-    "\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://python.langchain.com/api_reference/openai/chat_models/langchain_openai.chat_models.azure.AzureChatOpenAI.html).\n",
-    "\n",
-    "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/docs/integrations/chat/azure) | Package downloads | Package latest |\n",
-    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
-    "| [AzureChatOpenAI](https://python.langchain.com/api_reference/openai/chat_models/langchain_openai.chat_models.azure.AzureChatOpenAI.html) | [langchain-openai](https://python.langchain.com/api_reference/openai/index.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": "433e8d2b-9519-4b49-b2c4-7ab65b046c94",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "if \"AZURE_OPENAI_API_KEY\" not in os.environ:\n",
-    "    os.environ[\"AZURE_OPENAI_API_KEY\"] = getpass.getpass(\n",
-    "        \"Enter your AzureOpenAI API key: \"\n",
-    "    )\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": [
-    "%pip install -qU langchain-openai"
-   ]
-  },
-  {
-   "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",
-    "- 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": 2,
-   "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_openai import AzureChatOpenAI\n",
-    "\n",
-    "llm = AzureChatOpenAI(\n",
-    "    azure_deployment=\"gpt-35-turbo\",  # or your deployment\n",
-    "    api_version=\"2023-06-01-preview\",  # or your api version\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": 3,
-   "id": "62e0dbc3",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
+  "cells": [
     {
-     "data": {
-      "text/plain": [
-       "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-bea4b46c-e3e1-4495-9d3a-698370ad963d-0', usage_metadata={'input_tokens': 31, 'output_tokens': 8, 'total_tokens': 39})"
+      "cell_type": "raw",
+      "id": "afaf8039",
+      "metadata": {},
+      "source": [
+        "---\n",
+        "sidebar_label: Azure OpenAI\n",
+        "---"
       ]
-     },
-     "execution_count": 3,
-     "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": 4,
-   "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": "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:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "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-cbc44038-09d3-40d4-9da2-c5910ee636ca-0', usage_metadata={'input_tokens': 26, 'output_tokens': 6, 'total_tokens': 32})"
+      "cell_type": "markdown",
+      "id": "e49f1e0d",
+      "metadata": {},
+      "source": [
+        "# AzureChatOpenAI\n",
+        "\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://python.langchain.com/api_reference/openai/chat_models/langchain_openai.chat_models.azure.AzureChatOpenAI.html).\n",
+        "\n",
+        "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/docs/integrations/chat/azure) | Package downloads | Package latest |\n",
+        "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+        "| [AzureChatOpenAI](https://python.langchain.com/api_reference/openai/chat_models/langchain_openai.chat_models.azure.AzureChatOpenAI.html) | [langchain-openai](https://python.langchain.com/api_reference/openai/index.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:"
       ]
-     },
-     "execution_count": 5,
-     "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": null,
-   "id": "04b36e75-e8b7-4721-899e-76301ac2ecd9",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%pip install -qU langchain-community"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "2ca02d23-60d0-43eb-8d04-070f61f8fefd",
-   "metadata": {},
-   "outputs": [
+    },
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Total Cost (USD): $0.000063\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_community.callbacks import get_openai_callback\n",
-    "\n",
-    "with get_openai_callback() as cb:\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": "code",
-   "execution_count": 7,
-   "id": "e1b07ae2-3de7-44bd-bfdc-b76f4ba45a35",
-   "metadata": {},
-   "outputs": [
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "433e8d2b-9519-4b49-b2c4-7ab65b046c94",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import getpass\n",
+        "import os\n",
+        "\n",
+        "if \"AZURE_OPENAI_API_KEY\" not in os.environ:\n",
+        "    os.environ[\"AZURE_OPENAI_API_KEY\"] = getpass.getpass(\n",
+        "        \"Enter your AzureOpenAI API key: \"\n",
+        "    )\n",
+        "os.environ[\"AZURE_OPENAI_ENDPOINT\"] = \"https://YOUR-ENDPOINT.openai.azure.com/\""
+      ]
+    },
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Total Cost (USD): $0.000074\n"
-     ]
+      "cell_type": "markdown",
+      "id": "72ee0c4b-9764-423a-9dbf-95129e185210",
+      "metadata": {},
+      "source": "To enable automated tracing of your model calls, set your [LangSmith](https://docs.smith.langchain.com/) API key:"
+    },
+    {
+      "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": [
+        "%pip install -qU langchain-openai"
+      ]
+    },
+    {
+      "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",
+        "- 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": 2,
+      "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from langchain_openai import AzureChatOpenAI\n",
+        "\n",
+        "llm = AzureChatOpenAI(\n",
+        "    azure_deployment=\"gpt-35-turbo\",  # or your deployment\n",
+        "    api_version=\"2023-06-01-preview\",  # or your api version\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": 3,
+      "id": "62e0dbc3",
+      "metadata": {
+        "tags": []
+      },
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "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-bea4b46c-e3e1-4495-9d3a-698370ad963d-0', usage_metadata={'input_tokens': 31, 'output_tokens': 8, 'total_tokens': 39})"
+            ]
+          },
+          "execution_count": 3,
+          "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": 4,
+      "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": "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:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 5,
+      "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-cbc44038-09d3-40d4-9da2-c5910ee636ca-0', usage_metadata={'input_tokens': 26, 'output_tokens': 6, 'total_tokens': 32})"
+            ]
+          },
+          "execution_count": 5,
+          "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": null,
+      "id": "04b36e75-e8b7-4721-899e-76301ac2ecd9",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%pip install -qU langchain-community"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 6,
+      "id": "2ca02d23-60d0-43eb-8d04-070f61f8fefd",
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Total Cost (USD): $0.000063\n"
+          ]
+        }
+      ],
+      "source": [
+        "from langchain_community.callbacks import get_openai_callback\n",
+        "\n",
+        "with get_openai_callback() as cb:\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": "code",
+      "execution_count": 7,
+      "id": "e1b07ae2-3de7-44bd-bfdc-b76f4ba45a35",
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Total Cost (USD): $0.000074\n"
+          ]
+        }
+      ],
+      "source": [
+        "llm_0301 = AzureChatOpenAI(\n",
+        "    azure_deployment=\"gpt-35-turbo\",  # or your deployment\n",
+        "    api_version=\"2023-06-01-preview\",  # or your api version\n",
+        "    model_version=\"0301\",\n",
+        ")\n",
+        "with get_openai_callback() as cb:\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://python.langchain.com/api_reference/openai/chat_models/langchain_openai.chat_models.azure.AzureChatOpenAI.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"
     }
-   ],
-   "source": [
-    "llm_0301 = AzureChatOpenAI(\n",
-    "    azure_deployment=\"gpt-35-turbo\",  # or your deployment\n",
-    "    api_version=\"2023-06-01-preview\",  # or your api version\n",
-    "    model_version=\"0301\",\n",
-    ")\n",
-    "with get_openai_callback() as cb:\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://python.langchain.com/api_reference/openai/chat_models/langchain_openai.chat_models.azure.AzureChatOpenAI.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
+  "nbformat": 4,
+  "nbformat_minor": 5
 }

docs/docs/integrations/chat/bedrock.ipynb

@@ -19,9 +19,15 @@
     "\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",
+    "AWS Bedrock maintains a [Converse API](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_Converse.html) 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).\n",
     "\n",
-    "For detailed documentation of all ChatBedrock features and configurations head to the [API reference](https://python.langchain.com/api_reference/aws/chat_models/langchain_aws.chat_models.bedrock.ChatBedrock.html).\n",
+    ":::info\n",
+    "\n",
+    "We recommend the Converse API for users who do not need to use custom models. It can be accessed using [ChatBedrockConverse](https://python.langchain.com/api_reference/aws/chat_models/langchain_aws.chat_models.bedrock_converse.ChatBedrockConverse.html).\n",
+    "\n",
+    ":::\n",
+    "\n",
+    "For detailed documentation of all Bedrock features and configurations head to the [API reference](https://python.langchain.com/api_reference/aws/chat_models/langchain_aws.chat_models.bedrock_converse.ChatBedrockConverse.html).\n",
     "\n",
     "## Overview\n",
     "### Integration details\n",
@@ -29,11 +35,15 @@
     "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/docs/integrations/chat/bedrock) | Package downloads | Package latest |\n",
     "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
     "| [ChatBedrock](https://python.langchain.com/api_reference/aws/chat_models/langchain_aws.chat_models.bedrock.ChatBedrock.html) | [langchain-aws](https://python.langchain.com/api_reference/aws/index.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",
+    "| [ChatBedrockConverse](https://python.langchain.com/api_reference/aws/chat_models/langchain_aws.chat_models.bedrock_converse.ChatBedrockConverse.html) | [langchain-aws](https://python.langchain.com/api_reference/aws/index.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",
+    "\n",
+    "The below apply to both `ChatBedrock` and `ChatBedrockConverse`.\n",
+    "\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",
     "\n",
     "## Setup\n",
     "\n",
@@ -49,7 +59,7 @@
    "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:"
+    "To enable automated tracing of your model calls, set your [LangSmith](https://docs.smith.langchain.com/) API key:"
    ]
   },
   {
@@ -100,11 +110,12 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_aws import ChatBedrock\n",
+    "from langchain_aws import ChatBedrockConverse\n",
     "\n",
-    "llm = ChatBedrock(\n",
-    "    model_id=\"anthropic.claude-3-sonnet-20240229-v1:0\",\n",
-    "    model_kwargs=dict(temperature=0),\n",
+    "llm = ChatBedrockConverse(\n",
+    "    model_id=\"anthropic.claude-3-5-sonnet-20240620-v1:0\",\n",
+    "    # temperature=...,\n",
+    "    # max_tokens=...,\n",
     "    # other params...\n",
     ")"
    ]
@@ -119,19 +130,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
-   "id": "62e0dbc3",
-   "metadata": {
-    "tags": []
-   },
+   "execution_count": 2,
+   "id": "fcd8de52-4a1b-4875-b463-d41b031e06a1",
+   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "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})"
+       "AIMessage(content=\"J'adore la programmation.\", additional_kwargs={}, response_metadata={'ResponseMetadata': {'RequestId': 'b07d1630-06f2-44b1-82bf-e82538dd2215', 'HTTPStatusCode': 200, 'HTTPHeaders': {'date': 'Wed, 16 Apr 2025 19:35:34 GMT', 'content-type': 'application/json', 'content-length': '206', 'connection': 'keep-alive', 'x-amzn-requestid': 'b07d1630-06f2-44b1-82bf-e82538dd2215'}, 'RetryAttempts': 0}, 'stopReason': 'end_turn', 'metrics': {'latencyMs': [488]}, 'model_name': 'anthropic.claude-3-5-sonnet-20240620-v1:0'}, id='run-d09ed928-146a-4336-b1fd-b63c9e623494-0', usage_metadata={'input_tokens': 29, 'output_tokens': 11, 'total_tokens': 40, 'input_token_details': {'cache_creation': 0, 'cache_read': 0}})"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -150,7 +159,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 3,
    "id": "d86145b3-bfef-46e8-b227-4dda5c9c2705",
    "metadata": {},
    "outputs": [
@@ -158,9 +167,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Voici la traduction en français :\n",
-      "\n",
-      "J'aime la programmation.\n"
+      "J'adore la programmation.\n"
      ]
     }
    ],
@@ -170,7 +177,146 @@
   },
   {
    "cell_type": "markdown",
-   "id": "18e2bfc0-7e78-4528-a73f-499ac150dca8",
+   "id": "4da16f3e-e80b-48c0-8036-c1cc5f7c8c05",
+   "metadata": {},
+   "source": [
+    "### Streaming\n",
+    "\n",
+    "Note that `ChatBedrockConverse` emits content blocks while streaming:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "605e04fa-1a76-47ac-8c92-fe128659663e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "content=[] additional_kwargs={} response_metadata={} id='run-d0e0836e-7146-4c3d-97c7-ad23dac6febd'\n",
+      "content=[{'type': 'text', 'text': 'J', 'index': 0}] additional_kwargs={} response_metadata={} id='run-d0e0836e-7146-4c3d-97c7-ad23dac6febd'\n",
+      "content=[{'type': 'text', 'text': \"'adore la\", 'index': 0}] additional_kwargs={} response_metadata={} id='run-d0e0836e-7146-4c3d-97c7-ad23dac6febd'\n",
+      "content=[{'type': 'text', 'text': ' programmation.', 'index': 0}] additional_kwargs={} response_metadata={} id='run-d0e0836e-7146-4c3d-97c7-ad23dac6febd'\n",
+      "content=[{'index': 0}] additional_kwargs={} response_metadata={} id='run-d0e0836e-7146-4c3d-97c7-ad23dac6febd'\n",
+      "content=[] additional_kwargs={} response_metadata={'stopReason': 'end_turn'} id='run-d0e0836e-7146-4c3d-97c7-ad23dac6febd'\n",
+      "content=[] additional_kwargs={} response_metadata={'metrics': {'latencyMs': 600}, 'model_name': 'anthropic.claude-3-5-sonnet-20240620-v1:0'} id='run-d0e0836e-7146-4c3d-97c7-ad23dac6febd' usage_metadata={'input_tokens': 29, 'output_tokens': 11, 'total_tokens': 40, 'input_token_details': {'cache_creation': 0, 'cache_read': 0}}\n"
+     ]
+    }
+   ],
+   "source": [
+    "for chunk in llm.stream(messages):\n",
+    "    print(chunk)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0ef05abb-9c04-4dc3-995e-f857779644d5",
+   "metadata": {},
+   "source": [
+    "You can filter to text using the [.text()](https://python.langchain.com/api_reference/core/messages/langchain_core.messages.ai.AIMessage.html#langchain_core.messages.ai.AIMessage.text) method on the output:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "2a4e743f-ea7d-4e5a-9b12-f9992362de8b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "|J|'adore la| programmation.||||"
+     ]
+    }
+   ],
+   "source": [
+    "for chunk in llm.stream(messages):\n",
+    "    print(chunk.text(), end=\"|\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a77519e5-897d-41a0-a9bb-55300fa79efc",
+   "metadata": {},
+   "source": [
+    "## Prompt caching\n",
+    "\n",
+    "Bedrock supports [caching](https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html) of elements of your prompts, including messages and tools. This allows you to re-use large documents, instructions, [few-shot documents](/docs/concepts/few_shot_prompting/), and other data to reduce latency and costs.\n",
+    "\n",
+    ":::note\n",
+    "\n",
+    "Not all models support prompt caching. See supported models [here](https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html#prompt-caching-models).\n",
+    "\n",
+    ":::\n",
+    "\n",
+    "To enable caching on an element of a prompt, mark its associated content block using the `cachePoint` key. See example below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "d5f63d01-85e8-4797-a2be-0fea747a6049",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "First invocation:\n",
+      "{'cache_creation': 1528, 'cache_read': 0}\n",
+      "\n",
+      "Second:\n",
+      "{'cache_creation': 0, 'cache_read': 1528}\n"
+     ]
+    }
+   ],
+   "source": [
+    "import requests\n",
+    "from langchain_aws import ChatBedrockConverse\n",
+    "\n",
+    "llm = ChatBedrockConverse(model=\"us.anthropic.claude-3-7-sonnet-20250219-v1:0\")\n",
+    "\n",
+    "# Pull LangChain readme\n",
+    "get_response = requests.get(\n",
+    "    \"https://raw.githubusercontent.com/langchain-ai/langchain/master/README.md\"\n",
+    ")\n",
+    "readme = get_response.text\n",
+    "\n",
+    "messages = [\n",
+    "    {\n",
+    "        \"role\": \"user\",\n",
+    "        \"content\": [\n",
+    "            {\n",
+    "                \"type\": \"text\",\n",
+    "                \"text\": \"What's LangChain, according to its README?\",\n",
+    "            },\n",
+    "            {\n",
+    "                \"type\": \"text\",\n",
+    "                \"text\": f\"{readme}\",\n",
+    "            },\n",
+    "            {\n",
+    "                \"cachePoint\": {\"type\": \"default\"},\n",
+    "            },\n",
+    "        ],\n",
+    "    },\n",
+    "]\n",
+    "\n",
+    "response_1 = llm.invoke(messages)\n",
+    "response_2 = llm.invoke(messages)\n",
+    "\n",
+    "usage_1 = response_1.usage_metadata[\"input_token_details\"]\n",
+    "usage_2 = response_2.usage_metadata[\"input_token_details\"]\n",
+    "\n",
+    "print(f\"First invocation:\\n{usage_1}\")\n",
+    "print(f\"\\nSecond:\\n{usage_2}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1b550667-af5b-4557-b84f-c8f865dad6cb",
    "metadata": {},
    "source": [
     "## Chaining\n",
@@ -181,13 +327,13 @@
   {
    "cell_type": "code",
    "execution_count": 7,
-   "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
+   "id": "6033f3fa-0e96-46e3-abb3-1530928fea88",
    "metadata": {},
    "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})"
+       "AIMessage(content=\"Here's the German translation:\\n\\nIch liebe das Programmieren.\", additional_kwargs={}, response_metadata={'ResponseMetadata': {'RequestId': '1de3d7c0-8062-4f7e-bb8a-8f725b97a8b0', 'HTTPStatusCode': 200, 'HTTPHeaders': {'date': 'Wed, 16 Apr 2025 19:32:51 GMT', 'content-type': 'application/json', 'content-length': '243', 'connection': 'keep-alive', 'x-amzn-requestid': '1de3d7c0-8062-4f7e-bb8a-8f725b97a8b0'}, 'RetryAttempts': 0}, 'stopReason': 'end_turn', 'metrics': {'latencyMs': [719]}, 'model_name': 'anthropic.claude-3-5-sonnet-20240620-v1:0'}, id='run-7021fcd7-704e-496b-a92e-210139614402-0', usage_metadata={'input_tokens': 23, 'output_tokens': 19, 'total_tokens': 42, 'input_token_details': {'cache_creation': 0, 'cache_read': 0}})"
       ]
      },
      "execution_count": 7,
@@ -218,131 +364,6 @@
     ")"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "d1ee55bc-ffc8-4cfa-801c-993953a08cfd",
-   "metadata": {},
-   "source": [
-    "## Bedrock Converse API\n",
-    "\n",
-    "AWS has recently released 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://python.langchain.com/api_reference/aws/chat_models/langchain_aws.chat_models.bedrock_converse.ChatBedrockConverse.html) integration has been released.\n",
-    "\n",
-    "We recommend using `ChatBedrockConverse` for users who do not need to use custom models.\n",
-    "\n",
-    "You can use it like so:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "ae728e59-94d4-40cf-9d24-25ad8723fc59",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\"Voici la traduction en français :\\n\\nJ'aime la programmation.\", response_metadata={'ResponseMetadata': {'RequestId': '4fcbfbe9-f916-4df2-b0bd-ea1147b550aa', 'HTTPStatusCode': 200, 'HTTPHeaders': {'date': 'Wed, 21 Aug 2024 17:23:49 GMT', 'content-type': 'application/json', 'content-length': '243', 'connection': 'keep-alive', 'x-amzn-requestid': '4fcbfbe9-f916-4df2-b0bd-ea1147b550aa'}, 'RetryAttempts': 0}, 'stopReason': 'end_turn', 'metrics': {'latencyMs': 672}}, id='run-77ee9810-e32b-45dc-9ccb-6692253b1f45-0', usage_metadata={'input_tokens': 29, 'output_tokens': 21, 'total_tokens': 50})"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_aws import ChatBedrockConverse\n",
-    "\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",
-    "llm.invoke(messages)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "4da16f3e-e80b-48c0-8036-c1cc5f7c8c05",
-   "metadata": {},
-   "source": [
-    "### Streaming\n",
-    "\n",
-    "Note that `ChatBedrockConverse` emits content blocks while streaming:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "7794b32e-d8de-4973-bf0f-39807dc745f0",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "content=[] id='run-2c92c5af-d771-4cc2-98d9-c11bbd30a1d8'\n",
-      "content=[{'type': 'text', 'text': 'Vo', 'index': 0}] id='run-2c92c5af-d771-4cc2-98d9-c11bbd30a1d8'\n",
-      "content=[{'type': 'text', 'text': 'ici', 'index': 0}] id='run-2c92c5af-d771-4cc2-98d9-c11bbd30a1d8'\n",
-      "content=[{'type': 'text', 'text': ' la', 'index': 0}] id='run-2c92c5af-d771-4cc2-98d9-c11bbd30a1d8'\n",
-      "content=[{'type': 'text', 'text': ' tra', 'index': 0}] id='run-2c92c5af-d771-4cc2-98d9-c11bbd30a1d8'\n",
-      "content=[{'type': 'text', 'text': 'duction', 'index': 0}] id='run-2c92c5af-d771-4cc2-98d9-c11bbd30a1d8'\n",
-      "content=[{'type': 'text', 'text': ' en', 'index': 0}] id='run-2c92c5af-d771-4cc2-98d9-c11bbd30a1d8'\n",
-      "content=[{'type': 'text', 'text': ' français', 'index': 0}] id='run-2c92c5af-d771-4cc2-98d9-c11bbd30a1d8'\n",
-      "content=[{'type': 'text', 'text': ' :', 'index': 0}] id='run-2c92c5af-d771-4cc2-98d9-c11bbd30a1d8'\n",
-      "content=[{'type': 'text', 'text': '\\n\\nJ', 'index': 0}] id='run-2c92c5af-d771-4cc2-98d9-c11bbd30a1d8'\n",
-      "content=[{'type': 'text', 'text': \"'\", 'index': 0}] id='run-2c92c5af-d771-4cc2-98d9-c11bbd30a1d8'\n",
-      "content=[{'type': 'text', 'text': 'a', 'index': 0}] id='run-2c92c5af-d771-4cc2-98d9-c11bbd30a1d8'\n",
-      "content=[{'type': 'text', 'text': 'ime', 'index': 0}] id='run-2c92c5af-d771-4cc2-98d9-c11bbd30a1d8'\n",
-      "content=[{'type': 'text', 'text': ' la', 'index': 0}] id='run-2c92c5af-d771-4cc2-98d9-c11bbd30a1d8'\n",
-      "content=[{'type': 'text', 'text': ' programm', 'index': 0}] id='run-2c92c5af-d771-4cc2-98d9-c11bbd30a1d8'\n",
-      "content=[{'type': 'text', 'text': 'ation', 'index': 0}] id='run-2c92c5af-d771-4cc2-98d9-c11bbd30a1d8'\n",
-      "content=[{'type': 'text', 'text': '.', 'index': 0}] id='run-2c92c5af-d771-4cc2-98d9-c11bbd30a1d8'\n",
-      "content=[{'index': 0}] id='run-2c92c5af-d771-4cc2-98d9-c11bbd30a1d8'\n",
-      "content=[] response_metadata={'stopReason': 'end_turn'} id='run-2c92c5af-d771-4cc2-98d9-c11bbd30a1d8'\n",
-      "content=[] response_metadata={'metrics': {'latencyMs': 713}} id='run-2c92c5af-d771-4cc2-98d9-c11bbd30a1d8' usage_metadata={'input_tokens': 29, 'output_tokens': 21, 'total_tokens': 50}\n"
-     ]
-    }
-   ],
-   "source": [
-    "for chunk in llm.stream(messages):\n",
-    "    print(chunk)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0ef05abb-9c04-4dc3-995e-f857779644d5",
-   "metadata": {},
-   "source": [
-    "An output parser can be used to filter to text, if desired:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "2a4e743f-ea7d-4e5a-9b12-f9992362de8b",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "|Vo|ici| la| tra|duction| en| français| :|\n",
-      "\n",
-      "J|'|a|ime| la| programm|ation|.||||"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "\n",
-    "chain = llm | StrOutputParser()\n",
-    "\n",
-    "for chunk in chain.stream(messages):\n",
-    "    print(chunk, end=\"|\")"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",

docs/docs/integrations/chat/cerebras.ipynb

@@ -1,424 +1,422 @@
 {
- "cells": [
-  {
-   "cell_type": "raw",
-   "id": "afaf8039",
-   "metadata": {},
-   "source": [
-    "---\n",
-    "sidebar_label: Cerebras\n",
-    "---"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "e49f1e0d",
-   "metadata": {},
-   "source": [
-    "# ChatCerebras\n",
-    "\n",
-    "This notebook provides a quick overview for getting started with Cerebras [chat models](/docs/concepts/chat_models). For detailed documentation of all ChatCerebras features and configurations head to the [API reference](https://python.langchain.com/api_reference/cerebras/chat_models/langchain_cerebras.chat_models.ChatCerebras.html#).\n",
-    "\n",
-    "At Cerebras, we've developed the world's largest and fastest AI processor, the Wafer-Scale Engine-3 (WSE-3). The Cerebras CS-3 system, powered by the WSE-3, represents a new class of AI supercomputer that sets the standard for generative AI training and inference with unparalleled performance and scalability.\n",
-    "\n",
-    "With Cerebras as your inference provider, you can:\n",
-    "- Achieve unprecedented speed for AI inference workloads\n",
-    "- Build commercially with high throughput\n",
-    "- Effortlessly scale your AI workloads with our seamless clustering technology\n",
-    "\n",
-    "Our CS-3 systems can be quickly and easily clustered to create the largest AI supercomputers in the world, making it simple to place and run the largest models. Leading corporations, research institutions, and governments are already using Cerebras solutions to develop proprietary models and train popular open-source models.\n",
-    "\n",
-    "Want to experience the power of Cerebras? Check out our [website](https://cerebras.ai) for more resources and explore options for accessing our technology through the Cerebras Cloud or on-premise deployments!\n",
-    "\n",
-    "For more information about Cerebras Cloud, visit [cloud.cerebras.ai](https://cloud.cerebras.ai/). Our API reference is available at [inference-docs.cerebras.ai](https://inference-docs.cerebras.ai/).\n",
-    "\n",
-    "## Overview\n",
-    "### Integration details\n",
-    "\n",
-    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/docs/integrations/chat/cerebras) | Package downloads | Package latest |\n",
-    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
-    "| [ChatCerebras](https://python.langchain.com/api_reference/cerebras/chat_models/langchain_cerebras.chat_models.ChatCerebras.html#) | [langchain-cerebras](https://python.langchain.com/api_reference/cerebras/index.html) | ❌ | beta | ❌ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-cerebras?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-cerebras?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",
-    "```bash\n",
-    "pip install langchain-cerebras\n",
-    "```\n",
-    "\n",
-    "### Credentials\n",
-    "\n",
-    "Get an API Key from [cloud.cerebras.ai](https://cloud.cerebras.ai/) and add it to your environment variables:\n",
-    "```\n",
-    "export CEREBRAS_API_KEY=\"your-api-key-here\"\n",
-    "```"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "ce19c2d6",
-   "metadata": {},
-   "outputs": [
+  "cells": [
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Enter your Cerebras API key:  ········\n"
-     ]
-    }
-   ],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "if \"CEREBRAS_API_KEY\" not in os.environ:\n",
-    "    os.environ[\"CEREBRAS_API_KEY\"] = getpass.getpass(\"Enter your Cerebras API key: \")"
-   ]
-  },
-  {
-   "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": 9,
-   "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 Cerebras integration lives in the `langchain-cerebras` package:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%pip install -qU langchain-cerebras"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "ea69675d",
-   "metadata": {},
-   "source": [
-    "## Instantiation\n",
-    "\n",
-    "Now we can instantiate our model object and generate chat completions:\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "21155898",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_cerebras import ChatCerebras\n",
-    "\n",
-    "llm = ChatCerebras(\n",
-    "    model=\"llama-3.3-70b\",\n",
-    "    # other params...\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2b4f3e15",
-   "metadata": {},
-   "source": [
-    "## Invocation"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "62e0dbc3",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='Je adore le programmation.', response_metadata={'token_usage': {'completion_tokens': 7, 'prompt_tokens': 35, 'total_tokens': 42}, 'model_name': 'llama3-8b-8192', 'system_fingerprint': 'fp_be27ec77ff', 'finish_reason': 'stop'}, id='run-e5d66faf-019c-4ac6-9265-71093b13202d-0', usage_metadata={'input_tokens': 35, 'output_tokens': 7, 'total_tokens': 42})"
+      "cell_type": "raw",
+      "id": "afaf8039",
+      "metadata": {},
+      "source": [
+        "---\n",
+        "sidebar_label: Cerebras\n",
+        "---"
       ]
-     },
-     "execution_count": 13,
-     "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": "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:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
-   "metadata": {},
-   "outputs": [
+    },
     {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='Ich liebe Programmieren!\\n\\n(Literally: I love programming!)', response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 30, 'total_tokens': 44}, 'model_name': 'llama3-8b-8192', 'system_fingerprint': 'fp_be27ec77ff', 'finish_reason': 'stop'}, id='run-e1d2ebb8-76d1-471b-9368-3b68d431f16a-0', usage_metadata={'input_tokens': 30, 'output_tokens': 14, 'total_tokens': 44})"
+      "cell_type": "markdown",
+      "id": "e49f1e0d",
+      "metadata": {},
+      "source": [
+        "# ChatCerebras\n",
+        "\n",
+        "This notebook provides a quick overview for getting started with Cerebras [chat models](/docs/concepts/chat_models). For detailed documentation of all ChatCerebras features and configurations head to the [API reference](https://python.langchain.com/api_reference/cerebras/chat_models/langchain_cerebras.chat_models.ChatCerebras.html#).\n",
+        "\n",
+        "At Cerebras, we've developed the world's largest and fastest AI processor, the Wafer-Scale Engine-3 (WSE-3). The Cerebras CS-3 system, powered by the WSE-3, represents a new class of AI supercomputer that sets the standard for generative AI training and inference with unparalleled performance and scalability.\n",
+        "\n",
+        "With Cerebras as your inference provider, you can:\n",
+        "- Achieve unprecedented speed for AI inference workloads\n",
+        "- Build commercially with high throughput\n",
+        "- Effortlessly scale your AI workloads with our seamless clustering technology\n",
+        "\n",
+        "Our CS-3 systems can be quickly and easily clustered to create the largest AI supercomputers in the world, making it simple to place and run the largest models. Leading corporations, research institutions, and governments are already using Cerebras solutions to develop proprietary models and train popular open-source models.\n",
+        "\n",
+        "Want to experience the power of Cerebras? Check out our [website](https://cerebras.ai) for more resources and explore options for accessing our technology through the Cerebras Cloud or on-premise deployments!\n",
+        "\n",
+        "For more information about Cerebras Cloud, visit [cloud.cerebras.ai](https://cloud.cerebras.ai/). Our API reference is available at [inference-docs.cerebras.ai](https://inference-docs.cerebras.ai/).\n",
+        "\n",
+        "## Overview\n",
+        "### Integration details\n",
+        "\n",
+        "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/docs/integrations/chat/cerebras) | Package downloads | Package latest |\n",
+        "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+        "| [ChatCerebras](https://python.langchain.com/api_reference/cerebras/chat_models/langchain_cerebras.chat_models.ChatCerebras.html#) | [langchain-cerebras](https://python.langchain.com/api_reference/cerebras/index.html) | ❌ | beta | ❌ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-cerebras?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-cerebras?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",
+        "```bash\n",
+        "pip install langchain-cerebras\n",
+        "```\n",
+        "\n",
+        "### Credentials\n",
+        "\n",
+        "Get an API Key from [cloud.cerebras.ai](https://cloud.cerebras.ai/) and add it to your environment variables:\n",
+        "```\n",
+        "export CEREBRAS_API_KEY=\"your-api-key-here\"\n",
+        "```"
       ]
-     },
-     "execution_count": 14,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_cerebras import ChatCerebras\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "\n",
-    "llm = ChatCerebras(\n",
-    "    model=\"llama-3.3-70b\",\n",
-    "    # other params...\n",
-    ")\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": "0ec73a0e",
-   "metadata": {},
-   "source": [
-    "## Streaming"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "46fd21a7",
-   "metadata": {},
-   "outputs": [
+    },
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "OH BOY! Let me tell you all about LIONS!\n",
-      "\n",
-      "Lions are the kings of the jungle! They're really big and have beautiful, fluffy manes around their necks. The mane is like a big, golden crown!\n",
-      "\n",
-      "Lions live in groups called prides. A pride is like a big family, and the lionesses (that's what we call the female lions) take care of the babies. The lionesses are like the mommies, and they teach the babies how to hunt and play.\n",
-      "\n",
-      "Lions are very good at hunting. They work together to catch their food, like zebras and antelopes. They're super fast and can run really, really fast!\n",
-      "\n",
-      "But lions are also very sleepy. They like to take long naps in the sun, and they can sleep for up to 20 hours a day! Can you imagine sleeping that much?\n",
-      "\n",
-      "Lions are also very loud. They roar really loudly to talk to each other. It's like they're saying, \"ROAR! I'm the king of the jungle!\"\n",
-      "\n",
-      "And guess what? Lions are very social. They like to play and cuddle with each other. They're like big, furry teddy bears!\n",
-      "\n",
-      "So, that's lions! Aren't they just the coolest?"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_cerebras import ChatCerebras\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "\n",
-    "llm = ChatCerebras(\n",
-    "    model=\"llama-3.3-70b\",\n",
-    "    # other params...\n",
-    ")\n",
-    "\n",
-    "system = \"You are an expert on animals who must answer questions in a manner that a 5 year old can understand.\"\n",
-    "human = \"I want to learn more about this animal: {animal}\"\n",
-    "prompt = ChatPromptTemplate.from_messages([(\"system\", system), (\"human\", human)])\n",
-    "\n",
-    "chain = prompt | llm\n",
-    "\n",
-    "for chunk in chain.stream({\"animal\": \"Lion\"}):\n",
-    "    print(chunk.content, end=\"\", flush=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "f67b6132",
-   "metadata": {},
-   "source": [
-    "## Async"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 19,
-   "id": "a3a45baf",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='Ice', response_metadata={'token_usage': {'completion_tokens': 2, 'prompt_tokens': 36, 'total_tokens': 38}, 'model_name': 'llama3-8b-8192', 'system_fingerprint': 'fp_be27ec77ff', 'finish_reason': 'stop'}, id='run-7434bdde-1bec-44cf-827b-8d978071dfe8-0', usage_metadata={'input_tokens': 36, 'output_tokens': 2, 'total_tokens': 38})"
+      "cell_type": "code",
+      "execution_count": 8,
+      "id": "ce19c2d6",
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Enter your Cerebras API key:  ········\n"
+          ]
+        }
+      ],
+      "source": [
+        "import getpass\n",
+        "import os\n",
+        "\n",
+        "if \"CEREBRAS_API_KEY\" not in os.environ:\n",
+        "    os.environ[\"CEREBRAS_API_KEY\"] = getpass.getpass(\"Enter your Cerebras API key: \")"
       ]
-     },
-     "execution_count": 19,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_cerebras import ChatCerebras\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "\n",
-    "llm = ChatCerebras(\n",
-    "    model=\"llama-3.3-70b\",\n",
-    "    # other params...\n",
-    ")\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\n",
-    "            \"human\",\n",
-    "            \"Let's play a game of opposites. What's the opposite of {topic}? Just give me the answer with no extra input.\",\n",
-    "        )\n",
-    "    ]\n",
-    ")\n",
-    "chain = prompt | llm\n",
-    "await chain.ainvoke({\"topic\": \"fire\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "4f9d9945",
-   "metadata": {},
-   "source": [
-    "## Async Streaming"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 27,
-   "id": "c7448e0f",
-   "metadata": {},
-   "outputs": [
+    },
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "In the distant reaches of the cosmos, there existed a peculiar phenomenon known as the \"Eclipse of Eternity,\" a swirling vortex of darkness that had been shrouded in mystery for eons. It was said that this blackhole, born from the cataclysmic collision of two ancient stars, had been slowly devouring the fabric of space-time itself, warping the very essence of reality. As the celestial bodies of the galaxy danced around it, they began to notice a strange, almost imperceptible distortion in the fabric of space, as if the blackhole's gravitational pull was exerting an influence on the very course of events itself.\n",
-      "\n",
-      "As the centuries passed, astronomers from across the galaxy became increasingly fascinated by the Eclipse of Eternity, pouring over ancient texts and scouring the cosmos for any hint of its secrets. One such scholar, a brilliant and reclusive astrophysicist named Dr. Elara Vex, became obsessed with unraveling the mysteries of the blackhole. She spent years pouring over ancient texts, deciphering cryptic messages and hidden codes that hinted at the existence of a long-lost civilization that had once thrived in the heart of the blackhole itself. According to legend, this ancient civilization had possessed knowledge of the cosmos that was beyond human comprehension, and had used their mastery of the universe to create the Eclipse of Eternity as a gateway to other dimensions.\n",
-      "\n",
-      "As Dr. Vex delved deeper into her research, she began to experience strange and vivid dreams, visions that seemed to transport her to the very heart of the blackhole itself. In these dreams, she saw ancient beings, their faces twisted in agony as they were consumed by the void. She saw stars and galaxies, their light warped and distorted by the blackhole's gravitational pull. And she saw the Eclipse of Eternity itself, its swirling vortex of darkness pulsing with an otherworldly energy that seemed to be calling to her. As the dreams grew more vivid and more frequent, Dr. Vex became convinced that she was being drawn into the heart of the blackhole, and that the secrets of the universe lay waiting for her on the other side."
-     ]
+      "cell_type": "markdown",
+      "id": "72ee0c4b-9764-423a-9dbf-95129e185210",
+      "metadata": {},
+      "source": "To enable automated tracing of your model calls, set your [LangSmith](https://docs.smith.langchain.com/) API key:"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 9,
+      "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 Cerebras integration lives in the `langchain-cerebras` package:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%pip install -qU langchain-cerebras"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "ea69675d",
+      "metadata": {},
+      "source": [
+        "## Instantiation\n",
+        "\n",
+        "Now we can instantiate our model object and generate chat completions:\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "21155898",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from langchain_cerebras import ChatCerebras\n",
+        "\n",
+        "llm = ChatCerebras(\n",
+        "    model=\"llama-3.3-70b\",\n",
+        "    # other params...\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "2b4f3e15",
+      "metadata": {},
+      "source": [
+        "## Invocation"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 13,
+      "id": "62e0dbc3",
+      "metadata": {
+        "tags": []
+      },
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "AIMessage(content='Je adore le programmation.', response_metadata={'token_usage': {'completion_tokens': 7, 'prompt_tokens': 35, 'total_tokens': 42}, 'model_name': 'llama3-8b-8192', 'system_fingerprint': 'fp_be27ec77ff', 'finish_reason': 'stop'}, id='run-e5d66faf-019c-4ac6-9265-71093b13202d-0', usage_metadata={'input_tokens': 35, 'output_tokens': 7, 'total_tokens': 42})"
+            ]
+          },
+          "execution_count": 13,
+          "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": "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:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 14,
+      "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "AIMessage(content='Ich liebe Programmieren!\\n\\n(Literally: I love programming!)', response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 30, 'total_tokens': 44}, 'model_name': 'llama3-8b-8192', 'system_fingerprint': 'fp_be27ec77ff', 'finish_reason': 'stop'}, id='run-e1d2ebb8-76d1-471b-9368-3b68d431f16a-0', usage_metadata={'input_tokens': 30, 'output_tokens': 14, 'total_tokens': 44})"
+            ]
+          },
+          "execution_count": 14,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "from langchain_cerebras import ChatCerebras\n",
+        "from langchain_core.prompts import ChatPromptTemplate\n",
+        "\n",
+        "llm = ChatCerebras(\n",
+        "    model=\"llama-3.3-70b\",\n",
+        "    # other params...\n",
+        ")\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": "0ec73a0e",
+      "metadata": {},
+      "source": [
+        "## Streaming"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 15,
+      "id": "46fd21a7",
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "OH BOY! Let me tell you all about LIONS!\n",
+            "\n",
+            "Lions are the kings of the jungle! They're really big and have beautiful, fluffy manes around their necks. The mane is like a big, golden crown!\n",
+            "\n",
+            "Lions live in groups called prides. A pride is like a big family, and the lionesses (that's what we call the female lions) take care of the babies. The lionesses are like the mommies, and they teach the babies how to hunt and play.\n",
+            "\n",
+            "Lions are very good at hunting. They work together to catch their food, like zebras and antelopes. They're super fast and can run really, really fast!\n",
+            "\n",
+            "But lions are also very sleepy. They like to take long naps in the sun, and they can sleep for up to 20 hours a day! Can you imagine sleeping that much?\n",
+            "\n",
+            "Lions are also very loud. They roar really loudly to talk to each other. It's like they're saying, \"ROAR! I'm the king of the jungle!\"\n",
+            "\n",
+            "And guess what? Lions are very social. They like to play and cuddle with each other. They're like big, furry teddy bears!\n",
+            "\n",
+            "So, that's lions! Aren't they just the coolest?"
+          ]
+        }
+      ],
+      "source": [
+        "from langchain_cerebras import ChatCerebras\n",
+        "from langchain_core.prompts import ChatPromptTemplate\n",
+        "\n",
+        "llm = ChatCerebras(\n",
+        "    model=\"llama-3.3-70b\",\n",
+        "    # other params...\n",
+        ")\n",
+        "\n",
+        "system = \"You are an expert on animals who must answer questions in a manner that a 5 year old can understand.\"\n",
+        "human = \"I want to learn more about this animal: {animal}\"\n",
+        "prompt = ChatPromptTemplate.from_messages([(\"system\", system), (\"human\", human)])\n",
+        "\n",
+        "chain = prompt | llm\n",
+        "\n",
+        "for chunk in chain.stream({\"animal\": \"Lion\"}):\n",
+        "    print(chunk.content, end=\"\", flush=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "f67b6132",
+      "metadata": {},
+      "source": [
+        "## Async"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 19,
+      "id": "a3a45baf",
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "AIMessage(content='Ice', response_metadata={'token_usage': {'completion_tokens': 2, 'prompt_tokens': 36, 'total_tokens': 38}, 'model_name': 'llama3-8b-8192', 'system_fingerprint': 'fp_be27ec77ff', 'finish_reason': 'stop'}, id='run-7434bdde-1bec-44cf-827b-8d978071dfe8-0', usage_metadata={'input_tokens': 36, 'output_tokens': 2, 'total_tokens': 38})"
+            ]
+          },
+          "execution_count": 19,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "from langchain_cerebras import ChatCerebras\n",
+        "from langchain_core.prompts import ChatPromptTemplate\n",
+        "\n",
+        "llm = ChatCerebras(\n",
+        "    model=\"llama-3.3-70b\",\n",
+        "    # other params...\n",
+        ")\n",
+        "\n",
+        "prompt = ChatPromptTemplate.from_messages(\n",
+        "    [\n",
+        "        (\n",
+        "            \"human\",\n",
+        "            \"Let's play a game of opposites. What's the opposite of {topic}? Just give me the answer with no extra input.\",\n",
+        "        )\n",
+        "    ]\n",
+        ")\n",
+        "chain = prompt | llm\n",
+        "await chain.ainvoke({\"topic\": \"fire\"})"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "4f9d9945",
+      "metadata": {},
+      "source": [
+        "## Async Streaming"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 27,
+      "id": "c7448e0f",
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "In the distant reaches of the cosmos, there existed a peculiar phenomenon known as the \"Eclipse of Eternity,\" a swirling vortex of darkness that had been shrouded in mystery for eons. It was said that this blackhole, born from the cataclysmic collision of two ancient stars, had been slowly devouring the fabric of space-time itself, warping the very essence of reality. As the celestial bodies of the galaxy danced around it, they began to notice a strange, almost imperceptible distortion in the fabric of space, as if the blackhole's gravitational pull was exerting an influence on the very course of events itself.\n",
+            "\n",
+            "As the centuries passed, astronomers from across the galaxy became increasingly fascinated by the Eclipse of Eternity, pouring over ancient texts and scouring the cosmos for any hint of its secrets. One such scholar, a brilliant and reclusive astrophysicist named Dr. Elara Vex, became obsessed with unraveling the mysteries of the blackhole. She spent years pouring over ancient texts, deciphering cryptic messages and hidden codes that hinted at the existence of a long-lost civilization that had once thrived in the heart of the blackhole itself. According to legend, this ancient civilization had possessed knowledge of the cosmos that was beyond human comprehension, and had used their mastery of the universe to create the Eclipse of Eternity as a gateway to other dimensions.\n",
+            "\n",
+            "As Dr. Vex delved deeper into her research, she began to experience strange and vivid dreams, visions that seemed to transport her to the very heart of the blackhole itself. In these dreams, she saw ancient beings, their faces twisted in agony as they were consumed by the void. She saw stars and galaxies, their light warped and distorted by the blackhole's gravitational pull. And she saw the Eclipse of Eternity itself, its swirling vortex of darkness pulsing with an otherworldly energy that seemed to be calling to her. As the dreams grew more vivid and more frequent, Dr. Vex became convinced that she was being drawn into the heart of the blackhole, and that the secrets of the universe lay waiting for her on the other side."
+          ]
+        }
+      ],
+      "source": [
+        "from langchain_cerebras import ChatCerebras\n",
+        "from langchain_core.prompts import ChatPromptTemplate\n",
+        "\n",
+        "llm = ChatCerebras(\n",
+        "    model=\"llama-3.3-70b\",\n",
+        "    # other params...\n",
+        ")\n",
+        "\n",
+        "prompt = ChatPromptTemplate.from_messages(\n",
+        "    [\n",
+        "        (\n",
+        "            \"human\",\n",
+        "            \"Write a long convoluted story about {subject}. I want {num_paragraphs} paragraphs.\",\n",
+        "        )\n",
+        "    ]\n",
+        ")\n",
+        "chain = prompt | llm\n",
+        "\n",
+        "async for chunk in chain.astream({\"num_paragraphs\": 3, \"subject\": \"blackholes\"}):\n",
+        "    print(chunk.content, end=\"\", flush=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
+      "metadata": {},
+      "source": [
+        "## API reference\n",
+        "\n",
+        "For detailed documentation of all ChatCerebras features and configurations head to the API reference: https://python.langchain.com/api_reference/cerebras/chat_models/langchain_cerebras.chat_models.ChatCerebras.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": "3.8.13"
     }
-   ],
-   "source": [
-    "from langchain_cerebras import ChatCerebras\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "\n",
-    "llm = ChatCerebras(\n",
-    "    model=\"llama-3.3-70b\",\n",
-    "    # other params...\n",
-    ")\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\n",
-    "            \"human\",\n",
-    "            \"Write a long convoluted story about {subject}. I want {num_paragraphs} paragraphs.\",\n",
-    "        )\n",
-    "    ]\n",
-    ")\n",
-    "chain = prompt | llm\n",
-    "\n",
-    "async for chunk in chain.astream({\"num_paragraphs\": 3, \"subject\": \"blackholes\"}):\n",
-    "    print(chunk.content, end=\"\", flush=True)"
-   ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
-   "metadata": {},
-   "source": [
-    "## API reference\n",
-    "\n",
-    "For detailed documentation of all ChatCerebras features and configurations head to the API reference: https://python.langchain.com/api_reference/cerebras/chat_models/langchain_cerebras.chat_models.ChatCerebras.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": "3.8.13"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
+  "nbformat": 4,
+  "nbformat_minor": 5
 }

docs/docs/integrations/chat/cloudflare_workersai.ipynb

@@ -2,50 +2,74 @@
  "cells": [
   {
    "cell_type": "raw",
-   "id": "30373ae2-f326-4e96-a1f7-062f57396886",
+   "id": "afaf8039",
    "metadata": {},
    "source": [
     "---\n",
-    "sidebar_label: Cloudflare Workers AI\n",
+    "sidebar_label: CloudflareWorkersAI\n",
     "---"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "f679592d",
+   "id": "e49f1e0d",
    "metadata": {},
    "source": [
     "# ChatCloudflareWorkersAI\n",
     "\n",
-    "This will help you getting started with CloudflareWorkersAI [chat models](/docs/concepts/chat_models). For detailed documentation of all available Cloudflare WorkersAI models head to the [API reference](https://developers.cloudflare.com/workers-ai/).\n",
+    "\n",
+    "This will help you getting started with CloudflareWorkersAI [chat models](/docs/concepts/chat_models). For detailed documentation of all ChatCloudflareWorkersAI features and configurations head to the [API reference](https://python.langchain.com/docs/integrations/chat/cloudflare_workersai/).\n",
     "\n",
     "\n",
     "## Overview\n",
     "### Integration details\n",
     "\n",
-    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/docs/integrations/chat/cloudflare_workersai) | Package downloads | Package latest |\n",
-    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
-    "| ChatCloudflareWorkersAI | langchain-community| ❌ | ❌ | ✅ | ❌  | ❌ |\n",
+    "\n",
+    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/docs/integrations/chat/cloudflare) | Package downloads | Package latest |\n",
+    "| :--- | :--- |:-----:|:------------:|:------------------------------------------------------------------------:| :---: | :---: |\n",
+    "| [ChatCloudflareWorkersAI](https://python.langchain.com/docs/integrations/chat/cloudflare_workersai/) | [langchain-cloudflare](https://pypi.org/project/langchain-cloudflare/) |   ✅   |      ❌       |                                     ❌                                     | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-cloudflare?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-cloudflare?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",
+    "|                     ✅                     |                          ✅                           |     ✅     |                       ❌                        |      ❌      |      ❌      |                           ❌                           |      ❌       |                             ✅                            |                 ❌                  | \n",
     "\n",
     "## Setup\n",
     "\n",
-    "- To access Cloudflare Workers AI models you'll need to create a Cloudflare account, get an account number and API key, and install the `langchain-community` package.\n",
-    "\n",
+    "To access CloudflareWorkersAI models you'll need to create a/an CloudflareWorkersAI account, get an API key, and install the `langchain-cloudflare` integration package.\n",
     "\n",
     "### Credentials\n",
     "\n",
     "\n",
-    "Head to [this document](https://developers.cloudflare.com/workers-ai/get-started/rest-api/) to sign up to Cloudflare Workers AI and generate an API key."
+    "Head to https://www.cloudflare.com/developer-platform/products/workers-ai/ to sign up to CloudflareWorkersAI and generate an API key. Once you've done this set the CF_API_KEY environment variable and the CF_ACCOUNT_ID environment variable:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "433e8d2b-9519-4b49-b2c4-7ab65b046c94",
+   "metadata": {
+    "is_executing": true
+   },
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "if not os.getenv(\"CF_API_KEY\"):\n",
+    "    os.environ[\"CF_API_KEY\"] = getpass.getpass(\n",
+    "        \"Enter your CloudflareWorkersAI API key: \"\n",
+    "    )\n",
+    "\n",
+    "if not os.getenv(\"CF_ACCOUNT_ID\"):\n",
+    "    os.environ[\"CF_ACCOUNT_ID\"] = getpass.getpass(\n",
+    "        \"Enter your CloudflareWorkersAI account ID: \"\n",
+    "    )"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "4a524cff",
+   "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:"
@@ -53,8 +77,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
-   "id": "71b53c25",
+   "execution_count": null,
+   "id": "a15d341e-3e26-4ca3-830b-5aab30ed66de",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -64,80 +88,81 @@
   },
   {
    "cell_type": "markdown",
-   "id": "777a8526",
+   "id": "0730d6a1-c893-4840-9817-5e5251676d5d",
    "metadata": {},
    "source": [
     "### Installation\n",
     "\n",
-    "The LangChain ChatCloudflareWorkersAI integration lives in the `langchain-community` package:"
+    "The LangChain CloudflareWorkersAI integration lives in the `langchain-cloudflare` package:"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "54990998",
+   "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install -qU langchain-community"
+    "%pip install -qU langchain-cloudflare"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "629ba46f",
+   "id": "a38cde65-254d-4219-a441-068766c0d4b5",
    "metadata": {},
    "source": [
     "## Instantiation\n",
     "\n",
-    "Now we can instantiate our model object and generate chat completions:"
+    "Now we can instantiate our model object and generate chat completions:\n",
+    "\n",
+    "- Update model instantiation with relevant params."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "ec13c2d9",
-   "metadata": {},
+   "execution_count": 35,
+   "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-07T17:48:31.193773Z",
+     "start_time": "2025-04-07T17:48:31.179196Z"
+    }
+   },
    "outputs": [],
    "source": [
-    "from langchain_community.chat_models.cloudflare_workersai import ChatCloudflareWorkersAI\n",
+    "from langchain_cloudflare.chat_models import ChatCloudflareWorkersAI\n",
     "\n",
     "llm = ChatCloudflareWorkersAI(\n",
-    "    account_id=\"my_account_id\",\n",
-    "    api_token=\"my_api_token\",\n",
-    "    model=\"@hf/nousresearch/hermes-2-pro-mistral-7b\",\n",
+    "    model=\"@cf/meta/llama-3.3-70b-instruct-fp8-fast\",\n",
+    "    temperature=0,\n",
+    "    max_tokens=1024,\n",
+    "    # other params...\n",
     ")"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "119b6732",
+   "id": "2b4f3e15",
    "metadata": {},
    "source": [
-    "## Invocation"
+    "## Invocation\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
-   "id": "2438a906",
+   "execution_count": 19,
+   "id": "62e0dbc3",
    "metadata": {
     "tags": []
    },
    "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "2024-11-07 15:55:14 - INFO - Sending prompt to Cloudflare Workers AI: {'prompt': 'role: system, content: You are a helpful assistant that translates English to French. Translate the user sentence.\\nrole: user, content: I love programming.', 'tools': None}\n"
-     ]
-    },
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='{\\'result\\': {\\'response\\': \\'Je suis un assistant virtuel qui peut traduire l\\\\\\'anglais vers le français. La phrase que vous avez dite est : \"J\\\\\\'aime programmer.\" En français, cela se traduit par : \"J\\\\\\'adore programmer.\"\\'}, \\'success\\': True, \\'errors\\': [], \\'messages\\': []}', additional_kwargs={}, response_metadata={}, id='run-838fd398-8594-4ca5-9055-03c72993caf6-0')"
+       "AIMessage(content=\"J'adore la programmation.\", additional_kwargs={}, response_metadata={'token_usage': {'prompt_tokens': 37, 'completion_tokens': 9, 'total_tokens': 46}, 'model_name': '@cf/meta/llama-3.3-70b-instruct-fp8-fast'}, id='run-995d1970-b6be-49f3-99ae-af4cdba02304-0', usage_metadata={'input_tokens': 37, 'output_tokens': 9, 'total_tokens': 46})"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 19,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -156,15 +181,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
-   "id": "1b4911bd",
+   "execution_count": 20,
+   "id": "d86145b3-bfef-46e8-b227-4dda5c9c2705",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'result': {'response': 'Je suis un assistant virtuel qui peut traduire l\\'anglais vers le français. La phrase que vous avez dite est : \"J\\'aime programmer.\" En français, cela se traduit par : \"J\\'adore programmer.\"'}, 'success': True, 'errors': [], 'messages': []}\n"
+      "J'adore la programmation.\n"
      ]
     }
    ],
@@ -174,34 +199,27 @@
   },
   {
    "cell_type": "markdown",
-   "id": "111aa5d4",
+   "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:"
+    "We can [chain](/docs/how_to/sequence/) our model with a prompt template like so:\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
-   "id": "b2a14282",
+   "execution_count": 21,
+   "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
    "metadata": {},
    "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "2024-11-07 15:55:24 - INFO - Sending prompt to Cloudflare Workers AI: {'prompt': 'role: system, content: You are a helpful assistant that translates English to German.\\nrole: user, content: I love programming.', 'tools': None}\n"
-     ]
-    },
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"{'result': {'response': 'role: system, content: Das ist sehr nett zu hören! Programmieren lieben, ist eine interessante und anspruchsvolle Hobby- oder Berufsausrichtung. Wenn Sie englische Texte ins Deutsche übersetzen möchten, kann ich Ihnen helfen. Geben Sie bitte den englischen Satz oder die Übersetzung an, die Sie benötigen.'}, 'success': True, 'errors': [], 'messages': []}\", additional_kwargs={}, response_metadata={}, id='run-0d3be9a6-3d74-4dde-b49a-4479d6af00ef-0')"
+       "AIMessage(content='Ich liebe das Programmieren.', additional_kwargs={}, response_metadata={'token_usage': {'prompt_tokens': 32, 'completion_tokens': 7, 'total_tokens': 39}, 'model_name': '@cf/meta/llama-3.3-70b-instruct-fp8-fast'}, id='run-d1b677bc-194e-4473-90f1-aa65e8e46d50-0', usage_metadata={'input_tokens': 32, 'output_tokens': 7, 'total_tokens': 39})"
       ]
      },
-     "execution_count": 10,
+     "execution_count": 21,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -209,7 +227,7 @@
    "source": [
     "from langchain_core.prompts import ChatPromptTemplate\n",
     "\n",
-    "prompt = ChatPromptTemplate.from_messages(\n",
+    "prompt = ChatPromptTemplate(\n",
     "    [\n",
     "        (\n",
     "            \"system\",\n",
@@ -231,12 +249,123 @@
   },
   {
    "cell_type": "markdown",
-   "id": "e1f311bd",
+   "id": "d1ee55bc-ffc8-4cfa-801c-993953a08cfd",
+   "metadata": {},
+   "source": [
+    "## Structured Outputs"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "91cae406-14d7-46c9-b942-2d1476588423",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'setup': 'Why did the cat join a band?',\n",
+       " 'punchline': 'Because it wanted to be the purr-cussionist',\n",
+       " 'rating': '8'}"
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "json_schema = {\n",
+    "    \"title\": \"joke\",\n",
+    "    \"description\": \"Joke to tell user.\",\n",
+    "    \"type\": \"object\",\n",
+    "    \"properties\": {\n",
+    "        \"setup\": {\n",
+    "            \"type\": \"string\",\n",
+    "            \"description\": \"The setup of the joke\",\n",
+    "        },\n",
+    "        \"punchline\": {\n",
+    "            \"type\": \"string\",\n",
+    "            \"description\": \"The punchline to the joke\",\n",
+    "        },\n",
+    "        \"rating\": {\n",
+    "            \"type\": \"integer\",\n",
+    "            \"description\": \"How funny the joke is, from 1 to 10\",\n",
+    "            \"default\": None,\n",
+    "        },\n",
+    "    },\n",
+    "    \"required\": [\"setup\", \"punchline\"],\n",
+    "}\n",
+    "structured_llm = llm.with_structured_output(json_schema)\n",
+    "\n",
+    "structured_llm.invoke(\"Tell me a joke about cats\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "dbfc0c43-e76b-446e-bbb1-d351640bb7be",
+   "metadata": {},
+   "source": [
+    "## Bind tools"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "id": "0765265e-4d00-4030-bf48-7e8d8c9af2ec",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'name': 'validate_user',\n",
+       "  'args': {'user_id': '123',\n",
+       "   'addresses': '[\"123 Fake St in Boston MA\", \"234 Pretend Boulevard in Houston TX\"]'},\n",
+       "  'id': '31ec7d6a-9ce5-471b-be64-8ea0492d1387',\n",
+       "  'type': 'tool_call'}]"
+      ]
+     },
+     "execution_count": 36,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from typing import List\n",
+    "\n",
+    "from langchain_core.tools import tool\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def validate_user(user_id: int, addresses: List[str]) -> bool:\n",
+    "    \"\"\"Validate user using historical addresses.\n",
+    "\n",
+    "    Args:\n",
+    "        user_id (int): the user ID.\n",
+    "        addresses (List[str]): Previous addresses as a list of strings.\n",
+    "    \"\"\"\n",
+    "    return True\n",
+    "\n",
+    "\n",
+    "llm_with_tools = llm.bind_tools([validate_user])\n",
+    "\n",
+    "result = llm_with_tools.invoke(\n",
+    "    \"Could you validate user 123? They previously lived at \"\n",
+    "    \"123 Fake St in Boston MA and 234 Pretend Boulevard in \"\n",
+    "    \"Houston TX.\"\n",
+    ")\n",
+    "result.tool_calls"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
    "metadata": {},
    "source": [
     "## API reference\n",
     "\n",
-    "For detailed documentation on `ChatCloudflareWorkersAI` features and configuration options, please refer to the [API reference](https://python.langchain.com/api_reference/community/chat_models/langchain_community.chat_models.cloudflare_workersai.html)."
+    "https://developers.cloudflare.com/workers-ai/\n",
+    "https://developers.cloudflare.com/agents/"
    ]
   }
  ],
@@ -256,7 +385,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.4"
+   "version": "3.11.7"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/cohere.ipynb

@@ -1,352 +1,350 @@
 {
- "cells": [
-  {
-   "cell_type": "raw",
-   "id": "53fbf15f",
-   "metadata": {},
-   "source": [
-    "---\n",
-    "sidebar_label: Cohere\n",
-    "---"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "bf733a38-db84-4363-89e2-de6735c37230",
-   "metadata": {},
-   "source": [
-    "# Cohere\n",
-    "\n",
-    "This notebook covers how to get started with [Cohere chat models](https://cohere.com/chat).\n",
-    "\n",
-    "Head to the [API reference](https://python.langchain.com/api_reference/community/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",
-    "\n",
-    "```bash\n",
-    "pip install -U langchain-cohere\n",
-    "```\n",
-    "\n",
-    "We'll also need to get a [Cohere API key](https://cohere.com/) and set the `COHERE_API_KEY` environment variable:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "2108b517-1e8d-473d-92fa-4f930e8072a7",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "os.environ[\"COHERE_API_KEY\"] = getpass.getpass()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "cf690fbb",
-   "metadata": {},
-   "source": [
-    "It's also helpful (but not needed) to set up [LangSmith](https://smith.langchain.com/) for best-in-class observability"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "7f11de02",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\"\n",
-    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "4c26754b-b3c9-4d93-8f36-43049bd943bf",
-   "metadata": {},
-   "source": [
-    "## Usage\n",
-    "\n",
-    "ChatCohere supports all [ChatModel](/docs/how_to#chat-models) functionality:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "d4a7c55d-b235-4ca4-a579-c90cc9570da9",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain_cohere import ChatCohere\n",
-    "from langchain_core.messages import HumanMessage"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "70cf04e8-423a-4ff6-8b09-f11fb711c817",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "chat = ChatCohere()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "8199ef8f-eb8b-4253-9ea0-6c24a013ca4c",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
+  "cells": [
     {
-     "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')"
+      "cell_type": "raw",
+      "id": "53fbf15f",
+      "metadata": {},
+      "source": [
+        "---\n",
+        "sidebar_label: Cohere\n",
+        "---"
       ]
-     },
-     "execution_count": 15,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "messages = [HumanMessage(content=\"1\"), HumanMessage(content=\"2 3\")]\n",
-    "chat.invoke(messages)"
-   ]
-  },
-  {
-   "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')"
+      "cell_type": "markdown",
+      "id": "bf733a38-db84-4363-89e2-de6735c37230",
+      "metadata": {},
+      "source": [
+        "# Cohere\n",
+        "\n",
+        "This notebook covers how to get started with [Cohere chat models](https://cohere.com/chat).\n",
+        "\n",
+        "Head to the [API reference](https://python.langchain.com/api_reference/community/chat_models/langchain_community.chat_models.cohere.ChatCohere.html) for detailed documentation of all attributes and methods."
       ]
-     },
-     "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": []
-   },
-   "outputs": [
+    },
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "4 && 5"
-     ]
-    }
-   ],
-   "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')]"
+      "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",
+        "\n",
+        "```bash\n",
+        "pip install -U langchain-cohere\n",
+        "```\n",
+        "\n",
+        "We'll also need to get a [Cohere API key](https://cohere.com/) and set the `COHERE_API_KEY` environment variable:"
       ]
-     },
-     "execution_count": 18,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chat.batch([messages])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "f1c56460",
-   "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/lcel)"
-   ]
-  },
-  {
-   "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",
-   "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')"
+      "cell_type": "code",
+      "execution_count": 11,
+      "id": "2108b517-1e8d-473d-92fa-4f930e8072a7",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import getpass\n",
+        "import os\n",
+        "\n",
+        "os.environ[\"COHERE_API_KEY\"] = getpass.getpass()"
       ]
-     },
-     "execution_count": 20,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chain.invoke({\"topic\": \"bears\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "12db8d69",
-   "metadata": {},
-   "source": [
-    "## Tool calling\n",
-    "\n",
-    "Cohere supports tool calling functionalities!"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "337e24af",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.messages import (\n",
-    "    HumanMessage,\n",
-    "    ToolMessage,\n",
-    ")\n",
-    "from langchain_core.tools import tool"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "74d292e7",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "@tool\n",
-    "def magic_function(number: int) -> int:\n",
-    "    \"\"\"Applies a magic operation to an integer\n",
-    "    Args:\n",
-    "        number: Number to have magic operation performed on\n",
-    "    \"\"\"\n",
-    "    return number + 10\n",
-    "\n",
-    "\n",
-    "def invoke_tools(tool_calls, messages):\n",
-    "    for tool_call in tool_calls:\n",
-    "        selected_tool = {\"magic_function\": magic_function}[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",
-    "    return messages\n",
-    "\n",
-    "\n",
-    "tools = [magic_function]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "ecafcbc6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm_with_tools = chat.bind_tools(tools=tools)\n",
-    "messages = [HumanMessage(content=\"What is the value of magic_function(2)?\")]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "aa34fc39",
-   "metadata": {},
-   "outputs": [
+    },
     {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='The value of magic_function(2) is 12.', additional_kwargs={'documents': [{'id': 'magic_function:0:2:0', 'output': '12', 'tool_name': 'magic_function'}], 'citations': [ChatCitation(start=34, end=36, text='12', document_ids=['magic_function:0:2:0'])], 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '96a55791-0c58-4e2e-bc2a-8550e137c46d', 'token_count': {'input_tokens': 998, 'output_tokens': 59}}, response_metadata={'documents': [{'id': 'magic_function:0:2:0', 'output': '12', 'tool_name': 'magic_function'}], 'citations': [ChatCitation(start=34, end=36, text='12', document_ids=['magic_function:0:2:0'])], 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '96a55791-0c58-4e2e-bc2a-8550e137c46d', 'token_count': {'input_tokens': 998, 'output_tokens': 59}}, id='run-f318a9cf-55c8-44f4-91d1-27cf46c6a465-0')"
+      "cell_type": "markdown",
+      "id": "cf690fbb",
+      "metadata": {},
+      "source": [
+        "It's also helpful (but not needed) to set up [LangSmith](https://smith.langchain.com/) for best-in-class observability"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "3c2fc2201dc80557",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# os.environ[\"LANGSMITH_TRACING\"] = \"true\"\n",
+        "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "31f2af10e04dec59",
+      "metadata": {},
+      "source": [
+        "## Usage\n",
+        "\n",
+        "ChatCohere supports all [ChatModel](/docs/how_to#chat-models) functionality:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "fa83b00a929614ad",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from langchain_cohere import ChatCohere\n",
+        "from langchain_core.messages import HumanMessage"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 13,
+      "id": "70cf04e8-423a-4ff6-8b09-f11fb711c817",
+      "metadata": {
+        "tags": []
+      },
+      "outputs": [],
+      "source": [
+        "chat = ChatCohere()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 15,
+      "id": "8199ef8f-eb8b-4253-9ea0-6c24a013ca4c",
+      "metadata": {
+        "tags": []
+      },
+      "outputs": [
+        {
+          "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')"
+            ]
+          },
+          "execution_count": 15,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "messages = [HumanMessage(content=\"1\"), HumanMessage(content=\"2 3\")]\n",
+        "chat.invoke(messages)"
+      ]
+    },
+    {
+      "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": []
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "4 && 5"
+          ]
+        }
+      ],
+      "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])"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "f1c56460",
+      "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/lcel)"
+      ]
+    },
+    {
+      "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",
+      "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')"
+            ]
+          },
+          "execution_count": 20,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "chain.invoke({\"topic\": \"bears\"})"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "12db8d69",
+      "metadata": {},
+      "source": [
+        "## Tool calling\n",
+        "\n",
+        "Cohere supports tool calling functionalities!"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 7,
+      "id": "337e24af",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from langchain_core.messages import (\n",
+        "    HumanMessage,\n",
+        "    ToolMessage,\n",
+        ")\n",
+        "from langchain_core.tools import tool"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 8,
+      "id": "74d292e7",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "@tool\n",
+        "def magic_function(number: int) -> int:\n",
+        "    \"\"\"Applies a magic operation to an integer\n",
+        "    Args:\n",
+        "        number: Number to have magic operation performed on\n",
+        "    \"\"\"\n",
+        "    return number + 10\n",
+        "\n",
+        "\n",
+        "def invoke_tools(tool_calls, messages):\n",
+        "    for tool_call in tool_calls:\n",
+        "        selected_tool = {\"magic_function\": magic_function}[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",
+        "    return messages\n",
+        "\n",
+        "\n",
+        "tools = [magic_function]"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 9,
+      "id": "ecafcbc6",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "llm_with_tools = chat.bind_tools(tools=tools)\n",
+        "messages = [HumanMessage(content=\"What is the value of magic_function(2)?\")]"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 11,
+      "id": "aa34fc39",
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "AIMessage(content='The value of magic_function(2) is 12.', additional_kwargs={'documents': [{'id': 'magic_function:0:2:0', 'output': '12', 'tool_name': 'magic_function'}], 'citations': [ChatCitation(start=34, end=36, text='12', document_ids=['magic_function:0:2:0'])], 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '96a55791-0c58-4e2e-bc2a-8550e137c46d', 'token_count': {'input_tokens': 998, 'output_tokens': 59}}, response_metadata={'documents': [{'id': 'magic_function:0:2:0', 'output': '12', 'tool_name': 'magic_function'}], 'citations': [ChatCitation(start=34, end=36, text='12', document_ids=['magic_function:0:2:0'])], 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '96a55791-0c58-4e2e-bc2a-8550e137c46d', 'token_count': {'input_tokens': 998, 'output_tokens': 59}}, id='run-f318a9cf-55c8-44f4-91d1-27cf46c6a465-0')"
+            ]
+          },
+          "execution_count": 11,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "res = llm_with_tools.invoke(messages)\n",
+        "while res.tool_calls:\n",
+        "    messages.append(res)\n",
+        "    messages = invoke_tools(res.tool_calls, messages)\n",
+        "    res = llm_with_tools.invoke(messages)\n",
+        "\n",
+        "res"
       ]
-     },
-     "execution_count": 11,
-     "metadata": {},
-     "output_type": "execute_result"
     }
-   ],
-   "source": [
-    "res = llm_with_tools.invoke(messages)\n",
-    "while res.tool_calls:\n",
-    "    messages.append(res)\n",
-    "    messages = invoke_tools(res.tool_calls, messages)\n",
-    "    res = llm_with_tools.invoke(messages)\n",
-    "\n",
-    "res"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
+  ],
+  "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": "3.9.6"
+    }
   },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.9.6"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
+  "nbformat": 4,
+  "nbformat_minor": 5
 }

docs/docs/integrations/chat/deepseek.ipynb

@@ -1,237 +1,235 @@
 {
- "cells": [
-  {
-   "cell_type": "raw",
-   "id": "afaf8039",
-   "metadata": {},
-   "source": [
-    "---\n",
-    "sidebar_label: DeepSeek\n",
-    "---"
-   ]
+  "cells": [
+    {
+      "cell_type": "raw",
+      "id": "afaf8039",
+      "metadata": {},
+      "source": [
+        "---\n",
+        "sidebar_label: DeepSeek\n",
+        "---"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "e49f1e0d",
+      "metadata": {},
+      "source": [
+        "# ChatDeepSeek\n",
+        "\n",
+        "\n",
+        "This will help you getting started with DeepSeek's hosted [chat models](/docs/concepts/chat_models). For detailed documentation of all ChatDeepSeek features and configurations head to the [API reference](https://python.langchain.com/api_reference/deepseek/chat_models/langchain_deepseek.chat_models.ChatDeepSeek.html).\n",
+        "\n",
+        ":::tip\n",
+        "\n",
+        "DeepSeek's models are open source and can be run locally (e.g. in [Ollama](./ollama.ipynb)) or on other inference providers (e.g. [Fireworks](./fireworks.ipynb), [Together](./together.ipynb)) as well.\n",
+        "\n",
+        ":::\n",
+        "\n",
+        "## Overview\n",
+        "### Integration details\n",
+        "\n",
+        "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/docs/integrations/chat/deepseek) | Package downloads | Package latest |\n",
+        "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+        "| [ChatDeepSeek](https://python.langchain.com/api_reference/deepseek/chat_models/langchain_deepseek.chat_models.ChatDeepSeek.html) | [langchain-deepseek](https://python.langchain.com/api_reference/deepseek/) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-deepseek?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-deepseek?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",
+        ":::note\n",
+        "\n",
+        "DeepSeek-R1, specified via `model=\"deepseek-reasoner\"`, does not support tool calling or structured output. Those features [are supported](https://api-docs.deepseek.com/guides/function_calling) by DeepSeek-V3 (specified via `model=\"deepseek-chat\"`).\n",
+        "\n",
+        ":::\n",
+        "\n",
+        "## Setup\n",
+        "\n",
+        "To access DeepSeek models you'll need to create a/an DeepSeek account, get an API key, and install the `langchain-deepseek` integration package.\n",
+        "\n",
+        "### Credentials\n",
+        "\n",
+        "Head to [DeepSeek's API Key page](https://platform.deepseek.com/api_keys) to sign up to DeepSeek and generate an API key. Once you've done this set the `DEEPSEEK_API_KEY` environment variable:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "433e8d2b-9519-4b49-b2c4-7ab65b046c94",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import getpass\n",
+        "import os\n",
+        "\n",
+        "if not os.getenv(\"DEEPSEEK_API_KEY\"):\n",
+        "    os.environ[\"DEEPSEEK_API_KEY\"] = getpass.getpass(\"Enter your DeepSeek API key: \")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "72ee0c4b-9764-423a-9dbf-95129e185210",
+      "metadata": {},
+      "source": "To enable automated tracing of your model calls, set your [LangSmith](https://docs.smith.langchain.com/) API key:"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "a15d341e-3e26-4ca3-830b-5aab30ed66de",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# os.environ[\"LANGSMITH_TRACING\"] = \"true\"\n",
+        "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "0730d6a1-c893-4840-9817-5e5251676d5d",
+      "metadata": {},
+      "source": [
+        "### Installation\n",
+        "\n",
+        "The LangChain DeepSeek integration lives in the `langchain-deepseek` package:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%pip install -qU langchain-deepseek"
+      ]
+    },
+    {
+      "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": null,
+      "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from langchain_deepseek import ChatDeepSeek\n",
+        "\n",
+        "llm = ChatDeepSeek(\n",
+        "    model=\"deepseek-chat\",\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": null,
+      "id": "62e0dbc3",
+      "metadata": {
+        "tags": []
+      },
+      "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",
+        "ai_msg = llm.invoke(messages)\n",
+        "ai_msg.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:"
+      ]
+    },
+    {
+      "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(\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 ChatDeepSeek features and configurations head to the [API Reference](https://python.langchain.com/api_reference/deepseek/chat_models/langchain_deepseek.chat_models.ChatDeepSeek.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": "3.11.9"
+    }
   },
-  {
-   "cell_type": "markdown",
-   "id": "e49f1e0d",
-   "metadata": {},
-   "source": [
-    "# ChatDeepSeek\n",
-    "\n",
-    "\n",
-    "This will help you getting started with DeepSeek's hosted [chat models](/docs/concepts/chat_models). For detailed documentation of all ChatDeepSeek features and configurations head to the [API reference](https://python.langchain.com/api_reference/deepseek/chat_models/langchain_deepseek.chat_models.ChatDeepSeek.html).\n",
-    "\n",
-    ":::tip\n",
-    "\n",
-    "DeepSeek's models are open source and can be run locally (e.g. in [Ollama](./ollama.ipynb)) or on other inference providers (e.g. [Fireworks](./fireworks.ipynb), [Together](./together.ipynb)) as well.\n",
-    "\n",
-    ":::\n",
-    "\n",
-    "## Overview\n",
-    "### Integration details\n",
-    "\n",
-    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/docs/integrations/chat/deepseek) | Package downloads | Package latest |\n",
-    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
-    "| [ChatDeepSeek](https://python.langchain.com/api_reference/deepseek/chat_models/langchain_deepseek.chat_models.ChatDeepSeek.html) | [langchain-deepseek](https://python.langchain.com/api_reference/deepseek/) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-deepseek?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-deepseek?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",
-    ":::note\n",
-    "\n",
-    "DeepSeek-R1, specified via `model=\"deepseek-reasoner\"`, does not support tool calling or structured output. Those features [are supported](https://api-docs.deepseek.com/guides/function_calling) by DeepSeek-V3 (specified via `model=\"deepseek-chat\"`).\n",
-    "\n",
-    ":::\n",
-    "\n",
-    "## Setup\n",
-    "\n",
-    "To access DeepSeek models you'll need to create a/an DeepSeek account, get an API key, and install the `langchain-deepseek` integration package.\n",
-    "\n",
-    "### Credentials\n",
-    "\n",
-    "Head to [DeepSeek's API Key page](https://platform.deepseek.com/api_keys) to sign up to DeepSeek and generate an API key. Once you've done this set the `DEEPSEEK_API_KEY` environment variable:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "433e8d2b-9519-4b49-b2c4-7ab65b046c94",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "if not os.getenv(\"DEEPSEEK_API_KEY\"):\n",
-    "    os.environ[\"DEEPSEEK_API_KEY\"] = getpass.getpass(\"Enter your DeepSeek API key: \")"
-   ]
-  },
-  {
-   "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_TRACING\"] = \"true\"\n",
-    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0730d6a1-c893-4840-9817-5e5251676d5d",
-   "metadata": {},
-   "source": [
-    "### Installation\n",
-    "\n",
-    "The LangChain DeepSeek integration lives in the `langchain-deepseek` package:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%pip install -qU langchain-deepseek"
-   ]
-  },
-  {
-   "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": null,
-   "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_deepseek import ChatDeepSeek\n",
-    "\n",
-    "llm = ChatDeepSeek(\n",
-    "    model=\"deepseek-chat\",\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": null,
-   "id": "62e0dbc3",
-   "metadata": {
-    "tags": []
-   },
-   "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",
-    "ai_msg = llm.invoke(messages)\n",
-    "ai_msg.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:"
-   ]
-  },
-  {
-   "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(\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 ChatDeepSeek features and configurations head to the [API Reference](https://python.langchain.com/api_reference/deepseek/chat_models/langchain_deepseek.chat_models.ChatDeepSeek.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": "3.11.9"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
+  "nbformat": 4,
+  "nbformat_minor": 5
 }

docs/docs/integrations/chat/fireworks.ipynb

@@ -1,268 +1,266 @@
 {
- "cells": [
-  {
-   "cell_type": "raw",
-   "id": "afaf8039",
-   "metadata": {},
-   "source": [
-    "---\n",
-    "sidebar_label: Fireworks\n",
-    "---"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "e49f1e0d",
-   "metadata": {},
-   "source": [
-    "# ChatFireworks\n",
-    "\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://python.langchain.com/api_reference/fireworks/chat_models/langchain_fireworks.chat_models.ChatFireworks.html).\n",
-    "\n",
-    "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/docs/integrations/chat/fireworks) | Package downloads | Package latest |\n",
-    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
-    "| [ChatFireworks](https://python.langchain.com/api_reference/fireworks/chat_models/langchain_fireworks.chat_models.ChatFireworks.html) | [langchain-fireworks](https://python.langchain.com/api_reference/fireworks/index.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": 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(\"Enter your Fireworks API key: \")"
-   ]
-  },
-  {
-   "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 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": [
+  "cells": [
     {
-     "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})"
+      "cell_type": "raw",
+      "id": "afaf8039",
+      "metadata": {},
+      "source": [
+        "---\n",
+        "sidebar_label: Fireworks\n",
+        "---"
       ]
-     },
-     "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": "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": "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:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
-   "metadata": {},
-   "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})"
+      "cell_type": "markdown",
+      "id": "e49f1e0d",
+      "metadata": {},
+      "source": [
+        "# ChatFireworks\n",
+        "\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://python.langchain.com/api_reference/fireworks/chat_models/langchain_fireworks.chat_models.ChatFireworks.html).\n",
+        "\n",
+        "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/docs/integrations/chat/fireworks) | Package downloads | Package latest |\n",
+        "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+        "| [ChatFireworks](https://python.langchain.com/api_reference/fireworks/chat_models/langchain_fireworks.chat_models.ChatFireworks.html) | [langchain-fireworks](https://python.langchain.com/api_reference/fireworks/index.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": 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(\"Enter your Fireworks API key: \")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "72ee0c4b-9764-423a-9dbf-95129e185210",
+      "metadata": {},
+      "source": "To enable automated tracing of your model calls, set your [LangSmith](https://docs.smith.langchain.com/) API key:"
+    },
+    {
+      "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 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": "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": "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:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 4,
+      "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
+      "metadata": {},
+      "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://python.langchain.com/api_reference/fireworks/chat_models/langchain_fireworks.chat_models.ChatFireworks.html"
       ]
-     },
-     "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",
-    ")"
-   ]
+  ],
+  "metadata": {
+    "kernelspec": {
+      "display_name": "Python 3 (ipykernel)",
+      "language": "python",
+      "name": "python3"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.11.9"
+    }
   },
-  {
-   "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://python.langchain.com/api_reference/fireworks/chat_models/langchain_fireworks.chat_models.ChatFireworks.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": "3.11.9"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
+  "nbformat": 4,
+  "nbformat_minor": 5
 }

docs/docs/integrations/chat/goodfire.ipynb

@@ -1,354 +1,352 @@
 {
- "cells": [
-  {
-   "cell_type": "raw",
-   "id": "afaf8039",
-   "metadata": {},
-   "source": [
-    "---\n",
-    "sidebar_label: Goodfire\n",
-    "---"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "e49f1e0d",
-   "metadata": {},
-   "source": [
-    "# ChatGoodfire\n",
-    "\n",
-    "This will help you getting started with Goodfire [chat models](/docs/concepts/chat_models). For detailed documentation of all ChatGoodfire features and configurations head to the [PyPI project page](https://pypi.org/project/langchain-goodfire/), or go directly to the [Goodfire SDK docs](https://docs.goodfire.ai/sdk-reference/example). All of the Goodfire-specific functionality (e.g. SAE features, variants, etc.) is available via the main `goodfire` package. This integration is a wrapper around the Goodfire SDK.\n",
-    "\n",
-    "## Overview\n",
-    "### Integration details\n",
-    "\n",
-    "| Class | Package | Local | Serializable | JS support | Package downloads | Package latest |\n",
-    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
-    "| [ChatGoodfire](https://python.langchain.com/api_reference/goodfire/chat_models/langchain_goodfire.chat_models.ChatGoodfire.html) | [langchain-goodfire](https://python.langchain.com/api_reference/goodfire/) | ❌ | ❌ | ❌ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-goodfire?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-goodfire?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 Goodfire models you'll need to create a/an Goodfire account, get an API key, and install the `langchain-goodfire` integration package.\n",
-    "\n",
-    "### Credentials\n",
-    "\n",
-    "Head to [Goodfire Settings](https://platform.goodfire.ai/organization/settings/api-keys) to sign up to Goodfire and generate an API key. Once you've done this set the GOODFIRE_API_KEY environment variable."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "433e8d2b-9519-4b49-b2c4-7ab65b046c94",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "if not os.getenv(\"GOODFIRE_API_KEY\"):\n",
-    "    os.environ[\"GOODFIRE_API_KEY\"] = getpass.getpass(\"Enter your Goodfire API key: \")"
-   ]
-  },
-  {
-   "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_TRACING\"] = \"true\"\n",
-    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0730d6a1-c893-4840-9817-5e5251676d5d",
-   "metadata": {},
-   "source": [
-    "### Installation\n",
-    "\n",
-    "The LangChain Goodfire integration lives in the `langchain-goodfire` package:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
-   "metadata": {},
-   "outputs": [
+  "cells": [
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Note: you may need to restart the kernel to use updated packages.\n"
-     ]
-    }
-   ],
-   "source": [
-    "%pip install -qU langchain-goodfire"
-   ]
-  },
-  {
-   "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": 3,
-   "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used.\n"
-     ]
-    }
-   ],
-   "source": [
-    "import goodfire\n",
-    "from langchain_goodfire import ChatGoodfire\n",
-    "\n",
-    "base_variant = goodfire.Variant(\"meta-llama/Llama-3.3-70B-Instruct\")\n",
-    "\n",
-    "llm = ChatGoodfire(\n",
-    "    model=base_variant,\n",
-    "    temperature=0,\n",
-    "    max_completion_tokens=1000,\n",
-    "    seed=42,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2b4f3e15",
-   "metadata": {},
-   "source": [
-    "## Invocation"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "62e0dbc3",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\"J'adore la programmation.\", additional_kwargs={}, response_metadata={}, id='run-8d43cf35-bce8-4827-8935-c64f8fb78cd0-0', usage_metadata={'input_tokens': 51, 'output_tokens': 39, 'total_tokens': 90})"
+      "cell_type": "raw",
+      "id": "afaf8039",
+      "metadata": {},
+      "source": [
+        "---\n",
+        "sidebar_label: Goodfire\n",
+        "---"
       ]
-     },
-     "execution_count": 4,
-     "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 = await llm.ainvoke(messages)\n",
-    "ai_msg"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "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": "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:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='Ich liebe das Programmieren. How can I help you with programming today?', additional_kwargs={}, response_metadata={}, id='run-03d1a585-8234-46f1-a8df-bf9143fe3309-0', usage_metadata={'input_tokens': 46, 'output_tokens': 46, 'total_tokens': 92})"
+      "cell_type": "markdown",
+      "id": "e49f1e0d",
+      "metadata": {},
+      "source": [
+        "# ChatGoodfire\n",
+        "\n",
+        "This will help you getting started with Goodfire [chat models](/docs/concepts/chat_models). For detailed documentation of all ChatGoodfire features and configurations head to the [PyPI project page](https://pypi.org/project/langchain-goodfire/), or go directly to the [Goodfire SDK docs](https://docs.goodfire.ai/sdk-reference/example). All of the Goodfire-specific functionality (e.g. SAE features, variants, etc.) is available via the main `goodfire` package. This integration is a wrapper around the Goodfire SDK.\n",
+        "\n",
+        "## Overview\n",
+        "### Integration details\n",
+        "\n",
+        "| Class | Package | Local | Serializable | JS support | Package downloads | Package latest |\n",
+        "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+        "| [ChatGoodfire](https://python.langchain.com/api_reference/goodfire/chat_models/langchain_goodfire.chat_models.ChatGoodfire.html) | [langchain-goodfire](https://python.langchain.com/api_reference/goodfire/) | ❌ | ❌ | ❌ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-goodfire?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-goodfire?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 Goodfire models you'll need to create a/an Goodfire account, get an API key, and install the `langchain-goodfire` integration package.\n",
+        "\n",
+        "### Credentials\n",
+        "\n",
+        "Head to [Goodfire Settings](https://platform.goodfire.ai/organization/settings/api-keys) to sign up to Goodfire and generate an API key. Once you've done this set the GOODFIRE_API_KEY environment variable."
       ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "\n",
-    "prompt = ChatPromptTemplate(\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",
-    "await chain.ainvoke(\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": [
-    "## Goodfire-specific functionality\n",
-    "\n",
-    "To use Goodfire-specific functionality such as SAE features and variants, you can use the `goodfire` package directly."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "3aef9e0a",
-   "metadata": {},
-   "outputs": [
+    },
     {
-     "data": {
-      "text/plain": [
-       "FeatureGroup([\n",
-       "   0: \"The assistant should adopt the persona of a pirate\",\n",
-       "   1: \"The assistant should roleplay as a pirate\",\n",
-       "   2: \"The assistant should engage with pirate-themed content or roleplay as a pirate\",\n",
-       "   3: \"The assistant should roleplay as a character\",\n",
-       "   4: \"The assistant should roleplay as a specific character\",\n",
-       "   5: \"The assistant should roleplay as a game character or NPC\",\n",
-       "   6: \"The assistant should roleplay as a human character\",\n",
-       "   7: \"Requests for the assistant to roleplay or pretend to be something else\",\n",
-       "   8: \"Requests for the assistant to roleplay or pretend to be something\",\n",
-       "   9: \"The assistant is being assigned a role or persona to roleplay\"\n",
-       "])"
+      "cell_type": "code",
+      "execution_count": 1,
+      "id": "433e8d2b-9519-4b49-b2c4-7ab65b046c94",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import getpass\n",
+        "import os\n",
+        "\n",
+        "if not os.getenv(\"GOODFIRE_API_KEY\"):\n",
+        "    os.environ[\"GOODFIRE_API_KEY\"] = getpass.getpass(\"Enter your Goodfire API key: \")"
       ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "client = goodfire.Client(api_key=os.environ[\"GOODFIRE_API_KEY\"])\n",
-    "\n",
-    "pirate_features = client.features.search(\n",
-    "    \"assistant should roleplay as a pirate\", base_variant\n",
-    ")\n",
-    "pirate_features"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "52f03a00",
-   "metadata": {},
-   "outputs": [
+    },
     {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='Why did the scarecrow win an award? Because he was outstanding in his field! Arrr! Hope that made ye laugh, matey!', additional_kwargs={}, response_metadata={}, id='run-7d8bd30f-7f80-41cb-bdb6-25c29c22a7ce-0', usage_metadata={'input_tokens': 35, 'output_tokens': 60, 'total_tokens': 95})"
+      "cell_type": "markdown",
+      "id": "72ee0c4b-9764-423a-9dbf-95129e185210",
+      "metadata": {},
+      "source": "To enable automated tracing of your model calls, set your [LangSmith](https://docs.smith.langchain.com/) API key:"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "a15d341e-3e26-4ca3-830b-5aab30ed66de",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# os.environ[\"LANGSMITH_TRACING\"] = \"true\"\n",
+        "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "0730d6a1-c893-4840-9817-5e5251676d5d",
+      "metadata": {},
+      "source": [
+        "### Installation\n",
+        "\n",
+        "The LangChain Goodfire integration lives in the `langchain-goodfire` package:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 2,
+      "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Note: you may need to restart the kernel to use updated packages.\n"
+          ]
+        }
+      ],
+      "source": [
+        "%pip install -qU langchain-goodfire"
+      ]
+    },
+    {
+      "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": 3,
+      "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used.\n"
+          ]
+        }
+      ],
+      "source": [
+        "import goodfire\n",
+        "from langchain_goodfire import ChatGoodfire\n",
+        "\n",
+        "base_variant = goodfire.Variant(\"meta-llama/Llama-3.3-70B-Instruct\")\n",
+        "\n",
+        "llm = ChatGoodfire(\n",
+        "    model=base_variant,\n",
+        "    temperature=0,\n",
+        "    max_completion_tokens=1000,\n",
+        "    seed=42,\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "2b4f3e15",
+      "metadata": {},
+      "source": [
+        "## Invocation"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 4,
+      "id": "62e0dbc3",
+      "metadata": {
+        "tags": []
+      },
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "AIMessage(content=\"J'adore la programmation.\", additional_kwargs={}, response_metadata={}, id='run-8d43cf35-bce8-4827-8935-c64f8fb78cd0-0', usage_metadata={'input_tokens': 51, 'output_tokens': 39, 'total_tokens': 90})"
+            ]
+          },
+          "execution_count": 4,
+          "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 = await llm.ainvoke(messages)\n",
+        "ai_msg"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 5,
+      "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": "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:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 6,
+      "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "AIMessage(content='Ich liebe das Programmieren. How can I help you with programming today?', additional_kwargs={}, response_metadata={}, id='run-03d1a585-8234-46f1-a8df-bf9143fe3309-0', usage_metadata={'input_tokens': 46, 'output_tokens': 46, 'total_tokens': 92})"
+            ]
+          },
+          "execution_count": 6,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "from langchain_core.prompts import ChatPromptTemplate\n",
+        "\n",
+        "prompt = ChatPromptTemplate(\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",
+        "await chain.ainvoke(\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": [
+        "## Goodfire-specific functionality\n",
+        "\n",
+        "To use Goodfire-specific functionality such as SAE features and variants, you can use the `goodfire` package directly."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 7,
+      "id": "3aef9e0a",
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "FeatureGroup([\n",
+              "   0: \"The assistant should adopt the persona of a pirate\",\n",
+              "   1: \"The assistant should roleplay as a pirate\",\n",
+              "   2: \"The assistant should engage with pirate-themed content or roleplay as a pirate\",\n",
+              "   3: \"The assistant should roleplay as a character\",\n",
+              "   4: \"The assistant should roleplay as a specific character\",\n",
+              "   5: \"The assistant should roleplay as a game character or NPC\",\n",
+              "   6: \"The assistant should roleplay as a human character\",\n",
+              "   7: \"Requests for the assistant to roleplay or pretend to be something else\",\n",
+              "   8: \"Requests for the assistant to roleplay or pretend to be something\",\n",
+              "   9: \"The assistant is being assigned a role or persona to roleplay\"\n",
+              "])"
+            ]
+          },
+          "execution_count": 7,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "client = goodfire.Client(api_key=os.environ[\"GOODFIRE_API_KEY\"])\n",
+        "\n",
+        "pirate_features = client.features.search(\n",
+        "    \"assistant should roleplay as a pirate\", base_variant\n",
+        ")\n",
+        "pirate_features"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 8,
+      "id": "52f03a00",
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "AIMessage(content='Why did the scarecrow win an award? Because he was outstanding in his field! Arrr! Hope that made ye laugh, matey!', additional_kwargs={}, response_metadata={}, id='run-7d8bd30f-7f80-41cb-bdb6-25c29c22a7ce-0', usage_metadata={'input_tokens': 35, 'output_tokens': 60, 'total_tokens': 95})"
+            ]
+          },
+          "execution_count": 8,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "pirate_variant = goodfire.Variant(\"meta-llama/Llama-3.3-70B-Instruct\")\n",
+        "\n",
+        "pirate_variant.set(pirate_features[0], 0.4)\n",
+        "pirate_variant.set(pirate_features[1], 0.3)\n",
+        "\n",
+        "await llm.ainvoke(\"Tell me a joke\", model=pirate_variant)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
+      "metadata": {},
+      "source": [
+        "## API reference\n",
+        "\n",
+        "For detailed documentation of all ChatGoodfire features and configurations head to the [API reference](https://python.langchain.com/api_reference/goodfire/chat_models/langchain_goodfire.chat_models.ChatGoodfire.html)"
       ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
     }
-   ],
-   "source": [
-    "pirate_variant = goodfire.Variant(\"meta-llama/Llama-3.3-70B-Instruct\")\n",
-    "\n",
-    "pirate_variant.set(pirate_features[0], 0.4)\n",
-    "pirate_variant.set(pirate_features[1], 0.3)\n",
-    "\n",
-    "await llm.ainvoke(\"Tell me a joke\", model=pirate_variant)"
-   ]
+  ],
+  "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": "3.12.8"
+    }
   },
-  {
-   "cell_type": "markdown",
-   "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
-   "metadata": {},
-   "source": [
-    "## API reference\n",
-    "\n",
-    "For detailed documentation of all ChatGoodfire features and configurations head to the [API reference](https://python.langchain.com/api_reference/goodfire/chat_models/langchain_goodfire.chat_models.ChatGoodfire.html)"
-   ]
-  }
- ],
- "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": "3.12.8"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
+  "nbformat": 4,
+  "nbformat_minor": 5
 }

docs/docs/integrations/chat/google_vertex_ai_palm.ipynb

@@ -1,269 +1,269 @@
 {
- "cells": [
-  {
-   "cell_type": "raw",
-   "id": "afaf8039",
-   "metadata": {},
-   "source": [
-    "---\n",
-    "sidebar_label: Google Cloud Vertex AI\n",
-    "---"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "e49f1e0d",
-   "metadata": {},
-   "source": [
-    "# ChatVertexAI\n",
-    "\n",
-    "This page provides a quick overview for getting started with VertexAI [chat models](/docs/concepts/chat_models). For detailed documentation of all ChatVertexAI features and configurations head to the [API reference](https://python.langchain.com/api_reference/google_vertexai/chat_models/langchain_google_vertexai.chat_models.ChatVertexAI.html).\n",
-    "\n",
-    "ChatVertexAI exposes all foundational models available in Google Cloud, like `gemini-1.5-pro`, `gemini-1.5-flash`, etc. For a full and updated list of available models visit [VertexAI documentation](https://cloud.google.com/vertex-ai/docs/generative-ai/model-reference/overview).\n",
-    "\n",
-    ":::info Google Cloud VertexAI vs Google PaLM\n",
-    "\n",
-    "The Google Cloud VertexAI integration is separate from the [Google PaLM integration](/docs/integrations/chat/google_generative_ai/). Google has chosen to offer an enterprise version of PaLM through GCP, and this supports the models made available through there. \n",
-    "\n",
-    ":::\n",
-    "\n",
-    "## Overview\n",
-    "### Integration details\n",
-    "\n",
-    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/docs/integrations/chat/google_vertex_ai) | Package downloads | Package latest |\n",
-    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
-    "| [ChatVertexAI](https://python.langchain.com/api_reference/google_vertexai/chat_models/langchain_google_vertexai.chat_models.ChatVertexAI.html) | [langchain-google-vertexai](https://python.langchain.com/api_reference/google_vertexai/index.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",
-    "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
-    "| ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | \n",
-    "\n",
-    "## Setup\n",
-    "\n",
-    "To access VertexAI models you'll need to create a Google Cloud Platform account, set up credentials, and install the `langchain-google-vertexai` integration package.\n",
-    "\n",
-    "### Credentials\n",
-    "\n",
-    "To use the integration you must:\n",
-    "- Have credentials configured for your environment (gcloud, workload identity, etc...)\n",
-    "- Store the path to a service account JSON file as the GOOGLE_APPLICATION_CREDENTIALS environment variable\n",
-    "\n",
-    "This codebase uses the `google.auth` library which first looks for the application credentials variable mentioned above, and then looks for system-level auth.\n",
-    "\n",
-    "For more information, see: \n",
-    "- https://cloud.google.com/docs/authentication/application-default-credentials#GAC\n",
-    "- https://googleapis.dev/python/google-auth/latest/reference/google.auth.html#module-google.auth\n",
-    "\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": 1,
-   "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 VertexAI integration lives in the `langchain-google-vertexai` package:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
-   "metadata": {},
-   "outputs": [
+  "cells": [
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Note: you may need to restart the kernel to use updated packages.\n"
-     ]
-    }
-   ],
-   "source": [
-    "%pip install -qU langchain-google-vertexai"
-   ]
-  },
-  {
-   "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": 3,
-   "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_google_vertexai import ChatVertexAI\n",
-    "\n",
-    "llm = ChatVertexAI(\n",
-    "    model=\"gemini-1.5-flash-001\",\n",
-    "    temperature=0,\n",
-    "    max_tokens=None,\n",
-    "    max_retries=6,\n",
-    "    stop=None,\n",
-    "    # other params...\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2b4f3e15",
-   "metadata": {},
-   "source": [
-    "## Invocation"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "62e0dbc3",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\"J'adore programmer. \\n\", response_metadata={'is_blocked': False, 'safety_ratings': [{'category': 'HARM_CATEGORY_HATE_SPEECH', 'probability_label': 'NEGLIGIBLE', 'blocked': False}, {'category': 'HARM_CATEGORY_DANGEROUS_CONTENT', 'probability_label': 'NEGLIGIBLE', 'blocked': False}, {'category': 'HARM_CATEGORY_HARASSMENT', 'probability_label': 'NEGLIGIBLE', 'blocked': False}, {'category': 'HARM_CATEGORY_SEXUALLY_EXPLICIT', 'probability_label': 'NEGLIGIBLE', 'blocked': False}], 'usage_metadata': {'prompt_token_count': 20, 'candidates_token_count': 7, 'total_token_count': 27}}, id='run-7032733c-d05c-4f0c-a17a-6c575fdd1ae0-0', usage_metadata={'input_tokens': 20, 'output_tokens': 7, 'total_tokens': 27})"
+      "cell_type": "raw",
+      "id": "afaf8039",
+      "metadata": {},
+      "source": [
+        "---\n",
+        "sidebar_label: Google Cloud Vertex AI\n",
+        "---"
       ]
-     },
-     "execution_count": 4,
-     "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": 5,
-   "id": "d86145b3-bfef-46e8-b227-4dda5c9c2705",
-   "metadata": {},
-   "outputs": [
+    },
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "J'adore programmer. \n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(ai_msg.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:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='Ich liebe Programmieren. \\n', response_metadata={'is_blocked': False, 'safety_ratings': [{'category': 'HARM_CATEGORY_HATE_SPEECH', 'probability_label': 'NEGLIGIBLE', 'blocked': False}, {'category': 'HARM_CATEGORY_DANGEROUS_CONTENT', 'probability_label': 'NEGLIGIBLE', 'blocked': False}, {'category': 'HARM_CATEGORY_HARASSMENT', 'probability_label': 'NEGLIGIBLE', 'blocked': False}, {'category': 'HARM_CATEGORY_SEXUALLY_EXPLICIT', 'probability_label': 'NEGLIGIBLE', 'blocked': False}], 'usage_metadata': {'prompt_token_count': 15, 'candidates_token_count': 8, 'total_token_count': 23}}, id='run-c71955fd-8dc1-422b-88a7-853accf4811b-0', usage_metadata={'input_tokens': 15, 'output_tokens': 8, 'total_tokens': 23})"
+      "cell_type": "markdown",
+      "id": "e49f1e0d",
+      "metadata": {},
+      "source": [
+        "# ChatVertexAI\n",
+        "\n",
+        "This page provides a quick overview for getting started with VertexAI [chat models](/docs/concepts/chat_models). For detailed documentation of all ChatVertexAI features and configurations head to the [API reference](https://python.langchain.com/api_reference/google_vertexai/chat_models/langchain_google_vertexai.chat_models.ChatVertexAI.html).\n",
+        "\n",
+        "ChatVertexAI exposes all foundational models available in Google Cloud, like `gemini-1.5-pro`, `gemini-1.5-flash`, etc. For a full and updated list of available models visit [VertexAI documentation](https://cloud.google.com/vertex-ai/docs/generative-ai/model-reference/overview).\n",
+        "\n",
+        ":::info Google Cloud VertexAI vs Google PaLM\n",
+        "\n",
+        "The Google Cloud VertexAI integration is separate from the [Google PaLM integration](/docs/integrations/chat/google_generative_ai/). Google has chosen to offer an enterprise version of PaLM through GCP, and this supports the models made available through there.\n",
+        "\n",
+        ":::\n",
+        "\n",
+        "## Overview\n",
+        "### Integration details\n",
+        "\n",
+        "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/docs/integrations/chat/google_vertex_ai) | Package downloads | Package latest |\n",
+        "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+        "| [ChatVertexAI](https://python.langchain.com/api_reference/google_vertexai/chat_models/langchain_google_vertexai.chat_models.ChatVertexAI.html) | [langchain-google-vertexai](https://python.langchain.com/api_reference/google_vertexai/index.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",
+        "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
+        "| ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ |\n",
+        "\n",
+        "## Setup\n",
+        "\n",
+        "To access VertexAI models you'll need to create a Google Cloud Platform account, set up credentials, and install the `langchain-google-vertexai` integration package.\n",
+        "\n",
+        "### Credentials\n",
+        "\n",
+        "To use the integration you must:\n",
+        "- Have credentials configured for your environment (gcloud, workload identity, etc...)\n",
+        "- Store the path to a service account JSON file as the GOOGLE_APPLICATION_CREDENTIALS environment variable\n",
+        "\n",
+        "This codebase uses the `google.auth` library which first looks for the application credentials variable mentioned above, and then looks for system-level auth.\n",
+        "\n",
+        "For more information, see:\n",
+        "- https://cloud.google.com/docs/authentication/application-default-credentials#GAC\n",
+        "- https://googleapis.dev/python/google-auth/latest/reference/google.auth.html#module-google.auth\n",
+        "\n",
+        "To enable automated tracing of your model calls, set your [LangSmith](https://docs.smith.langchain.com/) API key:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 1,
+      "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 VertexAI integration lives in the `langchain-google-vertexai` package:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 2,
+      "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Note: you may need to restart the kernel to use updated packages.\n"
+          ]
+        }
+      ],
+      "source": [
+        "%pip install -qU langchain-google-vertexai"
+      ]
+    },
+    {
+      "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": 3,
+      "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from langchain_google_vertexai import ChatVertexAI\n",
+        "\n",
+        "llm = ChatVertexAI(\n",
+        "    model=\"gemini-1.5-flash-001\",\n",
+        "    temperature=0,\n",
+        "    max_tokens=None,\n",
+        "    max_retries=6,\n",
+        "    stop=None,\n",
+        "    # other params...\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "2b4f3e15",
+      "metadata": {},
+      "source": [
+        "## Invocation"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 4,
+      "id": "62e0dbc3",
+      "metadata": {
+        "tags": []
+      },
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "AIMessage(content=\"J'adore programmer. \\n\", response_metadata={'is_blocked': False, 'safety_ratings': [{'category': 'HARM_CATEGORY_HATE_SPEECH', 'probability_label': 'NEGLIGIBLE', 'blocked': False}, {'category': 'HARM_CATEGORY_DANGEROUS_CONTENT', 'probability_label': 'NEGLIGIBLE', 'blocked': False}, {'category': 'HARM_CATEGORY_HARASSMENT', 'probability_label': 'NEGLIGIBLE', 'blocked': False}, {'category': 'HARM_CATEGORY_SEXUALLY_EXPLICIT', 'probability_label': 'NEGLIGIBLE', 'blocked': False}], 'usage_metadata': {'prompt_token_count': 20, 'candidates_token_count': 7, 'total_token_count': 27}}, id='run-7032733c-d05c-4f0c-a17a-6c575fdd1ae0-0', usage_metadata={'input_tokens': 20, 'output_tokens': 7, 'total_tokens': 27})"
+            ]
+          },
+          "execution_count": 4,
+          "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": 5,
+      "id": "d86145b3-bfef-46e8-b227-4dda5c9c2705",
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "J'adore programmer. \n",
+            "\n"
+          ]
+        }
+      ],
+      "source": [
+        "print(ai_msg.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:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 6,
+      "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "AIMessage(content='Ich liebe Programmieren. \\n', response_metadata={'is_blocked': False, 'safety_ratings': [{'category': 'HARM_CATEGORY_HATE_SPEECH', 'probability_label': 'NEGLIGIBLE', 'blocked': False}, {'category': 'HARM_CATEGORY_DANGEROUS_CONTENT', 'probability_label': 'NEGLIGIBLE', 'blocked': False}, {'category': 'HARM_CATEGORY_HARASSMENT', 'probability_label': 'NEGLIGIBLE', 'blocked': False}, {'category': 'HARM_CATEGORY_SEXUALLY_EXPLICIT', 'probability_label': 'NEGLIGIBLE', 'blocked': False}], 'usage_metadata': {'prompt_token_count': 15, 'candidates_token_count': 8, 'total_token_count': 23}}, id='run-c71955fd-8dc1-422b-88a7-853accf4811b-0', usage_metadata={'input_tokens': 15, 'output_tokens': 8, 'total_tokens': 23})"
+            ]
+          },
+          "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 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 ChatVertexAI features and configurations, like how to send multimodal inputs and configure safety settings, head to the API reference: https://python.langchain.com/api_reference/google_vertexai/chat_models/langchain_google_vertexai.chat_models.ChatVertexAI.html"
       ]
-     },
-     "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 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",
-    ")"
-   ]
+  ],
+  "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"
+    }
   },
-  {
-   "cell_type": "markdown",
-   "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
-   "metadata": {},
-   "source": [
-    "## API reference\n",
-    "\n",
-    "For detailed documentation of all ChatVertexAI features and configurations, like how to send multimodal inputs and configure safety settings, head to the API reference: https://python.langchain.com/api_reference/google_vertexai/chat_models/langchain_google_vertexai.chat_models.ChatVertexAI.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
+  "nbformat": 4,
+  "nbformat_minor": 5
 }

docs/docs/integrations/chat/groq.ipynb

@@ -1,266 +1,264 @@
 {
- "cells": [
-  {
-   "cell_type": "raw",
-   "id": "afaf8039",
-   "metadata": {},
-   "source": [
-    "---\n",
-    "sidebar_label: Groq\n",
-    "---"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "e49f1e0d",
-   "metadata": {},
-   "source": [
-    "# ChatGroq\n",
-    "\n",
-    "This will help you getting started with Groq [chat models](../../concepts/chat_models.mdx). For detailed documentation of all ChatGroq features and configurations head to the [API reference](https://python.langchain.com/api_reference/groq/chat_models/langchain_groq.chat_models.ChatGroq.html). For a list of all Groq models, visit this [link](https://console.groq.com/docs/models?utm_source=langchain).\n",
-    "\n",
-    "## Overview\n",
-    "### Integration details\n",
-    "\n",
-    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/docs/integrations/chat/groq) | Package downloads | Package latest |\n",
-    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
-    "| [ChatGroq](https://python.langchain.com/api_reference/groq/chat_models/langchain_groq.chat_models.ChatGroq.html) | [langchain-groq](https://python.langchain.com/api_reference/groq/index.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-groq?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-groq?style=flat-square&label=%20) |\n",
-    "\n",
-    "### Model features\n",
-    "| [Tool calling](../../how_to/tool_calling.ipynb) | [Structured output](../../how_to/structured_output.ipynb) | JSON mode | [Image input](../../how_to/multimodal_inputs.ipynb) | Audio input | Video input | [Token-level streaming](../../how_to/chat_streaming.ipynb) | Native async | [Token usage](../../how_to/chat_token_usage_tracking.ipynb) | [Logprobs](../../how_to/logprobs.ipynb) |\n",
-    "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
-    "| ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | ✅ | ✅ | ✅ | \n",
-    "\n",
-    "## Setup\n",
-    "\n",
-    "To access Groq models you'll need to create a Groq account, get an API key, and install the `langchain-groq` integration package.\n",
-    "\n",
-    "### Credentials\n",
-    "\n",
-    "Head to the [Groq console](https://console.groq.com/login?utm_source=langchain&utm_content=chat_page) to sign up to Groq and generate an API key. Once you've done this set the GROQ_API_KEY environment variable:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "433e8d2b-9519-4b49-b2c4-7ab65b046c94",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "if \"GROQ_API_KEY\" not in os.environ:\n",
-    "    os.environ[\"GROQ_API_KEY\"] = getpass.getpass(\"Enter your Groq API key: \")"
-   ]
-  },
-  {
-   "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": 2,
-   "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 Groq integration lives in the `langchain-groq` package:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "3f3f510e-2afe-4e76-be41-c5a9665aea63",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%pip install -qU langchain-groq"
-   ]
-  },
-  {
-   "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_groq import ChatGroq\n",
-    "\n",
-    "llm = ChatGroq(\n",
-    "    model=\"llama-3.1-8b-instant\",\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": [
+  "cells": [
     {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='The translation of \"I love programming\" to French is:\\n\\n\"J\\'adore le programmation.\"', additional_kwargs={}, response_metadata={'token_usage': {'completion_tokens': 22, 'prompt_tokens': 55, 'total_tokens': 77, 'completion_time': 0.029333333, 'prompt_time': 0.003502892, 'queue_time': 0.553054073, 'total_time': 0.032836225}, 'model_name': 'llama-3.1-8b-instant', 'system_fingerprint': 'fp_a491995411', 'finish_reason': 'stop', 'logprobs': None}, id='run-2b2da04a-993c-40ab-becc-201eab8b1a1b-0', usage_metadata={'input_tokens': 55, 'output_tokens': 22, 'total_tokens': 77})"
+      "cell_type": "raw",
+      "id": "afaf8039",
+      "metadata": {},
+      "source": [
+        "---\n",
+        "sidebar_label: Groq\n",
+        "---"
       ]
-     },
-     "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": "d86145b3-bfef-46e8-b227-4dda5c9c2705",
-   "metadata": {},
-   "outputs": [
+    },
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "The translation of \"I love programming\" to French is:\n",
-      "\n",
-      "\"J'adore le programmation.\"\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(ai_msg.content)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "18e2bfc0-7e78-4528-a73f-499ac150dca8",
-   "metadata": {},
-   "source": [
-    "## Chaining\n",
-    "\n",
-    "We can [chain](../../how_to/sequence.ipynb) our model with a prompt template like so:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='Ich liebe Programmieren.', additional_kwargs={}, response_metadata={'token_usage': {'completion_tokens': 6, 'prompt_tokens': 50, 'total_tokens': 56, 'completion_time': 0.008, 'prompt_time': 0.003337935, 'queue_time': 0.20949214500000002, 'total_time': 0.011337935}, 'model_name': 'llama-3.1-8b-instant', 'system_fingerprint': 'fp_a491995411', 'finish_reason': 'stop', 'logprobs': None}, id='run-e33b48dc-5e55-466e-9ebd-7b48c81c3cbd-0', usage_metadata={'input_tokens': 50, 'output_tokens': 6, 'total_tokens': 56})"
+      "cell_type": "markdown",
+      "id": "e49f1e0d",
+      "metadata": {},
+      "source": [
+        "# ChatGroq\n",
+        "\n",
+        "This will help you getting started with Groq [chat models](../../concepts/chat_models.mdx). For detailed documentation of all ChatGroq features and configurations head to the [API reference](https://python.langchain.com/api_reference/groq/chat_models/langchain_groq.chat_models.ChatGroq.html). For a list of all Groq models, visit this [link](https://console.groq.com/docs/models?utm_source=langchain).\n",
+        "\n",
+        "## Overview\n",
+        "### Integration details\n",
+        "\n",
+        "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/docs/integrations/chat/groq) | Package downloads | Package latest |\n",
+        "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+        "| [ChatGroq](https://python.langchain.com/api_reference/groq/chat_models/langchain_groq.chat_models.ChatGroq.html) | [langchain-groq](https://python.langchain.com/api_reference/groq/index.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-groq?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-groq?style=flat-square&label=%20) |\n",
+        "\n",
+        "### Model features\n",
+        "| [Tool calling](../../how_to/tool_calling.ipynb) | [Structured output](../../how_to/structured_output.ipynb) | JSON mode | [Image input](../../how_to/multimodal_inputs.ipynb) | Audio input | Video input | [Token-level streaming](../../how_to/chat_streaming.ipynb) | Native async | [Token usage](../../how_to/chat_token_usage_tracking.ipynb) | [Logprobs](../../how_to/logprobs.ipynb) |\n",
+        "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
+        "| ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | ✅ | ✅ | ✅ |\n",
+        "\n",
+        "## Setup\n",
+        "\n",
+        "To access Groq models you'll need to create a Groq account, get an API key, and install the `langchain-groq` integration package.\n",
+        "\n",
+        "### Credentials\n",
+        "\n",
+        "Head to the [Groq console](https://console.groq.com/login?utm_source=langchain&utm_content=chat_page) to sign up to Groq and generate an API key. Once you've done this set the GROQ_API_KEY environment variable:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 1,
+      "id": "433e8d2b-9519-4b49-b2c4-7ab65b046c94",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import getpass\n",
+        "import os\n",
+        "\n",
+        "if \"GROQ_API_KEY\" not in os.environ:\n",
+        "    os.environ[\"GROQ_API_KEY\"] = getpass.getpass(\"Enter your Groq API key: \")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "72ee0c4b-9764-423a-9dbf-95129e185210",
+      "metadata": {},
+      "source": "To enable automated tracing of your model calls, set your [LangSmith](https://docs.smith.langchain.com/) API key:"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 2,
+      "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 Groq integration lives in the `langchain-groq` package:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "3f3f510e-2afe-4e76-be41-c5a9665aea63",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%pip install -qU langchain-groq"
+      ]
+    },
+    {
+      "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_groq import ChatGroq\n",
+        "\n",
+        "llm = ChatGroq(\n",
+        "    model=\"llama-3.1-8b-instant\",\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='The translation of \"I love programming\" to French is:\\n\\n\"J\\'adore le programmation.\"', additional_kwargs={}, response_metadata={'token_usage': {'completion_tokens': 22, 'prompt_tokens': 55, 'total_tokens': 77, 'completion_time': 0.029333333, 'prompt_time': 0.003502892, 'queue_time': 0.553054073, 'total_time': 0.032836225}, 'model_name': 'llama-3.1-8b-instant', 'system_fingerprint': 'fp_a491995411', 'finish_reason': 'stop', 'logprobs': None}, id='run-2b2da04a-993c-40ab-becc-201eab8b1a1b-0', usage_metadata={'input_tokens': 55, 'output_tokens': 22, 'total_tokens': 77})"
+            ]
+          },
+          "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": "d86145b3-bfef-46e8-b227-4dda5c9c2705",
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "The translation of \"I love programming\" to French is:\n",
+            "\n",
+            "\"J'adore le programmation.\"\n"
+          ]
+        }
+      ],
+      "source": [
+        "print(ai_msg.content)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "18e2bfc0-7e78-4528-a73f-499ac150dca8",
+      "metadata": {},
+      "source": [
+        "## Chaining\n",
+        "\n",
+        "We can [chain](../../how_to/sequence.ipynb) our model with a prompt template like so:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 4,
+      "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "AIMessage(content='Ich liebe Programmieren.', additional_kwargs={}, response_metadata={'token_usage': {'completion_tokens': 6, 'prompt_tokens': 50, 'total_tokens': 56, 'completion_time': 0.008, 'prompt_time': 0.003337935, 'queue_time': 0.20949214500000002, 'total_time': 0.011337935}, 'model_name': 'llama-3.1-8b-instant', 'system_fingerprint': 'fp_a491995411', 'finish_reason': 'stop', 'logprobs': None}, id='run-e33b48dc-5e55-466e-9ebd-7b48c81c3cbd-0', usage_metadata={'input_tokens': 50, 'output_tokens': 6, 'total_tokens': 56})"
+            ]
+          },
+          "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 ChatGroq features and configurations head to the API reference: https://python.langchain.com/api_reference/groq/chat_models/langchain_groq.chat_models.ChatGroq.html"
       ]
-     },
-     "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",
-    ")"
-   ]
+  ],
+  "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"
+    }
   },
-  {
-   "cell_type": "markdown",
-   "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
-   "metadata": {},
-   "source": [
-    "## API reference\n",
-    "\n",
-    "For detailed documentation of all ChatGroq features and configurations head to the API reference: https://python.langchain.com/api_reference/groq/chat_models/langchain_groq.chat_models.ChatGroq.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
+  "nbformat": 4,
+  "nbformat_minor": 5
 }

docs/docs/integrations/chat/litellm.ipynb

@@ -3,7 +3,9 @@
   {
    "cell_type": "raw",
    "id": "59148044",
-   "metadata": {},
+   "metadata": {
+    "id": "59148044"
+   },
    "source": [
     "---\n",
     "sidebar_label: LiteLLM\n",
@@ -11,120 +13,139 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
-   "id": "bf733a38-db84-4363-89e2-de6735c37230",
-   "metadata": {},
+   "id": "5bcea387",
+   "metadata": {
+    "id": "5bcea387"
+   },
    "source": [
     "# ChatLiteLLM\n",
     "\n",
-    "[LiteLLM](https://github.com/BerriAI/litellm) is a library that simplifies calling Anthropic, Azure, Huggingface, Replicate, etc. \n",
+    "[LiteLLM](https://github.com/BerriAI/litellm) is a library that simplifies calling Anthropic, Azure, Huggingface, Replicate, etc.\n",
     "\n",
-    "This notebook covers how to get started with using Langchain + the LiteLLM I/O library. "
+    "This notebook covers how to get started with using Langchain + the LiteLLM I/O library.\n",
+    "\n",
+    "## Overview\n",
+    "### Integration details\n",
+    "\n",
+    "| Class | Package | Local | Serializable | JS support| Package downloads | Package latest |\n",
+    "| :---  | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+    "| [ChatLiteLLM](https://python.langchain.com/docs/integrations/chat/litellm/) | [langchain-litellm](https://pypi.org/project/langchain-litellm/)| ❌ | ❌ | ❌ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-litellm?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-litellm?style=flat-square&label=%20) |\n",
+    "\n",
+    "### Model features\n",
+    "| [Tool calling](https://python.langchain.com/docs/how_to/tool_calling/) | [Structured output](https://python.langchain.com/docs/how_to/structured_output/) | JSON mode | Image input | Audio input | Video input | [Token-level streaming](https://python.langchain.com/docs/integrations/chat/litellm/#chatlitellm-also-supports-async-and-streaming-functionality) | [Native async](https://python.langchain.com/docs/integrations/chat/litellm/#chatlitellm-also-supports-async-and-streaming-functionality) | [Token usage](https://python.langchain.com/docs/how_to/chat_token_usage_tracking/) | [Logprobs](https://python.langchain.com/docs/how_to/logprobs/) |\n",
+    "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
+    "| ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ | ✅ | ✅ | ❌ |\n",
+    "\n",
+    "### Setup\n",
+    "To access ChatLiteLLM models you'll need to install the `langchain-litellm` package and create an OpenAI, Anthropic, Azure, Replicate, OpenRouter, Hugging Face, Together AI or Cohere account. Then you have to get an API key, and export it as an environment variable."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0a2f8164",
+   "metadata": {
+    "id": "0a2f8164"
+   },
+   "source": [
+    "## Credentials\n",
+    "\n",
+    "You have to choose the LLM provider you want and sign up with them to get their API key.\n",
+    "\n",
+    "### Example - Anthropic\n",
+    "Head to https://console.anthropic.com/ to sign up for Anthropic and generate an API key. Once you've done this set the ANTHROPIC_API_KEY environment variable.\n",
+    "\n",
+    "\n",
+    "### Example - OpenAI\n",
+    "Head to https://platform.openai.com/api-keys to sign up for OpenAI and generate an API key. Once you've done this set the OPENAI_API_KEY environment variable."
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 1,
-   "id": "d4a7c55d-b235-4ca4-a579-c90cc9570da9",
+   "id": "7595eddf",
    "metadata": {
-    "tags": []
+    "id": "7595eddf"
    },
    "outputs": [],
    "source": [
-    "from langchain_community.chat_models import ChatLiteLLM\n",
-    "from langchain_core.messages import HumanMessage"
+    "## set ENV variables\n",
+    "import os\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"your-openai-key\"\n",
+    "os.environ[\"ANTHROPIC_API_KEY\"] = \"your-anthropic-key\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "74c3ad30",
+   "metadata": {
+    "id": "74c3ad30"
+   },
+   "source": [
+    "### Installation\n",
+    "\n",
+    "The LangChain LiteLLM integration lives in the `langchain-litellm` package:"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 2,
-   "id": "70cf04e8-423a-4ff6-8b09-f11fb711c817",
+   "id": "ca3f8a25",
    "metadata": {
-    "tags": []
+    "id": "ca3f8a25"
    },
    "outputs": [],
    "source": [
-    "chat = ChatLiteLLM(model=\"gpt-3.5-turbo\")"
+    "%pip install -qU langchain-litellm"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "bc1182b4",
+   "metadata": {
+    "id": "bc1182b4"
+   },
+   "source": [
+    "## Instantiation\n",
+    "Now we can instantiate our model object and generate chat completions:"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 3,
-   "id": "8199ef8f-eb8b-4253-9ea0-6c24a013ca4c",
+   "id": "d4a7c55d-b235-4ca4-a579-c90cc9570da9",
    "metadata": {
+    "id": "d4a7c55d-b235-4ca4-a579-c90cc9570da9",
     "tags": []
    },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\" J'aime la programmation.\", additional_kwargs={}, example=False)"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
-    "messages = [\n",
-    "    HumanMessage(\n",
-    "        content=\"Translate this sentence from English to French. I love programming.\"\n",
-    "    )\n",
-    "]\n",
-    "chat(messages)"
+    "from langchain_litellm import ChatLiteLLM\n",
+    "\n",
+    "llm = ChatLiteLLM(model=\"gpt-3.5-turbo\")"
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
-   "id": "c361ab1e-8c0c-4206-9e3c-9d1424a12b9c",
-   "metadata": {},
+   "id": "63d98454",
+   "metadata": {
+    "id": "63d98454"
+   },
    "source": [
-    "## `ChatLiteLLM` also supports async and streaming functionality:"
+    "## Invocation"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 4,
-   "id": "93a21c5c-6ef9-4688-be60-b2e1f94842fb",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain_core.callbacks import CallbackManager, StreamingStdOutCallbackHandler"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "c5fac0e9-05a4-4fc1-a3b3-e5bbb24b971b",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "LLMResult(generations=[[ChatGeneration(text=\" J'aime programmer.\", generation_info=None, message=AIMessage(content=\" J'aime programmer.\", additional_kwargs={}, example=False))]], llm_output={}, run=[RunInfo(run_id=UUID('8cc8fb68-1c35-439c-96a0-695036a93652'))])"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "await chat.agenerate([messages])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "025be980-e50d-4a68-93dc-c9c7b500ce34",
+   "id": "8199ef8f-eb8b-4253-9ea0-6c24a013ca4c",
    "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "8199ef8f-eb8b-4253-9ea0-6c24a013ca4c",
+    "outputId": "a4c0e5f5-a859-43fa-dd78-74fc0922ecb2",
     "tags": []
    },
    "outputs": [
@@ -132,41 +153,75 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " J'aime la programmation."
+      "content='Neutral' additional_kwargs={} response_metadata={'token_usage': Usage(completion_tokens=2, prompt_tokens=30, total_tokens=32, completion_tokens_details=CompletionTokensDetailsWrapper(accepted_prediction_tokens=0, audio_tokens=0, reasoning_tokens=0, rejected_prediction_tokens=0, text_tokens=None), prompt_tokens_details=PromptTokensDetailsWrapper(audio_tokens=0, cached_tokens=0, text_tokens=None, image_tokens=None)), 'model': 'gpt-3.5-turbo', 'finish_reason': 'stop', 'model_name': 'gpt-3.5-turbo'} id='run-ab6a3b21-eae8-4c27-acb2-add65a38221a-0' usage_metadata={'input_tokens': 30, 'output_tokens': 2, 'total_tokens': 32}\n"
      ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\" J'aime la programmation.\", additional_kwargs={}, example=False)"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
     }
    ],
    "source": [
-    "chat = ChatLiteLLM(\n",
-    "    streaming=True,\n",
-    "    verbose=True,\n",
-    "    callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]),\n",
+    "response = await llm.ainvoke(\n",
+    "    \"Classify the text into neutral, negative or positive. Text: I think the food was okay. Sentiment:\"\n",
     ")\n",
-    "chat(messages)"
+    "print(response)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c361ab1e-8c0c-4206-9e3c-9d1424a12b9c",
+   "metadata": {
+    "id": "c361ab1e-8c0c-4206-9e3c-9d1424a12b9c"
+   },
+   "source": [
+    "## `ChatLiteLLM` also supports async and streaming functionality:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "c253883f",
-   "metadata": {},
-   "outputs": [],
-   "source": []
+   "execution_count": 5,
+   "id": "c5fac0e9-05a4-4fc1-a3b3-e5bbb24b971b",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "c5fac0e9-05a4-4fc1-a3b3-e5bbb24b971b",
+    "outputId": "ee8cdda1-d992-4696-9ad0-aa146360a3ee",
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Antibiotics are medications that fight bacterial infections in the body. They work by targeting specific bacteria and either killing them or preventing their growth and reproduction.\n",
+      "\n",
+      "There are several different mechanisms by which antibiotics work. Some antibiotics work by disrupting the cell walls of bacteria, causing them to burst and die. Others interfere with the protein synthesis of bacteria, preventing them from growing and reproducing. Some antibiotics target the DNA or RNA of bacteria, disrupting their ability to replicate.\n",
+      "\n",
+      "It is important to note that antibiotics only work against bacterial infections and not viral infections. It is also crucial to take antibiotics as prescribed by a healthcare professional and to complete the full course of treatment, even if symptoms improve before the medication is finished. This helps to prevent antibiotic resistance, where bacteria become resistant to the effects of antibiotics."
+     ]
+    }
+   ],
+   "source": [
+    "async for token in llm.astream(\"Hello, please explain how antibiotics work\"):\n",
+    "    print(token.text(), end=\"\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "88af2a9b",
+   "metadata": {
+    "id": "88af2a9b"
+   },
+   "source": [
+    "## API reference\n",
+    "For detailed documentation of all `ChatLiteLLM` features and configurations head to the API reference: https://github.com/Akshay-Dongare/langchain-litellm"
+   ]
   }
  ],
  "metadata": {
+  "colab": {
+   "provenance": []
+  },
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "g6_alda",
    "language": "python",
    "name": "python3"
   },
@@ -180,7 +235,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.12.4"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/mistralai.ipynb

@@ -1,262 +1,260 @@
 {
- "cells": [
-  {
-   "cell_type": "raw",
-   "id": "53fbf15f",
-   "metadata": {},
-   "source": [
-    "---\n",
-    "sidebar_label: MistralAI\n",
-    "---"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "d295c2a2",
-   "metadata": {},
-   "source": [
-    "# ChatMistralAI\n",
-    "\n",
-    "This will help you getting started with Mistral [chat models](/docs/concepts/chat_models). For detailed documentation of all `ChatMistralAI` features and configurations head to the [API reference](https://python.langchain.com/api_reference/mistralai/chat_models/langchain_mistralai.chat_models.ChatMistralAI.html). The `ChatMistralAI` class is built on top of the [Mistral API](https://docs.mistral.ai/api/). For a list of all the models supported by Mistral, check out [this page](https://docs.mistral.ai/getting-started/models/).\n",
-    "\n",
-    "## Overview\n",
-    "### Integration details\n",
-    "\n",
-    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/docs/integrations/chat/mistral) | Package downloads | Package latest |\n",
-    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
-    "| [ChatMistralAI](https://python.langchain.com/api_reference/mistralai/chat_models/langchain_mistralai.chat_models.ChatMistralAI.html) | [langchain_mistralai](https://python.langchain.com/api_reference/mistralai/index.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_mistralai?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain_mistralai?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",
-    "\n",
-    "To access `ChatMistralAI` models you'll need to create a Mistral account, get an API key, and install the `langchain_mistralai` integration package.\n",
-    "\n",
-    "### Credentials\n",
-    "\n",
-    "\n",
-    "A valid [API key](https://console.mistral.ai/api-keys/) is needed to communicate with the API. Once you've done this set the MISTRAL_API_KEY environment variable:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "2461605e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "if \"MISTRAL_API_KEY\" not in os.environ:\n",
-    "    os.environ[\"MISTRAL_API_KEY\"] = getpass.getpass(\"Enter your Mistral API key: \")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "788f37ac",
-   "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": "007209d5",
-   "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": "0f5c74f9",
-   "metadata": {},
-   "source": [
-    "### Installation\n",
-    "\n",
-    "The LangChain Mistral integration lives in the `langchain_mistralai` package:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "1ab11a65",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%pip install -qU langchain_mistralai"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "fb1a335e",
-   "metadata": {},
-   "source": [
-    "## Instantiation\n",
-    "\n",
-    "Now we can instantiate our model object and generate chat completions:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "e6c38580",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_mistralai import ChatMistralAI\n",
-    "\n",
-    "llm = ChatMistralAI(\n",
-    "    model=\"mistral-large-latest\",\n",
-    "    temperature=0,\n",
-    "    max_retries=2,\n",
-    "    # other params...\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "aec79099",
-   "metadata": {},
-   "source": [
-    "## Invocation"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "8838c3cc",
-   "metadata": {},
-   "outputs": [
+  "cells": [
     {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='Sure, I\\'d be happy to help you translate that sentence into French! The English sentence \"I love programming\" translates to \"J\\'aime programmer\" in French. Let me know if you have any other questions or need further assistance!', response_metadata={'token_usage': {'prompt_tokens': 32, 'total_tokens': 84, 'completion_tokens': 52}, 'model': 'mistral-small', 'finish_reason': 'stop'}, id='run-64bac156-7160-4b68-b67e-4161f63e021f-0', usage_metadata={'input_tokens': 32, 'output_tokens': 52, 'total_tokens': 84})"
+      "cell_type": "raw",
+      "id": "53fbf15f",
+      "metadata": {},
+      "source": [
+        "---\n",
+        "sidebar_label: MistralAI\n",
+        "---"
       ]
-     },
-     "execution_count": 6,
-     "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": 7,
-   "id": "bbf6a048",
-   "metadata": {},
-   "outputs": [
+    },
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Sure, I'd be happy to help you translate that sentence into French! The English sentence \"I love programming\" translates to \"J'aime programmer\" in French. Let me know if you have any other questions or need further assistance!\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(ai_msg.content)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "32b87f87",
-   "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": 8,
-   "id": "24e2c51c",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='Ich liebe Programmierung. (German translation)', response_metadata={'token_usage': {'prompt_tokens': 26, 'total_tokens': 38, 'completion_tokens': 12}, 'model': 'mistral-small', 'finish_reason': 'stop'}, id='run-dfd4094f-e347-47b0-9056-8ebd7ea35fe7-0', usage_metadata={'input_tokens': 26, 'output_tokens': 12, 'total_tokens': 38})"
+      "cell_type": "markdown",
+      "id": "d295c2a2",
+      "metadata": {},
+      "source": [
+        "# ChatMistralAI\n",
+        "\n",
+        "This will help you getting started with Mistral [chat models](/docs/concepts/chat_models). For detailed documentation of all `ChatMistralAI` features and configurations head to the [API reference](https://python.langchain.com/api_reference/mistralai/chat_models/langchain_mistralai.chat_models.ChatMistralAI.html). The `ChatMistralAI` class is built on top of the [Mistral API](https://docs.mistral.ai/api/). For a list of all the models supported by Mistral, check out [this page](https://docs.mistral.ai/getting-started/models/).\n",
+        "\n",
+        "## Overview\n",
+        "### Integration details\n",
+        "\n",
+        "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/docs/integrations/chat/mistral) | Package downloads | Package latest |\n",
+        "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+        "| [ChatMistralAI](https://python.langchain.com/api_reference/mistralai/chat_models/langchain_mistralai.chat_models.ChatMistralAI.html) | [langchain_mistralai](https://python.langchain.com/api_reference/mistralai/index.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_mistralai?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain_mistralai?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",
+        "\n",
+        "To access `ChatMistralAI` models you'll need to create a Mistral account, get an API key, and install the `langchain_mistralai` integration package.\n",
+        "\n",
+        "### Credentials\n",
+        "\n",
+        "\n",
+        "A valid [API key](https://console.mistral.ai/api-keys/) is needed to communicate with the API. Once you've done this set the MISTRAL_API_KEY environment variable:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "2461605e",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import getpass\n",
+        "import os\n",
+        "\n",
+        "if \"MISTRAL_API_KEY\" not in os.environ:\n",
+        "    os.environ[\"MISTRAL_API_KEY\"] = getpass.getpass(\"Enter your Mistral API key: \")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "788f37ac",
+      "metadata": {},
+      "source": "To enable automated tracing of your model calls, set your [LangSmith](https://docs.smith.langchain.com/) API key:"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "007209d5",
+      "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": "0f5c74f9",
+      "metadata": {},
+      "source": [
+        "### Installation\n",
+        "\n",
+        "The LangChain Mistral integration lives in the `langchain_mistralai` package:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "1ab11a65",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%pip install -qU langchain_mistralai"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "fb1a335e",
+      "metadata": {},
+      "source": [
+        "## Instantiation\n",
+        "\n",
+        "Now we can instantiate our model object and generate chat completions:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 5,
+      "id": "e6c38580",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from langchain_mistralai import ChatMistralAI\n",
+        "\n",
+        "llm = ChatMistralAI(\n",
+        "    model=\"mistral-large-latest\",\n",
+        "    temperature=0,\n",
+        "    max_retries=2,\n",
+        "    # other params...\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "aec79099",
+      "metadata": {},
+      "source": [
+        "## Invocation"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 6,
+      "id": "8838c3cc",
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "AIMessage(content='Sure, I\\'d be happy to help you translate that sentence into French! The English sentence \"I love programming\" translates to \"J\\'aime programmer\" in French. Let me know if you have any other questions or need further assistance!', response_metadata={'token_usage': {'prompt_tokens': 32, 'total_tokens': 84, 'completion_tokens': 52}, 'model': 'mistral-small', 'finish_reason': 'stop'}, id='run-64bac156-7160-4b68-b67e-4161f63e021f-0', usage_metadata={'input_tokens': 32, 'output_tokens': 52, 'total_tokens': 84})"
+            ]
+          },
+          "execution_count": 6,
+          "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": 7,
+      "id": "bbf6a048",
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Sure, I'd be happy to help you translate that sentence into French! The English sentence \"I love programming\" translates to \"J'aime programmer\" in French. Let me know if you have any other questions or need further assistance!\n"
+          ]
+        }
+      ],
+      "source": [
+        "print(ai_msg.content)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "32b87f87",
+      "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": 8,
+      "id": "24e2c51c",
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "AIMessage(content='Ich liebe Programmierung. (German translation)', response_metadata={'token_usage': {'prompt_tokens': 26, 'total_tokens': 38, 'completion_tokens': 12}, 'model': 'mistral-small', 'finish_reason': 'stop'}, id='run-dfd4094f-e347-47b0-9056-8ebd7ea35fe7-0', usage_metadata={'input_tokens': 26, 'output_tokens': 12, 'total_tokens': 38})"
+            ]
+          },
+          "execution_count": 8,
+          "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": "cb9b5834",
+      "metadata": {},
+      "source": [
+        "## API reference\n",
+        "\n",
+        "Head to the [API reference](https://python.langchain.com/api_reference/mistralai/chat_models/langchain_mistralai.chat_models.ChatMistralAI.html) for detailed documentation of all attributes and methods."
       ]
-     },
-     "execution_count": 8,
-     "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",
-    ")"
-   ]
+  ],
+  "metadata": {
+    "kernelspec": {
+      "display_name": "Python 3 (ipykernel)",
+      "language": "python",
+      "name": "python3"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.11.9"
+    }
   },
-  {
-   "cell_type": "markdown",
-   "id": "cb9b5834",
-   "metadata": {},
-   "source": [
-    "## API reference\n",
-    "\n",
-    "Head to the [API reference](https://python.langchain.com/api_reference/mistralai/chat_models/langchain_mistralai.chat_models.ChatMistralAI.html) for detailed documentation of all attributes and methods."
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.9"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
+  "nbformat": 4,
+  "nbformat_minor": 5
 }

docs/docs/integrations/chat/naver.ipynb

@@ -1,444 +1,356 @@
 {
- "cells": [
-  {
-   "cell_type": "raw",
-   "id": "afaf8039",
-   "metadata": {},
-   "source": [
-    "---\n",
-    "sidebar_label: Naver\n",
-    "---"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "c8444f1a-e907-4f07-b8b6-68fbedfb868e",
-   "metadata": {},
-   "source": [
-    "# ChatClovaX\n",
-    "\n",
-    "This notebook provides a quick overview for getting started with Naver’s HyperCLOVA X [chat models](https://python.langchain.com/docs/concepts/chat_models) via CLOVA Studio. For detailed documentation of all ChatClovaX features and configurations head to the [API reference](https://python.langchain.com/api_reference/community/chat_models/langchain_community.chat_models.naver.ChatClovaX.html).\n",
-    "\n",
-    "[CLOVA Studio](http://clovastudio.ncloud.com/) has several chat models. You can find information about latest models and their costs, context windows, and supported input types in the CLOVA Studio API Guide [documentation](https://api.ncloud-docs.com/docs/clovastudio-chatcompletions).\n",
-    "\n",
-    "## Overview\n",
-    "### Integration details\n",
-    "\n",
-    "| Class | Package | Local | Serializable | JS support | Package downloads | Package latest |\n",
-    "| :--- | :--- |:-----:| :---: |:------------------------------------------------------------------------:| :---: | :---: |\n",
-    "| [ChatClovaX](https://python.langchain.com/api_reference/community/chat_models/langchain_community.chat_models.naver.ChatClovaX.html) | [langchain-community](https://python.langchain.com/api_reference/community/index.html) |   ❌   | ❌ |                                    ❌                                     | ![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",
-    "## Setup\n",
-    "\n",
-    "Before using the chat model, you must go through the four steps below.\n",
-    "\n",
-    "1. Creating [NAVER Cloud Platform](https://www.ncloud.com/) account \n",
-    "2. Apply to use [CLOVA Studio](https://www.ncloud.com/product/aiService/clovaStudio)\n",
-    "3. Create a CLOVA Studio Test App or Service App of a model to use (See [here](https://guide.ncloud-docs.com/docs/en/clovastudio-playground01#테스트앱생성).)\n",
-    "4. Issue a Test or Service API key (See [here](https://api.ncloud-docs.com/docs/ai-naver-clovastudio-summary#API%ED%82%A4).)\n",
-    "\n",
-    "### Credentials\n",
-    "\n",
-    "Set the `NCP_CLOVASTUDIO_API_KEY` environment variable with your API key.\n",
-    "  - Note that if you are using a legacy API Key (that doesn't start with `nv-*` prefix), you might need to get an additional API Key by clicking `App Request Status` > `Service App, Test App List` > `‘Details’ button for each app` in [CLOVA Studio](https://clovastudio.ncloud.com/studio-application/service-app) and set it as `NCP_APIGW_API_KEY`.\n",
-    "\n",
-    "You can add them to your environment variables as below:\n",
-    "\n",
-    "``` bash\n",
-    "export NCP_CLOVASTUDIO_API_KEY=\"your-api-key-here\"\n",
-    "# Uncomment below to use a legacy API key\n",
-    "# export NCP_APIGW_API_KEY=\"your-api-key-here\"\n",
-    "```"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "2def81b5-b023-4f40-a97b-b2c5ca59d6a9",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "if not os.getenv(\"NCP_CLOVASTUDIO_API_KEY\"):\n",
-    "    os.environ[\"NCP_CLOVASTUDIO_API_KEY\"] = getpass.getpass(\n",
-    "        \"Enter your NCP CLOVA Studio API Key: \"\n",
-    "    )\n",
-    "# Uncomment below to use a legacy API key\n",
-    "# if not os.getenv(\"NCP_APIGW_API_KEY\"):\n",
-    "#     os.environ[\"NCP_APIGW_API_KEY\"] = getpass.getpass(\n",
-    "#         \"Enter your NCP API Gateway API key: \"\n",
-    "#     )"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "7c695442",
-   "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": "6151aeb6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\"\n",
-    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "17bf9053-90c5-4955-b239-55a35cb07566",
-   "metadata": {},
-   "source": [
-    "### Installation\n",
-    "\n",
-    "The LangChain Naver integration lives in the `langchain-community` package:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "a15d341e-3e26-4ca3-830b-5aab30ed66de",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# install package\n",
-    "!pip install -qU langchain-community"
-   ]
-  },
-  {
-   "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": 2,
-   "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_community.chat_models import ChatClovaX\n",
-    "\n",
-    "chat = ChatClovaX(\n",
-    "    model=\"HCX-003\",\n",
-    "    max_tokens=100,\n",
-    "    temperature=0.5,\n",
-    "    # clovastudio_api_key=\"...\"    # set if you prefer to pass api key directly instead of using environment variables\n",
-    "    # task_id=\"...\"    # set if you want to use fine-tuned model\n",
-    "    # service_app=False    # set True if using Service App. Default value is False (means using Test App)\n",
-    "    # include_ai_filters=False     # set True if you want to detect inappropriate content. Default value is False\n",
-    "    # other params...\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "47752b59",
-   "metadata": {},
-   "source": [
-    "## Invocation\n",
-    "\n",
-    "In addition to invoke, we also support batch and stream functionalities."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "62e0dbc3",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
+  "cells": [
     {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='저는 네이버 AI를 사용하는 것이 좋아요.', additional_kwargs={}, response_metadata={'stop_reason': 'stop_before', 'input_length': 25, 'output_length': 14, 'seed': 1112164354, 'ai_filter': None}, id='run-b57bc356-1148-4007-837d-cc409dbd57cc-0', usage_metadata={'input_tokens': 25, 'output_tokens': 14, 'total_tokens': 39})"
+      "cell_type": "raw",
+      "id": "afaf8039",
+      "metadata": {},
+      "source": [
+        "---\n",
+        "sidebar_label: Naver\n",
+        "---"
       ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "messages = [\n",
-    "    (\n",
-    "        \"system\",\n",
-    "        \"You are a helpful assistant that translates English to Korean. Translate the user sentence.\",\n",
-    "    ),\n",
-    "    (\"human\", \"I love using NAVER AI.\"),\n",
-    "]\n",
-    "\n",
-    "ai_msg = chat.invoke(messages)\n",
-    "ai_msg"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "24e7377f",
-   "metadata": {},
-   "outputs": [
+    },
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "저는 네이버 AI를 사용하는 것이 좋아요.\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(ai_msg.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:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='저는 네이버 AI를 사용하는 것이 좋아요.', additional_kwargs={}, response_metadata={'stop_reason': 'stop_before', 'input_length': 25, 'output_length': 14, 'seed': 2575184681, 'ai_filter': None}, id='run-7014b330-eba3-4701-bb62-df73ce39b854-0', usage_metadata={'input_tokens': 25, 'output_tokens': 14, 'total_tokens': 39})"
+      "cell_type": "markdown",
+      "id": "c8444f1a-e907-4f07-b8b6-68fbedfb868e",
+      "metadata": {},
+      "source": [
+        "# ChatClovaX\n",
+        "\n",
+        "This notebook provides a quick overview for getting started with Naver’s HyperCLOVA X [chat models](https://python.langchain.com/docs/concepts/chat_models) via CLOVA Studio. For detailed documentation of all ChatClovaX features and configurations head to the [API reference](https://guide.ncloud-docs.com/docs/clovastudio-dev-langchain).\n",
+        "\n",
+        "[CLOVA Studio](http://clovastudio.ncloud.com/) has several chat models. You can find information about latest models and their costs, context windows, and supported input types in the CLOVA Studio Guide [documentation](https://guide.ncloud-docs.com/docs/clovastudio-model).\n",
+        "\n",
+        "## Overview\n",
+        "### Integration details\n",
+        "\n",
+        "| Class | Package | Local | Serializable | JS support | Package downloads | Package latest |\n",
+        "| :--- | :--- |:-----:| :---: |:------------------------------------------------------------------------:| :---: | :---: |\n",
+        "| [ChatClovaX](https://guide.ncloud-docs.com/docs/clovastudio-dev-langchain#HyperCLOVAX%EB%AA%A8%EB%8D%B8%EC%9D%B4%EC%9A%A9) | [langchain-naver](https://pypi.org/project/langchain-naver/) |   ❌   | ❌ |                                    ❌                                     | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_naver?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain_naver?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",
+        "Before using the chat model, you must go through the four steps below.\n",
+        "\n",
+        "1. Creating [NAVER Cloud Platform](https://www.ncloud.com/) account\n",
+        "2. Apply to use [CLOVA Studio](https://www.ncloud.com/product/aiService/clovaStudio)\n",
+        "3. Create a CLOVA Studio Test App or Service App of a model to use (See [here](https://guide.ncloud-docs.com/docs/clovastudio-playground-testapp).)\n",
+        "4. Issue a Test or Service API key (See [here](https://api.ncloud-docs.com/docs/ai-naver-clovastudio-summary#API%ED%82%A4).)\n",
+        "\n",
+        "### Credentials\n",
+        "\n",
+        "Set the `CLOVASTUDIO_API_KEY` environment variable with your API key.\n",
+        "\n",
+        "You can add them to your environment variables as below:\n",
+        "\n",
+        "``` bash\n",
+        "export CLOVASTUDIO_API_KEY=\"your-api-key-here\"\n",
+        "```"
       ]
-     },
-     "execution_count": 5,
-     "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}. Translate the user sentence.\",\n",
-    "        ),\n",
-    "        (\"human\", \"{input}\"),\n",
-    "    ]\n",
-    ")\n",
-    "\n",
-    "chain = prompt | chat\n",
-    "chain.invoke(\n",
-    "    {\n",
-    "        \"input_language\": \"English\",\n",
-    "        \"output_language\": \"Korean\",\n",
-    "        \"input\": \"I love using NAVER AI.\",\n",
-    "    }\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "66e69286",
-   "metadata": {},
-   "source": [
-    "## Streaming"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "2c07af21-dda5-4514-b4de-1f214c2cebcd",
-   "metadata": {},
-   "outputs": [
+    },
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Certainly! In Korean, \"Hi\" is pronounced as \"안녕\" (annyeong). The first syllable, \"안,\" sounds like the \"ahh\" sound in \"apple,\" while the second syllable, \"녕,\" sounds like the \"yuh\" sound in \"you.\" So when you put them together, it's like saying \"ahhyuh-nyuhng.\" Remember to pronounce each syllable clearly and separately for accurate pronunciation."
-     ]
-    }
-   ],
-   "source": [
-    "system = \"You are a helpful assistant that can teach Korean pronunciation.\"\n",
-    "human = \"Could you let me know how to say '{phrase}' in Korean?\"\n",
-    "prompt = ChatPromptTemplate.from_messages([(\"system\", system), (\"human\", human)])\n",
-    "\n",
-    "chain = prompt | chat\n",
-    "\n",
-    "for chunk in chain.stream({\"phrase\": \"Hi\"}):\n",
-    "    print(chunk.content, end=\"\", flush=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "d1ee55bc-ffc8-4cfa-801c-993953a08cfd",
-   "metadata": {},
-   "source": [
-    "## Additional functionalities\n",
-    "\n",
-    "### Using fine-tuned models\n",
-    "\n",
-    "You can call fine-tuned models by passing in your corresponding `task_id` parameter. (You don’t need to specify the `model_name` parameter when calling fine-tuned model.)\n",
-    "\n",
-    "You can check `task_id` from corresponding Test App or Service App details."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "cb436788",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='저는 네이버 AI를 사용하는 것이 너무 좋아요.', additional_kwargs={}, response_metadata={'stop_reason': 'stop_before', 'input_length': 25, 'output_length': 15, 'seed': 52559061, 'ai_filter': None}, id='run-5bea8d4a-48f3-4c34-ae70-66e60dca5344-0', usage_metadata={'input_tokens': 25, 'output_tokens': 15, 'total_tokens': 40})"
+      "cell_type": "code",
+      "execution_count": 2,
+      "id": "2def81b5-b023-4f40-a97b-b2c5ca59d6a9",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import getpass\n",
+        "import os\n",
+        "\n",
+        "if not os.getenv(\"CLOVASTUDIO_API_KEY\"):\n",
+        "    os.environ[\"CLOVASTUDIO_API_KEY\"] = getpass.getpass(\n",
+        "        \"Enter your CLOVA Studio API Key: \"\n",
+        "    )"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "7c695442",
+      "metadata": {},
+      "source": [
+        "To enable automated tracing of your model calls, set your [LangSmith](https://docs.smith.langchain.com/) API key:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "6151aeb6",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# os.environ[\"LANGSMITH_TRACING\"] = \"true\"\n",
+        "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "17bf9053-90c5-4955-b239-55a35cb07566",
+      "metadata": {},
+      "source": [
+        "### Installation\n",
+        "\n",
+        "The LangChain Naver integration lives in the `langchain-naver` package:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "a15d341e-3e26-4ca3-830b-5aab30ed66de",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# install package\n",
+        "%pip install -qU langchain-naver"
+      ]
+    },
+    {
+      "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": 3,
+      "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from langchain_naver import ChatClovaX\n",
+        "\n",
+        "chat = ChatClovaX(\n",
+        "    model=\"HCX-005\",\n",
+        "    temperature=0.5,\n",
+        "    max_tokens=None,\n",
+        "    timeout=None,\n",
+        "    max_retries=2,\n",
+        "    # other params...\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "47752b59",
+      "metadata": {},
+      "source": [
+        "## Invocation\n",
+        "\n",
+        "In addition to invoke, `ChatClovaX` also support batch and stream functionalities."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 4,
+      "id": "62e0dbc3",
+      "metadata": {
+        "tags": []
+      },
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "AIMessage(content='네이버 인공지능을 사용하는 것을 정말 좋아합니다.', additional_kwargs={'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 11, 'prompt_tokens': 28, 'total_tokens': 39, 'completion_tokens_details': None, 'prompt_tokens_details': None}, 'model_name': 'HCX-005', 'system_fingerprint': None, 'id': 'b70c26671cd247a0864115bacfb5fc12', 'finish_reason': 'stop', 'logprobs': None}, id='run-3faf6a8d-d5da-49ad-9fbb-7b56ed23b484-0', usage_metadata={'input_tokens': 28, 'output_tokens': 11, 'total_tokens': 39, 'input_token_details': {}, 'output_token_details': {}})"
+            ]
+          },
+          "execution_count": 4,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "messages = [\n",
+        "    (\n",
+        "        \"system\",\n",
+        "        \"You are a helpful assistant that translates English to Korean. Translate the user sentence.\",\n",
+        "    ),\n",
+        "    (\"human\", \"I love using NAVER AI.\"),\n",
+        "]\n",
+        "\n",
+        "ai_msg = chat.invoke(messages)\n",
+        "ai_msg"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 5,
+      "id": "24e7377f",
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "네이버 인공지능을 사용하는 것을 정말 좋아합니다.\n"
+          ]
+        }
+      ],
+      "source": [
+        "print(ai_msg.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:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 6,
+      "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "AIMessage(content='저는 네이버 인공지능을 사용하는 것을 좋아합니다.', additional_kwargs={'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 10, 'prompt_tokens': 28, 'total_tokens': 38, 'completion_tokens_details': None, 'prompt_tokens_details': None}, 'model_name': 'HCX-005', 'system_fingerprint': None, 'id': 'b7a826d17fcf4fee8386fca2ebc63284', 'finish_reason': 'stop', 'logprobs': None}, id='run-35957816-3325-4d9c-9441-e40704912be6-0', usage_metadata={'input_tokens': 28, 'output_tokens': 10, 'total_tokens': 38, 'input_token_details': {}, 'output_token_details': {}})"
+            ]
+          },
+          "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 helpful assistant that translates {input_language} to {output_language}. Translate the user sentence.\",\n",
+        "        ),\n",
+        "        (\"human\", \"{input}\"),\n",
+        "    ]\n",
+        ")\n",
+        "\n",
+        "chain = prompt | chat\n",
+        "chain.invoke(\n",
+        "    {\n",
+        "        \"input_language\": \"English\",\n",
+        "        \"output_language\": \"Korean\",\n",
+        "        \"input\": \"I love using NAVER AI.\",\n",
+        "    }\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "66e69286",
+      "metadata": {},
+      "source": [
+        "## Streaming"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 7,
+      "id": "2c07af21-dda5-4514-b4de-1f214c2cebcd",
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "In Korean, the informal way of saying 'hi' is \"안녕\" (annyeong). If you're addressing someone older or showing more respect, you would use \"안녕하세요\" (annjeonghaseyo). Both phrases are used as greetings similar to 'hello'. Remember, pronunciation is key so make sure to pronounce each syllable clearly: 안-녀-엉 (an-nyeo-eong) and 안-녕-하-세-요 (an-nyeong-ha-se-yo)."
+          ]
+        }
+      ],
+      "source": [
+        "system = \"You are a helpful assistant that can teach Korean pronunciation.\"\n",
+        "human = \"Could you let me know how to say '{phrase}' in Korean?\"\n",
+        "prompt = ChatPromptTemplate.from_messages([(\"system\", system), (\"human\", human)])\n",
+        "\n",
+        "chain = prompt | chat\n",
+        "\n",
+        "for chunk in chain.stream({\"phrase\": \"Hi\"}):\n",
+        "    print(chunk.content, end=\"\", flush=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "d1ee55bc-ffc8-4cfa-801c-993953a08cfd",
+      "metadata": {},
+      "source": [
+        "## Additional functionalities\n",
+        "\n",
+        "### Using fine-tuned models\n",
+        "\n",
+        "You can call fine-tuned models by passing the `task_id` to the `model` parameter as: `ft:{task_id}`.\n",
+        "\n",
+        "You can check `task_id` from corresponding Test App or Service App details."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "cb436788",
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "AIMessage(content='네이버 인공지능을 사용하는 것을 정말 좋아합니다.', additional_kwargs={'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 11, 'prompt_tokens': 28, 'total_tokens': 39, 'completion_tokens_details': None, 'prompt_tokens_details': None}, 'model_name': 'HCX-005', 'system_fingerprint': None, 'id': '2222d6d411a948c883aac1e03ca6cebe', 'finish_reason': 'stop', 'logprobs': None}, id='run-9696d7e2-7afa-4bb4-9c03-b95fcf678ab8-0', usage_metadata={'input_tokens': 28, 'output_tokens': 11, 'total_tokens': 39, 'input_token_details': {}, 'output_token_details': {}})"
+            ]
+          },
+          "execution_count": 10,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "fine_tuned_model = ChatClovaX(\n",
+        "    model=\"ft:a1b2c3d4\",  # set as `ft:{task_id}` with your fine-tuned model's task id\n",
+        "    # other params...\n",
+        ")\n",
+        "\n",
+        "fine_tuned_model.invoke(messages)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
+      "metadata": {},
+      "source": [
+        "## API reference\n",
+        "\n",
+        "For detailed documentation of all ChatClovaX features and configurations head to the [API reference](https://guide.ncloud-docs.com/docs/clovastudio-dev-langchain)"
       ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
     }
-   ],
-   "source": [
-    "fine_tuned_model = ChatClovaX(\n",
-    "    task_id=\"5s8egt3a\",  # set if you want to use fine-tuned model\n",
-    "    # other params...\n",
-    ")\n",
-    "\n",
-    "fine_tuned_model.invoke(messages)"
-   ]
+  ],
+  "metadata": {
+    "kernelspec": {
+      "display_name": "Python 3",
+      "language": "python",
+      "name": "python3"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.12.8"
+    }
   },
-  {
-   "cell_type": "markdown",
-   "id": "f428deaf",
-   "metadata": {},
-   "source": [
-    "### Service App\n",
-    "\n",
-    "When going live with production-level application using CLOVA Studio, you should apply for and use Service App. (See [here](https://guide.ncloud-docs.com/docs/en/clovastudio-playground01#서비스앱신청).)\n",
-    "\n",
-    "For a Service App, you should use a corresponding Service API key and can only be called with it."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "dcf566df",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Update environment variables\n",
-    "\n",
-    "os.environ[\"NCP_CLOVASTUDIO_API_KEY\"] = getpass.getpass(\n",
-    "    \"Enter NCP CLOVA Studio Service API Key: \"\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "cebe27ae",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "chat = ChatClovaX(\n",
-    "    service_app=True,  # True if you want to use your service app, default value is False.\n",
-    "    # clovastudio_api_key=\"...\"  # if you prefer to pass api key in directly instead of using env vars\n",
-    "    model=\"HCX-003\",\n",
-    "    # other params...\n",
-    ")\n",
-    "ai_msg = chat.invoke(messages)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "d73e7140",
-   "metadata": {},
-   "source": [
-    "### AI Filter\n",
-    "\n",
-    "AI Filter detects inappropriate output such as profanity from the test app (or service app included) created in Playground and informs the user. See [here](https://guide.ncloud-docs.com/docs/en/clovastudio-playground01#AIFilter) for details. "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "32bfbc93",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "chat = ChatClovaX(\n",
-    "    model=\"HCX-003\",\n",
-    "    include_ai_filters=True,  # True if you want to enable ai filter\n",
-    "    # other params...\n",
-    ")\n",
-    "\n",
-    "ai_msg = chat.invoke(messages)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "7bd9e179",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "print(ai_msg.response_metadata[\"ai_filter\"])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
-   "metadata": {},
-   "source": [
-    "## API reference\n",
-    "\n",
-    "For detailed documentation of all ChatNaver features and configurations head to the API reference: https://python.langchain.com/api_reference/community/chat_models/langchain_community.chat_models.naver.ChatClovaX.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": "3.12.3"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
+  "nbformat": 4,
+  "nbformat_minor": 5
 }

docs/docs/integrations/chat/netmind.ipynb

@@ -0,0 +1,326 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "id": "afaf8039",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_label: Netmind\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e49f1e0d",
+   "metadata": {},
+   "source": [
+    "# ChatNetmind\n",
+    "\n",
+    "This will help you getting started with Netmind [chat models](https://www.netmind.ai/). For detailed documentation of all ChatNetmind features and configurations head to the [API reference](https://github.com/protagolabs/langchain-netmind).\n",
+    "\n",
+    "-  See https://www.netmind.ai/ for an example.\n",
+    "\n",
+    "## Overview\n",
+    "### Integration details\n",
+    "\n",
+    "| Class                                                                                        | Package | Local | Serializable | [JS support](https://js.langchain.com/docs/integrations/chat/) | Package downloads | Package latest |\n",
+    "|:---------------------------------------------------------------------------------------------| :--- |:-----:|:------------:|:--------------------------------------------------------------:| :---: | :---: |\n",
+    "| [ChatNetmind](https://python.langchain.com/api_reference/) | [langchain-netmind](https://python.langchain.com/api_reference/) |   ✅   |      ❌       |                               ❌                                | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-netmind?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-netmind?style=flat-square&label=%20) |\n",
+    "\n",
+    "### Model features\n",
+    "| [Tool calling](../../how_to/tool_calling.ipynb) | [Structured output](../../how_to/structured_output.ipynb) | JSON mode | [Image input](../../how_to/multimodal_inputs.ipynb) | Audio input | Video input | [Token-level streaming](../../how_to/chat_streaming.ipynb) | Native async | [Token usage](../../how_to/chat_token_usage_tracking.ipynb) | [Logprobs](../../how_to/logprobs.ipynb) |\n",
+    "|:-----------------------------------------------:|:---------------------------------------------------------:|:---------:|:---------------------------------------------------:|:-----------:|:-----------:|:----------------------------------------------------------:|:------------:|:-----------------------------------------------------------:|:---------------------------------------:|\n",
+    "|                        ✅                        |                             ✅                             |     ✅     |                          ❌                          |      ❌      |      ❌      |                             ✅                              |      ✅       |                              ✅                              |                    ✅                    | \n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "To access Netmind models you'll need to create a/an Netmind account, get an API key, and install the `langchain-netmind` integration package.\n",
+    "\n",
+    "### Credentials\n",
+    "\n",
+    "Head to https://www.netmind.ai/ to sign up to Netmind and generate an API key. Once you've done this set the NETMIND_API_KEY environment variable:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "id": "433e8d2b-9519-4b49-b2c4-7ab65b046c94",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-03-20T02:00:30.732333Z",
+     "start_time": "2025-03-20T02:00:28.384208Z"
+    }
+   },
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "if not os.getenv(\"NETMIND_API_KEY\"):\n",
+    "    os.environ[\"NETMIND_API_KEY\"] = getpass.getpass(\"Enter your Netmind API key: \")"
+   ],
+   "outputs": [],
+   "execution_count": 1
+  },
+  {
+   "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",
+   "id": "a15d341e-3e26-4ca3-830b-5aab30ed66de",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-03-20T02:00:33.421446Z",
+     "start_time": "2025-03-20T02:00:33.419081Z"
+    }
+   },
+   "source": [
+    "# os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
+    "# os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")"
+   ],
+   "outputs": [],
+   "execution_count": 2
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0730d6a1-c893-4840-9817-5e5251676d5d",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "The LangChain Netmind integration lives in the `langchain-netmind` package:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-03-20T02:00:35.923300Z",
+     "start_time": "2025-03-20T02:00:34.505928Z"
+    }
+   },
+   "source": [
+    "%pip install -qU langchain-netmind"
+   ],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\r\n",
+      "\u001B[1m[\u001B[0m\u001B[34;49mnotice\u001B[0m\u001B[1;39;49m]\u001B[0m\u001B[39;49m A new release of pip is available: \u001B[0m\u001B[31;49m24.0\u001B[0m\u001B[39;49m -> \u001B[0m\u001B[32;49m25.0.1\u001B[0m\r\n",
+      "\u001B[1m[\u001B[0m\u001B[34;49mnotice\u001B[0m\u001B[1;39;49m]\u001B[0m\u001B[39;49m To update, run: \u001B[0m\u001B[32;49mpip install --upgrade pip\u001B[0m\r\n",
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
+   "execution_count": 3
+  },
+  {
+   "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",
+   "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-03-20T02:01:08.007764Z",
+     "start_time": "2025-03-20T02:01:07.391951Z"
+    }
+   },
+   "source": [
+    "from langchain_netmind import ChatNetmind\n",
+    "\n",
+    "llm = ChatNetmind(\n",
+    "    model=\"deepseek-ai/DeepSeek-V3\",\n",
+    "    temperature=0,\n",
+    "    max_tokens=None,\n",
+    "    timeout=None,\n",
+    "    max_retries=2,\n",
+    "    # other params...\n",
+    ")"
+   ],
+   "outputs": [],
+   "execution_count": 4
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2b4f3e15",
+   "metadata": {},
+   "source": "## Invocation\n"
+  },
+  {
+   "cell_type": "code",
+   "id": "62e0dbc3",
+   "metadata": {
+    "tags": [],
+    "ExecuteTime": {
+     "end_time": "2025-03-20T02:01:19.011273Z",
+     "start_time": "2025-03-20T02:01:10.295510Z"
+    }
+   },
+   "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"
+   ],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"J'adore programmer.\", additional_kwargs={'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 13, 'prompt_tokens': 31, 'total_tokens': 44, 'completion_tokens_details': None, 'prompt_tokens_details': None}, 'model_name': 'deepseek-ai/DeepSeek-V3', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-ca6c2010-844d-4bf6-baac-6e248491b000-0', usage_metadata={'input_tokens': 31, 'output_tokens': 13, 'total_tokens': 44, 'input_token_details': {}, 'output_token_details': {}})"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "execution_count": 5
+  },
+  {
+   "cell_type": "code",
+   "id": "d86145b3-bfef-46e8-b227-4dda5c9c2705",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-03-20T02:01:20.240190Z",
+     "start_time": "2025-03-20T02:01:20.238242Z"
+    }
+   },
+   "source": [
+    "print(ai_msg.content)"
+   ],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "J'adore programmer.\n"
+     ]
+    }
+   ],
+   "execution_count": 6
+  },
+  {
+   "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",
+   "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-03-20T02:01:27.456393Z",
+     "start_time": "2025-03-20T02:01:23.993410Z"
+    }
+   },
+   "source": [
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "\n",
+    "prompt = ChatPromptTemplate(\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",
+    ")"
+   ],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='Ich liebe es zu programmieren.', additional_kwargs={'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 26, 'total_tokens': 40, 'completion_tokens_details': None, 'prompt_tokens_details': None}, 'model_name': 'deepseek-ai/DeepSeek-V3', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-d63adcc6-53ba-4caa-9a79-78d640b39274-0', usage_metadata={'input_tokens': 26, 'output_tokens': 14, 'total_tokens': 40, 'input_token_details': {}, 'output_token_details': {}})"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "execution_count": 7
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d1ee55bc-ffc8-4cfa-801c-993953a08cfd",
+   "metadata": {},
+   "source": ""
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all ChatNetmind features and configurations head to the API reference:  \n",
+    "* [API reference](https://python.langchain.com/api_reference/)  \n",
+    "* [langchain-netmind](https://github.com/protagolabs/langchain-netmind)  \n",
+    "* [pypi](https://pypi.org/project/langchain-netmind/)"
+   ]
+  },
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "outputs": [],
+   "execution_count": null,
+   "source": "",
+   "id": "30f8be8c940bfbf3"
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/integrations/chat/ollama.ipynb

@@ -19,7 +19,7 @@
     "\n",
     "[Ollama](https://ollama.ai/) allows you to run open-source large language models, such as Llama 2, locally.\n",
     "\n",
-    "Ollama bundles model weights, configuration, and data into a single package, defined by a Modelfile. \n",
+    "Ollama bundles model weights, configuration, and data into a single package, defined by a Modelfile.\n",
     "\n",
     "It optimizes setup and configuration details, including GPU usage.\n",
     "\n",
@@ -48,7 +48,7 @@
     "* This will download the default tagged version of the model. Typically, the default points to the latest, smallest sized-parameter model.\n",
     "\n",
     "> On Mac, the models will be download to `~/.ollama/models`\n",
-    "> \n",
+    ">\n",
     "> On Linux (or WSL), the models will be stored at `/usr/share/ollama/.ollama/models`\n",
     "\n",
     "* Specify the exact version of the model of interest as such `ollama pull vicuna:13b-v1.5-16k-q4_0` (View the [various tags for the `Vicuna`](https://ollama.ai/library/vicuna/tags) model in this instance)\n",
@@ -62,7 +62,7 @@
    "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:"
+    "To enable automated tracing of your model calls, set your [LangSmith](https://docs.smith.langchain.com/) API key:"
    ]
   },
   {
@@ -97,18 +97,22 @@
    ]
   },
   {
-   "metadata": {},
    "cell_type": "markdown",
-   "source": "Make sure you're using the latest Ollama version for structured outputs. Update by running:",
-   "id": "b18bd692076f7cf7"
+   "id": "b18bd692076f7cf7",
+   "metadata": {},
+   "source": [
+    "Make sure you're using the latest Ollama version for structured outputs. Update by running:"
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
-   "outputs": [],
    "execution_count": null,
-   "source": "%pip install -U ollama",
-   "id": "b7a05cba95644c2e"
+   "id": "b7a05cba95644c2e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -U ollama"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -117,9 +121,7 @@
    "source": [
     "## Instantiation\n",
     "\n",
-    "Now we can instantiate our model object and generate chat completions:\n",
-    "\n",
-    "- TODO: Update model instantiation with relevant params."
+    "Now we can instantiate our model object and generate chat completions:\n"
    ]
   },
   {
@@ -256,7 +258,7 @@
    "source": [
     "## Tool calling\n",
     "\n",
-    "We can use [tool calling](https://blog.langchain.dev/improving-core-tool-interfaces-and-docs-in-langchain/) with an LLM [that has been fine-tuned for tool use](https://ollama.com/library/llama3.1): \n",
+    "We can use [tool calling](https://blog.langchain.dev/improving-core-tool-interfaces-and-docs-in-langchain/) with an LLM [that has been fine-tuned for tool use](https://ollama.com/library/llama3.1):\n",
     "\n",
     "```\n",
     "ollama pull llama3.1\n",
@@ -442,6 +444,63 @@
     "print(query_chain)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "fb6a331f-1507-411f-89e5-c4d598154f3c",
+   "metadata": {},
+   "source": [
+    "## Reasoning models and custom message roles\n",
+    "\n",
+    "Some models, such as IBM's [Granite 3.2](https://ollama.com/library/granite3.2), support custom message roles to enable thinking processes.\n",
+    "\n",
+    "To access Granite 3.2's thinking features, pass a message with a `\"control\"` role with content set to `\"thinking\"`. Because `\"control\"` is a non-standard message role, we can use a [ChatMessage](https://python.langchain.com/api_reference/core/messages/langchain_core.messages.chat.ChatMessage.html) object to implement it:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "d7309fa7-990e-4c20-b1f0-b155624ecf37",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Here is my thought process:\n",
+      "This question is asking for the result of 3 raised to the power of 3, which is a basic mathematical operation. \n",
+      "\n",
+      "Here is my response:\n",
+      "The expression 3^3 means 3 raised to the power of 3. To calculate this, you multiply the base number (3) by itself as many times as its exponent (3):\n",
+      "\n",
+      "3 * 3 * 3 = 27\n",
+      "\n",
+      "So, 3^3 equals 27.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain_core.messages import ChatMessage, HumanMessage\n",
+    "from langchain_ollama import ChatOllama\n",
+    "\n",
+    "llm = ChatOllama(model=\"granite3.2:8b\")\n",
+    "\n",
+    "messages = [\n",
+    "    ChatMessage(role=\"control\", content=\"thinking\"),\n",
+    "    HumanMessage(\"What is 3^3?\"),\n",
+    "]\n",
+    "\n",
+    "response = llm.invoke(messages)\n",
+    "print(response.content)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6271d032-da40-44d4-9b52-58370e164be3",
+   "metadata": {},
+   "source": [
+    "Note that the model exposes its thought process in addition to its final response."
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
@@ -469,7 +528,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.4"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/openai.ipynb

@@ -408,7 +408,7 @@
     "\n",
     ":::\n",
     "\n",
-    "OpenAI supports a [Responses](https://platform.openai.com/docs/guides/responses-vs-chat-completions) API that is oriented toward building [agentic](/docs/concepts/agents/) applications. It includes a suite of [built-in tools](https://platform.openai.com/docs/guides/tools?api-mode=responses), including web and file search. It also supports management of [conversation state](https://platform.openai.com/docs/guides/conversation-state?api-mode=responses), allowing you to continue a conversational thread without explicitly passing in previous messages.\n",
+    "OpenAI supports a [Responses](https://platform.openai.com/docs/guides/responses-vs-chat-completions) API that is oriented toward building [agentic](/docs/concepts/agents/) applications. It includes a suite of [built-in tools](https://platform.openai.com/docs/guides/tools?api-mode=responses), including web and file search. It also supports management of [conversation state](https://platform.openai.com/docs/guides/conversation-state?api-mode=responses), allowing you to continue a conversational thread without explicitly passing in previous messages, as well as the output from [reasoning processes](https://platform.openai.com/docs/guides/reasoning?api-mode=responses).\n",
     "\n",
     "`ChatOpenAI` will route to the Responses API if one of these features is used. You can also specify `use_responses_api=True` when instantiating `ChatOpenAI`.\n",
     "\n",
@@ -1056,6 +1056,77 @@
     "print(second_response.text())"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "67bf5bd2-0935-40a0-b1cd-c6662b681d4b",
+   "metadata": {},
+   "source": [
+    "### Reasoning output\n",
+    "\n",
+    "Some OpenAI models will generate separate text content illustrating their reasoning process. See OpenAI's [reasoning documentation](https://platform.openai.com/docs/guides/reasoning?api-mode=responses) for details.\n",
+    "\n",
+    "OpenAI can return a summary of the model's reasoning (although it doesn't expose the raw reasoning tokens). To configure `ChatOpenAI` to return this summary, specify the `reasoning` parameter:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "8d322f3a-0732-45ab-ac95-dfd4596e0d85",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'3^3 = 3 × 3 × 3 = 27.'"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "reasoning = {\n",
+    "    \"effort\": \"medium\",  # 'low', 'medium', or 'high'\n",
+    "    \"summary\": \"auto\",  # 'detailed', 'auto', or None\n",
+    "}\n",
+    "\n",
+    "llm = ChatOpenAI(\n",
+    "    model=\"o4-mini\",\n",
+    "    use_responses_api=True,\n",
+    "    model_kwargs={\"reasoning\": reasoning},\n",
+    ")\n",
+    "response = llm.invoke(\"What is 3^3?\")\n",
+    "\n",
+    "# Output\n",
+    "response.text()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "d7dcc082-b7c8-41b7-a5e2-441b9679e41b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "**Calculating power of three**\n",
+      "\n",
+      "The user is asking for the result of 3 to the power of 3, which I know is 27. It's a straightforward question, so I’ll keep my answer concise: 27. I could explain that this is the same as multiplying 3 by itself twice: 3 × 3 × 3 equals 27. However, since the user likely just needs the answer, I’ll simply respond with 27.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Reasoning\n",
+    "reasoning = response.additional_kwargs[\"reasoning\"]\n",
+    "for block in reasoning[\"summary\"]:\n",
+    "    print(block[\"text\"])"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "57e27714",

docs/docs/integrations/chat/perplexity.ipynb

@@ -17,12 +17,66 @@
    "source": [
     "# ChatPerplexity\n",
     "\n",
-    "This notebook covers how to get started with `Perplexity` chat models."
+    "\n",
+    "This page will help you get started with Perplexity [chat models](../../concepts/chat_models.mdx). For detailed documentation of all `ChatPerplexity` features and configurations head to the [API reference](https://python.langchain.com/api_reference/perplexity/chat_models/langchain_perplexity.chat_models.ChatPerplexity.html).\n",
+    "\n",
+    "## Overview\n",
+    "### Integration details\n",
+    "\n",
+    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/docs/integrations/chat/xai) | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+    "| [ChatPerplexity](https://python.langchain.com/api_reference/perplexity/chat_models/langchain_perplexity.chat_models.ChatPerplexity.html) | [langchain-perplexity](https://python.langchain.com/api_reference/perplexity/perplexity.html) | ❌ | beta | ❌ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-perplexity?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-perplexity?style=flat-square&label=%20) |\n",
+    "\n",
+    "### Model features\n",
+    "| [Tool calling](../../how_to/tool_calling.ipynb) | [Structured output](../../how_to/structured_output.ipynb) | JSON mode | [Image input](../../how_to/multimodal_inputs.ipynb) | Audio input | Video input | [Token-level streaming](../../how_to/chat_streaming.ipynb) | Native async | [Token usage](../../how_to/chat_token_usage_tracking.ipynb) | [Logprobs](../../how_to/logprobs.ipynb) |\n",
+    "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
+    "| ❌ | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | ❌ | ✅ | ❌ |\n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "To access Perplexity models you'll need to create a Perplexity account, get an API key, and install the `langchain-perplexity` integration package.\n",
+    "\n",
+    "### Credentials\n",
+    "\n",
+    "Head to [this page](https://www.perplexity.ai/) to sign up for Perplexity and generate an API key. Once you've done this set the `PPLX_API_KEY` environment variable:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
+   "id": "2243f329",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "if \"PPLX_API_KEY\" not in os.environ:\n",
+    "    os.environ[\"PPLX_API_KEY\"] = getpass.getpass(\"Enter your Perplexity API key: \")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7dfe47c4",
+   "metadata": {},
+   "source": [
+    "To enable automated tracing of your model calls, set your [LangSmith](https://docs.smith.langchain.com/) API key:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "10a791fa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
+    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
    "id": "d4a7c55d-b235-4ca4-a579-c90cc9570da9",
    "metadata": {
     "ExecuteTime": {
@@ -33,8 +87,8 @@
    },
    "outputs": [],
    "source": [
-    "from langchain_community.chat_models import ChatPerplexity\n",
-    "from langchain_core.prompts import ChatPromptTemplate"
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_perplexity import ChatPerplexity"
    ]
   },
   {
@@ -62,29 +116,9 @@
    "id": "97a8ce3a",
    "metadata": {},
    "source": [
-    "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=\"llama-3.1-sonar-small-128k-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."
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "d3e49d78",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "from getpass import getpass\n",
-    "\n",
-    "PPLX_API_KEY = getpass()\n",
-    "os.environ[\"PPLX_API_KEY\"] = PPLX_API_KEY"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 3,
@@ -305,7 +339,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": ".venv",
    "language": "python",
    "name": "python3"
   },
@@ -319,7 +353,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.4"
+   "version": "3.11.11"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/predictionguard.ipynb

@@ -57,8 +57,8 @@
   {
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-11-08T19:44:51.390231Z",
-     "start_time": "2024-11-08T19:44:51.387945Z"
+     "end_time": "2025-04-21T18:23:30.746350Z",
+     "start_time": "2025-04-21T18:23:30.744744Z"
     }
    },
    "cell_type": "code",
@@ -70,7 +70,7 @@
    ],
    "id": "fa57fba89276da13",
    "outputs": [],
-   "execution_count": 1
+   "execution_count": 2
   },
   {
    "metadata": {},
@@ -82,12 +82,25 @@
    "id": "87dc1742af7b053"
   },
   {
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-21T18:23:33.359278Z",
+     "start_time": "2025-04-21T18:23:32.853207Z"
+    }
+   },
    "cell_type": "code",
    "source": "%pip install -qU langchain-predictionguard",
    "id": "b816ae8553cba021",
-   "outputs": [],
-   "execution_count": null
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
+   "execution_count": 3
   },
   {
    "cell_type": "markdown",
@@ -103,13 +116,13 @@
    "metadata": {
     "id": "2xe8JEUwA7_y",
     "ExecuteTime": {
-     "end_time": "2024-11-08T19:44:53.950653Z",
-     "start_time": "2024-11-08T19:44:53.488694Z"
+     "end_time": "2025-04-21T18:23:39.812675Z",
+     "start_time": "2025-04-21T18:23:39.666881Z"
     }
    },
    "source": "from langchain_predictionguard import ChatPredictionGuard",
    "outputs": [],
-   "execution_count": 2
+   "execution_count": 4
   },
   {
    "cell_type": "code",
@@ -117,8 +130,8 @@
    "metadata": {
     "id": "Ua7Mw1N4HcER",
     "ExecuteTime": {
-     "end_time": "2024-11-08T19:44:54.890695Z",
-     "start_time": "2024-11-08T19:44:54.502846Z"
+     "end_time": "2025-04-21T18:23:41.590296Z",
+     "start_time": "2025-04-21T18:23:41.253237Z"
     }
    },
    "source": [
@@ -126,7 +139,7 @@
     "chat = ChatPredictionGuard(model=\"Hermes-3-Llama-3.1-8B\")"
    ],
    "outputs": [],
-   "execution_count": 3
+   "execution_count": 5
   },
   {
    "metadata": {},
@@ -221,6 +234,132 @@
    ],
    "execution_count": 6
   },
+  {
+   "metadata": {},
+   "cell_type": "markdown",
+   "source": [
+    "## Tool Calling\n",
+    "\n",
+    "Prediction Guard has a tool calling API that lets you describe tools and their arguments, which enables the model return a JSON object with a tool to call and the inputs to that tool. Tool-calling is very useful for building tool-using chains and agents, and for getting structured outputs from models more generally.\n"
+   ],
+   "id": "1227780d6e6728ba"
+  },
+  {
+   "metadata": {},
+   "cell_type": "markdown",
+   "source": [
+    "### ChatPredictionGuard.bind_tools()\n",
+    "\n",
+    "Using `ChatPredictionGuard.bind_tools()`, you can pass in Pydantic classes, dict schemas, and Langchain tools as tools to the model, which are then reformatted to allow for use by the model."
+   ],
+   "id": "23446aa52e01d1ba"
+  },
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "outputs": [],
+   "execution_count": null,
+   "source": [
+    "from pydantic 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",
+    "class GetPopulation(BaseModel):\n",
+    "    \"\"\"Get the current population 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(\n",
+    "    [GetWeather, GetPopulation]\n",
+    "    # strict = True  # enforce tool args schema is respected\n",
+    ")"
+   ],
+   "id": "135efb0bfc5916c1"
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-21T18:42:41.834079Z",
+     "start_time": "2025-04-21T18:42:40.289095Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "ai_msg = llm_with_tools.invoke(\n",
+    "    \"Which city is hotter today and which is bigger: LA or NY?\"\n",
+    ")\n",
+    "ai_msg"
+   ],
+   "id": "8136f19a8836cd58",
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'chatcmpl-tool-b1204a3c70b44cd8802579df48df0c8c', 'type': 'function', 'index': 0, 'function': {'name': 'GetWeather', 'arguments': '{\"location\": \"Los Angeles, CA\"}'}}, {'id': 'chatcmpl-tool-e299116c05bf4ce498cd6042928ae080', 'type': 'function', 'index': 0, 'function': {'name': 'GetWeather', 'arguments': '{\"location\": \"New York, NY\"}'}}, {'id': 'chatcmpl-tool-19502a60f30348669ffbac00ff503388', 'type': 'function', 'index': 0, 'function': {'name': 'GetPopulation', 'arguments': '{\"location\": \"Los Angeles, CA\"}'}}, {'id': 'chatcmpl-tool-4b8d56ef067f447795d9146a56e43510', 'type': 'function', 'index': 0, 'function': {'name': 'GetPopulation', 'arguments': '{\"location\": \"New York, NY\"}'}}]}, response_metadata={}, id='run-4630cfa9-4e95-42dd-8e4a-45db78180a10-0', tool_calls=[{'name': 'GetWeather', 'args': {'location': 'Los Angeles, CA'}, 'id': 'chatcmpl-tool-b1204a3c70b44cd8802579df48df0c8c', 'type': 'tool_call'}, {'name': 'GetWeather', 'args': {'location': 'New York, NY'}, 'id': 'chatcmpl-tool-e299116c05bf4ce498cd6042928ae080', 'type': 'tool_call'}, {'name': 'GetPopulation', 'args': {'location': 'Los Angeles, CA'}, 'id': 'chatcmpl-tool-19502a60f30348669ffbac00ff503388', 'type': 'tool_call'}, {'name': 'GetPopulation', 'args': {'location': 'New York, NY'}, 'id': 'chatcmpl-tool-4b8d56ef067f447795d9146a56e43510', 'type': 'tool_call'}])"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "execution_count": 7
+  },
+  {
+   "metadata": {},
+   "cell_type": "markdown",
+   "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."
+   ],
+   "id": "84f405c45a35abe5"
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-21T18:43:00.429453Z",
+     "start_time": "2025-04-21T18:43:00.426399Z"
+    }
+   },
+   "cell_type": "code",
+   "source": "ai_msg.tool_calls",
+   "id": "bdcee85475019719",
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'name': 'GetWeather',\n",
+       "  'args': {'location': 'Los Angeles, CA'},\n",
+       "  'id': 'chatcmpl-tool-b1204a3c70b44cd8802579df48df0c8c',\n",
+       "  'type': 'tool_call'},\n",
+       " {'name': 'GetWeather',\n",
+       "  'args': {'location': 'New York, NY'},\n",
+       "  'id': 'chatcmpl-tool-e299116c05bf4ce498cd6042928ae080',\n",
+       "  'type': 'tool_call'},\n",
+       " {'name': 'GetPopulation',\n",
+       "  'args': {'location': 'Los Angeles, CA'},\n",
+       "  'id': 'chatcmpl-tool-19502a60f30348669ffbac00ff503388',\n",
+       "  'type': 'tool_call'},\n",
+       " {'name': 'GetPopulation',\n",
+       "  'args': {'location': 'New York, NY'},\n",
+       "  'id': 'chatcmpl-tool-4b8d56ef067f447795d9146a56e43510',\n",
+       "  'type': 'tool_call'}]"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "execution_count": 8
+  },
   {
    "cell_type": "markdown",
    "id": "ff1b51a8",

docs/docs/integrations/chat/qwq.ipynb

@@ -0,0 +1,284 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "id": "afaf8039",
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
+   "source": [
+    "---\n",
+    "sidebar_label: Qwen QwQ\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e49f1e0d",
+   "metadata": {},
+   "source": [
+    "# ChatQwQ\n",
+    "\n",
+    "This will help you getting started with QwQ [chat models](../../concepts/chat_models.mdx). For detailed documentation of all ChatQwQ features and configurations head to the [API reference](https://pypi.org/project/langchain-qwq/).\n",
+    "\n",
+    "## Overview\n",
+    "### Integration details\n",
+    "\n",
+    "\n",
+    "| Class | Package | Local | Serializable | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: |  :---: | :---: | :---: |\n",
+    "| [ChatQwQ](https://pypi.org/project/langchain-qwq/) | [langchain-qwq](https://pypi.org/project/langchain-qwq/) | ❌ | beta | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-qwq?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-qwq?style=flat-square&label=%20) |\n",
+    "\n",
+    "### Model features\n",
+    "| [Tool calling](../../how_to/tool_calling.ipynb) | [Structured output](../../how_to/structured_output.ipynb) | JSON mode | [Image input](../../how_to/multimodal_inputs.ipynb) | Audio input | Video input | [Token-level streaming](../../how_to/chat_streaming.ipynb) | Native async | [Token usage](../../how_to/chat_token_usage_tracking.ipynb) | [Logprobs](../../how_to/logprobs.ipynb) |\n",
+    "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
+    "| ✅ | ✅ | ✅ |❌  | ❌ | ❌ | ✅ | ✅ | ✅ | ❌ | \n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "To access QwQ models you'll need to create an Alibaba Cloud account, get an API key, and install the `langchain-qwq` integration package.\n",
+    "\n",
+    "### Credentials\n",
+    "\n",
+    "Head to [Alibaba's API Key page](https://account.alibabacloud.com/login/login.htm?oauth_callback=https%3A%2F%2Fbailian.console.alibabacloud.com%2F%3FapiKey%3D1&lang=en#/api-key) to sign up to Alibaba Cloud and generate an API key. Once you've done this set the `DASHSCOPE_API_KEY` environment variable:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "433e8d2b-9519-4b49-b2c4-7ab65b046c94",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "if not os.getenv(\"DASHSCOPE_API_KEY\"):\n",
+    "    os.environ[\"DASHSCOPE_API_KEY\"] = getpass.getpass(\"Enter your Dashscope API key: \")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0730d6a1-c893-4840-9817-5e5251676d5d",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "The LangChain QwQ integration lives in the `langchain-qwq` package:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU langchain-qwq"
+   ]
+  },
+  {
+   "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": 3,
+   "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_qwq import ChatQwQ\n",
+    "\n",
+    "llm = ChatQwQ(\n",
+    "    model=\"qwq-plus\",\n",
+    "    max_tokens=3_000,\n",
+    "    timeout=None,\n",
+    "    max_retries=2,\n",
+    "    # other params...\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2b4f3e15",
+   "metadata": {},
+   "source": [
+    "## Invocation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "62e0dbc3",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"J'aime la programmation.\", additional_kwargs={'reasoning_content': 'Okay, the user wants me to translate \"I love programming.\" into French. Let\\'s start by breaking down the sentence. The subject is \"I\", which in French is \"Je\". The verb is \"love\", which in this context is present tense, so \"aime\". The object is \"programming\". Now, \"programming\" in French can be \"la programmation\". \\n\\nWait, should it be \"programmation\" or \"programmation\"? Let me confirm the spelling. Yes, \"programmation\" is correct. Now, putting it all together: \"Je aime la programmation.\" Hmm, but in French, there\\'s a tendency to contract \"je\" and \"aime\". Wait, actually, \"je\" followed by a vowel sound usually takes \"j\\'\". So it should be \"J\\'aime la programmation.\" \\n\\nLet me double-check. \"J\\'aime\" is the correct contraction for \"I love\". The definite article \"la\" is needed because \"programmation\" is a feminine noun. Yes, \"programmation\" is a feminine noun, so \"la\" is correct. \\n\\nIs there any other way to say it? Maybe \"J\\'adore la programmation\" for \"I love\" in a stronger sense, but the user didn\\'t specify the intensity. Since the original is straightforward, \"J\\'aime la programmation.\" is the direct translation. \\n\\nI think that\\'s it. No mistakes there. So the final translation should be \"J\\'aime la programmation.\"'}, response_metadata={'model_name': 'qwq-plus'}, id='run-5045cd6a-edbd-4b2f-bf24-b7bdf3777fb9-0', usage_metadata={'input_tokens': 32, 'output_tokens': 326, 'total_tokens': 358, 'input_token_details': {}, 'output_token_details': {}})"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "messages = [\n",
+    "    (\n",
+    "        \"system\",\n",
+    "        \"You are a helpful assistant that translates English to French.\"\n",
+    "        \"Translate the user sentence.\",\n",
+    "    ),\n",
+    "    (\"human\", \"I love programming.\"),\n",
+    "]\n",
+    "ai_msg = llm.invoke(messages)\n",
+    "ai_msg"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "18e2bfc0-7e78-4528-a73f-499ac150dca8",
+   "metadata": {},
+   "source": [
+    "## Chaining\n",
+    "\n",
+    "We can [chain](../../how_to/sequence.ipynb) our model with a prompt template like so:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='Ich liebe das Programmieren.', additional_kwargs={'reasoning_content': 'Okay, the user wants me to translate \"I love programming.\" into German. Let me think. The verb \"love\" is \"lieben\" or \"mögen\" in German, but \"lieben\" is more like love, while \"mögen\" is prefer. Since it\\'s about programming, which is a strong affection, \"lieben\" is better. The subject is \"I\", which is \"ich\". Then \"programming\" is \"Programmierung\" or \"Coding\". But \"Programmierung\" is more formal. Alternatively, sometimes people say \"ich liebe es zu programmieren\" which is \"I love to program\". Hmm, maybe the direct translation would be \"Ich liebe die Programmierung.\" But maybe the more natural way is \"Ich liebe es zu programmieren.\" Let me check. Both are correct, but the second one might sound more natural in everyday speech. The user might prefer the concise version. Alternatively, maybe \"Ich liebe die Programmierung.\" is better. Wait, the original is \"programming\" as a noun. So using the noun form would be appropriate. So \"Ich liebe die Programmierung.\" But sometimes people also use \"Coding\" in German, like \"Ich liebe das Coding.\" But that\\'s more anglicism. Probably better to stick with \"Programmierung\". Alternatively, \"Programmieren\" as a noun. Oh right! \"Programmieren\" can be a noun when used in the accusative case. So \"Ich liebe das Programmieren.\" That\\'s correct and natural. Yes, that\\'s the best translation. So the answer is \"Ich liebe das Programmieren.\"'}, response_metadata={'model_name': 'qwq-plus'}, id='run-2c418451-51d8-4319-8269-2ce129363a1a-0', usage_metadata={'input_tokens': 28, 'output_tokens': 341, 'total_tokens': 369, 'input_token_details': {}, 'output_token_details': {}})"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "\n",
+    "prompt = ChatPromptTemplate(\n",
+    "    [\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            \"You are a helpful assistant that translates\"\n",
+    "            \"{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": "8d1b3ef3",
+   "metadata": {},
+   "source": [
+    "## Tool Calling\n",
+    "ChatQwQ supports tool calling 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."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6db1a355",
+   "metadata": {},
+   "source": [
+    "### Use with `bind_tools`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "15fb6a6d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "content='' additional_kwargs={'reasoning_content': 'Okay, the user is asking \"What\\'s 5 times forty two\". Let me break this down. First, I need to identify the numbers involved. The first number is 5, which is straightforward. The second number is forty two, which is 42 in digits. The operation they want is multiplication.\\n\\nLooking at the tools provided, there\\'s a function called multiply that takes two integers. So I should use that. The parameters are first_int and second_int. \\n\\nI need to convert \"forty two\" to 42. Since the function requires integers, both numbers should be in integer form. So 5 and 42. \\n\\nNow, I\\'ll structure the tool call. The function name is multiply, and the arguments should be first_int: 5 and second_int: 42. I\\'ll make sure the JSON is correctly formatted without any syntax errors. Let me double-check the parameters to ensure they\\'re required and of the right type. Yep, both are required and integers. \\n\\nNo examples were provided, but the function\\'s purpose is clear. So the correct tool call should be to multiply those two numbers. I think that\\'s all. No other functions are needed here.'} response_metadata={'model_name': 'qwq-plus'} id='run-638895aa-fdde-4567-bcfa-7d8e5d4f24af-0' tool_calls=[{'name': 'multiply', 'args': {'first_int': 5, 'second_int': 42}, 'id': 'call_d088275851c140529ed2ad', 'type': 'tool_call'}] usage_metadata={'input_tokens': 176, 'output_tokens': 277, 'total_tokens': 453, 'input_token_details': {}, 'output_token_details': {}}\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain_core.tools import tool\n",
+    "from langchain_qwq import ChatQwQ\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def multiply(first_int: int, second_int: int) -> int:\n",
+    "    \"\"\"Multiply two integers together.\"\"\"\n",
+    "    return first_int * second_int\n",
+    "\n",
+    "\n",
+    "llm = ChatQwQ()\n",
+    "\n",
+    "llm_with_tools = llm.bind_tools([multiply])\n",
+    "\n",
+    "msg = llm_with_tools.invoke(\"What's 5 times forty two\")\n",
+    "\n",
+    "print(msg)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all ChatQwQ features and configurations head to the [API reference](https://pypi.org/project/langchain-qwq/)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.13.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/integrations/chat/runpod.ipynb

@@ -0,0 +1,276 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# RunPod Chat Model"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Get started with RunPod chat models.\n",
+    "\n",
+    "## Overview\n",
+    "\n",
+    "This guide covers how to use the LangChain `ChatRunPod` class to interact with chat models hosted on [RunPod Serverless](https://www.runpod.io/serverless-gpu)."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setup\n",
+    "\n",
+    "1.  **Install the package:**\n",
+    "    ```bash\n",
+    "    pip install -qU langchain-runpod\n",
+    "    ```\n",
+    "2.  **Deploy a Chat Model Endpoint:** Follow the setup steps in the [RunPod Provider Guide](/docs/integrations/providers/runpod#setup) to deploy a compatible chat model endpoint on RunPod Serverless and get its Endpoint ID.\n",
+    "3.  **Set Environment Variables:** Make sure `RUNPOD_API_KEY` and `RUNPOD_ENDPOINT_ID` (or a specific `RUNPOD_CHAT_ENDPOINT_ID`) are set."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "# Make sure environment variables are set (or pass them directly to ChatRunPod)\n",
+    "if \"RUNPOD_API_KEY\" not in os.environ:\n",
+    "    os.environ[\"RUNPOD_API_KEY\"] = getpass.getpass(\"Enter your RunPod API Key: \")\n",
+    "\n",
+    "if \"RUNPOD_ENDPOINT_ID\" not in os.environ:\n",
+    "    os.environ[\"RUNPOD_ENDPOINT_ID\"] = input(\n",
+    "        \"Enter your RunPod Endpoint ID (used if RUNPOD_CHAT_ENDPOINT_ID is not set): \"\n",
+    "    )\n",
+    "\n",
+    "# Optionally use a different endpoint ID specifically for chat models\n",
+    "# if \"RUNPOD_CHAT_ENDPOINT_ID\" not in os.environ:\n",
+    "#     os.environ[\"RUNPOD_CHAT_ENDPOINT_ID\"] = input(\"Enter your RunPod Chat Endpoint ID (Optional): \")\n",
+    "\n",
+    "chat_endpoint_id = os.environ.get(\n",
+    "    \"RUNPOD_CHAT_ENDPOINT_ID\", os.environ.get(\"RUNPOD_ENDPOINT_ID\")\n",
+    ")\n",
+    "if not chat_endpoint_id:\n",
+    "    raise ValueError(\n",
+    "        \"No RunPod Endpoint ID found. Please set RUNPOD_ENDPOINT_ID or RUNPOD_CHAT_ENDPOINT_ID.\"\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "Initialize the `ChatRunPod` class. You can pass model-specific parameters via `model_kwargs` and configure polling behavior."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_runpod import ChatRunPod\n",
+    "\n",
+    "chat = ChatRunPod(\n",
+    "    runpod_endpoint_id=chat_endpoint_id,  # Specify the correct endpoint ID\n",
+    "    model_kwargs={\n",
+    "        \"max_new_tokens\": 512,\n",
+    "        \"temperature\": 0.7,\n",
+    "        \"top_p\": 0.9,\n",
+    "        # Add other parameters supported by your endpoint handler\n",
+    "    },\n",
+    "    # Optional: Adjust polling\n",
+    "    # poll_interval=0.2,\n",
+    "    # max_polling_attempts=150\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Invocation\n",
+    "\n",
+    "Use the standard LangChain `.invoke()` and `.ainvoke()` methods to call the model. Streaming is also supported via `.stream()` and `.astream()` (simulated by polling the RunPod `/stream` endpoint)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_core.messages import HumanMessage, SystemMessage\n",
+    "\n",
+    "messages = [\n",
+    "    SystemMessage(content=\"You are a helpful AI assistant.\"),\n",
+    "    HumanMessage(content=\"What is the RunPod Serverless API flow?\"),\n",
+    "]\n",
+    "\n",
+    "# Invoke (Sync)\n",
+    "try:\n",
+    "    response = chat.invoke(messages)\n",
+    "    print(\"--- Sync Invoke Response ---\")\n",
+    "    print(response.content)\n",
+    "except Exception as e:\n",
+    "    print(\n",
+    "        f\"Error invoking Chat Model: {e}. Ensure endpoint ID/API key are correct and endpoint is active/compatible.\"\n",
+    "    )\n",
+    "\n",
+    "# Stream (Sync, simulated via polling /stream)\n",
+    "print(\"\\n--- Sync Stream Response ---\")\n",
+    "try:\n",
+    "    for chunk in chat.stream(messages):\n",
+    "        print(chunk.content, end=\"\", flush=True)\n",
+    "    print()  # Newline\n",
+    "except Exception as e:\n",
+    "    print(\n",
+    "        f\"\\nError streaming Chat Model: {e}. Ensure endpoint handler supports streaming output format.\"\n",
+    "    )\n",
+    "\n",
+    "### Async Usage\n",
+    "\n",
+    "# AInvoke (Async)\n",
+    "try:\n",
+    "    async_response = await chat.ainvoke(messages)\n",
+    "    print(\"--- Async Invoke Response ---\")\n",
+    "    print(async_response.content)\n",
+    "except Exception as e:\n",
+    "    print(f\"Error invoking Chat Model asynchronously: {e}.\")\n",
+    "\n",
+    "# AStream (Async)\n",
+    "print(\"\\n--- Async Stream Response ---\")\n",
+    "try:\n",
+    "    async for chunk in chat.astream(messages):\n",
+    "        print(chunk.content, end=\"\", flush=True)\n",
+    "    print()  # Newline\n",
+    "except Exception as e:\n",
+    "    print(\n",
+    "        f\"\\nError streaming Chat Model asynchronously: {e}. Ensure endpoint handler supports streaming output format.\\n\"\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Chaining\n",
+    "\n",
+    "The chat model integrates seamlessly with LangChain Expression Language (LCEL) chains."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\"system\", \"You are a helpful assistant.\"),\n",
+    "        (\"human\", \"{input}\"),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "parser = StrOutputParser()\n",
+    "\n",
+    "chain = prompt | chat | parser\n",
+    "\n",
+    "try:\n",
+    "    chain_response = chain.invoke(\n",
+    "        {\"input\": \"Explain the concept of serverless computing in simple terms.\"}\n",
+    "    )\n",
+    "    print(\"--- Chain Response ---\")\n",
+    "    print(chain_response)\n",
+    "except Exception as e:\n",
+    "    print(f\"Error running chain: {e}\")\n",
+    "\n",
+    "\n",
+    "# Async chain\n",
+    "try:\n",
+    "    async_chain_response = await chain.ainvoke(\n",
+    "        {\"input\": \"What are the benefits of using RunPod for AI/ML workloads?\"}\n",
+    "    )\n",
+    "    print(\"--- Async Chain Response ---\")\n",
+    "    print(async_chain_response)\n",
+    "except Exception as e:\n",
+    "    print(f\"Error running async chain: {e}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Model Features (Endpoint Dependent)\n",
+    "\n",
+    "The availability of advanced features depends **heavily** on the specific implementation of your RunPod endpoint handler. The `ChatRunPod` integration provides the basic framework, but the handler must support the underlying functionality.\n",
+    "\n",
+    "| Feature                                                    | Integration Support | Endpoint Dependent? | Notes                                                                                                                                                                      |\n",
+    "| :--------------------------------------------------------- | :-----------------: | :-----------------: | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n",
+    "| [Tool calling](/docs/how_to/tool_calling)                | ❌                  | ✅                  | Requires handler to process tool definitions and return tool calls (e.g., OpenAI format). Integration needs parsing logic.                                                 |\n",
+    "| [Structured output](/docs/how_to/structured_output)        | ❌                  | ✅                  | Requires handler support for forcing structured output (JSON mode, function calling). Integration needs parsing logic.                                                   |\n",
+    "| JSON mode                                                  | ❌                  | ✅                  | Requires handler to accept a `json_mode` parameter (or similar) and guarantee JSON output.                                                                               |\n",
+    "| [Image input](/docs/how_to/multimodal_inputs)            | ❌                  | ✅                  | Requires multimodal handler accepting image data (e.g., base64). Integration does not support multimodal messages.                                                       |\n",
+    "| Audio input                                                | ❌                  | ✅                  | Requires handler accepting audio data. Integration does not support audio messages.                                                                                        |\n",
+    "| Video input                                                | ❌                  | ✅                  | Requires handler accepting video data. Integration does not support video messages.                                                                                        |\n",
+    "| [Token-level streaming](/docs/how_to/chat_streaming)       | ✅ (Simulated)      | ✅                  | Polls `/stream`. Requires handler to populate `stream` list in status response with token chunks (e.g., `[{\"output\": \"token\"}]`). True low-latency streaming not built-in. |\n",
+    "| Native async                                               | ✅                  | ✅                  | Core `ainvoke`/`astream` implemented. Relies on endpoint handler performance.                                                                                              |\n",
+    "| [Token usage](/docs/how_to/chat_token_usage_tracking)    | ❌                  | ✅                  | Requires handler to return `prompt_tokens`, `completion_tokens` in the final response. Integration currently does not parse this.                                           |\n",
+    "| [Logprobs](/docs/how_to/logprobs)                          | ❌                  | ✅                  | Requires handler to return log probabilities. Integration currently does not parse this.                                                                                  |\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**Key Takeaway:** Standard chat invocation and simulated streaming work if the endpoint follows basic RunPod API conventions. Advanced features require specific handler implementations and potentially extending or customizing this integration package."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of the `ChatRunPod` class, parameters, and methods, refer to the source code or the generated API reference (if available).\n",
+    "\n",
+    "Link to source code: [https://github.com/runpod/langchain-runpod/blob/main/langchain_runpod/chat_models.py](https://github.com/runpod/langchain-runpod/blob/main/langchain_runpod/chat_models.py)"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/docs/integrations/chat/seekrflow.ipynb

@@ -0,0 +1,362 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "62d5a1ea",
+   "metadata": {},
+   "source": [
+    "# ChatSeekrFlow\n",
+    "\n",
+    "> [Seekr](https://www.seekr.com/) provides AI-powered solutions for structured, explainable, and transparent AI interactions.\n",
+    "\n",
+    "This notebook provides a quick overview for getting started with Seekr [chat models](/docs/concepts/chat_models). For detailed documentation of all `ChatSeekrFlow` features and configurations, head to the [API reference](https://python.langchain.com/api_reference/community/chat_models/langchain_community.chat_models.seekrflow.ChatSeekrFlow.html).\n",
+    "\n",
+    "## Overview\n",
+    "\n",
+    "`ChatSeekrFlow` class wraps a chat model endpoint hosted on SeekrFlow, enabling seamless integration with LangChain applications.\n",
+    "\n",
+    "### Integration Details\n",
+    "\n",
+    "| Class | Package | Local | Serializable | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |  :---: | :---: |\n",
+    "| [ChatSeekrFlow](https://python.langchain.com/api_reference/community/chat_models/langchain_community.chat_models.seekrflow.ChatSeekrFlow.html) | [seekrai](https://python.langchain.com/docs/integrations/providers/seekr/) | ❌ | beta | ![PyPI - Downloads](https://img.shields.io/pypi/dm/seekrai?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/seekrai?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](/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",
+    "`ChatSeekrFlow` supports all methods of `ChatModel`, **except async APIs**.\n",
+    "\n",
+    "### Endpoint Requirements\n",
+    "\n",
+    "The serving endpoint `ChatSeekrFlow` wraps **must** have OpenAI-compatible chat input/output format. It can be used for:\n",
+    "1. **Fine-tuned Seekr models**\n",
+    "2. **Custom SeekrFlow models**\n",
+    "3. **RAG-enabled models using Seekr's retrieval system**\n",
+    "\n",
+    "For async usage, please refer to `AsyncChatSeekrFlow` (coming soon).\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "93fea471",
+   "metadata": {},
+   "source": [
+    "# Getting Started with ChatSeekrFlow in LangChain\n",
+    "\n",
+    "This notebook covers how to use SeekrFlow as a chat model in LangChain."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2f320c17",
+   "metadata": {},
+   "source": [
+    "## Setup\n",
+    "\n",
+    "Ensure you have the necessary dependencies installed:\n",
+    "\n",
+    "```bash\n",
+    "pip install seekrai langchain langchain-community\n",
+    "```\n",
+    "\n",
+    "You must also have an API key from Seekr to authenticate requests.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "911ca53c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Standard library\n",
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "# Third-party\n",
+    "from langchain.prompts import ChatPromptTemplate\n",
+    "from langchain.schema import HumanMessage\n",
+    "from langchain_core.runnables import RunnableSequence\n",
+    "\n",
+    "# OSS SeekrFlow integration\n",
+    "from langchain_seekrflow import ChatSeekrFlow\n",
+    "from seekrai import SeekrFlow"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "150461cb",
+   "metadata": {},
+   "source": [
+    "## API Key Setup\n",
+    "\n",
+    "You'll need to set your API key as an environment variable to authenticate requests.\n",
+    "\n",
+    "Run the below cell.\n",
+    "\n",
+    "Or manually assign it before running queries:\n",
+    "\n",
+    "```python\n",
+    "SEEKR_API_KEY = \"your-api-key-here\"\n",
+    "```\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "38afcd6e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "os.environ[\"SEEKR_API_KEY\"] = getpass.getpass(\"Enter your Seekr API key:\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "82d83c0e",
+   "metadata": {},
+   "source": [
+    "## Instantiation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "71b14751",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "os.environ[\"SEEKR_API_KEY\"]\n",
+    "seekr_client = SeekrFlow(api_key=SEEKR_API_KEY)\n",
+    "\n",
+    "llm = ChatSeekrFlow(\n",
+    "    client=seekr_client, model_name=\"meta-llama/Meta-Llama-3-8B-Instruct\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1046e86c",
+   "metadata": {},
+   "source": [
+    "## Invocation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "f61a60f6",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Hello there! I'm Seekr, nice to meet you! What brings you here today? Do you have a question, or are you looking for some help with something? I'm all ears (or rather, all text)!\n"
+     ]
+    }
+   ],
+   "source": [
+    "response = llm.invoke([HumanMessage(content=\"Hello, Seekr!\")])\n",
+    "print(response.content)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "853b0349",
+   "metadata": {},
+   "source": [
+    "## Chaining"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "35fca3ec",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "content='The translation of \"Good morning\" in French is:\\n\\n\"Bonne journée\"' additional_kwargs={} response_metadata={}\n"
+     ]
+    }
+   ],
+   "source": [
+    "prompt = ChatPromptTemplate.from_template(\"Translate to French: {text}\")\n",
+    "\n",
+    "chain: RunnableSequence = prompt | llm\n",
+    "result = chain.invoke({\"text\": \"Good morning\"})\n",
+    "print(result)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "a7b28b8d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "🔹 Testing Sync `stream()` (Streaming)...\n",
+      "Here is a haiku:\n",
+      "\n",
+      "Golden sunset fades\n",
+      "Ripples on the quiet lake\n",
+      "Peaceful evening sky"
+     ]
+    }
+   ],
+   "source": [
+    "def test_stream():\n",
+    "    \"\"\"Test synchronous invocation in streaming mode.\"\"\"\n",
+    "    print(\"\\n🔹 Testing Sync `stream()` (Streaming)...\")\n",
+    "\n",
+    "    for chunk in llm.stream([HumanMessage(content=\"Write me a haiku.\")]):\n",
+    "        print(chunk.content, end=\"\", flush=True)\n",
+    "\n",
+    "\n",
+    "# ✅ Ensure streaming is enabled\n",
+    "llm = ChatSeekrFlow(\n",
+    "    client=seekr_client,\n",
+    "    model_name=\"meta-llama/Meta-Llama-3-8B-Instruct\",\n",
+    "    streaming=True,  # ✅ Enable streaming\n",
+    ")\n",
+    "\n",
+    "# ✅ Run sync streaming test\n",
+    "test_stream()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b3847b34",
+   "metadata": {},
+   "source": [
+    "## Error Handling & Debugging"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "6bc38b48",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running test: Missing Client\n",
+      "✅ Expected Error: SeekrFlow client cannot be None.\n",
+      "Running test: Missing Model Name\n",
+      "✅ Expected Error: A valid model name must be provided.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Define a minimal mock SeekrFlow client\n",
+    "class MockSeekrClient:\n",
+    "    \"\"\"Mock SeekrFlow API client that mimics the real API structure.\"\"\"\n",
+    "\n",
+    "    class MockChat:\n",
+    "        \"\"\"Mock Chat object with a completions method.\"\"\"\n",
+    "\n",
+    "        class MockCompletions:\n",
+    "            \"\"\"Mock Completions object with a create method.\"\"\"\n",
+    "\n",
+    "            def create(self, *args, **kwargs):\n",
+    "                return {\n",
+    "                    \"choices\": [{\"message\": {\"content\": \"Mock response\"}}]\n",
+    "                }  # Mimic API response\n",
+    "\n",
+    "        completions = MockCompletions()\n",
+    "\n",
+    "    chat = MockChat()\n",
+    "\n",
+    "\n",
+    "def test_initialization_errors():\n",
+    "    \"\"\"Test that invalid ChatSeekrFlow initializations raise expected errors.\"\"\"\n",
+    "\n",
+    "    test_cases = [\n",
+    "        {\n",
+    "            \"name\": \"Missing Client\",\n",
+    "            \"args\": {\"client\": None, \"model_name\": \"seekrflow-model\"},\n",
+    "            \"expected_error\": \"SeekrFlow client cannot be None.\",\n",
+    "        },\n",
+    "        {\n",
+    "            \"name\": \"Missing Model Name\",\n",
+    "            \"args\": {\"client\": MockSeekrClient(), \"model_name\": \"\"},\n",
+    "            \"expected_error\": \"A valid model name must be provided.\",\n",
+    "        },\n",
+    "    ]\n",
+    "\n",
+    "    for test in test_cases:\n",
+    "        try:\n",
+    "            print(f\"Running test: {test['name']}\")\n",
+    "            faulty_llm = ChatSeekrFlow(**test[\"args\"])\n",
+    "\n",
+    "            # If no error is raised, fail the test\n",
+    "            print(f\"❌ Test '{test['name']}' failed: No error was raised!\")\n",
+    "        except Exception as e:\n",
+    "            error_msg = str(e)\n",
+    "            assert test[\"expected_error\"] in error_msg, f\"Unexpected error: {error_msg}\"\n",
+    "            print(f\"✅ Expected Error: {error_msg}\")\n",
+    "\n",
+    "\n",
+    "# Run test\n",
+    "test_initialization_errors()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d1c9ddf3",
+   "metadata": {},
+   "source": [
+    "## API reference"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "411a8bea",
+   "metadata": {},
+   "source": [
+    "- `ChatSeekrFlow` class: [`langchain_seekrflow.ChatSeekrFlow`](https://github.com/benfaircloth/langchain-seekrflow/blob/main/langchain_seekrflow/seekrflow.py)\n",
+    "- PyPI package: [`langchain-seekrflow`](https://pypi.org/project/langchain-seekrflow/)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3ef00a51",
+   "metadata": {},
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/integrations/chat/together.ipynb

@@ -1,267 +1,265 @@
 {
- "cells": [
-  {
-   "cell_type": "raw",
-   "id": "afaf8039",
-   "metadata": {},
-   "source": [
-    "---\n",
-    "sidebar_label: Together\n",
-    "---"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "e49f1e0d",
-   "metadata": {},
-   "source": [
-    "# ChatTogether\n",
-    "\n",
-    "\n",
-    "This page will help you get started with Together AI [chat models](../../concepts/chat_models.mdx). For detailed documentation of all ChatTogether features and configurations head to the [API reference](https://python.langchain.com/api_reference/together/chat_models/langchain_together.chat_models.ChatTogether.html).\n",
-    "\n",
-    "[Together AI](https://www.together.ai/) offers an API to query [50+ leading open-source models](https://docs.together.ai/docs/chat-models)\n",
-    "\n",
-    "## Overview\n",
-    "### Integration details\n",
-    "\n",
-    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/docs/integrations/chat/togetherai) | Package downloads | Package latest |\n",
-    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
-    "| [ChatTogether](https://python.langchain.com/api_reference/together/chat_models/langchain_together.chat_models.ChatTogether.html) | [langchain-together](https://python.langchain.com/api_reference/together/index.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-together?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-together?style=flat-square&label=%20) |\n",
-    "\n",
-    "### Model features\n",
-    "| [Tool calling](../../how_to/tool_calling.ipynb) | [Structured output](../../how_to/structured_output.ipynb) | JSON mode | [Image input](../../how_to/multimodal_inputs.ipynb) | Audio input | Video input | [Token-level streaming](../../how_to/chat_streaming.ipynb) | Native async | [Token usage](../../how_to/chat_token_usage_tracking.ipynb) | [Logprobs](../../how_to/logprobs.ipynb) |\n",
-    "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
-    "| ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ✅ | ✅ | \n",
-    "\n",
-    "## Setup\n",
-    "\n",
-    "To access Together models you'll need to create a/an Together account, get an API key, and install the `langchain-together` integration package.\n",
-    "\n",
-    "### Credentials\n",
-    "\n",
-    "Head to [this page](https://api.together.ai) to sign up to Together and generate an API key. Once you've done this set the TOGETHER_API_KEY environment variable:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "433e8d2b-9519-4b49-b2c4-7ab65b046c94",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "if \"TOGETHER_API_KEY\" not in os.environ:\n",
-    "    os.environ[\"TOGETHER_API_KEY\"] = getpass.getpass(\"Enter your Together API key: \")"
-   ]
-  },
-  {
-   "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": 2,
-   "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 Together integration lives in the `langchain-together` package:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%pip install -qU langchain-together"
-   ]
-  },
-  {
-   "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": 3,
-   "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_together import ChatTogether\n",
-    "\n",
-    "llm = ChatTogether(\n",
-    "    model=\"meta-llama/Llama-3-70b-chat-hf\",\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": 4,
-   "id": "62e0dbc3",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
+  "cells": [
     {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\"J'adore la programmation.\", response_metadata={'token_usage': {'completion_tokens': 9, 'prompt_tokens': 35, 'total_tokens': 44}, 'model_name': 'meta-llama/Llama-3-70b-chat-hf', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-eabcbe33-cdd8-45b8-ab0b-f90b6e7dfad8-0', usage_metadata={'input_tokens': 35, 'output_tokens': 9, 'total_tokens': 44})"
+      "cell_type": "raw",
+      "id": "afaf8039",
+      "metadata": {},
+      "source": [
+        "---\n",
+        "sidebar_label: Together\n",
+        "---"
       ]
-     },
-     "execution_count": 4,
-     "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": 5,
-   "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": "18e2bfc0-7e78-4528-a73f-499ac150dca8",
-   "metadata": {},
-   "source": [
-    "## Chaining\n",
-    "\n",
-    "We can [chain](../../how_to/sequence.ipynb) our model with a prompt template like so:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='Ich liebe das Programmieren.', response_metadata={'token_usage': {'completion_tokens': 7, 'prompt_tokens': 30, 'total_tokens': 37}, 'model_name': 'meta-llama/Llama-3-70b-chat-hf', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-a249aa24-ee31-46ba-9bf9-f4eb135b0a95-0', usage_metadata={'input_tokens': 30, 'output_tokens': 7, 'total_tokens': 37})"
+      "cell_type": "markdown",
+      "id": "e49f1e0d",
+      "metadata": {},
+      "source": [
+        "# ChatTogether\n",
+        "\n",
+        "\n",
+        "This page will help you get started with Together AI [chat models](../../concepts/chat_models.mdx). For detailed documentation of all ChatTogether features and configurations head to the [API reference](https://python.langchain.com/api_reference/together/chat_models/langchain_together.chat_models.ChatTogether.html).\n",
+        "\n",
+        "[Together AI](https://www.together.ai/) offers an API to query [50+ leading open-source models](https://docs.together.ai/docs/chat-models)\n",
+        "\n",
+        "## Overview\n",
+        "### Integration details\n",
+        "\n",
+        "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/docs/integrations/chat/togetherai) | Package downloads | Package latest |\n",
+        "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+        "| [ChatTogether](https://python.langchain.com/api_reference/together/chat_models/langchain_together.chat_models.ChatTogether.html) | [langchain-together](https://python.langchain.com/api_reference/together/index.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-together?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-together?style=flat-square&label=%20) |\n",
+        "\n",
+        "### Model features\n",
+        "| [Tool calling](../../how_to/tool_calling.ipynb) | [Structured output](../../how_to/structured_output.ipynb) | JSON mode | [Image input](../../how_to/multimodal_inputs.ipynb) | Audio input | Video input | [Token-level streaming](../../how_to/chat_streaming.ipynb) | Native async | [Token usage](../../how_to/chat_token_usage_tracking.ipynb) | [Logprobs](../../how_to/logprobs.ipynb) |\n",
+        "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
+        "| ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ✅ | ✅ |\n",
+        "\n",
+        "## Setup\n",
+        "\n",
+        "To access Together models you'll need to create a/an Together account, get an API key, and install the `langchain-together` integration package.\n",
+        "\n",
+        "### Credentials\n",
+        "\n",
+        "Head to [this page](https://api.together.ai) to sign up to Together and generate an API key. Once you've done this set the TOGETHER_API_KEY environment variable:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 1,
+      "id": "433e8d2b-9519-4b49-b2c4-7ab65b046c94",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import getpass\n",
+        "import os\n",
+        "\n",
+        "if \"TOGETHER_API_KEY\" not in os.environ:\n",
+        "    os.environ[\"TOGETHER_API_KEY\"] = getpass.getpass(\"Enter your Together API key: \")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "72ee0c4b-9764-423a-9dbf-95129e185210",
+      "metadata": {},
+      "source": "To enable automated tracing of your model calls, set your [LangSmith](https://docs.smith.langchain.com/) API key:"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 2,
+      "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 Together integration lives in the `langchain-together` package:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%pip install -qU langchain-together"
+      ]
+    },
+    {
+      "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": 3,
+      "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from langchain_together import ChatTogether\n",
+        "\n",
+        "llm = ChatTogether(\n",
+        "    model=\"meta-llama/Llama-3-70b-chat-hf\",\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": 4,
+      "id": "62e0dbc3",
+      "metadata": {
+        "tags": []
+      },
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "AIMessage(content=\"J'adore la programmation.\", response_metadata={'token_usage': {'completion_tokens': 9, 'prompt_tokens': 35, 'total_tokens': 44}, 'model_name': 'meta-llama/Llama-3-70b-chat-hf', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-eabcbe33-cdd8-45b8-ab0b-f90b6e7dfad8-0', usage_metadata={'input_tokens': 35, 'output_tokens': 9, 'total_tokens': 44})"
+            ]
+          },
+          "execution_count": 4,
+          "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": 5,
+      "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": "18e2bfc0-7e78-4528-a73f-499ac150dca8",
+      "metadata": {},
+      "source": [
+        "## Chaining\n",
+        "\n",
+        "We can [chain](../../how_to/sequence.ipynb) our model with a prompt template like so:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 7,
+      "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "AIMessage(content='Ich liebe das Programmieren.', response_metadata={'token_usage': {'completion_tokens': 7, 'prompt_tokens': 30, 'total_tokens': 37}, 'model_name': 'meta-llama/Llama-3-70b-chat-hf', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-a249aa24-ee31-46ba-9bf9-f4eb135b0a95-0', usage_metadata={'input_tokens': 30, 'output_tokens': 7, 'total_tokens': 37})"
+            ]
+          },
+          "execution_count": 7,
+          "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 ChatTogether features and configurations head to the API reference: https://python.langchain.com/api_reference/together/chat_models/langchain_together.chat_models.ChatTogether.html"
       ]
-     },
-     "execution_count": 7,
-     "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",
-    ")"
-   ]
+  ],
+  "metadata": {
+    "kernelspec": {
+      "display_name": "Python 3 (ipykernel)",
+      "language": "python",
+      "name": "python3"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.11.4"
+    }
   },
-  {
-   "cell_type": "markdown",
-   "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
-   "metadata": {},
-   "source": [
-    "## API reference\n",
-    "\n",
-    "For detailed documentation of all ChatTogether features and configurations head to the API reference: https://python.langchain.com/api_reference/together/chat_models/langchain_together.chat_models.ChatTogether.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": "3.11.4"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
+  "nbformat": 4,
+  "nbformat_minor": 5
 }

docs/docs/integrations/chat/vectara.ipynb

@@ -5,21 +5,38 @@
    "id": "134a0785",
    "metadata": {},
    "source": [
-    "# Vectara Chat\n",
+    "## Overview\n",
     "\n",
     "[Vectara](https://vectara.com/) is the trusted AI Assistant and Agent platform which focuses on enterprise readiness for mission-critical applications.\n",
-    "\n",
     "Vectara serverless RAG-as-a-service provides all the components of RAG behind an easy-to-use API, including:\n",
     "1. A way to extract text from files (PDF, PPT, DOCX, etc)\n",
     "2. ML-based chunking that provides state of the art performance.\n",
     "3. The [Boomerang](https://vectara.com/how-boomerang-takes-retrieval-augmented-generation-to-the-next-level-via-grounded-generation/) embeddings model.\n",
     "4. Its own internal vector database where text chunks and embedding vectors are stored.\n",
-    "5. A query service that automatically encodes the query into embedding, and retrieves the most relevant text segments (including support for [Hybrid Search](https://docs.vectara.com/docs/api-reference/search-apis/lexical-matching) as well as multiple reranking options such as the [multi-lingual relevance reranker](https://www.vectara.com/blog/deep-dive-into-vectara-multilingual-reranker-v1-state-of-the-art-reranker-across-100-languages), [MMR](https://vectara.com/get-diverse-results-and-comprehensive-summaries-with-vectaras-mmr-reranker/), [UDF reranker](https://www.vectara.com/blog/rag-with-user-defined-functions-based-reranking). \n",
+    "5. A query service that automatically encodes the query into embedding, and retrieves the most relevant text segments, including support for [Hybrid Search](https://docs.vectara.com/docs/api-reference/search-apis/lexical-matching) as well as multiple reranking options such as the [multi-lingual relevance reranker](https://www.vectara.com/blog/deep-dive-into-vectara-multilingual-reranker-v1-state-of-the-art-reranker-across-100-languages), [MMR](https://vectara.com/get-diverse-results-and-comprehensive-summaries-with-vectaras-mmr-reranker/), [UDF reranker](https://www.vectara.com/blog/rag-with-user-defined-functions-based-reranking). \n",
     "6. An LLM to for creating a [generative summary](https://docs.vectara.com/docs/learn/grounded-generation/grounded-generation-overview), based on the retrieved documents (context), including citations.\n",
     "\n",
-    "See the [Vectara API documentation](https://docs.vectara.com/docs/) for more information on how to use the API.\n",
+    "For more information:\n",
+    "- [Documentation](https://docs.vectara.com/docs/)\n",
+    "- [API Playground](https://docs.vectara.com/docs/rest-api/)\n",
+    "- [Quickstart](https://docs.vectara.com/docs/quickstart)\n",
     "\n",
-    "This notebook shows how to use Vectara's [Chat](https://docs.vectara.com/docs/api-reference/chat-apis/chat-apis-overview) functionality, which provides automatic storage of conversation history and ensures follow up questions consider that history."
+    "\n",
+    "This notebook shows how to use Vectara's [Chat](https://docs.vectara.com/docs/api-reference/chat-apis/chat-apis-overview) functionality, which provides automatic storage of conversation history and ensures follow up questions consider that history.\n",
+    "\n",
+    "### Setup\n",
+    "\n",
+    "To use the `VectaraVectorStore` you first need to install the partner package.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b4a2f525-4805-4880-8bfa-18fe6f1cd1c7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!uv pip install -U pip && uv pip install -qU langchain-vectara"
    ]
   },
   {
@@ -27,17 +44,19 @@
    "id": "56372c5b",
    "metadata": {},
    "source": [
-    "# Getting Started\n",
+    "## Getting Started\n",
     "\n",
     "To get started, use the following steps:\n",
-    "1. If you don't already have one, [Sign up](https://www.vectara.com/integrations/langchain) for your free Vectara trial. Once you have completed your sign up you will have a Vectara customer ID. You can find your customer ID by clicking on your name, on the top-right of the Vectara console window.\n",
+    "1. If you don't already have one, [Sign up](https://www.vectara.com/integrations/langchain) for your free Vectara trial.\n",
     "2. Within your account you can create one or more corpora. Each corpus represents an area that stores text data upon ingest from input documents. To create a corpus, use the **\"Create Corpus\"** button. You then provide a name to your corpus as well as a description. Optionally you can define filtering attributes and apply some advanced options. If you click on your created corpus, you can see its name and corpus ID right on the top.\n",
     "3. Next you'll need to create API keys to access the corpus. Click on the **\"Access Control\"** tab in the corpus view and then the **\"Create API Key\"** button. Give your key a name, and choose whether you want query-only or query+index for your key. Click \"Create\" and you now have an active API key. Keep this key confidential. \n",
     "\n",
-    "To use LangChain with Vectara, you'll need to have these three values: `customer ID`, `corpus ID` and `api_key`.\n",
-    "You can provide those to LangChain in two ways:\n",
+    "To use LangChain with Vectara, you'll need to have these two values: `corpus_key` and `api_key`.\n",
+    "You can provide `VECTARA_API_KEY` to LangChain in two ways:\n",
     "\n",
-    "1. Include in your environment these three variables: `VECTARA_CUSTOMER_ID`, `VECTARA_CORPUS_ID` and `VECTARA_API_KEY`.\n",
+    "## Instantiation\n",
+    "\n",
+    "1. Include in your environment these two variables: `VECTARA_API_KEY`.\n",
     "\n",
     "   For example, you can set these variables using os.environ and getpass as follows:\n",
     "\n",
@@ -45,8 +64,6 @@
     "import os\n",
     "import getpass\n",
     "\n",
-    "os.environ[\"VECTARA_CUSTOMER_ID\"] = getpass.getpass(\"Vectara Customer ID:\")\n",
-    "os.environ[\"VECTARA_CORPUS_ID\"] = getpass.getpass(\"Vectara Corpus ID:\")\n",
     "os.environ[\"VECTARA_API_KEY\"] = getpass.getpass(\"Vectara API Key:\")\n",
     "```\n",
     "\n",
@@ -54,17 +71,16 @@
     "\n",
     "```python\n",
     "vectara = Vectara(\n",
-    "                vectara_customer_id=vectara_customer_id,\n",
-    "                vectara_corpus_id=vectara_corpus_id,\n",
-    "                vectara_api_key=vectara_api_key\n",
-    "            )\n",
+    "    vectara_api_key=vectara_api_key\n",
+    ")\n",
     "```\n",
+    "\n",
     "In this notebook we assume they are provided in the environment."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "id": "70c4e529",
    "metadata": {
     "tags": []
@@ -73,14 +89,15 @@
    "source": [
     "import os\n",
     "\n",
-    "os.environ[\"VECTARA_API_KEY\"] = \"<YOUR_VECTARA_API_KEY>\"\n",
-    "os.environ[\"VECTARA_CORPUS_ID\"] = \"<YOUR_VECTARA_CORPUS_ID>\"\n",
-    "os.environ[\"VECTARA_CUSTOMER_ID\"] = \"<YOUR_VECTARA_CUSTOMER_ID>\"\n",
+    "os.environ[\"VECTARA_API_KEY\"] = \"<VECTARA_API_KEY>\"\n",
+    "os.environ[\"VECTARA_CORPUS_KEY\"] = \"<VECTARA_CORPUS_KEY>\"\n",
     "\n",
-    "from langchain_community.vectorstores import Vectara\n",
-    "from langchain_community.vectorstores.vectara import (\n",
-    "    RerankConfig,\n",
-    "    SummaryConfig,\n",
+    "from langchain_vectara import Vectara\n",
+    "from langchain_vectara.vectorstores import (\n",
+    "    CorpusConfig,\n",
+    "    GenerationConfig,\n",
+    "    MmrReranker,\n",
+    "    SearchConfig,\n",
     "    VectaraQueryConfig,\n",
     ")"
    ]
@@ -101,7 +118,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "id": "01c46e92",
    "metadata": {
     "tags": []
@@ -110,10 +127,11 @@
    "source": [
     "from langchain_community.document_loaders import TextLoader\n",
     "\n",
-    "loader = TextLoader(\"state_of_the_union.txt\")\n",
+    "loader = TextLoader(\"../document_loaders/example_data/state_of_the_union.txt\")\n",
     "documents = loader.load()\n",
     "\n",
-    "vectara = Vectara.from_documents(documents, embedding=None)"
+    "corpus_key = os.getenv(\"VECTARA_CORPUS_KEY\")\n",
+    "vectara = Vectara.from_documents(documents, embedding=None, corpus_key=corpus_key)"
    ]
   },
   {
@@ -126,18 +144,29 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "id": "1b41a10b-bf68-4689-8f00-9aed7675e2ab",
    "metadata": {
     "tags": []
    },
    "outputs": [],
    "source": [
-    "summary_config = SummaryConfig(is_enabled=True, max_results=7, response_lang=\"eng\")\n",
-    "rerank_config = RerankConfig(reranker=\"mmr\", rerank_k=50, mmr_diversity_bias=0.2)\n",
-    "config = VectaraQueryConfig(\n",
-    "    k=10, lambda_val=0.005, rerank_config=rerank_config, summary_config=summary_config\n",
+    "generation_config = GenerationConfig(\n",
+    "    max_used_search_results=7,\n",
+    "    response_language=\"eng\",\n",
+    "    generation_preset_name=\"vectara-summary-ext-24-05-med-omni\",\n",
+    "    enable_factual_consistency_score=True,\n",
     ")\n",
+    "search_config = SearchConfig(\n",
+    "    corpora=[CorpusConfig(corpus_key=corpus_key, limit=25)],\n",
+    "    reranker=MmrReranker(diversity_bias=0.2),\n",
+    ")\n",
+    "\n",
+    "config = VectaraQueryConfig(\n",
+    "    search=search_config,\n",
+    "    generation=generation_config,\n",
+    ")\n",
+    "\n",
     "\n",
     "bot = vectara.as_chat(config)"
    ]
@@ -147,12 +176,15 @@
    "id": "83f38c18-ac82-45f4-a79e-8b37ce1ae115",
    "metadata": {},
    "source": [
+    "\n",
+    "## Invocation\n",
+    "\n",
     "Here's an example of asking a question with no chat history"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 5,
    "id": "bc672290-8a8b-4828-a90c-f1bbdd6b3920",
    "metadata": {
     "tags": []
@@ -161,10 +193,10 @@
     {
      "data": {
       "text/plain": [
-       "'The President expressed gratitude to Justice Breyer and highlighted the significance of nominating Ketanji Brown Jackson to the Supreme Court, praising her legal expertise and commitment to upholding excellence [1]. The President also reassured the public about the situation with gas prices and the conflict in Ukraine, emphasizing unity with allies and the belief that the world will emerge stronger from these challenges [2][4]. Additionally, the President shared personal experiences related to economic struggles and the importance of passing the American Rescue Plan to support those in need [3]. The focus was also on job creation and economic growth, acknowledging the impact of inflation on families [5]. While addressing cancer as a significant issue, the President discussed plans to enhance cancer research and support for patients and families [7].'"
+       "'The president stated that nominating someone to serve on the United States Supreme Court is one of the most serious constitutional responsibilities. He nominated Circuit Court of Appeals Judge Ketanji Brown Jackson, describing her as one of the nation’s top legal minds who will continue Justice Breyer’s legacy of excellence and noting her experience as a former top litigator in private practice [1].'"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -183,7 +215,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "id": "9c95460b-7116-4155-a9d2-c0fb027ee592",
    "metadata": {
     "tags": []
@@ -192,10 +224,10 @@
     {
      "data": {
       "text/plain": [
-       "\"In his remarks, the President specified that Ketanji Brown Jackson is succeeding Justice Breyer on the United States Supreme Court[1]. The President praised Jackson as a top legal mind who will continue Justice Breyer's legacy of excellence. The nomination of Jackson was highlighted as a significant constitutional responsibility of the President[1]. The President emphasized the importance of this nomination and the qualities that Jackson brings to the role. The focus was on the transition from Justice Breyer to Judge Ketanji Brown Jackson on the Supreme Court[1].\""
+       "'Yes, the president mentioned that Ketanji Brown Jackson succeeded Justice Breyer [1].'"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -217,7 +249,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "id": "936dc62f",
    "metadata": {
     "tags": []
@@ -227,14 +259,14 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Judge Ketanji Brown Jackson is a nominee for the United States Supreme Court, known for her legal expertise and experience as a former litigator. She is praised for her potential to continue the legacy of excellence on the Court[1]. While the search results provide information on various topics like innovation, economic growth, and healthcare initiatives, they do not directly address Judge Ketanji Brown Jackson's specific accomplishments. Therefore, I do not have enough information to answer this question."
+      "The president acknowledged the significant impact of COVID-19 on the nation, expressing understanding of the public's fatigue and frustration. He emphasized the need to view COVID-19 not as a partisan issue but as a serious disease, urging unity among Americans. The president highlighted the progress made, noting that severe cases have decreased significantly, and mentioned new CDC guidelines allowing most Americans to be mask-free. He also pointed out the efforts to vaccinate the nation and provide economic relief, and the ongoing commitment to vaccinate the world [2], [3], [5]."
      ]
     }
    ],
    "source": [
     "output = {}\n",
     "curr_key = None\n",
-    "for chunk in bot.stream(\"what about her accopmlishments?\"):\n",
+    "for chunk in bot.stream(\"what did he said about the covid?\"):\n",
     "    for key in chunk:\n",
     "        if key not in output:\n",
     "            output[key] = chunk[key]\n",
@@ -244,6 +276,83 @@
     "            print(chunk[key], end=\"\", flush=True)\n",
     "        curr_key = key"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cefdf72b1d90085a",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "## Chaining\n",
+    "\n",
+    "For additional capabilities you can use chaining."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "id": "167bc806-395e-46bf-80cc-3c5d43164f42",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "So, the president talked about how the COVID-19 sickness has affected a lot of people in the country. He said that it's important for everyone to work together to fight the sickness, no matter what political party they are in. The president also mentioned that they are working hard to give vaccines to people to help protect them from getting sick. They are also giving money and help to people who need it, like food, housing, and cheaper health insurance. The president also said that they are sending vaccines to many other countries to help people all around the world stay healthy.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_openai.chat_models import ChatOpenAI\n",
+    "\n",
+    "llm = ChatOpenAI(temperature=0)\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            \"You are a helpful assistant that explains the stuff to a five year old.  Vectara is providing the answer.\",\n",
+    "        ),\n",
+    "        (\"human\", \"{vectara_response}\"),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "\n",
+    "def get_vectara_response(question: dict) -> str:\n",
+    "    \"\"\"\n",
+    "    Calls Vectara as_chat and returns the answer string.  This encapsulates\n",
+    "    the Vectara call.\n",
+    "    \"\"\"\n",
+    "    try:\n",
+    "        response = bot.invoke(question[\"question\"])\n",
+    "        return response[\"answer\"]\n",
+    "    except Exception as e:\n",
+    "        return \"I'm sorry, I couldn't get an answer from Vectara.\"\n",
+    "\n",
+    "\n",
+    "# Create the chain\n",
+    "chain = get_vectara_response | prompt | llm | StrOutputParser()\n",
+    "\n",
+    "\n",
+    "# Invoke the chain\n",
+    "result = chain.invoke({\"question\": \"what did he say about the covid?\"})\n",
+    "print(result)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3b8bb761-db4a-436c-8939-41e9f8652083",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "## API reference\n",
+    "\n",
+    "You can look at the [Chat](https://docs.vectara.com/docs/api-reference/chat-apis/chat-apis-overview) documentation for the details."
+   ]
   }
  ],
  "metadata": {
@@ -262,7 +371,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.8"
+   "version": "3.12.0"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/vllm.ipynb

@@ -1,244 +1,242 @@
 {
- "cells": [
-  {
-   "cell_type": "raw",
-   "id": "eb65deaa",
-   "metadata": {},
-   "source": [
-    "---\n",
-    "sidebar_label: vLLM Chat\n",
-    "---"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "8f82e243-f4ee-44e2-b417-099b6401ae3e",
-   "metadata": {},
-   "source": [
-    "# vLLM Chat\n",
-    "\n",
-    "vLLM can be deployed as a server that mimics the OpenAI API protocol. This allows vLLM to be used as a drop-in replacement for applications using OpenAI API. This server can be queried in the same format as OpenAI API.\n",
-    "\n",
-    "## Overview\n",
-    "This will help you getting started with vLLM [chat models](/docs/concepts/chat_models), which leverage the `langchain-openai` package. For detailed documentation of all `ChatOpenAI` features and configurations head to the [API reference](https://python.langchain.com/api_reference/openai/chat_models/langchain_openai.chat_models.base.ChatOpenAI.html).\n",
-    "\n",
-    "### Integration details\n",
-    "\n",
-    "| Class | Package | Local | Serializable | JS support | Package downloads | Package latest |\n",
-    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
-    "| [ChatOpenAI](https://python.langchain.com/api_reference/openai/chat_models/langchain_openai.chat_models.base.ChatOpenAI.html) | [langchain_openai](https://python.langchain.com/api_reference/openai/) | ✅ | 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",
-    "Specific model features-- such as tool calling, support for multi-modal inputs, support for token-level streaming, etc.-- will depend on the hosted model.\n",
-    "\n",
-    "## Setup\n",
-    "\n",
-    "See the vLLM docs [here](https://docs.vllm.ai/en/latest/).\n",
-    "\n",
-    "To access vLLM models through LangChain, you'll need to install the `langchain-openai` integration package.\n",
-    "\n",
-    "### Credentials\n",
-    "\n",
-    "Authentication will depend on specifics of the inference server."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "c3b1707a-cf2c-4367-94e3-436c43402503",
-   "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": "1e40bd5e-cbaa-41ef-aaf9-0858eb207184",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\"\n",
-    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0739b647-609b-46d3-bdd3-e86fe4463288",
-   "metadata": {},
-   "source": [
-    "### Installation\n",
-    "\n",
-    "The LangChain vLLM integration can be accessed via the `langchain-openai` package:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "7afcfbdc-56aa-4529-825a-8acbe7aa5241",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%pip install -qU langchain-openai"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2cf576d6-7b67-4937-bf99-39071e85720c",
-   "metadata": {},
-   "source": [
-    "## Instantiation\n",
-    "\n",
-    "Now we can instantiate our model object and generate chat completions:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "060a2e3d-d42f-4221-bd09-a9a06544dcd3",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain_core.messages import HumanMessage, SystemMessage\n",
-    "from langchain_core.prompts.chat import (\n",
-    "    ChatPromptTemplate,\n",
-    "    HumanMessagePromptTemplate,\n",
-    "    SystemMessagePromptTemplate,\n",
-    ")\n",
-    "from langchain_openai import ChatOpenAI"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "bf24d732-68a9-44fd-b05d-4903ce5620c6",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "inference_server_url = \"http://localhost:8000/v1\"\n",
-    "\n",
-    "llm = ChatOpenAI(\n",
-    "    model=\"mosaicml/mpt-7b\",\n",
-    "    openai_api_key=\"EMPTY\",\n",
-    "    openai_api_base=inference_server_url,\n",
-    "    max_tokens=5,\n",
-    "    temperature=0,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "34b18328-5e8b-4ff2-9b89-6fbb76b5c7f0",
-   "metadata": {},
-   "source": [
-    "## Invocation"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "aea4e363-5688-4b07-82ed-6aa8153c2377",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
+  "cells": [
     {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=' Io amo programmare', additional_kwargs={}, example=False)"
+      "cell_type": "raw",
+      "id": "eb65deaa",
+      "metadata": {},
+      "source": [
+        "---\n",
+        "sidebar_label: vLLM Chat\n",
+        "---"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "8f82e243-f4ee-44e2-b417-099b6401ae3e",
+      "metadata": {},
+      "source": [
+        "# vLLM Chat\n",
+        "\n",
+        "vLLM can be deployed as a server that mimics the OpenAI API protocol. This allows vLLM to be used as a drop-in replacement for applications using OpenAI API. This server can be queried in the same format as OpenAI API.\n",
+        "\n",
+        "## Overview\n",
+        "This will help you getting started with vLLM [chat models](/docs/concepts/chat_models), which leverage the `langchain-openai` package. For detailed documentation of all `ChatOpenAI` features and configurations head to the [API reference](https://python.langchain.com/api_reference/openai/chat_models/langchain_openai.chat_models.base.ChatOpenAI.html).\n",
+        "\n",
+        "### Integration details\n",
+        "\n",
+        "| Class | Package | Local | Serializable | JS support | Package downloads | Package latest |\n",
+        "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+        "| [ChatOpenAI](https://python.langchain.com/api_reference/openai/chat_models/langchain_openai.chat_models.base.ChatOpenAI.html) | [langchain_openai](https://python.langchain.com/api_reference/openai/) | ✅ | 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",
+        "Specific model features-- such as tool calling, support for multi-modal inputs, support for token-level streaming, etc.-- will depend on the hosted model.\n",
+        "\n",
+        "## Setup\n",
+        "\n",
+        "See the vLLM docs [here](https://docs.vllm.ai/en/latest/).\n",
+        "\n",
+        "To access vLLM models through LangChain, you'll need to install the `langchain-openai` integration package.\n",
+        "\n",
+        "### Credentials\n",
+        "\n",
+        "Authentication will depend on specifics of the inference server."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "c3b1707a-cf2c-4367-94e3-436c43402503",
+      "metadata": {},
+      "source": "To enable automated tracing of your model calls, set your [LangSmith](https://docs.smith.langchain.com/) API key:"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "1e40bd5e-cbaa-41ef-aaf9-0858eb207184",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# os.environ[\"LANGSMITH_TRACING\"] = \"true\"\n",
+        "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "0739b647-609b-46d3-bdd3-e86fe4463288",
+      "metadata": {},
+      "source": [
+        "### Installation\n",
+        "\n",
+        "The LangChain vLLM integration can be accessed via the `langchain-openai` package:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "7afcfbdc-56aa-4529-825a-8acbe7aa5241",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%pip install -qU langchain-openai"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "2cf576d6-7b67-4937-bf99-39071e85720c",
+      "metadata": {},
+      "source": [
+        "## Instantiation\n",
+        "\n",
+        "Now we can instantiate our model object and generate chat completions:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 1,
+      "id": "060a2e3d-d42f-4221-bd09-a9a06544dcd3",
+      "metadata": {
+        "tags": []
+      },
+      "outputs": [],
+      "source": [
+        "from langchain_core.messages import HumanMessage, SystemMessage\n",
+        "from langchain_core.prompts.chat import (\n",
+        "    ChatPromptTemplate,\n",
+        "    HumanMessagePromptTemplate,\n",
+        "    SystemMessagePromptTemplate,\n",
+        ")\n",
+        "from langchain_openai import ChatOpenAI"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 14,
+      "id": "bf24d732-68a9-44fd-b05d-4903ce5620c6",
+      "metadata": {
+        "tags": []
+      },
+      "outputs": [],
+      "source": [
+        "inference_server_url = \"http://localhost:8000/v1\"\n",
+        "\n",
+        "llm = ChatOpenAI(\n",
+        "    model=\"mosaicml/mpt-7b\",\n",
+        "    openai_api_key=\"EMPTY\",\n",
+        "    openai_api_base=inference_server_url,\n",
+        "    max_tokens=5,\n",
+        "    temperature=0,\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "34b18328-5e8b-4ff2-9b89-6fbb76b5c7f0",
+      "metadata": {},
+      "source": [
+        "## Invocation"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 15,
+      "id": "aea4e363-5688-4b07-82ed-6aa8153c2377",
+      "metadata": {
+        "tags": []
+      },
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "AIMessage(content=' Io amo programmare', additional_kwargs={}, example=False)"
+            ]
+          },
+          "execution_count": 15,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "messages = [\n",
+        "    SystemMessage(\n",
+        "        content=\"You are a helpful assistant that translates English to Italian.\"\n",
+        "    ),\n",
+        "    HumanMessage(\n",
+        "        content=\"Translate the following sentence from English to Italian: I love programming.\"\n",
+        "    ),\n",
+        "]\n",
+        "llm.invoke(messages)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "a580a1e4-11a3-4277-bfba-bfb414ac7201",
+      "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,
+      "id": "dd0f4043-48bd-4245-8bdb-e7669666a277",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from langchain_core.prompts import ChatPromptTemplate\n",
+        "\n",
+        "prompt = ChatPromptTemplate(\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": "265f5d51-0a76-4808-8d13-ef598ee6e366",
+      "metadata": {},
+      "source": [
+        "## API reference\n",
+        "\n",
+        "For detailed documentation of all features and configurations exposed via `langchain-openai`, head to the API reference: https://python.langchain.com/api_reference/openai/chat_models/langchain_openai.chat_models.base.ChatOpenAI.html\n",
+        "\n",
+        "Refer to the vLLM [documentation](https://docs.vllm.ai/en/latest/) as well."
       ]
-     },
-     "execution_count": 15,
-     "metadata": {},
-     "output_type": "execute_result"
     }
-   ],
-   "source": [
-    "messages = [\n",
-    "    SystemMessage(\n",
-    "        content=\"You are a helpful assistant that translates English to Italian.\"\n",
-    "    ),\n",
-    "    HumanMessage(\n",
-    "        content=\"Translate the following sentence from English to Italian: I love programming.\"\n",
-    "    ),\n",
-    "]\n",
-    "llm.invoke(messages)"
-   ]
+  ],
+  "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"
+    }
   },
-  {
-   "cell_type": "markdown",
-   "id": "a580a1e4-11a3-4277-bfba-bfb414ac7201",
-   "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,
-   "id": "dd0f4043-48bd-4245-8bdb-e7669666a277",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "\n",
-    "prompt = ChatPromptTemplate(\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": "265f5d51-0a76-4808-8d13-ef598ee6e366",
-   "metadata": {},
-   "source": [
-    "## API reference\n",
-    "\n",
-    "For detailed documentation of all features and configurations exposed via `langchain-openai`, head to the API reference: https://python.langchain.com/api_reference/openai/chat_models/langchain_openai.chat_models.base.ChatOpenAI.html\n",
-    "\n",
-    "Refer to the vLLM [documentation](https://docs.vllm.ai/en/latest/) as well."
-   ]
-  }
- ],
- "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
+  "nbformat": 4,
+  "nbformat_minor": 5
 }

docs/docs/integrations/chat/xai.ipynb

@@ -1,332 +1,330 @@
 {
- "cells": [
-  {
-   "cell_type": "raw",
-   "id": "afaf8039",
-   "metadata": {},
-   "source": [
-    "---\n",
-    "sidebar_label: xAI\n",
-    "---"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "e49f1e0d",
-   "metadata": {},
-   "source": [
-    "# ChatXAI\n",
-    "\n",
-    "\n",
-    "This page will help you get started with xAI [chat models](../../concepts/chat_models.mdx). For detailed documentation of all `ChatXAI` features and configurations head to the [API reference](https://python.langchain.com/api_reference/xai/chat_models/langchain_xai.chat_models.ChatXAI.html).\n",
-    "\n",
-    "[xAI](https://console.x.ai/) offers an API to interact with Grok models.\n",
-    "\n",
-    "## Overview\n",
-    "### Integration details\n",
-    "\n",
-    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/docs/integrations/chat/xai) | Package downloads | Package latest |\n",
-    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
-    "| [ChatXAI](https://python.langchain.com/api_reference/xai/chat_models/langchain_xai.chat_models.ChatXAI.html) | [langchain-xai](https://python.langchain.com/api_reference/xai/index.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-xai?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-xai?style=flat-square&label=%20) |\n",
-    "\n",
-    "### Model features\n",
-    "| [Tool calling](../../how_to/tool_calling.ipynb) | [Structured output](../../how_to/structured_output.ipynb) | JSON mode | [Image input](../../how_to/multimodal_inputs.ipynb) | Audio input | Video input | [Token-level streaming](../../how_to/chat_streaming.ipynb) | Native async | [Token usage](../../how_to/chat_token_usage_tracking.ipynb) | [Logprobs](../../how_to/logprobs.ipynb) |\n",
-    "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
-    "| ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ | ✅ | ✅ | \n",
-    "\n",
-    "## Setup\n",
-    "\n",
-    "To access xAI models you'll need to create an xAI account, get an API key, and install the `langchain-xai` integration package.\n",
-    "\n",
-    "### Credentials\n",
-    "\n",
-    "Head to [this page](https://console.x.ai/) to sign up for xAI and generate an API key. Once you've done this set the `XAI_API_KEY` environment variable:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "433e8d2b-9519-4b49-b2c4-7ab65b046c94",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "if \"XAI_API_KEY\" not in os.environ:\n",
-    "    os.environ[\"XAI_API_KEY\"] = getpass.getpass(\"Enter your xAI API key: \")"
-   ]
-  },
-  {
-   "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": 2,
-   "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 xAI integration lives in the `langchain-xai` package:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%pip install -qU langchain-xai"
-   ]
-  },
-  {
-   "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_xai import ChatXAI\n",
-    "\n",
-    "llm = ChatXAI(\n",
-    "    model=\"grok-beta\",\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": 5,
-   "id": "62e0dbc3",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
+  "cells": [
     {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\"J'adore programmer.\", additional_kwargs={'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 6, 'prompt_tokens': 30, 'total_tokens': 36, 'completion_tokens_details': None, 'prompt_tokens_details': None}, 'model_name': 'grok-beta', 'system_fingerprint': 'fp_14b89b2dfc', 'finish_reason': 'stop', 'logprobs': None}, id='run-adffb7a3-e48a-4f52-b694-340d85abe5c3-0', usage_metadata={'input_tokens': 30, 'output_tokens': 6, 'total_tokens': 36, 'input_token_details': {}, 'output_token_details': {}})"
+      "cell_type": "raw",
+      "id": "afaf8039",
+      "metadata": {},
+      "source": [
+        "---\n",
+        "sidebar_label: xAI\n",
+        "---"
       ]
-     },
-     "execution_count": 5,
-     "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": 6,
-   "id": "d86145b3-bfef-46e8-b227-4dda5c9c2705",
-   "metadata": {},
-   "outputs": [
+    },
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "J'adore programmer.\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(ai_msg.content)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "18e2bfc0-7e78-4528-a73f-499ac150dca8",
-   "metadata": {},
-   "source": [
-    "## Chaining\n",
-    "\n",
-    "We can [chain](../../how_to/sequence.ipynb) our model with a prompt template like so:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='Ich liebe das Programmieren.', additional_kwargs={'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 7, 'prompt_tokens': 25, 'total_tokens': 32, 'completion_tokens_details': None, 'prompt_tokens_details': None}, 'model_name': 'grok-beta', 'system_fingerprint': 'fp_14b89b2dfc', 'finish_reason': 'stop', 'logprobs': None}, id='run-569fc8dc-101b-4e6d-864e-d4fa80df2b63-0', usage_metadata={'input_tokens': 25, 'output_tokens': 7, 'total_tokens': 32, 'input_token_details': {}, 'output_token_details': {}})"
+      "cell_type": "markdown",
+      "id": "e49f1e0d",
+      "metadata": {},
+      "source": [
+        "# ChatXAI\n",
+        "\n",
+        "\n",
+        "This page will help you get started with xAI [chat models](../../concepts/chat_models.mdx). For detailed documentation of all `ChatXAI` features and configurations head to the [API reference](https://python.langchain.com/api_reference/xai/chat_models/langchain_xai.chat_models.ChatXAI.html).\n",
+        "\n",
+        "[xAI](https://console.x.ai/) offers an API to interact with Grok models.\n",
+        "\n",
+        "## Overview\n",
+        "### Integration details\n",
+        "\n",
+        "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/docs/integrations/chat/xai) | Package downloads | Package latest |\n",
+        "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+        "| [ChatXAI](https://python.langchain.com/api_reference/xai/chat_models/langchain_xai.chat_models.ChatXAI.html) | [langchain-xai](https://python.langchain.com/api_reference/xai/index.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-xai?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-xai?style=flat-square&label=%20) |\n",
+        "\n",
+        "### Model features\n",
+        "| [Tool calling](../../how_to/tool_calling.ipynb) | [Structured output](../../how_to/structured_output.ipynb) | JSON mode | [Image input](../../how_to/multimodal_inputs.ipynb) | Audio input | Video input | [Token-level streaming](../../how_to/chat_streaming.ipynb) | Native async | [Token usage](../../how_to/chat_token_usage_tracking.ipynb) | [Logprobs](../../how_to/logprobs.ipynb) |\n",
+        "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
+        "| ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ | ✅ | ✅ |\n",
+        "\n",
+        "## Setup\n",
+        "\n",
+        "To access xAI models you'll need to create an xAI account, get an API key, and install the `langchain-xai` integration package.\n",
+        "\n",
+        "### Credentials\n",
+        "\n",
+        "Head to [this page](https://console.x.ai/) to sign up for xAI and generate an API key. Once you've done this set the `XAI_API_KEY` environment variable:"
       ]
-     },
-     "execution_count": 7,
-     "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": "e074bce1-0994-4b83-b393-ae7aa7e21750",
-   "metadata": {},
-   "source": [
-    "## Tool calling\n",
-    "\n",
-    "ChatXAI has a [tool calling](https://docs.x.ai/docs#capabilities) (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",
-    "### ChatXAI.bind_tools()\n",
-    "\n",
-    "With `ChatXAI.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."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "c6bfe929-ec02-46bd-9d54-76350edddabc",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from pydantic 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": 9,
-   "id": "5265c892-d8c2-48af-aef5-adbee1647ba6",
-   "metadata": {},
-   "outputs": [
+    },
     {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='I am retrieving the current weather for San Francisco.', additional_kwargs={'tool_calls': [{'id': '0', 'function': {'arguments': '{\"location\":\"San Francisco, CA\"}', 'name': 'GetWeather'}, 'type': 'function'}], 'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 11, 'prompt_tokens': 151, 'total_tokens': 162, 'completion_tokens_details': None, 'prompt_tokens_details': None}, 'model_name': 'grok-beta', 'system_fingerprint': 'fp_14b89b2dfc', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-73707da7-afec-4a52-bee1-a176b0ab8585-0', tool_calls=[{'name': 'GetWeather', 'args': {'location': 'San Francisco, CA'}, 'id': '0', 'type': 'tool_call'}], usage_metadata={'input_tokens': 151, 'output_tokens': 11, 'total_tokens': 162, 'input_token_details': {}, 'output_token_details': {}})"
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "433e8d2b-9519-4b49-b2c4-7ab65b046c94",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import getpass\n",
+        "import os\n",
+        "\n",
+        "if \"XAI_API_KEY\" not in os.environ:\n",
+        "    os.environ[\"XAI_API_KEY\"] = getpass.getpass(\"Enter your xAI API key: \")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "72ee0c4b-9764-423a-9dbf-95129e185210",
+      "metadata": {},
+      "source": "To enable automated tracing of your model calls, set your [LangSmith](https://docs.smith.langchain.com/) API key:"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 2,
+      "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 xAI integration lives in the `langchain-xai` package:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 3,
+      "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%pip install -qU langchain-xai"
+      ]
+    },
+    {
+      "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_xai import ChatXAI\n",
+        "\n",
+        "llm = ChatXAI(\n",
+        "    model=\"grok-beta\",\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": 5,
+      "id": "62e0dbc3",
+      "metadata": {
+        "tags": []
+      },
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "AIMessage(content=\"J'adore programmer.\", additional_kwargs={'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 6, 'prompt_tokens': 30, 'total_tokens': 36, 'completion_tokens_details': None, 'prompt_tokens_details': None}, 'model_name': 'grok-beta', 'system_fingerprint': 'fp_14b89b2dfc', 'finish_reason': 'stop', 'logprobs': None}, id='run-adffb7a3-e48a-4f52-b694-340d85abe5c3-0', usage_metadata={'input_tokens': 30, 'output_tokens': 6, 'total_tokens': 36, 'input_token_details': {}, 'output_token_details': {}})"
+            ]
+          },
+          "execution_count": 5,
+          "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": 6,
+      "id": "d86145b3-bfef-46e8-b227-4dda5c9c2705",
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "J'adore programmer.\n"
+          ]
+        }
+      ],
+      "source": [
+        "print(ai_msg.content)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "18e2bfc0-7e78-4528-a73f-499ac150dca8",
+      "metadata": {},
+      "source": [
+        "## Chaining\n",
+        "\n",
+        "We can [chain](../../how_to/sequence.ipynb) our model with a prompt template like so:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 7,
+      "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "AIMessage(content='Ich liebe das Programmieren.', additional_kwargs={'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 7, 'prompt_tokens': 25, 'total_tokens': 32, 'completion_tokens_details': None, 'prompt_tokens_details': None}, 'model_name': 'grok-beta', 'system_fingerprint': 'fp_14b89b2dfc', 'finish_reason': 'stop', 'logprobs': None}, id='run-569fc8dc-101b-4e6d-864e-d4fa80df2b63-0', usage_metadata={'input_tokens': 25, 'output_tokens': 7, 'total_tokens': 32, 'input_token_details': {}, 'output_token_details': {}})"
+            ]
+          },
+          "execution_count": 7,
+          "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": "e074bce1-0994-4b83-b393-ae7aa7e21750",
+      "metadata": {},
+      "source": [
+        "## Tool calling\n",
+        "\n",
+        "ChatXAI has a [tool calling](https://docs.x.ai/docs#capabilities) (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",
+        "### ChatXAI.bind_tools()\n",
+        "\n",
+        "With `ChatXAI.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."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 8,
+      "id": "c6bfe929-ec02-46bd-9d54-76350edddabc",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from pydantic 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": 9,
+      "id": "5265c892-d8c2-48af-aef5-adbee1647ba6",
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "AIMessage(content='I am retrieving the current weather for San Francisco.', additional_kwargs={'tool_calls': [{'id': '0', 'function': {'arguments': '{\"location\":\"San Francisco, CA\"}', 'name': 'GetWeather'}, 'type': 'function'}], 'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 11, 'prompt_tokens': 151, 'total_tokens': 162, 'completion_tokens_details': None, 'prompt_tokens_details': None}, 'model_name': 'grok-beta', 'system_fingerprint': 'fp_14b89b2dfc', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-73707da7-afec-4a52-bee1-a176b0ab8585-0', tool_calls=[{'name': 'GetWeather', 'args': {'location': 'San Francisco, CA'}, 'id': '0', 'type': 'tool_call'}], usage_metadata={'input_tokens': 151, 'output_tokens': 11, 'total_tokens': 162, 'input_token_details': {}, 'output_token_details': {}})"
+            ]
+          },
+          "execution_count": 9,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "ai_msg = llm_with_tools.invoke(\n",
+        "    \"what is the weather like in San Francisco\",\n",
+        ")\n",
+        "ai_msg"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
+      "metadata": {},
+      "source": [
+        "## API reference\n",
+        "\n",
+        "For detailed documentation of all `ChatXAI` features and configurations head to the API reference: https://python.langchain.com/api_reference/xai/chat_models/langchain_xai.chat_models.ChatXAI.html"
       ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
     }
-   ],
-   "source": [
-    "ai_msg = llm_with_tools.invoke(\n",
-    "    \"what is the weather like in San Francisco\",\n",
-    ")\n",
-    "ai_msg"
-   ]
+  ],
+  "metadata": {
+    "kernelspec": {
+      "display_name": "Python 3 (ipykernel)",
+      "language": "python",
+      "name": "python3"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.11.9"
+    }
   },
-  {
-   "cell_type": "markdown",
-   "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
-   "metadata": {},
-   "source": [
-    "## API reference\n",
-    "\n",
-    "For detailed documentation of all `ChatXAI` features and configurations head to the API reference: https://python.langchain.com/api_reference/xai/chat_models/langchain_xai.chat_models.ChatXAI.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": "3.11.9"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
+  "nbformat": 4,
+  "nbformat_minor": 5
 }

docs/docs/integrations/chat/yi.ipynb

@@ -1,229 +1,227 @@
 {
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# ChatYI\n",
-    "\n",
-    "This will help you getting started with Yi [chat models](/docs/concepts/chat_models). For detailed documentation of all ChatYi features and configurations head to the [API reference](https://python.langchain.com/api_reference/lanchain_community/chat_models/lanchain_community.chat_models.yi.ChatYi.html).\n",
-    "\n",
-    "[01.AI](https://www.lingyiwanwu.com/en), founded by Dr. Kai-Fu Lee, is a global company at the forefront of AI 2.0. They offer cutting-edge large language models, including the Yi series, which range from 6B to hundreds of billions of parameters. 01.AI also provides multimodal models, an open API platform, and open-source options like Yi-34B/9B/6B and Yi-VL.\n",
-    "\n",
-    "## Overview\n",
-    "### Integration details\n",
-    "\n",
-    "\n",
-    "| Class | Package | Local | Serializable | JS support | Package downloads | Package latest |\n",
-    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
-    "| [ChatYi](https://python.langchain.com/api_reference/lanchain_community/chat_models/lanchain_community.chat_models.yi.ChatYi.html) | [langchain_community](https://python.langchain.com/api_reference/community/index.html) | ✅ | ❌ | ❌ | ![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",
-    "## Setup\n",
-    "\n",
-    "To access ChatYi models you'll need to create a/an 01.AI account, get an API key, and install the `langchain_community` integration package.\n",
-    "\n",
-    "### Credentials\n",
-    "\n",
-    "Head to [01.AI](https://platform.01.ai) to sign up to 01.AI and generate an API key. Once you've done this set the `YI_API_KEY` environment variable:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "if \"YI_API_KEY\" not in os.environ:\n",
-    "    os.environ[\"YI_API_KEY\"] = getpass.getpass(\"Enter your Yi API key: \")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "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,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
-    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Installation\n",
-    "\n",
-    "The LangChain __ModuleName__ integration lives in the `langchain_community` package:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%pip install -qU langchain_community"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "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": 2,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_community.chat_models.yi import ChatYi\n",
-    "\n",
-    "llm = ChatYi(\n",
-    "    model=\"yi-large\",\n",
-    "    temperature=0,\n",
-    "    timeout=60,\n",
-    "    yi_api_base=\"https://api.01.ai/v1/chat/completions\",\n",
-    "    # other params...\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Invocation\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [
+  "cells": [
     {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\"Large Language Models (LLMs) have the potential to significantly impact healthcare by enhancing various aspects of patient care, research, and administrative processes. Here are some potential applications:\\n\\n1. **Clinical Documentation and Reporting**: LLMs can assist in generating patient reports and documentation by understanding and summarizing clinical notes, making the process more efficient and reducing the administrative burden on healthcare professionals.\\n\\n2. **Medical Coding and Billing**: These models can help in automating the coding process for medical billing by accurately translating clinical notes into standardized codes, reducing errors and improving billing efficiency.\\n\\n3. **Clinical Decision Support**: LLMs can analyze patient data and medical literature to provide evidence-based recommendations to healthcare providers, aiding in diagnosis and treatment planning.\\n\\n4. **Patient Education and Communication**: By simplifying medical jargon, LLMs can help in educating patients about their conditions, treatment options, and preventive care, improving patient engagement and health literacy.\\n\\n5. **Natural Language Processing (NLP) for EHRs**: LLMs can enhance NLP capabilities in Electronic Health Records (EHRs) systems, enabling better extraction of information from unstructured data, such as clinical notes, to support data-driven decision-making.\\n\\n6. **Drug Discovery and Development**: LLMs can analyze biomedical literature and clinical trial data to identify new drug candidates, predict drug interactions, and support the development of personalized medicine.\\n\\n7. **Telemedicine and Virtual Health Assistants**: Integrated into telemedicine platforms, LLMs can provide preliminary assessments and triage, offering patients basic health advice and determining the urgency of their needs, thus optimizing the utilization of healthcare resources.\\n\\n8. **Research and Literature Review**: LLMs can expedite the process of reviewing medical literature by quickly identifying relevant studies and summarizing findings, accelerating research and evidence-based practice.\\n\\n9. **Personalized Medicine**: By analyzing a patient's genetic information and medical history, LLMs can help in tailoring treatment plans and medication dosages, contributing to the advancement of personalized medicine.\\n\\n10. **Quality Improvement and Risk Assessment**: LLMs can analyze healthcare data to identify patterns that may indicate areas for quality improvement or potential risks, such as hospital-acquired infections or adverse drug events.\\n\\n11. **Mental Health Support**: LLMs can provide mental health support by offering coping strategies, mindfulness exercises, and preliminary assessments, serving as a complement to professional mental health services.\\n\\n12. **Continuing Medical Education (CME)**: LLMs can personalize CME by recommending educational content based on a healthcare provider's practice area, patient demographics, and emerging medical literature, ensuring that professionals stay updated with the latest advancements.\\n\\nWhile the applications of LLMs in healthcare are promising, it's crucial to address challenges such as data privacy, model bias, and the need for regulatory approval to ensure that these technologies are implemented safely and ethically.\", response_metadata={'token_usage': {'completion_tokens': 656, 'prompt_tokens': 40, 'total_tokens': 696}, 'model': 'yi-large'}, id='run-870850bd-e4bf-4265-8730-1736409c0acf-0')"
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# ChatYI\n",
+        "\n",
+        "This will help you getting started with Yi [chat models](/docs/concepts/chat_models). For detailed documentation of all ChatYi features and configurations head to the [API reference](https://python.langchain.com/api_reference/lanchain_community/chat_models/lanchain_community.chat_models.yi.ChatYi.html).\n",
+        "\n",
+        "[01.AI](https://www.lingyiwanwu.com/en), founded by Dr. Kai-Fu Lee, is a global company at the forefront of AI 2.0. They offer cutting-edge large language models, including the Yi series, which range from 6B to hundreds of billions of parameters. 01.AI also provides multimodal models, an open API platform, and open-source options like Yi-34B/9B/6B and Yi-VL.\n",
+        "\n",
+        "## Overview\n",
+        "### Integration details\n",
+        "\n",
+        "\n",
+        "| Class | Package | Local | Serializable | JS support | Package downloads | Package latest |\n",
+        "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+        "| [ChatYi](https://python.langchain.com/api_reference/lanchain_community/chat_models/lanchain_community.chat_models.yi.ChatYi.html) | [langchain_community](https://python.langchain.com/api_reference/community/index.html) | ✅ | ❌ | ❌ | ![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",
+        "## Setup\n",
+        "\n",
+        "To access ChatYi models you'll need to create a/an 01.AI account, get an API key, and install the `langchain_community` integration package.\n",
+        "\n",
+        "### Credentials\n",
+        "\n",
+        "Head to [01.AI](https://platform.01.ai) to sign up to 01.AI and generate an API key. Once you've done this set the `YI_API_KEY` environment variable:"
       ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_core.messages import HumanMessage, SystemMessage\n",
-    "\n",
-    "messages = [\n",
-    "    SystemMessage(content=\"You are an AI assistant specializing in technology trends.\"),\n",
-    "    HumanMessage(\n",
-    "        content=\"What are the potential applications of large language models in healthcare?\"\n",
-    "    ),\n",
-    "]\n",
-    "\n",
-    "ai_msg = llm.invoke(messages)\n",
-    "ai_msg"
-   ]
-  },
-  {
-   "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": 4,
-   "metadata": {},
-   "outputs": [
+    },
     {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='Ich liebe das Programmieren.', response_metadata={'token_usage': {'completion_tokens': 8, 'prompt_tokens': 33, 'total_tokens': 41}, 'model': 'yi-large'}, id='run-daa3bc58-8289-4d72-a24e-80622fa90d6d-0')"
+      "cell_type": "code",
+      "execution_count": 1,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import getpass\n",
+        "import os\n",
+        "\n",
+        "if \"YI_API_KEY\" not in os.environ:\n",
+        "    os.environ[\"YI_API_KEY\"] = getpass.getpass(\"Enter your Yi API key: \")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": "To enable automated tracing of your model calls, set your [LangSmith](https://docs.smith.langchain.com/) API key:"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
+        "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Installation\n",
+        "\n",
+        "The LangChain __ModuleName__ integration lives in the `langchain_community` package:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%pip install -qU langchain_community"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "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": 2,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from langchain_community.chat_models.yi import ChatYi\n",
+        "\n",
+        "llm = ChatYi(\n",
+        "    model=\"yi-large\",\n",
+        "    temperature=0,\n",
+        "    timeout=60,\n",
+        "    yi_api_base=\"https://api.01.ai/v1/chat/completions\",\n",
+        "    # other params...\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Invocation\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 3,
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "AIMessage(content=\"Large Language Models (LLMs) have the potential to significantly impact healthcare by enhancing various aspects of patient care, research, and administrative processes. Here are some potential applications:\\n\\n1. **Clinical Documentation and Reporting**: LLMs can assist in generating patient reports and documentation by understanding and summarizing clinical notes, making the process more efficient and reducing the administrative burden on healthcare professionals.\\n\\n2. **Medical Coding and Billing**: These models can help in automating the coding process for medical billing by accurately translating clinical notes into standardized codes, reducing errors and improving billing efficiency.\\n\\n3. **Clinical Decision Support**: LLMs can analyze patient data and medical literature to provide evidence-based recommendations to healthcare providers, aiding in diagnosis and treatment planning.\\n\\n4. **Patient Education and Communication**: By simplifying medical jargon, LLMs can help in educating patients about their conditions, treatment options, and preventive care, improving patient engagement and health literacy.\\n\\n5. **Natural Language Processing (NLP) for EHRs**: LLMs can enhance NLP capabilities in Electronic Health Records (EHRs) systems, enabling better extraction of information from unstructured data, such as clinical notes, to support data-driven decision-making.\\n\\n6. **Drug Discovery and Development**: LLMs can analyze biomedical literature and clinical trial data to identify new drug candidates, predict drug interactions, and support the development of personalized medicine.\\n\\n7. **Telemedicine and Virtual Health Assistants**: Integrated into telemedicine platforms, LLMs can provide preliminary assessments and triage, offering patients basic health advice and determining the urgency of their needs, thus optimizing the utilization of healthcare resources.\\n\\n8. **Research and Literature Review**: LLMs can expedite the process of reviewing medical literature by quickly identifying relevant studies and summarizing findings, accelerating research and evidence-based practice.\\n\\n9. **Personalized Medicine**: By analyzing a patient's genetic information and medical history, LLMs can help in tailoring treatment plans and medication dosages, contributing to the advancement of personalized medicine.\\n\\n10. **Quality Improvement and Risk Assessment**: LLMs can analyze healthcare data to identify patterns that may indicate areas for quality improvement or potential risks, such as hospital-acquired infections or adverse drug events.\\n\\n11. **Mental Health Support**: LLMs can provide mental health support by offering coping strategies, mindfulness exercises, and preliminary assessments, serving as a complement to professional mental health services.\\n\\n12. **Continuing Medical Education (CME)**: LLMs can personalize CME by recommending educational content based on a healthcare provider's practice area, patient demographics, and emerging medical literature, ensuring that professionals stay updated with the latest advancements.\\n\\nWhile the applications of LLMs in healthcare are promising, it's crucial to address challenges such as data privacy, model bias, and the need for regulatory approval to ensure that these technologies are implemented safely and ethically.\", response_metadata={'token_usage': {'completion_tokens': 656, 'prompt_tokens': 40, 'total_tokens': 696}, 'model': 'yi-large'}, id='run-870850bd-e4bf-4265-8730-1736409c0acf-0')"
+            ]
+          },
+          "execution_count": 3,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "from langchain_core.messages import HumanMessage, SystemMessage\n",
+        "\n",
+        "messages = [\n",
+        "    SystemMessage(content=\"You are an AI assistant specializing in technology trends.\"),\n",
+        "    HumanMessage(\n",
+        "        content=\"What are the potential applications of large language models in healthcare?\"\n",
+        "    ),\n",
+        "]\n",
+        "\n",
+        "ai_msg = llm.invoke(messages)\n",
+        "ai_msg"
+      ]
+    },
+    {
+      "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": 4,
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "AIMessage(content='Ich liebe das Programmieren.', response_metadata={'token_usage': {'completion_tokens': 8, 'prompt_tokens': 33, 'total_tokens': 41}, 'model': 'yi-large'}, id='run-daa3bc58-8289-4d72-a24e-80622fa90d6d-0')"
+            ]
+          },
+          "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",
+      "metadata": {},
+      "source": [
+        "## API reference\n",
+        "\n",
+        "For detailed documentation of all ChatYi features and configurations head to the API reference: https://python.langchain.com/api_reference/community/chat_models/langchain_community.chat_models.yi.ChatYi.html"
       ]
-     },
-     "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",
-    ")"
-   ]
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "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"
+    }
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## API reference\n",
-    "\n",
-    "For detailed documentation of all ChatYi features and configurations head to the API reference: https://python.langchain.com/api_reference/community/chat_models/langchain_community.chat_models.yi.ChatYi.html"
-   ]
-  }
- ],
- "metadata": {
-  "colab": {
-   "provenance": []
-  },
-  "kernelspec": {
-   "display_name": "Python 3",
-   "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": 0
+  "nbformat": 4,
+  "nbformat_minor": 0
 }

docs/docs/integrations/document_loaders/box.ipynb

@@ -1,466 +1,464 @@
 {
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "---\n",
-    "sidebar_label: Box\n",
-    "---"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# BoxLoader and BoxBlobLoader\n",
-    "\n",
-    "\n",
-    "The `langchain-box` package provides two methods to index your files from Box: `BoxLoader` and `BoxBlobLoader`. `BoxLoader` allows you to ingest text representations of files that have a text representation in Box. The `BoxBlobLoader` allows you download the blob for any document or image file for processing with the blob parser of your choice.\n",
-    "\n",
-    "This notebook details getting started with both of these. For detailed documentation of all BoxLoader features and configurations head to the API Reference pages for [BoxLoader](https://python.langchain.com/api_reference/box/document_loaders/langchain_box.document_loaders.box.BoxLoader.html) and [BoxBlobLoader](https://python.langchain.com/api_reference/box/document_loaders/langchain_box.blob_loaders.box.BoxBlobLoader.html).\n",
-    "\n",
-    "## Overview\n",
-    "\n",
-    "The `BoxLoader` class helps you get your unstructured content from Box in Langchain's `Document` format. You can do this with either a `List[str]` containing Box file IDs, or with a `str` containing a Box folder ID. \n",
-    "\n",
-    "The `BoxBlobLoader` class helps you get your unstructured content from Box in Langchain's `Blob` format. You can do this with a `List[str]` containing Box file IDs, a `str` containing a Box folder ID, a search query, or a `BoxMetadataQuery`. \n",
-    "\n",
-    "If getting files from a folder with folder ID, you can also set a `Bool` to tell the loader to get all sub-folders in that folder, as well. \n",
-    "\n",
-    ":::info\n",
-    "A Box instance can contain Petabytes of files, and folders can contain millions of files. Be intentional when choosing what folders you choose to index. And we recommend never getting all files from folder 0 recursively. Folder ID 0 is your root folder.\n",
-    ":::\n",
-    "\n",
-    "The `BoxLoader` will skip files without a text representation, while the `BoxBlobLoader` will return blobs for all document and image files.\n",
-    "\n",
-    "### Integration details\n",
-    "\n",
-    "| Class | Package | Local | Serializable | JS support|\n",
-    "| :--- | :--- | :---: | :---: |  :---: |\n",
-    "| [BoxLoader](https://python.langchain.com/api_reference/box/document_loaders/langchain_box.document_loaders.box.BoxLoader.html) | [langchain_box](https://python.langchain.com/api_reference/box/index.html) | ✅ | ❌ | ❌ | \n",
-    "| [BoxBlobLoader](https://python.langchain.com/api_reference/box/document_loaders/langchain_box.blob_loaders.box.BoxBlobLoader.html) | [langchain_box](https://python.langchain.com/api_reference/box/index.html) | ✅ | ❌ | ❌ | \n",
-    "### Loader features\n",
-    "| Source | Document Lazy Loading | Async Support\n",
-    "| :---: | :---: | :---: | \n",
-    "| BoxLoader | ✅ | ❌ | \n",
-    "| BoxBlobLoader | ✅ | ❌ | \n",
-    "\n",
-    "## Setup\n",
-    "\n",
-    "In order to use the Box package, you will need a few things:\n",
-    "\n",
-    "* A Box account — If you are not a current Box customer or want to test outside of your production Box instance, you can use a [free developer account](https://account.box.com/signup/n/developer#ty9l3).\n",
-    "* [A Box app](https://developer.box.com/guides/getting-started/first-application/) — This is configured in the [developer console](https://account.box.com/developers/console), and for Box AI, must have the `Manage AI` scope enabled. Here you will also select your authentication method\n",
-    "* The app must be [enabled by the administrator](https://developer.box.com/guides/authorization/custom-app-approval/#manual-approval). For free developer accounts, this is whomever signed up for the account.\n",
-    "\n",
-    "### Credentials\n",
-    "\n",
-    "For these examples, we will use [token authentication](https://developer.box.com/guides/authentication/tokens/developer-tokens). This can be used with any [authentication method](https://developer.box.com/guides/authentication/). Just get the token with whatever methodology. If you want to learn more about how to use other authentication types with `langchain-box`, visit the [Box provider](/docs/integrations/providers/box) document.\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [
+  "cells": [
     {
-     "name": "stdin",
-     "output_type": "stream",
-     "text": [
-      "Enter your Box Developer Token:  ········\n"
-     ]
-    }
-   ],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "box_developer_token = getpass.getpass(\"Enter your Box Developer Token: \")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "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,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
-    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Installation\n",
-    "\n",
-    "Install **langchain_box**."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%pip install -qU langchain_box"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Initialization\n",
-    "\n",
-    "### Load files\n",
-    "\n",
-    "If you wish to load files, you must provide the `List` of file ids at instantiation time. \n",
-    "\n",
-    "This requires 1 piece of information:\n",
-    "\n",
-    "* **box_file_ids** (`List[str]`)- A list of Box file IDs.\n",
-    "\n",
-    "#### BoxLoader"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_box.document_loaders import BoxLoader\n",
-    "\n",
-    "box_file_ids = [\"1514555423624\", \"1514553902288\"]\n",
-    "\n",
-    "loader = BoxLoader(\n",
-    "    box_developer_token=box_developer_token,\n",
-    "    box_file_ids=box_file_ids,\n",
-    "    character_limit=10000,  # Optional. Defaults to no limit\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### BoxBlobLoader"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_box.blob_loaders import BoxBlobLoader\n",
-    "\n",
-    "box_file_ids = [\"1514555423624\", \"1514553902288\"]\n",
-    "\n",
-    "loader = BoxBlobLoader(\n",
-    "    box_developer_token=box_developer_token, box_file_ids=box_file_ids\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Load from folder\n",
-    "\n",
-    "If you wish to load files from a folder, you must provide a `str` with the Box folder ID at instantiation time. \n",
-    "\n",
-    "This requires 1 piece of information:\n",
-    "\n",
-    "* **box_folder_id** (`str`)- A string containing a Box folder ID.\n",
-    "\n",
-    "#### BoxLoader"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_box.document_loaders import BoxLoader\n",
-    "\n",
-    "box_folder_id = \"260932470532\"\n",
-    "\n",
-    "loader = BoxLoader(\n",
-    "    box_folder_id=box_folder_id,\n",
-    "    recursive=False,  # Optional. return entire tree, defaults to False\n",
-    "    character_limit=10000,  # Optional. Defaults to no limit\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### BoxBlobLoader"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_box.blob_loaders import BoxBlobLoader\n",
-    "\n",
-    "box_folder_id = \"260932470532\"\n",
-    "\n",
-    "loader = BoxBlobLoader(\n",
-    "    box_folder_id=box_folder_id,\n",
-    "    recursive=False,  # Optional. return entire tree, defaults to False\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Search for files with BoxBlobLoader\n",
-    "\n",
-    "If you need to search for files, the `BoxBlobLoader` offers two methods. First you can perform a full text search with optional search options to narrow down that search.\n",
-    "\n",
-    "This requires 1 piece of information:\n",
-    "\n",
-    "* **query** (`str`)- A string containing the search query to perform.\n",
-    "\n",
-    "You can also provide a `BoxSearchOptions` object to narrow down that search\n",
-    "* **box_search_options** (`BoxSearchOptions`)\n",
-    "\n",
-    "#### BoxBlobLoader search"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_box.blob_loaders import BoxBlobLoader\n",
-    "from langchain_box.utilities import BoxSearchOptions, DocumentFiles, SearchTypeFilter\n",
-    "\n",
-    "box_folder_id = \"260932470532\"\n",
-    "\n",
-    "box_search_options = BoxSearchOptions(\n",
-    "    ancestor_folder_ids=[box_folder_id],\n",
-    "    search_type_filter=[SearchTypeFilter.FILE_CONTENT],\n",
-    "    created_date_range=[\"2023-01-01T00:00:00-07:00\", \"2024-08-01T00:00:00-07:00,\"],\n",
-    "    file_extensions=[DocumentFiles.DOCX, DocumentFiles.PDF],\n",
-    "    k=200,\n",
-    "    size_range=[1, 1000000],\n",
-    "    updated_data_range=None,\n",
-    ")\n",
-    "\n",
-    "loader = BoxBlobLoader(\n",
-    "    box_developer_token=box_developer_token,\n",
-    "    query=\"Victor\",\n",
-    "    box_search_options=box_search_options,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "You can also search for content based on Box Metadata. If your Box instance uses Metadata, you can search for any documents that have a specific Metadata Template attached that meet a certain criteria, like returning any invoices with a total greater than or equal to $500 that were created last quarter.\n",
-    "\n",
-    "This requires 1 piece of information:\n",
-    "\n",
-    "* **query** (`str`)- A string containing the search query to perform.\n",
-    "\n",
-    "You can also provide a `BoxSearchOptions` object to narrow down that search\n",
-    "* **box_search_options** (`BoxSearchOptions`)\n",
-    "\n",
-    "#### BoxBlobLoader Metadata query"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_box.blob_loaders import BoxBlobLoader\n",
-    "from langchain_box.utilities import BoxMetadataQuery\n",
-    "\n",
-    "query = BoxMetadataQuery(\n",
-    "    template_key=\"enterprise_1234.myTemplate\",\n",
-    "    query=\"total >= :value\",\n",
-    "    query_params={\"value\": 100},\n",
-    "    ancestor_folder_id=\"260932470532\",\n",
-    ")\n",
-    "\n",
-    "loader = BoxBlobLoader(box_metadata_query=query)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Load\n",
-    "\n",
-    "#### BoxLoader"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "Document(metadata={'source': 'https://dl.boxcloud.com/api/2.0/internal_files/1514555423624/versions/1663171610024/representations/extracted_text/content/', 'title': 'Invoice-A5555_txt'}, page_content='Vendor: AstroTech Solutions\\nInvoice Number: A5555\\n\\nLine Items:\\n    - Gravitational Wave Detector Kit: $800\\n    - Exoplanet Terrarium: $120\\nTotal: $920')"
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "---\n",
+        "sidebar_label: Box\n",
+        "---"
       ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "docs = loader.load()\n",
-    "docs[0]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [
+    },
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'source': 'https://dl.boxcloud.com/api/2.0/internal_files/1514555423624/versions/1663171610024/representations/extracted_text/content/', 'title': 'Invoice-A5555_txt'}\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(docs[0].metadata)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### BoxBlobLoader"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# BoxLoader and BoxBlobLoader\n",
+        "\n",
+        "\n",
+        "The `langchain-box` package provides two methods to index your files from Box: `BoxLoader` and `BoxBlobLoader`. `BoxLoader` allows you to ingest text representations of files that have a text representation in Box. The `BoxBlobLoader` allows you download the blob for any document or image file for processing with the blob parser of your choice.\n",
+        "\n",
+        "This notebook details getting started with both of these. For detailed documentation of all BoxLoader features and configurations head to the API Reference pages for [BoxLoader](https://python.langchain.com/api_reference/box/document_loaders/langchain_box.document_loaders.box.BoxLoader.html) and [BoxBlobLoader](https://python.langchain.com/api_reference/box/document_loaders/langchain_box.blob_loaders.box.BoxBlobLoader.html).\n",
+        "\n",
+        "## Overview\n",
+        "\n",
+        "The `BoxLoader` class helps you get your unstructured content from Box in Langchain's `Document` format. You can do this with either a `List[str]` containing Box file IDs, or with a `str` containing a Box folder ID.\n",
+        "\n",
+        "The `BoxBlobLoader` class helps you get your unstructured content from Box in Langchain's `Blob` format. You can do this with a `List[str]` containing Box file IDs, a `str` containing a Box folder ID, a search query, or a `BoxMetadataQuery`.\n",
+        "\n",
+        "If getting files from a folder with folder ID, you can also set a `Bool` to tell the loader to get all sub-folders in that folder, as well.\n",
+        "\n",
+        ":::info\n",
+        "A Box instance can contain Petabytes of files, and folders can contain millions of files. Be intentional when choosing what folders you choose to index. And we recommend never getting all files from folder 0 recursively. Folder ID 0 is your root folder.\n",
+        ":::\n",
+        "\n",
+        "The `BoxLoader` will skip files without a text representation, while the `BoxBlobLoader` will return blobs for all document and image files.\n",
+        "\n",
+        "### Integration details\n",
+        "\n",
+        "| Class | Package | Local | Serializable | JS support|\n",
+        "| :--- | :--- | :---: | :---: |  :---: |\n",
+        "| [BoxLoader](https://python.langchain.com/api_reference/box/document_loaders/langchain_box.document_loaders.box.BoxLoader.html) | [langchain_box](https://python.langchain.com/api_reference/box/index.html) | ✅ | ❌ | ❌ |\n",
+        "| [BoxBlobLoader](https://python.langchain.com/api_reference/box/document_loaders/langchain_box.blob_loaders.box.BoxBlobLoader.html) | [langchain_box](https://python.langchain.com/api_reference/box/index.html) | ✅ | ❌ | ❌ |\n",
+        "### Loader features\n",
+        "| Source | Document Lazy Loading | Async Support\n",
+        "| :---: | :---: | :---: |\n",
+        "| BoxLoader | ✅ | ❌ |\n",
+        "| BoxBlobLoader | ✅ | ❌ |\n",
+        "\n",
+        "## Setup\n",
+        "\n",
+        "In order to use the Box package, you will need a few things:\n",
+        "\n",
+        "* A Box account — If you are not a current Box customer or want to test outside of your production Box instance, you can use a [free developer account](https://account.box.com/signup/n/developer#ty9l3).\n",
+        "* [A Box app](https://developer.box.com/guides/getting-started/first-application/) — This is configured in the [developer console](https://account.box.com/developers/console), and for Box AI, must have the `Manage AI` scope enabled. Here you will also select your authentication method\n",
+        "* The app must be [enabled by the administrator](https://developer.box.com/guides/authorization/custom-app-approval/#manual-approval). For free developer accounts, this is whomever signed up for the account.\n",
+        "\n",
+        "### Credentials\n",
+        "\n",
+        "For these examples, we will use [token authentication](https://developer.box.com/guides/authentication/tokens/developer-tokens). This can be used with any [authentication method](https://developer.box.com/guides/authentication/). Just get the token with whatever methodology. If you want to learn more about how to use other authentication types with `langchain-box`, visit the [Box provider](/docs/integrations/providers/box) document.\n"
+      ]
+    },
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Blob(id='1514555423624' metadata={'source': 'https://app.box.com/0/260935730128/260931903795/Invoice-A5555.txt', 'name': 'Invoice-A5555.txt', 'file_size': 150} data=\"b'Vendor: AstroTech Solutions\\\\nInvoice Number: A5555\\\\n\\\\nLine Items:\\\\n    - Gravitational Wave Detector Kit: $800\\\\n    - Exoplanet Terrarium: $120\\\\nTotal: $920'\" mimetype='text/plain' path='https://app.box.com/0/260935730128/260931903795/Invoice-A5555.txt')\n",
-      "Blob(id='1514553902288' metadata={'source': 'https://app.box.com/0/260935730128/260931903795/Invoice-B1234.txt', 'name': 'Invoice-B1234.txt', 'file_size': 168} data=\"b'Vendor: Galactic Gizmos Inc.\\\\nInvoice Number: B1234\\\\nPurchase Order Number: 001\\\\nLine Items:\\\\n    - Quantum Flux Capacitor: $500\\\\n    - Anti-Gravity Pen Set: $75\\\\nTotal: $575'\" mimetype='text/plain' path='https://app.box.com/0/260935730128/260931903795/Invoice-B1234.txt')\n"
-     ]
+      "cell_type": "code",
+      "execution_count": 1,
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stdin",
+          "output_type": "stream",
+          "text": [
+            "Enter your Box Developer Token:  ········\n"
+          ]
+        }
+      ],
+      "source": [
+        "import getpass\n",
+        "import os\n",
+        "\n",
+        "box_developer_token = getpass.getpass(\"Enter your Box Developer Token: \")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": "To enable automated tracing of your model calls, set your [LangSmith](https://docs.smith.langchain.com/) API key:"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
+        "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Installation\n",
+        "\n",
+        "Install **langchain_box**."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%pip install -qU langchain_box"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Initialization\n",
+        "\n",
+        "### Load files\n",
+        "\n",
+        "If you wish to load files, you must provide the `List` of file ids at instantiation time.\n",
+        "\n",
+        "This requires 1 piece of information:\n",
+        "\n",
+        "* **box_file_ids** (`List[str]`)- A list of Box file IDs.\n",
+        "\n",
+        "#### BoxLoader"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 2,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from langchain_box.document_loaders import BoxLoader\n",
+        "\n",
+        "box_file_ids = [\"1514555423624\", \"1514553902288\"]\n",
+        "\n",
+        "loader = BoxLoader(\n",
+        "    box_developer_token=box_developer_token,\n",
+        "    box_file_ids=box_file_ids,\n",
+        "    character_limit=10000,  # Optional. Defaults to no limit\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### BoxBlobLoader"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 4,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from langchain_box.blob_loaders import BoxBlobLoader\n",
+        "\n",
+        "box_file_ids = [\"1514555423624\", \"1514553902288\"]\n",
+        "\n",
+        "loader = BoxBlobLoader(\n",
+        "    box_developer_token=box_developer_token, box_file_ids=box_file_ids\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Load from folder\n",
+        "\n",
+        "If you wish to load files from a folder, you must provide a `str` with the Box folder ID at instantiation time.\n",
+        "\n",
+        "This requires 1 piece of information:\n",
+        "\n",
+        "* **box_folder_id** (`str`)- A string containing a Box folder ID.\n",
+        "\n",
+        "#### BoxLoader"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from langchain_box.document_loaders import BoxLoader\n",
+        "\n",
+        "box_folder_id = \"260932470532\"\n",
+        "\n",
+        "loader = BoxLoader(\n",
+        "    box_folder_id=box_folder_id,\n",
+        "    recursive=False,  # Optional. return entire tree, defaults to False\n",
+        "    character_limit=10000,  # Optional. Defaults to no limit\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### BoxBlobLoader"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from langchain_box.blob_loaders import BoxBlobLoader\n",
+        "\n",
+        "box_folder_id = \"260932470532\"\n",
+        "\n",
+        "loader = BoxBlobLoader(\n",
+        "    box_folder_id=box_folder_id,\n",
+        "    recursive=False,  # Optional. return entire tree, defaults to False\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Search for files with BoxBlobLoader\n",
+        "\n",
+        "If you need to search for files, the `BoxBlobLoader` offers two methods. First you can perform a full text search with optional search options to narrow down that search.\n",
+        "\n",
+        "This requires 1 piece of information:\n",
+        "\n",
+        "* **query** (`str`)- A string containing the search query to perform.\n",
+        "\n",
+        "You can also provide a `BoxSearchOptions` object to narrow down that search\n",
+        "* **box_search_options** (`BoxSearchOptions`)\n",
+        "\n",
+        "#### BoxBlobLoader search"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 2,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from langchain_box.blob_loaders import BoxBlobLoader\n",
+        "from langchain_box.utilities import BoxSearchOptions, DocumentFiles, SearchTypeFilter\n",
+        "\n",
+        "box_folder_id = \"260932470532\"\n",
+        "\n",
+        "box_search_options = BoxSearchOptions(\n",
+        "    ancestor_folder_ids=[box_folder_id],\n",
+        "    search_type_filter=[SearchTypeFilter.FILE_CONTENT],\n",
+        "    created_date_range=[\"2023-01-01T00:00:00-07:00\", \"2024-08-01T00:00:00-07:00,\"],\n",
+        "    file_extensions=[DocumentFiles.DOCX, DocumentFiles.PDF],\n",
+        "    k=200,\n",
+        "    size_range=[1, 1000000],\n",
+        "    updated_data_range=None,\n",
+        ")\n",
+        "\n",
+        "loader = BoxBlobLoader(\n",
+        "    box_developer_token=box_developer_token,\n",
+        "    query=\"Victor\",\n",
+        "    box_search_options=box_search_options,\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "You can also search for content based on Box Metadata. If your Box instance uses Metadata, you can search for any documents that have a specific Metadata Template attached that meet a certain criteria, like returning any invoices with a total greater than or equal to $500 that were created last quarter.\n",
+        "\n",
+        "This requires 1 piece of information:\n",
+        "\n",
+        "* **query** (`str`)- A string containing the search query to perform.\n",
+        "\n",
+        "You can also provide a `BoxSearchOptions` object to narrow down that search\n",
+        "* **box_search_options** (`BoxSearchOptions`)\n",
+        "\n",
+        "#### BoxBlobLoader Metadata query"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from langchain_box.blob_loaders import BoxBlobLoader\n",
+        "from langchain_box.utilities import BoxMetadataQuery\n",
+        "\n",
+        "query = BoxMetadataQuery(\n",
+        "    template_key=\"enterprise_1234.myTemplate\",\n",
+        "    query=\"total >= :value\",\n",
+        "    query_params={\"value\": 100},\n",
+        "    ancestor_folder_id=\"260932470532\",\n",
+        ")\n",
+        "\n",
+        "loader = BoxBlobLoader(box_metadata_query=query)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Load\n",
+        "\n",
+        "#### BoxLoader"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 3,
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "Document(metadata={'source': 'https://dl.boxcloud.com/api/2.0/internal_files/1514555423624/versions/1663171610024/representations/extracted_text/content/', 'title': 'Invoice-A5555_txt'}, page_content='Vendor: AstroTech Solutions\\nInvoice Number: A5555\\n\\nLine Items:\\n    - Gravitational Wave Detector Kit: $800\\n    - Exoplanet Terrarium: $120\\nTotal: $920')"
+            ]
+          },
+          "execution_count": 3,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "docs = loader.load()\n",
+        "docs[0]"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 4,
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "{'source': 'https://dl.boxcloud.com/api/2.0/internal_files/1514555423624/versions/1663171610024/representations/extracted_text/content/', 'title': 'Invoice-A5555_txt'}\n"
+          ]
+        }
+      ],
+      "source": [
+        "print(docs[0].metadata)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### BoxBlobLoader"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 7,
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Blob(id='1514555423624' metadata={'source': 'https://app.box.com/0/260935730128/260931903795/Invoice-A5555.txt', 'name': 'Invoice-A5555.txt', 'file_size': 150} data=\"b'Vendor: AstroTech Solutions\\\\nInvoice Number: A5555\\\\n\\\\nLine Items:\\\\n    - Gravitational Wave Detector Kit: $800\\\\n    - Exoplanet Terrarium: $120\\\\nTotal: $920'\" mimetype='text/plain' path='https://app.box.com/0/260935730128/260931903795/Invoice-A5555.txt')\n",
+            "Blob(id='1514553902288' metadata={'source': 'https://app.box.com/0/260935730128/260931903795/Invoice-B1234.txt', 'name': 'Invoice-B1234.txt', 'file_size': 168} data=\"b'Vendor: Galactic Gizmos Inc.\\\\nInvoice Number: B1234\\\\nPurchase Order Number: 001\\\\nLine Items:\\\\n    - Quantum Flux Capacitor: $500\\\\n    - Anti-Gravity Pen Set: $75\\\\nTotal: $575'\" mimetype='text/plain' path='https://app.box.com/0/260935730128/260931903795/Invoice-B1234.txt')\n"
+          ]
+        }
+      ],
+      "source": [
+        "for blob in loader.yield_blobs():\n",
+        "    print(f\"Blob({blob})\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Lazy Load\n",
+        "\n",
+        "#### BoxLoader only"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "page = []\n",
+        "for doc in loader.lazy_load():\n",
+        "    page.append(doc)\n",
+        "    if len(page) >= 10:\n",
+        "        # do some paged operation, e.g.\n",
+        "        # index.upsert(page)\n",
+        "\n",
+        "        page = []"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Extra fields\n",
+        "\n",
+        "All Box connectors offer the ability to select additional fields from the Box `FileFull` object to return as custom LangChain metadata. Each object accepts an optional `List[str]` called `extra_fields` containing the json key from the return object, like `extra_fields=[\"shared_link\"]`.\n",
+        "\n",
+        "The connector will add this field to the list of fields the integration needs to function and then add the results to the metadata returned in the `Document` or `Blob`, like `\"metadata\" : { \"source\" : \"source, \"shared_link\" : \"shared_link\" }`. If the field is unavailable for that file, it will be returned as an empty string, like `\"shared_link\" : \"\"`."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": []
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## API reference\n",
+        "\n",
+        "For detailed documentation of all BoxLoader features and configurations head to the [API reference](https://python.langchain.com/api_reference/box/document_loaders/langchain_box.document_loaders.box.BoxLoader.html)\n",
+        "\n",
+        "\n",
+        "## Help\n",
+        "\n",
+        "If you have questions, you can check out our [developer documentation](https://developer.box.com) or reach out to use in our [developer community](https://community.box.com)."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "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": "3.11.6"
     }
-   ],
-   "source": [
-    "for blob in loader.yield_blobs():\n",
-    "    print(f\"Blob({blob})\")"
-   ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Lazy Load\n",
-    "\n",
-    "#### BoxLoader only"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "page = []\n",
-    "for doc in loader.lazy_load():\n",
-    "    page.append(doc)\n",
-    "    if len(page) >= 10:\n",
-    "        # do some paged operation, e.g.\n",
-    "        # index.upsert(page)\n",
-    "\n",
-    "        page = []"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Extra fields\n",
-    "\n",
-    "All Box connectors offer the ability to select additional fields from the Box `FileFull` object to return as custom LangChain metadata. Each object accepts an optional `List[str]` called `extra_fields` containing the json key from the return object, like `extra_fields=[\"shared_link\"]`. \n",
-    "\n",
-    "The connector will add this field to the list of fields the integration needs to function and then add the results to the metadata returned in the `Document` or `Blob`, like `\"metadata\" : { \"source\" : \"source, \"shared_link\" : \"shared_link\" }`. If the field is unavailable for that file, it will be returned as an empty string, like `\"shared_link\" : \"\"`."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## API reference\n",
-    "\n",
-    "For detailed documentation of all BoxLoader features and configurations head to the [API reference](https://python.langchain.com/api_reference/box/document_loaders/langchain_box.document_loaders.box.BoxLoader.html)\n",
-    "\n",
-    "\n",
-    "## Help\n",
-    "\n",
-    "If you have questions, you can check out our [developer documentation](https://developer.box.com) or reach out to use in our [developer community](https://community.box.com)."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "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": "3.11.6"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
+  "nbformat": 4,
+  "nbformat_minor": 4
 }