infra: fix release prerelease deps bug (#24323)

* Add how-to guide for dispatching custom callback events.
* Add links from index to the how to guide
* Add link from streaming from within a tool
* Update versionadded to correct release
https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D0.2.15

.devcontainer/docker-compose.yaml

@@ -5,10 +5,10 @@ services:
       dockerfile: libs/langchain/dev.Dockerfile
       context: ..
     volumes:
-   # Update this to wherever you want VS Code to mount the folder of your project
+      # Update this to wherever you want VS Code to mount the folder of your project
       - ..:/workspaces/langchain:cached
     networks:
-      - langchain-network 
+      - langchain-network
   #   environment:
   #     MONGO_ROOT_USERNAME: root
   #     MONGO_ROOT_PASSWORD: example123
@@ -28,5 +28,3 @@ services:
 networks:
   langchain-network:
     driver: bridge
-    
-    

.github/ISSUE_TEMPLATE/config.yml

@@ -4,9 +4,6 @@ contact_links:
   - name: 🤔 Question or Problem
     about: Ask a question or ask about a problem in GitHub Discussions.
     url: https://www.github.com/langchain-ai/langchain/discussions/categories/q-a
-  - name: Discord
-    url: https://discord.gg/6adMQxSpJS
-    about: General community discussions
   - name: Feature Request
     url: https://www.github.com/langchain-ai/langchain/discussions/categories/ideas
     about: Suggest a feature or an idea

.github/scripts/check_diff.py

@@ -6,6 +6,7 @@ import sys
 import tomllib
 from collections import defaultdict
 from typing import Dict, List, Set
+from pathlib import Path
 
 
 LANGCHAIN_DIRS = [
@@ -26,17 +27,48 @@ def all_package_dirs() -> Set[str]:
 
 
 def dependents_graph() -> dict:
+    """
+    Construct a mapping of package -> dependents, such that we can
+    run tests on all dependents of a package when a change is made.
+    """
     dependents = defaultdict(set)
 
     for path in glob.glob("./libs/**/pyproject.toml", recursive=True):
         if "template" in path:
             continue
+
+        # load regular and test deps from pyproject.toml
         with open(path, "rb") as f:
             pyproject = tomllib.load(f)["tool"]["poetry"]
+
         pkg_dir = "libs" + "/".join(path.split("libs")[1].split("/")[:-1])
-        for dep in pyproject["dependencies"]:
+        for dep in [
+            *pyproject["dependencies"].keys(),
+            *pyproject["group"]["test"]["dependencies"].keys(),
+        ]:
             if "langchain" in dep:
                 dependents[dep].add(pkg_dir)
+                continue
+
+        # load extended deps from extended_testing_deps.txt
+        package_path = Path(path).parent
+        extended_requirement_path = package_path / "extended_testing_deps.txt"
+        if extended_requirement_path.exists():
+            with open(extended_requirement_path, "r") as f:
+                extended_deps = f.read().splitlines()
+                for depline in extended_deps:
+                    if depline.startswith("-e "):
+                        # editable dependency
+                        assert depline.startswith(
+                            "-e ../partners/"
+                        ), "Extended test deps should only editable install partner packages"
+                        partner = depline.split("partners/")[1]
+                        dep = f"langchain-{partner}"
+                    else:
+                        dep = depline.split("==")[0]
+
+                    if "langchain" in dep:
+                        dependents[dep].add(pkg_dir)
     return dependents
 
 
@@ -53,6 +85,44 @@ def add_dependents(dirs_to_eval: Set[str], dependents: dict) -> List[str]:
     return list(updated)
 
 
+def _get_configs_for_single_dir(job: str, dir_: str) -> List[Dict[str, str]]:
+    min_python = "3.8"
+    max_python = "3.12"
+
+    # custom logic for specific directories
+    if dir_ == "libs/partners/milvus":
+        # milvus poetry doesn't allow 3.12 because they
+        # declare deps in funny way
+        max_python = "3.11"
+
+    return [
+        {"working-directory": dir_, "python-version": min_python},
+        {"working-directory": dir_, "python-version": max_python},
+    ]
+
+
+def _get_configs_for_multi_dirs(
+    job: str, dirs_to_run: List[str], dependents: dict
+) -> List[Dict[str, str]]:
+    if job == "lint":
+        dirs = add_dependents(
+            dirs_to_run["lint"] | dirs_to_run["test"] | dirs_to_run["extended-test"],
+            dependents,
+        )
+    elif job in ["test", "compile-integration-tests", "dependencies"]:
+        dirs = add_dependents(
+            dirs_to_run["test"] | dirs_to_run["extended-test"], dependents
+        )
+    elif job == "extended-tests":
+        dirs = list(dirs_to_run["extended-test"])
+    else:
+        raise ValueError(f"Unknown job: {job}")
+
+    return [
+        config for dir_ in dirs for config in _get_configs_for_single_dir(job, dir_)
+    ]
+
+
 if __name__ == "__main__":
     files = sys.argv[1:]
 
@@ -126,17 +196,23 @@ if __name__ == "__main__":
 
     dependents = dependents_graph()
 
-    outputs = {
-        "dirs-to-lint": add_dependents(
-            dirs_to_run["lint"] | dirs_to_run["test"] | dirs_to_run["extended-test"],
-            dependents,
-        ),
-        "dirs-to-test": add_dependents(
-            dirs_to_run["test"] | dirs_to_run["extended-test"], dependents
-        ),
-        "dirs-to-extended-test": list(dirs_to_run["extended-test"]),
-        "docs-edited": "true" if docs_edited else "",
+    # we now have dirs_by_job
+    # todo: clean this up
+
+    map_job_to_configs = {
+        job: _get_configs_for_multi_dirs(job, dirs_to_run, dependents)
+        for job in [
+            "lint",
+            "test",
+            "extended-tests",
+            "compile-integration-tests",
+            "dependencies",
+        ]
     }
-    for key, value in outputs.items():
+    map_job_to_configs["test-doc-imports"] = (
+        [{"python-version": "3.12"}] if docs_edited else []
+    )
+
+    for key, value in map_job_to_configs.items():
         json_output = json.dumps(value)
         print(f"{key}={json_output}")

.github/scripts/check_prerelease_dependencies.py

@@ -0,0 +1,35 @@
+import sys
+import tomllib
+
+if __name__ == "__main__":
+    # Get the TOML file path from the command line argument
+    toml_file = sys.argv[1]
+
+    # read toml file
+    with open(toml_file, "rb") as file:
+        toml_data = tomllib.load(file)
+
+    # see if we're releasing an rc
+    version = toml_data["tool"]["poetry"]["version"]
+    releasing_rc = "rc" in version
+
+    # if not, iterate through dependencies and make sure none allow prereleases
+    if not releasing_rc:
+        dependencies = toml_data["tool"]["poetry"]["dependencies"]
+        for lib in dependencies:
+            dep_version = dependencies[lib]
+            dep_version_string = (
+                dep_version["version"] if isinstance(dep_version, dict) else dep_version
+            )
+
+            if "rc" in dep_version_string:
+                raise ValueError(
+                    f"Dependency {lib} has a prerelease version. Please remove this."
+                )
+
+            if isinstance(dep_version, dict) and dep_version.get(
+                "allow-prereleases", False
+            ):
+                raise ValueError(
+                    f"Dependency {lib} has allow-prereleases set to true. Please remove this."
+                )

.github/scripts/get_min_versions.py

@@ -9,6 +9,7 @@ MIN_VERSION_LIBS = [
     "langchain-community",
     "langchain",
     "langchain-text-splitters",
+    "SQLAlchemy",
 ]
 
 

.github/workflows/_compile_integration_test.yml

@@ -7,6 +7,10 @@ on:
         required: true
         type: string
         description: "From which folder this pipeline executes"
+      python-version:
+        required: true
+        type: string
+        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -17,22 +21,14 @@ jobs:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version:
-          - "3.8"
-          - "3.9"
-          - "3.10"
-          - "3.11"
-          - "3.12"
-    name: "poetry run pytest -m compile tests/integration_tests #${{ matrix.python-version }}"
+    name: "poetry run pytest -m compile tests/integration_tests #${{ inputs.python-version }}"
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: ${{ inputs.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
           cache-key: compile-integration

.github/workflows/_dependencies.yml

@@ -11,6 +11,10 @@ on:
         required: false
         type: string
         description: "Relative path to the langchain library folder"
+      python-version:
+        required: true
+        type: string
+        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -21,22 +25,14 @@ jobs:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version:
-          - "3.8"
-          - "3.9"
-          - "3.10"
-          - "3.11"
-          - "3.12"
-    name: dependency checks ${{ matrix.python-version }}
+    name: dependency checks ${{ inputs.python-version }}
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: ${{ inputs.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
           cache-key: pydantic-cross-compat

.github/workflows/_integration_test.yml

@@ -6,6 +6,10 @@ on:
       working-directory:
         required: true
         type: string
+      python-version:
+        required: true
+        type: string
+        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -16,19 +20,14 @@ jobs:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version:
-          - "3.8"
-          - "3.11"
-    name: Python ${{ matrix.python-version }}
+    name: Python ${{ inputs.python-version }}
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: ${{ inputs.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
           cache-key: core

.github/workflows/_lint.yml

@@ -11,6 +11,10 @@ on:
         required: false
         type: string
         description: "Relative path to the langchain library folder"
+      python-version:
+        required: true
+        type: string
+        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -21,27 +25,15 @@ env:
 
 jobs:
   build:
-    name: "make lint #${{ matrix.python-version }}"
+    name: "make lint #${{ inputs.python-version }}"
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        # Only lint on the min and max supported Python versions.
-        # It's extremely unlikely that there's a lint issue on any version in between
-        # that doesn't show up on the min or max versions.
-        #
-        # GitHub rate-limits how many jobs can be running at any one time.
-        # Starting new jobs is also relatively slow,
-        # so linting on fewer versions makes CI faster.
-        python-version:
-          - "3.8"
-          - "3.12"
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: ${{ inputs.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
           cache-key: lint-with-extras
@@ -86,7 +78,7 @@ jobs:
         with:
           path: |
             ${{ env.WORKDIR }}/.mypy_cache
-          key: mypy-lint-${{ runner.os }}-${{ runner.arch }}-py${{ matrix.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}
+          key: mypy-lint-${{ runner.os }}-${{ runner.arch }}-py${{ inputs.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}
 
 
       - name: Analysing the code with our lint
@@ -120,7 +112,7 @@ jobs:
         with:
           path: |
             ${{ env.WORKDIR }}/.mypy_cache_test
-          key: mypy-test-${{ runner.os }}-${{ runner.arch }}-py${{ matrix.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}
+          key: mypy-test-${{ runner.os }}-${{ runner.arch }}-py${{ inputs.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}
 
       - name: Analysing the code with our lint
         working-directory: ${{ inputs.working-directory }}

.github/workflows/_release.yml

@@ -122,7 +122,6 @@ jobs:
           fi
           {
             echo 'release-body<<EOF'
-            echo "# Release $TAG"
             echo $PREAMBLE
             echo
             git log --format="%s" "$PREV_TAG"..HEAD -- $WORKING_DIR
@@ -222,6 +221,11 @@ jobs:
         run: make tests
         working-directory: ${{ inputs.working-directory }}
 
+      - name: Check for prerelease versions
+        working-directory: ${{ inputs.working-directory }}
+        run: |
+          poetry run python $GITHUB_WORKSPACE/.github/scripts/check_prerelease_dependencies.py pyproject.toml
+
       - name: Get minimum versions
         working-directory: ${{ inputs.working-directory }}
         id: min-version

.github/workflows/_test.yml

@@ -11,6 +11,10 @@ on:
         required: false
         type: string
         description: "Relative path to the langchain library folder"
+      python-version:
+        required: true
+        type: string
+        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -21,22 +25,14 @@ jobs:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version:
-          - "3.8"
-          - "3.9"
-          - "3.10"
-          - "3.11"
-          - "3.12"
-    name: "make test #${{ matrix.python-version }}"
+    name: "make test #${{ inputs.python-version }}"
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: ${{ inputs.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
           cache-key: core

.github/workflows/_test_doc_imports.yml

@@ -2,6 +2,11 @@ name: test_doc_imports
 
 on:
   workflow_call:
+    inputs:
+      python-version:
+        required: true
+        type: string
+        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -9,18 +14,14 @@ env:
 jobs:
   build:
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version:
-          - "3.12"
-    name: "check doc imports #${{ matrix.python-version }}"
+    name: "check doc imports #${{ inputs.python-version }}"
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: ${{ inputs.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           cache-key: core
 

.github/workflows/check_diffs.yml

@@ -33,91 +33,96 @@ jobs:
         run: |
           python .github/scripts/check_diff.py ${{ steps.files.outputs.all }} >> $GITHUB_OUTPUT
     outputs:
-      dirs-to-lint: ${{ steps.set-matrix.outputs.dirs-to-lint }}
-      dirs-to-test: ${{ steps.set-matrix.outputs.dirs-to-test }}
-      dirs-to-extended-test: ${{ steps.set-matrix.outputs.dirs-to-extended-test }}
-      docs-edited: ${{ steps.set-matrix.outputs.docs-edited }}
+      lint: ${{ steps.set-matrix.outputs.lint }}
+      test: ${{ steps.set-matrix.outputs.test }}
+      extended-tests: ${{ steps.set-matrix.outputs.extended-tests }}
+      compile-integration-tests: ${{ steps.set-matrix.outputs.compile-integration-tests }}
+      dependencies: ${{ steps.set-matrix.outputs.dependencies }}
+      test-doc-imports: ${{ steps.set-matrix.outputs.test-doc-imports }}
   lint:
-    name: cd ${{ matrix.working-directory }}
+    name: cd ${{ matrix.job-configs.working-directory }}
     needs: [ build ]
-    if: ${{ needs.build.outputs.dirs-to-lint != '[]' }}
+    if: ${{ needs.build.outputs.lint != '[]' }}
     strategy:
       matrix:
-        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-lint) }}
+        job-configs: ${{ fromJson(needs.build.outputs.lint) }}
     uses: ./.github/workflows/_lint.yml
     with:
-      working-directory: ${{ matrix.working-directory }}
+      working-directory: ${{ matrix.job-configs.working-directory }}
+      python-version: ${{ matrix.job-configs.python-version }}
     secrets: inherit
 
   test:
-    name: cd ${{ matrix.working-directory }}
+    name: cd ${{ matrix.job-configs.working-directory }}
     needs: [ build ]
-    if: ${{ needs.build.outputs.dirs-to-test != '[]' }}
+    if: ${{ needs.build.outputs.test != '[]' }}
     strategy:
       matrix:
-        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-test) }}
+        job-configs: ${{ fromJson(needs.build.outputs.test) }}
     uses: ./.github/workflows/_test.yml
     with:
-      working-directory: ${{ matrix.working-directory }}
+      working-directory: ${{ matrix.job-configs.working-directory }}
+      python-version: ${{ matrix.job-configs.python-version }}
     secrets: inherit
 
   test-doc-imports:
     needs: [ build ]
-    if: ${{ needs.build.outputs.dirs-to-test != '[]' || needs.build.outputs.docs-edited }}
-    uses: ./.github/workflows/_test_doc_imports.yml
-    secrets: inherit
-
-  compile-integration-tests:
-    name: cd ${{ matrix.working-directory }}
-    needs: [ build ]
-    if: ${{ needs.build.outputs.dirs-to-test != '[]' }}
+    if: ${{ needs.build.outputs.test-doc-imports != '[]' }}
     strategy:
       matrix:
-        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-test) }}
+        job-configs: ${{ fromJson(needs.build.outputs.test-doc-imports) }}
+    uses: ./.github/workflows/_test_doc_imports.yml
+    secrets: inherit
+    with:
+      python-version: ${{ matrix.job-configs.python-version }}
+
+  compile-integration-tests:
+    name: cd ${{ matrix.job-configs.working-directory }}
+    needs: [ build ]
+    if: ${{ needs.build.outputs.compile-integration-tests != '[]' }}
+    strategy:
+      matrix:
+        job-configs: ${{ fromJson(needs.build.outputs.compile-integration-tests) }}
     uses: ./.github/workflows/_compile_integration_test.yml
     with:
-      working-directory: ${{ matrix.working-directory }}
+      working-directory: ${{ matrix.job-configs.working-directory }}
+      python-version: ${{ matrix.job-configs.python-version }}
     secrets: inherit
 
   dependencies:
-    name: cd ${{ matrix.working-directory }}
+    name: cd ${{ matrix.job-configs.working-directory }}
     needs: [ build ]
-    if: ${{ needs.build.outputs.dirs-to-test != '[]' }}
+    if: ${{ needs.build.outputs.dependencies != '[]' }}
     strategy:
       matrix:
-        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-test) }}
+        job-configs: ${{ fromJson(needs.build.outputs.dependencies) }}
     uses: ./.github/workflows/_dependencies.yml
     with:
-      working-directory: ${{ matrix.working-directory }}
+      working-directory: ${{ matrix.job-configs.working-directory }}
+      python-version: ${{ matrix.job-configs.python-version }}
     secrets: inherit
 
   extended-tests:
-    name: "cd ${{ matrix.working-directory }} / make extended_tests #${{ matrix.python-version }}"
+    name: "cd ${{ matrix.job-configs.working-directory }} / make extended_tests #${{ matrix.job-configs.python-version }}"
     needs: [ build ]
-    if: ${{ needs.build.outputs.dirs-to-extended-test != '[]' }}
+    if: ${{ needs.build.outputs.extended-tests != '[]' }}
     strategy:
       matrix:
         # note different variable for extended test dirs
-        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-extended-test) }}
-        python-version:
-          - "3.8"
-          - "3.9"
-          - "3.10"
-          - "3.11"
-          - "3.12"
+        job-configs: ${{ fromJson(needs.build.outputs.extended-tests) }}
     runs-on: ubuntu-latest
     defaults:
       run:
-        working-directory: ${{ matrix.working-directory }}
+        working-directory: ${{ matrix.job-configs.working-directory }}
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ matrix.job-configs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: ${{ matrix.job-configs.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: ${{ matrix.working-directory }}
+          working-directory: ${{ matrix.job-configs.working-directory }}
           cache-key: extended
 
       - name: Install dependencies

README.md

@@ -11,7 +11,6 @@
 [![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)
-[![](https://dcbadge.vercel.app/api/server/6adMQxSpJS?compact=true&style=flat)](https://discord.gg/6adMQxSpJS)
 [![Twitter](https://img.shields.io/twitter/url/https/twitter.com/langchainai.svg?style=social&label=Follow%20%40LangChainAI)](https://twitter.com/langchainai)
 
 Looking for the JS/TS library? Check out [LangChain.js](https://github.com/langchain-ai/langchainjs).

cookbook/README.md

@@ -57,4 +57,5 @@ Notebook | Description
 [two_agent_debate_tools.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/two_agent_debate_tools.ipynb) | Simulate multi-agent dialogues where the agents can utilize various tools.
 [two_player_dnd.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/two_player_dnd.ipynb) | Simulate a two-player dungeons & dragons game, where a dialogue simulator class is used to coordinate the dialogue between the protagonist and the dungeon master.
 [wikibase_agent.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/wikibase_agent.ipynb) | Create a simple wikibase agent that utilizes sparql generation, with testing done on http://wikidata.org.
-[oracleai_demo.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/oracleai_demo.ipynb) | This guide outlines how to utilize Oracle AI Vector Search alongside Langchain for an end-to-end RAG pipeline, providing step-by-step examples. The process includes loading documents from various sources using OracleDocLoader, summarizing them either within or outside the database with OracleSummary, and generating embeddings similarly through OracleEmbeddings. It also covers chunking documents according to specific requirements using Advanced Oracle Capabilities from OracleTextSplitter, and finally, storing and indexing these documents in a Vector Store for querying with OracleVS.
+[oracleai_demo.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/oracleai_demo.ipynb) | This guide outlines how to utilize Oracle AI Vector Search alongside Langchain for an end-to-end RAG pipeline, providing step-by-step examples. The process includes loading documents from various sources using OracleDocLoader, summarizing them either within or outside the database with OracleSummary, and generating embeddings similarly through OracleEmbeddings. It also covers chunking documents according to specific requirements using Advanced Oracle Capabilities from OracleTextSplitter, and finally, storing and indexing these documents in a Vector Store for querying with OracleVS.
+[rag-locally-on-intel-cpu.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/rag-locally-on-intel-cpu.ipynb) | Perform Retrieval-Augmented-Generation (RAG) on locally downloaded open-source models using langchain and open source tools and execute it on Intel Xeon CPU. We showed an example of how to apply RAG on Llama 2 model and enable it to answer the queries related to Intel Q1 2024 earnings release.

cookbook/rag-locally-on-intel-cpu.ipynb

@@ -0,0 +1,756 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "10f50955-be55-422f-8c62-3a32f8cf02ed",
+   "metadata": {},
+   "source": [
+    "# RAG application running locally on Intel Xeon CPU using langchain and open-source models"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "48113be6-44bb-4aac-aed3-76a1365b9561",
+   "metadata": {},
+   "source": [
+    "Author - Pratool Bharti (pratool.bharti@intel.com)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8b10b54b-1572-4ea1-9c1e-1d29fcc3dcd9",
+   "metadata": {},
+   "source": [
+    "In this cookbook, we use langchain tools and open source models to execute locally on CPU. This notebook has been validated to run on Intel Xeon 8480+ CPU. Here we implement a RAG pipeline for Llama2 model to answer questions about Intel Q1 2024 earnings release."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "acadbcec-3468-4926-8ce5-03b678041c0a",
+   "metadata": {},
+   "source": [
+    "**Create a conda or virtualenv environment with python >=3.10 and install following libraries**\n",
+    "<br>\n",
+    "\n",
+    "`pip install --upgrade langchain langchain-community langchainhub langchain-chroma bs4 gpt4all pypdf pysqlite3-binary` <br>\n",
+    "`pip install llama-cpp-python   --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu`"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "84c392c8-700a-42ec-8e94-806597f22e43",
+   "metadata": {},
+   "source": [
+    "**Load pysqlite3 in sys modules since ChromaDB requires sqlite3.**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "145cd491-b388-4ea7-bdc8-2f4995cac6fd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "__import__(\"pysqlite3\")\n",
+    "import sys\n",
+    "\n",
+    "sys.modules[\"sqlite3\"] = sys.modules.pop(\"pysqlite3\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "14dde7e2-b236-49b9-b3a0-08c06410418c",
+   "metadata": {},
+   "source": [
+    "**Import essential components from langchain to load and split data**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "887643ba-249e-48d6-9aa7-d25087e8dfbf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
+    "from langchain_community.document_loaders import PyPDFLoader"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "922c0eba-8736-4de5-bd2f-3d0f00b16e43",
+   "metadata": {},
+   "source": [
+    "**Download Intel Q1 2024 earnings release**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "2d6a2419-5338-4188-8615-a40a65ff8019",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "--2024-07-15 15:04:43--  https://d1io3yog0oux5.cloudfront.net/_11d435a500963f99155ee058df09f574/intel/db/887/9014/earnings_release/Q1+24_EarningsRelease_FINAL.pdf\n",
+      "Resolving proxy-dmz.intel.com (proxy-dmz.intel.com)... 10.7.211.16\n",
+      "Connecting to proxy-dmz.intel.com (proxy-dmz.intel.com)|10.7.211.16|:912... connected.\n",
+      "Proxy request sent, awaiting response... 200 OK\n",
+      "Length: 133510 (130K) [application/pdf]\n",
+      "Saving to: ‘intel_q1_2024_earnings.pdf’\n",
+      "\n",
+      "intel_q1_2024_earni 100%[===================>] 130.38K  --.-KB/s    in 0.005s  \n",
+      "\n",
+      "2024-07-15 15:04:44 (24.6 MB/s) - ‘intel_q1_2024_earnings.pdf’ saved [133510/133510]\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "!wget  'https://d1io3yog0oux5.cloudfront.net/_11d435a500963f99155ee058df09f574/intel/db/887/9014/earnings_release/Q1+24_EarningsRelease_FINAL.pdf' -O intel_q1_2024_earnings.pdf"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e3612627-e105-453d-8a50-bbd6e39dedb5",
+   "metadata": {},
+   "source": [
+    "**Loading earning release pdf document through PyPDFLoader**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "cac6278e-ebad-4224-a062-bf6daca24cb0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = PyPDFLoader(\"intel_q1_2024_earnings.pdf\")\n",
+    "data = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a7dca43b-1c62-41df-90c7-6ed2904f823d",
+   "metadata": {},
+   "source": [
+    "**Splitting entire document in several chunks with each chunk size is 500 tokens**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "4486adbe-0d0e-4685-8c08-c1774ed6e993",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)\n",
+    "all_splits = text_splitter.split_documents(data)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "af142346-e793-4a52-9a56-63e3be416b3d",
+   "metadata": {},
+   "source": [
+    "**Looking at the first split of the document**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "e4240fd1-898e-4bfc-a377-02c9bc25b56e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Document(metadata={'source': 'intel_q1_2024_earnings.pdf', 'page': 0}, page_content='Intel Corporation\\n2200 Mission College Blvd.\\nSanta Clara, CA 95054-1549\\n                                                         \\nNews Release\\n Intel Reports First -Quarter 2024  Financial Results\\nNEWS SUMMARY\\n▪First-quarter revenue of $12.7 billion , up 9%  year over year (YoY).\\n▪First-quarter GAAP earnings (loss) per share (EPS) attributable to Intel was $(0.09) ; non-GAAP EPS \\nattributable to Intel was $0.18 .')"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "all_splits[0]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b88d2632-7c1b-49ef-a691-c0eb67d23e6a",
+   "metadata": {},
+   "source": [
+    "**One of the major step in RAG is to convert each split of document into embeddings and store in a vector database such that searching relevant documents are efficient.** <br>\n",
+    "**For that, importing Chroma vector database from langchain. Also, importing open source GPT4All for embedding models**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "9ff99dd7-9d47-4239-ba0a-d775792334ba",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_chroma import Chroma\n",
+    "from langchain_community.embeddings import GPT4AllEmbeddings"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b5d1f4dd-dd8d-4a20-95d1-2dbdd204375a",
+   "metadata": {},
+   "source": [
+    "**In next step, we will download one of the most popular embedding model \"all-MiniLM-L6-v2\". Find more details of the model at this link https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "05db3494-5d8e-4a13-9941-26330a86f5e5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model_name = \"all-MiniLM-L6-v2.gguf2.f16.gguf\"\n",
+    "gpt4all_kwargs = {\"allow_download\": \"True\"}\n",
+    "embeddings = GPT4AllEmbeddings(model_name=model_name, gpt4all_kwargs=gpt4all_kwargs)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4e53999e-1983-46ac-8039-2783e194c3ae",
+   "metadata": {},
+   "source": [
+    "**Store all the embeddings in the Chroma database**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "0922951a-9ddf-4761-973d-8e9a86f61284",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "vectorstore = Chroma.from_documents(documents=all_splits, embedding=embeddings)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "29f94fa0-6c75-4a65-a1a3-debc75422479",
+   "metadata": {},
+   "source": [
+    "**Now, let's find relevant splits from the documents related to the question**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "88c8152d-ec7a-4f0b-9d86-877789407537",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "4\n"
+     ]
+    }
+   ],
+   "source": [
+    "question = \"What is Intel CCG revenue in Q1 2024\"\n",
+    "docs = vectorstore.similarity_search(question)\n",
+    "print(len(docs))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "53330c6b-cb0f-43f9-b379-2e57ac1e5335",
+   "metadata": {},
+   "source": [
+    "**Look at the first retrieved document from the vector database**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "43a6d94f-b5c4-47b0-a353-2db4c3d24d9c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Document(metadata={'page': 1, 'source': 'intel_q1_2024_earnings.pdf'}, page_content='Client Computing Group (CCG) $7.5 billion up31%\\nData Center and AI (DCAI) $3.0 billion up5%\\nNetwork and Edge (NEX) $1.4 billion down 8%\\nTotal Intel Products revenue $11.9 billion up17%\\nIntel Foundry $4.4 billion down 10%\\nAll other:\\nAltera $342 million down 58%\\nMobileye $239 million down 48%\\nOther $194 million up17%\\nTotal all other revenue $775 million down 46%\\nIntersegment eliminations $(4.4) billion\\nTotal net revenue $12.7 billion up9%\\nIntel Products Highlights')"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "docs[0]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "64ba074f-4b36-442e-b7e2-b26d6e2815c3",
+   "metadata": {},
+   "source": [
+    "**Download Lllama-2 model from Huggingface and store locally** <br>\n",
+    "**You can download different quantization variant of Lllama-2 model from the link below. We are using Q8 version here (7.16GB).** <br>\n",
+    "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c8dd0811-6f43-4bc6-b854-2ab377639c9a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!huggingface-cli download TheBloke/Llama-2-7b-Chat-GGUF llama-2-7b-chat.Q8_0.gguf --local-dir . --local-dir-use-symlinks False"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3895b1f5-f51d-4539-abf0-af33d7ca48ea",
+   "metadata": {},
+   "source": [
+    "**Import langchain components required to load downloaded LLMs model**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "fb087088-aa62-44c0-8356-061e9b9f1186",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.callbacks.manager import CallbackManager\n",
+    "from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
+    "from langchain_community.llms import LlamaCpp"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5a8a111e-2614-4b70-b034-85cd3e7304cb",
+   "metadata": {},
+   "source": [
+    "**Loading the local Lllama-2 model using Llama-cpp library**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "fb917da2-c0d7-4995-b56d-26254276e0da",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "llama_model_loader: loaded meta data with 19 key-value pairs and 291 tensors from llama-2-7b-chat.Q8_0.gguf (version GGUF V2)\n",
+      "llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.\n",
+      "llama_model_loader: - kv   0:                       general.architecture str              = llama\n",
+      "llama_model_loader: - kv   1:                               general.name str              = LLaMA v2\n",
+      "llama_model_loader: - kv   2:                       llama.context_length u32              = 4096\n",
+      "llama_model_loader: - kv   3:                     llama.embedding_length u32              = 4096\n",
+      "llama_model_loader: - kv   4:                          llama.block_count u32              = 32\n",
+      "llama_model_loader: - kv   5:                  llama.feed_forward_length u32              = 11008\n",
+      "llama_model_loader: - kv   6:                 llama.rope.dimension_count u32              = 128\n",
+      "llama_model_loader: - kv   7:                 llama.attention.head_count u32              = 32\n",
+      "llama_model_loader: - kv   8:              llama.attention.head_count_kv u32              = 32\n",
+      "llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32              = 0.000001\n",
+      "llama_model_loader: - kv  10:                          general.file_type u32              = 7\n",
+      "llama_model_loader: - kv  11:                       tokenizer.ggml.model str              = llama\n",
+      "llama_model_loader: - kv  12:                      tokenizer.ggml.tokens arr[str,32000]   = [\"<unk>\", \"<s>\", \"</s>\", \"<0x00>\", \"<...\n",
+      "llama_model_loader: - kv  13:                      tokenizer.ggml.scores arr[f32,32000]   = [0.000000, 0.000000, 0.000000, 0.0000...\n",
+      "llama_model_loader: - kv  14:                  tokenizer.ggml.token_type arr[i32,32000]   = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...\n",
+      "llama_model_loader: - kv  15:                tokenizer.ggml.bos_token_id u32              = 1\n",
+      "llama_model_loader: - kv  16:                tokenizer.ggml.eos_token_id u32              = 2\n",
+      "llama_model_loader: - kv  17:            tokenizer.ggml.unknown_token_id u32              = 0\n",
+      "llama_model_loader: - kv  18:               general.quantization_version u32              = 2\n",
+      "llama_model_loader: - type  f32:   65 tensors\n",
+      "llama_model_loader: - type q8_0:  226 tensors\n",
+      "llm_load_vocab: special tokens cache size = 259\n",
+      "llm_load_vocab: token to piece cache size = 0.1684 MB\n",
+      "llm_load_print_meta: format           = GGUF V2\n",
+      "llm_load_print_meta: arch             = llama\n",
+      "llm_load_print_meta: vocab type       = SPM\n",
+      "llm_load_print_meta: n_vocab          = 32000\n",
+      "llm_load_print_meta: n_merges         = 0\n",
+      "llm_load_print_meta: vocab_only       = 0\n",
+      "llm_load_print_meta: n_ctx_train      = 4096\n",
+      "llm_load_print_meta: n_embd           = 4096\n",
+      "llm_load_print_meta: n_layer          = 32\n",
+      "llm_load_print_meta: n_head           = 32\n",
+      "llm_load_print_meta: n_head_kv        = 32\n",
+      "llm_load_print_meta: n_rot            = 128\n",
+      "llm_load_print_meta: n_swa            = 0\n",
+      "llm_load_print_meta: n_embd_head_k    = 128\n",
+      "llm_load_print_meta: n_embd_head_v    = 128\n",
+      "llm_load_print_meta: n_gqa            = 1\n",
+      "llm_load_print_meta: n_embd_k_gqa     = 4096\n",
+      "llm_load_print_meta: n_embd_v_gqa     = 4096\n",
+      "llm_load_print_meta: f_norm_eps       = 0.0e+00\n",
+      "llm_load_print_meta: f_norm_rms_eps   = 1.0e-06\n",
+      "llm_load_print_meta: f_clamp_kqv      = 0.0e+00\n",
+      "llm_load_print_meta: f_max_alibi_bias = 0.0e+00\n",
+      "llm_load_print_meta: f_logit_scale    = 0.0e+00\n",
+      "llm_load_print_meta: n_ff             = 11008\n",
+      "llm_load_print_meta: n_expert         = 0\n",
+      "llm_load_print_meta: n_expert_used    = 0\n",
+      "llm_load_print_meta: causal attn      = 1\n",
+      "llm_load_print_meta: pooling type     = 0\n",
+      "llm_load_print_meta: rope type        = 0\n",
+      "llm_load_print_meta: rope scaling     = linear\n",
+      "llm_load_print_meta: freq_base_train  = 10000.0\n",
+      "llm_load_print_meta: freq_scale_train = 1\n",
+      "llm_load_print_meta: n_ctx_orig_yarn  = 4096\n",
+      "llm_load_print_meta: rope_finetuned   = unknown\n",
+      "llm_load_print_meta: ssm_d_conv       = 0\n",
+      "llm_load_print_meta: ssm_d_inner      = 0\n",
+      "llm_load_print_meta: ssm_d_state      = 0\n",
+      "llm_load_print_meta: ssm_dt_rank      = 0\n",
+      "llm_load_print_meta: model type       = 7B\n",
+      "llm_load_print_meta: model ftype      = Q8_0\n",
+      "llm_load_print_meta: model params     = 6.74 B\n",
+      "llm_load_print_meta: model size       = 6.67 GiB (8.50 BPW) \n",
+      "llm_load_print_meta: general.name     = LLaMA v2\n",
+      "llm_load_print_meta: BOS token        = 1 '<s>'\n",
+      "llm_load_print_meta: EOS token        = 2 '</s>'\n",
+      "llm_load_print_meta: UNK token        = 0 '<unk>'\n",
+      "llm_load_print_meta: LF token         = 13 '<0x0A>'\n",
+      "llm_load_print_meta: max token length = 48\n",
+      "llm_load_tensors: ggml ctx size =    0.14 MiB\n",
+      "llm_load_tensors:        CPU buffer size =  6828.64 MiB\n",
+      "...................................................................................................\n",
+      "llama_new_context_with_model: n_ctx      = 2048\n",
+      "llama_new_context_with_model: n_batch    = 512\n",
+      "llama_new_context_with_model: n_ubatch   = 512\n",
+      "llama_new_context_with_model: flash_attn = 0\n",
+      "llama_new_context_with_model: freq_base  = 10000.0\n",
+      "llama_new_context_with_model: freq_scale = 1\n",
+      "llama_kv_cache_init:        CPU KV buffer size =  1024.00 MiB\n",
+      "llama_new_context_with_model: KV self size  = 1024.00 MiB, K (f16):  512.00 MiB, V (f16):  512.00 MiB\n",
+      "llama_new_context_with_model:        CPU  output buffer size =     0.12 MiB\n",
+      "llama_new_context_with_model:        CPU compute buffer size =   164.01 MiB\n",
+      "llama_new_context_with_model: graph nodes  = 1030\n",
+      "llama_new_context_with_model: graph splits = 1\n",
+      "AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 1 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 0 | \n",
+      "Model metadata: {'tokenizer.ggml.unknown_token_id': '0', 'tokenizer.ggml.eos_token_id': '2', 'general.architecture': 'llama', 'llama.context_length': '4096', 'general.name': 'LLaMA v2', 'llama.embedding_length': '4096', 'llama.feed_forward_length': '11008', 'llama.attention.layer_norm_rms_epsilon': '0.000001', 'llama.rope.dimension_count': '128', 'llama.attention.head_count': '32', 'tokenizer.ggml.bos_token_id': '1', 'llama.block_count': '32', 'llama.attention.head_count_kv': '32', 'general.quantization_version': '2', 'tokenizer.ggml.model': 'llama', 'general.file_type': '7'}\n",
+      "Using fallback chat format: llama-2\n"
+     ]
+    }
+   ],
+   "source": [
+    "llm = LlamaCpp(\n",
+    "    model_path=\"llama-2-7b-chat.Q8_0.gguf\",\n",
+    "    n_gpu_layers=-1,\n",
+    "    n_batch=512,\n",
+    "    n_ctx=2048,\n",
+    "    f16_kv=True,  # MUST set to True, otherwise you will run into problem after a couple of calls\n",
+    "    callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]),\n",
+    "    verbose=True,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "43e06f56-ef97-451b-87d9-8465ea442aed",
+   "metadata": {},
+   "source": [
+    "**Now let's ask the same question to Llama model without showing them the earnings release.**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "1033dd82-5532-437d-a548-27695e109589",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "?\n",
+      "(NASDAQ:INTC)\n",
+      "Intel's CCG (Client Computing Group) revenue for Q1 2024 was $9.6 billion, a decrease of 35% from the previous quarter and a decrease of 42% from the same period last year."
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "llama_print_timings:        load time =     131.20 ms\n",
+      "llama_print_timings:      sample time =      16.05 ms /    68 runs   (    0.24 ms per token,  4236.76 tokens per second)\n",
+      "llama_print_timings: prompt eval time =     131.14 ms /    16 tokens (    8.20 ms per token,   122.01 tokens per second)\n",
+      "llama_print_timings:        eval time =    3225.00 ms /    67 runs   (   48.13 ms per token,    20.78 tokens per second)\n",
+      "llama_print_timings:       total time =    3466.40 ms /    83 tokens\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\"?\\n(NASDAQ:INTC)\\nIntel's CCG (Client Computing Group) revenue for Q1 2024 was $9.6 billion, a decrease of 35% from the previous quarter and a decrease of 42% from the same period last year.\""
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "llm.invoke(question)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "75f5cb10-746f-4e37-9386-b85a4d2b84ef",
+   "metadata": {},
+   "source": [
+    "**As you can see, model is giving wrong information. Correct asnwer is CCG revenue in Q1 2024 is $7.5B. Now let's apply RAG using the earning release document**"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0f4150ec-5692-4756-b11a-22feb7ab88ff",
+   "metadata": {},
+   "source": [
+    "**in RAG, we modify the input prompt by adding relevent documents with the question. Here, we use one of the popular RAG prompt**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "226c14b0-f43e-4a1f-a1e4-04731d467ec4",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[HumanMessagePromptTemplate(prompt=PromptTemplate(input_variables=['context', 'question'], template=\"You are an assistant for question-answering tasks. Use the following pieces of retrieved context to answer the question. If you don't know the answer, just say that you don't know. Use three sentences maximum and keep the answer concise.\\nQuestion: {question} \\nContext: {context} \\nAnswer:\"))]"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain import hub\n",
+    "\n",
+    "rag_prompt = hub.pull(\"rlm/rag-prompt\")\n",
+    "rag_prompt.messages"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "77deb6a0-0950-450a-916a-f2a029676c20",
+   "metadata": {},
+   "source": [
+    "**Appending all retreived documents in a single document**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "2dbc3327-6ef3-4c1f-8797-0c71964b0921",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def format_docs(docs):\n",
+    "    return \"\\n\\n\".join(doc.page_content for doc in docs)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2e2d9f18-49d0-43a3-bea8-78746ffa86b7",
+   "metadata": {},
+   "source": [
+    "**The last step is to create a chain using langchain tool that will create an e2e pipeline. It will take question and context as an input.**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "427379c2-51ff-4e0f-8278-a45221363299",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.runnables import RunnablePassthrough, RunnablePick\n",
+    "\n",
+    "# Chain\n",
+    "chain = (\n",
+    "    RunnablePassthrough.assign(context=RunnablePick(\"context\") | format_docs)\n",
+    "    | rag_prompt\n",
+    "    | llm\n",
+    "    | StrOutputParser()\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "095d6280-c949-4d00-8e32-8895a82d245f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Llama.generate: prefix-match hit\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " Based on the provided context, Intel CCG revenue in Q1 2024 was $7.5 billion up 31%."
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "llama_print_timings:        load time =     131.20 ms\n",
+      "llama_print_timings:      sample time =       7.74 ms /    31 runs   (    0.25 ms per token,  4004.13 tokens per second)\n",
+      "llama_print_timings: prompt eval time =    2529.41 ms /   674 tokens (    3.75 ms per token,   266.46 tokens per second)\n",
+      "llama_print_timings:        eval time =    1542.94 ms /    30 runs   (   51.43 ms per token,    19.44 tokens per second)\n",
+      "llama_print_timings:       total time =    4123.68 ms /   704 tokens\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "' Based on the provided context, Intel CCG revenue in Q1 2024 was $7.5 billion up 31%.'"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"context\": docs, \"question\": question})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "638364b2-6bd2-4471-9961-d3a1d1b9d4ee",
+   "metadata": {},
+   "source": [
+    "**Now we see the results are correct as it is mentioned in earnings release.** <br>\n",
+    "**To further automate, we will create a chain that will take input as question and retriever so that we don't need to retrieve documents seperately**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "4654e5b7-635f-4767-8b31-4c430164cdd5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "retriever = vectorstore.as_retriever()\n",
+    "qa_chain = (\n",
+    "    {\"context\": retriever | format_docs, \"question\": RunnablePassthrough()}\n",
+    "    | rag_prompt\n",
+    "    | llm\n",
+    "    | StrOutputParser()\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0979f393-fd0a-4e82-b844-68371c6ad68f",
+   "metadata": {},
+   "source": [
+    "**Now we only need to pass the question to the chain and it will fetch the contexts directly from the vector database to generate the answer**\n",
+    "<br>\n",
+    "**Let's try with another question**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "3ea07b82-e6ec-4084-85f4-191373530172",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Llama.generate: prefix-match hit\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " According to the provided context, Intel DCAI revenue in Q1 2024 was $3.0 billion up 5%."
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "llama_print_timings:        load time =     131.20 ms\n",
+      "llama_print_timings:      sample time =       6.28 ms /    31 runs   (    0.20 ms per token,  4937.88 tokens per second)\n",
+      "llama_print_timings: prompt eval time =    2681.93 ms /   730 tokens (    3.67 ms per token,   272.19 tokens per second)\n",
+      "llama_print_timings:        eval time =    1471.07 ms /    30 runs   (   49.04 ms per token,    20.39 tokens per second)\n",
+      "llama_print_timings:       total time =    4206.77 ms /   760 tokens\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "' According to the provided context, Intel DCAI revenue in Q1 2024 was $3.0 billion up 5%.'"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "qa_chain.invoke(\"what is Intel DCAI revenue in Q1 2024?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9407f2a0-4a35-4315-8e96-02fcb80f210c",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "rag-on-intel",
+   "language": "python",
+   "name": "rag-on-intel"
+  },
+  "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/Makefile

@@ -13,7 +13,7 @@ OUTPUT_NEW_DOCS_DIR = $(OUTPUT_NEW_DIR)/docs
 
 PYTHON = .venv/bin/python
 
-PARTNER_DEPS_LIST := $(shell find ../libs/partners -mindepth 1 -maxdepth 1 -type d -exec test -e "{}/pyproject.toml" \; -print | grep -vE "airbyte|ibm" | tr '\n' ' ')
+PARTNER_DEPS_LIST := $(shell find ../libs/partners -mindepth 1 -maxdepth 1 -type d -exec test -e "{}/pyproject.toml" \; -print | grep -vE "airbyte|ibm|couchbase" | tr '\n' ' ')
 
 PORT ?= 3001
 

docs/api_reference/conf.py

@@ -178,3 +178,10 @@ autosummary_generate = True
 
 html_copy_source = False
 html_show_sourcelink = False
+
+# Set canonical URL from the Read the Docs Domain
+html_baseurl = os.environ.get("READTHEDOCS_CANONICAL_URL", "")
+
+# Tell Jinja2 templates the build is running on Read the Docs
+if os.environ.get("READTHEDOCS", "") == "True":
+    html_context["READTHEDOCS"] = True

docs/api_reference/create_api_rst.py

@@ -78,7 +78,7 @@ def _load_module_members(module_path: str, namespace: str) -> ModuleMembers:
             continue
 
         if inspect.isclass(type_):
-            # The clasification of the class is used to select a template
+            # The type of the class is used to select a template
             # for the object when rendering the documentation.
             # See `templates` directory for defined templates.
             # This is a hacky solution to distinguish between different

docs/docs/concepts.mdx

@@ -55,6 +55,7 @@ A developer platform that lets you debug, test, evaluate, and monitor LLM applic
     dark: useBaseUrl('/svg/langchain_stack_062024_dark.svg'),
   }}
   title="LangChain Framework Overview"
+  style={{ width: "100%" }}
 />
 
 ## LangChain Expression Language (LCEL)
@@ -85,8 +86,13 @@ Input and output schemas give every LCEL chain Pydantic and JSONSchema schemas i
 As your chains get more and more complex, it becomes increasingly important to understand what exactly is happening at every step.
 With LCEL, **all** steps are automatically logged to [LangSmith](https://docs.smith.langchain.com/) for maximum observability and debuggability.
 
-[**Seamless LangServe deployment**](/docs/langserve)
-Any chain created with LCEL can be easily deployed using [LangServe](/docs/langserve).
+LCEL aims to provide consistency around behavior and customization over legacy subclassed chains such as `LLMChain` and
+`ConversationalRetrievalChain`. Many of these legacy chains hide important details like prompts, and as a wider variety
+of viable models emerge, customization has become more and more important.
+
+If you are currently using one of these legacy chains, please see [this guide for guidance on how to migrate](/docs/how_to/migrate_chains/).
+
+For guides on how to do specific tasks with LCEL, check out [the relevant how-to guides](/docs/how_to/#langchain-expression-language-lcel).
 
 ### Runnable interface
 <span data-heading-keywords="invoke,runnable"></span>
@@ -516,6 +522,8 @@ Generally, when designing tools to be used by a chat model or LLM, it is importa
 
 For specifics on how to use tools, see the [relevant how-to guides here](/docs/how_to/#tools).
 
+To use an existing pre-built tool, see [here](/docs/integrations/tools/) for a list of pre-built tools.
+
 ### Toolkits
 
 Toolkits are collections of tools that are designed to be used together for specific tasks. They have convenient loading methods.
@@ -814,7 +822,7 @@ We recommend this method as a starting point when working with structured output
 - If multiple underlying techniques are supported, you can supply a `method` parameter to
 [toggle which one is used](/docs/how_to/structured_output/#advanced-specifying-the-method-for-structuring-outputs).
 
-You may want or need to use other techiniques if:
+You may want or need to use other techniques if:
 
 - The chat model you are using does not support tool calling.
 - You are working with very complex schemas and the model is having trouble generating outputs that conform.
@@ -1015,7 +1023,7 @@ See our [blog post overview](https://blog.langchain.dev/query-construction/) and
 
 #### Indexing
 
-Fouth, consider the design of your document index. A simple and powerful idea is to **decouple the documents that you index for retrieval from the documents that you pass to the LLM for generation.** Indexing frequently uses embedding models with vector stores, which [compress the semantic information in documents to fixed-size vectors](/docs/concepts/#embedding-models).
+Fourth, consider the design of your document index. A simple and powerful idea is to **decouple the documents that you index for retrieval from the documents that you pass to the LLM for generation.** Indexing frequently uses embedding models with vector stores, which [compress the semantic information in documents to fixed-size vectors](/docs/concepts/#embedding-models).
 
 Many RAG approaches focus on splitting documents into chunks and retrieving some number based on similarity to an input question for the LLM. But chunk size and chunk number can be difficult to set and affect results if they do not provide full context for the LLM to answer a question. Furthermore, LLMs are increasingly capable of processing millions of tokens. 
 
@@ -1123,7 +1131,7 @@ Table columns:
 | Token    | [many classes](/docs/how_to/split_by_token/)                                                                                                                                  | Tokens                                                                                                          |               | Splits text on tokens. There exist a few different ways to measure tokens.                                                                                                                                                                                                   |
 | Character  | [CharacterTextSplitter](/docs/how_to/character_text_splitter/)                                                                                                                | A user defined character                                                                                        |               | Splits text based on a user defined character. One of the simpler methods.                                                                                                                                                                                                   |
 | Semantic Chunker (Experimental) | [SemanticChunker](/docs/how_to/semantic-chunker/)                                                                                                                             | Sentences                                                                                                       |               | First splits on sentences. Then combines ones next to each other if they are semantically similar enough. Taken from [Greg Kamradt](https://github.com/FullStackRetrieval-com/RetrievalTutorials/blob/main/tutorials/LevelsOfTextSplitting/5_Levels_Of_Text_Splitting.ipynb) |
-| Integration: AI21 Semantic | [AI21SemanticTextSplitter](/docs/integrations/document_transformers/ai21_semantic_text_splitter/)                                                                                                                    |    ✅           | Identifies distinct topics that form coherent pieces of text and splits along those.                                                                                                                                                                                         |
+| Integration: AI21 Semantic | [AI21SemanticTextSplitter](/docs/integrations/document_transformers/ai21_semantic_text_splitter/)                                                                                                 |                  |    ✅           | Identifies distinct topics that form coherent pieces of text and splits along those.                                                                                                                                                                                         |
 
 ### Evaluation
 <span data-heading-keywords="evaluation,evaluate"></span>

docs/docs/contributing/documentation/style_guide.mdx

@@ -33,6 +33,8 @@ Some examples include:
 
 - [Build a Simple LLM Application with LCEL](/docs/tutorials/llm_chain/)
 - [Build a Retrieval Augmented Generation (RAG) App](/docs/tutorials/rag/)
+
+A good structural rule of thumb is to follow the structure of this [example from Numpy](https://numpy.org/numpy-tutorials/content/tutorial-svd.html).
   
 Here are some high-level tips on writing a good tutorial:
 

docs/docs/contributing/integrations.mdx

@@ -11,7 +11,7 @@ There are a few different places you can contribute integrations for LangChain:
 - **Community**: For lighter-weight integrations that are primarily maintained by LangChain and the Open Source Community.
 - **Partner Packages**: For independent packages that are co-maintained by LangChain and a partner.
 
-For the most part, new integrations should be added to the Community package. Partner packages require more maintenance as separate packages, so please confirm with the LangChain team before creating a new partner package.
+For the most part, **new integrations should be added to the Community package**. Partner packages require more maintenance as separate packages, so please confirm with the LangChain team before creating a new partner package.
 
 In the following sections, we'll walk through how to contribute to each of these packages from a fake company, `Parrot Link AI`.
 
@@ -60,6 +60,10 @@ And add documentation to:
 
 ## Partner package in LangChain repo
 
+:::caution
+Before starting a **partner** package, please confirm your intent with the LangChain team. Partner packages require more maintenance as separate packages, so we will close PRs that add new partner packages without prior discussion. See the above section for how to add a community integration.
+:::
+
 Partner packages can be hosted in the `LangChain` monorepo or in an external repo.
 
 Partner package in the `LangChain` repo is placed in `libs/partners/{partner}` 

docs/docs/how_to/callbacks_custom_events.ipynb

@@ -0,0 +1,342 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# How to dispatch custom callback events\n",
+    "\n",
+    ":::info Prerequisites\n",
+    "\n",
+    "This guide assumes familiarity with the following concepts:\n",
+    "\n",
+    "- [Callbacks](/docs/concepts/#callbacks)\n",
+    "- [Custom callback handlers](/docs/how_to/custom_callbacks)\n",
+    "- [Astream Events API](/docs/concepts/#astream_events) the `astream_events` method will surface custom callback events.\n",
+    ":::\n",
+    "\n",
+    "In some situations, you may want to dipsatch a custom callback event from within a [Runnable](/docs/concepts/#runnable-interface) so it can be surfaced\n",
+    "in a custom callback handler or via the [Astream Events API](/docs/concepts/#astream_events).\n",
+    "\n",
+    "For example, if you have a long running tool with multiple steps, you can dispatch custom events between the steps and use these custom events to monitor progress.\n",
+    "You could also surface these custom events to an end user of your application to show them how the current task is progressing.\n",
+    "\n",
+    "To dispatch a custom event you need to decide on two attributes for the event: the `name` and the `data`.\n",
+    "\n",
+    "| Attribute | Type | Description                                                                                              |\n",
+    "|-----------|------|----------------------------------------------------------------------------------------------------------|\n",
+    "| name      | str  | A user defined name for the event.                                                                       |\n",
+    "| data      | Any  | The data associated with the event. This can be anything, though we suggest making it JSON serializable. |\n",
+    "\n",
+    "\n",
+    ":::{.callout-important}\n",
+    "* Dispatching custom callback events requires `langchain-core>=0.2.15`.\n",
+    "* Custom callback events can only be dispatched from within an existing `Runnable`.\n",
+    "* If using `astream_events`, you must use `version='v2'` to see custom events.\n",
+    "* Sending or rendering custom callbacks events in LangSmith is not yet supported.\n",
+    ":::\n",
+    "\n",
+    "\n",
+    ":::caution COMPATIBILITY\n",
+    "LangChain cannot automatically propagate configuration, including callbacks necessary for astream_events(), to child runnables if you are running async code in python<=3.10. This is a common reason why you may fail to see events being emitted from custom runnables or tools.\n",
+    "\n",
+    "If you are running python<=3.10, you will need to manually propagate the `RunnableConfig` object to the child runnable in async environments. For an example of how to manually propagate the config, see the implementation of the `bar` RunnableLambda below.\n",
+    "\n",
+    "If you are running python>=3.11, the `RunnableConfig` will automatically propagate to child runnables in async environment. However, it is still a good idea to propagate the `RunnableConfig` manually if your code may run in other Python versions.\n",
+    ":::"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# | output: false\n",
+    "# | echo: false\n",
+    "\n",
+    "%pip install -qU langchain-core"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Astream Events API\n",
+    "\n",
+    "The most useful way to consume custom events is via the [Astream Events API](/docs/concepts/#astream_events).\n",
+    "\n",
+    "We can use the `async` `adispatch_custom_event` API to emit custom events in an async setting. \n",
+    "\n",
+    "\n",
+    ":::{.callout-important}\n",
+    "\n",
+    "To see custom events via the astream events API, you need to use the newer `v2` API of `astream_events`.\n",
+    ":::"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'event': 'on_chain_start', 'data': {'input': 'hello world'}, 'name': 'foo', 'tags': [], 'run_id': 'f354ffe8-4c22-4881-890a-c1cad038a9a6', 'metadata': {}, 'parent_ids': []}\n",
+      "{'event': 'on_custom_event', 'run_id': 'f354ffe8-4c22-4881-890a-c1cad038a9a6', 'name': 'event1', 'tags': [], 'metadata': {}, 'data': {'x': 'hello world'}, 'parent_ids': []}\n",
+      "{'event': 'on_custom_event', 'run_id': 'f354ffe8-4c22-4881-890a-c1cad038a9a6', 'name': 'event2', 'tags': [], 'metadata': {}, 'data': 5, 'parent_ids': []}\n",
+      "{'event': 'on_chain_stream', 'run_id': 'f354ffe8-4c22-4881-890a-c1cad038a9a6', 'name': 'foo', 'tags': [], 'metadata': {}, 'data': {'chunk': 'hello world'}, 'parent_ids': []}\n",
+      "{'event': 'on_chain_end', 'data': {'output': 'hello world'}, 'run_id': 'f354ffe8-4c22-4881-890a-c1cad038a9a6', 'name': 'foo', 'tags': [], 'metadata': {}, 'parent_ids': []}\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain_core.callbacks.manager import (\n",
+    "    adispatch_custom_event,\n",
+    ")\n",
+    "from langchain_core.runnables import RunnableLambda\n",
+    "from langchain_core.runnables.config import RunnableConfig\n",
+    "\n",
+    "\n",
+    "@RunnableLambda\n",
+    "async def foo(x: str) -> str:\n",
+    "    await adispatch_custom_event(\"event1\", {\"x\": x})\n",
+    "    await adispatch_custom_event(\"event2\", 5)\n",
+    "    return x\n",
+    "\n",
+    "\n",
+    "async for event in foo.astream_events(\"hello world\", version=\"v2\"):\n",
+    "    print(event)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "In python <= 3.10, you must propagate the config manually!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'event': 'on_chain_start', 'data': {'input': 'hello world'}, 'name': 'bar', 'tags': [], 'run_id': 'c787b09d-698a-41b9-8290-92aaa656f3e7', 'metadata': {}, 'parent_ids': []}\n",
+      "{'event': 'on_custom_event', 'run_id': 'c787b09d-698a-41b9-8290-92aaa656f3e7', 'name': 'event1', 'tags': [], 'metadata': {}, 'data': {'x': 'hello world'}, 'parent_ids': []}\n",
+      "{'event': 'on_custom_event', 'run_id': 'c787b09d-698a-41b9-8290-92aaa656f3e7', 'name': 'event2', 'tags': [], 'metadata': {}, 'data': 5, 'parent_ids': []}\n",
+      "{'event': 'on_chain_stream', 'run_id': 'c787b09d-698a-41b9-8290-92aaa656f3e7', 'name': 'bar', 'tags': [], 'metadata': {}, 'data': {'chunk': 'hello world'}, 'parent_ids': []}\n",
+      "{'event': 'on_chain_end', 'data': {'output': 'hello world'}, 'run_id': 'c787b09d-698a-41b9-8290-92aaa656f3e7', 'name': 'bar', 'tags': [], 'metadata': {}, 'parent_ids': []}\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain_core.callbacks.manager import (\n",
+    "    adispatch_custom_event,\n",
+    ")\n",
+    "from langchain_core.runnables import RunnableLambda\n",
+    "from langchain_core.runnables.config import RunnableConfig\n",
+    "\n",
+    "\n",
+    "@RunnableLambda\n",
+    "async def bar(x: str, config: RunnableConfig) -> str:\n",
+    "    \"\"\"An example that shows how to manually propagate config.\n",
+    "\n",
+    "    You must do this if you're running python<=3.10.\n",
+    "    \"\"\"\n",
+    "    await adispatch_custom_event(\"event1\", {\"x\": x}, config=config)\n",
+    "    await adispatch_custom_event(\"event2\", 5, config=config)\n",
+    "    return x\n",
+    "\n",
+    "\n",
+    "async for event in bar.astream_events(\"hello world\", version=\"v2\"):\n",
+    "    print(event)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Async Callback Handler\n",
+    "\n",
+    "You can also consume the dispatched event via an async callback handler."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Received event event1 with data: {'x': 1}, with tags: ['foo', 'bar'], with metadata: {} and run_id: a62b84be-7afd-4829-9947-7165df1f37d9\n",
+      "Received event event2 with data: 5, with tags: ['foo', 'bar'], with metadata: {} and run_id: a62b84be-7afd-4829-9947-7165df1f37d9\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "1"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from typing import Any, Dict, List, Optional\n",
+    "from uuid import UUID\n",
+    "\n",
+    "from langchain_core.callbacks import AsyncCallbackHandler\n",
+    "from langchain_core.callbacks.manager import (\n",
+    "    adispatch_custom_event,\n",
+    ")\n",
+    "from langchain_core.runnables import RunnableLambda\n",
+    "from langchain_core.runnables.config import RunnableConfig\n",
+    "\n",
+    "\n",
+    "class AsyncCustomCallbackHandler(AsyncCallbackHandler):\n",
+    "    async def on_custom_event(\n",
+    "        self,\n",
+    "        name: str,\n",
+    "        data: Any,\n",
+    "        *,\n",
+    "        run_id: UUID,\n",
+    "        tags: Optional[List[str]] = None,\n",
+    "        metadata: Optional[Dict[str, Any]] = None,\n",
+    "        **kwargs: Any,\n",
+    "    ) -> None:\n",
+    "        print(\n",
+    "            f\"Received event {name} with data: {data}, with tags: {tags}, with metadata: {metadata} and run_id: {run_id}\"\n",
+    "        )\n",
+    "\n",
+    "\n",
+    "@RunnableLambda\n",
+    "async def bar(x: str, config: RunnableConfig) -> str:\n",
+    "    \"\"\"An example that shows how to manually propagate config.\n",
+    "\n",
+    "    You must do this if you're running python<=3.10.\n",
+    "    \"\"\"\n",
+    "    await adispatch_custom_event(\"event1\", {\"x\": x}, config=config)\n",
+    "    await adispatch_custom_event(\"event2\", 5, config=config)\n",
+    "    return x\n",
+    "\n",
+    "\n",
+    "async_handler = AsyncCustomCallbackHandler()\n",
+    "await foo.ainvoke(1, {\"callbacks\": [async_handler], \"tags\": [\"foo\", \"bar\"]})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Sync Callback Handler\n",
+    "\n",
+    "Let's see how to emit custom events in a sync environment using `dispatch_custom_event`.\n",
+    "\n",
+    "You **must** call `dispatch_custom_event` from within an existing `Runnable`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Received event event1 with data: {'x': 1}, with tags: ['foo', 'bar'], with metadata: {} and run_id: 27b5ce33-dc26-4b34-92dd-08a89cb22268\n",
+      "Received event event2 with data: {'x': 1}, with tags: ['foo', 'bar'], with metadata: {} and run_id: 27b5ce33-dc26-4b34-92dd-08a89cb22268\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "1"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from typing import Any, Dict, List, Optional\n",
+    "from uuid import UUID\n",
+    "\n",
+    "from langchain_core.callbacks import BaseCallbackHandler\n",
+    "from langchain_core.callbacks.manager import (\n",
+    "    dispatch_custom_event,\n",
+    ")\n",
+    "from langchain_core.runnables import RunnableLambda\n",
+    "from langchain_core.runnables.config import RunnableConfig\n",
+    "\n",
+    "\n",
+    "class CustomHandler(BaseCallbackHandler):\n",
+    "    def on_custom_event(\n",
+    "        self,\n",
+    "        name: str,\n",
+    "        data: Any,\n",
+    "        *,\n",
+    "        run_id: UUID,\n",
+    "        tags: Optional[List[str]] = None,\n",
+    "        metadata: Optional[Dict[str, Any]] = None,\n",
+    "        **kwargs: Any,\n",
+    "    ) -> None:\n",
+    "        print(\n",
+    "            f\"Received event {name} with data: {data}, with tags: {tags}, with metadata: {metadata} and run_id: {run_id}\"\n",
+    "        )\n",
+    "\n",
+    "\n",
+    "@RunnableLambda\n",
+    "def foo(x: int, config: RunnableConfig) -> int:\n",
+    "    dispatch_custom_event(\"event1\", {\"x\": x})\n",
+    "    dispatch_custom_event(\"event2\", {\"x\": x})\n",
+    "    return x\n",
+    "\n",
+    "\n",
+    "handler = CustomHandler()\n",
+    "foo.invoke(1, {\"callbacks\": [handler], \"tags\": [\"foo\", \"bar\"]})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Next steps\n",
+    "\n",
+    "You've seen how to emit custom events, you can check out the more in depth guide for [astream events](/docs/how_to/streaming/#using-stream-events) which is the easiest way to leverage custom events."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

docs/docs/how_to/chat_models_universal_init.ipynb

@@ -15,6 +15,12 @@
     "\n",
     "Make sure you have the integration packages installed for any model providers you want to support. E.g. you should have `langchain-openai` installed to init an OpenAI model.\n",
     "\n",
+    ":::\n",
+    "\n",
+    ":::info Requires ``langchain >= 0.2.8``\n",
+    "\n",
+    "This functionality was added in ``langchain-core == 0.2.8``. Please make sure your package is up to date.\n",
+    "\n",
     ":::"
    ]
   },
@@ -25,7 +31,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install -qU langchain langchain-openai langchain-anthropic langchain-google-vertexai"
+    "%pip install -qU langchain>=0.2.8 langchain-openai langchain-anthropic langchain-google-vertexai"
    ]
   },
   {
@@ -76,32 +82,6 @@
     "print(\"Gemini 1.5: \" + gemini_15.invoke(\"what's your name\").content + \"\\n\")"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "fff9a4c8-b6ee-4a1a-8d3d-0ecaa312d4ed",
-   "metadata": {},
-   "source": [
-    "## Simple config example"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "75c25d39-bf47-4b51-a6c6-64d9c572bfd6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "user_config = {\n",
-    "    \"model\": \"...user-specified...\",\n",
-    "    \"model_provider\": \"...user-specified...\",\n",
-    "    \"temperature\": 0,\n",
-    "    \"max_tokens\": 1000,\n",
-    "}\n",
-    "\n",
-    "llm = init_chat_model(**user_config)\n",
-    "llm.invoke(\"what's your name\")"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "f811f219-5e78-4b62-b495-915d52a22532",
@@ -125,12 +105,215 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "da07b5c0-d2e6-42e4-bfcd-2efcfaae6221",
+   "cell_type": "markdown",
+   "id": "476a44db-c50d-4846-951d-0f1c9ba8bbaa",
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "source": [
+    "## Creating a configurable model\n",
+    "\n",
+    "You can also create a runtime-configurable model by specifying `configurable_fields`. If you don't specify a `model` value, then \"model\" and \"model_provider\" be configurable by default."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "6c037f27-12d7-4e83-811e-4245c0e3ba58",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"I'm an AI language model created by OpenAI, and I don't have a personal name. You can call me Assistant or any other name you prefer! How can I assist you today?\", response_metadata={'token_usage': {'completion_tokens': 37, 'prompt_tokens': 11, 'total_tokens': 48}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_d576307f90', 'finish_reason': 'stop', 'logprobs': None}, id='run-5428ab5c-b5c0-46de-9946-5d4ca40dbdc8-0', usage_metadata={'input_tokens': 11, 'output_tokens': 37, 'total_tokens': 48})"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "configurable_model = init_chat_model(temperature=0)\n",
+    "\n",
+    "configurable_model.invoke(\n",
+    "    \"what's your name\", config={\"configurable\": {\"model\": \"gpt-4o\"}}\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "321e3036-abd2-4e1f-bcc6-606efd036954",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"My name is Claude. It's nice to meet you!\", response_metadata={'id': 'msg_012XvotUJ3kGLXJUWKBVxJUi', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 11, 'output_tokens': 15}}, id='run-1ad1eefe-f1c6-4244-8bc6-90e2cb7ee554-0', usage_metadata={'input_tokens': 11, 'output_tokens': 15, 'total_tokens': 26})"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "configurable_model.invoke(\n",
+    "    \"what's your name\", config={\"configurable\": {\"model\": \"claude-3-5-sonnet-20240620\"}}\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7f3b3d4a-4066-45e4-8297-ea81ac8e70b7",
+   "metadata": {},
+   "source": [
+    "### Configurable model with default values\n",
+    "\n",
+    "We can create a configurable model with default model values, specify which parameters are configurable, and add prefixes to configurable params:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "814a2289-d0db-401e-b555-d5116112b413",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"I'm an AI language model created by OpenAI, and I don't have a personal name. You can call me Assistant or any other name you prefer! How can I assist you today?\", response_metadata={'token_usage': {'completion_tokens': 37, 'prompt_tokens': 11, 'total_tokens': 48}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_ce0793330f', 'finish_reason': 'stop', 'logprobs': None}, id='run-3923e328-7715-4cd6-b215-98e4b6bf7c9d-0', usage_metadata={'input_tokens': 11, 'output_tokens': 37, 'total_tokens': 48})"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "first_llm = init_chat_model(\n",
+    "    model=\"gpt-4o\",\n",
+    "    temperature=0,\n",
+    "    configurable_fields=(\"model\", \"model_provider\", \"temperature\", \"max_tokens\"),\n",
+    "    config_prefix=\"first\",  # useful when you have a chain with multiple models\n",
+    ")\n",
+    "\n",
+    "first_llm.invoke(\"what's your name\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "6c8755ba-c001-4f5a-a497-be3f1db83244",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"My name is Claude. It's nice to meet you!\", response_metadata={'id': 'msg_01RyYR64DoMPNCfHeNnroMXm', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 11, 'output_tokens': 15}}, id='run-22446159-3723-43e6-88df-b84797e7751d-0', usage_metadata={'input_tokens': 11, 'output_tokens': 15, 'total_tokens': 26})"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "first_llm.invoke(\n",
+    "    \"what's your name\",\n",
+    "    config={\n",
+    "        \"configurable\": {\n",
+    "            \"first_model\": \"claude-3-5-sonnet-20240620\",\n",
+    "            \"first_temperature\": 0.5,\n",
+    "            \"first_max_tokens\": 100,\n",
+    "        }\n",
+    "    },\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0072b1a3-7e44-4b4e-8b07-efe1ba91a689",
+   "metadata": {},
+   "source": [
+    "### Using a configurable model declaratively\n",
+    "\n",
+    "We can call declarative operations like `bind_tools`, `with_structured_output`, `with_configurable`, etc. on a configurable model and chain a configurable model in the same way that we would a regularly instantiated chat model object."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "067dabee-1050-4110-ae24-c48eba01e13b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'name': 'GetPopulation',\n",
+       "  'args': {'location': 'Los Angeles, CA'},\n",
+       "  'id': 'call_sYT3PFMufHGWJD32Hi2CTNUP'},\n",
+       " {'name': 'GetPopulation',\n",
+       "  'args': {'location': 'New York, NY'},\n",
+       "  'id': 'call_j1qjhxRnD3ffQmRyqjlI1Lnk'}]"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
+    "\n",
+    "\n",
+    "class GetWeather(BaseModel):\n",
+    "    \"\"\"Get the current weather in a given location\"\"\"\n",
+    "\n",
+    "    location: str = Field(..., description=\"The city and state, e.g. San Francisco, CA\")\n",
+    "\n",
+    "\n",
+    "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 = init_chat_model(temperature=0)\n",
+    "llm_with_tools = llm.bind_tools([GetWeather, GetPopulation])\n",
+    "\n",
+    "llm_with_tools.invoke(\n",
+    "    \"what's bigger in 2024 LA or NYC\", config={\"configurable\": {\"model\": \"gpt-4o\"}}\n",
+    ").tool_calls"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "e57dfe9f-cd24-4e37-9ce9-ccf8daf78f89",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'name': 'GetPopulation',\n",
+       "  'args': {'location': 'Los Angeles, CA'},\n",
+       "  'id': 'toolu_01CxEHxKtVbLBrvzFS7GQ5xR'},\n",
+       " {'name': 'GetPopulation',\n",
+       "  'args': {'location': 'New York City, NY'},\n",
+       "  'id': 'toolu_013A79qt5toWSsKunFBDZd5S'}]"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "llm_with_tools.invoke(\n",
+    "    \"what's bigger in 2024 LA or NYC\",\n",
+    "    config={\"configurable\": {\"model\": \"claude-3-5-sonnet-20240620\"}},\n",
+    ").tool_calls"
+   ]
   }
  ],
  "metadata": {
@@ -149,7 +332,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.11.9"
   }
  },
  "nbformat": 4,

docs/docs/how_to/chat_token_usage_tracking.ipynb

@@ -153,7 +153,7 @@
     "\n",
     "#### OpenAI\n",
     "\n",
-    "For example, OpenAI will return a message [chunk](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.ai.AIMessageChunk.html) at the end of a stream with token usage information. This behavior is supported by `langchain-openai >= 0.1.8` and can be enabled by setting `stream_options={\"include_usage\": True}`.\n",
+    "For example, OpenAI will return a message [chunk](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.ai.AIMessageChunk.html) at the end of a stream with token usage information. This behavior is supported by `langchain-openai >= 0.1.8` and can be enabled by setting `stream_usage=True`. This attribute can also be set when `ChatOpenAI` is instantiated.\n",
     "\n",
     "```{=mdx}\n",
     ":::note\n",
@@ -172,18 +172,18 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "content='' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
-      "content='Hello' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
-      "content='!' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
-      "content=' How' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
-      "content=' can' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
-      "content=' I' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
-      "content=' assist' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
-      "content=' you' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
-      "content=' today' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
-      "content='?' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
-      "content='' response_metadata={'finish_reason': 'stop'} id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf'\n",
-      "content='' id='run-b40e502e-d30e-4617-94ad-95b4dfee14bf' usage_metadata={'input_tokens': 8, 'output_tokens': 9, 'total_tokens': 17}\n"
+      "content='' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
+      "content='Hello' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
+      "content='!' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
+      "content=' How' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
+      "content=' can' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
+      "content=' I' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
+      "content=' assist' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
+      "content=' you' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
+      "content=' today' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
+      "content='?' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
+      "content='' response_metadata={'finish_reason': 'stop', 'model_name': 'gpt-3.5-turbo-0125'} id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623'\n",
+      "content='' id='run-adb20c31-60c7-43a2-99b2-d4a53ca5f623' usage_metadata={'input_tokens': 8, 'output_tokens': 9, 'total_tokens': 17}\n"
      ]
     }
    ],
@@ -191,7 +191,7 @@
     "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\")\n",
     "\n",
     "aggregate = None\n",
-    "for chunk in llm.stream(\"hello\", stream_options={\"include_usage\": True}):\n",
+    "for chunk in llm.stream(\"hello\", stream_usage=True):\n",
     "    print(chunk)\n",
     "    aggregate = chunk if aggregate is None else aggregate + chunk"
    ]
@@ -229,7 +229,7 @@
    "id": "7dba63e8-0ed7-4533-8f0f-78e19c38a25c",
    "metadata": {},
    "source": [
-    "To disable streaming token counts for OpenAI, set `\"include_usage\"` to False in `stream_options`, or omit it from the parameters:"
+    "To disable streaming token counts for OpenAI, set `stream_usage` to False, or omit it from the parameters:"
    ]
   },
   {
@@ -242,17 +242,17 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "content='' id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n",
-      "content='Hello' id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n",
-      "content='!' id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n",
-      "content=' How' id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n",
-      "content=' can' id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n",
-      "content=' I' id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n",
-      "content=' assist' id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n",
-      "content=' you' id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n",
-      "content=' today' id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n",
-      "content='?' id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n",
-      "content='' response_metadata={'finish_reason': 'stop'} id='run-0085d64c-13d2-431b-a0fa-399be8cd3c52'\n"
+      "content='' id='run-8e758550-94b0-4cca-a298-57482793c25d'\n",
+      "content='Hello' id='run-8e758550-94b0-4cca-a298-57482793c25d'\n",
+      "content='!' id='run-8e758550-94b0-4cca-a298-57482793c25d'\n",
+      "content=' How' id='run-8e758550-94b0-4cca-a298-57482793c25d'\n",
+      "content=' can' id='run-8e758550-94b0-4cca-a298-57482793c25d'\n",
+      "content=' I' id='run-8e758550-94b0-4cca-a298-57482793c25d'\n",
+      "content=' assist' id='run-8e758550-94b0-4cca-a298-57482793c25d'\n",
+      "content=' you' id='run-8e758550-94b0-4cca-a298-57482793c25d'\n",
+      "content=' today' id='run-8e758550-94b0-4cca-a298-57482793c25d'\n",
+      "content='?' id='run-8e758550-94b0-4cca-a298-57482793c25d'\n",
+      "content='' response_metadata={'finish_reason': 'stop', 'model_name': 'gpt-3.5-turbo-0125'} id='run-8e758550-94b0-4cca-a298-57482793c25d'\n"
      ]
     }
    ],
@@ -267,7 +267,7 @@
    "id": "6a5d9617-be3a-419a-9276-de9c29fa50ae",
    "metadata": {},
    "source": [
-    "You can also enable streaming token usage by setting `model_kwargs` when instantiating the chat model. This can be useful when incorporating chat models into LangChain [chains](/docs/concepts#langchain-expression-language-lcel): usage metadata can be monitored when [streaming intermediate steps](/docs/how_to/streaming#using-stream-events) or using tracing software such as [LangSmith](https://docs.smith.langchain.com/).\n",
+    "You can also enable streaming token usage by setting `stream_usage` when instantiating the chat model. This can be useful when incorporating chat models into LangChain [chains](/docs/concepts#langchain-expression-language-lcel): usage metadata can be monitored when [streaming intermediate steps](/docs/how_to/streaming#using-stream-events) or using tracing software such as [LangSmith](https://docs.smith.langchain.com/).\n",
     "\n",
     "See the below example, where we return output structured to a desired schema, but can still observe token usage streamed from intermediate steps."
    ]
@@ -275,7 +275,7 @@
   {
    "cell_type": "code",
    "execution_count": 8,
-   "id": "57dec1fb-bd9c-4c98-8798-8fbbe67f6b2c",
+   "id": "0b1523d8-127e-4314-82fa-bd97aca37f9a",
    "metadata": {},
    "outputs": [
     {
@@ -301,7 +301,7 @@
     "\n",
     "llm = ChatOpenAI(\n",
     "    model=\"gpt-3.5-turbo-0125\",\n",
-    "    model_kwargs={\"stream_options\": {\"include_usage\": True}},\n",
+    "    stream_usage=True,\n",
     ")\n",
     "# Under the hood, .with_structured_output binds tools to the\n",
     "# chat model and appends a parser.\n",
@@ -341,7 +341,7 @@
   {
    "cell_type": "code",
    "execution_count": 9,
-   "id": "31667d54",
+   "id": "b04a4486-72fd-48ce-8f9e-5d281b441195",
    "metadata": {},
    "outputs": [
     {
@@ -361,7 +361,11 @@
     "\n",
     "from langchain_community.callbacks.manager import get_openai_callback\n",
     "\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n",
+    "llm = ChatOpenAI(\n",
+    "    model=\"gpt-3.5-turbo-0125\",\n",
+    "    temperature=0,\n",
+    "    stream_usage=True,\n",
+    ")\n",
     "\n",
     "with get_openai_callback() as cb:\n",
     "    result = llm.invoke(\"Tell me a joke\")\n",
@@ -379,14 +383,14 @@
   {
    "cell_type": "code",
    "execution_count": 10,
-   "id": "e09420f4",
+   "id": "05f22a1d-b021-490f-8840-f628a07459f2",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "55\n"
+      "54\n"
      ]
     }
    ],
@@ -397,37 +401,29 @@
     "    print(cb.total_tokens)"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "9ac51188-c8f4-4230-90fd-3cd78cdd955d",
-   "metadata": {},
-   "source": [
-    "```{=mdx}\n",
-    ":::note\n",
-    "Cost information is currently not available in streaming mode. This is because model names are currently not propagated through chunks in streaming mode, and the model name is used to look up the correct pricing. Token counts however are available:\n",
-    ":::\n",
-    "```"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 11,
-   "id": "b241069a-265d-4497-af34-b0a5f95ae67f",
+   "id": "c00c9158-7bb4-4279-88e6-ea70f46e6ac2",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "28\n"
+      "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\", stream_options={\"include_usage\": True}):\n",
+    "    for chunk in llm.stream(\"Tell me a joke\"):\n",
     "        pass\n",
-    "    print(cb.total_tokens)"
+    "    print(cb)"
    ]
   },
   {
@@ -457,21 +453,7 @@
     ")\n",
     "tools = load_tools([\"wikipedia\"])\n",
     "agent = create_tool_calling_agent(llm, tools, prompt)\n",
-    "agent_executor = AgentExecutor(\n",
-    "    agent=agent, tools=tools, verbose=True, stream_runnable=False\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "9c1ae74d-8300-4041-9ff4-66093ee592b1",
-   "metadata": {},
-   "source": [
-    "```{=mdx}\n",
-    ":::note\n",
-    "We have to set `stream_runnable=False` for cost information, as described above. By default the AgentExecutor will stream the underlying agent so that you can get the most granular results when streaming events via AgentExecutor.stream_events.\n",
-    ":::\n",
-    "```"
+    "agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)"
    ]
   },
   {
@@ -503,36 +485,30 @@
       "\n",
       "\n",
       "\n",
-      "Page: Anna's hummingbird\n",
-      "Summary: Anna's hummingbird (Calypte anna) is a North American species of hummingbird. It was named after Anna Masséna, Duchess of Rivoli.\n",
-      "It is native to western coastal regions of North America. In the early 20th century, Anna's hummingbirds bred only in northern Baja California and Southern California. The transplanting of exotic ornamental plants in residential areas throughout the Pacific coast and inland deserts provided expanded nectar and nesting sites, allowing the species to expand its breeding range. Year-round residence of Anna's hummingbirds in the Pacific Northwest is an example of ecological release dependent on acclimation to colder winter temperatures, introduced plants, and human provision of nectar feeders during winter.\n",
-      "These birds feed on nectar from flowers using a long extendable tongue. They also consume small insects and other arthropods caught in flight or gleaned from vegetation.\u001b[0m\u001b[32;1m\u001b[1;3m\n",
+      "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",
-      "\n",
-      "\n",
       "Page: Fastest animals\n",
       "Summary: This is a list of the fastest animals in the world, by types of animal.\n",
       "\n",
-      "\n",
-      "\n",
       "Page: Falcon\n",
       "Summary: Falcons () are birds of prey in the genus Falco, which includes about 40 species. Falcons are widely distributed on all continents of the world except Antarctica, though closely related raptors did occur there in the Eocene.\n",
       "Adult falcons have thin, tapered wings, which enable them to fly at high speed and change direction rapidly. Fledgling falcons, in their first year of flying, have longer flight feathers, which make their configuration more like that of a general-purpose bird such as a broad wing. This makes flying easier while learning the exceptional skills required to be effective hunters as adults.\n",
       "The falcons are the largest genus in the Falconinae subfamily of Falconidae, which itself also includes another subfamily comprising caracaras and a few other species. All these birds kill with their beaks, using a tomial \"tooth\" on the side of their beaks—unlike the hawks, eagles, and other birds of prey in the Accipitridae, which use their feet.\n",
       "The largest falcon is the gyrfalcon at up to 65 cm in length.  The smallest falcon species is the pygmy falcon, which measures just 20 cm.  As with hawks and owls, falcons exhibit sexual dimorphism, with the females typically larger than the males, thus allowing a wider range of prey species.\n",
       "Some small falcons with long, narrow wings are called \"hobbies\" and some which hover while hunting are called \"kestrels\".\n",
-      "As is the case with many birds of prey, falcons have exceptional powers of vision; the visual acuity of one species has been measured at 2.6 times that of a normal human. Peregrine falcons have been recorded diving at speeds of 320 km/h (200 mph), making them the fastest-moving creatures on Earth; the fastest recorded dive attained a vertical speed of 390 km/h (240 mph).\u001b[0m\u001b[32;1m\u001b[1;3mThe scientific name for a hummingbird is Trochilidae. The fastest bird species is the peregrine falcon (Falco peregrinus), which can exceed speeds of 320 km/h (200 mph) in its dives.\u001b[0m\n",
+      "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: 1787\n",
-      "Prompt Tokens: 1687\n",
-      "Completion Tokens: 100\n",
-      "Total Cost (USD): $0.0009935\n"
+      "Total Tokens: 1675\n",
+      "Prompt Tokens: 1538\n",
+      "Completion Tokens: 137\n",
+      "Total Cost (USD): $0.0009745000000000001\n"
      ]
     }
    ],

docs/docs/how_to/code_splitter.ipynb

@@ -300,7 +300,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 2,
    "id": "ac9295d3",
    "metadata": {},
    "outputs": [],
@@ -312,10 +312,8 @@
     "\n",
     "## Quick Install\n",
     "\n",
-    "```bash\n",
     "# Hopefully this code block isn't split\n",
     "pip install langchain\n",
-    "```\n",
     "\n",
     "As an open-source project in a rapidly developing field, we are extremely open to contributions.\n",
     "\"\"\""
@@ -323,7 +321,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 3,
    "id": "3a0cb17a",
    "metadata": {},
    "outputs": [
@@ -332,15 +330,14 @@
       "text/plain": [
        "[Document(page_content='# 🦜️🔗 LangChain'),\n",
        " Document(page_content='⚡ Building applications with LLMs through composability ⚡'),\n",
-       " Document(page_content='## Quick Install\\n\\n```bash'),\n",
+       " Document(page_content='## Quick Install'),\n",
        " Document(page_content=\"# Hopefully this code block isn't split\"),\n",
        " Document(page_content='pip install langchain'),\n",
-       " Document(page_content='```'),\n",
        " Document(page_content='As an open-source project in a rapidly developing field, we'),\n",
        " Document(page_content='are extremely open to contributions.')]"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -742,7 +739,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.4"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/how_to/configure.ipynb

@@ -48,20 +48,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "id": "40ed76a2",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[33mWARNING: You are using pip version 22.0.4; however, version 24.0 is available.\n",
-      "You should consider upgrading via the '/Users/jacoblee/.pyenv/versions/3.10.5/bin/python -m pip install --upgrade pip' command.\u001b[0m\u001b[33m\n",
-      "\u001b[0mNote: you may need to restart the kernel to use updated packages.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "%pip install --upgrade --quiet langchain langchain-openai\n",
     "\n",

docs/docs/how_to/convert_runnable_to_tool.ipynb

@@ -0,0 +1,549 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "9a8bceb3-95bd-4496-bb9e-57655136e070",
+   "metadata": {},
+   "source": [
+    "# How to use Runnables as Tools\n",
+    "\n",
+    ":::info Prerequisites\n",
+    "\n",
+    "This guide assumes familiarity with the following concepts:\n",
+    "\n",
+    "- [Runnables](/docs/concepts#runnable-interface)\n",
+    "- [Tools](/docs/concepts#tools)\n",
+    "- [Agents](/docs/tutorials/agents)\n",
+    "\n",
+    ":::\n",
+    "\n",
+    "Here we will demonstrate how to convert a LangChain `Runnable` into a tool that can be used by agents, chains, or chat models.\n",
+    "\n",
+    "## Dependencies\n",
+    "\n",
+    "**Note**: this guide requires `langchain-core` >= 0.2.13. We will also use [OpenAI](/docs/integrations/platforms/openai/) for embeddings, but any LangChain embeddings should suffice. We will use a simple [LangGraph](https://langchain-ai.github.io/langgraph/) agent for demonstration purposes."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "92341f48-2c29-4ce9-8ab8-0a7c7a7c98a1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%capture --no-stderr\n",
+    "%pip install -U langchain-core langchain-openai langgraph"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2b0dcc1a-48e8-4a81-b920-3563192ce076",
+   "metadata": {},
+   "source": [
+    "LangChain [tools](/docs/concepts#tools) are interfaces that an agent, chain, or chat model can use to interact with the world. See [here](/docs/how_to/#tools) for how-to guides covering tool-calling, built-in tools, custom tools, and more information.\n",
+    "\n",
+    "LangChain tools-- instances of [BaseTool](https://api.python.langchain.com/en/latest/tools/langchain_core.tools.BaseTool.html)-- are [Runnables](/docs/concepts/#runnable-interface) with additional constraints that enable them to be invoked effectively by language models:\n",
+    "\n",
+    "- Their inputs are constrained to be serializable, specifically strings and Python `dict` objects;\n",
+    "- They contain names and descriptions indicating how and when they should be used;\n",
+    "- They may contain a detailed [args_schema](https://python.langchain.com/v0.2/docs/how_to/custom_tools/) for their arguments. That is, while a tool (as a `Runnable`) might accept a single `dict` input, the specific keys and type information needed to populate a dict should be specified in the `args_schema`.\n",
+    "\n",
+    "Runnables that accept string or `dict` input can be converted to tools using the [as_tool](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.Runnable.html#langchain_core.runnables.base.Runnable.as_tool) method, which allows for the specification of names, descriptions, and additional schema information for arguments."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b4d76680-1b6b-4862-8c4f-22766a1d41f2",
+   "metadata": {},
+   "source": [
+    "## Basic usage\n",
+    "\n",
+    "With typed `dict` input:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "b2cc4231-64a3-4733-a284-932dcbf2fcc3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from typing import List\n",
+    "\n",
+    "from langchain_core.runnables import RunnableLambda\n",
+    "from typing_extensions import TypedDict\n",
+    "\n",
+    "\n",
+    "class Args(TypedDict):\n",
+    "    a: int\n",
+    "    b: List[int]\n",
+    "\n",
+    "\n",
+    "def f(x: Args) -> str:\n",
+    "    return str(x[\"a\"] * max(x[\"b\"]))\n",
+    "\n",
+    "\n",
+    "runnable = RunnableLambda(f)\n",
+    "as_tool = runnable.as_tool(\n",
+    "    name=\"My tool\",\n",
+    "    description=\"Explanation of when to use tool.\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "57f2d435-624d-459a-903d-8509fbbde610",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Explanation of when to use tool.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "{'title': 'My tool',\n",
+       " 'type': 'object',\n",
+       " 'properties': {'a': {'title': 'A', 'type': 'integer'},\n",
+       "  'b': {'title': 'B', 'type': 'array', 'items': {'type': 'integer'}}},\n",
+       " 'required': ['a', 'b']}"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "print(as_tool.description)\n",
+    "\n",
+    "as_tool.args_schema.schema()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "54ae7384-a03d-4fa4-8cdf-9604a4bc39ee",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'6'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "as_tool.invoke({\"a\": 3, \"b\": [1, 2]})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9038f587-4613-4f50-b349-135f9e7e3b15",
+   "metadata": {},
+   "source": [
+    "Without typing information, arg types can be specified via `arg_types`:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "169f733c-4936-497f-8577-ee769dc16b88",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from typing import Any, Dict\n",
+    "\n",
+    "\n",
+    "def g(x: Dict[str, Any]) -> str:\n",
+    "    return str(x[\"a\"] * max(x[\"b\"]))\n",
+    "\n",
+    "\n",
+    "runnable = RunnableLambda(g)\n",
+    "as_tool = runnable.as_tool(\n",
+    "    name=\"My tool\",\n",
+    "    description=\"Explanation of when to use tool.\",\n",
+    "    arg_types={\"a\": int, \"b\": List[int]},\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "32b1a992-8997-4c98-8eb2-c9fe9431b799",
+   "metadata": {},
+   "source": [
+    "Alternatively, the schema can be fully specified by directly passing the desired [args_schema](https://api.python.langchain.com/en/latest/tools/langchain_core.tools.BaseTool.html#langchain_core.tools.BaseTool.args_schema) for the tool:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "eb102705-89b7-48dc-9158-d36d5f98ae8e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
+    "\n",
+    "\n",
+    "class GSchema(BaseModel):\n",
+    "    \"\"\"Apply a function to an integer and list of integers.\"\"\"\n",
+    "\n",
+    "    a: int = Field(..., description=\"Integer\")\n",
+    "    b: List[int] = Field(..., description=\"List of ints\")\n",
+    "\n",
+    "\n",
+    "runnable = RunnableLambda(g)\n",
+    "as_tool = runnable.as_tool(GSchema)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7c474d85-4e01-4fae-9bba-0c6c8c26475c",
+   "metadata": {},
+   "source": [
+    "String input is also supported:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "c475282a-58d6-4c2b-af7d-99b73b7d8a13",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def f(x: str) -> str:\n",
+    "    return x + \"a\"\n",
+    "\n",
+    "\n",
+    "def g(x: str) -> str:\n",
+    "    return x + \"z\"\n",
+    "\n",
+    "\n",
+    "runnable = RunnableLambda(f) | g\n",
+    "as_tool = runnable.as_tool()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "ad6d8d96-3a87-40bd-a2ac-44a8acde0a8e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'baz'"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "as_tool.invoke(\"b\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "89fdb3a7-d228-48f0-8f73-262af4febb58",
+   "metadata": {},
+   "source": [
+    "## In agents\n",
+    "\n",
+    "Below we will incorporate LangChain Runnables as tools in an [agent](/docs/concepts/#agents) application. We will demonstrate with:\n",
+    "\n",
+    "- a document [retriever](/docs/concepts/#retrievers);\n",
+    "- a simple [RAG](/docs/tutorials/rag/) chain, allowing an agent to delegate relevant queries to it.\n",
+    "\n",
+    "We first instantiate a chat model that supports [tool calling](/docs/how_to/tool_calling/):\n",
+    "\n",
+    "```{=mdx}\n",
+    "<ChatModelTabs\n",
+    "  customVarName=\"llm\"\n",
+    "/>\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "d06c9f2a-4475-450f-9106-54db1d99623b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# | output: false\n",
+    "# | echo: false\n",
+    "\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e8a2038a-d762-4196-b5e3-fdb89c11e71d",
+   "metadata": {},
+   "source": [
+    "Following the [RAG tutorial](/docs/tutorials/rag/), let's first construct a retriever:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "23d2a47e-6712-4294-81c8-2c1d76b4bb81",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.documents import Document\n",
+    "from langchain_core.vectorstores import InMemoryVectorStore\n",
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "\n",
+    "documents = [\n",
+    "    Document(\n",
+    "        page_content=\"Dogs are great companions, known for their loyalty and friendliness.\",\n",
+    "    ),\n",
+    "    Document(\n",
+    "        page_content=\"Cats are independent pets that often enjoy their own space.\",\n",
+    "    ),\n",
+    "]\n",
+    "\n",
+    "vectorstore = InMemoryVectorStore.from_documents(\n",
+    "    documents, embedding=OpenAIEmbeddings()\n",
+    ")\n",
+    "\n",
+    "retriever = vectorstore.as_retriever(\n",
+    "    search_type=\"similarity\",\n",
+    "    search_kwargs={\"k\": 1},\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9ba737ac-43a2-4a6f-b855-5bd0305017f1",
+   "metadata": {},
+   "source": [
+    "We next create use a simple pre-built [LangGraph agent](https://python.langchain.com/v0.2/docs/tutorials/agents/) and provide it the tool:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "c939cf2a-60e9-4afd-8b47-84d76ccb13f5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langgraph.prebuilt import create_react_agent\n",
+    "\n",
+    "tools = [\n",
+    "    retriever.as_tool(\n",
+    "        name=\"pet_info_retriever\",\n",
+    "        description=\"Get information about pets.\",\n",
+    "    )\n",
+    "]\n",
+    "agent = create_react_agent(llm, tools)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "be29437b-a187-4a0a-9a5d-419c56f2434e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_W8cnfOjwqEn4cFcg19LN9mYD', 'function': {'arguments': '{\"__arg1\":\"dogs\"}', 'name': 'pet_info_retriever'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 19, 'prompt_tokens': 60, 'total_tokens': 79}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-d7f81de9-1fb7-4caf-81ed-16dcdb0b2ab4-0', tool_calls=[{'name': 'pet_info_retriever', 'args': {'__arg1': 'dogs'}, 'id': 'call_W8cnfOjwqEn4cFcg19LN9mYD'}], usage_metadata={'input_tokens': 60, 'output_tokens': 19, 'total_tokens': 79})]}}\n",
+      "----\n",
+      "{'tools': {'messages': [ToolMessage(content=\"[Document(id='86f835fe-4bbe-4ec6-aeb4-489a8b541707', page_content='Dogs are great companions, known for their loyalty and friendliness.')]\", name='pet_info_retriever', tool_call_id='call_W8cnfOjwqEn4cFcg19LN9mYD')]}}\n",
+      "----\n",
+      "{'agent': {'messages': [AIMessage(content='Dogs are known for being great companions, known for their loyalty and friendliness.', response_metadata={'token_usage': {'completion_tokens': 18, 'prompt_tokens': 134, 'total_tokens': 152}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-9ca5847a-a5eb-44c0-a774-84cc2c5bbc5b-0', usage_metadata={'input_tokens': 134, 'output_tokens': 18, 'total_tokens': 152})]}}\n",
+      "----\n"
+     ]
+    }
+   ],
+   "source": [
+    "for chunk in agent.stream({\"messages\": [(\"human\", \"What are dogs known for?\")]}):\n",
+    "    print(chunk)\n",
+    "    print(\"----\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "96f2ac9c-36f4-4b7a-ae33-f517734c86aa",
+   "metadata": {},
+   "source": [
+    "See [LangSmith trace](https://smith.langchain.com/public/44e438e3-2faf-45bd-b397-5510fc145eb9/r) for the above run."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a722fd8a-b957-4ba7-b408-35596b76835f",
+   "metadata": {},
+   "source": [
+    "Going further, we can create a simple [RAG](/docs/tutorials/rag/) chain that takes an additional parameter-- here, the \"style\" of the answer."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "bea518c9-c711-47c2-b8cc-dbd102f71f09",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from operator import itemgetter\n",
+    "\n",
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_core.runnables import RunnablePassthrough\n",
+    "\n",
+    "system_prompt = \"\"\"\n",
+    "You are an assistant for question-answering tasks.\n",
+    "Use the below context to answer the question. If\n",
+    "you don't know the answer, say you don't know.\n",
+    "Use three sentences maximum and keep the answer\n",
+    "concise.\n",
+    "\n",
+    "Answer in the style of {answer_style}.\n",
+    "\n",
+    "Question: {question}\n",
+    "\n",
+    "Context: {context}\n",
+    "\"\"\"\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_messages([(\"system\", system_prompt)])\n",
+    "\n",
+    "rag_chain = (\n",
+    "    {\n",
+    "        \"context\": itemgetter(\"question\") | retriever,\n",
+    "        \"question\": itemgetter(\"question\"),\n",
+    "        \"answer_style\": itemgetter(\"answer_style\"),\n",
+    "    }\n",
+    "    | prompt\n",
+    "    | llm\n",
+    "    | StrOutputParser()\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "955a23db-5218-4c34-8486-450a2ddb3443",
+   "metadata": {},
+   "source": [
+    "Note that the input schema for our chain contains the required arguments, so it converts to a tool without further specification:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "2c9f6e61-80ed-4abb-8e77-84de3ccbc891",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'title': 'RunnableParallel<context,question,answer_style>Input',\n",
+       " 'type': 'object',\n",
+       " 'properties': {'question': {'title': 'Question'},\n",
+       "  'answer_style': {'title': 'Answer Style'}}}"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "rag_chain.input_schema.schema()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "a3f9cf5b-8c71-4b0f-902b-f92e028780c9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "rag_tool = rag_chain.as_tool(\n",
+    "    name=\"pet_expert\",\n",
+    "    description=\"Get information about pets.\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4570615b-8f96-4d97-ae01-1c08b14be584",
+   "metadata": {},
+   "source": [
+    "Below we again invoke the agent. Note that the agent populates the required parameters in its `tool_calls`:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "06409913-a2ad-400f-a202-7b8dd2ef483a",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_17iLPWvOD23zqwd1QVQ00Y63', 'function': {'arguments': '{\"question\":\"What are dogs known for according to pirates?\",\"answer_style\":\"quote\"}', 'name': 'pet_expert'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 28, 'prompt_tokens': 59, 'total_tokens': 87}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-7fef44f3-7bba-4e63-8c51-2ad9c5e65e2e-0', tool_calls=[{'name': 'pet_expert', 'args': {'question': 'What are dogs known for according to pirates?', 'answer_style': 'quote'}, 'id': 'call_17iLPWvOD23zqwd1QVQ00Y63'}], usage_metadata={'input_tokens': 59, 'output_tokens': 28, 'total_tokens': 87})]}}\n",
+      "----\n",
+      "{'tools': {'messages': [ToolMessage(content='\"Dogs are known for their loyalty and friendliness, making them great companions for pirates on long sea voyages.\"', name='pet_expert', tool_call_id='call_17iLPWvOD23zqwd1QVQ00Y63')]}}\n",
+      "----\n",
+      "{'agent': {'messages': [AIMessage(content='According to pirates, dogs are known for their loyalty and friendliness, making them great companions for pirates on long sea voyages.', response_metadata={'token_usage': {'completion_tokens': 27, 'prompt_tokens': 119, 'total_tokens': 146}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-5a30edc3-7be0-4743-b980-ca2f8cad9b8d-0', usage_metadata={'input_tokens': 119, 'output_tokens': 27, 'total_tokens': 146})]}}\n",
+      "----\n"
+     ]
+    }
+   ],
+   "source": [
+    "agent = create_react_agent(llm, [rag_tool])\n",
+    "\n",
+    "for chunk in agent.stream(\n",
+    "    {\"messages\": [(\"human\", \"What would a pirate say dogs are known for?\")]}\n",
+    "):\n",
+    "    print(chunk)\n",
+    "    print(\"----\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "96cc9bc3-e79e-49a8-9915-428ea225358b",
+   "metadata": {},
+   "source": [
+    "See [LangSmith trace](https://smith.langchain.com/public/147ae4e6-4dfb-4dd9-8ca0-5c5b954f08ac/r) for the above run."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/how_to/custom_chat_model.ipynb

@@ -131,7 +131,7 @@
    "source": [
     "## Base Chat Model\n",
     "\n",
-    "Let's implement a chat model that echoes back the first `n` characetrs of the last message in the prompt!\n",
+    "Let's implement a chat model that echoes back the first `n` characters of the last message in the prompt!\n",
     "\n",
     "To do so, we will inherit from `BaseChatModel` and we'll need to implement the following:\n",
     "\n",

docs/docs/how_to/custom_tools.ipynb

@@ -16,13 +16,15 @@
     "| args_schema   | Pydantic BaseModel      | Optional but recommended, can be used to provide more information (e.g., few-shot examples) or validation for expected parameters |\n",
     "| return_direct   | boolean      | Only relevant for agents. When True, after invoking the given tool, the agent will stop and return the result direcly to the user.  |\n",
     "\n",
-    "LangChain provides 3 ways to create tools:\n",
+    "LangChain supports the creation of tools from:\n",
     "\n",
-    "1. Using [@tool decorator](https://api.python.langchain.com/en/latest/tools/langchain_core.tools.tool.html#langchain_core.tools.tool) -- the simplest way to define a custom tool.\n",
-    "2. Using [StructuredTool.from_function](https://api.python.langchain.com/en/latest/tools/langchain_core.tools.StructuredTool.html#langchain_core.tools.StructuredTool.from_function) class method -- this is similar to the `@tool` decorator, but allows more configuration and specification of both sync and async implementations.\n",
+    "1. Functions;\n",
+    "2. LangChain [Runnables](/docs/concepts#runnable-interface);\n",
     "3. By sub-classing from [BaseTool](https://api.python.langchain.com/en/latest/tools/langchain_core.tools.BaseTool.html) -- This is the most flexible method, it provides the largest degree of control, at the expense of more effort and code.\n",
     "\n",
-    "The `@tool` or the `StructuredTool.from_function` class method should be sufficient for most use cases.\n",
+    "Creating tools from functions may be sufficient for most use cases, and can be done via a simple [@tool decorator](https://api.python.langchain.com/en/latest/tools/langchain_core.tools.tool.html#langchain_core.tools.tool). If more configuration is needed-- e.g., specification of both sync and async implementations-- one can also use the [StructuredTool.from_function](https://api.python.langchain.com/en/latest/tools/langchain_core.tools.StructuredTool.html#langchain_core.tools.StructuredTool.from_function) class method.\n",
+    "\n",
+    "In this guide we provide an overview of these methods.\n",
     "\n",
     ":::{.callout-tip}\n",
     "\n",
@@ -35,7 +37,9 @@
    "id": "c7326b23",
    "metadata": {},
    "source": [
-    "## @tool decorator\n",
+    "## Creating tools from functions\n",
+    "\n",
+    "### @tool decorator\n",
     "\n",
     "This `@tool` decorator is the simplest way to define a custom tool. The decorator uses the function name as the tool name by default, but this can be overridden by passing a string as the first argument. Additionally, the decorator will use the function's docstring as the tool's description - so a docstring MUST be provided. "
    ]
@@ -51,7 +55,7 @@
      "output_type": "stream",
      "text": [
       "multiply\n",
-      "multiply(a: int, b: int) -> int - Multiply two numbers.\n",
+      "Multiply two numbers.\n",
       "{'a': {'title': 'A', 'type': 'integer'}, 'b': {'title': 'B', 'type': 'integer'}}\n"
      ]
     }
@@ -96,6 +100,57 @@
     "    return a * b"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "8f0edc51-c586-414c-8941-c8abe779943f",
+   "metadata": {},
+   "source": [
+    "Note that `@tool` supports parsing of annotations, nested schemas, and other features:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "5626423f-053e-4a66-adca-1d794d835397",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'title': 'multiply_by_maxSchema',\n",
+       " 'description': 'Multiply a by the maximum of b.',\n",
+       " 'type': 'object',\n",
+       " 'properties': {'a': {'title': 'A',\n",
+       "   'description': 'scale factor',\n",
+       "   'type': 'string'},\n",
+       "  'b': {'title': 'B',\n",
+       "   'description': 'list of ints over which to take maximum',\n",
+       "   'type': 'array',\n",
+       "   'items': {'type': 'integer'}}},\n",
+       " 'required': ['a', 'b']}"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from typing import Annotated, List\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def multiply_by_max(\n",
+    "    a: Annotated[str, \"scale factor\"],\n",
+    "    b: Annotated[List[int], \"list of ints over which to take maximum\"],\n",
+    ") -> int:\n",
+    "    \"\"\"Multiply a by the maximum of b.\"\"\"\n",
+    "    return a * max(b)\n",
+    "\n",
+    "\n",
+    "multiply_by_max.args_schema.schema()"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "98d6eee9",
@@ -106,7 +161,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "id": "9216d03a-f6ea-4216-b7e1-0661823a4c0b",
    "metadata": {},
    "outputs": [
@@ -115,7 +170,7 @@
      "output_type": "stream",
      "text": [
       "multiplication-tool\n",
-      "multiplication-tool(a: int, b: int) -> int - Multiply two numbers.\n",
+      "Multiply two numbers.\n",
       "{'a': {'title': 'A', 'description': 'first number', 'type': 'integer'}, 'b': {'title': 'B', 'description': 'second number', 'type': 'integer'}}\n",
       "True\n"
      ]
@@ -143,19 +198,84 @@
     "print(multiply.return_direct)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "33a9e94d-0b60-48f3-a4c2-247dce096e66",
+   "metadata": {},
+   "source": [
+    "#### Docstring parsing"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6d0cb586-93d4-4ff1-9779-71df7853cb68",
+   "metadata": {},
+   "source": [
+    "`@tool` can optionally parse [Google Style docstrings](https://google.github.io/styleguide/pyguide.html#383-functions-and-methods) and associate the docstring components (such as arg descriptions) to the relevant parts of the tool schema. To toggle this behavior, specify `parse_docstring`:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "336f5538-956e-47d5-9bde-b732559f9e61",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'title': 'fooSchema',\n",
+       " 'description': 'The foo.',\n",
+       " 'type': 'object',\n",
+       " 'properties': {'bar': {'title': 'Bar',\n",
+       "   'description': 'The bar.',\n",
+       "   'type': 'string'},\n",
+       "  'baz': {'title': 'Baz', 'description': 'The baz.', 'type': 'integer'}},\n",
+       " 'required': ['bar', 'baz']}"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "@tool(parse_docstring=True)\n",
+    "def foo(bar: str, baz: int) -> str:\n",
+    "    \"\"\"The foo.\n",
+    "\n",
+    "    Args:\n",
+    "        bar: The bar.\n",
+    "        baz: The baz.\n",
+    "    \"\"\"\n",
+    "    return bar\n",
+    "\n",
+    "\n",
+    "foo.args_schema.schema()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f18a2503-5393-421b-99fa-4a01dd824d0e",
+   "metadata": {},
+   "source": [
+    ":::{.callout-caution}\n",
+    "By default, `@tool(parse_docstring=True)` will raise `ValueError` if the docstring does not parse correctly. See [API Reference](https://api.python.langchain.com/en/latest/tools/langchain_core.tools.tool.html) for detail and examples.\n",
+    ":::"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "b63fcc3b",
    "metadata": {},
    "source": [
-    "## StructuredTool\n",
+    "### StructuredTool\n",
     "\n",
     "The `StrurcturedTool.from_function` class method provides a bit more configurability than the `@tool` decorator, without requiring much additional code."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 6,
    "id": "564fbe6f-11df-402d-b135-ef6ff25e1e63",
    "metadata": {},
    "outputs": [
@@ -198,7 +318,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 7,
    "id": "6bc055d4-1fbe-4db5-8881-9c382eba6b1b",
    "metadata": {},
    "outputs": [
@@ -208,7 +328,7 @@
      "text": [
       "6\n",
       "Calculator\n",
-      "Calculator(a: int, b: int) -> int - multiply numbers\n",
+      "multiply numbers\n",
       "{'a': {'title': 'A', 'description': 'first number', 'type': 'integer'}, 'b': {'title': 'B', 'description': 'second number', 'type': 'integer'}}\n"
      ]
     }
@@ -239,6 +359,63 @@
     "print(calculator.args)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "5517995d-54e3-449b-8fdb-03561f5e4647",
+   "metadata": {},
+   "source": [
+    "## Creating tools from Runnables\n",
+    "\n",
+    "LangChain [Runnables](/docs/concepts#runnable-interface) that accept string or `dict` input can be converted to tools using the [as_tool](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.Runnable.html#langchain_core.runnables.base.Runnable.as_tool) method, which allows for the specification of names, descriptions, and additional schema information for arguments.\n",
+    "\n",
+    "Example usage:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "8ef593c5-cf72-4c10-bfc9-7d21874a0c24",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'answer_style': {'title': 'Answer Style', 'type': 'string'}}"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_core.language_models import GenericFakeChatModel\n",
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [(\"human\", \"Hello. Please respond in the style of {answer_style}.\")]\n",
+    ")\n",
+    "\n",
+    "# Placeholder LLM\n",
+    "llm = GenericFakeChatModel(messages=iter([\"hello matey\"]))\n",
+    "\n",
+    "chain = prompt | llm | StrOutputParser()\n",
+    "\n",
+    "as_tool = chain.as_tool(\n",
+    "    name=\"Style responder\", description=\"Description of when to use tool.\"\n",
+    ")\n",
+    "as_tool.args"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0521b787-a146-45a6-8ace-ae1ac4669dd7",
+   "metadata": {},
+   "source": [
+    "See [this guide](/docs/how_to/convert_runnable_to_tool) for more detail."
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "b840074b-9c10-4ca0-aed8-626c52b2398f",
@@ -251,7 +428,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 10,
    "id": "1dad8f8e",
    "metadata": {},
    "outputs": [],
@@ -300,7 +477,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 11,
    "id": "bb551c33",
    "metadata": {},
    "outputs": [
@@ -351,7 +528,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 12,
    "id": "6615cb77-fd4c-4676-8965-f92cc71d4944",
    "metadata": {},
    "outputs": [
@@ -383,7 +560,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 13,
    "id": "bb2af583-eadd-41f4-a645-bf8748bd3dcd",
    "metadata": {},
    "outputs": [
@@ -428,7 +605,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 14,
    "id": "4ad0932c-8610-4278-8c57-f9218f654c8a",
    "metadata": {},
    "outputs": [
@@ -473,7 +650,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 15,
    "id": "7094c0e8-6192-4870-a942-aad5b5ae48fd",
    "metadata": {},
    "outputs": [],
@@ -496,7 +673,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 16,
    "id": "b4d22022-b105-4ccc-a15b-412cb9ea3097",
    "metadata": {},
    "outputs": [
@@ -506,7 +683,7 @@
        "'Error: There is no city by the name of foobar.'"
       ]
      },
-     "execution_count": 12,
+     "execution_count": 16,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -530,7 +707,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 17,
    "id": "3fad1728-d367-4e1b-9b54-3172981271cf",
    "metadata": {},
    "outputs": [
@@ -540,7 +717,7 @@
        "\"There is no such city, but it's probably above 0K there!\""
       ]
      },
-     "execution_count": 13,
+     "execution_count": 17,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -564,7 +741,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 18,
    "id": "ebfe7c1f-318d-4e58-99e1-f31e69473c46",
    "metadata": {},
    "outputs": [
@@ -574,7 +751,7 @@
        "'The following errors occurred during tool execution: `Error: There is no city by the name of foobar.`'"
       ]
      },
-     "execution_count": 14,
+     "execution_count": 18,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -591,13 +768,189 @@
     "\n",
     "get_weather_tool.invoke({\"city\": \"foobar\"})"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1a8d8383-11b3-445e-956f-df4e96995e00",
+   "metadata": {},
+   "source": [
+    "## Returning artifacts of Tool execution\n",
+    "\n",
+    "Sometimes there are artifacts of a tool's execution that we want to make accessible to downstream components in our chain or agent, but that we don't want to expose to the model itself. For example if a tool returns custom objects like Documents, we may want to pass some view or metadata about this output to the model without passing the raw output to the model. At the same time, we may want to be able to access this full output elsewhere, for example in downstream tools.\n",
+    "\n",
+    "The Tool and [ToolMessage](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.tool.ToolMessage.html) interfaces make it possible to distinguish between the parts of the tool output meant for the model (this is the ToolMessage.content) and those parts which are meant for use outside the model (ToolMessage.artifact).\n",
+    "\n",
+    ":::info Requires ``langchain-core >= 0.2.19``\n",
+    "\n",
+    "This functionality was added in ``langchain-core == 0.2.19``. Please make sure your package is up to date.\n",
+    "\n",
+    ":::\n",
+    "\n",
+    "If we want our tool to distinguish between message content and other artifacts, we need to specify `response_format=\"content_and_artifact\"` when defining our tool and make sure that we return a tuple of (content, artifact):"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "14905425-0334-43a0-9de9-5bcf622ede0e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import random\n",
+    "from typing import List, Tuple\n",
+    "\n",
+    "from langchain_core.tools import tool\n",
+    "\n",
+    "\n",
+    "@tool(response_format=\"content_and_artifact\")\n",
+    "def generate_random_ints(min: int, max: int, size: int) -> Tuple[str, List[int]]:\n",
+    "    \"\"\"Generate size random ints in the range [min, max].\"\"\"\n",
+    "    array = [random.randint(min, max) for _ in range(size)]\n",
+    "    content = f\"Successfully generated array of {size} random ints in [{min}, {max}].\"\n",
+    "    return content, array"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "49f057a6-8938-43ea-8faf-ae41e797ceb8",
+   "metadata": {},
+   "source": [
+    "If we invoke our tool directly with the tool arguments, we'll get back just the content part of the output:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "0f2e1528-404b-46e6-b87c-f0957c4b9217",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Successfully generated array of 10 random ints in [0, 9].'"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "generate_random_ints.invoke({\"min\": 0, \"max\": 9, \"size\": 10})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1e62ebba-1737-4b97-b61a-7313ade4e8c2",
+   "metadata": {},
+   "source": [
+    "If we invoke our tool with a ToolCall (like the ones generated by tool-calling models), we'll get back a ToolMessage that contains both the content and artifact generated by the Tool:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "cc197777-26eb-46b3-a83b-c2ce116c6311",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "ToolMessage(content='Successfully generated array of 10 random ints in [0, 9].', name='generate_random_ints', tool_call_id='123', artifact=[1, 4, 2, 5, 3, 9, 0, 4, 7, 7])"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "generate_random_ints.invoke(\n",
+    "    {\n",
+    "        \"name\": \"generate_random_ints\",\n",
+    "        \"args\": {\"min\": 0, \"max\": 9, \"size\": 10},\n",
+    "        \"id\": \"123\",  # required\n",
+    "        \"type\": \"tool_call\",  # required\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "dfdc1040-bf25-4790-b4c3-59452db84e11",
+   "metadata": {},
+   "source": [
+    "We can do the same when subclassing BaseTool:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "fe1a09d1-378b-4b91-bb5e-0697c3d7eb92",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.tools import BaseTool\n",
+    "\n",
+    "\n",
+    "class GenerateRandomFloats(BaseTool):\n",
+    "    name: str = \"generate_random_floats\"\n",
+    "    description: str = \"Generate size random floats in the range [min, max].\"\n",
+    "    response_format: str = \"content_and_artifact\"\n",
+    "\n",
+    "    ndigits: int = 2\n",
+    "\n",
+    "    def _run(self, min: float, max: float, size: int) -> Tuple[str, List[float]]:\n",
+    "        range_ = max - min\n",
+    "        array = [\n",
+    "            round(min + (range_ * random.random()), ndigits=self.ndigits)\n",
+    "            for _ in range(size)\n",
+    "        ]\n",
+    "        content = f\"Generated {size} floats in [{min}, {max}], rounded to {self.ndigits} decimals.\"\n",
+    "        return content, array\n",
+    "\n",
+    "    # Optionally define an equivalent async method\n",
+    "\n",
+    "    # async def _arun(self, min: float, max: float, size: int) -> Tuple[str, List[float]]:\n",
+    "    #     ..."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "8c3d16f6-1c4a-48ab-b05a-38547c592e79",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "ToolMessage(content='Generated 3 floats in [0.1, 3.3333], rounded to 4 decimals.', name='generate_random_floats', tool_call_id='123', artifact=[1.4277, 0.7578, 2.4871])"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "rand_gen = GenerateRandomFloats(ndigits=4)\n",
+    "\n",
+    "rand_gen.invoke(\n",
+    "    {\n",
+    "        \"name\": \"generate_random_floats\",\n",
+    "        \"args\": {\"min\": 0.1, \"max\": 3.3333, \"size\": 3},\n",
+    "        \"id\": \"123\",\n",
+    "        \"type\": \"tool_call\",\n",
+    "    }\n",
+    ")"
+   ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "poetry-venv-311",
    "language": "python",
-   "name": "python3"
+   "name": "poetry-venv-311"
   },
   "language_info": {
    "codemirror_mode": {
@@ -609,7 +962,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.11.9"
   },
   "vscode": {
    "interpreter": {

docs/docs/how_to/dynamic_chain.ipynb

@@ -58,6 +58,8 @@
     }
    ],
    "source": [
+    "from operator import itemgetter\n",
+    "\n",
     "from langchain_core.output_parsers import StrOutputParser\n",
     "from langchain_core.prompts import ChatPromptTemplate\n",
     "from langchain_core.runnables import Runnable, RunnablePassthrough, chain\n",
@@ -86,7 +88,7 @@
     "        # NOTE: This is returning another Runnable, not an actual output.\n",
     "        return contextualize_question\n",
     "    else:\n",
-    "        return RunnablePassthrough()\n",
+    "        return RunnablePassthrough() | itemgetter(\"question\")\n",
     "\n",
     "\n",
     "@chain\n",

docs/docs/how_to/embed_text.mdx

@@ -67,15 +67,16 @@ If you'd prefer not to set an environment variable you can pass the key in direc
 ```python
 from langchain_cohere import CohereEmbeddings
 
-embeddings_model = CohereEmbeddings(cohere_api_key="...")
+embeddings_model = CohereEmbeddings(cohere_api_key="...", model='embed-english-v3.0')
 ```
 
-Otherwise you can initialize without any params:
+Otherwise you can initialize simply as shown below:
 ```python
 from langchain_cohere import CohereEmbeddings
 
-embeddings_model = CohereEmbeddings()
+embeddings_model = CohereEmbeddings(model='embed-english-v3.0')
 ```
+Do note that it is mandatory to pass the model parameter while initializing the CohereEmbeddings class.
 
   </TabItem>
   <TabItem value="huggingface" label="Hugging Face">

docs/docs/how_to/hybrid.ipynb

@@ -9,11 +9,13 @@
    "source": [
     "# Hybrid Search\n",
     "\n",
-    "The standard search in LangChain is done by vector similarity. However, a number of vectorstores implementations (Astra DB, ElasticSearch, Neo4J, AzureSearch, ...) also support more advanced search combining vector similarity search and other search techniques (full-text, BM25, and so on). This is generally referred to as \"Hybrid\" search.\n",
+    "The standard search in LangChain is done by vector similarity. However, a number of vectorstores implementations (Astra DB, ElasticSearch, Neo4J, AzureSearch, Qdrant...) also support more advanced search combining vector similarity search and other search techniques (full-text, BM25, and so on). This is generally referred to as \"Hybrid\" search.\n",
     "\n",
     "**Step 1: Make sure the vectorstore you are using supports hybrid search**\n",
     "\n",
-    "At the moment, there is no unified way to perform hybrid search in LangChain. Each vectorstore may have their own way to do it. This is generally exposed as a keyword argument that is passed in during `similarity_search`. By reading the documentation or source code, figure out whether the vectorstore you are using supports hybrid search, and, if so, how to use it.\n",
+    "At the moment, there is no unified way to perform hybrid search in LangChain. Each vectorstore may have their own way to do it. This is generally exposed as a keyword argument that is passed in during `similarity_search`.\n",
+    "\n",
+    "By reading the documentation or source code, figure out whether the vectorstore you are using supports hybrid search, and, if so, how to use it.\n",
     "\n",
     "**Step 2: Add that parameter as a configurable field for the chain**\n",
     "\n",

docs/docs/how_to/index.mdx

@@ -43,6 +43,7 @@ This highlights functionality that is core to using LangChain.
 - [How to: create a dynamic (self-constructing) chain](/docs/how_to/dynamic_chain/)
 - [How to: inspect runnables](/docs/how_to/inspect)
 - [How to: add fallbacks to a runnable](/docs/how_to/fallbacks)
+- [How to: migrate chains to LCEL](/docs/how_to/migrate_chains)
 
 ## Components
 
@@ -83,8 +84,8 @@ These are the core building blocks you can use when building applications.
 - [How to: use chat model to call tools](/docs/how_to/tool_calling)
 - [How to: stream tool calls](/docs/how_to/tool_streaming)
 - [How to: few shot prompt tool behavior](/docs/how_to/tools_few_shot)
-- [How to: bind model-specific formated tools](/docs/how_to/tools_model_specific)
-- [How to: force specific tool call](/docs/how_to/tool_choice)
+- [How to: bind model-specific formatted tools](/docs/how_to/tools_model_specific)
+- [How to: force a specific tool call](/docs/how_to/tool_choice)
 - [How to: init any model in one line](/docs/how_to/chat_models_universal_init/)
 
 ### Messages
@@ -182,10 +183,11 @@ Indexing is the process of keeping your vectorstore in-sync with the underlying
 
 ### Tools
 
-LangChain [Tools](/docs/concepts/#tools) contain a description of the tool (to pass to the language model) as well as the implementation of the function to call.
+LangChain [Tools](/docs/concepts/#tools) contain a description of the tool (to pass to the language model) as well as the implementation of the function to call. Refer [here](/docs/integrations/tools/) for a list of pre-buit tools. 
 
 - [How to: create custom tools](/docs/how_to/custom_tools)
 - [How to: use built-in tools and built-in toolkits](/docs/how_to/tools_builtin)
+- [How to: convert Runnables to tools](/docs/how_to/convert_runnable_to_tool)
 - [How to: use chat model to call tools](/docs/how_to/tool_calling)
 - [How to: pass tool results back to model](/docs/how_to/tool_results_pass_to_model)
 - [How to: add ad-hoc tool calling capability to LLMs and chat models](/docs/how_to/tools_prompting)
@@ -193,6 +195,9 @@ LangChain [Tools](/docs/concepts/#tools) contain a description of the tool (to p
 - [How to: add a human in the loop to tool usage](/docs/how_to/tools_human)
 - [How to: handle errors when calling tools](/docs/how_to/tools_error)
 - [How to: disable parallel tool calling](/docs/how_to/tool_choice)
+- [How to: access the `RunnableConfig` object within a custom tool](/docs/how_to/tool_configure)
+- [How to: stream events from child runs within a custom tool](/docs/how_to/tool_stream_events)
+- [How to: return extra artifacts from a tool](/docs/how_to/tool_artifacts/)
 
 ### Multimodal
 
@@ -204,7 +209,7 @@ LangChain [Tools](/docs/concepts/#tools) contain a description of the tool (to p
 
 :::note
 
-For in depth how-to guides for agents, please check out [LangGraph](https://github.com/langchain-ai/langgraph) documentation.
+For in depth how-to guides for agents, please check out [LangGraph](https://langchain-ai.github.io/langgraph/) documentation.
 
 :::
 
@@ -220,6 +225,7 @@ For in depth how-to guides for agents, please check out [LangGraph](https://gith
 - [How to: pass callbacks into a module constructor](/docs/how_to/callbacks_constructor)
 - [How to: create custom callback handlers](/docs/how_to/custom_callbacks)
 - [How to: use callbacks in async environments](/docs/how_to/callbacks_async)
+- [How to: dispatch custom callback events](/docs/how_to/callbacks_custom_events)
 
 ### Custom
 
@@ -232,6 +238,7 @@ All of LangChain components can easily be extended to support your own versions.
 - [How to: write a custom output parser class](/docs/how_to/output_parser_custom)
 - [How to: create custom callback handlers](/docs/how_to/custom_callbacks)
 - [How to: define a custom tool](/docs/how_to/custom_tools)
+- [How to: dispatch custom callback events](/docs/how_to/callbacks_custom_events)
 
 ### Serialization
 - [How to: save and load LangChain objects](/docs/how_to/serialization)

docs/docs/how_to/merge_message_runs.ipynb

@@ -63,6 +63,38 @@
     "Notice that if the contents of one of the messages to merge is a list of content blocks then the merged message will have a list of content blocks. And if both messages to merge have string contents then those are concatenated with a newline character."
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "11f7e8d3",
+   "metadata": {},
+   "source": [
+    "The `merge_message_runs` utility also works with messages composed together using the overloaded `+` operation:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b51855c5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "messages = (\n",
+    "    SystemMessage(\"you're a good assistant.\")\n",
+    "    + SystemMessage(\"you always respond with a joke.\")\n",
+    "    + HumanMessage([{\"type\": \"text\", \"text\": \"i wonder why it's called langchain\"}])\n",
+    "    + HumanMessage(\"and who is harrison chasing anyways\")\n",
+    "    + AIMessage(\n",
+    "        'Well, I guess they thought \"WordRope\" and \"SentenceString\" just didn\\'t have the same ring to it!'\n",
+    "    )\n",
+    "    + AIMessage(\n",
+    "        \"Why, he's probably chasing after the last cup of coffee in the office!\"\n",
+    "    )\n",
+    ")\n",
+    "\n",
+    "merged = merge_message_runs(messages)\n",
+    "print(\"\\n\\n\".join([repr(x) for x in merged]))"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "1b2eee74-71c8-4168-b968-bca580c25d18",

docs/docs/how_to/migrate_chains.ipynb

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

docs/docs/how_to/tool_artifacts.ipynb

@@ -0,0 +1,395 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "503e36ae-ca62-4f8a-880c-4fe78ff5df93",
+   "metadata": {},
+   "source": [
+    "# How to return extra artifacts from a tool\n",
+    "\n",
+    ":::info Prerequisites\n",
+    "This guide assumes familiarity with the following concepts:\n",
+    "\n",
+    "- [Tools](/docs/concepts/#tools)\n",
+    "- [Function/tool calling](/docs/concepts/#functiontool-calling)\n",
+    "\n",
+    ":::\n",
+    "\n",
+    "Tools are utilities that can be called by a model, and whose outputs are designed to be fed back to a model. Sometimes, however, there are artifacts of a tool's execution that we want to make accessible to downstream components in our chain or agent, but that we don't want to expose to the model itself. For example if a tool returns a custom object, a dataframe or an image, we may want to pass some metadata about this output to the model without passing the actual output to the model. At the same time, we may want to be able to access this full output elsewhere, for example in downstream tools.\n",
+    "\n",
+    "The Tool and [ToolMessage](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.tool.ToolMessage.html) interfaces make it possible to distinguish between the parts of the tool output meant for the model (this is the ToolMessage.content) and those parts which are meant for use outside the model (ToolMessage.artifact).\n",
+    "\n",
+    ":::info Requires ``langchain-core >= 0.2.19``\n",
+    "\n",
+    "This functionality was added in ``langchain-core == 0.2.19``. Please make sure your package is up to date.\n",
+    "\n",
+    ":::\n",
+    "\n",
+    "## Defining the tool\n",
+    "\n",
+    "If we want our tool to distinguish between message content and other artifacts, we need to specify `response_format=\"content_and_artifact\"` when defining our tool and make sure that we return a tuple of (content, artifact):"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "762b9199-885f-4946-9c98-cc54d72b0d76",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU \"langchain-core>=0.2.19\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "b9eb179d-1f41-4748-9866-b3d3e8c73cd0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import random\n",
+    "from typing import List, Tuple\n",
+    "\n",
+    "from langchain_core.tools import tool\n",
+    "\n",
+    "\n",
+    "@tool(response_format=\"content_and_artifact\")\n",
+    "def generate_random_ints(min: int, max: int, size: int) -> Tuple[str, List[int]]:\n",
+    "    \"\"\"Generate size random ints in the range [min, max].\"\"\"\n",
+    "    array = [random.randint(min, max) for _ in range(size)]\n",
+    "    content = f\"Successfully generated array of {size} random ints in [{min}, {max}].\"\n",
+    "    return content, array"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0ab05d25-af4a-4e5a-afe2-f090416d7ee7",
+   "metadata": {},
+   "source": [
+    "## Invoking the tool with ToolCall\n",
+    "\n",
+    "If we directly invoke our tool with just the tool arguments, you'll notice that we only get back the content part of the Tool output:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "5e7d5e77-3102-4a59-8ade-e4e699dd1817",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Successfully generated array of 10 random ints in [0, 9].'"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Failed to batch ingest runs: LangSmithRateLimitError('Rate limit exceeded for https://api.smith.langchain.com/runs/batch. HTTPError(\\'429 Client Error: Too Many Requests for url: https://api.smith.langchain.com/runs/batch\\', \\'{\"detail\":\"Monthly unique traces usage limit exceeded\"}\\')')\n"
+     ]
+    }
+   ],
+   "source": [
+    "generate_random_ints.invoke({\"min\": 0, \"max\": 9, \"size\": 10})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "30db7228-f04c-489e-afda-9a572eaa90a1",
+   "metadata": {},
+   "source": [
+    "In order to get back both the content and the artifact, we need to invoke our model with a ToolCall (which is just a dictionary with \"name\", \"args\", \"id\" and \"type\" keys), which has additional info needed to generate a ToolMessage like the tool call ID:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "da1d939d-a900-4b01-92aa-d19011a6b034",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "ToolMessage(content='Successfully generated array of 10 random ints in [0, 9].', name='generate_random_ints', tool_call_id='123', artifact=[2, 8, 0, 6, 0, 0, 1, 5, 0, 0])"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "generate_random_ints.invoke(\n",
+    "    {\n",
+    "        \"name\": \"generate_random_ints\",\n",
+    "        \"args\": {\"min\": 0, \"max\": 9, \"size\": 10},\n",
+    "        \"id\": \"123\",  # required\n",
+    "        \"type\": \"tool_call\",  # required\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a3cfc03d-020b-42c7-b0f8-c824af19e45e",
+   "metadata": {},
+   "source": [
+    "## Using with a model\n",
+    "\n",
+    "With a [tool-calling model](/docs/how_to/tool_calling/), we can easily use a model to call our Tool and generate ToolMessages:\n",
+    "\n",
+    "```{=mdx}\n",
+    "import ChatModelTabs from \"@theme/ChatModelTabs\";\n",
+    "\n",
+    "<ChatModelTabs\n",
+    "  customVarName=\"llm\"\n",
+    "/>\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "74de0286-b003-4b48-9cdd-ecab435515ca",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# | echo: false\n",
+    "# | output: false\n",
+    "\n",
+    "from langchain_anthropic import ChatAnthropic\n",
+    "\n",
+    "llm = ChatAnthropic(model=\"claude-3-5-sonnet-20240620\", temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "8a67424b-d19c-43df-ac7b-690bca42146c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'name': 'generate_random_ints',\n",
+       "  'args': {'min': 1, 'max': 24, 'size': 6},\n",
+       "  'id': 'toolu_01EtALY3Wz1DVYhv1TLvZGvE',\n",
+       "  'type': 'tool_call'}]"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "llm_with_tools = llm.bind_tools([generate_random_ints])\n",
+    "\n",
+    "ai_msg = llm_with_tools.invoke(\"generate 6 positive ints less than 25\")\n",
+    "ai_msg.tool_calls"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "00c4e906-3ca8-41e8-a0be-65cb0db7d574",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "ToolMessage(content='Successfully generated array of 6 random ints in [1, 24].', name='generate_random_ints', tool_call_id='toolu_01EtALY3Wz1DVYhv1TLvZGvE', artifact=[2, 20, 23, 8, 1, 15])"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "generate_random_ints.invoke(ai_msg.tool_calls[0])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ddef2690-70de-4542-ab20-2337f77f3e46",
+   "metadata": {},
+   "source": [
+    "If we just pass in the tool call args, we'll only get back the content:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "f4a6c9a6-0ffc-4b0e-a59f-f3c3d69d824d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Successfully generated array of 6 random ints in [1, 24].'"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "generate_random_ints.invoke(ai_msg.tool_calls[0][\"args\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "98d6443b-ff41-4d91-8523-b6274fc74ee5",
+   "metadata": {},
+   "source": [
+    "If we wanted to declaratively create a chain, we could do this:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "eb55ec23-95a4-464e-b886-d9679bf3aaa2",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[ToolMessage(content='Successfully generated array of 1 random ints in [1, 5].', name='generate_random_ints', tool_call_id='toolu_01FwYhnkwDPJPbKdGq4ng6uD', artifact=[5])]"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from operator import attrgetter\n",
+    "\n",
+    "chain = llm_with_tools | attrgetter(\"tool_calls\") | generate_random_ints.map()\n",
+    "\n",
+    "chain.invoke(\"give me a random number between 1 and 5\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4df46be2-babb-4bfe-a641-91cd3d03ffaf",
+   "metadata": {},
+   "source": [
+    "## Creating from BaseTool class\n",
+    "\n",
+    "If you want to create a BaseTool object directly, instead of decorating a function with `@tool`, you can do so like this:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "9a9129e1-6aee-4a10-ad57-62ef3bf0276c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.tools import BaseTool\n",
+    "\n",
+    "\n",
+    "class GenerateRandomFloats(BaseTool):\n",
+    "    name: str = \"generate_random_floats\"\n",
+    "    description: str = \"Generate size random floats in the range [min, max].\"\n",
+    "    response_format: str = \"content_and_artifact\"\n",
+    "\n",
+    "    ndigits: int = 2\n",
+    "\n",
+    "    def _run(self, min: float, max: float, size: int) -> Tuple[str, List[float]]:\n",
+    "        range_ = max - min\n",
+    "        array = [\n",
+    "            round(min + (range_ * random.random()), ndigits=self.ndigits)\n",
+    "            for _ in range(size)\n",
+    "        ]\n",
+    "        content = f\"Generated {size} floats in [{min}, {max}], rounded to {self.ndigits} decimals.\"\n",
+    "        return content, array\n",
+    "\n",
+    "    # Optionally define an equivalent async method\n",
+    "\n",
+    "    # async def _arun(self, min: float, max: float, size: int) -> Tuple[str, List[float]]:\n",
+    "    #     ..."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "d7322619-f420-4b29-8ee5-023e693d0179",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Generated 3 floats in [0.1, 3.3333], rounded to 4 decimals.'"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "rand_gen = GenerateRandomFloats(ndigits=4)\n",
+    "rand_gen.invoke({\"min\": 0.1, \"max\": 3.3333, \"size\": 3})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "0892f277-23a6-4bb8-a0e9-59f533ac9750",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "ToolMessage(content='Generated 3 floats in [0.1, 3.3333], rounded to 4 decimals.', name='generate_random_floats', tool_call_id='123', artifact=[1.5789, 2.464, 2.2719])"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "rand_gen.invoke(\n",
+    "    {\n",
+    "        \"name\": \"generate_random_floats\",\n",
+    "        \"args\": {\"min\": 0.1, \"max\": 3.3333, \"size\": 3},\n",
+    "        \"id\": \"123\",\n",
+    "        \"type\": \"tool_call\",\n",
+    "    }\n",
+    ")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "poetry-venv-311",
+   "language": "python",
+   "name": "poetry-venv-311"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/how_to/tool_choice.ipynb

@@ -6,6 +6,14 @@
    "source": [
     "# How to force tool calling behavior\n",
     "\n",
+    ":::info Prerequisites\n",
+    "\n",
+    "This guide assumes familiarity with the following concepts:\n",
+    "- [Chat models](/docs/concepts/#chat-models)\n",
+    "- [LangChain Tools](/docs/concepts/#tools)\n",
+    "- [How to use a model to call tools](/docs/how_to/tool_calling)\n",
+    ":::\n",
+    "\n",
     "In order to force our LLM to spelect a specific tool, we can use the `tool_choice` parameter to ensure certain behavior. First, let's define our model and tools:"
    ]
   },

docs/docs/how_to/tool_configure.ipynb

@@ -0,0 +1,132 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# How to access the RunnableConfig object within a custom tool\n",
+    "\n",
+    ":::info Prerequisites\n",
+    "\n",
+    "This guide assumes familiarity with the following concepts:\n",
+    "\n",
+    "- [LangChain Tools](/docs/concepts/#tools)\n",
+    "- [Custom tools](/docs/how_to/custom_tools)\n",
+    "- [LangChain Expression Language (LCEL)](/docs/concepts/#langchain-expression-language-lcel)\n",
+    "- [Configuring runnable behavior](/docs/how_to/configure/)\n",
+    "\n",
+    ":::\n",
+    "\n",
+    "If you have a tool  that call chat models, retrievers, or other runnables, you may want to access internal events from those runnables or configure them with additional properties. This guide shows you how to manually pass parameters properly so that you can do this using the `astream_events()` method.\n",
+    "\n",
+    "Tools are runnables, and you can treat them the same way as any other runnable at the interface level - you can call `invoke()`, `batch()`, and `stream()` on them as normal. However, when writing custom tools, you may want to invoke other runnables like chat models or retrievers. In order to properly trace and configure those sub-invocations, you'll need to manually access and pass in the tool's current [`RunnableConfig`](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.config.RunnableConfig.html) object. This guide show you some examples of how to do that.\n",
+    "\n",
+    ":::caution Compatibility\n",
+    "\n",
+    "This guide requires `langchain-core>=0.2.16`.\n",
+    "\n",
+    ":::\n",
+    "\n",
+    "## Inferring by parameter type\n",
+    "\n",
+    "To access reference the active config object from your custom tool, you'll need to add a parameter to your tool's signature typed as `RunnableConfig`. When you invoke your tool, LangChain will inspect your tool's signature, look for a parameter typed as `RunnableConfig`, and if it exists, populate that parameter with the correct value.\n",
+    "\n",
+    "**Note:** The actual name of the parameter doesn't matter, only the typing.\n",
+    "\n",
+    "To illustrate this, define a custom tool that takes a two parameters - one typed as a string, the other typed as `RunnableConfig`:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU langchain_core"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.runnables import RunnableConfig\n",
+    "from langchain_core.tools import tool\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "async def reverse_tool(text: str, special_config_param: RunnableConfig) -> str:\n",
+    "    \"\"\"A test tool that combines input text with a configurable parameter.\"\"\"\n",
+    "    return (text + special_config_param[\"configurable\"][\"additional_field\"])[::-1]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Then, if we invoke the tool with a `config` containing a `configurable` field, we can see that `additional_field` is passed through correctly:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'321cba'"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "await reverse_tool.ainvoke(\n",
+    "    {\"text\": \"abc\"}, config={\"configurable\": {\"additional_field\": \"123\"}}\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Next steps\n",
+    "\n",
+    "You've now seen how to configure and stream events from within a tool. Next, check out the following guides for more on using tools:\n",
+    "\n",
+    "- [Stream events from child runs within a custom tool](/docs/how_to/tool_stream_events/)\n",
+    "- Pass [tool results back to a model](/docs/how_to/tool_results_pass_to_model)\n",
+    "\n",
+    "You can also check out some more specific uses of tool calling:\n",
+    "\n",
+    "- Building [tool-using chains and agents](/docs/how_to#tools)\n",
+    "- Getting [structured outputs](/docs/how_to/structured_output/) from models"
+   ]
+  }
+ ],
+ "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": "3.10.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/docs/how_to/tool_results_pass_to_model.ipynb

@@ -6,12 +6,20 @@
    "source": [
     "# How to pass tool outputs to the model\n",
     "\n",
-    "If we're using the model-generated tool invocations to actually call tools and want to pass the tool results back to the model, we can do so using `ToolMessage`s. First, let's define our tools and our model."
+    ":::info Prerequisites\n",
+    "This guide assumes familiarity with the following concepts:\n",
+    "\n",
+    "- [Tools](/docs/concepts/#tools)\n",
+    "- [Function/tool calling](/docs/concepts/#functiontool-calling)\n",
+    "\n",
+    ":::\n",
+    "\n",
+    "If we're using the model-generated tool invocations to actually call tools and want to pass the tool results back to the model, we can do so using `ToolMessage`s and `ToolCall`s. First, let's define our tools and our model."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -35,7 +43,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -54,25 +62,32 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Now we can use ``ToolMessage`` to pass back the output of the tool calls to the model."
+    "The nice thing about Tools is that if we invoke them with a ToolCall, we'll automatically get back a ToolMessage that can be fed back to the model: \n",
+    "\n",
+    ":::info Requires ``langchain-core >= 0.2.19``\n",
+    "\n",
+    "This functionality was added in ``langchain-core == 0.2.19``. Please make sure your package is up to date.\n",
+    "\n",
+    ":::"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
        "[HumanMessage(content='What is 3 * 12? Also, what is 11 + 49?'),\n",
-       " AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_svc2GLSxNFALbaCAbSjMI9J8', 'function': {'arguments': '{\"a\": 3, \"b\": 12}', 'name': 'Multiply'}, 'type': 'function'}, {'id': 'call_r8jxte3zW6h3MEGV3zH2qzFh', 'function': {'arguments': '{\"a\": 11, \"b\": 49}', 'name': 'Add'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 50, 'prompt_tokens': 105, 'total_tokens': 155}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_d9767fc5b9', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-a79ad1dd-95f1-4a46-b688-4c83f327a7b3-0', tool_calls=[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_svc2GLSxNFALbaCAbSjMI9J8'}, {'name': 'Add', 'args': {'a': 11, 'b': 49}, 'id': 'call_r8jxte3zW6h3MEGV3zH2qzFh'}]),\n",
-       " ToolMessage(content='36', tool_call_id='call_svc2GLSxNFALbaCAbSjMI9J8'),\n",
-       " ToolMessage(content='60', tool_call_id='call_r8jxte3zW6h3MEGV3zH2qzFh')]"
+       " AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_Smg3NHJNxrKfAmd4f9GkaYn3', 'function': {'arguments': '{\"a\": 3, \"b\": 12}', 'name': 'multiply'}, 'type': 'function'}, {'id': 'call_55K1C0DmH6U5qh810gW34xZ0', 'function': {'arguments': '{\"a\": 11, \"b\": 49}', 'name': 'add'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 49, 'prompt_tokens': 88, 'total_tokens': 137}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-56657feb-96dd-456c-ab8e-1857eab2ade0-0', tool_calls=[{'name': 'multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_Smg3NHJNxrKfAmd4f9GkaYn3', 'type': 'tool_call'}, {'name': 'add', 'args': {'a': 11, 'b': 49}, 'id': 'call_55K1C0DmH6U5qh810gW34xZ0', 'type': 'tool_call'}], usage_metadata={'input_tokens': 88, 'output_tokens': 49, 'total_tokens': 137}),\n",
+       " ToolMessage(content='36', name='multiply', tool_call_id='call_Smg3NHJNxrKfAmd4f9GkaYn3'),\n",
+       " ToolMessage(content='60', name='add', tool_call_id='call_55K1C0DmH6U5qh810gW34xZ0')]"
       ]
      },
+     "execution_count": 5,
      "metadata": {},
-     "output_type": "display_data"
+     "output_type": "execute_result"
     }
    ],
    "source": [
@@ -85,24 +100,25 @@
     "messages.append(ai_msg)\n",
     "for tool_call in ai_msg.tool_calls:\n",
     "    selected_tool = {\"add\": add, \"multiply\": multiply}[tool_call[\"name\"].lower()]\n",
-    "    tool_output = selected_tool.invoke(tool_call[\"args\"])\n",
-    "    messages.append(ToolMessage(tool_output, tool_call_id=tool_call[\"id\"]))\n",
+    "    tool_msg = selected_tool.invoke(tool_call)\n",
+    "    messages.append(tool_msg)\n",
     "messages"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='3 * 12 is 36 and 11 + 49 is 60.', response_metadata={'token_usage': {'completion_tokens': 18, 'prompt_tokens': 171, 'total_tokens': 189}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_d9767fc5b9', 'finish_reason': 'stop', 'logprobs': None}, id='run-20b52149-e00d-48ea-97cf-f8de7a255f8c-0')"
+       "AIMessage(content='3 * 12 is 36 and 11 + 49 is 60.', response_metadata={'token_usage': {'completion_tokens': 18, 'prompt_tokens': 153, 'total_tokens': 171}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-ba5032f0-f773-406d-a408-8314e66511d0-0', usage_metadata={'input_tokens': 153, 'output_tokens': 18, 'total_tokens': 171})"
       ]
      },
+     "execution_count": 6,
      "metadata": {},
-     "output_type": "display_data"
+     "output_type": "execute_result"
     }
    ],
    "source": [
@@ -118,10 +134,24 @@
   }
  ],
  "metadata": {
+  "kernelspec": {
+   "display_name": "poetry-venv-311",
+   "language": "python",
+   "name": "poetry-venv-311"
+  },
   "language_info": {
-   "name": "python"
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.9"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

docs/docs/how_to/tool_runtime.ipynb

@@ -12,7 +12,7 @@
     "- [Chat models](/docs/concepts/#chat-models)\n",
     "- [LangChain Tools](/docs/concepts/#tools)\n",
     "- [How to create tools](/docs/how_to/custom_tools)\n",
-    "- [How to use a model to call tools](https://python.langchain.com/v0.2/docs/how_to/tool_calling)\n",
+    "- [How to use a model to call tools](/docs/how_to/tool_calling)\n",
     ":::\n",
     "\n",
     ":::{.callout-info} Supported models\n",

docs/docs/how_to/tool_stream_events.ipynb

@@ -0,0 +1,302 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# How to stream events from child runs within a custom tool\n",
+    "\n",
+    ":::info Prerequisites\n",
+    "\n",
+    "This guide assumes familiarity with the following concepts:\n",
+    "- [LangChain Tools](/docs/concepts/#tools)\n",
+    "- [Custom tools](/docs/how_to/custom_tools)\n",
+    "- [Using stream events](/docs/how_to/streaming/#using-stream-events)\n",
+    "- [Accessing RunnableConfig within a custom tool](/docs/how_to/tool_configure/)\n",
+    "\n",
+    ":::\n",
+    "\n",
+    "If you have tools that call chat models, retrievers, or other runnables, you may want to access internal events from those runnables or configure them with additional properties. This guide shows you how to manually pass parameters properly so that you can do this using the `astream_events()` method.\n",
+    "\n",
+    ":::caution Compatibility\n",
+    "\n",
+    "LangChain cannot automatically propagate configuration, including callbacks necessary for `astream_events()`, to child runnables if you are running `async` code in `python<=3.10`. This is a common reason why you may fail to see events being emitted from custom runnables or tools.\n",
+    "\n",
+    "If you are running python<=3.10, you will need to manually propagate the `RunnableConfig` object to the child runnable in async environments. For an example of how to manually propagate the config, see the implementation of the `bar` RunnableLambda below.\n",
+    "\n",
+    "If you are running python>=3.11, the `RunnableConfig` will automatically propagate to child runnables in async environment. However, it is still a good idea to propagate the `RunnableConfig` manually if your code may run in older Python versions.\n",
+    "\n",
+    "This guide also requires `langchain-core>=0.2.16`.\n",
+    ":::\n",
+    "\n",
+    "Say you have a custom tool that calls a chain that condenses its input by prompting a chat model to return only 10 words, then reversing the output. First, define it in a naive way:\n",
+    "\n",
+    "```{=mdx}\n",
+    "import ChatModelTabs from \"@theme/ChatModelTabs\";\n",
+    "\n",
+    "<ChatModelTabs customVarName=\"model\" />\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# | output: false\n",
+    "# | echo: false\n",
+    "\n",
+    "%pip install -qU langchain langchain_anthropic langchain_core\n",
+    "\n",
+    "import os\n",
+    "from getpass import getpass\n",
+    "\n",
+    "from langchain_anthropic import ChatAnthropic\n",
+    "\n",
+    "if \"ANTHROPIC_API_KEY\" not in os.environ:\n",
+    "    os.environ[\"ANTHROPIC_API_KEY\"] = getpass()\n",
+    "\n",
+    "model = ChatAnthropic(model=\"claude-3-5-sonnet-20240620\", temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_core.tools import tool\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "async def special_summarization_tool(long_text: str) -> str:\n",
+    "    \"\"\"A tool that summarizes input text using advanced techniques.\"\"\"\n",
+    "    prompt = ChatPromptTemplate.from_template(\n",
+    "        \"You are an expert writer. Summarize the following text in 10 words or less:\\n\\n{long_text}\"\n",
+    "    )\n",
+    "\n",
+    "    def reverse(x: str):\n",
+    "        return x[::-1]\n",
+    "\n",
+    "    chain = prompt | model | StrOutputParser() | reverse\n",
+    "    summary = await chain.ainvoke({\"long_text\": long_text})\n",
+    "    return summary"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Invoking the tool directly works just fine:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'.yad noitaudarg rof tiftuo sesoohc yrraB ;scisyhp seifed eeB'"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "LONG_TEXT = \"\"\"\n",
+    "NARRATOR:\n",
+    "(Black screen with text; The sound of buzzing bees can be heard)\n",
+    "According to all known laws of aviation, there is no way a bee should be able to fly. Its wings are too small to get its fat little body off the ground. The bee, of course, flies anyway because bees don't care what humans think is impossible.\n",
+    "BARRY BENSON:\n",
+    "(Barry is picking out a shirt)\n",
+    "Yellow, black. Yellow, black. Yellow, black. Yellow, black. Ooh, black and yellow! Let's shake it up a little.\n",
+    "JANET BENSON:\n",
+    "Barry! Breakfast is ready!\n",
+    "BARRY:\n",
+    "Coming! Hang on a second.\n",
+    "\"\"\"\n",
+    "\n",
+    "await special_summarization_tool.ainvoke({\"long_text\": LONG_TEXT})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "But if you wanted to access the raw output from the chat model rather than the full tool, you might try to use the [`astream_events()`](/docs/how_to/streaming/#using-stream-events) method and look for an `on_chat_model_end` event. Here's what happens:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "stream = special_summarization_tool.astream_events(\n",
+    "    {\"long_text\": LONG_TEXT}, version=\"v2\"\n",
+    ")\n",
+    "\n",
+    "async for event in stream:\n",
+    "    if event[\"event\"] == \"on_chat_model_end\":\n",
+    "        # Never triggers in python<=3.10!\n",
+    "        print(event)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "You'll notice (unless you're running through this guide in `python>=3.11`) that there are no chat model events emitted from the child run!\n",
+    "\n",
+    "This is because the example above does not pass the tool's config object into the internal chain. To fix this, redefine your tool to take a special parameter typed as `RunnableConfig` (see [this guide](/docs/how_to/tool_configure) for more details). You'll also need to pass that parameter through into the internal chain when executing it:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.runnables import RunnableConfig\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "async def special_summarization_tool_with_config(\n",
+    "    long_text: str, config: RunnableConfig\n",
+    ") -> str:\n",
+    "    \"\"\"A tool that summarizes input text using advanced techniques.\"\"\"\n",
+    "    prompt = ChatPromptTemplate.from_template(\n",
+    "        \"You are an expert writer. Summarize the following text in 10 words or less:\\n\\n{long_text}\"\n",
+    "    )\n",
+    "\n",
+    "    def reverse(x: str):\n",
+    "        return x[::-1]\n",
+    "\n",
+    "    chain = prompt | model | StrOutputParser() | reverse\n",
+    "    # Pass the \"config\" object as an argument to any executed runnables\n",
+    "    summary = await chain.ainvoke({\"long_text\": long_text}, config=config)\n",
+    "    return summary"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "And now try the same `astream_events()` call as before with your new tool:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'event': 'on_chat_model_end', 'data': {'output': AIMessage(content='Bee defies physics; Barry chooses outfit for graduation day.', response_metadata={'stop_reason': 'end_turn', 'stop_sequence': None}, id='run-d23abc80-0dce-4f74-9d7b-fb98ca4f2a9e', usage_metadata={'input_tokens': 182, 'output_tokens': 16, 'total_tokens': 198}), 'input': {'messages': [[HumanMessage(content=\"You are an expert writer. Summarize the following text in 10 words or less:\\n\\n\\nNARRATOR:\\n(Black screen with text; The sound of buzzing bees can be heard)\\nAccording to all known laws of aviation, there is no way a bee should be able to fly. Its wings are too small to get its fat little body off the ground. The bee, of course, flies anyway because bees don't care what humans think is impossible.\\nBARRY BENSON:\\n(Barry is picking out a shirt)\\nYellow, black. Yellow, black. Yellow, black. Yellow, black. Ooh, black and yellow! Let's shake it up a little.\\nJANET BENSON:\\nBarry! Breakfast is ready!\\nBARRY:\\nComing! Hang on a second.\\n\")]]}}, 'run_id': 'd23abc80-0dce-4f74-9d7b-fb98ca4f2a9e', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['f25c41fe-8972-4893-bc40-cecf3922c1fa']}\n"
+     ]
+    }
+   ],
+   "source": [
+    "stream = special_summarization_tool_with_config.astream_events(\n",
+    "    {\"long_text\": LONG_TEXT}, version=\"v2\"\n",
+    ")\n",
+    "\n",
+    "async for event in stream:\n",
+    "    if event[\"event\"] == \"on_chat_model_end\":\n",
+    "        print(event)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Awesome! This time there's an event emitted.\n",
+    "\n",
+    "For streaming, `astream_events()` automatically calls internal runnables in a chain with streaming enabled if possible, so if you wanted to a stream of tokens as they are generated from the chat model, you could simply filter to look for `on_chat_model_stream` events with no other changes:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='', id='run-f24ab147-0b82-4e63-810a-b12bd8d1fb42', usage_metadata={'input_tokens': 182, 'output_tokens': 0, 'total_tokens': 182})}, 'run_id': 'f24ab147-0b82-4e63-810a-b12bd8d1fb42', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['385f3612-417c-4a70-aae0-cce3a5ba6fb6']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='Bee', id='run-f24ab147-0b82-4e63-810a-b12bd8d1fb42')}, 'run_id': 'f24ab147-0b82-4e63-810a-b12bd8d1fb42', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['385f3612-417c-4a70-aae0-cce3a5ba6fb6']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content=' def', id='run-f24ab147-0b82-4e63-810a-b12bd8d1fb42')}, 'run_id': 'f24ab147-0b82-4e63-810a-b12bd8d1fb42', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['385f3612-417c-4a70-aae0-cce3a5ba6fb6']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='ies physics', id='run-f24ab147-0b82-4e63-810a-b12bd8d1fb42')}, 'run_id': 'f24ab147-0b82-4e63-810a-b12bd8d1fb42', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['385f3612-417c-4a70-aae0-cce3a5ba6fb6']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content=';', id='run-f24ab147-0b82-4e63-810a-b12bd8d1fb42')}, 'run_id': 'f24ab147-0b82-4e63-810a-b12bd8d1fb42', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['385f3612-417c-4a70-aae0-cce3a5ba6fb6']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content=' Barry', id='run-f24ab147-0b82-4e63-810a-b12bd8d1fb42')}, 'run_id': 'f24ab147-0b82-4e63-810a-b12bd8d1fb42', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['385f3612-417c-4a70-aae0-cce3a5ba6fb6']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content=' cho', id='run-f24ab147-0b82-4e63-810a-b12bd8d1fb42')}, 'run_id': 'f24ab147-0b82-4e63-810a-b12bd8d1fb42', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['385f3612-417c-4a70-aae0-cce3a5ba6fb6']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='oses outfit', id='run-f24ab147-0b82-4e63-810a-b12bd8d1fb42')}, 'run_id': 'f24ab147-0b82-4e63-810a-b12bd8d1fb42', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['385f3612-417c-4a70-aae0-cce3a5ba6fb6']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content=' for', id='run-f24ab147-0b82-4e63-810a-b12bd8d1fb42')}, 'run_id': 'f24ab147-0b82-4e63-810a-b12bd8d1fb42', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['385f3612-417c-4a70-aae0-cce3a5ba6fb6']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content=' graduation', id='run-f24ab147-0b82-4e63-810a-b12bd8d1fb42')}, 'run_id': 'f24ab147-0b82-4e63-810a-b12bd8d1fb42', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['385f3612-417c-4a70-aae0-cce3a5ba6fb6']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content=' day', id='run-f24ab147-0b82-4e63-810a-b12bd8d1fb42')}, 'run_id': 'f24ab147-0b82-4e63-810a-b12bd8d1fb42', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['385f3612-417c-4a70-aae0-cce3a5ba6fb6']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='.', id='run-f24ab147-0b82-4e63-810a-b12bd8d1fb42')}, 'run_id': 'f24ab147-0b82-4e63-810a-b12bd8d1fb42', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['385f3612-417c-4a70-aae0-cce3a5ba6fb6']}\n",
+      "{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='', response_metadata={'stop_reason': 'end_turn', 'stop_sequence': None}, id='run-f24ab147-0b82-4e63-810a-b12bd8d1fb42', usage_metadata={'input_tokens': 0, 'output_tokens': 16, 'total_tokens': 16})}, 'run_id': 'f24ab147-0b82-4e63-810a-b12bd8d1fb42', 'name': 'ChatAnthropic', 'tags': ['seq:step:2'], 'metadata': {'ls_provider': 'anthropic', 'ls_model_name': 'claude-3-5-sonnet-20240620', 'ls_model_type': 'chat', 'ls_temperature': 0.0, 'ls_max_tokens': 1024}, 'parent_ids': ['385f3612-417c-4a70-aae0-cce3a5ba6fb6']}\n"
+     ]
+    }
+   ],
+   "source": [
+    "stream = special_summarization_tool_with_config.astream_events(\n",
+    "    {\"long_text\": LONG_TEXT}, version=\"v2\"\n",
+    ")\n",
+    "\n",
+    "async for event in stream:\n",
+    "    if event[\"event\"] == \"on_chat_model_stream\":\n",
+    "        print(event)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Next steps\n",
+    "\n",
+    "You've now seen how to stream events from within a tool. Next, check out the following guides for more on using tools:\n",
+    "\n",
+    "- Pass [runtime values to tools](/docs/how_to/tool_runtime)\n",
+    "- Pass [tool results back to a model](/docs/how_to/tool_results_pass_to_model)\n",
+    "- [Dispatch custom callback events](/docs/how_to/callbacks_custom_events)\n",
+    "\n",
+    "You can also check out some more specific uses of tool calling:\n",
+    "\n",
+    "- Building [tool-using chains and agents](/docs/how_to#tools)\n",
+    "- Getting [structured outputs](/docs/how_to/structured_output/) from models"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

docs/docs/how_to/tools_chain.ipynb

@@ -419,13 +419,13 @@
       "Invoking: `exponentiate` with `{'base': 405, 'exponent': 2}`\n",
       "\n",
       "\n",
-      "\u001b[0m\u001b[38;5;200m\u001b[1;3m164025\u001b[0m\u001b[32;1m\u001b[1;3mThe result of taking 3 to the fifth power is 243. \n",
+      "\u001b[0m\u001b[38;5;200m\u001b[1;3m13286025\u001b[0m\u001b[32;1m\u001b[1;3mThe result of taking 3 to the fifth power is 243. \n",
       "\n",
       "The sum of twelve and three is 15. \n",
       "\n",
       "Multiplying 243 by 15 gives 3645. \n",
       "\n",
-      "Finally, squaring 3645 gives 164025.\u001b[0m\n",
+      "Finally, squaring 3645 gives 13286025.\u001b[0m\n",
       "\n",
       "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
@@ -434,7 +434,7 @@
      "data": {
       "text/plain": [
        "{'input': 'Take 3 to the fifth power and multiply that by the sum of twelve and three, then square the whole result',\n",
-       " 'output': 'The result of taking 3 to the fifth power is 243. \\n\\nThe sum of twelve and three is 15. \\n\\nMultiplying 243 by 15 gives 3645. \\n\\nFinally, squaring 3645 gives 164025.'}"
+       " 'output': 'The result of taking 3 to the fifth power is 243. \\n\\nThe sum of twelve and three is 15. \\n\\nMultiplying 243 by 15 gives 3645. \\n\\nFinally, squaring 3645 gives 13286025.'}"
       ]
      },
      "execution_count": 18,

docs/docs/how_to/tools_error.ipynb

@@ -7,9 +7,18 @@
    "source": [
     "# How to handle tool errors\n",
     "\n",
-    "Using a model to invoke a tool has some obvious potential failure modes. Firstly, the model needs to return a output that can be parsed at all. Secondly, the model needs to return tool arguments that are valid.\n",
+    ":::info Prerequisites\n",
     "\n",
-    "We can build error handling into our chains to mitigate these failure modes."
+    "This guide assumes familiarity with the following concepts:\n",
+    "- [Chat models](/docs/concepts/#chat-models)\n",
+    "- [LangChain Tools](/docs/concepts/#tools)\n",
+    "- [How to use a model to call tools](/docs/how_to/tool_calling)\n",
+    "\n",
+    ":::\n",
+    "\n",
+    "Calling tools with an LLM is generally more reliable than pure prompting, but it isn't perfect. The model may try to call a tool that doesn't exist or fail to return arguments that match the requested schema. Strategies like keeping schemas simple, reducing the number of tools you pass at once, and having good names and descriptions can help mitigate this risk, but aren't foolproof.\n",
+    "\n",
+    "This guide covers some ways to build error handling into your chains to mitigate these failure modes."
    ]
   },
   {
@@ -42,7 +51,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "id": "08785b6d-722d-4620-b6ec-36deb3842c69",
    "metadata": {},
    "outputs": [],
@@ -72,7 +81,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 4,
    "id": "86258950-5e61-4340-81b9-84a5d26e8773",
    "metadata": {},
    "outputs": [],
@@ -82,12 +91,14 @@
     "\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass()\n",
+    "\n",
     "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 5,
    "id": "1d20604e-c4d1-4d21-841b-23e4f61aec36",
    "metadata": {},
    "outputs": [],
@@ -99,28 +110,13 @@
     "@tool\n",
     "def complex_tool(int_arg: int, float_arg: float, dict_arg: dict) -> int:\n",
     "    \"\"\"Do something complex with a complex tool.\"\"\"\n",
-    "    return int_arg * float_arg"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "553c2c13-28c8-4451-8a3a-6c31d52dc31d",
-   "metadata": {},
-   "outputs": [],
-   "source": [
+    "    return int_arg * float_arg\n",
+    "\n",
+    "\n",
     "llm_with_tools = llm.bind_tools(\n",
     "    [complex_tool],\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "802b2eca-9f79-4d6c-8257-85139ca5c752",
-   "metadata": {},
-   "outputs": [],
-   "source": [
+    ")\n",
+    "\n",
     "# Define chain\n",
     "chain = llm_with_tools | (lambda msg: msg.tool_calls[0][\"args\"]) | complex_tool"
    ]
@@ -135,7 +131,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 6,
    "id": "d354664c-ac44-4967-a35f-8912b3ad9477",
    "metadata": {},
    "outputs": [
@@ -146,14 +142,14 @@
      "traceback": [
       "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
       "\u001b[0;31mValidationError\u001b[0m                           Traceback (most recent call last)",
-      "Cell \u001b[0;32mIn[12], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mchain\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minvoke\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m      2\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43muse complex tool. the args are 5, 2.1, empty dictionary. don\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mt forget dict_arg\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\n\u001b[1;32m      3\u001b[0m \u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/langchain/libs/core/langchain_core/runnables/base.py:2499\u001b[0m, in \u001b[0;36mRunnableSequence.invoke\u001b[0;34m(self, input, config)\u001b[0m\n\u001b[1;32m   2497\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m   2498\u001b[0m     \u001b[38;5;28;01mfor\u001b[39;00m i, step \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28menumerate\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msteps):\n\u001b[0;32m-> 2499\u001b[0m         \u001b[38;5;28minput\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[43mstep\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minvoke\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   2500\u001b[0m \u001b[43m            \u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m   2501\u001b[0m \u001b[43m            \u001b[49m\u001b[38;5;66;43;03m# mark each step as a child run\u001b[39;49;00m\n\u001b[1;32m   2502\u001b[0m \u001b[43m            \u001b[49m\u001b[43mpatch_config\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   2503\u001b[0m \u001b[43m                \u001b[49m\u001b[43mconfig\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_child\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43mf\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mseq:step:\u001b[39;49m\u001b[38;5;132;43;01m{\u001b[39;49;00m\u001b[43mi\u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[38;5;132;43;01m}\u001b[39;49;00m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m   2504\u001b[0m \u001b[43m            \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   2505\u001b[0m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   2506\u001b[0m \u001b[38;5;66;03m# finish the root run\u001b[39;00m\n\u001b[1;32m   2507\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n",
-      "File \u001b[0;32m~/langchain/libs/core/langchain_core/tools.py:241\u001b[0m, in \u001b[0;36mBaseTool.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m    234\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21minvoke\u001b[39m(\n\u001b[1;32m    235\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m    236\u001b[0m     \u001b[38;5;28minput\u001b[39m: Union[\u001b[38;5;28mstr\u001b[39m, Dict],\n\u001b[1;32m    237\u001b[0m     config: Optional[RunnableConfig] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m    238\u001b[0m     \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Any,\n\u001b[1;32m    239\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Any:\n\u001b[1;32m    240\u001b[0m     config \u001b[38;5;241m=\u001b[39m ensure_config(config)\n\u001b[0;32m--> 241\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrun\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    242\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m    243\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mcallbacks\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    244\u001b[0m \u001b[43m        \u001b[49m\u001b[43mtags\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtags\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    245\u001b[0m \u001b[43m        \u001b[49m\u001b[43mmetadata\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmetadata\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    246\u001b[0m \u001b[43m        \u001b[49m\u001b[43mrun_name\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mrun_name\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    247\u001b[0m \u001b[43m        \u001b[49m\u001b[43mrun_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpop\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mrun_id\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    248\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    249\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/langchain/libs/core/langchain_core/tools.py:387\u001b[0m, in \u001b[0;36mBaseTool.run\u001b[0;34m(self, tool_input, verbose, start_color, color, callbacks, tags, metadata, run_name, run_id, **kwargs)\u001b[0m\n\u001b[1;32m    385\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m ValidationError \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    386\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandle_validation_error:\n\u001b[0;32m--> 387\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m    388\u001b[0m     \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandle_validation_error, \u001b[38;5;28mbool\u001b[39m):\n\u001b[1;32m    389\u001b[0m         observation \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mTool input validation error\u001b[39m\u001b[38;5;124m\"\u001b[39m\n",
-      "File \u001b[0;32m~/langchain/libs/core/langchain_core/tools.py:378\u001b[0m, in \u001b[0;36mBaseTool.run\u001b[0;34m(self, tool_input, verbose, start_color, color, callbacks, tags, metadata, run_name, run_id, **kwargs)\u001b[0m\n\u001b[1;32m    364\u001b[0m run_manager \u001b[38;5;241m=\u001b[39m callback_manager\u001b[38;5;241m.\u001b[39mon_tool_start(\n\u001b[1;32m    365\u001b[0m     {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mname\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mname, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdescription\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdescription},\n\u001b[1;32m    366\u001b[0m     tool_input \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(tool_input, \u001b[38;5;28mstr\u001b[39m) \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mstr\u001b[39m(tool_input),\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    375\u001b[0m     \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs,\n\u001b[1;32m    376\u001b[0m )\n\u001b[1;32m    377\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 378\u001b[0m     parsed_input \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_parse_input\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtool_input\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    379\u001b[0m     tool_args, tool_kwargs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_to_args_and_kwargs(parsed_input)\n\u001b[1;32m    380\u001b[0m     observation \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m    381\u001b[0m         \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_run(\u001b[38;5;241m*\u001b[39mtool_args, run_manager\u001b[38;5;241m=\u001b[39mrun_manager, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mtool_kwargs)\n\u001b[1;32m    382\u001b[0m         \u001b[38;5;28;01mif\u001b[39;00m new_arg_supported\n\u001b[1;32m    383\u001b[0m         \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_run(\u001b[38;5;241m*\u001b[39mtool_args, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mtool_kwargs)\n\u001b[1;32m    384\u001b[0m     )\n",
-      "File \u001b[0;32m~/langchain/libs/core/langchain_core/tools.py:283\u001b[0m, in \u001b[0;36mBaseTool._parse_input\u001b[0;34m(self, tool_input)\u001b[0m\n\u001b[1;32m    281\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    282\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m input_args \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m--> 283\u001b[0m         result \u001b[38;5;241m=\u001b[39m \u001b[43minput_args\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mparse_obj\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtool_input\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    284\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m {\n\u001b[1;32m    285\u001b[0m             k: \u001b[38;5;28mgetattr\u001b[39m(result, k)\n\u001b[1;32m    286\u001b[0m             \u001b[38;5;28;01mfor\u001b[39;00m k, v \u001b[38;5;129;01min\u001b[39;00m result\u001b[38;5;241m.\u001b[39mdict()\u001b[38;5;241m.\u001b[39mitems()\n\u001b[1;32m    287\u001b[0m             \u001b[38;5;28;01mif\u001b[39;00m k \u001b[38;5;129;01min\u001b[39;00m tool_input\n\u001b[1;32m    288\u001b[0m         }\n\u001b[1;32m    289\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m tool_input\n",
-      "File \u001b[0;32m~/langchain/.venv/lib/python3.9/site-packages/pydantic/v1/main.py:526\u001b[0m, in \u001b[0;36mBaseModel.parse_obj\u001b[0;34m(cls, obj)\u001b[0m\n\u001b[1;32m    524\u001b[0m         exc \u001b[38;5;241m=\u001b[39m \u001b[38;5;167;01mTypeError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m expected dict not \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mobj\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__class__\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m)\n\u001b[1;32m    525\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m ValidationError([ErrorWrapper(exc, loc\u001b[38;5;241m=\u001b[39mROOT_KEY)], \u001b[38;5;28mcls\u001b[39m) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01me\u001b[39;00m\n\u001b[0;32m--> 526\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mcls\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mobj\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/langchain/.venv/lib/python3.9/site-packages/pydantic/v1/main.py:341\u001b[0m, in \u001b[0;36mBaseModel.__init__\u001b[0;34m(__pydantic_self__, **data)\u001b[0m\n\u001b[1;32m    339\u001b[0m values, fields_set, validation_error \u001b[38;5;241m=\u001b[39m validate_model(__pydantic_self__\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__class__\u001b[39m, data)\n\u001b[1;32m    340\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m validation_error:\n\u001b[0;32m--> 341\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m validation_error\n\u001b[1;32m    342\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m    343\u001b[0m     object_setattr(__pydantic_self__, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124m__dict__\u001b[39m\u001b[38;5;124m'\u001b[39m, values)\n",
+      "Cell \u001b[0;32mIn[6], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mchain\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minvoke\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m      2\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43muse complex tool. the args are 5, 2.1, empty dictionary. don\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mt forget dict_arg\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\n\u001b[1;32m      3\u001b[0m \u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/.pyenv/versions/3.10.5/lib/python3.10/site-packages/langchain_core/runnables/base.py:2572\u001b[0m, in \u001b[0;36mRunnableSequence.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m   2570\u001b[0m             \u001b[38;5;28minput\u001b[39m \u001b[38;5;241m=\u001b[39m step\u001b[38;5;241m.\u001b[39minvoke(\u001b[38;5;28minput\u001b[39m, config, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m   2571\u001b[0m         \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 2572\u001b[0m             \u001b[38;5;28minput\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[43mstep\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minvoke\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   2573\u001b[0m \u001b[38;5;66;03m# finish the root run\u001b[39;00m\n\u001b[1;32m   2574\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n",
+      "File \u001b[0;32m~/.pyenv/versions/3.10.5/lib/python3.10/site-packages/langchain_core/tools.py:380\u001b[0m, in \u001b[0;36mBaseTool.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m    373\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21minvoke\u001b[39m(\n\u001b[1;32m    374\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m    375\u001b[0m     \u001b[38;5;28minput\u001b[39m: Union[\u001b[38;5;28mstr\u001b[39m, Dict],\n\u001b[1;32m    376\u001b[0m     config: Optional[RunnableConfig] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m    377\u001b[0m     \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Any,\n\u001b[1;32m    378\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Any:\n\u001b[1;32m    379\u001b[0m     config \u001b[38;5;241m=\u001b[39m ensure_config(config)\n\u001b[0;32m--> 380\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrun\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    381\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m    382\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mcallbacks\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    383\u001b[0m \u001b[43m        \u001b[49m\u001b[43mtags\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtags\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    384\u001b[0m \u001b[43m        \u001b[49m\u001b[43mmetadata\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmetadata\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    385\u001b[0m \u001b[43m        \u001b[49m\u001b[43mrun_name\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mrun_name\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    386\u001b[0m \u001b[43m        \u001b[49m\u001b[43mrun_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpop\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mrun_id\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    387\u001b[0m \u001b[43m        \u001b[49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    388\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    389\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/.pyenv/versions/3.10.5/lib/python3.10/site-packages/langchain_core/tools.py:537\u001b[0m, in \u001b[0;36mBaseTool.run\u001b[0;34m(self, tool_input, verbose, start_color, color, callbacks, tags, metadata, run_name, run_id, config, **kwargs)\u001b[0m\n\u001b[1;32m    535\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m ValidationError \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    536\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandle_validation_error:\n\u001b[0;32m--> 537\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m    538\u001b[0m     \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandle_validation_error, \u001b[38;5;28mbool\u001b[39m):\n\u001b[1;32m    539\u001b[0m         observation \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mTool input validation error\u001b[39m\u001b[38;5;124m\"\u001b[39m\n",
+      "File \u001b[0;32m~/.pyenv/versions/3.10.5/lib/python3.10/site-packages/langchain_core/tools.py:526\u001b[0m, in \u001b[0;36mBaseTool.run\u001b[0;34m(self, tool_input, verbose, start_color, color, callbacks, tags, metadata, run_name, run_id, config, **kwargs)\u001b[0m\n\u001b[1;32m    524\u001b[0m context \u001b[38;5;241m=\u001b[39m copy_context()\n\u001b[1;32m    525\u001b[0m context\u001b[38;5;241m.\u001b[39mrun(_set_config_context, child_config)\n\u001b[0;32m--> 526\u001b[0m parsed_input \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_parse_input\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtool_input\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    527\u001b[0m tool_args, tool_kwargs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_to_args_and_kwargs(parsed_input)\n\u001b[1;32m    528\u001b[0m observation \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m    529\u001b[0m     context\u001b[38;5;241m.\u001b[39mrun(\n\u001b[1;32m    530\u001b[0m         \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_run, \u001b[38;5;241m*\u001b[39mtool_args, run_manager\u001b[38;5;241m=\u001b[39mrun_manager, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mtool_kwargs\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    533\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m context\u001b[38;5;241m.\u001b[39mrun(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_run, \u001b[38;5;241m*\u001b[39mtool_args, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mtool_kwargs)\n\u001b[1;32m    534\u001b[0m )\n",
+      "File \u001b[0;32m~/.pyenv/versions/3.10.5/lib/python3.10/site-packages/langchain_core/tools.py:424\u001b[0m, in \u001b[0;36mBaseTool._parse_input\u001b[0;34m(self, tool_input)\u001b[0m\n\u001b[1;32m    422\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    423\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m input_args \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m--> 424\u001b[0m         result \u001b[38;5;241m=\u001b[39m \u001b[43minput_args\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mparse_obj\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtool_input\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    425\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m {\n\u001b[1;32m    426\u001b[0m             k: \u001b[38;5;28mgetattr\u001b[39m(result, k)\n\u001b[1;32m    427\u001b[0m             \u001b[38;5;28;01mfor\u001b[39;00m k, v \u001b[38;5;129;01min\u001b[39;00m result\u001b[38;5;241m.\u001b[39mdict()\u001b[38;5;241m.\u001b[39mitems()\n\u001b[1;32m    428\u001b[0m             \u001b[38;5;28;01mif\u001b[39;00m k \u001b[38;5;129;01min\u001b[39;00m tool_input\n\u001b[1;32m    429\u001b[0m         }\n\u001b[1;32m    430\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m tool_input\n",
+      "File \u001b[0;32m~/.pyenv/versions/3.10.5/lib/python3.10/site-packages/pydantic/main.py:526\u001b[0m, in \u001b[0;36mpydantic.main.BaseModel.parse_obj\u001b[0;34m()\u001b[0m\n",
+      "File \u001b[0;32m~/.pyenv/versions/3.10.5/lib/python3.10/site-packages/pydantic/main.py:341\u001b[0m, in \u001b[0;36mpydantic.main.BaseModel.__init__\u001b[0;34m()\u001b[0m\n",
       "\u001b[0;31mValidationError\u001b[0m: 1 validation error for complex_toolSchema\ndict_arg\n  field required (type=value_error.missing)"
      ]
     }
@@ -176,10 +172,26 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 8,
    "id": "8fedb550-683d-45ae-8876-ae7acb332019",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Calling tool with arguments:\n",
+      "\n",
+      "{'int_arg': 5, 'float_arg': 2.1}\n",
+      "\n",
+      "raised the following error:\n",
+      "\n",
+      "<class 'pydantic.error_wrappers.ValidationError'>: 1 validation error for complex_toolSchema\n",
+      "dict_arg\n",
+      "  field required (type=value_error.missing)\n"
+     ]
+    }
+   ],
    "source": [
     "from typing import Any\n",
     "\n",
@@ -193,32 +205,8 @@
     "        return f\"Calling tool with arguments:\\n\\n{tool_args}\\n\\nraised the following error:\\n\\n{type(e)}: {e}\"\n",
     "\n",
     "\n",
-    "chain = llm_with_tools | (lambda msg: msg.tool_calls[0][\"args\"]) | try_except_tool"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "71a2c98d-c0be-4c0a-bb3d-41ad4596526c",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Calling tool with arguments:\n",
-      "\n",
-      "{'int_arg': 5, 'float_arg': 2.1}\n",
-      "\n",
-      "raised the following error:\n",
-      "\n",
-      "<class 'pydantic.v1.error_wrappers.ValidationError'>: 1 validation error for complex_toolSchema\n",
-      "dict_arg\n",
-      "  field required (type=value_error.missing)\n"
-     ]
-    }
-   ],
-   "source": [
+    "chain = llm_with_tools | (lambda msg: msg.tool_calls[0][\"args\"]) | try_except_tool\n",
+    "\n",
     "print(\n",
     "    chain.invoke(\n",
     "        \"use complex tool. the args are 5, 2.1, empty dictionary. don't forget dict_arg\"\n",
@@ -238,7 +226,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 10,
    "id": "02cc4223-35fa-4240-976a-012299ca703c",
    "metadata": {},
    "outputs": [
@@ -248,19 +236,22 @@
        "10.5"
       ]
      },
-     "execution_count": 17,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
     "chain = llm_with_tools | (lambda msg: msg.tool_calls[0][\"args\"]) | complex_tool\n",
+    "\n",
     "better_model = ChatOpenAI(model=\"gpt-4-1106-preview\", temperature=0).bind_tools(\n",
     "    [complex_tool], tool_choice=\"complex_tool\"\n",
     ")\n",
+    "\n",
     "better_chain = better_model | (lambda msg: msg.tool_calls[0][\"args\"]) | complex_tool\n",
     "\n",
     "chain_with_fallback = chain.with_fallbacks([better_chain])\n",
+    "\n",
     "chain_with_fallback.invoke(\n",
     "    \"use complex tool. the args are 5, 2.1, empty dictionary. don't forget dict_arg\"\n",
     ")"
@@ -271,7 +262,7 @@
    "id": "412f8c4e-cc83-4d87-84a1-5ba2f8edb1e9",
    "metadata": {},
    "source": [
-    "Looking at the [Langsmith trace](https://smith.langchain.com/public/00e91fc2-e1a4-4b0f-a82e-e6b3119d196c/r) for this chain run, we can see that the first chain call fails as expected and it's the fallback that succeeds."
+    "Looking at the [LangSmith trace](https://smith.langchain.com/public/00e91fc2-e1a4-4b0f-a82e-e6b3119d196c/r) for this chain run, we can see that the first chain call fails as expected and it's the fallback that succeeds."
    ]
   },
   {
@@ -286,17 +277,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 11,
    "id": "b5659956-9454-468a-9753-a3ff9052b8f5",
    "metadata": {},
    "outputs": [],
    "source": [
-    "import json\n",
-    "from typing import Any\n",
-    "\n",
     "from langchain_core.messages import AIMessage, HumanMessage, ToolCall, ToolMessage\n",
-    "from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
-    "from langchain_core.runnables import RunnablePassthrough\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
     "\n",
     "\n",
     "class CustomToolException(Exception):\n",
@@ -336,7 +323,7 @@
     "# affect the prompt at all, but gives us the option to insert an arbitrary list of Messages\n",
     "# into the prompt if needed. We'll use this on retries to insert the error message.\n",
     "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [(\"human\", \"{input}\"), MessagesPlaceholder(\"last_output\", optional=True)]\n",
+    "    [(\"human\", \"{input}\"), (\"placeholder\", \"{last_output}\")]\n",
     ")\n",
     "chain = prompt | llm_with_tools | tool_custom_exception\n",
     "\n",
@@ -348,7 +335,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 12,
    "id": "4c45f5bd-cbb4-47d5-b4b6-aec50673c750",
    "metadata": {},
    "outputs": [
@@ -358,7 +345,7 @@
        "10.5"
       ]
      },
-     "execution_count": 14,
+     "execution_count": 12,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -378,6 +365,24 @@
    "source": [
     "And our chain succeeds! Looking at the [LangSmith trace](https://smith.langchain.com/public/c11e804c-e14f-4059-bd09-64766f999c14/r), we can see that indeed our initial chain still fails, and it's only on retrying that the chain succeeds."
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6b97af9f",
+   "metadata": {},
+   "source": [
+    "## Next steps\n",
+    "\n",
+    "Now you've seen some strategies how to handle tool calling errors. Next, you can learn more about how to use tools:\n",
+    "\n",
+    "- Few shot prompting [with tools](/docs/how_to/tools_few_shot/)\n",
+    "- Stream [tool calls](/docs/how_to/tool_streaming/)\n",
+    "- Pass [runtime values to tools](/docs/how_to/tool_runtime)\n",
+    "\n",
+    "You can also check out some more specific uses of tool calling:\n",
+    "\n",
+    "- Getting [structured outputs](/docs/how_to/structured_output/) from models"
+   ]
   }
  ],
  "metadata": {
@@ -396,7 +401,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.1"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/llamacpp.ipynb

@@ -41,7 +41,7 @@
     "\n",
     "### Installation\n",
     "\n",
-    "The LangChain OpenAI integration lives in the `langchain-community` and `llama-cpp-python` packages:"
+    "The LangChain LlamaCpp integration lives in the `langchain-community` and `llama-cpp-python` packages:"
    ]
   },
   {

docs/docs/integrations/document_loaders/airbyte_cdk.ipynb

@@ -1,5 +1,19 @@
 {
  "cells": [
+  {
+   "cell_type": "raw",
+   "id": "bd931196",
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
+   "source": [
+    "---\n",
+    "sidebar_class_name: hidden\n",
+    "---"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "1f3a5ebf",

docs/docs/integrations/document_loaders/airbyte_gong.ipynb

@@ -1,5 +1,15 @@
 {
  "cells": [
+  {
+   "cell_type": "raw",
+   "id": "344fc5a3",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_class_name: hidden\n",
+    "---"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "1f3a5ebf",

docs/docs/integrations/document_loaders/airbyte_hubspot.ipynb

@@ -1,5 +1,15 @@
 {
  "cells": [
+  {
+   "cell_type": "raw",
+   "id": "a792e839",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_class_name: hidden\n",
+    "---"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "1f3a5ebf",

docs/docs/integrations/document_loaders/airbyte_json.ipynb

@@ -1,5 +1,15 @@
 {
  "cells": [
+  {
+   "cell_type": "raw",
+   "id": "61c2629c",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_class_name: hidden\n",
+    "---"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "1f3a5ebf",

docs/docs/integrations/document_loaders/airbyte_salesforce.ipynb

@@ -1,5 +1,15 @@
 {
  "cells": [
+  {
+   "cell_type": "raw",
+   "id": "e329385c",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_class_name: hidden\n",
+    "---"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "1f3a5ebf",

docs/docs/integrations/document_loaders/airbyte_shopify.ipynb

@@ -1,5 +1,15 @@
 {
  "cells": [
+  {
+   "cell_type": "raw",
+   "id": "3169f380",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_class_name: hidden\n",
+    "---"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "1f3a5ebf",

docs/docs/integrations/document_loaders/airbyte_stripe.ipynb

@@ -1,5 +1,15 @@
 {
  "cells": [
+  {
+   "cell_type": "raw",
+   "id": "87552e5a",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_class_name: hidden\n",
+    "---"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "1f3a5ebf",

docs/docs/integrations/document_loaders/airbyte_typeform.ipynb

@@ -1,5 +1,15 @@
 {
  "cells": [
+  {
+   "cell_type": "raw",
+   "id": "9a10cdcc",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_class_name: hidden\n",
+    "---"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "1f3a5ebf",

docs/docs/integrations/document_loaders/airbyte_zendesk_support.ipynb

@@ -1,5 +1,15 @@
 {
  "cells": [
+  {
+   "cell_type": "raw",
+   "id": "41200199",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_class_name: hidden\n",
+    "---"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "1f3a5ebf",

docs/docs/integrations/document_loaders/scrapfly.ipynb

@@ -37,7 +37,7 @@
     "scrapfly_loader = ScrapflyLoader(\n",
     "    [\"https://web-scraping.dev/products\"],\n",
     "    api_key=\"Your ScrapFly API key\",  # Get your API key from https://www.scrapfly.io/\n",
-    "    ignore_scrape_failures=True,  # Ignore unprocessable web pages and log their exceptions\n",
+    "    continue_on_failure=True,  # Ignore unprocessable web pages and log their exceptions\n",
     ")\n",
     "\n",
     "# Load documents from URLs as markdown\n",
@@ -72,7 +72,7 @@
     "scrapfly_loader = ScrapflyLoader(\n",
     "    [\"https://web-scraping.dev/products\"],\n",
     "    api_key=\"Your ScrapFly API key\",  # Get your API key from https://www.scrapfly.io/\n",
-    "    ignore_scrape_failures=True,  # Ignore unprocessable web pages and log their exceptions\n",
+    "    continue_on_failure=True,  # Ignore unprocessable web pages and log their exceptions\n",
     "    scrape_config=scrapfly_scrape_config,  # Pass the scrape_config object\n",
     "    scrape_format=\"markdown\",  # The scrape result format, either `markdown`(default) or `text`\n",
     ")\n",

docs/docs/integrations/llm_caching.ipynb

@@ -12,7 +12,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 1,
    "id": "10ad9224",
    "metadata": {
     "ExecuteTime": {
@@ -1809,7 +1809,6 @@
    "cell_type": "markdown",
    "id": "0c69d84d",
    "metadata": {
-    "jp-MarkdownHeadingCollapsed": true,
     "tags": []
    },
    "source": [
@@ -1891,7 +1890,6 @@
    "cell_type": "markdown",
    "id": "5da41b77",
    "metadata": {
-    "jp-MarkdownHeadingCollapsed": true,
     "tags": []
    },
    "source": [
@@ -2149,6 +2147,7 @@
   },
   {
    "cell_type": "markdown",
+   "id": "2ac1a8c7",
    "metadata": {},
    "source": [
     "## SingleStoreDB Semantic Cache\n",
@@ -2173,6 +2172,353 @@
     ")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "7019c991-0101-4f9c-b212-5729a5471293",
+   "metadata": {},
+   "source": [
+    "## Couchbase Caches\n",
+    "\n",
+    "Use [Couchbase](https://couchbase.com/) as a cache for prompts and responses."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d6aac680-ba32-4c19-8864-6471cf0e7d5a",
+   "metadata": {},
+   "source": [
+    "### Couchbase Cache\n",
+    "\n",
+    "The standard cache that looks for an exact match of the user prompt."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "9b4764e4-c75f-4185-b326-524287a826be",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Create couchbase connection object\n",
+    "from datetime import timedelta\n",
+    "\n",
+    "from couchbase.auth import PasswordAuthenticator\n",
+    "from couchbase.cluster import Cluster\n",
+    "from couchbase.options import ClusterOptions\n",
+    "from langchain_couchbase.cache import CouchbaseCache\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "COUCHBASE_CONNECTION_STRING = (\n",
+    "    \"couchbase://localhost\"  # or \"couchbases://localhost\" if using TLS\n",
+    ")\n",
+    "DB_USERNAME = \"Administrator\"\n",
+    "DB_PASSWORD = \"Password\"\n",
+    "\n",
+    "auth = PasswordAuthenticator(DB_USERNAME, DB_PASSWORD)\n",
+    "options = ClusterOptions(auth)\n",
+    "cluster = Cluster(COUCHBASE_CONNECTION_STRING, options)\n",
+    "\n",
+    "# Wait until the cluster is ready for use.\n",
+    "cluster.wait_until_ready(timedelta(seconds=5))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "4b5e73c5-92c1-4eab-84e2-77924ea9c123",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Specify the bucket, scope and collection to store the cached documents\n",
+    "BUCKET_NAME = \"langchain-testing\"\n",
+    "SCOPE_NAME = \"_default\"\n",
+    "COLLECTION_NAME = \"_default\"\n",
+    "\n",
+    "set_llm_cache(\n",
+    "    CouchbaseCache(\n",
+    "        cluster=cluster,\n",
+    "        bucket_name=BUCKET_NAME,\n",
+    "        scope_name=SCOPE_NAME,\n",
+    "        collection_name=COLLECTION_NAME,\n",
+    "    )\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "db8d28cc-8d93-47b4-8326-57a29a06fb3c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 22.2 ms, sys: 14 ms, total: 36.2 ms\n",
+      "Wall time: 938 ms\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\"\\n\\nWhy couldn't the bicycle stand up by itself? Because it was two-tired!\""
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "# The first time, it is not yet in the cache, so it should take longer\n",
+    "llm.invoke(\"Tell me a joke\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "b470dc81-2e7f-4743-9435-ce9071394eea",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 53 ms, sys: 29 ms, total: 82 ms\n",
+      "Wall time: 84.2 ms\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\"\\n\\nWhy couldn't the bicycle stand up by itself? Because it was two-tired!\""
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "# The second time, it is in the cache, so it should be much faster\n",
+    "llm.invoke(\"Tell me a joke\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "43626f33-d184-4260-b641-c9341cef5842",
+   "metadata": {},
+   "source": [
+    "### Couchbase Semantic Cache\n",
+    "Semantic caching allows users to retrieve cached prompts based on semantic similarity between the user input and previously cached inputs. Under the hood it uses Couchbase as both a cache and a vectorstore. This needs an appropriate Vector Search Index defined to work. Please look at the usage example on how to set up the index."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "6b470c03-d7fe-4270-89e1-638251619a53",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Create Couchbase connection object\n",
+    "from datetime import timedelta\n",
+    "\n",
+    "from couchbase.auth import PasswordAuthenticator\n",
+    "from couchbase.cluster import Cluster\n",
+    "from couchbase.options import ClusterOptions\n",
+    "from langchain_couchbase.cache import CouchbaseSemanticCache\n",
+    "from langchain_openai import ChatOpenAI, OpenAIEmbeddings\n",
+    "\n",
+    "COUCHBASE_CONNECTION_STRING = (\n",
+    "    \"couchbase://localhost\"  # or \"couchbases://localhost\" if using TLS\n",
+    ")\n",
+    "DB_USERNAME = \"Administrator\"\n",
+    "DB_PASSWORD = \"Password\"\n",
+    "\n",
+    "auth = PasswordAuthenticator(DB_USERNAME, DB_PASSWORD)\n",
+    "options = ClusterOptions(auth)\n",
+    "cluster = Cluster(COUCHBASE_CONNECTION_STRING, options)\n",
+    "\n",
+    "# Wait until the cluster is ready for use.\n",
+    "cluster.wait_until_ready(timedelta(seconds=5))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f831bc4c-f330-4bd7-9b80-76771d91827e",
+   "metadata": {},
+   "source": [
+    "Notes:\n",
+    "- The search index for the semantic cache needs to be defined before using the semantic cache. \n",
+    "- The optional parameter, `score_threshold` in the Semantic Cache that you can use to tune the results of the semantic search.\n",
+    "\n",
+    "### How to Import an Index to the Full Text Search service?\n",
+    " - [Couchbase Server](https://docs.couchbase.com/server/current/search/import-search-index.html)\n",
+    "     - Click on Search -> Add Index -> Import\n",
+    "     - Copy the following Index definition in the Import screen\n",
+    "     - Click on Create Index to create the index.\n",
+    " - [Couchbase Capella](https://docs.couchbase.com/cloud/search/import-search-index.html)\n",
+    "     - Copy the index definition to a new file `index.json`\n",
+    "     - Import the file in Capella using the instructions in the documentation.\n",
+    "     - Click on Create Index to create the index.\n",
+    "\n",
+    "#### Example index for the vector search. \n",
+    "  ```\n",
+    "  {\n",
+    "    \"type\": \"fulltext-index\",\n",
+    "    \"name\": \"langchain-testing._default.semantic-cache-index\",\n",
+    "    \"sourceType\": \"gocbcore\",\n",
+    "    \"sourceName\": \"langchain-testing\",\n",
+    "    \"planParams\": {\n",
+    "      \"maxPartitionsPerPIndex\": 1024,\n",
+    "      \"indexPartitions\": 16\n",
+    "    },\n",
+    "    \"params\": {\n",
+    "      \"doc_config\": {\n",
+    "        \"docid_prefix_delim\": \"\",\n",
+    "        \"docid_regexp\": \"\",\n",
+    "        \"mode\": \"scope.collection.type_field\",\n",
+    "        \"type_field\": \"type\"\n",
+    "      },\n",
+    "      \"mapping\": {\n",
+    "        \"analysis\": {},\n",
+    "        \"default_analyzer\": \"standard\",\n",
+    "        \"default_datetime_parser\": \"dateTimeOptional\",\n",
+    "        \"default_field\": \"_all\",\n",
+    "        \"default_mapping\": {\n",
+    "          \"dynamic\": true,\n",
+    "          \"enabled\": false\n",
+    "        },\n",
+    "        \"default_type\": \"_default\",\n",
+    "        \"docvalues_dynamic\": false,\n",
+    "        \"index_dynamic\": true,\n",
+    "        \"store_dynamic\": true,\n",
+    "        \"type_field\": \"_type\",\n",
+    "        \"types\": {\n",
+    "          \"_default.semantic-cache\": {\n",
+    "            \"dynamic\": false,\n",
+    "            \"enabled\": true,\n",
+    "            \"properties\": {\n",
+    "              \"embedding\": {\n",
+    "                \"dynamic\": false,\n",
+    "                \"enabled\": true,\n",
+    "                \"fields\": [\n",
+    "                  {\n",
+    "                    \"dims\": 1536,\n",
+    "                    \"index\": true,\n",
+    "                    \"name\": \"embedding\",\n",
+    "                    \"similarity\": \"dot_product\",\n",
+    "                    \"type\": \"vector\",\n",
+    "                    \"vector_index_optimized_for\": \"recall\"\n",
+    "                  }\n",
+    "                ]\n",
+    "              },\n",
+    "              \"metadata\": {\n",
+    "                \"dynamic\": true,\n",
+    "                \"enabled\": true\n",
+    "              },\n",
+    "              \"text\": {\n",
+    "                \"dynamic\": false,\n",
+    "                \"enabled\": true,\n",
+    "                \"fields\": [\n",
+    "                  {\n",
+    "                    \"index\": true,\n",
+    "                    \"name\": \"text\",\n",
+    "                    \"store\": true,\n",
+    "                    \"type\": \"text\"\n",
+    "                  }\n",
+    "                ]\n",
+    "              }\n",
+    "            }\n",
+    "          }\n",
+    "        }\n",
+    "      },\n",
+    "      \"store\": {\n",
+    "        \"indexType\": \"scorch\",\n",
+    "        \"segmentVersion\": 16\n",
+    "      }\n",
+    "    },\n",
+    "    \"sourceParams\": {}\n",
+    "  }\n",
+    "  ```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "ae0766c8-ea34-4604-b0dc-cf2bbe8077f4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "BUCKET_NAME = \"langchain-testing\"\n",
+    "SCOPE_NAME = \"_default\"\n",
+    "COLLECTION_NAME = \"semantic-cache\"\n",
+    "INDEX_NAME = \"semantic-cache-index\"\n",
+    "embeddings = OpenAIEmbeddings()\n",
+    "\n",
+    "cache = CouchbaseSemanticCache(\n",
+    "    cluster=cluster,\n",
+    "    embedding=embeddings,\n",
+    "    bucket_name=BUCKET_NAME,\n",
+    "    scope_name=SCOPE_NAME,\n",
+    "    collection_name=COLLECTION_NAME,\n",
+    "    index_name=INDEX_NAME,\n",
+    "    score_threshold=0.8,\n",
+    ")\n",
+    "\n",
+    "set_llm_cache(cache)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "a2e82743-10ea-4319-b43e-193475ae5449",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "The average lifespan of a dog is around 12 years, but this can vary depending on the breed, size, and overall health of the individual dog. Some smaller breeds may live longer, while larger breeds may have shorter lifespans. Proper care, diet, and exercise can also play a role in extending a dog's lifespan.\n",
+      "CPU times: user 826 ms, sys: 2.46 s, total: 3.28 s\n",
+      "Wall time: 2.87 s\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "# The first time, it is not yet in the cache, so it should take longer\n",
+    "print(llm.invoke(\"How long do dogs live?\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "c36f4e29-d872-4334-a1f1-0e6d10c5d9f2",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "The average lifespan of a dog is around 12 years, but this can vary depending on the breed, size, and overall health of the individual dog. Some smaller breeds may live longer, while larger breeds may have shorter lifespans. Proper care, diet, and exercise can also play a role in extending a dog's lifespan.\n",
+      "CPU times: user 9.82 ms, sys: 2.61 ms, total: 12.4 ms\n",
+      "Wall time: 311 ms\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "# The second time, it is in the cache, so it should be much faster\n",
+    "print(llm.invoke(\"What is the expected lifespan of a dog?\"))"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "ae1f5e1c-085e-4998-9f2d-b5867d2c3d5b",
@@ -2228,7 +2574,9 @@
     "| langchain_core.caches | [InMemoryCache](https://api.python.langchain.com/en/latest/caches/langchain_core.caches.InMemoryCache.html) |\n",
     "| langchain_elasticsearch.cache | [ElasticsearchCache](https://api.python.langchain.com/en/latest/cache/langchain_elasticsearch.cache.ElasticsearchCache.html) |\n",
     "| langchain_mongodb.cache | [MongoDBAtlasSemanticCache](https://api.python.langchain.com/en/latest/cache/langchain_mongodb.cache.MongoDBAtlasSemanticCache.html) |\n",
-    "| langchain_mongodb.cache | [MongoDBCache](https://api.python.langchain.com/en/latest/cache/langchain_mongodb.cache.MongoDBCache.html) |\n"
+    "| langchain_mongodb.cache | [MongoDBCache](https://api.python.langchain.com/en/latest/cache/langchain_mongodb.cache.MongoDBCache.html) |\n",
+    "| langchain_couchbase.cache | [CouchbaseCache](https://api.python.langchain.com/en/latest/cache/langchain_couchbase.cache.CouchbaseCache.html) |\n",
+    "| langchain_couchbase.cache | [CouchbaseSemanticCache](https://api.python.langchain.com/en/latest/cache/langchain_couchbase.cache.CouchbaseSemanticCache.html) |\n"
    ]
   },
   {
@@ -2256,7 +2604,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.12"
+   "version": "3.10.13"
   }
  },
  "nbformat": 4,

docs/docs/integrations/llms/gpt4all.ipynb

@@ -14,21 +14,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "metadata": {
     "tags": []
    },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Note: you may need to restart the kernel to use updated packages.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet  gpt4all > /dev/null"
+    "%pip install --upgrade --quiet langchain-community gpt4all"
    ]
   },
   {
@@ -47,9 +39,7 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.chains import LLMChain\n",
     "from langchain_community.llms import GPT4All\n",
-    "from langchain_core.callbacks import StreamingStdOutCallbackHandler\n",
     "from langchain_core.prompts import PromptTemplate"
    ]
   },
@@ -92,64 +82,79 @@
     "\n",
     "For more info, visit https://github.com/nomic-ai/gpt4all.\n",
     "\n",
-    "---"
+    "---\n",
+    "\n",
+    "This integration does not yet support streaming in chunks via the [`.stream()`](https://python.langchain.com/v0.2/docs/how_to/streaming/) method. The below example uses a callback handler with `streaming=True`:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
     "local_path = (\n",
-    "    \"./models/ggml-gpt4all-l13b-snoozy.bin\"  # replace with your desired local file path\n",
+    "    \"./models/Meta-Llama-3-8B-Instruct.Q4_0.gguf\"  # replace with your local file path\n",
     ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 10,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Token:  Justin\n",
+      "Token:  Bieber\n",
+      "Token:  was\n",
+      "Token:  born\n",
+      "Token:  on\n",
+      "Token:  March\n",
+      "Token:  \n",
+      "Token: 1\n",
+      "Token: ,\n",
+      "Token:  \n"
+     ]
+    }
+   ],
    "source": [
-    "# Callbacks support token-wise streaming\n",
-    "callbacks = [StreamingStdOutCallbackHandler()]\n",
+    "from langchain_core.callbacks import BaseCallbackHandler\n",
+    "\n",
+    "count = 0\n",
+    "\n",
+    "\n",
+    "class MyCustomHandler(BaseCallbackHandler):\n",
+    "    def on_llm_new_token(self, token: str, **kwargs) -> None:\n",
+    "        global count\n",
+    "        if count < 10:\n",
+    "            print(f\"Token: {token}\")\n",
+    "            count += 1\n",
+    "\n",
     "\n",
     "# Verbose is required to pass to the callback manager\n",
-    "llm = GPT4All(model=local_path, callbacks=callbacks, verbose=True)\n",
+    "llm = GPT4All(model=local_path, callbacks=[MyCustomHandler()], streaming=True)\n",
     "\n",
     "# If you want to use a custom model add the backend parameter\n",
     "# Check https://docs.gpt4all.io/gpt4all_python.html for supported backends\n",
-    "llm = GPT4All(model=local_path, backend=\"gptj\", callbacks=callbacks, verbose=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm_chain = LLMChain(prompt=prompt, llm=llm)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
+    "# llm = GPT4All(model=local_path, backend=\"gptj\", callbacks=callbacks, streaming=True)\n",
+    "\n",
+    "chain = prompt | llm\n",
+    "\n",
     "question = \"What NFL team won the Super Bowl in the year Justin Bieber was born?\"\n",
     "\n",
-    "llm_chain.run(question)"
+    "# Streamed tokens will be logged/aggregated via the passed callback\n",
+    "res = chain.invoke({\"question\": question})"
    ]
   },
   {
-   "attachments": {},
-   "cell_type": "markdown",
+   "cell_type": "code",
+   "execution_count": null,
    "metadata": {},
-   "source": [
-    "Justin Bieber was born on March 1, 1994. In 1994, The Cowboys won Super Bowl XXVIII."
-   ]
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {

docs/docs/integrations/llms/huggingface_pipelines.ipynb

@@ -143,6 +143,25 @@
     "print(chain.invoke({\"question\": question}))"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "5141dc4d",
+   "metadata": {},
+   "source": [
+    "Streaming repsonse."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f1819250-2db9-4143-b88a-12e92d4e2386",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for chunk in chain.stream(question):\n",
+    "    print(chunk, end=\"\", flush=True)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "dbbc3a37",

docs/docs/integrations/llms/openvino.ipynb

@@ -245,7 +245,7 @@
    "source": [
     "### Streaming\n",
     "\n",
-    "To get streaming of LLM output, you can create a Huggingface `TextIteratorStreamer` for `_forward_params`."
+    "You can use `stream` method to get a streaming of LLM output, "
    ]
   },
   {
@@ -255,24 +255,11 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from threading import Thread\n",
+    "generation_config = {\"skip_prompt\": True, \"pipeline_kwargs\": {\"max_new_tokens\": 100}}\n",
+    "chain = prompt | ov_llm.bind(**generation_config)\n",
     "\n",
-    "from transformers import TextIteratorStreamer\n",
-    "\n",
-    "streamer = TextIteratorStreamer(\n",
-    "    ov_llm.pipeline.tokenizer,\n",
-    "    timeout=30.0,\n",
-    "    skip_prompt=True,\n",
-    "    skip_special_tokens=True,\n",
-    ")\n",
-    "pipeline_kwargs = {\"pipeline_kwargs\": {\"streamer\": streamer, \"max_new_tokens\": 100}}\n",
-    "chain = prompt | ov_llm.bind(**pipeline_kwargs)\n",
-    "\n",
-    "t1 = Thread(target=chain.invoke, args=({\"question\": question},))\n",
-    "t1.start()\n",
-    "\n",
-    "for new_text in streamer:\n",
-    "    print(new_text, end=\"\", flush=True)"
+    "for chunk in chain.stream(question):\n",
+    "    print(chunk, end=\"\", flush=True)"
    ]
   },
   {

docs/docs/integrations/llms/tongyi.ipynb

@@ -27,7 +27,7 @@
    "outputs": [],
    "source": [
     "# Install the package\n",
-    "%pip install --upgrade --quiet  dashscope"
+    "%pip install --upgrade --quiet  langchain-community dashscope"
    ]
   },
   {

docs/docs/integrations/providers/couchbase.mdx

@@ -27,3 +27,65 @@ See a [usage example](/docs/integrations/document_loaders/couchbase).
 ```python
 from langchain_community.document_loaders.couchbase import CouchbaseLoader
 ```
+
+## LLM Caches
+
+### CouchbaseCache
+Use Couchbase as a cache for prompts and responses.
+
+See a [usage example](/docs/integrations/llm_caching/#couchbase-cache).
+
+To import this cache:
+```python
+from langchain_couchbase.cache import CouchbaseCache
+```
+
+To use this cache with your LLMs:
+```python
+from langchain_core.globals import set_llm_cache
+
+cluster = couchbase_cluster_connection_object
+
+set_llm_cache(
+    CouchbaseCache(
+        cluster=cluster,
+        bucket_name=BUCKET_NAME,
+        scope_name=SCOPE_NAME,
+        collection_name=COLLECTION_NAME,
+    )
+)
+```
+
+
+### CouchbaseSemanticCache
+Semantic caching allows users to retrieve cached prompts based on the semantic similarity between the user input and previously cached inputs. Under the hood it uses Couchbase as both a cache and a vectorstore.
+The CouchbaseSemanticCache needs a Search Index defined to work. Please look at the [usage example](/docs/integrations/vectorstores/couchbase) on how to set up the index.
+
+See a [usage example](/docs/integrations/llm_caching/#couchbase-semantic-cache).
+
+To import this cache:
+```python
+from langchain_couchbase.cache import CouchbaseSemanticCache
+```
+
+To use this cache with your LLMs:
+```python
+from langchain_core.globals import set_llm_cache
+
+# use any embedding provider...
+from langchain_openai.Embeddings import OpenAIEmbeddings
+
+embeddings = OpenAIEmbeddings()
+cluster = couchbase_cluster_connection_object
+
+set_llm_cache(
+    CouchbaseSemanticCache(
+        cluster=cluster,
+        embedding = embeddings,
+        bucket_name=BUCKET_NAME,
+        scope_name=SCOPE_NAME,
+        collection_name=COLLECTION_NAME,
+        index_name=INDEX_NAME,
+    )
+)
+```

docs/docs/integrations/providers/gpt4all.mdx

@@ -7,7 +7,7 @@ This page covers how to use the `GPT4All` wrapper within LangChain. The tutorial
 - Install the Python package with `pip install gpt4all`
 - Download a [GPT4All model](https://gpt4all.io/index.html) and place it in your desired directory
 
-In this example, We are using `mistral-7b-openorca.Q4_0.gguf`(Best overall fast chat model):
+In this example, we are using `mistral-7b-openorca.Q4_0.gguf`:
 
 ```bash
 mkdir models
@@ -30,7 +30,7 @@ model = GPT4All(model="./models/mistral-7b-openorca.Q4_0.gguf", n_threads=8)
 response = model.invoke("Once upon a time, ")
 ```
 
-You can also customize the generation parameters, such as n_predict, temp, top_p, top_k, and others.
+You can also customize the generation parameters, such as `n_predict`, `temp`, `top_p`, `top_k`, and others.
 
 To stream the model's predictions, add in a CallbackManager.
 
@@ -45,11 +45,11 @@ callbacks = [StreamingStdOutCallbackHandler()]
 model = GPT4All(model="./models/mistral-7b-openorca.Q4_0.gguf", n_threads=8)
 
 # Generate text. Tokens are streamed through the callback manager.
-model("Once upon a time, ", callbacks=callbacks)
+model.invoke("Once upon a time, ", callbacks=callbacks)
 ```
 
 ## Model File
 
-You can find links to model file downloads in the [https://gpt4all.io/](https://gpt4all.io/index.html).
+You can download model files from the GPT4All client. You can download the client from the [GPT4All](https://gpt4all.io/index.html) website.
 
 For a more detailed walkthrough of this, see [this notebook](/docs/integrations/llms/gpt4all)

docs/docs/integrations/providers/nvidia.mdx

@@ -61,7 +61,7 @@ When ready to deploy, you can self-host models with NVIDIA NIM—which is includ
 ```python
 from langchain_nvidia_ai_endpoints import ChatNVIDIA, NVIDIAEmbeddings, NVIDIARerank
 
-# connect to an chat NIM running at localhost:8000, specifyig a specific model
+# connect to a chat NIM running at localhost:8000, specifying a model
 llm = ChatNVIDIA(base_url="http://localhost:8000/v1", model="meta/llama3-8b-instruct")
 
 # connect to an embedding NIM running at localhost:8080

docs/docs/integrations/providers/pebblo/pebblo_retrieval_qa.ipynb

@@ -60,6 +60,7 @@
     "**PebbloRetrievalQA chain supports the following vector databases:**\n",
     "- Qdrant\n",
     "- Pinecone\n",
+    "- Postgres(utilizing the pgvector extension)\n",
     "\n",
     "\n",
     "**Load vector database with authorization and semantic information in metadata:**\n",

docs/docs/integrations/providers/premai.md

@@ -202,7 +202,7 @@ Prem Templates are also available for Streaming too.
 
 ## Prem Embeddings
 
-In this section we are going to dicuss how we can get access to different embedding model using `PremEmbeddings` with LangChain. Lets start by importing our modules and setting our API Key. 
+In this section we cover how we can get access to different embedding models using `PremEmbeddings` with LangChain. Let's start by importing our modules and setting our API Key.
 
 ```python
 import os

docs/docs/integrations/providers/qdrant.mdx

@@ -21,7 +21,7 @@ whether for semantic search or example selection.
 
 To import this vectorstore:
 ```python
-from langchain_qdrant import Qdrant
+from langchain_qdrant import QdrantVectorStore
 ```
 
 For a more detailed walkthrough of the Qdrant wrapper, see [this notebook](/docs/integrations/vectorstores/qdrant)

docs/docs/integrations/providers/shaleprotocol.md

@@ -21,7 +21,7 @@ For example
 ```python
 from langchain_openai import OpenAI
 from langchain_core.prompts import PromptTemplate
-from langchain.chains import LLMChain
+from langchain_core.output_parsers import StrOutputParser
 
 import os
 os.environ['OPENAI_API_BASE'] = "https://shale.live/v1"
@@ -35,10 +35,11 @@ template = """Question: {question}
 
 prompt = PromptTemplate.from_template(template)
 
-llm_chain = LLMChain(prompt=prompt, llm=llm)
+
+llm_chain = prompt | llm | StrOutputParser()
 
 question = "What NFL team won the Super Bowl in the year Justin Beiber was born?"
 
-llm_chain.run(question)
+llm_chain.invoke(question)
 
 ```

docs/docs/integrations/retrievers/cohere-reranker.ipynb

@@ -309,9 +309,9 @@
     "documents = TextLoader(\"../../how_to/state_of_the_union.txt\").load()\n",
     "text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=100)\n",
     "texts = text_splitter.split_documents(documents)\n",
-    "retriever = FAISS.from_documents(texts, CohereEmbeddings()).as_retriever(\n",
-    "    search_kwargs={\"k\": 20}\n",
-    ")\n",
+    "retriever = FAISS.from_documents(\n",
+    "    texts, CohereEmbeddings(model=\"embed-english-v3.0\")\n",
+    ").as_retriever(search_kwargs={\"k\": 20})\n",
     "\n",
     "query = \"What did the president say about Ketanji Brown Jackson\"\n",
     "docs = retriever.invoke(query)\n",
@@ -324,7 +324,8 @@
    "metadata": {},
    "source": [
     "## Doing reranking with CohereRerank\n",
-    "Now let's wrap our base retriever with a `ContextualCompressionRetriever`. We'll add an `CohereRerank`, uses the Cohere rerank endpoint to rerank the returned results."
+    "Now let's wrap our base retriever with a `ContextualCompressionRetriever`. We'll add an `CohereRerank`, uses the Cohere rerank endpoint to rerank the returned results.\n",
+    "Do note that it is mandatory to specify the model name in CohereRerank!"
    ]
   },
   {
@@ -339,7 +340,7 @@
     "from langchain_community.llms import Cohere\n",
     "\n",
     "llm = Cohere(temperature=0)\n",
-    "compressor = CohereRerank()\n",
+    "compressor = CohereRerank(model=\"rerank-english-v3.0\")\n",
     "compression_retriever = ContextualCompressionRetriever(\n",
     "    base_compressor=compressor, base_retriever=retriever\n",
     ")\n",

docs/docs/integrations/text_embedding/azureopenai.ipynb

@@ -27,7 +27,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet langchain_openai"
+    "%pip install --upgrade --quiet langchain-openai"
    ]
   },
   {

docs/docs/integrations/text_embedding/cohere.ipynb

@@ -40,7 +40,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "embeddings = CohereEmbeddings(model=\"embed-english-light-v3.0\")"
+    "embeddings = CohereEmbeddings(\n",
+    "    model=\"embed-english-light-v3.0\"\n",
+    ")  # It is mandatory to pass a model parameter to initialize the CohereEmbeddings object"
    ]
   },
   {

docs/docs/integrations/vectorstores/annoy.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# Annoy\n",
     "\n",
-    "> [Annoy](https://github.com/spotify/annoy) (`Approximate Nearest Neighbors Oh Yeah`) is a C++ library with Python bindings to search for points in space that are close to a given query point. It also creates large read-only file-based data structures that are mmapped into memory so that many processes may share the same data.\n",
+    "> [Annoy](https://github.com/spotify/annoy) (`Approximate Nearest Neighbors Oh Yeah`) is a C++ library with Python bindings to search for points in space that are close to a given query point. It also creates large read-only file-based data structures that are mapped into memory so that many processes may share the same data.\n",
     "\n",
     "You'll need to install `langchain-community` with `pip install -qU langchain-community` to use this integration\n",
     "\n",

docs/docs/integrations/vectorstores/aperturedb.ipynb

@@ -0,0 +1,310 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "683953b3",
+   "metadata": {},
+   "source": [
+    "# ApertureDB\n",
+    "\n",
+    "[ApertureDB](https://docs.aperturedata.io) is a database that stores, indexes, and manages multi-modal data like text, images, videos, bounding boxes, and embeddings, together with their associated metadata.\n",
+    "\n",
+    "This notebook explains how to use the embeddings functionality of ApertureDB."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e7393beb",
+   "metadata": {},
+   "source": [
+    "## Install ApertureDB Python SDK\n",
+    "\n",
+    "This installs the [Python SDK](https://docs.aperturedata.io/category/aperturedb-python-sdk) used to write client code for ApertureDB."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "a62cff8a-bcf7-4e33-bbbc-76999c2e3e20",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
+   "source": [
+    "%pip install --upgrade --quiet aperturedb"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4fe12f77",
+   "metadata": {},
+   "source": [
+    "## Run an ApertureDB instance\n",
+    "\n",
+    "To continue, you should have an [ApertureDB instance up and running](https://docs.aperturedata.io/HowToGuides/start/Setup) and configure your environment to use it.  \n",
+    "There are various ways to do that, for example:\n",
+    "\n",
+    "```bash\n",
+    "docker run --publish 55555:55555 aperturedata/aperturedb-standalone\n",
+    "adb config create local --active --no-interactive\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "667eabca",
+   "metadata": {},
+   "source": [
+    "## Download some web documents\n",
+    "We're going to do a mini-crawl here of one web page."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "0798dfdb",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "USER_AGENT environment variable not set, consider setting it to identify your requests.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# For loading documents from web\n",
+    "from langchain_community.document_loaders import WebBaseLoader\n",
+    "\n",
+    "loader = WebBaseLoader(\"https://docs.aperturedata.io\")\n",
+    "docs = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5f077d11",
+   "metadata": {},
+   "source": [
+    "## Select embeddings model\n",
+    "\n",
+    "We want to use OllamaEmbeddings so we have to import the necessary modules.\n",
+    "\n",
+    "Ollama can be set up as a docker container as described in the [documentation](https://hub.docker.com/r/ollama/ollama), for example:\n",
+    "```bash\n",
+    "# Run server\n",
+    "docker run -d -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama\n",
+    "# Tell server to load a specific model\n",
+    "docker exec ollama ollama run llama2\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "8b6ed9cd-81b9-46e5-9c20-5aafca2844d0",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_community.embeddings import OllamaEmbeddings\n",
+    "\n",
+    "embeddings = OllamaEmbeddings()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b7b313e6",
+   "metadata": {},
+   "source": [
+    "## Split documents into segments\n",
+    "\n",
+    "We want to turn our single document into multiple segments."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "3c4b7b31",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
+    "\n",
+    "text_splitter = RecursiveCharacterTextSplitter()\n",
+    "documents = text_splitter.split_documents(docs)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "46339d32",
+   "metadata": {},
+   "source": [
+    "## Create vectorstore from documents and embeddings\n",
+    "\n",
+    "This code creates a vectorstore in the ApertureDB instance.\n",
+    "Within the instance, this vectorstore is represented as a \"[descriptor set](https://docs.aperturedata.io/category/descriptorset-commands)\".\n",
+    "By default, the descriptor set is named `langchain`.  The following code will generate embeddings for each document and store them in ApertureDB as descriptors.  This will take a few seconds as the embeddings are bring generated."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "dcf88bdf",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_community.vectorstores import ApertureDB\n",
+    "\n",
+    "vector_db = ApertureDB.from_documents(documents, embeddings)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7672877b",
+   "metadata": {},
+   "source": [
+    "## Select a large language model\n",
+    "\n",
+    "Again, we use the Ollama server we set up for local processing."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "9a005e4b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.llms import Ollama\n",
+    "\n",
+    "llm = Ollama(model=\"llama2\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cd54f2ad",
+   "metadata": {},
+   "source": [
+    "## Build a RAG chain\n",
+    "\n",
+    "Now we have all the components we need to create a RAG (Retrieval-Augmented Generation) chain.  This chain does the following:\n",
+    "1. Generate embedding descriptor for user query\n",
+    "2. Find text segments that are similar to the user query using the vector store\n",
+    "3. Pass user query and context documents to the LLM using a prompt template\n",
+    "4. Return the LLM's answer"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "a8c513ab",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Based on the provided context, ApertureDB can store images. In fact, it is specifically designed to manage multimodal data such as images, videos, documents, embeddings, and associated metadata including annotations. So, ApertureDB has the capability to store and manage images.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Create prompt\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_template(\"\"\"Answer the following question based only on the provided context:\n",
+    "\n",
+    "<context>\n",
+    "{context}\n",
+    "</context>\n",
+    "\n",
+    "Question: {input}\"\"\")\n",
+    "\n",
+    "\n",
+    "# Create a chain that passes documents to an LLM\n",
+    "from langchain.chains.combine_documents import create_stuff_documents_chain\n",
+    "\n",
+    "document_chain = create_stuff_documents_chain(llm, prompt)\n",
+    "\n",
+    "\n",
+    "# Treat the vectorstore as a document retriever\n",
+    "retriever = vector_db.as_retriever()\n",
+    "\n",
+    "\n",
+    "# Create a RAG chain that connects the retriever to the LLM\n",
+    "from langchain.chains import create_retrieval_chain\n",
+    "\n",
+    "retrieval_chain = create_retrieval_chain(retriever, document_chain)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3bc6a882",
+   "metadata": {},
+   "source": [
+    "## Run the RAG chain\n",
+    "\n",
+    "Finally we pass a question to the chain and get our answer.  This will take a few seconds to run as the LLM generates an answer from the query and context documents."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "020f29f1",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Based on the provided context, ApertureDB can store images in several ways:\n",
+      "\n",
+      "1. Multimodal data management: ApertureDB offers a unified interface to manage multimodal data such as images, videos, documents, embeddings, and associated metadata including annotations. This means that images can be stored along with other types of data in a single database instance.\n",
+      "2. Image storage: ApertureDB provides image storage capabilities through its integration with the public cloud providers or on-premise installations. This allows customers to host their own ApertureDB instances and store images on their preferred cloud provider or on-premise infrastructure.\n",
+      "3. Vector database: ApertureDB also offers a vector database that enables efficient similarity search and classification of images based on their semantic meaning. This can be useful for applications where image search and classification are important, such as in computer vision or machine learning workflows.\n",
+      "\n",
+      "Overall, ApertureDB provides flexible and scalable storage options for images, allowing customers to choose the deployment model that best suits their needs.\n"
+     ]
+    }
+   ],
+   "source": [
+    "user_query = \"How can ApertureDB store images?\"\n",
+    "response = retrieval_chain.invoke({\"input\": user_query})\n",
+    "print(response[\"answer\"])"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/integrations/vectorstores/azuresearch.ipynb

@@ -169,6 +169,23 @@
     ")"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Specify additional properties for the Azure client such as the following https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/core/azure-core/README.md#configurations\n",
+    "vector_store: AzureSearch = AzureSearch(\n",
+    "    azure_search_endpoint=vector_store_address,\n",
+    "    azure_search_key=vector_store_password,\n",
+    "    index_name=index_name,\n",
+    "    embedding_function=embeddings.embed_query,\n",
+    "    # Configure max retries for the Azure client\n",
+    "    additional_search_client_options={\"retry_total\": 4},\n",
+    ")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},

docs/docs/integrations/vectorstores/databricks_vector_search.ipynb

@@ -174,7 +174,10 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Similarity search"
+    "## Similarity search\n",
+    "Optional keyword arguments to similarity_search include specifying k number of documents to retrive, \n",
+    "a filters dictionary for metadata filtering based on [this syntax](https://docs.databricks.com/en/generative-ai/create-query-vector-search.html#use-filters-on-queries),\n",
+    "as well as the [query_type](https://api-docs.databricks.com/python/vector-search/databricks.vector_search.html#databricks.vector_search.index.VectorSearchIndex.similarity_search) which can be ANN or HYBRID "
    ]
   },
   {

docs/docs/integrations/vectorstores/pgvector.ipynb

@@ -78,7 +78,7 @@
     "# See docker command above to launch a postgres instance with pgvector enabled.\n",
     "connection = \"postgresql+psycopg://langchain:langchain@localhost:6024/langchain\"  # Uses psycopg3!\n",
     "collection_name = \"my_docs\"\n",
-    "embeddings = CohereEmbeddings()\n",
+    "embeddings = CohereEmbeddings(model=\"embed-english-v3.0\")\n",
     "\n",
     "vectorstore = PGVector(\n",
     "    embeddings=embeddings,\n",

docs/docs/integrations/vectorstores/qdrant.ipynb

@@ -8,14 +8,15 @@
    "source": [
     "# Qdrant\n",
     "\n",
-    ">[Qdrant](https://qdrant.tech/documentation/) (read: quadrant ) is a vector similarity search engine. It provides a production-ready service with a convenient API to store, search, and manage points - vectors with an additional payload. `Qdrant` is tailored to extended filtering support. It makes it useful for all sorts of neural network or semantic-based matching, faceted search, and other applications.\n",
+    ">[Qdrant](https://qdrant.tech/documentation/) (read: quadrant ) is a vector similarity search engine. It provides a production-ready service with a convenient API to store, search, and manage vectors with additional payload and extended filtering support. It makes it useful for all sorts of neural network or semantic-based matching, faceted search, and other applications.\n",
     "\n",
+    "This documentation demonstrates how to use Qdrant with Langchain for dense/sparse and hybrid retrieval.\n",
     "\n",
-    "This notebook shows how to use functionality related to the `Qdrant` vector database. \n",
+    "> This page documents the `QdrantVectorStore` class that supports multiple retrieval modes via Qdrant's new [Query API](https://qdrant.tech/blog/qdrant-1.10.x/). It requires you to run Qdrant v1.10.0 or above.\n",
     "\n",
     "There are various modes of how to run `Qdrant`, and depending on the chosen one, there will be some subtle differences. The options include:\n",
     "- Local mode, no server required\n",
-    "- On-premise server deployment\n",
+    "- Docker deployments\n",
     "- Qdrant Cloud\n",
     "\n",
     "See the [installation instructions](https://qdrant.tech/documentation/install/)."
@@ -30,7 +31,7 @@
    },
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet  langchain-qdrant langchain-openai langchain langchain-community"
+    "%pip install langchain-qdrant langchain-openai langchain"
    ]
   },
   {
@@ -39,30 +40,7 @@
    "id": "7b2f111b-357a-4f42-9730-ef0603bdc1b5",
    "metadata": {},
    "source": [
-    "We want to use `OpenAIEmbeddings` so we have to get the OpenAI API Key."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "082e7e8b-ac52-430c-98d6-8f0924457642",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "OpenAI API Key: ········\n"
-     ]
-    }
-   ],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")"
+    "We will use `OpenAIEmbeddings` for demonstration."
    ]
   },
   {
@@ -80,7 +58,7 @@
    "source": [
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_openai import OpenAIEmbeddings\n",
-    "from langchain_qdrant import Qdrant\n",
+    "from langchain_qdrant import QdrantVectorStore\n",
     "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
@@ -97,7 +75,7 @@
    },
    "outputs": [],
    "source": [
-    "loader = TextLoader(\"../../how_to/state_of_the_union.txt\")\n",
+    "loader = TextLoader(\"some-file.txt\")\n",
     "documents = loader.load()\n",
     "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
     "docs = text_splitter.split_documents(documents)\n",
@@ -115,7 +93,7 @@
     "\n",
     "### Local mode\n",
     "\n",
-    "Python client allows you to run the same code in local mode without running the Qdrant server. That's great for testing things out and debugging or if you plan to store just a small amount of vectors. The embeddings might be fully kepy in memory or persisted on disk.\n",
+    "Python client allows you to run the same code in local mode without running the Qdrant server. That's great for testing things out and debugging or storing just a small amount of vectors. The embeddings might be fully kept in memory or persisted on disk.\n",
     "\n",
     "#### In-memory\n",
     "\n",
@@ -135,7 +113,7 @@
    },
    "outputs": [],
    "source": [
-    "qdrant = Qdrant.from_documents(\n",
+    "qdrant = QdrantVectorStore.from_documents(\n",
     "    docs,\n",
     "    embeddings,\n",
     "    location=\":memory:\",  # Local mode with in-memory storage only\n",
@@ -151,7 +129,7 @@
    "source": [
     "#### On-disk storage\n",
     "\n",
-    "Local mode, without using the Qdrant server, may also store your vectors on disk so they're persisted between runs."
+    "Local mode, without using the Qdrant server, may also store your vectors on disk so they persist between runs."
    ]
   },
   {
@@ -167,7 +145,7 @@
    },
    "outputs": [],
    "source": [
-    "qdrant = Qdrant.from_documents(\n",
+    "qdrant = QdrantVectorStore.from_documents(\n",
     "    docs,\n",
     "    embeddings,\n",
     "    path=\"/tmp/local_qdrant\",\n",
@@ -199,7 +177,7 @@
    "outputs": [],
    "source": [
     "url = \"<---qdrant url here --->\"\n",
-    "qdrant = Qdrant.from_documents(\n",
+    "qdrant = QdrantVectorStore.from_documents(\n",
     "    docs,\n",
     "    embeddings,\n",
     "    url=url,\n",
@@ -233,7 +211,7 @@
    "source": [
     "url = \"<---qdrant cloud cluster url here --->\"\n",
     "api_key = \"<---api key here--->\"\n",
-    "qdrant = Qdrant.from_documents(\n",
+    "qdrant = QdrantVectorStore.from_documents(\n",
     "    docs,\n",
     "    embeddings,\n",
     "    url=url,\n",
@@ -266,7 +244,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "qdrant = Qdrant.from_existing_collection(\n",
+    "qdrant = QdrantVectorStore.from_existing_collection(\n",
     "    embeddings=embeddings,\n",
     "    collection_name=\"my_documents\",\n",
     "    url=\"http://localhost:6333\",\n",
@@ -297,7 +275,7 @@
    "outputs": [],
    "source": [
     "url = \"<---qdrant url here --->\"\n",
-    "qdrant = Qdrant.from_documents(\n",
+    "qdrant = QdrantVectorStore.from_documents(\n",
     "    docs,\n",
     "    embeddings,\n",
     "    url=url,\n",
@@ -320,12 +298,31 @@
    "source": [
     "## Similarity search\n",
     "\n",
-    "The simplest scenario for using Qdrant vector store is to perform a similarity search. Under the hood, our query will be encoded with the `embedding_function` and used to find similar documents in Qdrant collection."
+    "The simplest scenario for using Qdrant vector store is to perform a similarity search. Under the hood, our query will be encoded into vector embeddings and used to find similar documents in Qdrant collection.\n",
+    "\n",
+    "`QdrantVectorStore` supports 3 modes for similarity searches. They can be configured using the `retrieval_mode` parameter when setting up the class.\n",
+    "\n",
+    "- Dense Vector Search(Default)\n",
+    "- Sparse Vector Search\n",
+    "- Hybrid Search"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b3a78d46",
+   "metadata": {},
+   "source": [
+    "### Dense Vector Search\n",
+    "\n",
+    "To search with only dense vectors,\n",
+    "\n",
+    "- The `retrieval_mode` parameter should be set to `RetrievalMode.DENSE`(default).\n",
+    "- A [dense embeddings](https://python.langchain.com/v0.2/docs/integrations/text_embedding/) value should be provided for the `embedding` parameter."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": null,
    "id": "a8c513ab",
    "metadata": {
     "ExecuteTime": {
@@ -336,38 +333,108 @@
    },
    "outputs": [],
    "source": [
+    "from langchain_qdrant import RetrievalMode\n",
+    "\n",
+    "qdrant = QdrantVectorStore.from_documents(\n",
+    "    docs,\n",
+    "    embedding=embeddings,\n",
+    "    location=\":memory:\",\n",
+    "    collection_name=\"my_documents\",\n",
+    "    retrieval_mode=RetrievalMode.DENSE,\n",
+    ")\n",
+    "\n",
     "query = \"What did the president say about Ketanji Brown Jackson\"\n",
     "found_docs = qdrant.similarity_search(query)"
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "fc516993",
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2023-04-04T10:51:25.220984Z",
-     "start_time": "2023-04-04T10:51:25.213943Z"
-    },
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
-      "\n",
-      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
-      "\n",
-      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
-      "\n",
-      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n"
-     ]
-    }
-   ],
+   "cell_type": "markdown",
+   "id": "dbd93d85",
+   "metadata": {},
    "source": [
-    "print(found_docs[0].page_content)"
+    "### Sparse Vector Search\n",
+    "\n",
+    "To search with only sparse vectors,\n",
+    "\n",
+    "- The `retrieval_mode` parameter should be set to `RetrievalMode.SPARSE`.\n",
+    "- An implementation of the [`SparseEmbeddings`](https://github.com/langchain-ai/langchain/blob/master/libs/partners/qdrant/langchain_qdrant/sparse_embeddings.py) interface using any sparse embeddings provider has to be provided as value to the `sparse_embedding` parameter.\n",
+    "\n",
+    "The `langchain-qdrant` package provides a [FastEmbed](https://github.com/qdrant/fastembed) based implementation out of the box.\n",
+    "\n",
+    "To use it, install the FastEmbed package."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ceb493a3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install fastembed"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "052e3412",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_qdrant import FastEmbedSparse, RetrievalMode\n",
+    "\n",
+    "sparse_embeddings = FastEmbedSparse(model_name=\"Qdrant/BM25\")\n",
+    "\n",
+    "qdrant = QdrantVectorStore.from_documents(\n",
+    "    docs,\n",
+    "    sparse_embedding=sparse_embeddings,\n",
+    "    location=\":memory:\",\n",
+    "    collection_name=\"my_documents\",\n",
+    "    retrieval_mode=RetrievalMode.SPARSE,\n",
+    ")\n",
+    "\n",
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "found_docs = qdrant.similarity_search(query)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f4b6c456",
+   "metadata": {},
+   "source": [
+    "### Hybrid Vector Search\n",
+    "\n",
+    "To perform a hybrid search using dense and sparse vectors with score fusion,\n",
+    "\n",
+    "- The `retrieval_mode` parameter should be set to `RetrievalMode.HYBRID`.\n",
+    "- A [dense embeddings](https://python.langchain.com/v0.2/docs/integrations/text_embedding/) value should be provided for the `embedding` parameter.\n",
+    "- An implementation of the [`SparseEmbeddings`](https://github.com/langchain-ai/langchain/blob/master/libs/partners/qdrant/langchain_qdrant/sparse_embeddings.py) interface using any sparse embeddings provider has to be provided as value to the `sparse_embedding` parameter.\n",
+    "\n",
+    "Note that if you've added documents with the `HYBRID` mode, you can switch to any retrieval mode when searching. Since both the dense and sparse vectors are available in the collection."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ce56f6e9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_qdrant import FastEmbedSparse, RetrievalMode\n",
+    "\n",
+    "sparse_embeddings = FastEmbedSparse(model_name=\"Qdrant/BM25\")\n",
+    "\n",
+    "qdrant = QdrantVectorStore.from_documents(\n",
+    "    docs,\n",
+    "    embedding=embeddings,\n",
+    "    sparse_embedding=sparse_embeddings,\n",
+    "    location=\":memory:\",\n",
+    "    collection_name=\"my_documents\",\n",
+    "    retrieval_mode=RetrievalMode.HYBRID,\n",
+    ")\n",
+    "\n",
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "found_docs = qdrant.similarity_search(query)"
    ]
   },
   {
@@ -400,7 +467,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": null,
    "id": "756a6887",
    "metadata": {
     "ExecuteTime": {
@@ -408,23 +475,7 @@
      "start_time": "2023-04-04T10:51:25.635947Z"
     }
    },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
-      "\n",
-      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
-      "\n",
-      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
-      "\n",
-      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n",
-      "\n",
-      "Score: 0.8153784913324512\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "document, score = found_docs[0]\n",
     "print(document.page_content)\n",
@@ -449,10 +500,10 @@
    "metadata": {},
    "source": [
     "```python\n",
-    "from qdrant_client.http import models as rest\n",
+    "from qdrant_client.http import models\n",
     "\n",
     "query = \"What did the president say about Ketanji Brown Jackson\"\n",
-    "found_docs = qdrant.similarity_search_with_score(query, filter=rest.Filter(...))\n",
+    "found_docs = qdrant.similarity_search_with_score(query, filter=models.Filter(...))\n",
     "```"
    ]
   },
@@ -469,7 +520,9 @@
    "source": [
     "## Maximum marginal relevance search (MMR)\n",
     "\n",
-    "If you'd like to look up for some similar documents, but you'd also like to receive diverse results, MMR is method you should consider. Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents."
+    "If you'd like to look up some similar documents, but you'd also like to receive diverse results, MMR is the method you should consider. Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents.\n",
+    "\n",
+    "Note that MMR search is only available if you've added documents with `DENSE` or `HYBRID` modes. Since it requires dense vectors."
    ]
   },
   {
@@ -490,7 +543,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": null,
    "id": "80c6db11",
    "metadata": {
     "ExecuteTime": {
@@ -498,40 +551,7 @@
      "start_time": "2023-04-04T10:51:26.013329Z"
     }
    },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "1. Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
-      "\n",
-      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
-      "\n",
-      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
-      "\n",
-      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence. \n",
-      "\n",
-      "2. We can’t change how divided we’ve been. But we can change how we move forward—on COVID-19 and other issues we must face together. \n",
-      "\n",
-      "I recently visited the New York City Police Department days after the funerals of Officer Wilbert Mora and his partner, Officer Jason Rivera. \n",
-      "\n",
-      "They were responding to a 9-1-1 call when a man shot and killed them with a stolen gun. \n",
-      "\n",
-      "Officer Mora was 27 years old. \n",
-      "\n",
-      "Officer Rivera was 22. \n",
-      "\n",
-      "Both Dominican Americans who’d grown up on the same streets they later chose to patrol as police officers. \n",
-      "\n",
-      "I spoke with their families and told them that we are forever in debt for their sacrifice, and we will carry on their mission to restore the trust and safety every community deserves. \n",
-      "\n",
-      "I’ve worked on these issues a long time. \n",
-      "\n",
-      "I know what works: Investing in crime prevention and community police officers who’ll walk the beat, who’ll know the neighborhood, and who can restore trust and safety. \n",
-      "\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "for i, doc in enumerate(found_docs):\n",
     "    print(f\"{i + 1}.\", doc.page_content, \"\\n\")"
@@ -545,7 +565,7 @@
    "source": [
     "## Qdrant as a Retriever\n",
     "\n",
-    "Qdrant, as all the other vector stores, is a LangChain Retriever, by using cosine similarity. "
+    "Qdrant, as all the other vector stores, is a LangChain Retriever. "
    ]
   },
   {
@@ -589,7 +609,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": null,
    "id": "f3c70c31",
    "metadata": {
     "ExecuteTime": {
@@ -597,18 +617,7 @@
      "start_time": "2023-04-04T10:51:26.046407Z"
     }
    },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "Document(page_content='Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', metadata={'source': '../../../state_of_the_union.txt'})"
-      ]
-     },
-     "execution_count": 17,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "query = \"What did the president say about Ketanji Brown Jackson\"\n",
     "retriever.invoke(query)[0]"
@@ -622,11 +631,11 @@
    "source": [
     "## Customizing Qdrant\n",
     "\n",
-    "There are some options to use an existing Qdrant collection within your Langchain application. In such cases you may need to define how to map Qdrant point into the Langchain `Document`.\n",
+    "There are options to use an existing Qdrant collection within your Langchain application. In such cases, you may need to define how to map Qdrant point into the Langchain `Document`.\n",
     "\n",
     "### Named vectors\n",
     "\n",
-    "Qdrant supports [multiple vectors per point](https://qdrant.tech/documentation/concepts/collections/#collection-with-multiple-vectors) by named vectors. Langchain requires just a single embedding per document and, by default, uses a single vector. However, if you work with a collection created externally or want to have the named vector used, you can configure it by providing its name.\n"
+    "Qdrant supports [multiple vectors per point](https://qdrant.tech/documentation/concepts/collections/#collection-with-multiple-vectors) by named vectors. If you work with a collection created externally or want to have the differently named vector used, you can configure it by providing its name.\n"
    ]
   },
   {
@@ -638,25 +647,18 @@
    },
    "outputs": [],
    "source": [
-    "Qdrant.from_documents(\n",
+    "QdrantVectorStore.from_documents(\n",
     "    docs,\n",
-    "    embeddings,\n",
+    "    embedding=embeddings,\n",
+    "    sparse_embedding=sparse_embeddings,\n",
     "    location=\":memory:\",\n",
     "    collection_name=\"my_documents_2\",\n",
+    "    retrieval_mode=RetrievalMode.HYBRID,\n",
     "    vector_name=\"custom_vector\",\n",
+    "    sparse_vector_name=\"custom_sparse_vector\",\n",
     ")"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "b34f5230",
-   "metadata": {
-    "collapsed": false
-   },
-   "source": [
-    "As a Langchain user, you won't see any difference whether you use named vectors or not. Qdrant integration will handle the conversion under the hood."
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "b2350093",
@@ -694,7 +696,7 @@
    },
    "outputs": [],
    "source": [
-    "Qdrant.from_documents(\n",
+    "QdrantVectorStore.from_documents(\n",
     "    docs,\n",
     "    embeddings,\n",
     "    location=\":memory:\",\n",
@@ -729,7 +731,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.3"
+   "version": "3.11.8"
   }
  },
  "nbformat": 4,

docs/docs/introduction.mdx

@@ -22,6 +22,7 @@ import useBaseUrl from '@docusaurus/useBaseUrl';
     light: useBaseUrl('/svg/langchain_stack_062024.svg'),
     dark: useBaseUrl('/svg/langchain_stack_062024_dark.svg'),
   }}
+  style={{ width: "100%" }}
   title="LangChain Framework Overview"
 />
 

docs/docs/tutorials/chatbot.ipynb

@@ -270,8 +270,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.chat_message_histories import ChatMessageHistory\n",
-    "from langchain_core.chat_history import BaseChatMessageHistory\n",
+    "from langchain_core.chat_history import (\n",
+    "    BaseChatMessageHistory,\n",
+    "    InMemoryChatMessageHistory,\n",
+    ")\n",
     "from langchain_core.runnables.history import RunnableWithMessageHistory\n",
     "\n",
     "store = {}\n",
@@ -279,7 +281,7 @@
     "\n",
     "def get_session_history(session_id: str) -> BaseChatMessageHistory:\n",
     "    if session_id not in store:\n",
-    "        store[session_id] = ChatMessageHistory()\n",
+    "        store[session_id] = InMemoryChatMessageHistory()\n",
     "    return store[session_id]\n",
     "\n",
     "\n",

docs/docs/tutorials/rag.ipynb

@@ -107,7 +107,7 @@
     "```\n",
     "## Preview\n",
     "\n",
-    "In this guide we’ll build a QA app over as website. The specific website we will use is the [LLM Powered Autonomous\n",
+    "In this guide we’ll build an app that answers questions about the content of a website. The specific website we will use is the [LLM Powered Autonomous\n",
     "Agents](https://lilianweng.github.io/posts/2023-06-23-agent/) blog post\n",
     "by Lilian Weng, which allows us to ask questions about the contents of\n",
     "the post.\n",

docs/docs/tutorials/retrievers.ipynb

@@ -269,7 +269,7 @@
    "id": "b4991642-7275-40a9-b11a-e3beccbf2614",
    "metadata": {},
    "source": [
-    "Return documents based on similarity to a embedded query:"
+    "Return documents based on similarity to an embedded query:"
    ]
   },
   {

docs/docs/versions/v0_2/deprecations.mdx

@@ -568,6 +568,8 @@ Removal: 0.3.0
 
 Alternative: [RunnableSequence](/docs/how_to/sequence/), e.g., `prompt | llm`
 
+This [migration guide](/docs/how_to/migrate_chains/#llmchain) has a side-by-side comparison.
+
 
 #### LLMSingleActionAgent
 
@@ -754,6 +756,7 @@ Removal: 0.3.0
 
 
 Alternative: [create_retrieval_chain](https://api.python.langchain.com/en/latest/chains/langchain.chains.retrieval.create_retrieval_chain.html#langchain-chains-retrieval-create-retrieval-chain)
+This [migration guide](/docs/how_to/migrate_chains/#retrievalqa) has a side-by-side comparison.
 
 
 #### load_agent_from_config
@@ -820,6 +823,7 @@ Removal: 0.3.0
 
 
 Alternative: [create_history_aware_retriever](https://api.python.langchain.com/en/latest/chains/langchain.chains.history_aware_retriever.create_history_aware_retriever.html) together with [create_retrieval_chain](https://api.python.langchain.com/en/latest/chains/langchain.chains.retrieval.create_retrieval_chain.html#langchain-chains-retrieval-create-retrieval-chain) (see example in docstring)
+This [migration guide](/docs/how_to/migrate_chains/#conversationalretrievalchain) has a side-by-side comparison.
 
 
 #### create_extraction_chain_pydantic

docs/docs/versions/v0_2/index.mdx

@@ -11,6 +11,7 @@ LangChain v0.2 was released in May 2024. This release includes a number of [brea
 :::note Reference
 
 - [Breaking Changes & Deprecations](/docs/versions/v0_2/deprecations)
+- [Migrating legacy chains to LCEL](/docs/how_to/migrate_chains/)
 - [Migrating to Astream Events v2](/docs/versions/v0_2/migrating_astream_events)
 
 :::

docs/docusaurus.config.js

@@ -275,10 +275,6 @@ const config = {
           {
             title: "Community",
             items: [
-              {
-                label: "Discord",
-                href: "https://discord.gg/cU2adEyC7w",
-              },
               {
                 label: "Twitter",
                 href: "https://twitter.com/LangChainAI",

docs/ignore-step.sh

@@ -0,0 +1,23 @@
+#!/bin/bash
+
+echo "VERCEL_ENV: $VERCEL_ENV"
+echo "VERCEL_GIT_COMMIT_REF: $VERCEL_GIT_COMMIT_REF"
+
+
+if [ "$VERCEL_ENV" == "production" ] || [ "$VERCEL_GIT_COMMIT_REF" == "master" ] || [ "$VERCEL_GIT_COMMIT_REF" == "v0.1" ]; then 
+    echo "✅ Production build - proceeding with build"
+    exit 1; 
+else 
+    echo "Checking for changes in docs/ and templates/:"
+    echo "---"
+    git log -n 50 --pretty=format:"%s" -- . ../templates | grep -v '(#'
+    if [ $? -eq 0 ]; then
+        echo "---"
+        echo "✅ Changes detected in docs/ or templates/ - proceeding with build"
+        exit 1
+    else
+        echo "---"
+        echo "🛑 No changes detected in docs/ or templates/ - ignoring build"
+        exit 0
+    fi
+fi

docs/scripts/document_loader_feat_table.py

@@ -23,6 +23,18 @@ The following table shows the feature support for all document loaders.
 
 """
 
+DEPRECATED = [
+    "AirbyteCDKLoader",
+    "AirbyteGongLoader",
+    "AirbyteHubspotLoader",
+    "AirbyteJSONLoader",
+    "AirbyteSalesforceLoader",
+    "AirbyteShopifyLoader",
+    "AirbyteStripeLoader",
+    "AirbyteTypeformLoader",
+    "AirbyteZendeskSupportLoader",
+]
+
 
 def get_document_loader_table() -> str:
     """Get the table of document loaders."""
@@ -55,7 +67,7 @@ def get_document_loader_table() -> str:
     title = ["Document Loader", "Description", "Lazy loading", "Native async support"]
     rows = [title, [":-"] * 2 + [":-:"] * (len(title) - 2)]
     for loader, feats in sorted(doc_loaders_feat_table.items()):
-        if not feats:
+        if not feats or loader in DEPRECATED:
             continue
         rows += [
             [loader, feats["description"]]

docs/src/theme/Columns.js

@@ -10,7 +10,7 @@ export function ColumnContainer({children}) {
 
 export function Column({children}) {
     return (
-        <div style={{ flex: "1 0 300px", padding: "10px", overflowX: "clip", zoom: '80%' }}>
+        <div style={{ flex: "1 0 300px", padding: "10px", overflowX: "scroll", zoom: '80%' }}>
             {children}
         </div>
     )

docs/vercel.json

@@ -1,6 +1,7 @@
 {
   "buildCommand": "yarn build",
   "outputDirectory": "build",
+  "ignoreCommand": "bash ignore-step.sh",
   "trailingSlash": true,
   "rewrites": [
     {

libs/community/Makefile

@@ -46,7 +46,7 @@ lint_tests: MYPY_CACHE=.mypy_cache_test
 
 lint lint_diff lint_package lint_tests:
 	./scripts/check_pydantic.sh .
-	./scripts/lint_imports.sh
+	./scripts/lint_imports.sh .
 	./scripts/check_pickle.sh .
 	poetry run ruff check .
 	[ "$(PYTHON_FILES)" = "" ] || poetry run ruff format $(PYTHON_FILES) --diff

libs/community/extended_testing_deps.txt

@@ -52,7 +52,7 @@ openapi-pydantic>=0.3.2,<0.4
 oracle-ads>=2.9.1,<3
 oracledb>=2.2.0,<3
 pandas>=2.0.1,<3
-pdfminer-six>=20221105
+pdfminer-six>=20221105,<20240706
 pgvector>=0.1.6,<0.2
 praw>=7.7.1,<8
 premai>=0.3.25,<0.4
@@ -72,6 +72,7 @@ rspace_client>=2.5.0,<3
 scikit-learn>=1.2.2,<2
 simsimd>=4.3.1,<5
 sqlite-vss>=0.1.2,<0.2
+sseclient-py>=1.8.0,<2
 streamlit>=1.18.0,<2
 sympy>=1.12,<2
 telethon>=1.28.5,<2

libs/community/langchain_community/agent_toolkits/file_management/toolkit.py

@@ -63,7 +63,7 @@ class FileManagementToolkit(BaseToolkit):
     selected_tools: Optional[List[str]] = None
     """If provided, only provide the selected tools. Defaults to all."""
 
-    @root_validator
+    @root_validator(pre=True)
     def validate_tools(cls, values: dict) -> dict:
         selected_tools = values.get("selected_tools") or []
         for tool_name in selected_tools:

libs/community/langchain_community/agent_toolkits/playwright/toolkit.py

@@ -74,7 +74,7 @@ class PlayWrightBrowserToolkit(BaseToolkit):
         extra = Extra.forbid
         arbitrary_types_allowed = True
 
-    @root_validator
+    @root_validator(pre=True)
     def validate_imports_and_browser_provided(cls, values: dict) -> dict:
         """Check that the arguments are valid."""
         lazy_import_playwright_browsers()

libs/community/langchain_community/callbacks/openai_info.py

@@ -223,19 +223,23 @@ class OpenAICallbackHandler(BaseCallbackHandler):
                 message = generation.message
                 if isinstance(message, AIMessage):
                     usage_metadata = message.usage_metadata
+                    response_metadata = message.response_metadata
                 else:
                     usage_metadata = None
+                    response_metadata = None
             except AttributeError:
                 usage_metadata = None
+                response_metadata = None
         else:
             usage_metadata = None
+            response_metadata = None
         if usage_metadata:
             token_usage = {"total_tokens": usage_metadata["total_tokens"]}
             completion_tokens = usage_metadata["output_tokens"]
             prompt_tokens = usage_metadata["input_tokens"]
-            if response.llm_output is None:
-                # model name (and therefore cost) is unavailable in
-                # streaming responses
+            if response_model_name := (response_metadata or {}).get("model_name"):
+                model_name = standardize_model_name(response_model_name)
+            elif response.llm_output is None:
                 model_name = ""
             else:
                 model_name = standardize_model_name(

libs/community/langchain_community/chains/pebblo_retrieval/base.py

@@ -272,14 +272,11 @@ class PebbloRetrievalQA(Chain):
         """
         Validate that the vectorstore of the retriever is supported vectorstores.
         """
-        if not any(
-            isinstance(retriever.vectorstore, supported_class)
-            for supported_class in SUPPORTED_VECTORSTORES
-        ):
+        if retriever.vectorstore.__class__.__name__ not in SUPPORTED_VECTORSTORES:
             raise ValueError(
                 f"Vectorstore must be an instance of one of the supported "
                 f"vectorstores: {SUPPORTED_VECTORSTORES}. "
-                f"Got {type(retriever.vectorstore).__name__} instead."
+                f"Got '{retriever.vectorstore.__class__.__name__}' instead."
             )
         return retriever
 

libs/community/langchain_community/chains/pebblo_retrieval/enforcement_filters.py

@@ -13,7 +13,7 @@ The methods in this module are designed to work with different types of vector s
 """
 
 import logging
-from typing import List, Optional, Union
+from typing import Any, List, Optional, Union
 
 from langchain_core.vectorstores import VectorStoreRetriever
 
@@ -21,11 +21,33 @@ from langchain_community.chains.pebblo_retrieval.models import (
     AuthContext,
     SemanticContext,
 )
-from langchain_community.vectorstores import Pinecone, Qdrant
 
 logger = logging.getLogger(__name__)
 
-SUPPORTED_VECTORSTORES = [Pinecone, Qdrant]
+PINECONE = "Pinecone"
+QDRANT = "Qdrant"
+PGVECTOR = "PGVector"
+
+SUPPORTED_VECTORSTORES = {PINECONE, QDRANT, PGVECTOR}
+
+
+def clear_enforcement_filters(retriever: VectorStoreRetriever) -> None:
+    """
+    Clear the identity and semantic enforcement filters in the retriever search_kwargs.
+    """
+    if retriever.vectorstore.__class__.__name__ == PGVECTOR:
+        search_kwargs = retriever.search_kwargs
+        if "filter" in search_kwargs:
+            filters = search_kwargs["filter"]
+            _pgvector_clear_pebblo_filters(
+                search_kwargs, filters, "authorized_identities"
+            )
+            _pgvector_clear_pebblo_filters(
+                search_kwargs, filters, "pebblo_semantic_topics"
+            )
+            _pgvector_clear_pebblo_filters(
+                search_kwargs, filters, "pebblo_semantic_entities"
+            )
 
 
 def set_enforcement_filters(
@@ -36,6 +58,8 @@ def set_enforcement_filters(
     """
     Set identity and semantic enforcement filters in the retriever.
     """
+    # Clear existing enforcement filters
+    clear_enforcement_filters(retriever)
     if auth_context is not None:
         _set_identity_enforcement_filter(retriever, auth_context)
     if semantic_context is not None:
@@ -233,6 +257,244 @@ def _apply_pinecone_authorization_filter(
         }
 
 
+def _apply_pgvector_filter(
+    search_kwargs: dict, filters: Optional[Any], pebblo_filter: dict
+) -> None:
+    """
+    Apply pebblo filters in the search_kwargs filters.
+    """
+    if isinstance(filters, dict):
+        if len(filters) == 1:
+            # The only operators allowed at the top level are $and, $or, and $not
+            # First check if an operator or a field
+            key, value = list(filters.items())[0]
+            if key.startswith("$"):
+                # Then it's an operator
+                if key.lower() not in ["$and", "$or", "$not"]:
+                    raise ValueError(
+                        f"Invalid filter condition. Expected $and, $or or $not "
+                        f"but got: {key}"
+                    )
+                if not isinstance(value, list):
+                    raise ValueError(
+                        f"Expected a list, but got {type(value)} for value: {value}"
+                    )
+
+                # Here we handle the $and, $or, and $not operators(Semantic filters)
+                if key.lower() == "$and":
+                    # Add pebblo_filter to the $and list as it is
+                    value.append(pebblo_filter)
+                elif key.lower() == "$not":
+                    # Check if pebblo_filter is an operator or a field
+                    _key, _value = list(pebblo_filter.items())[0]
+                    if _key.startswith("$"):
+                        # Then it's a operator
+                        if _key.lower() == "$not":
+                            # It's Semantic filter, add it's value to filters
+                            value.append(_value)
+                            logger.warning(
+                                "Adding $not operator to the existing $not operator"
+                            )
+                            return
+                        else:
+                            # Only $not operator is supported in pebblo_filter
+                            raise ValueError(
+                                f"Invalid filter key. Expected '$not' but got: {_key}"
+                            )
+                    else:
+                        # Then it's a field(Auth filter), move filters into $and
+                        search_kwargs["filter"] = {"$and": [filters, pebblo_filter]}
+                        return
+                elif key.lower() == "$or":
+                    search_kwargs["filter"] = {"$and": [filters, pebblo_filter]}
+            else:
+                # Then it's a field and we can check pebblo_filter now
+                # Check if pebblo_filter is an operator or a field
+                _key, _ = list(pebblo_filter.items())[0]
+                if _key.startswith("$"):
+                    # Then it's a operator
+                    if _key.lower() == "$not":
+                        # It's a $not operator(Semantic filter), move filters into $and
+                        search_kwargs["filter"] = {"$and": [filters, pebblo_filter]}
+                        return
+                    else:
+                        # Only $not operator is allowed in pebblo_filter
+                        raise ValueError(
+                            f"Invalid filter key. Expected '$not' but got: {_key}"
+                        )
+                else:
+                    # Then it's a field(This handles Auth filter)
+                    filters.update(pebblo_filter)
+                    return
+        elif len(filters) > 1:
+            # Then all keys have to be fields (they cannot be operators)
+            for key in filters.keys():
+                if key.startswith("$"):
+                    raise ValueError(
+                        f"Invalid filter condition. Expected a field but got: {key}"
+                    )
+            # filters should all be fields and we can check pebblo_filter now
+            # Check if pebblo_filter is an operator or a field
+            _key, _ = list(pebblo_filter.items())[0]
+            if _key.startswith("$"):
+                # Then it's a operator
+                if _key.lower() == "$not":
+                    # It's a $not operator(Semantic filter), move filters into '$and'
+                    search_kwargs["filter"] = {"$and": [filters, pebblo_filter]}
+                    return
+                else:
+                    # Only $not operator is supported in pebblo_filter
+                    raise ValueError(
+                        f"Invalid filter key. Expected '$not' but got: {_key}"
+                    )
+            else:
+                # Then it's a field(This handles Auth filter)
+                filters.update(pebblo_filter)
+                return
+        else:
+            # Got an empty dictionary for filters, set pebblo_filter in filter
+            search_kwargs.setdefault("filter", {}).update(pebblo_filter)
+    elif filters is None:
+        # If filters is None, set pebblo_filter as a new filter
+        search_kwargs.setdefault("filter", {}).update(pebblo_filter)
+    else:
+        raise ValueError(
+            f"Invalid filter. Expected a dictionary/None but got type: {type(filters)}"
+        )
+
+
+def _pgvector_clear_pebblo_filters(
+    search_kwargs: dict, filters: dict, pebblo_filter_key: str
+) -> None:
+    """
+    Remove pebblo filters from the search_kwargs filters.
+    """
+    if isinstance(filters, dict):
+        if len(filters) == 1:
+            # The only operators allowed at the top level are $and, $or, and $not
+            # First check if an operator or a field
+            key, value = list(filters.items())[0]
+            if key.startswith("$"):
+                # Then it's an operator
+                # Validate the operator's key and value type
+                if key.lower() not in ["$and", "$or", "$not"]:
+                    raise ValueError(
+                        f"Invalid filter condition. Expected $and, $or or $not "
+                        f"but got: {key}"
+                    )
+                elif not isinstance(value, list):
+                    raise ValueError(
+                        f"Expected a list, but got {type(value)} for value: {value}"
+                    )
+
+                # Here we handle the $and, $or, and $not operators
+                if key.lower() == "$and":
+                    # Remove the pebblo filter from the $and list
+                    for i, _filter in enumerate(value):
+                        if pebblo_filter_key in _filter:
+                            # This handles Auth filter
+                            value.pop(i)
+                            break
+                        # Check for $not operator with Semantic filter
+                        if "$not" in _filter:
+                            sem_filter_found = False
+                            # This handles Semantic filter
+                            for j, nested_filter in enumerate(_filter["$not"]):
+                                if pebblo_filter_key in nested_filter:
+                                    if len(_filter["$not"]) == 1:
+                                        # If only one filter is left,
+                                        # then remove the $not operator
+                                        value.pop(i)
+                                    else:
+                                        value[i]["$not"].pop(j)
+                                    sem_filter_found = True
+                                    break
+                            if sem_filter_found:
+                                break
+                    if len(value) == 1:
+                        # If only one filter is left, then remove the $and operator
+                        search_kwargs["filter"] = value[0]
+                elif key.lower() == "$not":
+                    # Remove the pebblo filter from the $not list
+                    for i, _filter in enumerate(value):
+                        if pebblo_filter_key in _filter:
+                            # This removes Semantic filter
+                            value.pop(i)
+                            break
+                    if len(value) == 0:
+                        # If no filter is left, then unset the filter
+                        search_kwargs["filter"] = {}
+                elif key.lower() == "$or":
+                    # If $or, pebblo filter will not be present
+                    return
+            else:
+                # Then it's a field, check if it's a pebblo filter
+                if key == pebblo_filter_key:
+                    filters.pop(key)
+                return
+        elif len(filters) > 1:
+            # Then all keys have to be fields (they cannot be operators)
+            if pebblo_filter_key in filters:
+                # This handles Auth filter
+                filters.pop(pebblo_filter_key)
+            return
+        else:
+            # Got an empty dictionary for filters, ignore the filter
+            return
+    elif filters is None:
+        # If filters is None, ignore the filter
+        return
+    else:
+        raise ValueError(
+            f"Invalid filter. Expected a dictionary/None but got type: {type(filters)}"
+        )
+
+
+def _apply_pgvector_semantic_filter(
+    search_kwargs: dict, semantic_context: Optional[SemanticContext]
+) -> None:
+    """
+    Set semantic enforcement filter in search_kwargs for PGVector vectorstore.
+    """
+    # Check if semantic_context is provided
+    if semantic_context is not None:
+        _semantic_filters = []
+        filters = search_kwargs.get("filter")
+        if semantic_context.pebblo_semantic_topics is not None:
+            # Add pebblo_semantic_topics filter to search_kwargs
+            topic_filter: dict = {
+                "pebblo_semantic_topics": {
+                    "$eq": semantic_context.pebblo_semantic_topics.deny
+                }
+            }
+            _semantic_filters.append(topic_filter)
+
+        if semantic_context.pebblo_semantic_entities is not None:
+            # Add pebblo_semantic_entities filter to search_kwargs
+            entity_filter: dict = {
+                "pebblo_semantic_entities": {
+                    "$eq": semantic_context.pebblo_semantic_entities.deny
+                }
+            }
+            _semantic_filters.append(entity_filter)
+
+        if len(_semantic_filters) > 0:
+            semantic_filter: dict = {"$not": _semantic_filters}
+            _apply_pgvector_filter(search_kwargs, filters, semantic_filter)
+
+
+def _apply_pgvector_authorization_filter(
+    search_kwargs: dict, auth_context: Optional[AuthContext]
+) -> None:
+    """
+    Set identity enforcement filter in search_kwargs for PGVector vectorstore.
+    """
+    if auth_context is not None:
+        auth_filter: dict = {"authorized_identities": {"$eq": auth_context.user_auth}}
+        filters = search_kwargs.get("filter")
+        _apply_pgvector_filter(search_kwargs, filters, auth_filter)
+
+
 def _set_identity_enforcement_filter(
     retriever: VectorStoreRetriever, auth_context: Optional[AuthContext]
 ) -> None:
@@ -243,10 +505,12 @@ def _set_identity_enforcement_filter(
     of the retriever based on the type of the vectorstore.
     """
     search_kwargs = retriever.search_kwargs
-    if isinstance(retriever.vectorstore, Pinecone):
+    if retriever.vectorstore.__class__.__name__ == PINECONE:
         _apply_pinecone_authorization_filter(search_kwargs, auth_context)
-    elif isinstance(retriever.vectorstore, Qdrant):
+    elif retriever.vectorstore.__class__.__name__ == QDRANT:
         _apply_qdrant_authorization_filter(search_kwargs, auth_context)
+    elif retriever.vectorstore.__class__.__name__ == PGVECTOR:
+        _apply_pgvector_authorization_filter(search_kwargs, auth_context)
 
 
 def _set_semantic_enforcement_filter(
@@ -259,7 +523,9 @@ def _set_semantic_enforcement_filter(
     of the retriever based on the type of the vectorstore.
     """
     search_kwargs = retriever.search_kwargs
-    if isinstance(retriever.vectorstore, Pinecone):
+    if retriever.vectorstore.__class__.__name__ == PINECONE:
         _apply_pinecone_semantic_filter(search_kwargs, semantic_context)
-    elif isinstance(retriever.vectorstore, Qdrant):
+    elif retriever.vectorstore.__class__.__name__ == QDRANT:
         _apply_qdrant_semantic_filter(search_kwargs, semantic_context)
+    elif retriever.vectorstore.__class__.__name__ == PGVECTOR:
+        _apply_pgvector_semantic_filter(search_kwargs, semantic_context)

libs/community/langchain_community/chat_message_histories/sql.py

@@ -113,7 +113,33 @@ _warned_once_already = False
 
 
 class SQLChatMessageHistory(BaseChatMessageHistory):
-    """Chat message history stored in an SQL database."""
+    """Chat message history stored in an SQL database.
+
+    Example:
+        .. code-block:: python
+
+            from langchain_core.messages import HumanMessage
+
+            from langchain_community.chat_message_histories import SQLChatMessageHistory
+
+            # create sync sql message history by connection_string
+            message_history = SQLChatMessageHistory(
+                session_id='foo', connection_string='sqlite///:memory.db'
+            )
+            message_history.add_message(HumanMessage("hello"))
+            message_history.message
+
+            # create async sql message history using aiosqlite
+            # from sqlalchemy.ext.asyncio import create_async_engine
+            #
+            # async_engine = create_async_engine("sqlite+aiosqlite:///memory.db")
+            # async_message_history = SQLChatMessageHistory(
+            #     session_id='foo', connection=async_engine,
+            # )
+            # await async_message_history.aadd_message(HumanMessage("hello"))
+            # await async_message_history.aget_messages()
+
+    """
 
     @property
     @deprecated("0.2.2", removal="0.3.0", alternative="session_maker")
@@ -131,6 +157,21 @@ class SQLChatMessageHistory(BaseChatMessageHistory):
         engine_args: Optional[Dict[str, Any]] = None,
         async_mode: Optional[bool] = None,  # Use only if connection is a string
     ):
+        """Initialize with a SQLChatMessageHistory instance.
+
+        Args:
+            session_id: Indicates the id of the same session.
+            connection_string: String parameter configuration for connecting
+                to the database.
+            table_name: Table name used to save data.
+            session_id_field_name: The name of field of `session_id`.
+            custom_message_converter: Custom message converter for converting
+                database data and `BaseMessage`
+            connection: Database connection object, which can be a string containing
+                connection configuration, Engine object or AsyncEngine object.
+            engine_args: Additional configuration for creating database engines.
+            async_mode: Whether it is an asynchronous connection.
+        """
         assert not (
             connection_string and connection
         ), "connection_string and connection are mutually exclusive"

libs/community/langchain_community/chat_models/anyscale.py

@@ -25,7 +25,7 @@ if TYPE_CHECKING:
 logger = logging.getLogger(__name__)
 
 DEFAULT_API_BASE = "https://api.endpoints.anyscale.com/v1"
-DEFAULT_MODEL = "meta-llama/Llama-2-7b-chat-hf"
+DEFAULT_MODEL = "meta-llama/Meta-Llama-3-8B-Instruct"
 
 
 class ChatAnyscale(ChatOpenAI):

libs/community/langchain_community/chat_models/azure_openai.py

@@ -9,8 +9,8 @@ from typing import Any, Callable, Dict, List, Union
 
 from langchain_core._api.deprecation import deprecated
 from langchain_core.outputs import ChatResult
-from langchain_core.pydantic_v1 import BaseModel, Field, root_validator
-from langchain_core.utils import get_from_dict_or_env
+from langchain_core.pydantic_v1 import BaseModel, Field
+from langchain_core.utils import get_from_dict_or_env, pre_init
 
 from langchain_community.chat_models.openai import ChatOpenAI
 from langchain_community.utils.openai import is_openai_v1
@@ -106,7 +106,7 @@ class AzureChatOpenAI(ChatOpenAI):
         """Get the namespace of the langchain object."""
         return ["langchain", "chat_models", "azure_openai"]
 
-    @root_validator()
+    @pre_init
     def validate_environment(cls, values: Dict) -> Dict:
         """Validate that api key and python package exists in environment."""
         if values["n"] < 1: