core: release 0.3.19 (#28137)

This page was previously not discoverable.

.github/CODEOWNERS

@@ -0,0 +1,2 @@
+/.github/   @efriis @baskaryan @ccurme
+/libs/packages.yml   @efriis

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,7 +1,7 @@
 Thank you for contributing to LangChain!
 
 - [ ] **PR title**: "package: description"
-  - Where "package" is whichever of langchain, community, core, etc. is being modified. Use "docs: ..." for purely docs changes, "templates: ..." for template changes, "infra: ..." for CI changes.
+  - Where "package" is whichever of langchain, community, core, etc. is being modified. Use "docs: ..." for purely docs changes, "infra: ..." for CI changes.
   - Example: "community: add foobar LLM"
 
 

.github/scripts/check_diff.py

@@ -37,7 +37,6 @@ IGNORED_PARTNERS = [
 PY_312_MAX_PACKAGES = [
     f"libs/partners/{integration}"
     for integration in [
-        "anthropic",
         "chroma",
         "couchbase",
         "huggingface",
@@ -307,7 +306,7 @@ if __name__ == "__main__":
                 f"Unknown lib: {file}. check_diff.py likely needs "
                 "an update for this new library!"
             )
-        elif any(file.startswith(p) for p in ["docs/", "templates/", "cookbook/"]):
+        elif any(file.startswith(p) for p in ["docs/", "cookbook/"]):
             if file.startswith("docs/"):
                 docs_edited = True
             dirs_to_run["lint"].add(".")

.github/scripts/get_min_versions.py

@@ -7,17 +7,23 @@ else:
     # for python 3.10 and below, which doesnt have stdlib tomllib
     import tomli as tomllib
 
-from packaging.version import parse as parse_version
 from packaging.specifiers import SpecifierSet
 from packaging.version import Version
 
+
+import requests
+from packaging.version import parse
+from typing import List
+
 import re
 
+
 MIN_VERSION_LIBS = [
     "langchain-core",
     "langchain-community",
     "langchain",
     "langchain-text-splitters",
+    "numpy",
     "SQLAlchemy",
 ]
 
@@ -31,29 +37,61 @@ SKIP_IF_PULL_REQUEST = [
 ]
 
 
-def get_min_version(version: str) -> str:
-    # base regex for x.x.x with cases for rc/post/etc
-    # valid strings: https://peps.python.org/pep-0440/#public-version-identifiers
-    vstring = r"\d+(?:\.\d+){0,2}(?:(?:a|b|rc|\.post|\.dev)\d+)?"
-    # case ^x.x.x
-    _match = re.match(f"^\\^({vstring})$", version)
-    if _match:
-        return _match.group(1)
+def get_pypi_versions(package_name: str) -> List[str]:
+    """
+    Fetch all available versions for a package from PyPI.
 
-    # case >=x.x.x,<y.y.y
-    _match = re.match(f"^>=({vstring}),<({vstring})$", version)
-    if _match:
-        _min = _match.group(1)
-        _max = _match.group(2)
-        assert parse_version(_min) < parse_version(_max)
-        return _min
+    Args:
+        package_name (str): Name of the package
 
-    # case x.x.x
-    _match = re.match(f"^({vstring})$", version)
-    if _match:
-        return _match.group(1)
+    Returns:
+        List[str]: List of all available versions
 
-    raise ValueError(f"Unrecognized version format: {version}")
+    Raises:
+        requests.exceptions.RequestException: If PyPI API request fails
+        KeyError: If package not found or response format unexpected
+    """
+    pypi_url = f"https://pypi.org/pypi/{package_name}/json"
+    response = requests.get(pypi_url)
+    response.raise_for_status()
+    return list(response.json()["releases"].keys())
+
+
+def get_minimum_version(package_name: str, spec_string: str) -> Optional[str]:
+    """
+    Find the minimum published version that satisfies the given constraints.
+
+    Args:
+        package_name (str): Name of the package
+        spec_string (str): Version specification string (e.g., ">=0.2.43,<0.4.0,!=0.3.0")
+
+    Returns:
+        Optional[str]: Minimum compatible version or None if no compatible version found
+    """
+    # rewrite occurrences of ^0.0.z to 0.0.z (can be anywhere in constraint string)
+    spec_string = re.sub(r"\^0\.0\.(\d+)", r"0.0.\1", spec_string)
+    # rewrite occurrences of ^0.y.z to >=0.y.z,<0.y+1 (can be anywhere in constraint string)
+    for y in range(1, 10):
+        spec_string = re.sub(rf"\^0\.{y}\.(\d+)", rf">=0.{y}.\1,<0.{y+1}", spec_string)
+    # rewrite occurrences of ^x.y.z to >=x.y.z,<x+1.0.0 (can be anywhere in constraint string)
+    for x in range(1, 10):
+        spec_string = re.sub(
+            rf"\^{x}\.(\d+)\.(\d+)", rf">={x}.\1.\2,<{x+1}", spec_string
+        )
+
+    spec_set = SpecifierSet(spec_string)
+    all_versions = get_pypi_versions(package_name)
+
+    valid_versions = []
+    for version_str in all_versions:
+        try:
+            version = parse(version_str)
+            if spec_set.contains(version):
+                valid_versions.append(version)
+        except ValueError:
+            continue
+
+    return str(min(valid_versions)) if valid_versions else None
 
 
 def get_min_version_from_toml(
@@ -96,7 +134,7 @@ def get_min_version_from_toml(
                 ][0]["version"]
 
             # Use parse_version to get the minimum supported version from version_string
-            min_version = get_min_version(version_string)
+            min_version = get_minimum_version(lib, version_string)
 
             # Store the minimum version in the min_versions dictionary
             min_versions[lib] = min_version
@@ -112,6 +150,20 @@ def check_python_version(version_string, constraint_string):
     :param constraint_string: A string representing the package's Python version constraints (e.g. ">=3.6, <4.0").
     :return: True if the version matches the constraints, False otherwise.
     """
+
+    # rewrite occurrences of ^0.0.z to 0.0.z (can be anywhere in constraint string)
+    constraint_string = re.sub(r"\^0\.0\.(\d+)", r"0.0.\1", constraint_string)
+    # rewrite occurrences of ^0.y.z to >=0.y.z,<0.y+1.0 (can be anywhere in constraint string)
+    for y in range(1, 10):
+        constraint_string = re.sub(
+            rf"\^0\.{y}\.(\d+)", rf">=0.{y}.\1,<0.{y+1}.0", constraint_string
+        )
+    # rewrite occurrences of ^x.y.z to >=x.y.z,<x+1.0.0 (can be anywhere in constraint string)
+    for x in range(1, 10):
+        constraint_string = re.sub(
+            rf"\^{x}\.0\.(\d+)", rf">={x}.0.\1,<{x+1}.0.0", constraint_string
+        )
+
     try:
         version = Version(version_string)
         constraints = SpecifierSet(constraint_string)

.github/workflows/_integration_test.yml

@@ -41,12 +41,6 @@ jobs:
         shell: bash
         run: poetry run pip install "boto3<2" "google-cloud-aiplatform<2"
 
-      - name: 'Authenticate to Google Cloud'
-        id: 'auth'
-        uses: google-github-actions/auth@v2
-        with:
-          credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
-
       - name: Run integration tests
         shell: bash
         env:
@@ -81,11 +75,11 @@ jobs:
           ES_URL: ${{ secrets.ES_URL }}
           ES_CLOUD_ID: ${{ secrets.ES_CLOUD_ID }}
           ES_API_KEY: ${{ secrets.ES_API_KEY }}
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} # for airbyte
           MONGODB_ATLAS_URI: ${{ secrets.MONGODB_ATLAS_URI }}
           VOYAGE_API_KEY: ${{ secrets.VOYAGE_API_KEY }}
           COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
           UPSTAGE_API_KEY: ${{ secrets.UPSTAGE_API_KEY }}
+          XAI_API_KEY: ${{ secrets.XAI_API_KEY }}
         run: |
           make integration_tests
 

.github/workflows/_release.yml

@@ -95,9 +95,30 @@ jobs:
           PKG_NAME: ${{ needs.build.outputs.pkg-name }}
           VERSION: ${{ needs.build.outputs.version }}
         run: |
-          REGEX="^$PKG_NAME==\\d+\\.\\d+\\.\\d+\$"
-          echo $REGEX
-          PREV_TAG=$(git tag --sort=-creatordate | grep -P $REGEX || true | head -1)
+          PREV_TAG="$PKG_NAME==${VERSION%.*}.$(( ${VERSION##*.} - 1 ))"; [[ "${VERSION##*.}" -eq 0 ]] && PREV_TAG=""
+
+          # backup case if releasing e.g. 0.3.0, looks up last release
+          # note if last release (chronologically) was e.g. 0.1.47 it will get 
+          # that instead of the last 0.2 release
+          if [ -z "$PREV_TAG" ]; then
+            REGEX="^$PKG_NAME==\\d+\\.\\d+\\.\\d+\$"
+            echo $REGEX
+            PREV_TAG=$(git tag --sort=-creatordate | (grep -P $REGEX || true) | head -1)
+          fi
+
+          # if PREV_TAG is empty, let it be empty
+          if [ -z "$PREV_TAG" ]; then
+            echo "No previous tag found - first release"
+          else
+            # confirm prev-tag actually exists in git repo with git tag
+            GIT_TAG_RESULT=$(git tag -l "$PREV_TAG")
+            if [ -z "$GIT_TAG_RESULT" ]; then
+              echo "Previous tag $PREV_TAG not found in git repo"
+              exit 1
+            fi
+          fi
+
+
           TAG="${PKG_NAME}==${VERSION}"
           if [ "$TAG" == "$PREV_TAG" ]; then
             echo "No new version to release"
@@ -231,7 +252,7 @@ jobs:
         working-directory: ${{ inputs.working-directory }}
         id: min-version
         run: |
-          poetry run pip install packaging
+          poetry run pip install packaging requests
           python_version="$(poetry run python --version | awk '{print $2}')"
           min_versions="$(poetry run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml release $python_version)"
           echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"
@@ -246,12 +267,6 @@ jobs:
           make tests
         working-directory: ${{ inputs.working-directory }}
 
-      - name: 'Authenticate to Google Cloud'
-        id: 'auth'
-        uses: google-github-actions/auth@v2
-        with:
-          credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
-
       - name: Import integration test dependencies
         run: poetry install --with test,test_integration
         working-directory: ${{ inputs.working-directory }}
@@ -289,11 +304,11 @@ jobs:
           ES_URL: ${{ secrets.ES_URL }}
           ES_CLOUD_ID: ${{ secrets.ES_CLOUD_ID }}
           ES_API_KEY: ${{ secrets.ES_API_KEY }}
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} # for airbyte
           MONGODB_ATLAS_URI: ${{ secrets.MONGODB_ATLAS_URI }}
           VOYAGE_API_KEY: ${{ secrets.VOYAGE_API_KEY }}
           UPSTAGE_API_KEY: ${{ secrets.UPSTAGE_API_KEY }}
           FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
+          XAI_API_KEY: ${{ secrets.XAI_API_KEY }}
         run: make integration_tests
         working-directory: ${{ inputs.working-directory }}
 

.github/workflows/_test.yml

@@ -47,7 +47,7 @@ jobs:
         id: min-version
         shell: bash
         run: |
-          poetry run pip install packaging tomli
+          poetry run pip install packaging tomli requests
           python_version="$(poetry run python --version | awk '{print $2}')"
           min_versions="$(poetry run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml pull_request $python_version)"
           echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"

.github/workflows/api_doc_build.yml

@@ -72,9 +72,7 @@ jobs:
       - name: Install dependencies
         working-directory: langchain
         run: |
-          
-          # skip airbyte due to pandas dependency issue
-          python -m uv pip install $(ls ./libs/partners | grep -vE "airbyte" | xargs -I {} echo "./libs/partners/{}")
+          python -m uv pip install $(ls ./libs/partners | xargs -I {} echo "./libs/partners/{}")
           python -m uv pip install libs/core libs/langchain libs/text-splitters libs/community libs/experimental
           python -m uv pip install -r docs/api_reference/requirements.txt
 

.github/workflows/check_diffs.yml

@@ -31,7 +31,7 @@ jobs:
         uses: Ana06/get-changed-files@v2.2.0
       - id: set-matrix
         run: |
-          python -m pip install packaging
+          python -m pip install packaging requests
           python .github/scripts/check_diff.py ${{ steps.files.outputs.all }} >> $GITHUB_OUTPUT
     outputs:
       lint: ${{ steps.set-matrix.outputs.lint }}

MIGRATE.md

@@ -1,11 +1,11 @@
 # Migrating
 
-Please see the following guides for migratin LangChain code:
+Please see the following guides for migrating LangChain code:
 
 * Migrate to [LangChain v0.3](https://python.langchain.com/docs/versions/v0_3/)
 * Migrate to [LangChain v0.2](https://python.langchain.com/docs/versions/v0_2/)
 * Migrating from [LangChain 0.0.x Chains](https://python.langchain.com/docs/versions/migrating_chains/)
-* Upgrate to [LangGraph Memory](https://python.langchain.com/docs/versions/migrating_memory/)
+* Upgrade to [LangGraph Memory](https://python.langchain.com/docs/versions/migrating_memory/)
 
-The [LangChain CLI](https://python.langchain.com/docs/versions/v0_3/#migrate-using-langchain-cli) can help automatically upgrade your code to use non deprecated imports. 
+The [LangChain CLI](https://python.langchain.com/docs/versions/v0_3/#migrate-using-langchain-cli) can help you automatically upgrade your code to use non-deprecated imports. 
 This will be especially helpful if you're still on either version 0.0.x or 0.1.x of LangChain.

Makefile

@@ -66,12 +66,12 @@ spell_fix:
 
 ## lint: Run linting on the project.
 lint lint_package lint_tests:
-	poetry run ruff check docs templates cookbook
-	poetry run ruff format docs templates cookbook --diff
-	poetry run ruff check --select I docs templates cookbook
-	git grep 'from langchain import' docs/docs templates cookbook | grep -vE 'from langchain import (hub)' && exit 1 || exit 0
+	poetry run ruff check docs cookbook
+	poetry run ruff format docs cookbook cookbook --diff
+	poetry run ruff check --select I docs cookbook
+	git grep 'from langchain import' docs/docs cookbook | grep -vE 'from langchain import (hub)' && exit 1 || exit 0
 
 ## format: Format the project files.
 format format_diff:
-	poetry run ruff format docs templates cookbook
-	poetry run ruff check --select I --fix docs templates cookbook
+	poetry run ruff format docs cookbook
+	poetry run ruff check --select I --fix docs cookbook

README.md

@@ -59,7 +59,8 @@ For these applications, LangChain simplifies the entire application lifecycle:
 
 - **[LangGraph Cloud](https://langchain-ai.github.io/langgraph/cloud/)**: Turn your LangGraph applications into production-ready APIs and Assistants.
 
-![Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers.](docs/static/svg/langchain_stack_062024.svg "LangChain Architecture Overview")
+![Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers.](docs/static/svg/langchain_stack_112024.svg#gh-light-mode-only "LangChain Architecture Overview")
+![Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers.](docs/static/svg/langchain_stack_112024_dark.svg#gh-dark-mode-only "LangChain Architecture Overview")
 
 ## 🧱 What can you build with LangChain?
 

cookbook/README.md

@@ -62,4 +62,5 @@ Notebook | Description
 [wikibase_agent.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/wikibase_agent.ipynb) | Create a simple wikibase agent that utilizes sparql generation, with testing done on http://wikidata.org.
 [oracleai_demo.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/oracleai_demo.ipynb) | This guide outlines how to utilize Oracle AI Vector Search alongside Langchain for an end-to-end RAG pipeline, providing step-by-step examples. The process includes loading documents from various sources using OracleDocLoader, summarizing them either within or outside the database with OracleSummary, and generating embeddings similarly through OracleEmbeddings. It also covers chunking documents according to specific requirements using Advanced Oracle Capabilities from OracleTextSplitter, and finally, storing and indexing these documents in a Vector Store for querying with OracleVS.
 [rag-locally-on-intel-cpu.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/rag-locally-on-intel-cpu.ipynb) | Perform Retrieval-Augmented-Generation (RAG) on locally downloaded open-source models using langchain and open source tools and execute it on Intel Xeon CPU. We showed an example of how to apply RAG on Llama 2 model and enable it to answer the queries related to Intel Q1 2024 earnings release.
-[visual_RAG_vdms.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/visual_RAG_vdms.ipynb) | Performs Visual Retrieval-Augmented-Generation (RAG) using videos and scene descriptions generated by open source models.
+[visual_RAG_vdms.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/visual_RAG_vdms.ipynb) | Performs Visual Retrieval-Augmented-Generation (RAG) using videos and scene descriptions generated by open source models.
+[contextual_rag.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/contextual_rag.ipynb) | Performs contextual retrieval-augmented generation (RAG) prepending chunk-specific explanatory context to each chunk before embedding.

docs/api_reference/create_api_rst.py

@@ -530,7 +530,6 @@ def _out_file_path(package_name: str) -> Path:
 
 def _build_index(dirs: List[str]) -> None:
     custom_names = {
-        "airbyte": "Airbyte",
         "aws": "AWS",
         "ai21": "AI21",
         "ibm": "IBM",

docs/cassettes/llm_chain_1b2481f0.msgpack.zlib

@@ -1 +1 @@
-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

docs/cassettes/llm_chain_3e45595a.msgpack.zlib

@@ -1 +1 @@
-eNptVQ1sE2UY3iCKI/GHIEQiQlkkKtnd7vp37caQrRvb2Fi3dowV0Hq9+9rednffcd93WzsCxkFUQiRcECIhUXFda+bcRkD+BBOVP6NkigacGogGIYZEwWggRsDvuk62jEv6833v+z7v3/O+153pADqSoJrfL6kY6LyAyQGZ3RkdrDMAwpvTCsBxKKYa/cHmHkOXRhbFMdZQSXExr0k01IDKS7QAleIOtliI87iY/NdkkIVJRaCYHDm8vlABCPExgApLbGvWFwqQuFIxORQ267yKZB4DG44DWxTKMuyU1JiNBANtEuZliVdLCotshTqUgWWAkggDpXBDkW0CTlwar2QgoBdueIHcKFAEsnUV0zDltHRUcmLJL8I64BVyiPIyAuSCwGqkANjQLQyG5jZk4oAXSXku5j2WikOEzYGJKQ/yggAILlAFKJKozQ9jXZJWZBNB1Eqpj8SngmxBzb52ADSKpNMB0qNW5hCvabIk8Ja8uA1BtT+XD4WTGpgs7rOyokgVVWwe8JMgymuLG5OkN6qNpZ0emhlKUAjzkiqTYlMyT+JJa1n5x+MFGi+0ExAq13czPWo8MF4HIrN3BS/4gxMgeV2Im728rrid+8ff64aKJQWYGV/jZHc54T13DpplaW7fBGCUVAWzN9uIQxOMAdaTlAAJhrmXSQsQtkvAHPkzHBai4YhSFgonnLTRKiuOyqAgoeaGEKc52GbaW6G1hKpXKjHYWVPfmKANkaFYzs45XXbO46JYmqFZmqXC9bImLmsL2lscclelxwgEwlWBptpwC4SrnYaC2xqqEK4DDdEQG6pZReuJSNTdVGWs5tbFkzWhaj4mLKe5ZEtHlb9iXaTcHggp7TVaeamNRGd0SGJZm1zvYe0rQ+vqIx2uGsbXRDu5MGpzQKUh4Xa0NdHYXYk5H/S6a8eFx3o9FJOL0M04PYz1DIxxQwZqDMfNHtbjfF8HSCNTBjalScmwgbpThIfgqzOZ3Li956+7R+FZqUrCSfP4Ml0qstk5WxBoNjtjd9pYV4nLW+LkbNUrmvt9OTfN96Xgvuy4RgkNq8YonxHihtoOxD7ffcl+3CI76aQVPplOCiQ0iACVi8rsb6UCo3uGqq3cPzpZFNRjvCp1Zd2ax7Os7+xKdIqCIYrxjk6F8XY5HVIEGEL0QM5E06HlhgREKcjscbDugZxkjHd9JFdCAoZi2CNk9CWBjJmVjAZ1TCEgkM2Gk+ZIkcInrBkrc7Auh5sUvpSsIkE2RBA0IpVQIcxEpTZNBzLkxaMJiuwLIEuKRBqT/c5tTWSmXMT48GQFDNsB2a+92bZ+Ml6uAwvdSuEeiNPr9R67v9IYEOf1cvajE3UQGB8Ja1fQ4ckKOYCUnVVQf2JMn5JEc+RpcgjbgV2Ielgv7+IjEYHxsC7ew7HAzXgZ4Ha77YO+ZZSPF+KACmbZZ2YqQw3lK2p9B1up8TSi/NroOyWjQqRK0Wg6CHTSFrNPkKEhklWpgzTBCpSHzAMewStEHEAUIizriQocVUGW0Bja/6RLWXs2+3J5JW01U42dzK+Yv/WhvOwzlXzu3sXbWfgZ8/jmm/9Ov3a2ceFzC599si3zSK/vteUrZ+2+vPCwZ+PA7e1LX7/7oreg4KnWxT9dLX3nj7kF+X3da5ce2bH2YMvwheHQG1d+5ZacWx+5uefXH46d+u3HK8ifefStB6YpLw9d/uDa3tT5NrEqfbrX98UTgR1FZ2f7pYOrO97tnW4MuXZd3Zo8Vj9v2ultzVvm6TdmFSw4caTUxwV/nqHPGB5YvvXilw8umF9ckL8NNy7tGlxc9zmz56XaV7/5y9iZWnN5aElizqLdm85v2jjn0rnvWqvXPH+9aXBn08ZVnjffrj/zd/3skq4tm2/9fgffWjWzv+e8/umB6plTdqycP+3brpn1006dCFw6c6PM37Sgrvf22aKvLwTTu6f8sk+4WXv9meHvZ39kf7jkWvOhAHdy4T9TrUJNzbtTtWzX3Cl5ef8BjH8o1g==
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

docs/cassettes/llm_chain_3e82f933.msgpack.zlib

@@ -1 +0,0 @@
-eNptVWtsFFUULpSgEh8VRGOMYboaf5jOdGZfs1Mkpt2Wtva9Wyqr0XX2zt3daWfmTufeaXdbqxEJCVHUkYjvH6XLLja18mgEQYxRVDQIGo2mKBpf8YGvoMSoIXhnu5U2ZZJ93HvO+c7rO2c2FAaghVVkLJpQDQItGRB6wM6GggX7bYjJxrwOSRopuc6OaPeYbanTN6cJMXFNdbVsqhwyoSGrHEB69YBQDdIyqab/TQ0WYXIJpGSn3xr26BBjOQWxp4a5c9gDEHVlEHrwdFuygTWZQIakIZNEmoYGVSPFJC2kMw1GSlNxmqGRIaaZyJoqG54qxmMhDbrGOIsJ1D0jVcw8zLRaOVfLxtDyjNxFb3SkQM29SpmE9bs6Bj0J9BcTC8o6PSRlDUN6QXFNWg1iWy4Gz4kjhTSUFVqrL8oqcmmEiTM5P/+XZAAgxYUGQApNwXkxNaSaVYwCk25+4zRAAxar64z3QWiyNJ0BmJ+xcnbJpqmpQHbl1b0YGROlhFiSNeFC8bibFUtLahBnqoMGUdtc3ZmljTIYgfOHOH5XhsVEVg2NVp7VZBpP3izKD84VmDLooyBsiQROfsZ4cq4Ows6ONhl0ROdByhZIOztkSw/69869t2yDqDp0CuHOhe5KwvPufJwgcOLuecA4awBnR7ER++YZQ2JlWYAohjPK5wFCfSp0pk/H4yAZT+hrYvGMn7PXa7qvPgpU3N0eE02f0M1JdWZPrHGdnkKDTa2dGc5WeFYQvaI/4BVDAVbgeE7gBDbeqpnK2t6ot8enDdWH7Egk3hDpao73IHSH39ZJb3sDJi2wPRkTYk23c1YmkQx2Ndh3iP3pbFOsUU6B2zgx2zPQ0FHXn6j1RmJ6X5NZu5qh0dkDqrKmV2sNCd51sf7WxECgiQ93cX4xjnt9SG/PBH29XRwJ1hMxjKRg85zwBCnE8qUIg7w/xLvP5Cw3NGikSNoZEyRxpwWxSUcOPpinJSM23pCjPIRHjxRKs7e9o+U8hVfm6iknnUNrLbWK8YpMFJqMl/f6GSFQE5Bq/EGmsa17Ilxy031BCu4uzm6S0rBhlvIFkLaNPqiMhy9I9kMu2Wkn3fDpdLIwYyIM2VJUzsR6NjKzdNjm+r0zk8UiKyUb6lDRrXOoyPrBocygAmxFSQ8M6rw05PepCWiD5FTJxLSQ64YGxOrYGQt6xcmSZJZ34zRXSgKe5YVX6OirgI6Zm4yJLMJiCOiaI1lnukqXM+6MrfEJAV+QFn41XUVAsxUYtRP1SKfMxKsZ04IakpUDGZbuC6ipukobU/wurVDs5ALUeP9CBYL6IF22O4ptfW2u3IIuupvCeRC/JEmvXlhpFkiUpKB0YL4OhnMjEbw63r9QoQSQ8/p0PJGZ1WdVxZm+kR7iCb8EkkmJktIrepWkKCdlPiRBRQ4lFN4bkF4Kr2XDMkhDNlpkn1Ooj7XXtjWHX17PzqUR22HOvGAKBsKGmkzmo9CibXHGgYZsha5KC+YpVqQ25kyFgAQSPhiSAAiGkkBk6+gSmkX7n3Q5d88W3zQP5N1mGqm3FoVXPXRxWfEpp59z58hj77e/yVds/C27bO/3V595dOl3myqWL2dClUvqnFPa8ug7fT9vWTL+z69H1GemLuKko98/ffQYd+VisujpsnUtPVt8Hz372dThr0dPPP7VFPvTwcKnT54+u/tjdPzLv/jNl5+4d/TrsVORrm8u3XPT8OvvjSkPv/AHfTtMXv3jmQPll61Mb3/RuuWuttSpv/cMfpxbufTI4UbPxoqDv153cHrx/cyKve92qfySWKXy5g2Vr2/dvOxIBblHvfamG7qVa38ZndxG+t+7ZZv+2O6t+pYfz5z93Rd+4o+pS9as+jNy5/U/fT52qQLMe6wPPhzxHE4Ndg9/suK5wtv9x6Yariu/5mwbf0x8Ax5/av0zK46fvrXjbqZFf+NdztxZ0ANLj2565KRTcV852PrkiZ4fnv/0ZOvJq/799gq3UuVly2L7Oq5fXFb2H5UFMyI=

docs/cassettes/llm_chain_6bacb837.msgpack.zlib

@@ -1 +0,0 @@
-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

docs/cassettes/output_parser_string_28eeace3-3896-497f-93ad-544cbfb7f15c.msgpack.zlib

@@ -0,0 +1 @@
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

docs/cassettes/output_parser_string_8ac74999-0740-4178-8efd-32a855592f71.msgpack.zlib

@@ -0,0 +1 @@
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

docs/cassettes/output_parser_string_8c87553e-4f85-46c4-8f1e-666f6a261a50.msgpack.zlib

@@ -0,0 +1 @@
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

docs/cassettes/output_parser_string_9cbb8848-9101-465e-b230-0f7af6fb4105.msgpack.zlib

@@ -0,0 +1 @@
+eNqFVGtsFFUU3spDSNDwsuoP43SpbQid3ZlOKWyXCHVpa2laSrvKy7Lenbm7M3T23unM3UK7VEMp/IAYO6gYkSDIdpesLXSVhBhAQ7CJCDEGiKYlxQSEVBvwUWIgUfHOdrelAXH/7Nx7vnPOd853zm2PN0PdUDDK6lYQgToQCT0YZntch01haJCOWAgSGUvR2pX13kNhXel/QSZEM0qcTqApDoCIrGNNER0iDjmbeWcIGgYIQiPqx1LLQJY3Yg+BzT6CGyEy7CUMzxUWFTD2DIrerI/YdaxC+mUPG1C3U6uIKRVErKvVMiD5BkNkyGyCgP7pjIKYeoCYch0gUTFEXMB4Spfa2xqssFiCquUmqiAsQVZgF7IyUBrDrAoILcYKTjBW03kRCKXyBiHxpaNbCAkaoq5oViMsawUkE/IHdBxiAKNiEVgQh+WiIC1MfIYowxCgPhG7RpsCdaKkSozYM+DUgbRoqbQG0RUUtLe10QBWtxUdShaxcbRVUwaN/RuhSCi6oS0uQyBR2a7YZkZlbBAz+YAUR4EoQo2wEIlYolnMnmCrohUwEgxYrUjQFiOY0tpMNEKosUBVmmFs1MvsBZqmKqMknBsNjLrTkrAWmwfNCUs5lgqKiHm8NMPDWdtCJwcxnENY5OB7N7MGAQpSqfRUDkoppqXsJ+43aEBspHHY9FSasVHnI/djsGF2VQNxZf2EkEAXZbML6KHios/uv9fDiCghaMY9tQ+mSxvH0wkOnncsSk4IbLQg0ewKANWAybEmj7kkCrlCgeWKWY4/PiE0JHoLK2KawTzIHck0UIUoSGTzkFDEHdahodFlg9ti1I2EjfYoFQue/zqeXo+PV1aNSz0rupwKZ55aDaUChheYGtzM0NRFDF9cUiSU8AuZimpvtyedxvtQnZJeujRGgGpVlpmLuCiHUSOUEp6HTkS/fbxineZXlZBC2PTbQHW0jma0iOO4/rxHInW6GQqyMkYFl8v1P3FpZyAxj1n1sTzP8oI3XaWwrp95mOfoA5PmE7P4UEa5j0CO88mgmUei/4PPwnWJNGlWkcyT9NvH8aVevM6vlVVt3FwceKW+pnCVJq0Q6g41K8BM8A6eCWIcVOFRTznrAfTJYOtT6pvx5WtrSqsrPd1r2Drsx7QNXkDbhTCCsXqo04EzE6KKwxJdYR3GqHtd6Vrz2GJYyAmLBaEY+BcL/mIX+xLdjMwcjOkctfY/9ShvjY0+PH1ZG57fNc2W+k16bdWqqjPLZvyzoGLDls/fCg/W/loN24c6klsPv3x2oPvUzdbjg9f3Gbe/rPrk6m/zc+9+scW3e97QY3MvHTw/9azq+iD/h5+vX8xhv41/dKLvalPrvemz7/R2ZZflvF7JnHZfzOYmP/cMu61j4ClpWSnisi9VRa5t2N46J3LmtPbujB2ezk73OenZS8O/b8q7WHHuVnv7CUFcXhZY8KRj5+41Wpn97SvvwGT+TztPrnE5b8h9PRUfDne656Pvht4beVX0LZm5a29H/p97r1Rq2wuONbh88xqD7jfcPw5/6t8aWXL7oPnmnn3C2hk39w82DSwJbJPqdlyfFh/uG7nw/fD7W27kud1Tp2cP71k9O7g0e31isHxqePK1P2qy5/61qG1K9UheTu/lwH6OHJhz98gs+emzNyZ/Uy7mfnXr8V/u9HQmL3c+ceACKThd9mJPQ271yBSb7d69SbYVd/6Wr2bZbP8COXvwZg==

docs/cassettes/sql_csv_27c84b27-9367-4c58-8a88-ade1fbf6683c.msgpack.zlib

@@ -1 +1 @@
-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

docs/cassettes/sql_csv_2e56a891-4c3f-4e5a-a5ee-3973112ffeb9.msgpack.zlib

@@ -1 +1 @@
-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

docs/cassettes/sql_csv_35ea904e-795f-411b-bef8-6484dbb6e35c.msgpack.zlib

@@ -1 +1 @@
-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

docs/cassettes/sql_csv_476128f2-aa61-47f5-a371-dcff7b391d19.msgpack.zlib

@@ -1 +1 @@
-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

docs/cassettes/sql_csv_77a70e1b-d3ee-4fa6-a4a0-d2e5005e6c8a.msgpack.zlib

@@ -1 +1 @@
-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

docs/cassettes/sql_csv_9e87a820-e4ce-417e-b580-043fb2d5c8f2.msgpack.zlib

@@ -1 +1 @@
-eNqlV21wFdUZDiKWqf6g7RTtVOT0Dh2+spvd+52ktOaDhISESz5ICGKTc3fPzZ5kv7Jn9yaXJHakdlpRyqwOY4cWWyAklUlBBRWFoJ0WWoodWywqqaDTH8WvmYrMiLW19N2995IboaL1/Lh3z573vOc57/uc5z27cSxNLEYNfcY41W1iYcmGDnM3jlmkzyHMvmdUI7ZiyCOrEy2tuxyLnl6i2LbJykpKsEl5wyQ6prxkaCVpsURSsF0Cz6ZKfDcjSUPOTM5+azCgEcZwN2GBMnTHYEAyYC3dhk6gw3CQgtMEYUkCG2QbCCMT6zJmSMY2TllYI6hLTnXxKN9WEIsgCrYKQYZjm46NjJRnwysEy4sW87bRqWGrVzb69UWLu8rW6/mZU09dXV1TnaH8T4tjpWmayH5ntaRiQDSEVnkQPlsbQi1kIO+1optkvdOkSvVuVtJiGg4jDFUkDWzlFsMWRISVVClUleGxcAzVwCAaWq8PcRxX5v3kW0GnbKiM++zt8qShKxxe0T7dWJmHEyEhizzbCjoheGy0eJTohz2uwJYFeay0sKPL14inhlWST1UwWOj9Y038hDEfSIwPRjxPPs5p1gUd0cfJeFRvKLqHUFZJBi2qUQ1IjkTgDe3uZqhVwRliLUZVjuZlFialiI/UdxSKfw6cMZEPxkOhHM7g/8Dpx5MyANqAqY7hbNDeXqoT/Vr8LMQZjF4rZp8cz1IvoFmcoWvGE0uesABQbCtoUQNVM6gRZ9BqQtTFqMaxLaKq5Oo4Q5HPEc9IiBfR5byHr8HPdqqqFGsAU7cyqAIg6Z+en5+I85rxjPNCjp9XFaupp1qQKh3kErTEQr5ag+gWo36L2sQXx9UZkG4dSYZMfGHVWT9YUntKSpuJ7Vg6Sqxq6PBnpLFK5WnzQIqRbtgK0BsRlZGpudWGvtBGIJEOyGPmKjquZ5BKkxa2KOQbXMDatoJ1lHSoanNUz69j6DDurZPVfT5QjAKWoRKvPrAMs4kWGC5G08pGO1SahdkKIBkWUAZ7e0dJYvcTLybdWeApEM5Cb16kAsN3whsN9qZ6r7pNmwvxEQ7ikDQ8Wx3eivDPgIlYg04Kw7bhBeAwoUKCoedL4GPeO8NQOyXFoJL3bjBgZ0x/oZSj+5XUc3j52TPQoZZ4Bqa/9U6LmGonZnZgeDjnLVci/29HYCcTJlnUzJkGKvJxZgocLR6tYR47qJ8jMkAkB9hi5jOuaRA3OKZ1uldWmWI4qgxhBZZlqTHdEM6JAuF2mMeOnE9DLUbMgFsD1by0Z+szjOBk0iJpim0orxwcl16CmOMVchvJBlgCyZBqGL3TDJMkBYKbWwAsgTTANCtHZZ8pJvauCHB3YX5cTAvuJJZNSbYLx8LK+E8fi4pPbqZT0yS2FwnL8WOcjztkH5bMpsW7ClGLyF5mcg7vLDA1kj1E8jI4fOfwmHcDAShni+aMKAaz3b3Tb0n7vOMBjIMaYsiwgPur7g3ULEYySQGFyR6guE78JLt7egkxOQh6moxmZ7mPYtNUqeRzvaSHGfp47khwHpYrh/d4fOfgMOi2eyABICrqSnJcEPlIkBceHeCYDXVDhSPLqRjwjGYTfKhwwMRSLzjhcldFdzQ7eW+hjcHc3Y1YSrRMc4ktSXF3Y0uLhvcXvodge/Rwx6pWX7lcbnBqORBugQ8/Ns0xy+iSu9s/mk9Nm0xsK8NJBvhwdwijEhCKEvf0e52dUqozqS3r4/sigoNXOj1rjY54ooJvaGteEw3H19WapWk70daeXhcKV9O2BrmXE2PB0mhQiMZCnMgLvMiL3IDSlrI6K/poe1roXL5OSsj1lWwgqEb5FX316+zKsFAXCTVWVTcm61g9WdPRUy/3rSTrkqFqIjcFG2mTUpkyI6lQ28qoXNvhVDu1LevEpnIE6Jw0lZetijXwTdqKGiWoKFUUr6kN19Utb0ltiHS0x2tWVcbWhOpKIw1taaeuqQBeUAxzQg5hVAjHBa/tzXMDSle3rbgjwWA8+EuLMBNu5uT7oxAz22EbR7yD8Pzvx3I39J2JlVMcnjtSDaR0J1od0D+4dCUkGwWFYBiJ8TJRLBNLUW1j63hVbp3Wq3LwsVYLDmsKeLg8z/kxSXH0XiLvqboq2yeyJYTz8INwc2TANBjhcqjc8bVcc/bbhKur3p89WpxhdWOdbvCXdSd82vdvGOiXJUeWlXS/JpRuCIdokjhS6kBuCgiFtwwA4jTm7orExb25kTzx9sBeBU4UOEF8ZoAD5Scq1SgE1P/NfSAxdyQC0T54pYFt9BL4lBoL++kQjhRaWHCrobq39pSbcGlp6eGrG+VdhcAkEg8/M92KkUI0YlBjB680yLnYFdXY+EDenKOye3oBdDrDwKKIHA6SmBBPihiHJSxIYlwIiim5NCnHnvYEUQI3XjZNw7I5BpUDbhoZ93Sxhgc8lVkWEiOhKGy1HHRaUh2ZtDjJasPbBCtHJlRpA8v7qmq4KiwphGvxCeiOVXesqmisq3pyLVfIJC5hZj9Fx3QDZDqVGm0hFmTG3SOphiODXFpkFHw1V3S4B+JyNBkLpiSMcTKULA1xlSBEeW+XeTfiae0YhrsHS0vufiW0LFAWDocC5VCNlsWjkCf/g/Xu0az4H53x6vz7Zhf5baba3LhlUpgzca59LduxtWjWJFmu/3XfgZOb0k+MzV0t/6zuby+dP/hky5e+8Z/BrddXdr38hRPbzl08OzTvumO3j84R58y6uDPc8967Hyz+48PP/u611uWXkpt+ftuFMy/27PveO8c5/KqgXPz6D76zf3Rj/a4/rTw5r7jY2rL5rXfuOrL++d8c/ejxWfX1TZEDr35w/NCbZ37bnq590Iw+Wy7e+MB186rVecKxV3ZM/PRWZ9Pgj9bGv11bb//43OymS/eKj45sm22eG7mwfvCWztsrJnfpJ1/a2jzzua88Um3u5o+dKb3p7EM1fbsfGPjmzef3f/S1h+aff7v76TtOnfph55KlN9y13dYm73m8/r4jFTMPb6mNpe6/++/kROSJkhUL526uP3gh9uX7ZzyVWbPz/cYPzVeee+2L2sTdykz65He33Gbduvn0Gzc+FZ/UxzaOD19IL/nqvU78YS1m3rP0qPTu5GC58pOj49b67WWZTfP/9edFf9i8e/uhN8Ny88r2BXOf7l16w7nj9tnNibeLTp1q/fXaJZsT3/qo4szsI/9oe2Teuczb/Bv/PjD/9eMs0sW9ML50YsHyF0j5+3e9eP3Ns0Zv7rnlpk2D9MNt1e2/+Ms/b9z6+sj1e9O3nVjwYFlt7/g7LwfjN1yaUVR06dLMItZz+NDWmUVF/wULibGL
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

docs/cassettes/sql_csv_c6a9c8ec-1d06-4870-a584-b8d7b6c6ddfe.msgpack.zlib

@@ -1 +1 @@
-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

docs/cassettes/sql_csv_ff6e98ec-52f1-4ffd-9ea8-bacedfa29f28.msgpack.zlib

@@ -1 +1 @@
-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

docs/cassettes/summarize_refine_0701bb7d-fbc6-497e-a577-25d56e6e43c6.msgpack.zlib

@@ -1 +1 @@
-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
+eNrtmAlY1FYewPFou61a0fWotWpkXW2VDMncw0iVQ67KISCIRzGTvJkJzCRjkoEZrPdRED81itbW2lpAUERRQVHEo1rvC22tRRTrFkVF60URW4r7ZoCCq7v9dqv7tf0M3zdJ3vvn//7ne7+PmTmJgONplmmTRzMC4AhSgC/8kpk5HJhkBbwwO9sMBCNLZYWHRUZlWjm6bLBRECy8p4cHYaElrAUwBC0hWbNHIu5BGgnBAz5bTMCpJkvHUvayvMluZsDzhAHwbp7IuMluJAuXYgT44hbD0QJACAQOkTQPEN5qNhOcHWH1iGAEiJ41mdgkmjF4It4WqJVHCA4gHKDc3BE3jjUBhw4rDzi3KRPgiJmlgMkxZLAIqJxFzTRDOyQZOIbDOy9wgDDDFz1h4gEcEIDZAp0WrJxDEybBpuQYAUHBkCzMMrK8IG541Ml8giQB1A0YkqWgWeJ6QzJtcUcooDcRAsiFbjDAGUIxNwEAC0qY6ESQ3fiVuJGAPtAk4Zj3iOdZJq8pEqhgt4DHp3MdnqEwbowgbvfm7QwZBi3xDvIIt8OUMAguUUgl0o02lBcImoHR4VETAY3Ktjjnd7SesBBkAtSENqVbzG78eENrGZYXV4cQZFjkIyoJjjSKqwnOrJQXtB7nrIxAm4GY4xv++HJNky3LySQ4LlFtekSxwyNxvfPm6fyl2aJHlACBs6MkC3WJn2EbmoNlAoxBMIqZuEq6hgO8BRYamJUNPxOs/MwsmBhw7FBOU8VlhL3TnNEKl55ZfjBJ4s5IQnBHMA0SyiYiUkwqR3CNp1TpiauQgJCoPN+mZaKemJNNURzB8HqYlxHNNZBDGq1MAqByfZ+Y/Z2O7ENvHObDkkWBzcLyAG2ySswbg0Y0thoa5FfQWGooyxkIhk52LivudJZBUrItiSKtFGVMTDJjmmS5jNYBK6kvbPrEwrGOZaBBqJkXM+UKfEPTTHMOcqGvGIpjKIYX21BY9cBEm2kYT+dvU7/zYpYCw7BtjwsIbAJgeDFHjjmvXa0lOGCGSXOs3aJGrtFoSp4s1KxKBkU0SnXxo1I8aG0NLjXz2x4XaFKRgfF5tmZplKbEsgHwJU5OkbhOSWBSlRTTADmp0ivgBWSAApRCKZNthzsBTUItjmRaWE5AeUDCzU2wi2XuZsLmaDovGa6QKaGnWoRmSJOVApFWnR/r8IHXIhYOmFiCyvf1R30J0gjQSGf9iTl+saHeIUG+uZHQSF+WTaDB4nNt2sXFkfo4ndmL4EbrZMHhxmgrFWGUJOhHJ9nUASHS+ORJZpM9Tm01J+PKYOWkALvMG8VVMhxXYzKVCsUlmASX4Gi00Wekzm9SYiBPGM2+ClZCRceMkUTS3gafBEWibJSKoqEIFSUP0ihNATZFaJB+kpHyx4LjjbZohYFI5hkJJlOooDM+UWNjQu2GYI2QBL0hBKOXhxaBtUnD+Ho1dQgKOwRt7A9Fc39oEcoZAy/Jo1ujFgmE50IYY7JrkUhHMAG8E2YQCTd4r1CWAWXpMAbWRJryCh3rR/vKSIYVLFYhQRWCjw2KCowCgXa7jPKNeSfYW6mnJL5+uNmY1CoIGpUUxZrioMTkamcVtpj+P1q1dQzauuHRMIvz5BJzGJZnaL0+OxJwsIHEXNLEWim4y3MgG+Y8wjtWLFQDDJPhakpKwJrSaQjUB26dzdp+2R6yHEdEDmGCNZZIigVGmZebp1wuc9MiZsJLrYTt5DwmZ2Q7apIx7G+zqF/aX1ycV7v5EUeZcsy1pHpIj6HjZlRuEy+tKK/oULO47Yj+pZXBFXP/0bXy9fV96i62O9JZE9i2cu++Yycs+k0nX5juti561bHotF4zh5wddmGhR3FRzZQpxh/ZhXH9ftqnX/tpQ5+pN1d+BF5gGzLEtOsnbru+8cqmYacGZvQ4tsHKx509en0X7a+bmCY5+iNyeebRGUOX3ovf9ea67LwPDD8sOzwxYkjdBBeXoQvZE9fQhpgha/Q9qT3pwsJ4a5+24eIE//TQ1MVGj3ilOHfnqn6Z+b6W5cMD2pe9JD233cuvcHjfjtoFSUV7Uy5Irr1Rcetj7XcHE7oenJJSEmRomJdU+Za5PMVz08ndAy+t8q8d41Lfq/etd5eG97/rmtV9qs+nnaovHw4NmfzJoQ6D3M+F3K4nahfEJoySbxcKMFBYlrEy/cvEH050vei6P+RyUWzFvbfPDLw47cBUt/mfI8Zy11OL7ReSXk9bvvB25qbqeQf3DL655NvSxMrJ8/ufvta+uDS694Sy5F1X40e/kdYThv7hw3YuXYIuFrm2c3F5ijB0rk3Bf6Ch8QzSdIVzLGUlHWSkpxnC1MxFkhaJlqcRNpoXYOX8Ak9WCyKwkJ9oHrGwEOs8W2RbURRkDniwmUx2B0/BLQ4ymInlnrhCKEhCnGbaWutCW10toz4mK9ABjqObltHB91/7puUpAB6YjBP9mJY13aGFMAzAOc5ytOHfhOSZQ2GFi+tzLPydYWE26TxkxbK7v/Mz9hmcfo8hsVym+O+QuMevILH6T4TEMqniD4LEmPI3IHEmbn4iE2NAo8TluFSBQa6VqqVStVIpl+mVhB6o5YBSPXsm/u2spZGq1SriKbJWRmvWCkk4j3Ur+SlmqLB11pYd1Ac7L6d3fXNOaU3EPHG1YVzqrsFeSybsbbjvll9QUdotuYvxynHsXlZR2+n0/to9lUjguYm5OwLu3azt8OGg4qK4frvv528dVr9rmmf9os71c5bGXio3pNdsKBYrXpyVtVP7pTQDObbhvR1X3ovJL9qRuvHdzw5vfjt8y52lZ0Jj1iVvWXvdvD+pIPn2WJ1ucl2si0tJiOHEtW59v+l7/W6fTcsXXxVvevi6uCcv6TIw4nTq7L9FS7JqFpSGnLrlgy0f7tfe80V0Dh6Qsma4dlFF3Zi91as6+ST4m3B/r7Cqn45vob9gRrr15DNx2dTiLPmuzqeK6CsetpyVob5/HTXgFpfh9/bGVK/uLruzzfP7vbLZdWenrxZN8/6gE/ugbAHKblz0nteSyqDlL1xkjoSdf33OgMKgmHIq4lCbMxnjoz38V//cfdR4a4P2mKGiquLcDw/J3a4ROiQqJGVNYf0YW6+05dOu7j4g0X7StkAYOXvrtcJqfO6akw8zO4RcmDf2zpns7/LU3ac10Vdq7CsV6NOmr2O/b/pyR5KMtKkRmv4Von47mREM/GtUaIedmvQcy55j2XMs+39gmRJ7ulim+TP9p1L+h8Ey7BlgGaHWEypSLtVr5BgkVDWgcFKK4wqgwgmNTIb9IbBMQZA63VPEsrzWWPb5vHIHlg3p61metlJRvWjcqqKuY4M7oKtfi03eumVpzewB7ArJg/tu2tSCGz2ScduV48YrQSd7uUQuvjk9VQwgPpbUflrz/vs/X7pTXZUUllFf1zBxpNePlrramqp39t3NWvV9lxEla75v3ysHH7y5Azr0bsrhLfHfr4sfV6Eq/xAbMGpQ2be6UZFE+uj92ee/GlHW7UxtXt+glzuaXrooc5le9WAFNzZ1d9mrR+pnvtZxRudDiWf7u1wJGjT7jmtUynn/ZflZSO9TJ07dP0F33OPlM9Tz79u+Drj9pnesa9bhqtJrL2tr3l1ZdXraq+eDr267vMzjapct2XFJRQdtN3L2RI7W0lMOhJ09/9GLVWs7GBrm3T+Si23ta0dWSOcGLjh+4612dfgtQ/KoDzVhB/YrT4cVHr79WeyNb5KHDImdcChQrO5+8esHvZn1Xxxa+qrqJzAzrcvl3PEes8IiTnUSLwhT+1xBb60u2rzv4Tf5s12vuh352p4eXOJessA+kq2NI8/2OTkjVj03Jfvm0j6l2vxlPb/csfWG7a11IRdi3LVgWptGQCuue7h2GAS0fwIz6Q8x

docs/docs/concepts/architecture.mdx

@@ -8,8 +8,8 @@ LangChain is a framework that consists of a number of packages.
 <ThemedImage
     alt="Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers."
     sources={{
-        light: useBaseUrl('/svg/langchain_stack_062024.svg'),
-        dark: useBaseUrl('/svg/langchain_stack_062024_dark.svg'),
+        light: useBaseUrl('/svg/langchain_stack_112024.svg'),
+        dark: useBaseUrl('/svg/langchain_stack_112024_dark.svg'),
     }}
     title="LangChain Framework Overview"
     style={{ width: "100%" }}

docs/docs/concepts/chat_history.mdx

@@ -17,7 +17,7 @@ Most conversations start with a **system message** that sets the context for the
 
 The **assistant** may respond directly to the user or if configured with tools request that a [tool](/docs/concepts/tool_calling) be invoked to perform a specific task.
 
-So a full conversation often involves a combination of two patterns of alternating messages:
+A full conversation often involves a combination of two patterns of alternating messages:
 
 1. The **user** and the **assistant** representing a back-and-forth conversation.
 2. The **assistant** and **tool messages** representing an ["agentic" workflow](/docs/concepts/agents) where the assistant is invoking tools to perform specific tasks.

docs/docs/concepts/chat_models.mdx

@@ -2,13 +2,13 @@
 
 ## Overview
 
-Large Language Models (LLMs) are advanced machine learning models that excel in a wide range of language-related tasks such as text generation, translation, summarization, question answering, and more, without needing task-specific tuning for every scenario.
+Large Language Models (LLMs) are advanced machine learning models that excel in a wide range of language-related tasks such as text generation, translation, summarization, question answering, and more, without needing task-specific fine tuning for every scenario.
 
 Modern LLMs are typically accessed through a chat model interface that takes a list of [messages](/docs/concepts/messages) as input and returns a [message](/docs/concepts/messages) as output.
 
 The newest generation of chat models offer additional capabilities:
 
-* [Tool calling](/docs/concepts/tool_calling): Many popular chat models offer a native [tool calling](/docs/concepts/tool_calling) API. This API allows developers to build rich applications that enable AI to interact with external services, APIs, and databases. Tool calling can also be used to extract structured information from unstructured data and perform various other tasks.
+* [Tool calling](/docs/concepts/tool_calling): Many popular chat models offer a native [tool calling](/docs/concepts/tool_calling) API. This API allows developers to build rich applications that enable LLMs to interact with external services, APIs, and databases. Tool calling can also be used to extract structured information from unstructured data and perform various other tasks.
 * [Structured output](/docs/concepts/structured_outputs): A technique to make a chat model respond in a structured format, such as JSON that matches a given schema.
 * [Multimodality](/docs/concepts/multimodality): The ability to work with data other than text; for example, images, audio, and video.
 
@@ -19,7 +19,7 @@ LangChain provides a consistent interface for working with chat models from diff
 * Integrations with many chat model providers (e.g., Anthropic, OpenAI, Ollama, Microsoft Azure, Google Vertex, Amazon Bedrock, Hugging Face, Cohere, Groq). Please see [chat model integrations](/docs/integrations/chat/) for an up-to-date list of supported models.
 * Use either LangChain's [messages](/docs/concepts/messages) format or OpenAI format.
 * Standard [tool calling API](/docs/concepts/tool_calling): standard interface for binding tools to models, accessing tool call requests made by models, and sending tool results back to the model.
-* Standard API for structuring outputs (/docs/concepts/structured_outputs) via the `with_structured_output` method.
+* Standard API for [structuring outputs](/docs/concepts/structured_outputs/#structured-output-method) via the `with_structured_output` method.
 * Provides support for [async programming](/docs/concepts/async), [efficient batching](/docs/concepts/runnables/#optimized-parallel-execution-batch), [a rich streaming API](/docs/concepts/streaming).
 * Integration with [LangSmith](https://docs.smith.langchain.com) for monitoring and debugging production-grade applications based on LLMs.
 * Additional features like standardized [token usage](/docs/concepts/messages/#aimessage), [rate limiting](#rate-limiting), [caching](#caching) and more.
@@ -44,7 +44,7 @@ Models that do **not** include the prefix "Chat" in their name or include "LLM"
 
 ## Interface
 
-LangChain chat models implement the [BaseChatModel](https://python.langchain.com/api_reference/core/language_models/langchain_core.language_models.chat_models.BaseChatModel.html) interface. Because [BaseChatModel] also implements the [Runnable Interface](/docs/concepts/runnables), chat models support a [standard streaming interface](/docs/concepts/streaming), [async programming](/docs/concepts/async), optimized [batching](/docs/concepts/runnables/#optimized-parallel-execution-batch), and more. Please see the [Runnable Interface](/docs/concepts/runnables) for more details.
+LangChain chat models implement the [BaseChatModel](https://python.langchain.com/api_reference/core/language_models/langchain_core.language_models.chat_models.BaseChatModel.html) interface. Because `BaseChatModel` also implements the [Runnable Interface](/docs/concepts/runnables), chat models support a [standard streaming interface](/docs/concepts/streaming), [async programming](/docs/concepts/async), optimized [batching](/docs/concepts/runnables/#optimized-parallel-execution-batch), and more. Please see the [Runnable Interface](/docs/concepts/runnables) for more details.
 
 Many of the key methods of chat models operate on [messages](/docs/concepts/messages) as input and return messages as output.
 
@@ -85,7 +85,7 @@ Many chat models have standardized parameters that can be used to configure the
 | Parameter      | Description                                                                                                                                                                                                                                                                                                    |
 |----------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
 | `model`        | The name or identifier of the specific AI model you want to use (e.g., `"gpt-3.5-turbo"` or `"gpt-4"`).                                                                                                                                                                                                        |
-| `temperature`  | Controls the randomness of the model's output. A higher value (e.g., 1.0) makes responses more creative, while a lower value (e.g., 0.1) makes them more deterministic and focused.                                                                                                                            |
+| `temperature`  | Controls the randomness of the model's output. A higher value (e.g., 1.0) makes responses more creative, while a lower value (e.g., 0.0) makes them more deterministic and focused.                                                                                                                            |
 | `timeout`      | The maximum time (in seconds) to wait for a response from the model before canceling the request. Ensures the request doesn’t hang indefinitely.                                                                                                                                                               |
 | `max_tokens`   | Limits the total number of tokens (words and punctuation) in the response. This controls how long the output can be.                                                                                                                                                                                           |
 | `stop`         | Specifies stop sequences that indicate when the model should stop generating tokens. For example, you might use specific strings to signal the end of a response.                                                                                                                                              |
@@ -97,9 +97,9 @@ Many chat models have standardized parameters that can be used to configure the
 Some important things to note:
 
 - Standard parameters only apply to model providers that expose parameters with the intended functionality. For example, some providers do not expose a configuration for maximum output tokens, so max_tokens can't be supported on these.
-- Standard params are currently only enforced on integrations that have their own integration packages (e.g. `langchain-openai`, `langchain-anthropic`, etc.), they're not enforced on models in ``langchain-community``.
+- Standard parameters are currently only enforced on integrations that have their own integration packages (e.g. `langchain-openai`, `langchain-anthropic`, etc.), they're not enforced on models in `langchain-community`.
 
-ChatModels also accept other parameters that are specific to that integration. To find all the parameters supported by a ChatModel head to the [API reference](https://python.langchain.com/api_reference/) for that model.
+Chat models also accept other parameters that are specific to that integration. To find all the parameters supported by a Chat model head to the their respective [API reference](https://python.langchain.com/api_reference/) for that model.
 
 ## Tool calling
 
@@ -150,7 +150,7 @@ An alternative approach is to use semantic caching, where you cache responses ba
 
 A semantic cache introduces a dependency on another model on the critical path of your application (e.g., the semantic cache may rely on an [embedding model](/docs/concepts/embedding_models) to convert text to a vector representation), and it's not guaranteed to capture the meaning of the input accurately.
 
-However, there might be situations where caching chat model responses is beneficial. For example, if you have a chat model that is used to answer frequently asked questions, caching responses can help reduce the load on the model provider and improve response times.
+However, there might be situations where caching chat model responses is beneficial. For example, if you have a chat model that is used to answer frequently asked questions, caching responses can help reduce the load on the model provider, costs, and improve response times.
 
 Please see the [how to cache chat model responses](/docs/how_to/chat_model_caching/) guide for more details.
 

docs/docs/concepts/document_loaders.mdx

@@ -29,7 +29,7 @@ loader = CSVLoader(
 data = loader.load()
 ```
 
-or if working with large datasets, you can use the `.lazy_load` method:
+When working with large datasets, you can use the `.lazy_load` method:
 
 ```python
 for document in loader.lazy_load():

docs/docs/concepts/index.mdx

@@ -68,6 +68,7 @@ The conceptual guide does not cover step-by-step instructions or specific implem
 - **[langchain](/docs/concepts/architecture#langchain)**: A package for higher level components (e.g., some pre-built chains).
 - **[langgraph](/docs/concepts/architecture#langgraph)**: Powerful orchestration layer for LangChain. Use to build complex pipelines and workflows.
 - **[langserve](/docs/concepts/architecture#langserve)**: Use to deploy LangChain Runnables as REST endpoints. Uses FastAPI. Works primarily for LangChain Runnables, does not currently integrate with LangGraph.
+- **[LLMs (legacy)](/docs/concepts/text_llms)**: Older language models that take a string as input and return a string as output.
 - **[Managing chat history](/docs/concepts/chat_history#managing-chat-history)**: Techniques to maintain and manage the chat history.
 - **[OpenAI format](/docs/concepts/messages#openai-format)**: OpenAI's message format for chat models.
 - **[Propagation of RunnableConfig](/docs/concepts/runnables/#propagation-of-runnableconfig)**: Propagating configuration through Runnables. Read if working with python 3.9, 3.10 and async.

docs/docs/concepts/lcel.mdx

@@ -6,7 +6,7 @@
 
 The **L**ang**C**hain **E**xpression **L**anguage (LCEL) takes a [declarative](https://en.wikipedia.org/wiki/Declarative_programming) approach to building new [Runnables](/docs/concepts/runnables) from existing Runnables.
 
-This means that you describe what you want to happen, rather than how you want it to happen, allowing LangChain to optimize the run-time execution of the chains.
+This means that you describe what *should* happen, rather than *how* it should happen, allowing LangChain to optimize the run-time execution of the chains.
 
 We often refer to a `Runnable` created using LCEL as a "chain". It's important to remember that a "chain" is `Runnable` and it implements the full [Runnable Interface](/docs/concepts/runnables).
 
@@ -20,8 +20,8 @@ We often refer to a `Runnable` created using LCEL as a "chain". It's important t
 
 LangChain optimizes the run-time execution of chains built with LCEL in a number of ways:
 
-- **Optimize parallel execution**: Run Runnables in parallel using [RunnableParallel](#runnableparallel) or run multiple inputs through a given chain in parallel using the [Runnable Batch API](/docs/concepts/runnables/#optimized-parallel-execution-batch). Parallel execution can significantly reduce the latency as processing can be done in parallel instead of sequentially.
-- **Guarantee Async support**: Any chain built with LCEL can be run asynchronously using the [Runnable Async API](/docs/concepts/runnables/#asynchronous-support). This can be useful when running chains in a server environment where you want to handle large number of requests concurrently.
+- **Optimized parallel execution**: Run Runnables in parallel using [RunnableParallel](#runnableparallel) or run multiple inputs through a given chain in parallel using the [Runnable Batch API](/docs/concepts/runnables/#optimized-parallel-execution-batch). Parallel execution can significantly reduce the latency as processing can be done in parallel instead of sequentially.
+- **Guaranteed Async support**: Any chain built with LCEL can be run asynchronously using the [Runnable Async API](/docs/concepts/runnables/#asynchronous-support). This can be useful when running chains in a server environment where you want to handle large number of requests concurrently.
 - **Simplify streaming**: LCEL chains can be streamed, allowing for incremental output as the chain is executed. LangChain can optimize the streaming of the output to minimize the time-to-first-token(time elapsed until the first chunk of output from a [chat model](/docs/concepts/chat_models) or [llm](/docs/concepts/text_llms) comes out).
 
 Other benefits include:
@@ -38,7 +38,7 @@ LCEL is an [orchestration solution](https://en.wikipedia.org/wiki/Orchestration_
 
 While we have seen users run chains with hundreds of steps in production, we generally recommend using LCEL for simpler orchestration tasks. When the application requires complex state management, branching, cycles or multiple agents, we recommend that users take advantage of [LangGraph](/docs/concepts/architecture#langgraph).
 
-In LangGraph, users define graphs that specify the flow of the application. This allows users to keep using LCEL within individual nodes when LCEL is needed, while making it easy to define complex orchestration logic that is more readable and maintainable.
+In LangGraph, users define graphs that specify the application's flow. This allows users to keep using LCEL within individual nodes when LCEL is needed, while making it easy to define complex orchestration logic that is more readable and maintainable.
 
 Here are some guidelines:
 

docs/docs/concepts/messages.mdx

@@ -8,11 +8,11 @@
 
 Messages are the unit of communication in [chat models](/docs/concepts/chat_models). They are used to represent the input and output of a chat model, as well as any additional context or metadata that may be associated with a conversation.
 
-Each message has a **role** (e.g., "user", "assistant"), **content** (e.g., text, multimodal data), and additional metadata that can vary depending on the chat model provider.
+Each message has a **role** (e.g., "user", "assistant") and **content** (e.g., text, multimodal data) with additional metadata that varies depending on the chat model provider.
 
 LangChain provides a unified message format that can be used across chat models, allowing users to work with different chat models without worrying about the specific details of the message format used by each model provider.
 
-## What inside a message?
+## What is inside a message?
 
 A message typically consists of the following pieces of information:
 
@@ -39,6 +39,7 @@ The content of a message text or a list of dictionaries representing [multimodal
 Currently, most chat models support text as the primary content type, with some models also supporting multimodal data. However, support for multimodal data is still limited across most chat model providers.
 
 For more information see:
+* [SystemMessage](#systemmessage) -- for content which should be passed to direct the conversation
 * [HumanMessage](#humanmessage) -- for content in the input from the user.
 * [AIMessage](#aimessage) -- for content in the response from the model.
 * [Multimodality](/docs/concepts/multimodality) -- for more information on multimodal content.

docs/docs/concepts/output_parsers.mdx

@@ -26,6 +26,7 @@ LangChain has lots of different types of output parsers. This is a list of outpu
 
 | Name                                                                                                                                                                                                                                    | Supports Streaming | Has Format Instructions | Calls LLM | Input Type         | Output Type          | Description                                                                                                                                                                                                                                              |
 |-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------|-------------------------|-----------|--------------------|----------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| [Str](https://python.langchain.com/api_reference/core/output_parsers/langchain_core.output_parsers.string.StrOutputParser.html)                                                                                                         | ✅                  |                         |           | `str` \| `Message` | String                | Parses texts from message objects. Useful for handling variable formats of message content (e.g., extracting text from content blocks).                                                                                                                |
 | [JSON](https://python.langchain.com/api_reference/core/output_parsers/langchain_core.output_parsers.json.JSONOutputParser.html#langchain_core.output_parsers.json.JSONOutputParser)                                                     | ✅                  | ✅                       |           | `str` \| `Message` | JSON object          | Returns a JSON object as specified. You can specify a Pydantic model and it will return JSON for that model. Probably the most reliable output parser for getting structured data that does NOT use function calling.                                    |
 | [XML](https://python.langchain.com/api_reference/core/output_parsers/langchain_core.output_parsers.xml.XMLOutputParser.html#langchain_core.output_parsers.xml.XMLOutputParser)                                                          | ✅                  | ✅                       |           | `str` \| `Message` | `dict`               | Returns a dictionary of tags. Use when XML output is needed. Use with models that are good at writing XML (like Anthropic's).                                                                                                                            |
 | [CSV](https://python.langchain.com/api_reference/core/output_parsers/langchain_core.output_parsers.list.CommaSeparatedListOutputParser.html#langchain_core.output_parsers.list.CommaSeparatedListOutputParser)                          | ✅                  | ✅                       |           | `str` \| `Message` | `List[str]`          | Returns a list of comma separated values.                                                                                                                                                                                                                |

docs/docs/concepts/retrieval.mdx

@@ -27,7 +27,7 @@ These systems accommodate various data formats:
 - Unstructured text (e.g., documents) is often stored in vector stores or lexical search indexes.
 - Structured data is typically housed in relational or graph databases with defined schemas.
 
-Despite this diversity in data formats, modern AI applications increasingly aim to make all types of data accessible through natural language interfaces. 
+Despite the growing diversity in data formats, modern AI applications increasingly aim to make all types of data accessible through natural language interfaces. 
 Models play a crucial role in this process by translating natural language queries into formats compatible with the underlying search index or database. 
 This translation enables more intuitive and flexible interactions with complex data structures.
 
@@ -41,7 +41,7 @@ This translation enables more intuitive and flexible interactions with complex d
 
 ## Query analysis 
 
-While users typically prefer to interact with retrieval systems using natural language, retrieval systems can specific query syntax or benefit from particular keywords. 
+While users typically prefer to interact with retrieval systems using natural language, these systems may require specific query syntax or benefit from certain keywords. 
 Query analysis serves as a bridge between raw user input and optimized search queries. Some common applications of query analysis include:
 
 1. **Query Re-writing**: Queries can be re-written or expanded to improve semantic or lexical searches.

docs/docs/concepts/runnables.mdx

@@ -1,6 +1,6 @@
 # Runnable interface
 
-The Runnable interface is foundational for working with LangChain components, and it's implemented across many of them, such as [language models](/docs/concepts/chat_models), [output parsers](/docs/concepts/output_parsers), [retrievers](/docs/concepts/retrievers), [compiled LangGraph graphs](
+The Runnable interface is the foundation for working with LangChain components, and it's implemented across many of them, such as [language models](/docs/concepts/chat_models), [output parsers](/docs/concepts/output_parsers), [retrievers](/docs/concepts/retrievers), [compiled LangGraph graphs](
 https://langchain-ai.github.io/langgraph/concepts/low_level/#compiling-your-graph) and more.
 
 This guide covers the main concepts and methods of the Runnable interface, which allows developers to interact with various LangChain components in a consistent and predictable manner.
@@ -42,7 +42,7 @@ Some Runnables may provide their own implementations of `batch` and `batch_as_co
 rely on a `batch` API provided by a model provider).
 
 :::note
-The async versions of `abatch` and `abatch_as_completed` these rely on asyncio's [gather](https://docs.python.org/3/library/asyncio-task.html#asyncio.gather) and [as_completed](https://docs.python.org/3/library/asyncio-task.html#asyncio.as_completed) functions to run the `ainvoke` method in parallel.
+The async versions of `abatch` and `abatch_as_completed` relies on asyncio's [gather](https://docs.python.org/3/library/asyncio-task.html#asyncio.gather) and [as_completed](https://docs.python.org/3/library/asyncio-task.html#asyncio.as_completed) functions to run the `ainvoke` method in parallel.
 :::
 
 :::tip
@@ -58,7 +58,7 @@ Runnables expose an asynchronous API, allowing them to be called using the `awai
 
 Please refer to the [Async Programming with LangChain](/docs/concepts/async) guide for more details.
 
-## Streaming apis
+## Streaming APIs
 <span data-heading-keywords="streaming-api"></span>
 
 Streaming is critical in making applications based on LLMs feel responsive to end-users.
@@ -101,7 +101,7 @@ This is an advanced feature that is unnecessary for most users. You should proba
 skip this section unless you have a specific need to inspect the schema of a Runnable.
 :::
 
-In some advanced uses, you may want to programmatically **inspect** the Runnable and determine what input and output types the Runnable expects and produces.
+In more advanced use cases, you may want to programmatically **inspect** the Runnable and determine what input and output types the Runnable expects and produces.
 
 The Runnable interface provides methods to get the [JSON Schema](https://json-schema.org/) of the input and output types of a Runnable, as well as [Pydantic schemas](https://docs.pydantic.dev/latest/) for the input and output types.
 
@@ -315,7 +315,7 @@ the `RunnableConfig` manually to sub-calls in some cases. Please see the
 [Propagating RunnableConfig](#propagation-of-runnableconfig) section for more information.
 :::
 
-## Creating a runnable from a function
+## Creating a runnable from a function {#custom-runnables}
 
 You may need to create a custom Runnable that runs arbitrary logic. This is especially
 useful if using [LangChain Expression Language (LCEL)](/docs/concepts/lcel) to compose

docs/docs/concepts/streaming.mdx

@@ -77,13 +77,13 @@ When using `stream()` or `astream()` with chat models, the output is streamed as
 
 [LangGraph](/docs/concepts/architecture#langgraph) compiled graphs are [Runnables](/docs/concepts/runnables) and support the standard streaming APIs.
 
-When using the *stream* and *astream* methods with LangGraph, you can **one or more** [streaming mode](https://langchain-ai.github.io/langgraph/reference/types/#langgraph.types.StreamMode) which allow you to control the type of output that is streamed. The available streaming modes are:
+When using the *stream* and *astream* methods with LangGraph, you can choose **one or more** [streaming mode](https://langchain-ai.github.io/langgraph/reference/types/#langgraph.types.StreamMode) which allow you to control the type of output that is streamed. The available streaming modes are:
 
 - **"values"**: Emit all values of the [state](https://langchain-ai.github.io/langgraph/concepts/low_level/) for each step.
 - **"updates"**: Emit only the node name(s) and updates that were returned by the node(s) after each step.
 - **"debug"**: Emit debug events for each step.
 - **"messages"**: Emit LLM [messages](/docs/concepts/messages) [token-by-token](/docs/concepts/tokens).
-- **"custom"**: Emit custom output witten using [LangGraph's StreamWriter](https://langchain-ai.github.io/langgraph/reference/types/#langgraph.types.StreamWriter).
+- **"custom"**: Emit custom output written using [LangGraph's StreamWriter](https://langchain-ai.github.io/langgraph/reference/types/#langgraph.types.StreamWriter).
 
 For more information, please see:
 * [LangGraph streaming conceptual guide](https://langchain-ai.github.io/langgraph/concepts/streaming/) for more information on how to stream when working with LangGraph.

docs/docs/concepts/structured_outputs.mdx

@@ -119,11 +119,11 @@ json_object = json.loads(ai_msg.content)
 
 There are a few challenges when producing structured output with the above methods: 
 
-(1) If using tool calling, tool call arguments needs to be parsed from a dictionary back to the original schema.  
+(1) When tool calling is used, tool call arguments needs to be parsed from a dictionary back to the original schema.  
 
 (2) In addition, the model needs to be instructed to *always* use the tool when we want to enforce structured output, which is a provider specific setting. 
 
-(3) If using JSON mode, the output needs to be parsed into a JSON object. 
+(3) When JSON mode is used, the output needs to be parsed into a JSON object. 
 
 With these challenges in mind, LangChain provides a helper function (`with_structured_output()`) to streamline the process.
 

docs/docs/concepts/tool_calling.mdx

@@ -128,7 +128,7 @@ For more details on usage, see our [how-to guides](/docs/how_to/#tools)!
 
 [Tools](/docs/concepts/tools/) implement the [Runnable](/docs/concepts/runnables/) interface, which means that they can be invoked (e.g., `tool.invoke(args)`) directly.
 
-[LangGraph](https://langchain-ai.github.io/langgraph/) offers pre-built components (e.g., [`ToolNode`](https://langchain-ai.github.io/langgraph/reference/prebuilt/#toolnode)) that will often invoke the tool in behalf of the user.
+[LangGraph](https://langchain-ai.github.io/langgraph/) offers pre-built components (e.g., [`ToolNode`](https://langchain-ai.github.io/langgraph/reference/prebuilt/#langgraph.prebuilt.tool_node.ToolNode)) that will often invoke the tool in behalf of the user.
 
 :::info[Further reading]
 

docs/docs/concepts/tools.mdx

@@ -6,7 +6,7 @@
 
 ## Overview
 
-The **tool** abstraction in LangChain associates a python **function** with a **schema** that defines the function's **name**, **description** and **input**. 
+The **tool** abstraction in LangChain associates a Python **function** with a **schema** that defines the function's **name**, **description** and **expected arguments**. 
 
 **Tools** can be passed to [chat models](/docs/concepts/chat_models) that support [tool calling](/docs/concepts/tool_calling) allowing the model to request the execution of a specific function with specific inputs.
 
@@ -14,7 +14,7 @@ The **tool** abstraction in LangChain associates a python **function** with a **
 
 - Tools are a way to encapsulate a function and its schema in a way that can be passed to a chat model.
 - Create tools using the [@tool](https://python.langchain.com/api_reference/core/tools/langchain_core.tools.convert.tool.html) decorator, which simplifies the process of tool creation, supporting the following:
-   - Automatically infer the tool's **name**, **description** and **inputs**, while also supporting customization.
+   - Automatically infer the tool's **name**, **description** and **expected arguments**, while also supporting customization.
    - Defining tools that return **artifacts** (e.g. images, dataframes, etc.)
    - Hiding input arguments from the schema (and hence from the model) using **injected tool arguments**.
 

docs/docs/concepts/why_langchain.mdx

@@ -1,9 +1,9 @@
-# Why langchain?
+# Why LangChain?
 
-The goal of `langchain` the Python package and LangChain the company is to make it as easy possible for developers to build applications that reason.
+The goal of `langchain` the Python package and LangChain the company is to make it as easy as possible for developers to build applications that reason.
 While LangChain originally started as a single open source package, it has evolved into a company and a whole ecosystem.
 This page will talk about the LangChain ecosystem as a whole.
-Most of the components within in the LangChain ecosystem can be used by themselves - so if you feel particularly drawn to certain components but not others, that is totally fine! Pick and choose whichever components you like best.
+Most of the components within the LangChain ecosystem can be used by themselves - so if you feel particularly drawn to certain components but not others, that is totally fine! Pick and choose whichever components you like best for your own use case!
 
 ## Features
 
@@ -17,8 +17,8 @@ LangChain exposes a standard interface for key components, making it easy to swi
 [Orchestration](https://en.wikipedia.org/wiki/Orchestration_(computing)) is crucial for building such applications.
 
 3. **Observability and evaluation:** As applications become more complex, it becomes increasingly difficult to understand what is happening within them.
-Furthermore, the pace of development can become rate-limited by the [paradox of choice](https://en.wikipedia.org/wiki/Paradox_of_choice):
-for example, developers often wonder how to engineer their prompt or which LLM best balances accuracy, latency, and cost. 
+Furthermore, the pace of development can become rate-limited by the [paradox of choice](https://en.wikipedia.org/wiki/Paradox_of_choice).
+For example, developers often wonder how to engineer their prompt or which LLM best balances accuracy, latency, and cost. 
 [Observability](https://en.wikipedia.org/wiki/Observability) and evaluations can help developers monitor their applications and rapidly answer these types of questions with confidence.
 
 
@@ -72,11 +72,11 @@ There are several common characteristics of LLM applications that this orchestra
 * **[Persistence](https://langchain-ai.github.io/langgraph/concepts/persistence/):** The application needs to maintain [short-term and / or long-term memory](https://langchain-ai.github.io/langgraph/concepts/memory/).
 * **[Human-in-the-loop](https://langchain-ai.github.io/langgraph/concepts/human_in_the_loop/):** The application needs human interaction, e.g., pausing, reviewing, editing, approving certain steps.
 
-The recommended way to do orchestration for these complex applications is [LangGraph](https://langchain-ai.github.io/langgraph/concepts/high_level/).
+The recommended way to orchestrate components for complex applications is [LangGraph](https://langchain-ai.github.io/langgraph/concepts/high_level/).
 LangGraph is a library that gives developers a high degree of control by expressing the flow of the application as a set of nodes and edges.
 LangGraph comes with built-in support for [persistence](https://langchain-ai.github.io/langgraph/concepts/persistence/), [human-in-the-loop](https://langchain-ai.github.io/langgraph/concepts/human_in_the_loop/), [memory](https://langchain-ai.github.io/langgraph/concepts/memory/), and other features.
-It's particularly  well suited for building [agents](https://langchain-ai.github.io/langgraph/concepts/agentic_concepts/) or [multi-agent](https://langchain-ai.github.io/langgraph/concepts/multi_agent/) applications. 
-Importantly, individual LangChain components can be used within LangGraph nodes, but you can also use LangGraph **without** using LangChain components.
+It's particularly well suited for building [agents](https://langchain-ai.github.io/langgraph/concepts/agentic_concepts/) or [multi-agent](https://langchain-ai.github.io/langgraph/concepts/multi_agent/) applications. 
+Importantly, individual LangChain components can be used as LangGraph nodes, but you can also use LangGraph **without** using LangChain components.
 
 :::info[Further reading]
 

docs/docs/contributing/how_to/documentation/style_guide.mdx

@@ -4,8 +4,8 @@ sidebar_class_name: "hidden"
 
 # Documentation Style Guide
 
-As LangChain continues to grow, the surface area of documentation required to cover it continues to grow too.
-This page provides guidelines for anyone writing documentation for LangChain, as well as some of our philosophies around
+As LangChain continues to grow, the amount of documentation required to cover the various concepts and integrations continues to grow too.
+This page provides guidelines for anyone writing documentation for LangChain and outlines some of our philosophies around
 organization and structure.
 
 ## Philosophy
@@ -18,9 +18,9 @@ Under this framework, all documentation falls under one of four categories: [Tut
 ### Tutorials
 
 Tutorials are lessons that take the reader through a practical activity. Their purpose is to help the user
-gain understanding of concepts and how they interact by showing one way to achieve some goal in a hands-on way. They should **avoid** giving
-multiple permutations of ways to achieve that goal in-depth. Instead, it should guide a new user through a recommended path to accomplishing the tutorial's goal. While the end result of a tutorial does not necessarily need to
-be completely production-ready, it should be useful and practically satisfy the the goal that you clearly stated in the tutorial's introduction. Information on how to address additional scenarios
+gain an understanding of concepts and how they interact by showing one way to achieve a specific goal in a hands-on manner. They should **avoid** giving
+multiple permutations of ways to achieve that goal in-depth. Instead, it should guide a new user through a recommended path to accomplish the tutorial's goal. While the end result of a tutorial does not necessarily need to
+be completely production-ready, it should be useful and practically satisfy the goal that is clearly stated in the tutorial's introduction. Information on how to address additional scenarios
 belongs in how-to guides.
 
 To quote the Diataxis website:
@@ -53,8 +53,8 @@ Here are some high-level tips on writing a good tutorial:
 ### How-to guides
 
 A how-to guide, as the name implies, demonstrates how to do something discrete and specific.
-It should assume that the user is already familiar with underlying concepts, and is trying to solve an immediate problem, but
-should still give some background or list the scenarios where the information contained within can be relevant.
+It should assume that the user is already familiar with underlying concepts, and is focused on solving an immediate problem. However,
+it should still provide some background or list certain scenarios where the information may be relevant.
 They can and should discuss alternatives if one approach may be better than another in certain cases.
 
 To quote the Diataxis website:
@@ -79,10 +79,10 @@ Here are some high-level tips on writing a good how-to guide:
 
 ### Conceptual guide
 
-LangChain's conceptual guide falls under the **Explanation** quadrant of Diataxis. They should cover LangChain terms and concepts
-in a more abstract way than how-to guides or tutorials, and should be geared towards curious users interested in
-gaining a deeper understanding of the framework. Try to avoid excessively large code examples - the goal here is to
-impart perspective to the user rather than to finish a practical project. These guides should cover **why** things work they way they do.
+LangChain's conceptual guide falls under the **Explanation** quadrant of Diataxis. These guides should cover LangChain terms and concepts
+in a more abstract way than how-to guides or tutorials, targeting curious users interested in
+gaining a deeper understanding and insights of the framework. Try to avoid excessively large code examples as the primary goal is to
+provide perspective to the user rather than to finish a practical project. These guides should cover **why** things work they way they do.
 
 This guide on documentation style is meant to fall under this category.
 
@@ -137,14 +137,14 @@ be only one (very rarely two), canonical pages for a given concept or feature. I
 
 ### Link to other sections
 
-Because sections of the docs do not exist in a vacuum, it is important to link to other sections as often as possible
-to allow a developer to learn more about an unfamiliar topic inline.
+Because sections of the docs do not exist in a vacuum, it is important to link to other sections frequently,
+to allow a developer to learn more about an unfamiliar topic within the flow of reading.
 
-This includes linking to the API references as well as conceptual sections!
+This includes linking to the API references and conceptual sections!
 
 ### Be concise
 
-In general, take a less-is-more approach. If a section with a good explanation of a concept already exists, you should link to it rather than
+In general, take a less-is-more approach. If another section with a good explanation of a concept exists, you should link to it rather than
 re-explain it, unless the concept you are documenting presents some new wrinkle.
 
 Be concise, including in code samples.

docs/docs/contributing/tutorials/docs.mdx

@@ -8,7 +8,7 @@ This tutorial will guide you through making a simple documentation edit, like co
 
 ---
 
-## Editing a Documentation Page on GitHub**
+## Editing a Documentation Page on GitHub
 
 Sometimes you want to make a small change, like fixing a typo, and the easiest way to do this is to use GitHub's editor directly.
 

docs/docs/how_to/HTML_header_metadata_splitter.ipynb

@@ -13,7 +13,7 @@
     "# How to split by HTML header \n",
     "## Description and motivation\n",
     "\n",
-    "[HTMLHeaderTextSplitter](https://python.langchain.com/api_reference/text_splitters/html/langchain_text_splitters.html.HTMLHeaderTextSplitter.html) is a \"structure-aware\" chunker that splits text at the HTML element level and adds metadata for each header \"relevant\" to any given chunk. It can return chunks element by element or combine elements with the same metadata, with the objectives of (a) keeping related text grouped (more or less) semantically and (b) preserving context-rich information encoded in document structures. It can be used with other text splitters as part of a chunking pipeline.\n",
+    "[HTMLHeaderTextSplitter](https://python.langchain.com/api_reference/text_splitters/html/langchain_text_splitters.html.HTMLHeaderTextSplitter.html) is a \"structure-aware\" [text splitter](/docs/concepts/text_splitters/) that splits text at the HTML element level and adds metadata for each header \"relevant\" to any given chunk. It can return chunks element by element or combine elements with the same metadata, with the objectives of (a) keeping related text grouped (more or less) semantically and (b) preserving context-rich information encoded in document structures. It can be used with other text splitters as part of a chunking pipeline.\n",
     "\n",
     "It is analogous to the [MarkdownHeaderTextSplitter](/docs/how_to/markdown_header_metadata_splitter) for markdown files.\n",
     "\n",

docs/docs/how_to/HTML_section_aware_splitter.ipynb

@@ -12,7 +12,7 @@
    "source": [
     "# How to split by HTML sections\n",
     "## Description and motivation\n",
-    "Similar in concept to the [HTMLHeaderTextSplitter](/docs/how_to/HTML_header_metadata_splitter), the `HTMLSectionSplitter` is a \"structure-aware\" chunker that splits text at the element level and adds metadata for each header \"relevant\" to any given chunk.\n",
+    "Similar in concept to the [HTMLHeaderTextSplitter](/docs/how_to/HTML_header_metadata_splitter), the `HTMLSectionSplitter` is a \"structure-aware\" [text splitter](/docs/concepts/text_splitters/) that splits text at the element level and adds metadata for each header \"relevant\" to any given chunk.\n",
     "\n",
     "It can return chunks element by element or combine elements with the same metadata, with the objectives of (a) keeping related text grouped (more or less) semantically and (b) preserving context-rich information encoded in document structures.\n",
     "\n",

docs/docs/how_to/MultiQueryRetriever.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# How to use the MultiQueryRetriever\n",
     "\n",
-    "Distance-based vector database retrieval embeds (represents) queries in high-dimensional space and finds similar embedded documents based on a distance metric. But, retrieval may produce different results with subtle changes in query wording, or if the embeddings do not capture the semantics of the data well. Prompt engineering / tuning is sometimes done to manually address these problems, but can be tedious.\n",
+    "Distance-based [vector database](/docs/concepts/vectorstores/) retrieval [embeds](/docs/concepts/embedding_models/) (represents) queries in high-dimensional space and finds similar embedded documents based on a distance metric. But, retrieval may produce different results with subtle changes in query wording, or if the embeddings do not capture the semantics of the data well. Prompt engineering / tuning is sometimes done to manually address these problems, but can be tedious.\n",
     "\n",
     "The [MultiQueryRetriever](https://python.langchain.com/api_reference/langchain/retrievers/langchain.retrievers.multi_query.MultiQueryRetriever.html) automates the process of prompt tuning by using an LLM to generate multiple queries from different perspectives for a given user input query. For each query, it retrieves a set of relevant documents and takes the unique union across all queries to get a larger set of potentially relevant documents. By generating multiple perspectives on the same question, the `MultiQueryRetriever` can mitigate some of the limitations of the distance-based retrieval and get a richer set of results.\n",
     "\n",
@@ -151,7 +151,7 @@
    "id": "7e170263-facd-4065-bb68-d11fb9123a45",
    "metadata": {},
    "source": [
-    "Note that the underlying queries generated by the retriever are logged at the `INFO` level."
+    "Note that the underlying queries generated by the [retriever](/docs/concepts/retrievers/) are logged at the `INFO` level."
    ]
   },
   {

docs/docs/how_to/add_scores_retriever.ipynb

@@ -7,11 +7,11 @@
    "source": [
     "# How to add scores to retriever results\n",
     "\n",
-    "Retrievers will return sequences of [Document](https://python.langchain.com/api_reference/core/documents/langchain_core.documents.base.Document.html) objects, which by default include no information about the process that retrieved them (e.g., a similarity score against a query). Here we demonstrate how to add retrieval scores to the `.metadata` of documents:\n",
+    "[Retrievers](/docs/concepts/retrievers/) will return sequences of [Document](https://python.langchain.com/api_reference/core/documents/langchain_core.documents.base.Document.html) objects, which by default include no information about the process that retrieved them (e.g., a similarity score against a query). Here we demonstrate how to add retrieval scores to the `.metadata` of documents:\n",
     "1. From [vectorstore retrievers](/docs/how_to/vectorstore_retriever);\n",
     "2. From higher-order LangChain retrievers, such as [SelfQueryRetriever](/docs/how_to/self_query) or [MultiVectorRetriever](/docs/how_to/multi_vector).\n",
     "\n",
-    "For (1), we will implement a short wrapper function around the corresponding vector store. For (2), we will update a method of the corresponding class.\n",
+    "For (1), we will implement a short wrapper function around the corresponding [vector store](/docs/concepts/vectorstores/). For (2), we will update a method of the corresponding class.\n",
     "\n",
     "## Create vector store\n",
     "\n",

docs/docs/how_to/agent_executor.ipynb

@@ -22,7 +22,7 @@
     ":::\n",
     "\n",
     "By themselves, language models can't take actions - they just output text.\n",
-    "A big use case for LangChain is creating **agents**.\n",
+    "A big use case for LangChain is creating **[agents](/docs/concepts/agents/)**.\n",
     "Agents are systems that use an LLM as a reasoning engine to determine which actions to take and what the inputs to those actions should be.\n",
     "The results of those actions can then be fed back into the agent and it determines whether more actions are needed, or whether it is okay to finish.\n",
     "\n",

docs/docs/how_to/caching_embeddings.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# Caching\n",
     "\n",
-    "Embeddings can be stored or temporarily cached to avoid needing to recompute them.\n",
+    "[Embeddings](/docs/concepts/embedding_models/) can be stored or temporarily cached to avoid needing to recompute them.\n",
     "\n",
     "Caching embeddings can be done using a `CacheBackedEmbeddings`. The cache backed embedder is a wrapper around an embedder that caches\n",
     "embeddings in a key-value store. The text is hashed and the hash is used as the key in the cache.\n",

docs/docs/how_to/character_text_splitter.ipynb

@@ -21,7 +21,7 @@
    "source": [
     "# How to split by character\n",
     "\n",
-    "This is the simplest method. This splits based on a given character sequence, which defaults to `\"\\n\\n\"`. Chunk length is measured by number of characters.\n",
+    "This is the simplest method. This [splits](/docs/concepts/text_splitters/) based on a given character sequence, which defaults to `\"\\n\\n\"`. Chunk length is measured by number of characters.\n",
     "\n",
     "1. How the text is split: by single character separator.\n",
     "2. How the chunk size is measured: by number of characters.\n",

docs/docs/how_to/chat_model_caching.ipynb

@@ -15,7 +15,7 @@
     "\n",
     ":::\n",
     "\n",
-    "LangChain provides an optional caching layer for chat models. This is useful for two main reasons:\n",
+    "LangChain provides an optional caching layer for [chat models](/docs/concepts/chat_models). This is useful for two main reasons:\n",
     "\n",
     "- It can save you money by reducing the number of API calls you make to the LLM provider, if you're often requesting the same completion multiple times. This is especially useful during app development.\n",
     "- It can speed up your application by reducing the number of API calls you make to the LLM provider.\n",

docs/docs/how_to/chat_models_universal_init.ipynb

@@ -7,13 +7,13 @@
    "source": [
     "# How to init any model in one line\n",
     "\n",
-    "Many LLM applications let end users specify what model provider and model they want the application to be powered by. This requires writing some logic to initialize different ChatModels based on some user configuration. The `init_chat_model()` helper method makes it easy to initialize a number of different model integrations without having to worry about import paths and class names.\n",
+    "Many LLM applications let end users specify what model provider and model they want the application to be powered by. This requires writing some logic to initialize different [chat models](/docs/concepts/chat_models/) based on some user configuration. The `init_chat_model()` helper method makes it easy to initialize a number of different model integrations without having to worry about import paths and class names.\n",
     "\n",
     ":::tip Supported models\n",
     "\n",
     "See the [init_chat_model()](https://python.langchain.com/api_reference/langchain/chat_models/langchain.chat_models.base.init_chat_model.html) API reference for a full list of supported integrations.\n",
     "\n",
-    "Make sure you have the integration packages installed for any model providers you want to support. E.g. you should have `langchain-openai` installed to init an OpenAI model.\n",
+    "Make sure you have the [integration packages](/docs/integrations/chat/) installed for any model providers you want to support. E.g. you should have `langchain-openai` installed to init an OpenAI model.\n",
     "\n",
     ":::"
    ]

docs/docs/how_to/chat_token_usage_tracking.ipynb

@@ -14,7 +14,7 @@
     "\n",
     ":::\n",
     "\n",
-    "Tracking token usage to calculate cost is an important part of putting your app in production. This guide goes over how to obtain this information from your LangChain model calls.\n",
+    "Tracking [token](/docs/concepts/tokens/) usage to calculate cost is an important part of putting your app in production. This guide goes over how to obtain this information from your LangChain model calls.\n",
     "\n",
     "This guide requires `langchain-anthropic` and `langchain-openai >= 0.1.9`."
    ]

docs/docs/how_to/chatbots_memory.ipynb

@@ -15,7 +15,7 @@
    "source": [
     "# How to add memory to chatbots\n",
     "\n",
-    "A key feature of chatbots is their ability to use content of previous conversation turns as context. This state management can take several forms, including:\n",
+    "A key feature of chatbots is their ability to use the content of previous conversational turns as context. This state management can take several forms, including:\n",
     "\n",
     "- Simply stuffing previous messages into a chat model prompt.\n",
     "- The above, but trimming old messages to reduce the amount of distracting information the model has to deal with.\n",
@@ -185,7 +185,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    " We'll pass the latest input to the conversation here and let the LangGraph keep track of the conversation history using the checkpointer:"
+    " We'll pass the latest input to the conversation here and let LangGraph keep track of the conversation history using the checkpointer:"
    ]
   },
   {

docs/docs/how_to/chatbots_retrieval.ipynb

@@ -15,7 +15,7 @@
    "source": [
     "# How to add retrieval to chatbots\n",
     "\n",
-    "Retrieval is a common technique chatbots use to augment their responses with data outside a chat model's training data. This section will cover how to implement retrieval in the context of chatbots, but it's worth noting that retrieval is a very subtle and deep topic - we encourage you to explore [other parts of the documentation](/docs/how_to#qa-with-rag) that go into greater depth!\n",
+    "[Retrieval](/docs/concepts/retrieval/) is a common technique chatbots use to augment their responses with data outside a chat model's training data. This section will cover how to implement retrieval in the context of chatbots, but it's worth noting that retrieval is a very subtle and deep topic - we encourage you to explore [other parts of the documentation](/docs/how_to#qa-with-rag) that go into greater depth!\n",
     "\n",
     "## Setup\n",
     "\n",
@@ -80,7 +80,7 @@
    "source": [
     "## Creating a retriever\n",
     "\n",
-    "We'll use [the LangSmith documentation](https://docs.smith.langchain.com/overview) as source material and store the content in a vectorstore for later retrieval. Note that this example will gloss over some of the specifics around parsing and storing a data source - you can see more [in-depth documentation on creating retrieval systems here](/docs/how_to#qa-with-rag).\n",
+    "We'll use [the LangSmith documentation](https://docs.smith.langchain.com/overview) as source material and store the content in a [vector store](/docs/concepts/vectorstores/) for later retrieval. Note that this example will gloss over some of the specifics around parsing and storing a data source - you can see more [in-depth documentation on creating retrieval systems here](/docs/how_to#qa-with-rag).\n",
     "\n",
     "Let's use a document loader to pull text from the docs:"
    ]

docs/docs/how_to/chatbots_tools.ipynb

@@ -42,7 +42,7 @@
    "metadata": {},
    "outputs": [
     {
-     "name": "stdin",
+     "name": "stdout",
      "output_type": "stream",
      "text": [
       "OpenAI API Key: ········\n",
@@ -78,7 +78,7 @@
     "\n",
     "Our end goal is to create an agent that can respond conversationally to user questions while looking up information as needed.\n",
     "\n",
-    "First, let's initialize Tavily and an OpenAI chat model capable of tool calling:"
+    "First, let's initialize Tavily and an OpenAI [chat model](/docs/concepts/chat_models/) capable of tool calling:"
    ]
   },
   {

docs/docs/how_to/code_splitter.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# How to split code\n",
     "\n",
-    "[RecursiveCharacterTextSplitter](https://python.langchain.com/api_reference/text_splitters/character/langchain_text_splitters.character.RecursiveCharacterTextSplitter.html) includes pre-built lists of separators that are useful for splitting text in a specific programming language.\n",
+    "[RecursiveCharacterTextSplitter](https://python.langchain.com/api_reference/text_splitters/character/langchain_text_splitters.character.RecursiveCharacterTextSplitter.html) includes pre-built lists of separators that are useful for [splitting text](/docs/concepts/text_splitters/) in a specific programming language.\n",
     "\n",
     "Supported languages are stored in the `langchain_text_splitters.Language` enum. They include:\n",
     "\n",

docs/docs/how_to/contextual_compression.ipynb

@@ -7,13 +7,13 @@
    "source": [
     "# How to do retrieval with contextual compression\n",
     "\n",
-    "One challenge with retrieval is that usually you don't know the specific queries your document storage system will face when you ingest data into the system. This means that the information most relevant to a query may be buried in a document with a lot of irrelevant text. Passing that full document through your application can lead to more expensive LLM calls and poorer responses.\n",
+    "One challenge with [retrieval](/docs/concepts/retrieval/) is that usually you don't know the specific queries your document storage system will face when you ingest data into the system. This means that the information most relevant to a query may be buried in a document with a lot of irrelevant text. Passing that full document through your application can lead to more expensive LLM calls and poorer responses.\n",
     "\n",
     "Contextual compression is meant to fix this. The idea is simple: instead of immediately returning retrieved documents as-is, you can compress them using the context of the given query, so that only the relevant information is returned. “Compressing” here refers to both compressing the contents of an individual document and filtering out documents wholesale.\n",
     "\n",
     "To use the Contextual Compression Retriever, you'll need:\n",
     "\n",
-    "- a base retriever\n",
+    "- a base [retriever](/docs/concepts/retrievers/)\n",
     "- a Document Compressor\n",
     "\n",
     "The Contextual Compression Retriever passes queries to the base retriever, takes the initial documents and passes them through the Document Compressor. The Document Compressor takes a list of documents and shortens it by reducing the contents of documents or dropping documents altogether.\n",

docs/docs/how_to/custom_chat_model.ipynb

@@ -14,15 +14,15 @@
     "\n",
     ":::\n",
     "\n",
-    "In this guide, we'll learn how to create a custom chat model using LangChain abstractions.\n",
+    "In this guide, we'll learn how to create a custom [chat model](/docs/concepts/chat_models/) using LangChain abstractions.\n",
     "\n",
     "Wrapping your LLM with the standard [`BaseChatModel`](https://python.langchain.com/api_reference/core/language_models/langchain_core.language_models.chat_models.BaseChatModel.html) interface allow you to use your LLM in existing LangChain programs with minimal code modifications!\n",
     "\n",
-    "As an bonus, your LLM will automatically become a LangChain `Runnable` and will benefit from some optimizations out of the box (e.g., batch via a threadpool), async support, the `astream_events` API, etc.\n",
+    "As an bonus, your LLM will automatically become a LangChain [Runnable](/docs/concepts/runnables/) and will benefit from some optimizations out of the box (e.g., batch via a threadpool), async support, the `astream_events` API, etc.\n",
     "\n",
     "## Inputs and outputs\n",
     "\n",
-    "First, we need to talk about **messages**, which are the inputs and outputs of chat models.\n",
+    "First, we need to talk about **[messages](/docs/concepts/messages/)**, which are the inputs and outputs of chat models.\n",
     "\n",
     "### Messages\n",
     "\n",
@@ -503,7 +503,7 @@
     "\n",
     "Documentation:\n",
     "\n",
-    "* The model contains doc-strings for all initialization arguments, as these will be surfaced in the [APIReference](https://python.langchain.com/api_reference/langchain/index.html).\n",
+    "* The model contains doc-strings for all initialization arguments, as these will be surfaced in the [API Reference](https://python.langchain.com/api_reference/langchain/index.html).\n",
     "* The class doc-string for the model contains a link to the model API if the model is powered by a service.\n",
     "\n",
     "Tests:\n",

docs/docs/how_to/custom_retriever.ipynb

@@ -19,9 +19,9 @@
     "\n",
     "## Overview\n",
     "\n",
-    "Many LLM applications involve retrieving information from external data sources using a `Retriever`. \n",
+    "Many LLM applications involve retrieving information from external data sources using a [Retriever](/docs/concepts/retrievers/). \n",
     "\n",
-    "A retriever is responsible for retrieving a list of relevant `Documents` to a given user `query`.\n",
+    "A retriever is responsible for retrieving a list of relevant [Documents](https://python.langchain.com/api_reference/core/documents/langchain_core.documents.base.Document.html) to a given user `query`.\n",
     "\n",
     "The retrieved documents are often formatted into prompts that are fed into an LLM, allowing the LLM to use the information in the to generate an appropriate response (e.g., answering a user question based on a knowledge base).\n",
     "\n",

docs/docs/how_to/custom_tools.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# How to create tools\n",
     "\n",
-    "When constructing an agent, you will need to provide it with a list of `Tool`s that it can use. Besides the actual function that is called, the Tool consists of several components:\n",
+    "When constructing an [agent](/docs/concepts/agents/), you will need to provide it with a list of [Tools](/docs/concepts/tools/) that it can use. Besides the actual function that is called, the Tool consists of several components:\n",
     "\n",
     "| Attribute     | Type                            | Description                                                                                                                                                                    |\n",
     "|---------------|---------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n",
@@ -20,7 +20,7 @@
     "\n",
     "1. Functions;\n",
     "2. LangChain [Runnables](/docs/concepts/runnables);\n",
-    "3. By sub-classing from [BaseTool](https://python.langchain.com/api_reference/core/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",
+    "3. By sub-classing from [BaseTool](https://python.langchain.com/api_reference/core/tools/langchain_core.tools.base.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",
     "Creating tools from functions may be sufficient for most use cases, and can be done via a simple [@tool decorator](https://python.langchain.com/api_reference/core/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://python.langchain.com/api_reference/core/tools/langchain_core.tools.structured.StructuredTool.html#langchain_core.tools.structured.StructuredTool.from_function) class method.\n",
     "\n",

docs/docs/how_to/document_loader_csv.ipynb

@@ -157,7 +157,7 @@
     "    temp_file_path = temp_file.name\n",
     "\n",
     "loader = CSVLoader(file_path=temp_file_path)\n",
-    "loader.load()\n",
+    "data = loader.load()\n",
     "for record in data[:2]:\n",
     "    print(record)"
    ]

docs/docs/how_to/document_loader_custom.ipynb

@@ -26,7 +26,7 @@
     "`Document` objects are often formatted into prompts that are fed into an LLM, allowing the LLM to use the information in the `Document` to generate a desired response (e.g., summarizing the document).\n",
     "`Documents` can be either used immediately or indexed into a vectorstore for future retrieval and use.\n",
     "\n",
-    "The main abstractions for Document Loading are:\n",
+    "The main abstractions for [Document Loading](/docs/concepts/document_loaders/) are:\n",
     "\n",
     "\n",
     "| Component      | Description                    |\n",

docs/docs/how_to/document_loader_pdf.ipynb

@@ -9,7 +9,7 @@
     "\n",
     "[Portable Document Format (PDF)](https://en.wikipedia.org/wiki/PDF), standardized as ISO 32000, is a file format developed by Adobe in 1992 to present documents, including text formatting and images, in a manner independent of application software, hardware, and operating systems.\n",
     "\n",
-    "This guide covers how to load `PDF` documents into the LangChain [Document](https://python.langchain.com/api_reference/core/documents/langchain_core.documents.base.Document.html) format that we use downstream.\n",
+    "This guide covers how to [load](/docs/concepts/document_loaders/) `PDF` documents into the LangChain [Document](https://python.langchain.com/api_reference/core/documents/langchain_core.documents.base.Document.html) format that we use downstream.\n",
     "\n",
     "Text in PDFs is typically represented via text boxes. They may also contain images. A PDF parser might do some combination of the following:\n",
     "\n",
@@ -48,7 +48,7 @@
     "\n",
     "## Simple and fast text extraction\n",
     "\n",
-    "If you are looking for a simple string representation of text that is embedded in a PDF, the method below is appropriate. It will return a list of [Document](https://python.langchain.com/api_reference/core/documents/langchain_core.documents.base.Document.html) objects-- one per page-- containing a single string of the page's text in the Document's `page_content` attribute. It will not parse text in images or scanned PDF pages. Under the hood it uses the [pypydf](https://pypdf.readthedocs.io/en/stable/) Python library.\n",
+    "If you are looking for a simple string representation of text that is embedded in a PDF, the method below is appropriate. It will return a list of [Document](https://python.langchain.com/api_reference/core/documents/langchain_core.documents.base.Document.html) objects-- one per page-- containing a single string of the page's text in the Document's `page_content` attribute. It will not parse text in images or scanned PDF pages. Under the hood it uses the [pypdf](https://pypdf.readthedocs.io/en/stable/) Python library.\n",
     "\n",
     "LangChain [document loaders](/docs/concepts/document_loaders) implement `lazy_load` and its async variant, `alazy_load`, which return iterators of `Document` objects. We will use these below."
    ]
@@ -250,7 +250,7 @@
    "metadata": {},
    "outputs": [
     {
-     "name": "stdin",
+     "name": "stdout",
      "output_type": "stream",
      "text": [
       "Unstructured API Key: ········\n"

docs/docs/how_to/document_loader_web.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# How to load web pages\n",
     "\n",
-    "This guide covers how to load web pages into the LangChain [Document](https://python.langchain.com/api_reference/core/documents/langchain_core.documents.base.Document.html) format that we use downstream. Web pages contain text, images, and other multimedia elements, and are typically represented with HTML. They may include links to other pages or resources.\n",
+    "This guide covers how to [load](/docs/concepts/document_loaders/) web pages into the LangChain [Document](https://python.langchain.com/api_reference/core/documents/langchain_core.documents.base.Document.html) format that we use downstream. Web pages contain text, images, and other multimedia elements, and are typically represented with HTML. They may include links to other pages or resources.\n",
     "\n",
     "LangChain integrates with a host of parsers that are appropriate for web pages. The right parser will depend on your needs. Below we demonstrate two possibilities:\n",
     "\n",

docs/docs/how_to/ensemble_retriever.ipynb

@@ -6,7 +6,7 @@
    "source": [
     "# How to combine results from multiple retrievers\n",
     "\n",
-    "The [EnsembleRetriever](https://python.langchain.com/api_reference/langchain/retrievers/langchain.retrievers.ensemble.EnsembleRetriever.html) supports ensembling of results from multiple retrievers. It is initialized with a list of [BaseRetriever](https://python.langchain.com/api_reference/core/retrievers/langchain_core.retrievers.BaseRetriever.html) objects. EnsembleRetrievers rerank the results of the constituent retrievers based on the [Reciprocal Rank Fusion](https://plg.uwaterloo.ca/~gvcormac/cormacksigir09-rrf.pdf) algorithm.\n",
+    "The [EnsembleRetriever](https://python.langchain.com/api_reference/langchain/retrievers/langchain.retrievers.ensemble.EnsembleRetriever.html) supports ensembling of results from multiple [retrievers](/docs/concepts/retrievers/). It is initialized with a list of [BaseRetriever](https://python.langchain.com/api_reference/core/retrievers/langchain_core.retrievers.BaseRetriever.html) objects. EnsembleRetrievers rerank the results of the constituent retrievers based on the [Reciprocal Rank Fusion](https://plg.uwaterloo.ca/~gvcormac/cormacksigir09-rrf.pdf) algorithm.\n",
     "\n",
     "By leveraging the strengths of different algorithms, the `EnsembleRetriever` can achieve better performance than any single algorithm. \n",
     "\n",

docs/docs/how_to/example_selectors.ipynb

@@ -17,7 +17,7 @@
    "source": [
     "# How to use example selectors\n",
     "\n",
-    "If you have a large number of examples, you may need to select which ones to include in the prompt. The Example Selector is the class responsible for doing so.\n",
+    "If you have a large number of examples, you may need to select which ones to include in the prompt. The [Example Selector](/docs/concepts/example_selectors/) is the class responsible for doing so.\n",
     "\n",
     "The base interface is defined as below:\n",
     "\n",
@@ -36,7 +36,7 @@
     "\n",
     "The only method it needs to define is a ``select_examples`` method. This takes in the input variables and then returns a list of examples. It is up to each specific implementation as to how those examples are selected.\n",
     "\n",
-    "LangChain has a few different types of example selectors. For an overview of all these types, see the below table.\n",
+    "LangChain has a few different types of example selectors. For an overview of all these types, see the [below table](#example-selector-types).\n",
     "\n",
     "In this guide, we will walk through creating a custom example selector."
    ]

docs/docs/how_to/example_selectors_langsmith.ipynb

@@ -23,7 +23,7 @@
     "]} />\n",
     "\n",
     "\n",
-    "LangSmith datasets have built-in support for similarity search, making them a great tool for building and querying few-shot examples.\n",
+    "[LangSmith](https://docs.smith.langchain.com/) datasets have built-in support for similarity search, making them a great tool for building and querying few-shot examples.\n",
     "\n",
     "In this guide we'll see how to use an indexed LangSmith dataset as a few-shot example selector.\n",
     "\n",

docs/docs/how_to/example_selectors_length_based.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# How to select examples by length\n",
     "\n",
-    "This example selector selects which examples to use based on length. This is useful when you are worried about constructing a prompt that will go over the length of the context window. For longer inputs, it will select fewer examples to include, while for shorter inputs it will select more."
+    "This [example selector](/docs/concepts/example_selectors/) selects which examples to use based on length. This is useful when you are worried about constructing a prompt that will go over the length of the context window. For longer inputs, it will select fewer examples to include, while for shorter inputs it will select more."
    ]
   },
   {

docs/docs/how_to/example_selectors_mmr.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# How to select examples by maximal marginal relevance (MMR)\n",
     "\n",
-    "The `MaxMarginalRelevanceExampleSelector` selects examples based on a combination of which examples are most similar to the inputs, while also optimizing for diversity. It does this by finding the examples with the embeddings that have the greatest cosine similarity with the inputs, and then iteratively adding them while penalizing them for closeness to already selected examples.\n"
+    "The `MaxMarginalRelevanceExampleSelector` selects [examples](/docs/concepts/example_selectors/) based on a combination of which examples are most similar to the inputs, while also optimizing for diversity. It does this by finding the examples with the embeddings that have the greatest cosine similarity with the inputs, and then iteratively adding them while penalizing them for closeness to already selected examples.\n"
    ]
   },
   {

docs/docs/how_to/example_selectors_ngram.ipynb

@@ -9,7 +9,7 @@
     "\n",
     "The `NGramOverlapExampleSelector` selects and orders examples based on which examples are most similar to the input, according to an ngram overlap score. The ngram overlap score is a float between 0.0 and 1.0, inclusive. \n",
     "\n",
-    "The selector allows for a threshold score to be set. Examples with an ngram overlap score less than or equal to the threshold are excluded. The threshold is set to -1.0, by default, so will not exclude any examples, only reorder them. Setting the threshold to 0.0 will exclude examples that have no ngram overlaps with the input.\n"
+    "The [selector](/docs/concepts/example_selectors/) allows for a threshold score to be set. Examples with an ngram overlap score less than or equal to the threshold are excluded. The threshold is set to -1.0, by default, so will not exclude any examples, only reorder them. Setting the threshold to 0.0 will exclude examples that have no ngram overlaps with the input.\n"
    ]
   },
   {

docs/docs/how_to/example_selectors_similarity.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# How to select examples by similarity\n",
     "\n",
-    "This object selects examples based on similarity to the inputs. It does this by finding the examples with the embeddings that have the greatest cosine similarity with the inputs.\n"
+    "This object selects [examples](/docs/concepts/example_selectors/) based on similarity to the inputs. It does this by finding the examples with the embeddings that have the greatest cosine similarity with the inputs.\n"
    ]
   },
   {

docs/docs/how_to/extraction_examples.ipynb

@@ -9,7 +9,7 @@
     "\n",
     "The quality of extractions can often be improved by providing reference examples to the LLM.\n",
     "\n",
-    "Data extraction attempts to generate structured representations of information found in text and other unstructured or semi-structured formats. [Tool-calling](/docs/concepts/tool_calling) LLM features are often used in this context. This guide demonstrates how to build few-shot examples of tool calls to help steer the behavior of extraction and similar applications.\n",
+    "Data extraction attempts to generate [structured representations](/docs/concepts/structured_outputs/) of information found in text and other unstructured or semi-structured formats. [Tool-calling](/docs/concepts/tool_calling) LLM features are often used in this context. This guide demonstrates how to build few-shot examples of tool calls to help steer the behavior of extraction and similar applications.\n",
     "\n",
     ":::tip\n",
     "While this guide focuses how to use examples with a tool calling model, this technique is generally applicable, and will work\n",

docs/docs/how_to/extraction_parse.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# How to use prompting alone (no tool calling) to do extraction\n",
     "\n",
-    "Tool calling features are not required for generating structured output from LLMs. LLMs that are able to follow prompt instructions well can be tasked with outputting information in a given format.\n",
+    "[Tool calling](/docs/concepts/tool_calling/) features are not required for generating structured output from LLMs. LLMs that are able to follow prompt instructions well can be tasked with outputting information in a given format.\n",
     "\n",
     "This approach relies on designing good prompts and then parsing the output of the LLMs to make them extract information well.\n",
     "\n",

docs/docs/how_to/few_shot_examples.ipynb

@@ -27,7 +27,7 @@
     "\n",
     ":::\n",
     "\n",
-    "In this guide, we'll learn how to create a simple prompt template that provides the model with example inputs and outputs when generating. Providing the LLM with a few such examples is called few-shotting, and is a simple yet powerful way to guide generation and in some cases drastically improve model performance.\n",
+    "In this guide, we'll learn how to create a simple prompt template that provides the model with example inputs and outputs when generating. Providing the LLM with a few such examples is called [few-shotting](/docs/concepts/few_shot_prompting/), and is a simple yet powerful way to guide generation and in some cases drastically improve model performance.\n",
     "\n",
     "A few-shot prompt template can be constructed from either a set of examples, or from an [Example Selector](https://python.langchain.com/api_reference/core/example_selectors/langchain_core.example_selectors.base.BaseExampleSelector.html) class responsible for choosing a subset of examples from the defined set.\n",
     "\n",

docs/docs/how_to/few_shot_examples_chat.ipynb

@@ -27,7 +27,7 @@
     "\n",
     ":::\n",
     "\n",
-    "This guide covers how to prompt a chat model with example inputs and outputs. Providing the model with a few such examples is called few-shotting, and is a simple yet powerful way to guide generation and in some cases drastically improve model performance.\n",
+    "This guide covers how to prompt a chat model with example inputs and outputs. Providing the model with a few such examples is called [few-shotting](/docs/concepts/few_shot_prompting/), and is a simple yet powerful way to guide generation and in some cases drastically improve model performance.\n",
     "\n",
     "There does not appear to be solid consensus on how best to do few-shot prompting, and the optimal prompt compilation will likely vary by model. Because of this, we provide few-shot prompt templates like the [FewShotChatMessagePromptTemplate](https://python.langchain.com/api_reference/core/prompts/langchain_core.prompts.few_shot.FewShotChatMessagePromptTemplate.html?highlight=fewshot#langchain_core.prompts.few_shot.FewShotChatMessagePromptTemplate) as a flexible starting point, and you can modify or replace them as you see fit.\n",
     "\n",

docs/docs/how_to/filter_messages.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# How to filter messages\n",
     "\n",
-    "In more complex chains and agents we might track state with a list of messages. This list can start to accumulate messages from multiple different models, speakers, sub-chains, etc., and we may only want to pass subsets of this full list of messages to each model call in the chain/agent.\n",
+    "In more complex chains and agents we might track state with a list of [messages](/docs/concepts/messages/). This list can start to accumulate messages from multiple different models, speakers, sub-chains, etc., and we may only want to pass subsets of this full list of messages to each model call in the chain/agent.\n",
     "\n",
     "The `filter_messages` utility makes it easy to filter messages by type, id, or name.\n",
     "\n",

docs/docs/how_to/graph_constructing.ipynb

@@ -15,7 +15,7 @@
    "source": [
     "# How to construct knowledge graphs\n",
     "\n",
-    "In this guide we'll go over the basic ways of constructing a knowledge graph based on unstructured text. The constructured graph can then be used as knowledge base in a RAG application.\n",
+    "In this guide we'll go over the basic ways of constructing a knowledge graph based on unstructured text. The constructured graph can then be used as knowledge base in a [RAG](/docs/concepts/rag/) application.\n",
     "\n",
     "## ⚠️ Security note ⚠️\n",
     "\n",
@@ -44,6 +44,9 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
+      "\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m24.0\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.3.1\u001b[0m\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
       "Note: you may need to restart the kernel to use updated packages.\n"
      ]
     }
@@ -65,7 +68,7 @@
    "metadata": {},
    "outputs": [
     {
-     "name": "stdin",
+     "name": "stdout",
      "output_type": "stream",
      "text": [
       " ········\n"
@@ -105,7 +108,7 @@
     "os.environ[\"NEO4J_USERNAME\"] = \"neo4j\"\n",
     "os.environ[\"NEO4J_PASSWORD\"] = \"password\"\n",
     "\n",
-    "graph = Neo4jGraph()"
+    "graph = Neo4jGraph(refresh_schema=False)"
    ]
   },
   {
@@ -149,8 +152,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Nodes:[Node(id='Marie Curie', type='Person'), Node(id='Pierre Curie', type='Person'), Node(id='University Of Paris', type='Organization')]\n",
-      "Relationships:[Relationship(source=Node(id='Marie Curie', type='Person'), target=Node(id='Pierre Curie', type='Person'), type='MARRIED'), Relationship(source=Node(id='Marie Curie', type='Person'), target=Node(id='University Of Paris', type='Organization'), type='PROFESSOR')]\n"
+      "Nodes:[Node(id='Marie Curie', type='Person', properties={}), Node(id='Pierre Curie', type='Person', properties={}), Node(id='University Of Paris', type='Organization', properties={})]\n",
+      "Relationships:[Relationship(source=Node(id='Marie Curie', type='Person', properties={}), target=Node(id='Pierre Curie', type='Person', properties={}), type='MARRIED', properties={}), Relationship(source=Node(id='Marie Curie', type='Person', properties={}), target=Node(id='University Of Paris', type='Organization', properties={}), type='PROFESSOR', properties={})]\n"
      ]
     }
    ],
@@ -191,8 +194,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Nodes:[Node(id='Marie Curie', type='Person'), Node(id='Pierre Curie', type='Person'), Node(id='University Of Paris', type='Organization')]\n",
-      "Relationships:[Relationship(source=Node(id='Marie Curie', type='Person'), target=Node(id='Pierre Curie', type='Person'), type='SPOUSE'), Relationship(source=Node(id='Marie Curie', type='Person'), target=Node(id='University Of Paris', type='Organization'), type='WORKED_AT')]\n"
+      "Nodes:[Node(id='Marie Curie', type='Person', properties={}), Node(id='Pierre Curie', type='Person', properties={}), Node(id='University Of Paris', type='Organization', properties={})]\n",
+      "Relationships:[Relationship(source=Node(id='Marie Curie', type='Person', properties={}), target=Node(id='Pierre Curie', type='Person', properties={}), type='SPOUSE', properties={}), Relationship(source=Node(id='Marie Curie', type='Person', properties={}), target=Node(id='University Of Paris', type='Organization', properties={}), type='WORKED_AT', properties={})]\n"
      ]
     }
    ],
@@ -209,6 +212,44 @@
     "print(f\"Relationships:{graph_documents_filtered[0].relationships}\")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "To define the graph schema more precisely, consider using a three-tuple approach for relationships. In this approach, each tuple consists of three elements: the source node, the relationship type, and the target node."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Nodes:[Node(id='Marie Curie', type='Person', properties={}), Node(id='Pierre Curie', type='Person', properties={}), Node(id='University Of Paris', type='Organization', properties={})]\n",
+      "Relationships:[Relationship(source=Node(id='Marie Curie', type='Person', properties={}), target=Node(id='Pierre Curie', type='Person', properties={}), type='SPOUSE', properties={}), Relationship(source=Node(id='Marie Curie', type='Person', properties={}), target=Node(id='University Of Paris', type='Organization', properties={}), type='WORKED_AT', properties={})]\n"
+     ]
+    }
+   ],
+   "source": [
+    "allowed_relationships = [\n",
+    "    (\"Person\", \"SPOUSE\", \"Person\"),\n",
+    "    (\"Person\", \"NATIONALITY\", \"Country\"),\n",
+    "    (\"Person\", \"WORKED_AT\", \"Organization\"),\n",
+    "]\n",
+    "\n",
+    "llm_transformer_tuple = LLMGraphTransformer(\n",
+    "    llm=llm,\n",
+    "    allowed_nodes=[\"Person\", \"Country\", \"Organization\"],\n",
+    "    allowed_relationships=allowed_relationships,\n",
+    ")\n",
+    "llm_transformer_tuple = llm_transformer_filtered.convert_to_graph_documents(documents)\n",
+    "print(f\"Nodes:{graph_documents_filtered[0].nodes}\")\n",
+    "print(f\"Relationships:{graph_documents_filtered[0].relationships}\")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -229,15 +270,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Nodes:[Node(id='Marie Curie', type='Person', properties={'born_year': '1867'}), Node(id='Pierre Curie', type='Person'), Node(id='University Of Paris', type='Organization')]\n",
-      "Relationships:[Relationship(source=Node(id='Marie Curie', type='Person'), target=Node(id='Pierre Curie', type='Person'), type='SPOUSE'), Relationship(source=Node(id='Marie Curie', type='Person'), target=Node(id='University Of Paris', type='Organization'), type='WORKED_AT')]\n"
+      "Nodes:[Node(id='Marie Curie', type='Person', properties={'born_year': '1867'}), Node(id='Pierre Curie', type='Person', properties={}), Node(id='University Of Paris', type='Organization', properties={}), Node(id='Poland', type='Country', properties={}), Node(id='France', type='Country', properties={})]\n",
+      "Relationships:[Relationship(source=Node(id='Marie Curie', type='Person', properties={}), target=Node(id='Poland', type='Country', properties={}), type='NATIONALITY', properties={}), Relationship(source=Node(id='Marie Curie', type='Person', properties={}), target=Node(id='France', type='Country', properties={}), type='NATIONALITY', properties={}), Relationship(source=Node(id='Marie Curie', type='Person', properties={}), target=Node(id='Pierre Curie', type='Person', properties={}), type='SPOUSE', properties={}), Relationship(source=Node(id='Marie Curie', type='Person', properties={}), target=Node(id='University Of Paris', type='Organization', properties={}), type='WORKED_AT', properties={})]\n"
      ]
     }
    ],
@@ -264,12 +305,71 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
     "graph.add_graph_documents(graph_documents_props)"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Most graph databases support indexes to optimize data import and retrieval. Since we might not know all the node labels in advance, we can handle this by adding a secondary base label to each node using the `baseEntityLabel` parameter."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "graph.add_graph_documents(graph_documents, baseEntityLabel=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Results will look like:\n",
+    "\n",
+    "![graph_construction3.png](../../static/img/graph_construction3.png)\n",
+    "\n",
+    "The final option is to also import the source documents for the extracted nodes and relationships. This approach lets us track which documents each entity appeared in."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "graph.add_graph_documents(graph_documents, include_source=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Graph will have the following structure:\n",
+    "\n",
+    "![graph_construction4.png](../../static/img/graph_construction4.png)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "In this visualization, the source document is highlighted in blue, with all entities extracted from it connected by `MENTIONS` relationships."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
@@ -288,7 +388,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.1"
+   "version": "3.11.5"
   }
  },
  "nbformat": 4,

docs/docs/how_to/hybrid.ipynb

@@ -9,7 +9,7 @@
    "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, 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",
+    "The standard search in LangChain is done by vector similarity. However, a number of [vector store](/docs/integrations/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",

docs/docs/how_to/index.mdx

@@ -74,6 +74,7 @@ These are the core building blocks you can use when building applications.
 ### Chat models
 
 [Chat Models](/docs/concepts/chat_models) are newer forms of language models that take messages in and output a message.
+See [supported integrations](/docs/integrations/chat/) for details on getting started with chat models from a specific provider.
 
 - [How to: do function/tool calling](/docs/how_to/tool_calling)
 - [How to: get models to return structured output](/docs/how_to/structured_output)
@@ -114,6 +115,7 @@ What LangChain calls [LLMs](/docs/concepts/text_llms) are older forms of languag
 
 [Output Parsers](/docs/concepts/output_parsers) are responsible for taking the output of an LLM and parsing into more structured format.
 
+- [How to: parse text from message objects](/docs/how_to/output_parser_string)
 - [How to: use output parsers to parse an LLM response into structured format](/docs/how_to/output_parser_structured)
 - [How to: parse JSON output](/docs/how_to/output_parser_json)
 - [How to: parse XML output](/docs/how_to/output_parser_xml)
@@ -153,6 +155,7 @@ What LangChain calls [LLMs](/docs/concepts/text_llms) are older forms of languag
 ### Embedding models
 
 [Embedding Models](/docs/concepts/embedding_models) take a piece of text and create a numerical representation of it.
+See [supported integrations](/docs/integrations/text_embedding/) for details on getting started with embedding models from a specific provider.
 
 - [How to: embed text data](/docs/how_to/embed_text)
 - [How to: cache embedding results](/docs/how_to/caching_embeddings)
@@ -160,6 +163,7 @@ What LangChain calls [LLMs](/docs/concepts/text_llms) are older forms of languag
 ### Vector stores
 
 [Vector stores](/docs/concepts/vectorstores) are databases that can efficiently store and retrieve embeddings.
+See [supported integrations](/docs/integrations/vectorstores/) for details on getting started with vector stores from a specific provider.
 
 - [How to: use a vector store to retrieve data](/docs/how_to/vectorstores)
 

docs/docs/how_to/indexing.ipynb

@@ -9,7 +9,7 @@
     "\n",
     "Here, we will look at a basic indexing workflow using the LangChain indexing API. \n",
     "\n",
-    "The indexing API lets you load and keep in sync documents from any source into a vector store. Specifically, it helps:\n",
+    "The indexing API lets you load and keep in sync documents from any source into a [vector store](/docs/concepts/vectorstores/). Specifically, it helps:\n",
     "\n",
     "* Avoid writing duplicated content into the vector store\n",
     "* Avoid re-writing unchanged content\n",

docs/docs/how_to/lcel_cheatsheet.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# LangChain Expression Language Cheatsheet\n",
     "\n",
-    "This is a quick reference for all the most important LCEL primitives. For more advanced usage see the [LCEL how-to guides](/docs/how_to/#langchain-expression-language-lcel) and the [full API reference](https://python.langchain.com/api_reference/core/runnables/langchain_core.runnables.base.Runnable.html).\n",
+    "This is a quick reference for all the most important [LCEL](/docs/concepts/lcel/) primitives. For more advanced usage see the [LCEL how-to guides](/docs/how_to/#langchain-expression-language-lcel) and the [full API reference](https://python.langchain.com/api_reference/core/runnables/langchain_core.runnables.base.Runnable.html).\n",
     "\n",
     "### Invoke a runnable\n",
     "#### [Runnable.invoke()](https://python.langchain.com/api_reference/core/runnables/langchain_core.runnables.base.Runnable.html#langchain_core.runnables.base.Runnable.invoke) / [Runnable.ainvoke()](https://python.langchain.com/api_reference/core/runnables/langchain_core.runnables.base.Runnable.html#langchain_core.runnables.base.Runnable.ainvoke)"

docs/docs/how_to/llm_caching.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# How to cache LLM responses\n",
     "\n",
-    "LangChain provides an optional caching layer for LLMs. This is useful for two reasons:\n",
+    "LangChain provides an optional [caching](/docs/concepts/chat_models/#caching) layer for LLMs. This is useful for two reasons:\n",
     "\n",
     "It can save you money by reducing the number of API calls you make to the LLM provider, if you're often requesting the same completion multiple times.\n",
     "It can speed up your application by reducing the number of API calls you make to the LLM provider.\n"

docs/docs/how_to/llm_token_usage_tracking.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# How to track token usage for LLMs\n",
     "\n",
-    "Tracking token usage to calculate cost is an important part of putting your app in production. This guide goes over how to obtain this information from your LangChain model calls.\n",
+    "Tracking [token](/docs/concepts/tokens/) usage to calculate cost is an important part of putting your app in production. This guide goes over how to obtain this information from your LangChain model calls.\n",
     "\n",
     ":::info Prerequisites\n",
     "\n",

docs/docs/how_to/logprobs.ipynb

@@ -11,10 +11,11 @@
     "\n",
     "This guide assumes familiarity with the following concepts:\n",
     "- [Chat models](/docs/concepts/chat_models)\n",
+    "- [Tokens](/docs/concepts/tokens)\n",
     "\n",
     ":::\n",
     "\n",
-    "Certain chat models can be configured to return token-level log probabilities representing the likelihood of a given token. This guide walks through how to get this information in LangChain."
+    "Certain [chat models](/docs/concepts/chat_models/) can be configured to return token-level log probabilities representing the likelihood of a given token. This guide walks through how to get this information in LangChain."
    ]
   },
   {

docs/docs/how_to/merge_message_runs.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# How to merge consecutive messages of the same type\n",
     "\n",
-    "Certain models do not support passing in consecutive messages of the same type (a.k.a. \"runs\" of the same message type).\n",
+    "Certain models do not support passing in consecutive [messages](/docs/concepts/messages/) of the same type (a.k.a. \"runs\" of the same message type).\n",
     "\n",
     "The `merge_message_runs` utility makes it easy to merge consecutive messages of the same type.\n",
     "\n",

docs/docs/how_to/multi_vector.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# How to retrieve using multiple vectors per document\n",
     "\n",
-    "It can often be useful to store multiple vectors per document. There are multiple use cases where this is beneficial. For example, we can embed multiple chunks of a document and associate those embeddings with the parent document, allowing retriever hits on the chunks to return the larger document.\n",
+    "It can often be useful to store multiple [vectors](/docs/concepts/vectorstores/) per document. There are multiple use cases where this is beneficial. For example, we can [embed](/docs/concepts/embedding_models/) multiple chunks of a document and associate those embeddings with the parent document, allowing [retriever](/docs/concepts/retrievers/) hits on the chunks to return the larger document.\n",
     "\n",
     "LangChain implements a base [MultiVectorRetriever](https://python.langchain.com/api_reference/langchain/retrievers/langchain.retrievers.multi_vector.MultiVectorRetriever.html), which simplifies this process. Much of the complexity lies in how to create the multiple vectors per document. This notebook covers some of the common ways to create those vectors and use the `MultiVectorRetriever`.\n",
     "\n",
@@ -207,7 +207,7 @@
    "id": "cdef8339-f9fa-4b3b-955f-ad9dbdf2734f",
    "metadata": {},
    "source": [
-    "The default search type the retriever performs on the vector database is a similarity search. LangChain vector stores also support searching via [Max Marginal Relevance](https://python.langchain.com/api_reference/core/vectorstores/langchain_core.vectorstores.VectorStore.html#langchain_core.vectorstores.VectorStore.max_marginal_relevance_search). This can be controlled via the `search_type` parameter of the retriever:"
+    "The default search type the retriever performs on the vector database is a similarity search. LangChain vector stores also support searching via [Max Marginal Relevance](https://python.langchain.com/api_reference/core/vectorstores/langchain_core.vectorstores.base.VectorStore.html#langchain_core.vectorstores.base.VectorStore.max_marginal_relevance_search). This can be controlled via the `search_type` parameter of the retriever:"
    ]
   },
   {

docs/docs/how_to/multimodal_inputs.ipynb

@@ -7,11 +7,11 @@
    "source": [
     "# How to pass multimodal data directly to models\n",
     "\n",
-    "Here we demonstrate how to pass multimodal input directly to models. \n",
+    "Here we demonstrate how to pass [multimodal](/docs/concepts/multimodality/) input directly to models. \n",
     "We currently expect all input to be passed in the same format as [OpenAI expects](https://platform.openai.com/docs/guides/vision).\n",
     "For other model providers that support multimodal input, we have added logic inside the class to convert to the expected format.\n",
     "\n",
-    "In this example we will ask a model to describe an image."
+    "In this example we will ask a [model](/docs/concepts/chat_models/#multimodality) to describe an image."
    ]
   },
   {

docs/docs/how_to/multimodal_prompts.ipynb

@@ -7,9 +7,9 @@
    "source": [
     "# How to use multimodal prompts\n",
     "\n",
-    "Here we demonstrate how to use prompt templates to format multimodal inputs to models. \n",
+    "Here we demonstrate how to use prompt templates to format [multimodal](/docs/concepts/multimodality/) inputs to models. \n",
     "\n",
-    "In this example we will ask a model to describe an image."
+    "In this example we will ask a [model](/docs/concepts/chat_models/#multimodality) to describe an image."
    ]
   },
   {