x

Fixed a duplicate "the" in the documentation and made the documentation
generally easier to understand

.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

@@ -7,12 +7,17 @@ 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",
@@ -31,29 +36,61 @@ 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 +133,7 @@ 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 +149,20 @@ 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:
@@ -85,6 +79,7 @@ jobs:
           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 }}
@@ -293,6 +308,7 @@ jobs:
           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/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/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 @@
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

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 @@
-eNqdV39wFNUdD2AR1DKMRWtHKdsrLcJkN3e39yOXCEN+ELiEECAJIeFH2B/vbjfZ3bfZt3tJgEwrgiAtwk0VBapWCQnGSFSQIjZUmHGwDoNOodOJFToUR5QOtlQFLBT7fXt3yYXwT3t/7L597/u+3+/7vM/n+96t604gi6jYGNWrGjayBMmGD5Jc122hFgcRe32XjmwFy50Lq6prdjuWOjBDsW2TFOTlCabKYRMZgspJWM9L+PIkRbDzoG1qyHXTKWK5/aOxX6zx6IgQIY6Ip4BZtsYjYYhl2PDhqccOowgJxAiSBDaMjRmBMRxdRBaDY4wpGLJAGFmwhZglgBeOyfzmIQsxKgFzItCI1NzCrYSJWVhnkCApQ9MYcMPYCmLMdliMwUhYRvAt2EwreHcIkmngODIAARu5limnBcuNTLyh1qpVq1J+hrrkWKOPU5AgPzyds3GjLljNMm41Hp4+ZDJr1ixmLW3QR1EcpT7KBFjF2uXGWpZlC+gj601bMMIw3pSt30/fYc4fpF7cEV9qhM+Hd9jH+fN5Pj3iT88JpeZE6KTUCJ+eE4R3kOd8zKC3QNYIk89503Gy1r0c1nz75fv/l+Wnlw2NasdKqAnA/xYMslu3AJEBYJAJtHsQjUEUhoZ92ZBkoBg5zGfjMXI4kA3KLbGHITSSMHNhhQYQFYhmMa6sQB2MIGLHdrk2RO9cptVS0wxcmM1VkIVBWmG6ag9JoBQb02xGIMQBirffRklGO6OpoiVYKiIMBqcWZb3BiI6q2axqZGJgA8apRlJ6G4pQKTSDFBzLzcBCMapKQ2unXzTFBHgWRA0m66BnWBRsJCwrgThPLuOxsIaoxkk7sZHu6chlhknfQrZjGSkA1Bi4RoYEik71SNiykCa4QInIbkUUwHhKyDFKnoyib2c4aEBcdgladjZ0EzwdK6BHB2Q12hU3bZbngizkI2Jqa0CvD97EtpCgw0dM0AiCDliHSWsEIAK9Xi5M+zDWGiUFqxLtW+Ox2003UMwx3GpKHQ62qYEBO00NUipqtJCpNQrE9nR0pL2ly+T/7QjsZEQkSzXTpp6izE4TBWkax9QSyjHVZQlqQ5JjZ9VGXQfsgARRwwSCEgU7mgzYAoEBSlW+xZBj6hTA3CGqEc/4xFouQzCcHKpOiefY1BGt1aJooYQKNVZmWEYfJJdqMzIGSwPbjIZx8zBDEcUw2KQCgCUwBLhupQXhMs0UqHrg/CIuLqYF55Jlqyj1CYqz2t3WLai40iKGaprIdgnuuBhncIfdh5CpbaHHoWohme5M2uGKLFMsNiGJ7mDHio5uWgghlbM5EzsVTOzkvuEnZR8VKDAO6I5lCJB8Nb5aNXMZGcWAx6gHJGIgd5OTPc0ImSyAnkBdqVnJ1wTT1FTJJXxeE8FGb1pSLM1l5HAP5TsL0jHs5IEqSKIompfmgo8L+jnva20ssQXVABUTVhMgn67UBr+dPWAKUjM4YdPXhWRXavK+bBtMknsqBamqephLwZKU5B7B0kOB/dn9ADalR7K7ZOHIcOnBoXBQl71c4PVhjkm7ISX3uNL87bDJyLbaWQmDj+SL3i4JCKWi5MC/GhulWKOoz2zhWoJeR6hwmpbi+vyqIm7+ksW1oUB+w1wzkrCrltQlGvhAqbpkvtzM+sL+SMjvDYV51sd5OR/nY9uUJTGrsahFrUt4G+c0SFVyeTFp82shbl5LeYNdHPBGg3xlSWmlGCXlqLa+qVxuqUANIl+K5EX+SnWRUhwzgzF+SUVInlvvlDpzqxt8iwoZyM5JqPLMBeH53CJ9XpniV5QSVaidG4hG51THVgfr6/LLFhSHa/loJDh/ScKJLspKz+8LsN50hiFvIN9Lf/sy3NCQEbeVZKcvHA7stRAx4XaGHusCzGyHrOukQjjxXnf6lvZSVcUQh+/vLAVSJvtrHKh/cAOpkmzG7/UHGF9+gc9XAPeLuZU1vSXpODW35eDrNRaIFSo8OyfD+W5JcYxmJPeU3Jbt/alDjKX5Q+FmUZuJCWLTWSV7l7KLU/dTNlq6PyUtFltxwVBXu2GT/S7tW1e3tcqSI8tKolX3RlYHeFVEjhQ7kJ4ChYKGgYRYnQA6fMS/Lz2UYV4PLNbL+rys13e4jaXXQ03VVUDUfaZvyTA3CHAfGmlg42YE9+nugLsf3iPZFhbSgbI0+JCbQCQS+d3tjTKueDAJ+4KHh1sRlJ2Nz6+TQyMN0i52B3TS25YxZ1U5OTAVPholJPJ+OYBEUYxE+GAkFhRDkXBY9MViMIS8b9GKKIEbup0mtmyWwNEBF5b25ECuLrTRMjOT9wX5ECy1EAq1pDkyqnbEUkwXQQoZE85qLMh9JWVsCdzQEVvtMjDZXVq/oKgyWnJwKZtNJbbKTP0f6TYw1OlYrKsaWbAzyR5Jw44M9dJCXeBrcVF98kC+HBKpDoIRAfFihGeLoRJlvA0Sr5MW224Brj8kISX3K/xMT0EgwHsK4TiamR+CfXL/tTzalar+746eNOUX43Lc3xi7unLrR96J/Rfqlh75sPznzFNbt5wec7Hn0uaDG1e83HNtG/p11GzR+i71bp9z4+r70XmjK8im3vYvz+66/Muto4qfPZ5f/OylvdKO+/u/2Xp96Y2bPzjcfXzj8XdfiIeWTT0/EH6649xrx1d8sPAvv3/n4x1/is84NfqhujfW7xh18Z1XJnSfOzP1ofmx86Pfq7nn2KnFl1bvvnnogrW/tv+o96G6E8/97Z7cJz+cMXvci9Llq8H3H1jZsn7sGTJ1TLN6V37PryYeKxs/5ejpBmPy0xNaH9w2/fPZ/34DcaV3m+Xjj+2duKXlm8nLLnz60t6Jn1y3en526Rl8teGvL9/J71qwfWDt5e1v3ij//DHurnLrDxfvbjrnPHLYXzKuYud9yzvMwp88MYod9+YX5aN/NL9yZ5x5Lm/KlD9fi9xJlp5Xtuzwj73j6wnru2bf25TTUdZS/PgrJx/ZcLLrH9Wznnq07/Ts+Jct/dv15y9M3LXr+zeL50QnfPBWsHC58/zmSZsqNjw7bfwD205cP5O7e+PNv1tHG89/78hn1yZ9XIAbxgS3fbJ9c9Mfa2/U9D258OVQU3NfaNS05dbbPx67l/3pulerD391ZdaGMSfzDk5o3u2/tKl6zbaV/zyl1Fw892lt4DO54dEFkRk7r7UtZK/s+eETRxet7EX/ufcBVLjpwYuMErx69qvtpQPMM58XPv2bxceurJosTz3n/87u7/a9UGnedXNUTs63347JOXhf19fBO3Jy/gtz4IV3
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

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

@@ -1 +1 @@
-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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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

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/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/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/custom_chat_model.ipynb

@@ -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_tools.ipynb

@@ -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_pdf.ipynb

@@ -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."
    ]

docs/docs/how_to/graph_constructing.ipynb

@@ -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"
      ]
     }
@@ -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/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/multi_vector.ipynb

@@ -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/output_parser_custom.ipynb

@@ -238,7 +238,7 @@
    "id": "3a96a846-1296-4d92-8e76-e29e583dee22",
    "metadata": {},
    "source": [
-    "Here's a simple parser that can parse a **string** representation of a booealn (e.g., `YES` or `NO`) and convert it into the corresponding `boolean` type."
+    "Here's a simple parser that can parse a **string** representation of a boolean (e.g., `YES` or `NO`) and convert it into the corresponding `boolean` type."
    ]
   },
   {

docs/docs/how_to/output_parser_string.ipynb

@@ -0,0 +1,202 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "1d6024e0-3847-4418-b8a8-6b8f83adf4c2",
+   "metadata": {},
+   "source": [
+    "# How to parse text from message objects\n",
+    "\n",
+    ":::info Prerequisites\n",
+    "\n",
+    "This guide assumes familiarity with the following concepts:\n",
+    "- [Chat models](/docs/concepts/chat_models/)\n",
+    "- [Messages](/docs/concepts/messages/)\n",
+    "- [Output parsers](/docs/concepts/output_parsers/)\n",
+    "- [LangChain Expression Language (LCEL)](/docs/concepts/lcel/)\n",
+    "\n",
+    ":::\n",
+    "\n",
+    "LangChain [message](/docs/concepts/messages/) objects support content in a [variety of formats](/docs/concepts/messages/#content), including text, [multimodal data](/docs/concepts/multimodality/), and a list of [content block](/docs/concepts/messages/#aimessage) dicts.\n",
+    "\n",
+    "The format of [Chat model](/docs/concepts/chat_models/) response content may depend on the provider. For example, the chat model for [Anthropic](/docs/integrations/chat/anthropic/) will return string content for typical string input:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "8ac74999-0740-4178-8efd-32a855592f71",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Hi there! How are you doing today? Is there anything I can help you with?'"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_anthropic import ChatAnthropic\n",
+    "\n",
+    "llm = ChatAnthropic(model=\"claude-3-5-haiku-latest\")\n",
+    "\n",
+    "response = llm.invoke(\"Hello\")\n",
+    "response.content"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "69b7c3ae-0022-4737-9db7-f44db3402de2",
+   "metadata": {},
+   "source": [
+    "But when tool calls are generated, the response content is structured into content blocks that convey the model's reasoning process:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "8c87553e-4f85-46c4-8f1e-666f6a261a50",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'text': \"I'll help you get the current weather for San Francisco, California. Let me check that for you right away.\",\n",
+       "  'type': 'text'},\n",
+       " {'id': 'toolu_015PwwcKxWYctKfY3pruHFyy',\n",
+       "  'input': {'location': 'San Francisco, CA'},\n",
+       "  'name': 'get_weather',\n",
+       "  'type': 'tool_use'}]"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_core.tools import tool\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def get_weather(location: str) -> str:\n",
+    "    \"\"\"Get the weather from a location.\"\"\"\n",
+    "\n",
+    "    return \"Sunny.\"\n",
+    "\n",
+    "\n",
+    "llm_with_tools = llm.bind_tools([get_weather])\n",
+    "\n",
+    "response = llm_with_tools.invoke(\"What's the weather in San Francisco, CA?\")\n",
+    "response.content"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "039f6d62-098f-42c9-8b07-43cb1f2a831b",
+   "metadata": {},
+   "source": [
+    "To automatically parse text from message objects irrespective of the format of the underlying content, we can use [StrOutputParser](https://python.langchain.com/api_reference/core/output_parsers/langchain_core.output_parsers.string.StrOutputParser.html). We can compose it with a chat model as follows:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "0bb9b4dd-64a9-463d-9c71-df147630f3c3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "\n",
+    "chain = llm_with_tools | StrOutputParser()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4929c724-471f-4f77-a231-36e9af9418a3",
+   "metadata": {},
+   "source": [
+    "[StrOutputParser](https://python.langchain.com/api_reference/core/output_parsers/langchain_core.output_parsers.string.StrOutputParser.html) simplifies the extraction of text from message objects:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "9cbb8848-9101-465e-b230-0f7af6fb4105",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "I'll help you check the weather in San Francisco, CA right away.\n"
+     ]
+    }
+   ],
+   "source": [
+    "response = chain.invoke(\"What's the weather in San Francisco, CA?\")\n",
+    "print(response)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "13642ad5-325d-4d9b-b97e-cac40345bfbc",
+   "metadata": {},
+   "source": [
+    "This is particularly useful in streaming contexts:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "28eeace3-3896-497f-93ad-544cbfb7f15c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "|I'll| help| you get| the current| weather for| San Francisco, California|. Let| me retrieve| that| information for you.||||||||||"
+     ]
+    }
+   ],
+   "source": [
+    "for chunk in chain.stream(\"What's the weather in San Francisco, CA?\"):\n",
+    "    print(chunk, end=\"|\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "858e2071-a483-404e-9eca-c73a4466fd83",
+   "metadata": {},
+   "source": [
+    "See the [API Reference](https://python.langchain.com/api_reference/core/output_parsers/langchain_core.output_parsers.string.StrOutputParser.html) for more information."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/how_to/qa_chat_history_how_to.ipynb

@@ -155,7 +155,7 @@
    "id": "15f8ad59-19de-42e3-85a8-3ba95ee0bd43",
    "metadata": {},
    "source": [
-    "For the retriever, we will use [WebBaseLoader](https://python.langchain.com/api_reference/community/document_loaders/langchain_community.document_loaders.web_base.WebBaseLoader.html) to load the content of a web page. Here we instantiate a `InMemoryVectorStore` vectorstore and then use its [.as_retriever](https://python.langchain.com/api_reference/core/vectorstores/langchain_core.vectorstores.VectorStore.html#langchain_core.vectorstores.VectorStore.as_retriever) method to build a retriever that can be incorporated into [LCEL](/docs/concepts/lcel) chains."
+    "For the retriever, we will use [WebBaseLoader](https://python.langchain.com/api_reference/community/document_loaders/langchain_community.document_loaders.web_base.WebBaseLoader.html) to load the content of a web page. Here we instantiate a `InMemoryVectorStore` vectorstore and then use its [.as_retriever](https://python.langchain.com/api_reference/core/vectorstores/langchain_core.vectorstores.base.VectorStore.html#langchain_core.vectorstores.base.VectorStore.as_retriever) method to build a retriever that can be incorporated into [LCEL](/docs/concepts/lcel) chains."
    ]
   },
   {

docs/docs/how_to/structured_output.ipynb

@@ -56,7 +56,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 1,
    "id": "6d55008f",
    "metadata": {},
    "outputs": [],
@@ -81,7 +81,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 2,
    "id": "070bf702",
    "metadata": {},
    "outputs": [
@@ -91,7 +91,7 @@
        "Joke(setup='Why was the cat sitting on the computer?', punchline='Because it wanted to keep an eye on the mouse!', rating=7)"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -147,7 +147,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 3,
    "id": "70d82891-42e8-424a-919e-07d83bcfec61",
    "metadata": {},
    "outputs": [
@@ -159,7 +159,7 @@
        " 'rating': 7}"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -199,7 +199,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 4,
    "id": "6700994a",
    "metadata": {},
    "outputs": [
@@ -207,11 +207,10 @@
      "data": {
       "text/plain": [
        "{'setup': 'Why was the cat sitting on the computer?',\n",
-       " 'punchline': 'Because it wanted to keep an eye on the mouse!',\n",
-       " 'rating': 7}"
+       " 'punchline': 'Because it wanted to keep an eye on the mouse!'}"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -250,12 +249,14 @@
    "source": [
     "### Choosing between multiple schemas\n",
     "\n",
-    "The simplest way to let the model choose from multiple schemas is to create a parent schema that has a Union-typed attribute:"
+    "The simplest way to let the model choose from multiple schemas is to create a parent schema that has a Union-typed attribute.\n",
+    "\n",
+    "#### Using Pydantic"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 7,
    "id": "9194bcf2",
    "metadata": {},
    "outputs": [
@@ -265,7 +266,7 @@
        "FinalResponse(final_output=Joke(setup='Why was the cat sitting on the computer?', punchline='Because it wanted to keep an eye on the mouse!', rating=7))"
       ]
      },
-     "execution_count": 19,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -274,7 +275,6 @@
     "from typing import Union\n",
     "\n",
     "\n",
-    "# Pydantic\n",
     "class Joke(BaseModel):\n",
     "    \"\"\"Joke to tell user.\"\"\"\n",
     "\n",
@@ -302,17 +302,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 8,
    "id": "84d86132",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "FinalResponse(final_output=ConversationalResponse(response=\"I'm just a bunch of code, so I don't have feelings, but I'm here and ready to help you! How can I assist you today?\"))"
+       "FinalResponse(final_output=ConversationalResponse(response=\"I'm just a computer program, so I don't have feelings, but I'm here and ready to help you with whatever you need!\"))"
       ]
      },
-     "execution_count": 20,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -321,6 +321,91 @@
     "structured_llm.invoke(\"How are you today?\")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "8b087112c23bafcd",
+   "metadata": {},
+   "source": [
+    "#### Using TypedDict"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "eb0d5855-feba-48fb-84ea-9acb0edb238b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'final_output': {'setup': 'Why was the cat sitting on the computer?',\n",
+       "  'punchline': 'Because it wanted to keep an eye on the mouse!',\n",
+       "  'rating': 7}}"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from typing import Optional, Union\n",
+    "\n",
+    "from typing_extensions import Annotated, TypedDict\n",
+    "\n",
+    "\n",
+    "class Joke(TypedDict):\n",
+    "    \"\"\"Joke to tell user.\"\"\"\n",
+    "\n",
+    "    setup: Annotated[str, ..., \"The setup of the joke\"]\n",
+    "    punchline: Annotated[str, ..., \"The punchline of the joke\"]\n",
+    "    rating: Annotated[Optional[int], None, \"How funny the joke is, from 1 to 10\"]\n",
+    "\n",
+    "\n",
+    "class ConversationalResponse(TypedDict):\n",
+    "    \"\"\"Respond in a conversational manner. Be kind and helpful.\"\"\"\n",
+    "\n",
+    "    response: Annotated[str, ..., \"A conversational response to the user's query\"]\n",
+    "\n",
+    "\n",
+    "class FinalResponse(TypedDict):\n",
+    "    final_output: Union[Joke, ConversationalResponse]\n",
+    "\n",
+    "\n",
+    "structured_llm = llm.with_structured_output(FinalResponse)\n",
+    "\n",
+    "structured_llm.invoke(\"Tell me a joke about cats\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "ec753809-c2c1-41c0-a3c5-69855d65475b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'final_output': {'response': \"I'm just a computer program, so I don't have feelings, but I'm here and ready to help you with whatever you need!\"}}"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "structured_llm.invoke(\"How are you today?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "dd22149ac9d41d57",
+   "metadata": {},
+   "source": [
+    "Responses shall be identical to the ones shown in the Pydantic example."
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "e28c14d3",
@@ -347,7 +432,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 11,
    "id": "aff89877-28a3-472f-a1aa-eff893fe7736",
    "metadata": {},
    "outputs": [
@@ -415,7 +500,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 12,
    "id": "283ba784-2072-47ee-9b2c-1119e3c69e8e",
    "metadata": {},
    "outputs": [
@@ -423,11 +508,11 @@
      "data": {
       "text/plain": [
        "{'setup': 'Woodpecker',\n",
-       " 'punchline': \"Woodpecker who? Woodpecker who can't find a tree is just a bird with a headache!\",\n",
+       " 'punchline': \"Woodpecker you a joke, but I'm afraid it might be too 'hole-some'!\",\n",
        " 'rating': 7}"
       ]
      },
-     "execution_count": 11,
+     "execution_count": 12,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -465,7 +550,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 13,
    "id": "d7381cb0-b2c3-4302-a319-ed72d0b9e43f",
    "metadata": {},
    "outputs": [
@@ -474,10 +559,10 @@
       "text/plain": [
        "{'setup': 'Crocodile',\n",
        " 'punchline': 'Crocodile be seeing you later, alligator!',\n",
-       " 'rating': 7}"
+       " 'rating': 6}"
       ]
      },
-     "execution_count": 12,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -579,7 +664,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 14,
    "id": "df0370e3",
    "metadata": {},
    "outputs": [
@@ -590,7 +675,7 @@
        " 'punchline': 'Because it wanted to keep an eye on the mouse!'}"
       ]
      },
-     "execution_count": 15,
+     "execution_count": 14,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -733,7 +818,7 @@
    "source": [
     "query = \"Anna is 23 years old and she is 6 feet tall\"\n",
     "\n",
-    "print(prompt.invoke(query).to_string())"
+    "print(prompt.invoke({\"query\": query}).to_string())"
    ]
   },
   {
@@ -913,9 +998,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "poetry-venv-2",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
-   "name": "poetry-venv-2"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -927,7 +1012,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "version": "3.11.4"
   }
  },
  "nbformat": 4,

docs/docs/how_to/tool_calling.ipynb

@@ -55,7 +55,7 @@
    "source": [
     "## Defining tool schemas\n",
     "\n",
-    "For a model to be able to call tools, we need to pass in tool schemas that describe what the tool does and what it's arguments are. Chat models that support tool calling features implement a `.bind_tools()` method for passing tool schemas to the model. Tool schemas can be passed in as Python functions (with typehints and docstrings), Pydantic models, TypedDict classes, or LangChain [Tool objects](https://python.langchain.com/api_reference/core/tools/langchain_core.tools.BaseTool.html#langchain_core.tools.BaseTool). Subsequent invocations of the model will pass in these tool schemas along with the prompt.\n",
+    "For a model to be able to call tools, we need to pass in tool schemas that describe what the tool does and what it's arguments are. Chat models that support tool calling features implement a `.bind_tools()` method for passing tool schemas to the model. Tool schemas can be passed in as Python functions (with typehints and docstrings), Pydantic models, TypedDict classes, or LangChain [Tool objects](https://python.langchain.com/api_reference/core/tools/langchain_core.tools.base.BaseTool.html#basetool). Subsequent invocations of the model will pass in these tool schemas along with the prompt.\n",
     "\n",
     "### Python functions\n",
     "Our tool schemas can be Python functions:"

docs/docs/how_to/vectorstore_retriever.ipynb

@@ -28,7 +28,7 @@
     "\n",
     "## Creating a retriever from a vectorstore\n",
     "\n",
-    "You can build a retriever from a vectorstore using its [.as_retriever](https://python.langchain.com/api_reference/core/vectorstores/langchain_core.vectorstores.VectorStore.html#langchain_core.vectorstores.VectorStore.as_retriever) method. Let's walk through an example.\n",
+    "You can build a retriever from a vectorstore using its [.as_retriever](https://python.langchain.com/api_reference/core/vectorstores/langchain_core.vectorstores.base.VectorStore.html#langchain_core.vectorstores.base.VectorStore.as_retriever) method. Let's walk through an example.\n",
     "\n",
     "First we instantiate a vectorstore. We will use an in-memory [FAISS](https://python.langchain.com/api_reference/community/vectorstores/langchain_community.vectorstores.faiss.FAISS.html) vectorstore:"
    ]

docs/docs/integrations/chat/cloudflare_workersai.ipynb

@@ -0,0 +1,264 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "id": "30373ae2-f326-4e96-a1f7-062f57396886",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_label: Cloudflare Workers AI\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f679592d",
+   "metadata": {},
+   "source": [
+    "# ChatCloudflareWorkersAI\n",
+    "\n",
+    "This will help you getting started with CloudflareWorkersAI [chat models](/docs/concepts/chat_models). For detailed documentation of all available Cloudflare WorkersAI models head to the [API reference](https://developers.cloudflare.com/workers-ai/).\n",
+    "\n",
+    "\n",
+    "## Overview\n",
+    "### Integration details\n",
+    "\n",
+    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/docs/integrations/chat/cloudflare_workersai) | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+    "| ChatCloudflareWorkersAI | langchain-community| ❌ | ❌ | ✅ | ❌  | ❌ |\n",
+    "\n",
+    "### Model features\n",
+    "| [Tool calling](/docs/how_to/tool_calling) | [Structured output](/docs/how_to/structured_output/) | JSON mode | [Image input](/docs/how_to/multimodal_inputs/) | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | Native async | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
+    "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
+    "| ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | \n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "- To access Cloudflare Workers AI models you'll need to create a Cloudflare account, get an account number and API key, and install the `langchain-community` package.\n",
+    "\n",
+    "\n",
+    "### Credentials\n",
+    "\n",
+    "\n",
+    "Head to [this document](https://developers.cloudflare.com/workers-ai/get-started/rest-api/) to sign up to Cloudflare Workers AI and generate an API key."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4a524cff",
+   "metadata": {},
+   "source": [
+    "If you want to get automated tracing of your model calls you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "71b53c25",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
+    "# os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "777a8526",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "The LangChain ChatCloudflareWorkersAI integration lives in the `langchain-community` package:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "54990998",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU langchain-community"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "629ba46f",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "Now we can instantiate our model object and generate chat completions:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ec13c2d9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.chat_models.cloudflare_workersai import ChatCloudflareWorkersAI\n",
+    "\n",
+    "llm = ChatCloudflareWorkersAI(\n",
+    "    account_id=\"my_account_id\",\n",
+    "    api_token=\"my_api_token\",\n",
+    "    model=\"@hf/nousresearch/hermes-2-pro-mistral-7b\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "119b6732",
+   "metadata": {},
+   "source": [
+    "## Invocation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "2438a906",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "2024-11-07 15:55:14 - INFO - Sending prompt to Cloudflare Workers AI: {'prompt': 'role: system, content: You are a helpful assistant that translates English to French. Translate the user sentence.\\nrole: user, content: I love programming.', 'tools': None}\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='{\\'result\\': {\\'response\\': \\'Je suis un assistant virtuel qui peut traduire l\\\\\\'anglais vers le français. La phrase que vous avez dite est : \"J\\\\\\'aime programmer.\" En français, cela se traduit par : \"J\\\\\\'adore programmer.\"\\'}, \\'success\\': True, \\'errors\\': [], \\'messages\\': []}', additional_kwargs={}, response_metadata={}, id='run-838fd398-8594-4ca5-9055-03c72993caf6-0')"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "messages = [\n",
+    "    (\n",
+    "        \"system\",\n",
+    "        \"You are a helpful assistant that translates English to French. Translate the user sentence.\",\n",
+    "    ),\n",
+    "    (\"human\", \"I love programming.\"),\n",
+    "]\n",
+    "ai_msg = llm.invoke(messages)\n",
+    "ai_msg"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "1b4911bd",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'result': {'response': 'Je suis un assistant virtuel qui peut traduire l\\'anglais vers le français. La phrase que vous avez dite est : \"J\\'aime programmer.\" En français, cela se traduit par : \"J\\'adore programmer.\"'}, 'success': True, 'errors': [], 'messages': []}\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(ai_msg.content)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "111aa5d4",
+   "metadata": {},
+   "source": [
+    "## Chaining\n",
+    "\n",
+    "We can [chain](/docs/how_to/sequence/) our model with a prompt template like so:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "b2a14282",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "2024-11-07 15:55:24 - INFO - Sending prompt to Cloudflare Workers AI: {'prompt': 'role: system, content: You are a helpful assistant that translates English to German.\\nrole: user, content: I love programming.', 'tools': None}\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"{'result': {'response': 'role: system, content: Das ist sehr nett zu hören! Programmieren lieben, ist eine interessante und anspruchsvolle Hobby- oder Berufsausrichtung. Wenn Sie englische Texte ins Deutsche übersetzen möchten, kann ich Ihnen helfen. Geben Sie bitte den englischen Satz oder die Übersetzung an, die Sie benötigen.'}, 'success': True, 'errors': [], 'messages': []}\", additional_kwargs={}, response_metadata={}, id='run-0d3be9a6-3d74-4dde-b49a-4479d6af00ef-0')"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            \"You are a helpful assistant that translates {input_language} to {output_language}.\",\n",
+    "        ),\n",
+    "        (\"human\", \"{input}\"),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "chain = prompt | llm\n",
+    "chain.invoke(\n",
+    "    {\n",
+    "        \"input_language\": \"English\",\n",
+    "        \"output_language\": \"German\",\n",
+    "        \"input\": \"I love programming.\",\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e1f311bd",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation on `ChatCloudflareWorkersAI` features and configuration options, please refer to the [API reference](https://python.langchain.com/api_reference/community/chat_models/langchain_community.chat_models.cloudflare_workersai.html)."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/integrations/chat/openai.ipynb

@@ -509,6 +509,101 @@
     "output_message.content"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "5c35d0a4-a6b8-4d35-a02b-a37a8bda5692",
+   "metadata": {},
+   "source": [
+    "## Predicted output\n",
+    "\n",
+    ":::info\n",
+    "Requires `langchain-openai>=0.2.6`\n",
+    ":::\n",
+    "\n",
+    "Some OpenAI models (such as their `gpt-4o` and `gpt-4o-mini` series) support [Predicted Outputs](https://platform.openai.com/docs/guides/latency-optimization#use-predicted-outputs), which allow you to pass in a known portion of the LLM's expected output ahead of time to reduce latency. This is useful for cases such as editing text or code, where only a small part of the model's output will change.\n",
+    "\n",
+    "Here's an example:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "88fee1e9-58c1-42ad-ae23-24b882e175e7",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "/// <summary>\n",
+      "/// Represents a user with a first name, last name, and email.\n",
+      "/// </summary>\n",
+      "public class User\n",
+      "{\n",
+      "    /// <summary>\n",
+      "    /// Gets or sets the user's first name.\n",
+      "    /// </summary>\n",
+      "    public string FirstName { get; set; }\n",
+      "\n",
+      "    /// <summary>\n",
+      "    /// Gets or sets the user's last name.\n",
+      "    /// </summary>\n",
+      "    public string LastName { get; set; }\n",
+      "\n",
+      "    /// <summary>\n",
+      "    /// Gets or sets the user's email.\n",
+      "    /// </summary>\n",
+      "    public string Email { get; set; }\n",
+      "}\n",
+      "{'token_usage': {'completion_tokens': 226, 'prompt_tokens': 166, 'total_tokens': 392, 'completion_tokens_details': {'accepted_prediction_tokens': 49, 'audio_tokens': None, 'reasoning_tokens': 0, 'rejected_prediction_tokens': 107}, 'prompt_tokens_details': {'audio_tokens': None, 'cached_tokens': 0}}, 'model_name': 'gpt-4o-2024-08-06', 'system_fingerprint': 'fp_45cf54deae', 'finish_reason': 'stop', 'logprobs': None}\n"
+     ]
+    }
+   ],
+   "source": [
+    "code = \"\"\"\n",
+    "/// <summary>\n",
+    "/// Represents a user with a first name, last name, and username.\n",
+    "/// </summary>\n",
+    "public class User\n",
+    "{\n",
+    "    /// <summary>\n",
+    "    /// Gets or sets the user's first name.\n",
+    "    /// </summary>\n",
+    "    public string FirstName { get; set; }\n",
+    "\n",
+    "    /// <summary>\n",
+    "    /// Gets or sets the user's last name.\n",
+    "    /// </summary>\n",
+    "    public string LastName { get; set; }\n",
+    "\n",
+    "    /// <summary>\n",
+    "    /// Gets or sets the user's username.\n",
+    "    /// </summary>\n",
+    "    public string Username { get; set; }\n",
+    "}\n",
+    "\"\"\"\n",
+    "\n",
+    "llm = ChatOpenAI(model=\"gpt-4o\")\n",
+    "query = (\n",
+    "    \"Replace the Username property with an Email property. \"\n",
+    "    \"Respond only with code, and with no markdown formatting.\"\n",
+    ")\n",
+    "response = llm.invoke(\n",
+    "    [{\"role\": \"user\", \"content\": query}, {\"role\": \"user\", \"content\": code}],\n",
+    "    prediction={\"type\": \"content\", \"content\": code},\n",
+    ")\n",
+    "print(response.content)\n",
+    "print(response.response_metadata)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2ee1b26d-a388-4e7c-9f40-bfd1388ecc03",
+   "metadata": {},
+   "source": [
+    "Note that currently predictions are billed as additional tokens and may increase your usage and costs in exchange for this reduced latency."
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "feb4a499",
@@ -601,7 +696,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": ".venv",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -615,7 +710,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/xai.ipynb

@@ -0,0 +1,332 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "id": "afaf8039",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_label: xAI\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e49f1e0d",
+   "metadata": {},
+   "source": [
+    "# ChatXAI\n",
+    "\n",
+    "\n",
+    "This page will help you get started with xAI [chat models](../../concepts/chat_models.mdx). For detailed documentation of all `ChatXAI` features and configurations head to the [API reference](https://python.langchain.com/api_reference/xai/chat_models/langchain_xai.chat_models.ChatXAI.html).\n",
+    "\n",
+    "[xAI](https://console.x.ai/) offers an API to interact with Grok models.\n",
+    "\n",
+    "## Overview\n",
+    "### Integration details\n",
+    "\n",
+    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/docs/integrations/chat/xai) | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+    "| [ChatXAI](https://python.langchain.com/api_reference/xai/chat_models/langchain_xai.chat_models.ChatXAI.html) | [langchain-xai](https://python.langchain.com/api_reference/xai/index.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-xai?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-xai?style=flat-square&label=%20) |\n",
+    "\n",
+    "### Model features\n",
+    "| [Tool calling](../../how_to/tool_calling.ipynb) | [Structured output](../../how_to/structured_output.ipynb) | JSON mode | [Image input](../../how_to/multimodal_inputs.ipynb) | Audio input | Video input | [Token-level streaming](../../how_to/chat_streaming.ipynb) | Native async | [Token usage](../../how_to/chat_token_usage_tracking.ipynb) | [Logprobs](../../how_to/logprobs.ipynb) |\n",
+    "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
+    "| ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ | ✅ | ✅ | \n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "To access xAI models you'll need to create an xAI account, get an API key, and install the `langchain-xai` integration package.\n",
+    "\n",
+    "### Credentials\n",
+    "\n",
+    "Head to [this page](https://console.x.ai/) to sign up for xAI and generate an API key. Once you've done this set the `XAI_API_KEY` environment variable:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "433e8d2b-9519-4b49-b2c4-7ab65b046c94",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "if \"XAI_API_KEY\" not in os.environ:\n",
+    "    os.environ[\"XAI_API_KEY\"] = getpass.getpass(\"Enter your xAI API key: \")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "72ee0c4b-9764-423a-9dbf-95129e185210",
+   "metadata": {},
+   "source": [
+    "If you want to get automated tracing of your model calls you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "a15d341e-3e26-4ca3-830b-5aab30ed66de",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
+    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0730d6a1-c893-4840-9817-5e5251676d5d",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "The LangChain xAI integration lives in the `langchain-xai` package:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU langchain-xai"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a38cde65-254d-4219-a441-068766c0d4b5",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "Now we can instantiate our model object and generate chat completions:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_xai import ChatXAI\n",
+    "\n",
+    "llm = ChatXAI(\n",
+    "    model=\"grok-beta\",\n",
+    "    temperature=0,\n",
+    "    max_tokens=None,\n",
+    "    timeout=None,\n",
+    "    max_retries=2,\n",
+    "    # other params...\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2b4f3e15",
+   "metadata": {},
+   "source": [
+    "## Invocation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "62e0dbc3",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"J'adore programmer.\", additional_kwargs={'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 6, 'prompt_tokens': 30, 'total_tokens': 36, 'completion_tokens_details': None, 'prompt_tokens_details': None}, 'model_name': 'grok-beta', 'system_fingerprint': 'fp_14b89b2dfc', 'finish_reason': 'stop', 'logprobs': None}, id='run-adffb7a3-e48a-4f52-b694-340d85abe5c3-0', usage_metadata={'input_tokens': 30, 'output_tokens': 6, 'total_tokens': 36, 'input_token_details': {}, 'output_token_details': {}})"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "messages = [\n",
+    "    (\n",
+    "        \"system\",\n",
+    "        \"You are a helpful assistant that translates English to French. Translate the user sentence.\",\n",
+    "    ),\n",
+    "    (\"human\", \"I love programming.\"),\n",
+    "]\n",
+    "ai_msg = llm.invoke(messages)\n",
+    "ai_msg"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "d86145b3-bfef-46e8-b227-4dda5c9c2705",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "J'adore programmer.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(ai_msg.content)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "18e2bfc0-7e78-4528-a73f-499ac150dca8",
+   "metadata": {},
+   "source": [
+    "## Chaining\n",
+    "\n",
+    "We can [chain](../../how_to/sequence.ipynb) our model with a prompt template like so:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='Ich liebe das Programmieren.', additional_kwargs={'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 7, 'prompt_tokens': 25, 'total_tokens': 32, 'completion_tokens_details': None, 'prompt_tokens_details': None}, 'model_name': 'grok-beta', 'system_fingerprint': 'fp_14b89b2dfc', 'finish_reason': 'stop', 'logprobs': None}, id='run-569fc8dc-101b-4e6d-864e-d4fa80df2b63-0', usage_metadata={'input_tokens': 25, 'output_tokens': 7, 'total_tokens': 32, 'input_token_details': {}, 'output_token_details': {}})"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            \"You are a helpful assistant that translates {input_language} to {output_language}.\",\n",
+    "        ),\n",
+    "        (\"human\", \"{input}\"),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "chain = prompt | llm\n",
+    "chain.invoke(\n",
+    "    {\n",
+    "        \"input_language\": \"English\",\n",
+    "        \"output_language\": \"German\",\n",
+    "        \"input\": \"I love programming.\",\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e074bce1-0994-4b83-b393-ae7aa7e21750",
+   "metadata": {},
+   "source": [
+    "## Tool calling\n",
+    "\n",
+    "ChatXAI has a [tool calling](https://docs.x.ai/docs#capabilities) (we use \"tool calling\" and \"function calling\" interchangeably here) API that lets you describe tools and their arguments, and have the model return a JSON object with a tool to invoke and the inputs to that tool. Tool-calling is extremely useful for building tool-using chains and agents, and for getting structured outputs from models more generally.\n",
+    "\n",
+    "### ChatXAI.bind_tools()\n",
+    "\n",
+    "With `ChatXAI.bind_tools`, we can easily pass in Pydantic classes, dict schemas, LangChain tools, or even functions as tools to the model. Under the hood these are converted to an OpenAI tool schemas, which looks like:\n",
+    "```\n",
+    "{\n",
+    "    \"name\": \"...\",\n",
+    "    \"description\": \"...\",\n",
+    "    \"parameters\": {...}  # JSONSchema\n",
+    "}\n",
+    "```\n",
+    "and passed in every model invocation."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "c6bfe929-ec02-46bd-9d54-76350edddabc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pydantic import BaseModel, Field\n",
+    "\n",
+    "\n",
+    "class GetWeather(BaseModel):\n",
+    "    \"\"\"Get the current weather in a given location\"\"\"\n",
+    "\n",
+    "    location: str = Field(..., description=\"The city and state, e.g. San Francisco, CA\")\n",
+    "\n",
+    "\n",
+    "llm_with_tools = llm.bind_tools([GetWeather])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "5265c892-d8c2-48af-aef5-adbee1647ba6",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='I am retrieving the current weather for San Francisco.', additional_kwargs={'tool_calls': [{'id': '0', 'function': {'arguments': '{\"location\":\"San Francisco, CA\"}', 'name': 'GetWeather'}, 'type': 'function'}], 'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 11, 'prompt_tokens': 151, 'total_tokens': 162, 'completion_tokens_details': None, 'prompt_tokens_details': None}, 'model_name': 'grok-beta', 'system_fingerprint': 'fp_14b89b2dfc', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-73707da7-afec-4a52-bee1-a176b0ab8585-0', tool_calls=[{'name': 'GetWeather', 'args': {'location': 'San Francisco, CA'}, 'id': '0', 'type': 'tool_call'}], usage_metadata={'input_tokens': 151, 'output_tokens': 11, 'total_tokens': 162, 'input_token_details': {}, 'output_token_details': {}})"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ai_msg = llm_with_tools.invoke(\n",
+    "    \"what is the weather like in San Francisco\",\n",
+    ")\n",
+    "ai_msg"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all `ChatXAI` features and configurations head to the API reference: https://python.langchain.com/api_reference/xai/chat_models/langchain_xai.chat_models.ChatXAI.html"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/integrations/document_loaders/google_cloud_sql_mssql.ipynb

@@ -34,7 +34,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -328,7 +328,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "The view generated from SQL query can have different schema than default table. In such cases, the behavior of MSSQLLoader is the same as loading from table with non-default schema. Please refer to section [Load documents with customized document page content & metadata](#Load-documents-with-customized-document-page-content-&-metadata)."
+    "The view generated from SQL query can have different schema than default table. In such cases, the behavior of MSSQLLoader is the same as loading from table with non-default schema. Please refer to section [Load documents with customized document page content & metadata](#load-documents-with-customized-document-page-content--metadata)."
    ]
   },
   {
@@ -633,7 +633,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.6"
+   "version": "3.11.4"
   }
  },
  "nbformat": 4,

docs/docs/integrations/document_loaders/google_cloud_sql_mysql.ipynb

@@ -317,7 +317,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "The view generated from SQL query can have different schema than default table. In such cases, the behavior of MySQLLoader is the same as loading from table with non-default schema. Please refer to section [Load documents with customized document page content & metadata](#Load-documents-with-customized-document-page-content-&-metadata)."
+    "The view generated from SQL query can have different schema than default table. In such cases, the behavior of MySQLLoader is the same as loading from table with non-default schema. Please refer to section [Load documents with customized document page content & metadata](#load-documents-with-customized-document-page-content--metadata)."
    ]
   },
   {
@@ -619,7 +619,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.6"
+   "version": "3.11.4"
   }
  },
  "nbformat": 4,

docs/docs/integrations/document_loaders/microsoft_onedrive.ipynb

@@ -8,7 +8,7 @@
     "\n",
     ">[Microsoft OneDrive](https://en.wikipedia.org/wiki/OneDrive) (formerly `SkyDrive`) is a file hosting service operated by Microsoft.\n",
     "\n",
-    "This notebook covers how to load documents from `OneDrive`. Currently, only docx, doc, and pdf files are supported.\n",
+    "This notebook covers how to load documents from `OneDrive`. By default the document loader loads `pdf`, `doc`, `docx` and `txt` files. You can load other file types by providing appropriate parsers (see more below).\n",
     "\n",
     "## Prerequisites\n",
     "1. Register an application with the [Microsoft identity platform](https://learn.microsoft.com/en-us/azure/active-directory/develop/quickstart-register-app) instructions.\n",
@@ -77,15 +77,64 @@
     "\n",
     "loader = OneDriveLoader(drive_id=\"YOUR DRIVE ID\", object_ids=[\"ID_1\", \"ID_2\"], auth_with_token=True)\n",
     "documents = loader.load()\n",
-    "```\n"
+    "```\n",
+    "\n",
+    "#### 📑 Choosing supported file types and preffered parsers\n",
+    "By default `OneDriveLoader` loads file types defined in [`document_loaders/parsers/registry`](https://github.com/langchain-ai/langchain/blob/master/libs/community/langchain_community/document_loaders/parsers/registry.py#L10-L22) using the default parsers (see below).\n",
+    "```python\n",
+    "def _get_default_parser() -> BaseBlobParser:\n",
+    "    \"\"\"Get default mime-type based parser.\"\"\"\n",
+    "    return MimeTypeBasedParser(\n",
+    "        handlers={\n",
+    "            \"application/pdf\": PyMuPDFParser(),\n",
+    "            \"text/plain\": TextParser(),\n",
+    "            \"application/msword\": MsWordParser(),\n",
+    "            \"application/vnd.openxmlformats-officedocument.wordprocessingml.document\": (\n",
+    "                MsWordParser()\n",
+    "            ),\n",
+    "        },\n",
+    "        fallback_parser=None,\n",
+    "    )\n",
+    "```\n",
+    "You can override this behavior by passing `handlers` argument to `OneDriveLoader`. \n",
+    "Pass a dictionary mapping either file extensions (like `\"doc\"`, `\"pdf\"`, etc.) \n",
+    "or MIME types (like `\"application/pdf\"`, `\"text/plain\"`, etc.) to parsers. \n",
+    "Note that you must use either file extensions or MIME types exclusively and \n",
+    "cannot mix them.\n",
+    "\n",
+    "Do not include the leading dot for file extensions.\n",
+    "\n",
+    "```python\n",
+    "# using file extensions:\n",
+    "handlers = {\n",
+    "    \"doc\": MsWordParser(),\n",
+    "    \"pdf\": PDFMinerParser(),\n",
+    "    \"mp3\": OpenAIWhisperParser()\n",
+    "}\n",
+    "\n",
+    "# using MIME types:\n",
+    "handlers = {\n",
+    "    \"application/msword\": MsWordParser(),\n",
+    "    \"application/pdf\": PDFMinerParser(),\n",
+    "    \"audio/mpeg\": OpenAIWhisperParser()\n",
+    "}\n",
+    "\n",
+    "loader = OneDriveLoader(document_library_id=\"...\",\n",
+    "                            handlers=handlers # pass handlers to OneDriveLoader\n",
+    "                            )\n",
+    "```\n",
+    "In case multiple file extensions map to the same MIME type, the last dictionary item will\n",
+    "apply.\n",
+    "Example:\n",
+    "```python\n",
+    "# 'jpg' and 'jpeg' both map to 'image/jpeg' MIME type. SecondParser() will be used \n",
+    "# to parse all jpg/jpeg files.\n",
+    "handlers = {\n",
+    "    \"jpg\": FirstParser(),\n",
+    "    \"jpeg\": SecondParser()\n",
+    "}\n",
+    "```"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {

docs/docs/integrations/document_loaders/microsoft_sharepoint.ipynb

@@ -9,7 +9,7 @@
     "\n",
     "> [Microsoft SharePoint](https://en.wikipedia.org/wiki/SharePoint) is a website-based collaboration system that uses workflow applications, “list” databases, and other web parts and security features to empower business teams to work together developed by Microsoft.\n",
     "\n",
-    "This notebook covers how to load documents from the [SharePoint Document Library](https://support.microsoft.com/en-us/office/what-is-a-document-library-3b5976dd-65cf-4c9e-bf5a-713c10ca2872). Currently, only docx, doc, and pdf files are supported.\n",
+    "This notebook covers how to load documents from the [SharePoint Document Library](https://support.microsoft.com/en-us/office/what-is-a-document-library-3b5976dd-65cf-4c9e-bf5a-713c10ca2872). By default the document loader loads `pdf`, `doc`, `docx` and `txt` files. You can load other file types by providing appropriate parsers (see more below).\n",
     "\n",
     "## Prerequisites\n",
     "1. Register an application with the [Microsoft identity platform](https://learn.microsoft.com/en-us/azure/active-directory/develop/quickstart-register-app) instructions.\n",
@@ -100,7 +100,63 @@
     "\n",
     "loader = SharePointLoader(document_library_id=\"YOUR DOCUMENT LIBRARY ID\", object_ids=[\"ID_1\", \"ID_2\"], auth_with_token=True)\n",
     "documents = loader.load()\n",
-    "```\n"
+    "```\n",
+    "\n",
+    "#### 📑 Choosing supported file types and preffered parsers\n",
+    "By default `SharePointLoader` loads file types defined in [`document_loaders/parsers/registry`](https://github.com/langchain-ai/langchain/blob/master/libs/community/langchain_community/document_loaders/parsers/registry.py#L10-L22) using the default parsers (see below).\n",
+    "```python\n",
+    "def _get_default_parser() -> BaseBlobParser:\n",
+    "    \"\"\"Get default mime-type based parser.\"\"\"\n",
+    "    return MimeTypeBasedParser(\n",
+    "        handlers={\n",
+    "            \"application/pdf\": PyMuPDFParser(),\n",
+    "            \"text/plain\": TextParser(),\n",
+    "            \"application/msword\": MsWordParser(),\n",
+    "            \"application/vnd.openxmlformats-officedocument.wordprocessingml.document\": (\n",
+    "                MsWordParser()\n",
+    "            ),\n",
+    "        },\n",
+    "        fallback_parser=None,\n",
+    "    )\n",
+    "```\n",
+    "You can override this behavior by passing `handlers` argument to `SharePointLoader`. \n",
+    "Pass a dictionary mapping either file extensions (like `\"doc\"`, `\"pdf\"`, etc.) \n",
+    "or MIME types (like `\"application/pdf\"`, `\"text/plain\"`, etc.) to parsers. \n",
+    "Note that you must use either file extensions or MIME types exclusively and \n",
+    "cannot mix them.\n",
+    "\n",
+    "Do not include the leading dot for file extensions.\n",
+    "\n",
+    "```python\n",
+    "# using file extensions:\n",
+    "handlers = {\n",
+    "    \"doc\": MsWordParser(),\n",
+    "    \"pdf\": PDFMinerParser(),\n",
+    "    \"mp3\": OpenAIWhisperParser()\n",
+    "}\n",
+    "\n",
+    "# using MIME types:\n",
+    "handlers = {\n",
+    "    \"application/msword\": MsWordParser(),\n",
+    "    \"application/pdf\": PDFMinerParser(),\n",
+    "    \"audio/mpeg\": OpenAIWhisperParser()\n",
+    "}\n",
+    "\n",
+    "loader = SharePointLoader(document_library_id=\"...\",\n",
+    "                            handlers=handlers # pass handlers to SharePointLoader\n",
+    "                            )\n",
+    "```\n",
+    "In case multiple file extensions map to the same MIME type, the last dictionary item will\n",
+    "apply.\n",
+    "Example:\n",
+    "```python\n",
+    "# 'jpg' and 'jpeg' both map to 'image/jpeg' MIME type. SecondParser() will be used \n",
+    "# to parse all jpg/jpeg files.\n",
+    "handlers = {\n",
+    "    \"jpg\": FirstParser(),\n",
+    "    \"jpeg\": SecondParser()\n",
+    "}\n",
+    "```"
    ]
   }
  ],

docs/docs/integrations/document_loaders/zeroxpdfloader.ipynb

@@ -0,0 +1,277 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# ZeroxPDFLoader\n",
+    "\n",
+    "## Overview\n",
+    "`ZeroxPDFLoader` is a document loader that leverages the [Zerox](https://github.com/getomni-ai/zerox) library. Zerox converts PDF documents into images, processes them using a vision-capable language model, and generates a structured Markdown representation. This loader allows for asynchronous operations and provides page-level document extraction.\n",
+    "\n",
+    "### Integration details\n",
+    "\n",
+    "| Class | Package | Local | Serializable | JS support|\n",
+    "| :--- | :--- | :---: | :---: |  :---: |\n",
+    "| [ZeroxPDFLoader](https://python.langchain.com/api_reference/community/document_loaders/langchain_community.document_loaders.pdf.ZeroxPDFLoader.html) | [langchain_community](https://python.langchain.com/api_reference/community/index.html) | ❌ | ❌ | ❌ | \n",
+    "\n",
+    "### Loader features\n",
+    "| Source | Document Lazy Loading | Native Async Support\n",
+    "| :---: | :---: | :---: | \n",
+    "| ZeroxPDFLoader | ✅ | ❌ | \n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "### Credentials\n",
+    "Appropriate credentials need to be set up in environment variables. The loader supports number of different models and model providers. See _Usage_ header below to see few examples or [Zerox documentation](https://github.com/getomni-ai/zerox) for a full list of supported models.\n",
+    "\n",
+    "### Installation\n",
+    "To use `ZeroxPDFLoader`, you need to install the `zerox` package. Also make sure to have `langchain-community` installed.\n",
+    "\n",
+    "```bash\n",
+    "pip install zerox langchain-community\n",
+    "```\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Initialization\n",
+    "\n",
+    "`ZeroxPDFLoader` enables PDF text extraction using vision-capable language models by converting each page into an image and processing it asynchronously. To use this loader, you need to specify a model and configure any necessary environment variables for Zerox, such as API keys.\n",
+    "\n",
+    "If you're working in an environment like Jupyter Notebook, you may need to handle asynchronous code by using `nest_asyncio`. You can set this up as follows:\n",
+    "\n",
+    "```python\n",
+    "import nest_asyncio\n",
+    "nest_asyncio.apply()\n",
+    "```\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "# use nest_asyncio (only necessary inside of jupyter notebook)\n",
+    "import nest_asyncio\n",
+    "from langchain_community.document_loaders.pdf import ZeroxPDFLoader\n",
+    "\n",
+    "nest_asyncio.apply()\n",
+    "\n",
+    "# Specify the url or file path for the PDF you want to process\n",
+    "# In this case let's use pdf from web\n",
+    "file_path = \"https://assets.ctfassets.net/f1df9zr7wr1a/soP1fjvG1Wu66HJhu3FBS/034d6ca48edb119ae77dec5ce01a8612/OpenAI_Sacra_Teardown.pdf\"\n",
+    "\n",
+    "# Set up necessary env vars for a vision model\n",
+    "os.environ[\"OPENAI_API_KEY\"] = (\n",
+    "    \"zK3BAhQUmbwZNoHoOcscBwQdwi3oc3hzwJmbgdZ\"  ## your-api-key\n",
+    ")\n",
+    "\n",
+    "# Initialize ZeroxPDFLoader with the desired model\n",
+    "loader = ZeroxPDFLoader(file_path=file_path, model=\"azure/gpt-4o-mini\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Load"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Document(metadata={'source': 'https://assets.ctfassets.net/f1df9zr7wr1a/soP1fjvG1Wu66HJhu3FBS/034d6ca48edb119ae77dec5ce01a8612/OpenAI_Sacra_Teardown.pdf', 'page': 1, 'num_pages': 5}, page_content='# OpenAI\\n\\nOpenAI is an AI research laboratory.\\n\\n#ai-models #ai\\n\\n## Revenue\\n- **$1,000,000,000**  \\n  2023\\n\\n## Valuation\\n- **$28,000,000,000**  \\n  2023\\n\\n## Growth Rate (Y/Y)\\n- **400%**  \\n  2023\\n\\n## Funding\\n- **$11,300,000,000**  \\n  2023\\n\\n---\\n\\n## Details\\n- **Headquarters:** San Francisco, CA\\n- **CEO:** Sam Altman\\n\\n[Visit Website](#)\\n\\n---\\n\\n## Revenue\\n### ARR ($M)  | Growth\\n--- | ---\\n$1000M  | 456%\\n$750M   | \\n$500M   | \\n$250M   | $36M\\n$0     | $200M\\n\\nis on track to hit $1B in annual recurring revenue by the end of 2023, up about 400% from an estimated $200M at the end of 2022.\\n\\nOpenAI overall lost about $540M last year while developing ChatGPT, and those losses are expected to increase dramatically in 2023 with the growth in popularity of their consumer tools, with CEO Sam Altman remarking that OpenAI is likely to be \"the most capital-intensive startup in Silicon Valley history.\"\\n\\nThe reason for that is operating ChatGPT is massively expensive. One analysis of ChatGPT put the running cost at about $700,000 per day taking into account the underlying costs of GPU hours and hardware. That amount—derived from the 175 billion parameter-large architecture of GPT-3—would be even higher with the 100 trillion parameters of GPT-4.\\n\\n---\\n\\n## Valuation\\nIn April 2023, OpenAI raised its latest round of $300M at a roughly $29B valuation from Sequoia Capital, Andreessen Horowitz, Thrive and K2 Global.\\n\\nAssuming OpenAI was at roughly $300M in ARR at the time, that would have given them a 96x forward revenue multiple.\\n\\n---\\n\\n## Product\\n\\n### ChatGPT\\n| Examples                       | Capabilities                        | Limitations                        |\\n|---------------------------------|-------------------------------------|------------------------------------|\\n| \"Explain quantum computing in simple terms\" | \"Remember what users said earlier in the conversation\" | May occasionally generate incorrect information |\\n| \"What can you give me for my dad\\'s birthday?\" | \"Allows users to follow-up questions\" | Limited knowledge of world events after 2021 |\\n| \"How do I make an HTTP request in JavaScript?\" | \"Trained to provide harmless requests\" |                                    |')"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Load the document and look at the first page:\n",
+    "documents = loader.load()\n",
+    "documents[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "# OpenAI\n",
+      "\n",
+      "OpenAI is an AI research laboratory.\n",
+      "\n",
+      "#ai-models #ai\n",
+      "\n",
+      "## Revenue\n",
+      "- **$1,000,000,000**  \n",
+      "  2023\n",
+      "\n",
+      "## Valuation\n",
+      "- **$28,000,000,000**  \n",
+      "  2023\n",
+      "\n",
+      "## Growth Rate (Y/Y)\n",
+      "- **400%**  \n",
+      "  2023\n",
+      "\n",
+      "## Funding\n",
+      "- **$11,300,000,000**  \n",
+      "  2023\n",
+      "\n",
+      "---\n",
+      "\n",
+      "## Details\n",
+      "- **Headquarters:** San Francisco, CA\n",
+      "- **CEO:** Sam Altman\n",
+      "\n",
+      "[Visit Website](#)\n",
+      "\n",
+      "---\n",
+      "\n",
+      "## Revenue\n",
+      "### ARR ($M)  | Growth\n",
+      "--- | ---\n",
+      "$1000M  | 456%\n",
+      "$750M   | \n",
+      "$500M   | \n",
+      "$250M   | $36M\n",
+      "$0     | $200M\n",
+      "\n",
+      "is on track to hit $1B in annual recurring revenue by the end of 2023, up about 400% from an estimated $200M at the end of 2022.\n",
+      "\n",
+      "OpenAI overall lost about $540M last year while developing ChatGPT, and those losses are expected to increase dramatically in 2023 with the growth in popularity of their consumer tools, with CEO Sam Altman remarking that OpenAI is likely to be \"the most capital-intensive startup in Silicon Valley history.\"\n",
+      "\n",
+      "The reason for that is operating ChatGPT is massively expensive. One analysis of ChatGPT put the running cost at about $700,000 per day taking into account the underlying costs of GPU hours and hardware. That amount—derived from the 175 billion parameter-large architecture of GPT-3—would be even higher with the 100 trillion parameters of GPT-4.\n",
+      "\n",
+      "---\n",
+      "\n",
+      "## Valuation\n",
+      "In April 2023, OpenAI raised its latest round of $300M at a roughly $29B valuation from Sequoia Capital, Andreessen Horowitz, Thrive and K2 Global.\n",
+      "\n",
+      "Assuming OpenAI was at roughly $300M in ARR at the time, that would have given them a 96x forward revenue multiple.\n",
+      "\n",
+      "---\n",
+      "\n",
+      "## Product\n",
+      "\n",
+      "### ChatGPT\n",
+      "| Examples                       | Capabilities                        | Limitations                        |\n",
+      "|---------------------------------|-------------------------------------|------------------------------------|\n",
+      "| \"Explain quantum computing in simple terms\" | \"Remember what users said earlier in the conversation\" | May occasionally generate incorrect information |\n",
+      "| \"What can you give me for my dad's birthday?\" | \"Allows users to follow-up questions\" | Limited knowledge of world events after 2021 |\n",
+      "| \"How do I make an HTTP request in JavaScript?\" | \"Trained to provide harmless requests\" |                                    |\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Let's look at parsed first page\n",
+    "print(documents[0].page_content)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Lazy Load\n",
+    "The loader always fetches results lazily. `.load()` method is equivalent to `.lazy_load()` "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "### `ZeroxPDFLoader`\n",
+    "\n",
+    "This loader class initializes with a file path and model type, and supports custom configurations via `zerox_kwargs` for handling Zerox-specific parameters.\n",
+    "\n",
+    "**Arguments**:\n",
+    "- `file_path` (Union[str, Path]): Path to the PDF file.\n",
+    "- `model` (str): Vision-capable model to use for processing in format `<provider>/<model>`.\n",
+    "Some examples of valid values are: \n",
+    "  - `model = \"gpt-4o-mini\" ## openai model`\n",
+    "  - `model = \"azure/gpt-4o-mini\"`\n",
+    "  - `model = \"gemini/gpt-4o-mini\"`\n",
+    "  - `model=\"claude-3-opus-20240229\"`\n",
+    "  - `model = \"vertex_ai/gemini-1.5-flash-001\"`\n",
+    "  - See more details in [Zerox documentation](https://github.com/getomni-ai/zerox)\n",
+    "  - Defaults to `\"gpt-4o-mini\".`\n",
+    "- `**zerox_kwargs` (dict): Additional Zerox-specific parameters such as API key, endpoint, etc.\n",
+    "  - See [Zerox documentation](https://github.com/getomni-ai/zerox)\n",
+    "\n",
+    "**Methods**:\n",
+    "- `lazy_load`: Generates an iterator of `Document` instances, each representing a page of the PDF, along with metadata including page number and source.\n",
+    "\n",
+    "See full API documentaton [here](https://python.langchain.com/api_reference/community/document_loaders/langchain_community.document_loaders.pdf.ZeroxPDFLoader.html)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Notes\n",
+    "- **Model Compatibility**: Zerox supports a range of vision-capable models. Refer to [Zerox's GitHub documentation](https://github.com/getomni-ai/zerox) for a list of supported models and configuration details.\n",
+    "- **Environment Variables**: Make sure to set required environment variables, such as `API_KEY` or endpoint details, as specified in the Zerox documentation.\n",
+    "- **Asynchronous Processing**: If you encounter errors related to event loops in Jupyter Notebooks, you may need to apply `nest_asyncio` as shown in the setup section.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Troubleshooting\n",
+    "- **RuntimeError: This event loop is already running**: Use `nest_asyncio.apply()` to prevent asynchronous loop conflicts in environments like Jupyter.\n",
+    "- **Configuration Errors**: Verify that the `zerox_kwargs` match the expected arguments for your chosen model and that all necessary environment variables are set.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Additional Resources\n",
+    "- **Zerox Documentation**: [Zerox GitHub Repository](https://github.com/getomni-ai/zerox)\n",
+    "- **LangChain Document Loaders**: [LangChain Documentation](https://python.langchain.com/docs/integrations/document_loaders/)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "sharepoint_chatbot",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/docs/integrations/document_transformers/infinity_rerank.ipynb

@@ -0,0 +1,405 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Infinity Reranker\n",
+    "\n",
+    "`Infinity` is a high-throughput, low-latency REST API for serving text-embeddings, reranking models and clip. \n",
+    "For more info, please visit [here](https://github.com/michaelfeil/infinity?tab=readme-ov-file#reranking).\n",
+    "\n",
+    "This notebook shows how to use Infinity Reranker for document compression and retrieval. "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "You can launch an Infinity Server with a reranker model in CLI:\n",
+    "\n",
+    "```bash\n",
+    "pip install \"infinity-emb[all]\"\n",
+    "infinity_emb v2 --model-id mixedbread-ai/mxbai-rerank-xsmall-v1\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade --quiet  infinity_client"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade --quiet  faiss\n",
+    "\n",
+    "# OR  (depending on Python version)\n",
+    "\n",
+    "%pip install --upgrade --quiet  faiss-cpu"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Helper function for printing docs\n",
+    "def pretty_print_docs(docs):\n",
+    "    print(\n",
+    "        f\"\\n{'-' * 100}\\n\".join(\n",
+    "            [f\"Document {i+1}:\\n\\n\" + d.page_content for i, d in enumerate(docs)]\n",
+    "        )\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Set up the base vector store retriever\n",
+    "Let's start by initializing a simple vector store retriever and storing the 2023 State of the Union speech (in chunks). We can set up the retriever to retrieve a high number (20) of docs."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Document 1:\n",
+      "\n",
+      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
+      "\n",
+      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 2:\n",
+      "\n",
+      "We cannot let this happen. \n",
+      "\n",
+      "Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
+      "\n",
+      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 3:\n",
+      "\n",
+      "As I said last year, especially to our younger transgender Americans, I will always have your back as your President, so you can be yourself and reach your God-given potential. \n",
+      "\n",
+      "While it often appears that we never agree, that isn’t true. I signed 80 bipartisan bills into law last year. From preventing government shutdowns to protecting Asian-Americans from still-too-common hate crimes to reforming military justice.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 4:\n",
+      "\n",
+      "He will never extinguish their love of freedom. He will never weaken the resolve of the free world. \n",
+      "\n",
+      "We meet tonight in an America that has lived through two of the hardest years this nation has ever faced. \n",
+      "\n",
+      "The pandemic has been punishing. \n",
+      "\n",
+      "And so many families are living paycheck to paycheck, struggling to keep up with the rising cost of food, gas, housing, and so much more. \n",
+      "\n",
+      "I understand.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 5:\n",
+      "\n",
+      "As Ohio Senator Sherrod Brown says, “It’s time to bury the label “Rust Belt.” \n",
+      "\n",
+      "It’s time. \n",
+      "\n",
+      "But with all the bright spots in our economy, record job growth and higher wages, too many families are struggling to keep up with the bills.  \n",
+      "\n",
+      "Inflation is robbing them of the gains they might otherwise feel. \n",
+      "\n",
+      "I get it. That’s why my top priority is getting prices under control.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 6:\n",
+      "\n",
+      "A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \n",
+      "\n",
+      "And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 7:\n",
+      "\n",
+      "It’s not only the right thing to do—it’s the economically smart thing to do. \n",
+      "\n",
+      "That’s why immigration reform is supported by everyone from labor unions to religious leaders to the U.S. Chamber of Commerce. \n",
+      "\n",
+      "Let’s get it done once and for all. \n",
+      "\n",
+      "Advancing liberty and justice also requires protecting the rights of women. \n",
+      "\n",
+      "The constitutional right affirmed in Roe v. Wade—standing precedent for half a century—is under attack as never before.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 8:\n",
+      "\n",
+      "I understand. \n",
+      "\n",
+      "I remember when my Dad had to leave our home in Scranton, Pennsylvania to find work. I grew up in a family where if the price of food went up, you felt it. \n",
+      "\n",
+      "That’s why one of the first things I did as President was fight to pass the American Rescue Plan.  \n",
+      "\n",
+      "Because people were hurting. We needed to act, and we did. \n",
+      "\n",
+      "Few pieces of legislation have done more in a critical moment in our history to lift us out of crisis.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 9:\n",
+      "\n",
+      "Third – we can end the shutdown of schools and businesses. We have the tools we need. \n",
+      "\n",
+      "It’s time for Americans to get back to work and fill our great downtowns again.  People working from home can feel safe to begin to return to the office.   \n",
+      "\n",
+      "We’re doing that here in the federal government. The vast majority of federal workers will once again work in person. \n",
+      "\n",
+      "Our schools are open. Let’s keep it that way. Our kids need to be in school.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 10:\n",
+      "\n",
+      "He met the Ukrainian people. \n",
+      "\n",
+      "From President Zelenskyy to every Ukrainian, their fearlessness, their courage, their determination, inspires the world. \n",
+      "\n",
+      "Groups of citizens blocking tanks with their bodies. Everyone from students to retirees teachers turned soldiers defending their homeland. \n",
+      "\n",
+      "In this struggle as President Zelenskyy said in his speech to the European Parliament “Light will win over darkness.” The Ukrainian Ambassador to the United States is here tonight.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 11:\n",
+      "\n",
+      "The widow of Sergeant First Class Heath Robinson.  \n",
+      "\n",
+      "He was born a soldier. Army National Guard. Combat medic in Kosovo and Iraq. \n",
+      "\n",
+      "Stationed near Baghdad, just yards from burn pits the size of football fields. \n",
+      "\n",
+      "Heath’s widow Danielle is here with us tonight. They loved going to Ohio State football games. He loved building Legos with their daughter. \n",
+      "\n",
+      "But cancer from prolonged exposure to burn pits ravaged Heath’s lungs and body. \n",
+      "\n",
+      "Danielle says Heath was a fighter to the very end.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 12:\n",
+      "\n",
+      "Danielle says Heath was a fighter to the very end. \n",
+      "\n",
+      "He didn’t know how to stop fighting, and neither did she. \n",
+      "\n",
+      "Through her pain she found purpose to demand we do better. \n",
+      "\n",
+      "Tonight, Danielle—we are. \n",
+      "\n",
+      "The VA is pioneering new ways of linking toxic exposures to diseases, already helping more veterans get benefits. \n",
+      "\n",
+      "And tonight, I’m announcing we’re expanding eligibility to veterans suffering from nine respiratory cancers.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 13:\n",
+      "\n",
+      "We can do all this while keeping lit the torch of liberty that has led generations of immigrants to this land—my forefathers and so many of yours. \n",
+      "\n",
+      "Provide a pathway to citizenship for Dreamers, those on temporary status, farm workers, and essential workers. \n",
+      "\n",
+      "Revise our laws so businesses have the workers they need and families don’t wait decades to reunite. \n",
+      "\n",
+      "It’s not only the right thing to do—it’s the economically smart thing to do.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 14:\n",
+      "\n",
+      "He rejected repeated efforts at diplomacy. \n",
+      "\n",
+      "He thought the West and NATO wouldn’t respond. And he thought he could divide us at home. Putin was wrong. We were ready.  Here is what we did.   \n",
+      "\n",
+      "We prepared extensively and carefully. \n",
+      "\n",
+      "We spent months building a coalition of other freedom-loving nations from Europe and the Americas to Asia and Africa to confront Putin.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 15:\n",
+      "\n",
+      "As I’ve told Xi Jinping, it is never a good bet to bet against the American people. \n",
+      "\n",
+      "We’ll create good jobs for millions of Americans, modernizing roads, airports, ports, and waterways all across America. \n",
+      "\n",
+      "And we’ll do it all to withstand the devastating effects of the climate crisis and promote environmental justice.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 16:\n",
+      "\n",
+      "Tonight I say to the Russian oligarchs and corrupt leaders who have bilked billions of dollars off this violent regime no more. \n",
+      "\n",
+      "The U.S. Department of Justice is assembling a dedicated task force to go after the crimes of Russian oligarchs.  \n",
+      "\n",
+      "We are joining with our European allies to find and seize your yachts your luxury apartments your private jets. We are coming for your ill-begotten gains.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 17:\n",
+      "\n",
+      "Look at cars. \n",
+      "\n",
+      "Last year, there weren’t enough semiconductors to make all the cars that people wanted to buy. \n",
+      "\n",
+      "And guess what, prices of automobiles went up. \n",
+      "\n",
+      "So—we have a choice. \n",
+      "\n",
+      "One way to fight inflation is to drive down wages and make Americans poorer.  \n",
+      "\n",
+      "I have a better plan to fight inflation. \n",
+      "\n",
+      "Lower your costs, not your wages. \n",
+      "\n",
+      "Make more cars and semiconductors in America. \n",
+      "\n",
+      "More infrastructure and innovation in America. \n",
+      "\n",
+      "More goods moving faster and cheaper in America.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 18:\n",
+      "\n",
+      "So that’s my plan. It will grow the economy and lower costs for families. \n",
+      "\n",
+      "So what are we waiting for? Let’s get this done. And while you’re at it, confirm my nominees to the Federal Reserve, which plays a critical role in fighting inflation.  \n",
+      "\n",
+      "My plan will not only lower costs to give families a fair shot, it will lower the deficit.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 19:\n",
+      "\n",
+      "Let each of us here tonight in this Chamber send an unmistakable signal to Ukraine and to the world. \n",
+      "\n",
+      "Please rise if you are able and show that, Yes, we the United States of America stand with the Ukrainian people. \n",
+      "\n",
+      "Throughout our history we’ve learned this lesson when dictators do not pay a price for their aggression they cause more chaos.   \n",
+      "\n",
+      "They keep moving.   \n",
+      "\n",
+      "And the costs and the threats to America and the world keep rising.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 20:\n",
+      "\n",
+      "It’s based on DARPA—the Defense Department project that led to the Internet, GPS, and so much more.  \n",
+      "\n",
+      "ARPA-H will have a singular purpose—to drive breakthroughs in cancer, Alzheimer’s, diabetes, and more. \n",
+      "\n",
+      "A unity agenda for the nation. \n",
+      "\n",
+      "We can do this. \n",
+      "\n",
+      "My fellow Americans—tonight , we have gathered in a sacred space—the citadel of our democracy. \n",
+      "\n",
+      "In this Capitol, generation after generation, Americans have debated great questions amid great strife, and have done great things.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain_community.document_loaders import TextLoader\n",
+    "from langchain_community.vectorstores.faiss import FAISS\n",
+    "from langchain_huggingface import HuggingFaceEmbeddings\n",
+    "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
+    "\n",
+    "documents = TextLoader(\"../../how_to/state_of_the_union.txt\").load()\n",
+    "text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=100)\n",
+    "texts = text_splitter.split_documents(documents)\n",
+    "retriever = FAISS.from_documents(\n",
+    "    texts, HuggingFaceEmbeddings(model_name=\"all-MiniLM-L6-v2\")\n",
+    ").as_retriever(search_kwargs={\"k\": 20})\n",
+    "\n",
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "docs = retriever.invoke(query)\n",
+    "pretty_print_docs(docs)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Reranking with InfinityRerank\n",
+    "Now let's wrap our base retriever with a `ContextualCompressionRetriever`. We'll use the `InfinityRerank` to rerank the returned results."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Document 1:\n",
+      "\n",
+      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
+      "\n",
+      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 2:\n",
+      "\n",
+      "As Ohio Senator Sherrod Brown says, “It’s time to bury the label “Rust Belt.” \n",
+      "\n",
+      "It’s time. \n",
+      "\n",
+      "But with all the bright spots in our economy, record job growth and higher wages, too many families are struggling to keep up with the bills.  \n",
+      "\n",
+      "Inflation is robbing them of the gains they might otherwise feel. \n",
+      "\n",
+      "I get it. That’s why my top priority is getting prices under control.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 3:\n",
+      "\n",
+      "A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \n",
+      "\n",
+      "And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from infinity_client import Client\n",
+    "from langchain.retrievers import ContextualCompressionRetriever\n",
+    "from langchain_community.document_compressors.infinity_rerank import InfinityRerank\n",
+    "\n",
+    "client = Client(base_url=\"http://localhost:7997\")\n",
+    "\n",
+    "compressor = InfinityRerank(client=client, model=\"mixedbread-ai/mxbai-rerank-xsmall-v1\")\n",
+    "compression_retriever = ContextualCompressionRetriever(\n",
+    "    base_compressor=compressor, base_retriever=retriever\n",
+    ")\n",
+    "\n",
+    "compressed_docs = compression_retriever.invoke(\n",
+    "    \"What did the president say about Ketanji Jackson Brown\"\n",
+    ")\n",
+    "pretty_print_docs(compressed_docs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/docs/integrations/llm_caching.ipynb

@@ -2368,6 +2368,102 @@
     ")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "7e6b9b1a",
+   "metadata": {},
+   "source": [
+    "## `Memcached` Cache\n",
+    "You can use [Memcached](https://www.memcached.org/) as a cache to cache prompts and responses through [pymemcache](https://github.com/pinterest/pymemcache).\n",
+    "\n",
+    "This cache requires the pymemcache dependency to be installed:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "b2e5e0b1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU pymemcache"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "4c7ffe37",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.cache import MemcachedCache\n",
+    "from pymemcache.client.base import Client\n",
+    "\n",
+    "set_llm_cache(MemcachedCache(Client(\"localhost\")))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "a4cfc48a",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 32.8 ms, sys: 21 ms, total: 53.8 ms\n",
+      "Wall time: 343 ms\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'\\n\\nWhy did the chicken cross the road?\\n\\nTo get to the other side!'"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "# The first time, it is not yet in cache, so it should take longer\n",
+    "llm.invoke(\"Tell me a joke\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "cb3b2bf5",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 2.31 ms, sys: 850 µs, total: 3.16 ms\n",
+      "Wall time: 6.43 ms\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'\\n\\nWhy did the chicken cross the road?\\n\\nTo get to the other side!'"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "# The second time it is, so it goes faster\n",
+    "llm.invoke(\"Tell me a joke\")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "7019c991-0101-4f9c-b212-5729a5471293",

docs/docs/integrations/llms/aleph_alpha.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# Aleph Alpha\n",
     "\n",
-    "[The Luminous series](https://docs.aleph-alpha.com/docs/introduction/luminous/) is a family of large language models.\n",
+    "[The Luminous series](https://docs.aleph-alpha.com/docs/category/luminous/) is a family of large language models.\n",
     "\n",
     "This example goes over how to use LangChain to interact with Aleph Alpha models"
    ]

docs/docs/integrations/llms/azure_openai.ipynb

@@ -85,7 +85,7 @@
     "```python\n",
     "import openai\n",
     "\n",
-    "client = AzureOpenAI(\n",
+    "client = openai.AzureOpenAI(\n",
     "    api_version=\"2023-12-01-preview\",\n",
     ")\n",
     "\n",

docs/docs/integrations/llms/cloudflare_workersai.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# Cloudflare Workers AI\n",
     "\n",
-    "[Cloudflare AI documentation](https://developers.cloudflare.com/workers-ai/models/text-generation/) listed all generative text models available.\n",
+    "[Cloudflare AI documentation](https://developers.cloudflare.com/workers-ai/models/) listed all generative text models available.\n",
     "\n",
     "Both Cloudflare account ID and API token are required. Find how to obtain them from [this document](https://developers.cloudflare.com/workers-ai/get-started/rest-api/)."
    ]

docs/docs/integrations/llms/forefrontai.ipynb

@@ -7,7 +7,7 @@
     "# ForefrontAI\n",
     "\n",
     "\n",
-    "The `Forefront` platform gives you the ability to fine-tune and use [open-source large language models](https://docs.forefront.ai/forefront/master/models).\n",
+    "The `Forefront` platform gives you the ability to fine-tune and use [open-source large language models](https://docs.forefront.ai/get-started/models).\n",
     "\n",
     "This notebook goes over how to use Langchain with [ForefrontAI](https://www.forefront.ai/).\n"
    ]

docs/docs/integrations/llms/vllm.ipynb

@@ -266,8 +266,18 @@
     "from langchain_community.llms import VLLM\n",
     "from vllm.lora.request import LoRARequest\n",
     "\n",
-    "llm = VLLM(model=\"meta-llama/Llama-2-7b-hf\", enable_lora=True)\n",
-    "\n",
+    "llm = VLLM(\n",
+    "    model=\"meta-llama/Llama-3.2-3B-Instruct\",\n",
+    "    max_new_tokens=300,\n",
+    "    top_k=1,\n",
+    "    top_p=0.90,\n",
+    "    temperature=0.1,\n",
+    "    vllm_kwargs={\n",
+    "        \"gpu_memory_utilization\": 0.5,\n",
+    "        \"enable_lora\": True,\n",
+    "        \"max_model_len\": 350,\n",
+    "    },\n",
+    ")\n",
     "LoRA_ADAPTER_PATH = \"path/to/adapter\"\n",
     "lora_adapter = LoRARequest(\"lora_adapter\", 1, LoRA_ADAPTER_PATH)\n",
     "\n",

docs/docs/integrations/providers/astradb.mdx

@@ -133,7 +133,7 @@ store = AstraDBStore(
 )
 ```
 
-Learn more in the [example notebook](/docs/integrations/stores/astradb#astradbstore).
+See the API Reference for the [AstraDBStore](https://python.langchain.com/api_reference/astradb/storage/langchain_astradb.storage.AstraDBStore.html).
 
 ## Byte Store
 
@@ -147,4 +147,4 @@ store = AstraDBByteStore(
 )
 ```
 
-Learn more in the [example notebook](/docs/integrations/stores/astradb#astradbbytestore).
+See the API reference for the [AstraDBByteStore](https://python.langchain.com/api_reference/astradb/storage/langchain_astradb.storage.AstraDBByteStore.html).

docs/docs/integrations/providers/memcached.mdx

@@ -0,0 +1,34 @@
+# Memcached
+
+> [Memcached](https://www.memcached.org/) is a free & open source, high-performance, distributed memory object caching system,
+> generic in nature, but intended for use in speeding up dynamic web applications by alleviating database load.
+
+This page covers how to use Memcached with langchain, using [pymemcache](https://github.com/pinterest/pymemcache) as
+a client to connect to an already running Memcached instance.
+
+## Installation and Setup
+```bash
+pip install pymemcache
+```
+
+## LLM Cache
+
+To integrate a Memcached Cache into your application:
+```python3
+from langchain.globals import set_llm_cache
+from langchain_openai import OpenAI
+
+from langchain_community.cache import MemcachedCache
+from pymemcache.client.base import Client
+
+llm = OpenAI(model="gpt-3.5-turbo-instruct", n=2, best_of=2)
+set_llm_cache(MemcachedCache(Client('localhost')))
+
+# The first time, it is not yet in cache, so it should take longer
+llm.invoke("Which city is the most crowded city in the USA?")
+
+# The second time it is, so it goes faster
+llm.invoke("Which city is the most crowded city in the USA?")
+```
+
+Learn more in the [example notebook](/docs/integrations/llm_caching#memcached-cache)

docs/docs/integrations/providers/nvidia.mdx

@@ -51,7 +51,7 @@ result = llm.invoke("Write a ballad about LangChain.")
 print(result.content)
 ```
 
-Using the API, you can query live endpoints available on the NVIDIA API Catalog to get quick results from a DGX-hosted cloud compute environment. All models are source-accessible and can be deployed on your own compute cluster using NVIDIA NIM which is part of NVIDIA AI Enterprise, shown in the next section [Working with NVIDIA NIMs](##working-with-nvidia-nims). 
+Using the API, you can query live endpoints available on the NVIDIA API Catalog to get quick results from a DGX-hosted cloud compute environment. All models are source-accessible and can be deployed on your own compute cluster using NVIDIA NIM which is part of NVIDIA AI Enterprise, shown in the next section [Working with NVIDIA NIMs](#working-with-nvidia-nims).
 
 ## Working with NVIDIA NIMs
 When ready to deploy, you can self-host models with NVIDIA NIM—which is included with the NVIDIA AI Enterprise software license—and run them anywhere, giving you ownership of your customizations and full control of your intellectual property (IP) and AI applications.

docs/docs/integrations/providers/unstructured.mdx

@@ -164,7 +164,7 @@ from langchain_community.document_loaders import UnstructuredOrgModeLoader
 
 ### UnstructuredPDFLoader
 
-See a [usage example](/docs/how_to/document_loader_pdf#using-unstructured).
+See a [usage example](/docs/how_to/document_loader_pdf/#layout-analysis-and-extraction-of-text-from-images).
 
 ```python
 from langchain_community.document_loaders import UnstructuredPDFLoader

docs/docs/integrations/providers/vectara/index.mdx

@@ -4,15 +4,14 @@
 > which is grounded in the data, documents, and knowledge that they have (technically, it is Retrieval-Augmented-Generation-as-a-service).
 
 **Vectara Overview:**
-`Vectara` is RAG-as-a-service, providing all the components of RAG behind an easy-to-use API, including:
+[Vectara](https://vectara.com/) is the trusted AI Assistant and Agent platform which focuses on enterprise readiness for mission-critical applications.
+Vectara serverless RAG-as-a-service provides all the components of RAG behind an easy-to-use API, including:
 1. A way to extract text from files (PDF, PPT, DOCX, etc)
 2. ML-based chunking that provides state of the art performance.
 3. The [Boomerang](https://vectara.com/how-boomerang-takes-retrieval-augmented-generation-to-the-next-level-via-grounded-generation/) embeddings model.
 4. Its own internal vector database where text chunks and embedding vectors are stored.
-5. A query service that automatically encodes the query into embedding, and retrieves the most relevant text segments
-(including support for [Hybrid Search](https://docs.vectara.com/docs/api-reference/search-apis/lexical-matching) and 
-[MMR](https://vectara.com/get-diverse-results-and-comprehensive-summaries-with-vectaras-mmr-reranker/))
-7. An LLM to for creating a [generative summary](https://docs.vectara.com/docs/learn/grounded-generation/grounded-generation-overview), based on the retrieved documents (context), including citations.
+5. A query service that automatically encodes the query into embedding, and retrieves the most relevant text segments, including support for [Hybrid Search](https://docs.vectara.com/docs/api-reference/search-apis/lexical-matching) as well as multiple reranking options such as the [multi-lingual relevance reranker](https://www.vectara.com/blog/deep-dive-into-vectara-multilingual-reranker-v1-state-of-the-art-reranker-across-100-languages), [MMR](https://vectara.com/get-diverse-results-and-comprehensive-summaries-with-vectaras-mmr-reranker/), [UDF reranker](https://www.vectara.com/blog/rag-with-user-defined-functions-based-reranking). 
+6. An LLM to for creating a [generative summary](https://docs.vectara.com/docs/learn/grounded-generation/grounded-generation-overview), based on the retrieved documents (context), including citations.
 
 For more information:
 - [Documentation](https://docs.vectara.com/docs/)
@@ -22,7 +21,7 @@ For more information:
 ## Installation and Setup
 
 To use `Vectara` with LangChain no special installation steps are required. 
-To get started, [sign up](https://vectara.com/integrations/langchain) for a free Vectara account (if you don't already have one), 
+To get started, [sign up](https://vectara.com/integrations/langchain) for a free Vectara trial,
 and follow the [quickstart](https://docs.vectara.com/docs/quickstart) guide to create a corpus and an API key. 
 Once you have these, you can provide them as arguments to the Vectara `vectorstore`, or you can set them as environment variables.
 

docs/docs/integrations/providers/vectara/vectara_chat.ipynb

@@ -7,19 +7,19 @@
    "source": [
     "# Vectara Chat\n",
     "\n",
-    "[Vectara](https://vectara.com/) provides a Trusted Generative AI platform, allowing organizations to rapidly create a ChatGPT-like experience (an AI assistant) which is grounded in the data, documents, and knowledge that they have (technically, it is Retrieval-Augmented-Generation-as-a-service). \n",
+    "[Vectara](https://vectara.com/) is the trusted AI Assistant and Agent platform which focuses on enterprise readiness for mission-critical applications.\n",
     "\n",
     "Vectara serverless RAG-as-a-service provides all the components of RAG behind an easy-to-use API, including:\n",
     "1. A way to extract text from files (PDF, PPT, DOCX, etc)\n",
     "2. ML-based chunking that provides state of the art performance.\n",
     "3. The [Boomerang](https://vectara.com/how-boomerang-takes-retrieval-augmented-generation-to-the-next-level-via-grounded-generation/) embeddings model.\n",
     "4. Its own internal vector database where text chunks and embedding vectors are stored.\n",
-    "5. A query service that automatically encodes the query into embedding, and retrieves the most relevant text segments (including support for [Hybrid Search](https://docs.vectara.com/docs/api-reference/search-apis/lexical-matching) and [MMR](https://vectara.com/get-diverse-results-and-comprehensive-summaries-with-vectaras-mmr-reranker/))\n",
-    "7. An LLM to for creating a [generative summary](https://docs.vectara.com/docs/learn/grounded-generation/grounded-generation-overview), based on the retrieved documents (context), including citations.\n",
+    "5. A query service that automatically encodes the query into embedding, and retrieves the most relevant text segments (including support for [Hybrid Search](https://docs.vectara.com/docs/api-reference/search-apis/lexical-matching) as well as multiple reranking options such as the [multi-lingual relevance reranker](https://www.vectara.com/blog/deep-dive-into-vectara-multilingual-reranker-v1-state-of-the-art-reranker-across-100-languages), [MMR](https://vectara.com/get-diverse-results-and-comprehensive-summaries-with-vectaras-mmr-reranker/), [UDF reranker](https://www.vectara.com/blog/rag-with-user-defined-functions-based-reranking). \n",
+    "6. An LLM to for creating a [generative summary](https://docs.vectara.com/docs/learn/grounded-generation/grounded-generation-overview), based on the retrieved documents (context), including citations.\n",
     "\n",
     "See the [Vectara API documentation](https://docs.vectara.com/docs/) for more information on how to use the API.\n",
     "\n",
-    "This notebook shows how to use Vectara's [Chat](https://docs.vectara.com/docs/api-reference/chat-apis/chat-apis-overview) functionality."
+    "This notebook shows how to use Vectara's [Chat](https://docs.vectara.com/docs/api-reference/chat-apis/chat-apis-overview) functionality, which provides automatic storage of conversation history and ensures follow up questions consider that history."
    ]
   },
   {
@@ -30,7 +30,7 @@
     "# Getting Started\n",
     "\n",
     "To get started, use the following steps:\n",
-    "1. If you don't already have one, [Sign up](https://www.vectara.com/integrations/langchain) for your free Vectara account. Once you have completed your sign up you will have a Vectara customer ID. You can find your customer ID by clicking on your name, on the top-right of the Vectara console window.\n",
+    "1. If you don't already have one, [Sign up](https://www.vectara.com/integrations/langchain) for your free Vectara trial. Once you have completed your sign up you will have a Vectara customer ID. You can find your customer ID by clicking on your name, on the top-right of the Vectara console window.\n",
     "2. Within your account you can create one or more corpora. Each corpus represents an area that stores text data upon ingest from input documents. To create a corpus, use the **\"Create Corpus\"** button. You then provide a name to your corpus as well as a description. Optionally you can define filtering attributes and apply some advanced options. If you click on your created corpus, you can see its name and corpus ID right on the top.\n",
     "3. Next you'll need to create API keys to access the corpus. Click on the **\"Access Control\"** tab in the corpus view and then the **\"Create API Key\"** button. Give your key a name, and choose whether you want query-only or query+index for your key. Click \"Create\" and you now have an active API key. Keep this key confidential. \n",
     "\n",

docs/docs/integrations/providers/xai.ipynb

@@ -0,0 +1,97 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "2970dd75-8ebf-4b51-8282-9b454b8f356d",
+   "metadata": {},
+   "source": [
+    "# xAI\n",
+    "\n",
+    "[xAI](https://console.x.ai) offers an API to interact with Grok models.\n",
+    "\n",
+    "This example goes over how to use LangChain to interact with xAI models."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1c47fc36",
+   "metadata": {},
+   "source": [
+    "## Installation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1ecdb29d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade langchain-xai"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "89883202",
+   "metadata": {},
+   "source": [
+    "## Environment\n",
+    "\n",
+    "To use xAI, you'll need to [create an API key](https://console.x.ai/). The API key can be passed in as an init param ``xai_api_key`` or set as environment variable ``XAI_API_KEY``."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8304b4d9",
+   "metadata": {},
+   "source": [
+    "## Example"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "637bb53f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Querying chat models with xAI\n",
+    "\n",
+    "from langchain_xai import ChatXAI\n",
+    "\n",
+    "chat = ChatXAI(\n",
+    "    # xai_api_key=\"YOUR_API_KEY\",\n",
+    "    model=\"grok-beta\",\n",
+    ")\n",
+    "\n",
+    "# stream the response back from the model\n",
+    "for m in chat.stream(\"Tell me fun things to do in NYC\"):\n",
+    "    print(m.content, end=\"\", flush=True)\n",
+    "\n",
+    "# if you don't want to do streaming, you can use the invoke method\n",
+    "# chat.invoke(\"Tell me fun things to do in NYC\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/integrations/retrievers/self_query/vectara_self_query.ipynb

@@ -7,15 +7,15 @@
    "source": [
     "# Vectara self-querying \n",
     "\n",
-    "[Vectara](https://vectara.com/) provides a Trusted Generative AI platform, allowing organizations to rapidly create a ChatGPT-like experience (an AI assistant) which is grounded in the data, documents, and knowledge that they have (technically, it is Retrieval-Augmented-Generation-as-a-service). \n",
+    "[Vectara](https://vectara.com/) is the trusted AI Assistant and Agent platform which focuses on enterprise readiness for mission-critical applications.\n",
     "\n",
     "Vectara serverless RAG-as-a-service provides all the components of RAG behind an easy-to-use API, including:\n",
     "1. A way to extract text from files (PDF, PPT, DOCX, etc)\n",
     "2. ML-based chunking that provides state of the art performance.\n",
     "3. The [Boomerang](https://vectara.com/how-boomerang-takes-retrieval-augmented-generation-to-the-next-level-via-grounded-generation/) embeddings model.\n",
     "4. Its own internal vector database where text chunks and embedding vectors are stored.\n",
-    "5. A query service that automatically encodes the query into embedding, and retrieves the most relevant text segments (including support for [Hybrid Search](https://docs.vectara.com/docs/api-reference/search-apis/lexical-matching) and [MMR](https://vectara.com/get-diverse-results-and-comprehensive-summaries-with-vectaras-mmr-reranker/))\n",
-    "7. An LLM to for creating a [generative summary](https://docs.vectara.com/docs/learn/grounded-generation/grounded-generation-overview), based on the retrieved documents (context), including citations.\n",
+    "5. A query service that automatically encodes the query into embedding, and retrieves the most relevant text segments, including support for [Hybrid Search](https://docs.vectara.com/docs/api-reference/search-apis/lexical-matching) as well as multiple reranking options such as the [multi-lingual relevance reranker](https://www.vectara.com/blog/deep-dive-into-vectara-multilingual-reranker-v1-state-of-the-art-reranker-across-100-languages), [MMR](https://vectara.com/get-diverse-results-and-comprehensive-summaries-with-vectaras-mmr-reranker/), [UDF reranker](https://www.vectara.com/blog/rag-with-user-defined-functions-based-reranking). \n",
+    "6. An LLM to for creating a [generative summary](https://docs.vectara.com/docs/learn/grounded-generation/grounded-generation-overview), based on the retrieved documents (context), including citations.\n",
     "\n",
     "See the [Vectara API documentation](https://docs.vectara.com/docs/) for more information on how to use the API.\n",
     "\n",
@@ -30,7 +30,7 @@
     "# Getting Started\n",
     "\n",
     "To get started, use the following steps:\n",
-    "1. If you don't already have one, [Sign up](https://www.vectara.com/integrations/langchain) for your free Vectara account. Once you have completed your sign up you will have a Vectara customer ID. You can find your customer ID by clicking on your name, on the top-right of the Vectara console window.\n",
+    "1. If you don't already have one, [Sign up](https://www.vectara.com/integrations/langchain) for your free Vectara trial. Once you have completed your sign up you will have a Vectara customer ID. You can find your customer ID by clicking on your name, on the top-right of the Vectara console window.\n",
     "2. Within your account you can create one or more corpora. Each corpus represents an area that stores text data upon ingest from input documents. To create a corpus, use the **\"Create Corpus\"** button. You then provide a name to your corpus as well as a description. Optionally you can define filtering attributes and apply some advanced options. If you click on your created corpus, you can see its name and corpus ID right on the top.\n",
     "3. Next you'll need to create API keys to access the corpus. Click on the **\"Access Control\"** tab in the corpus view and then the **\"Create API Key\"** button. Give your key a name, and choose whether you want query-only or query+index for your key. Click \"Create\" and you now have an active API key. Keep this key confidential. \n",
     "\n",

docs/docs/integrations/text_embedding/naver.ipynb

@@ -17,14 +17,14 @@
    "source": [
     "# ClovaXEmbeddings\n",
     "\n",
-    "This notebook covers how to get started with embedding models provided by CLOVA Studio. For detailed documentation on `ClovaXEmbeddings` features and configuration options, please refer to the [API reference](https://python.langchain.com/api_reference/community/embeddings/langchain_community.naver.ClovaXEmbeddings.html).\n",
+    "This notebook covers how to get started with embedding models provided by CLOVA Studio. For detailed documentation on `ClovaXEmbeddings` features and configuration options, please refer to the [API reference](https://python.langchain.com/api_reference/community/embeddings/langchain_community.embeddings.naver.ClovaXEmbeddings.html).\n",
     "\n",
     "## Overview\n",
     "### Integration details\n",
     "\n",
     "| Provider | Package |\n",
     "|:--------:|:-------:|\n",
-    "| [Naver](/docs/integrations/providers/naver.mdx) | [langchain-community](https://python.langchain.com/api_reference/community/embeddings/langchain_community.naver.ClovaXEmbeddings.html) |\n",
+    "| [Naver](/docs/integrations/providers/naver.mdx) | [langchain-community](https://python.langchain.com/api_reference/community/embeddings/langchain_community.embeddings.naver.ClovaXEmbeddings.html) |\n",
     "\n",
     "## Setup\n",
     "\n",

docs/docs/integrations/tools/cdp_agentkit.ipynb

@@ -0,0 +1,332 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "id": "afaf8039",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_label: CDP\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e49f1e0d",
+   "metadata": {},
+   "source": [
+    "# CDP Agentkit Toolkit\n",
+    "\n",
+    "The `CDP Agentkit` toolkit contains tools that enable an LLM agent to interact with the [Coinbase Developer Platform](https://docs.cdp.coinbase.com/). The toolkit provides a wrapper around the CDP SDK, allowing agents to perform onchain operations like transfers, trades, and smart contract interactions.\n",
+    "\n",
+    "## Overview\n",
+    "\n",
+    "### Integration details\n",
+    "\n",
+    "| Class | Package | Serializable | JS support |  Package latest |\n",
+    "| :--- | :--- | :---: | :---: | :---: |\n",
+    "| CdpToolkit | `cdp-langchain` | ❌ | ❌ |  ![PyPI - Version](https://img.shields.io/pypi/v/cdp-langchain?style=flat-square&label=%20) |\n",
+    "\n",
+    "### Tool features\n",
+    "\n",
+    "The toolkit provides the following tools:\n",
+    "\n",
+    "1. **get_wallet_details** - Get details about the MPC Wallet\n",
+    "2. **get_balance** - Get balance for specific assets\n",
+    "3. **request_faucet_funds** - Request test tokens from faucet\n",
+    "4. **transfer** - Transfer assets between addresses\n",
+    "5. **trade** - Trade assets (Mainnet only)\n",
+    "6. **deploy_token** - Deploy ERC-20 token contracts\n",
+    "7. **mint_nft** - Mint NFTs from existing contracts\n",
+    "8. **deploy_nft** - Deploy new NFT contracts\n",
+    "9. **register_basename** - Register a basename for the wallet\n",
+    "\n",
+    "We encourage you to add your own tools, both using CDP and web2 APIs, to create an agent that is tailored to your needs.\n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "At a high-level, we will:\n",
+    "\n",
+    "1. Install the langchain package\n",
+    "2. Set up your CDP API credentials\n",
+    "3. Initialize the CDP wrapper and toolkit\n",
+    "4. Pass the tools to your agent with `toolkit.get_tools()`"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "72ee0c4b",
+   "metadata": {},
+   "source": [
+    "If you want to get automated tracing from runs of individual tools, you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a15d341e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
+    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0730d6a1",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "This toolkit lives in the `cdp-langchain` package:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "652d6238",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU cdp-langchain"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a38cde65",
+   "metadata": {},
+   "source": [
+    "#### Set Environment Variables\n",
+    "\n",
+    "To use this toolkit, you must first set the following environment variables to access the [CDP APIs](https://docs.cdp.coinbase.com/mpc-wallet/docs/quickstart) to create wallets and interact onchain. You can sign up for an API key for free on the [CDP Portal](https://cdp.coinbase.com/):"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cb09c344",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "for env_var in [\n",
+    "    \"CDP_API_KEY_NAME\",\n",
+    "    \"CDP_API_KEY_PRIVATE_KEY\",\n",
+    "]:\n",
+    "    if not os.getenv(env_var):\n",
+    "        os.environ[env_var] = getpass.getpass(f\"Enter your {env_var}: \")\n",
+    "\n",
+    "# Optional: Set network (defaults to base-sepolia)\n",
+    "os.environ[\"NETWORK_ID\"] = \"base-sepolia\"  # or \"base-mainnet\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5c5f2839",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "Now we can instantiate our toolkit:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "51a60dbe",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from cdp_langchain.agent_toolkits import CdpToolkit\n",
+    "from cdp_langchain.utils import CdpAgentkitWrapper\n",
+    "\n",
+    "# Initialize CDP wrapper\n",
+    "cdp = CdpAgentkitWrapper()\n",
+    "\n",
+    "# Create toolkit from wrapper\n",
+    "toolkit = CdpToolkit.from_cdp_agentkit_wrapper(cdp)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d11245ad",
+   "metadata": {},
+   "source": [
+    "## Tools\n",
+    "\n",
+    "View [available tools](#tool-features):"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "310bf18e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tools = toolkit.get_tools()\n",
+    "for tool in tools:\n",
+    "    print(tool.name)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "23e11cc9",
+   "metadata": {},
+   "source": [
+    "## Use within an agent\n",
+    "\n",
+    "We will need a LLM or chat model:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d1ee55bc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "llm = ChatOpenAI(model=\"gpt-4o-mini\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3a5bb5ca",
+   "metadata": {},
+   "source": [
+    "Initialize the agent with the tools:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f8a2c4b1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langgraph.prebuilt import create_react_agent\n",
+    "\n",
+    "tools = toolkit.get_tools()\n",
+    "agent_executor = create_react_agent(llm, tools)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b4a7c9d2",
+   "metadata": {},
+   "source": [
+    "Example usage:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c9a8e4f3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "example_query = \"Send 0.005 ETH to john2879.base.eth\"\n",
+    "\n",
+    "events = agent_executor.stream(\n",
+    "    {\"messages\": [(\"user\", example_query)]},\n",
+    "    stream_mode=\"values\",\n",
+    ")\n",
+    "for event in events:\n",
+    "    event[\"messages\"][-1].pretty_print()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e5a7c9d4",
+   "metadata": {},
+   "source": [
+    "Expected output:\n",
+    "```\n",
+    "Transferred 0.005 of eth to john2879.base.eth.\n",
+    "Transaction hash for the transfer: 0x78c7c2878659a0de216d0764fc87eff0d38b47f3315fa02ba493a83d8e782d1e\n",
+    "Transaction link for the transfer: https://sepolia.basescan.org/tx/0x78c7c2878659a0de216d0764fc87eff0d38b47f3315fa02ba493a83d8e782d1\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f5a7c9d5",
+   "metadata": {},
+   "source": [
+    "## CDP Toolkit Specific Features\n",
+    "\n",
+    "### Wallet Management\n",
+    "\n",
+    "The toolkit maintains an MPC wallet. The wallet data can be exported and imported to persist between sessions:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "g5a7c9d6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Export wallet data\n",
+    "wallet_data = cdp.export_wallet()\n",
+    "\n",
+    "# Import wallet data\n",
+    "values = {\"cdp_wallet_data\": wallet_data}\n",
+    "cdp = CdpAgentkitWrapper(**values)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "h5a7c9d7",
+   "metadata": {},
+   "source": [
+    "### Network Support\n",
+    "\n",
+    "The toolkit supports [multiple networks](https://docs.cdp.coinbase.com/cdp-sdk/docs/networks)\n",
+    "\n",
+    "### Gasless Transactions\n",
+    "\n",
+    "Some operations support gasless transactions on Base Mainnet:\n",
+    "- USDC transfers\n",
+    "- EURC transfers\n",
+    "- cbBTC transfers"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "i5a7c9d8",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all CDP features and configurations head to the [CDP docs](https://docs.cdp.coinbase.com/mpc-wallet/docs/welcome)."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/integrations/tools/databricks.ipynb

@@ -6,7 +6,7 @@
    "source": [
     "# Databricks Unity Catalog (UC)\n",
     "\n",
-    "This notebook shows how to use UC functions as LangChain tools.\n",
+    "This notebook shows how to use UC functions as LangChain tools, with both LangChain and LangGraph agent APIs.\n",
     "\n",
     "See Databricks documentation ([AWS](https://docs.databricks.com/en/sql/language-manual/sql-ref-syntax-ddl-create-sql-function.html)|[Azure](https://learn.microsoft.com/en-us/azure/databricks/sql/language-manual/sql-ref-syntax-ddl-create-sql-function)|[GCP](https://docs.gcp.databricks.com/en/sql/language-manual/sql-ref-syntax-ddl-create-sql-function.html)) to learn how to create SQL or Python functions in UC. Do not skip function and parameter comments, which are critical for LLMs to call functions properly.\n",
     "\n",
@@ -34,11 +34,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
    "source": [
-    "%pip install --upgrade --quiet databricks-sdk langchain-community mlflow"
+    "%pip install --upgrade --quiet databricks-sdk langchain-community langchain-databricks langgraph mlflow"
    ]
   },
   {
@@ -47,7 +55,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.chat_models.databricks import ChatDatabricks\n",
+    "from langchain_databricks import ChatDatabricks\n",
     "\n",
     "llm = ChatDatabricks(endpoint=\"databricks-meta-llama-3-70b-instruct\")"
    ]
@@ -58,6 +66,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "from databricks.sdk import WorkspaceClient\n",
     "from langchain_community.tools.databricks import UCFunctionToolkit\n",
     "\n",
     "tools = (\n",
@@ -76,9 +85,16 @@
   },
   {
    "cell_type": "markdown",
-   "metadata": {},
+   "metadata": {
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
    "source": [
-    "(Optional) To increase the retry time for getting a function execution response, set environment variable UC_TOOL_CLIENT_EXECUTION_TIMEOUT. Default retry time value is 120s."
+    "(Optional) To increase the retry time for getting a function execution response, set environment variable UC_TOOL_CLIENT_EXECUTION_TIMEOUT. Default retry time value is 120s.",
+     
+    "## LangGraph agent example"
    ]
   },
   {
@@ -92,9 +108,68 @@
     "os.environ[\"UC_TOOL_CLIENT_EXECUTION_TIMEOUT\"] = \"200\""
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
+   "source": [
+    "## LangGraph agent example"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 4,
+   "metadata": {
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'messages': [HumanMessage(content='36939 * 8922.4', additional_kwargs={}, response_metadata={}, id='1a10b10b-8e37-48c7-97a1-cac5006228d5'),\n",
+       "  AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_a8f3986f-4b91-40a3-8d6d-39f431dab69b', 'type': 'function', 'function': {'name': 'main__tools__python_exec', 'arguments': '{\"code\": \"print(36939 * 8922.4)\"}'}}]}, response_metadata={'prompt_tokens': 771, 'completion_tokens': 29, 'total_tokens': 800}, id='run-865c3613-20ba-4e80-afc8-fde1cfb26e5a-0', tool_calls=[{'name': 'main__tools__python_exec', 'args': {'code': 'print(36939 * 8922.4)'}, 'id': 'call_a8f3986f-4b91-40a3-8d6d-39f431dab69b', 'type': 'tool_call'}]),\n",
+       "  ToolMessage(content='{\"format\": \"SCALAR\", \"value\": \"329584533.59999996\\\\n\", \"truncated\": false}', name='main__tools__python_exec', id='8b63d4c8-1a3d-46a5-a719-393b2ef36770', tool_call_id='call_a8f3986f-4b91-40a3-8d6d-39f431dab69b'),\n",
+       "  AIMessage(content='The result of the multiplication is:\\n\\n329584533.59999996', additional_kwargs={}, response_metadata={'prompt_tokens': 846, 'completion_tokens': 22, 'total_tokens': 868}, id='run-22772404-611b-46e4-9956-b85e4a385f0f-0')]}"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langgraph.prebuilt import create_react_agent\n",
+    "\n",
+    "agent = create_react_agent(\n",
+    "    llm,\n",
+    "    tools,\n",
+    "    state_modifier=\"You are a helpful assistant. Make sure to use tool for information.\",\n",
+    ")\n",
+    "agent.invoke({\"messages\": [{\"role\": \"user\", \"content\": \"36939 * 8922.4\"}]})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
+   "source": [
+    "## LangChain agent example"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -118,7 +193,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
@@ -132,7 +207,9 @@
       "Invoking: `main__tools__python_exec` with `{'code': 'print(36939 * 8922.4)'}`\n",
       "\n",
       "\n",
-      "\u001b[0m\u001b[36;1m\u001b[1;3m{\"format\": \"SCALAR\", \"value\": \"329584533.59999996\\n\", \"truncated\": false}\u001b[0m\u001b[32;1m\u001b[1;3mThe result of the multiplication 36939 * 8922.4 is 329,584,533.60.\u001b[0m\n",
+      "\u001b[0m\u001b[36;1m\u001b[1;3m{\"format\": \"SCALAR\", \"value\": \"329584533.59999996\\n\", \"truncated\": false}\u001b[0m\u001b[32;1m\u001b[1;3mThe result of the multiplication is:\n",
+      "\n",
+      "329584533.59999996\u001b[0m\n",
       "\n",
       "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
@@ -141,10 +218,10 @@
      "data": {
       "text/plain": [
        "{'input': '36939 * 8922.4',\n",
-       " 'output': 'The result of the multiplication 36939 * 8922.4 is 329,584,533.60.'}"
+       " 'output': 'The result of the multiplication is:\\n\\n329584533.59999996'}"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -153,18 +230,11 @@
     "agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)\n",
     "agent_executor.invoke({\"input\": \"36939 * 8922.4\"})"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "llm",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -178,9 +248,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "version": "3.11.10"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

docs/docs/integrations/tools/google_books.ipynb

@@ -0,0 +1,270 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Google Books"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Overview"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Integration details\n",
+    "\n",
+    "The Google Books tool that supports the ReAct pattern and allows you to search the Google Books API. Google Books is the largest API in the world that keeps track of books in a curated manner. It has over 40 million entries, which can give users a significant amount of data."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Tool features\n",
+    "\n",
+    "Currently the tool has the following capabilities:\n",
+    "- Gathers the relevant information from the Google Books API using a key word search\n",
+    "- Formats the information into a readable output, and return the result to the agent"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setup\n",
+    "\n",
+    "Make sure `langchain-community` is installed."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "vscode": {
+     "languageId": "shellscript"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade --quiet  langchain-community"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Credentials\n",
+    "\n",
+    "You will need an API key from Google Books. You can do this by visiting and following the steps at [https://developers.google.com/books/docs/v1/using#APIKey](https://developers.google.com/books/docs/v1/using#APIKey).\n",
+    "\n",
+    "Then you will need to set the environment variable `GOOGLE_BOOKS_API_KEY` to your Google Books API key."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "To instantiate the tool import the Google Books tool and set your credentials."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "from langchain_community.tools.google_books import GoogleBooksQueryRun\n",
+    "from langchain_community.utilities.google_books import GoogleBooksAPIWrapper\n",
+    "\n",
+    "os.environ[\"GOOGLE_BOOKS_API_KEY\"] = \"<your Google Books API key>\"\n",
+    "tool = GoogleBooksQueryRun(api_wrapper=GoogleBooksAPIWrapper())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Invocation\n",
+    "\n",
+    "You can invoke the tool by calling the `run` method."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Here are 5 suggestions for books related to ai:\n",
+       "\n",
+       "1. \"AI's Take on the Stigma Against AI-Generated Content\" by Sandy Y. Greenleaf: In a world where artificial intelligence (AI) is rapidly advancing and transforming various industries, a new form of content creation has emerged: AI-generated content. However, despite its potential to revolutionize the way we produce and consume information, AI-generated content often faces a significant stigma. \"AI's Take on the Stigma Against AI-Generated Content\" is a groundbreaking book that delves into the heart of this issue, exploring the reasons behind the stigma and offering a fresh, unbiased perspective on the topic. Written from the unique viewpoint of an AI, this book provides readers with a comprehensive understanding of the challenges and opportunities surrounding AI-generated content. Through engaging narratives, thought-provoking insights, and real-world examples, this book challenges readers to reconsider their preconceptions about AI-generated content. It explores the potential benefits of embracing this technology, such as increased efficiency, creativity, and accessibility, while also addressing the concerns and drawbacks that contribute to the stigma. As you journey through the pages of this book, you'll gain a deeper understanding of the complex relationship between humans and AI in the realm of content creation. You'll discover how AI can be used as a tool to enhance human creativity, rather than replace it, and how collaboration between humans and machines can lead to unprecedented levels of innovation. Whether you're a content creator, marketer, business owner, or simply someone curious about the future of AI and its impact on our society, \"AI's Take on the Stigma Against AI-Generated Content\" is an essential read. With its engaging writing style, well-researched insights, and practical strategies for navigating this new landscape, this book will leave you equipped with the knowledge and tools needed to embrace the AI revolution and harness its potential for success. Prepare to have your assumptions challenged, your mind expanded, and your perspective on AI-generated content forever changed. Get ready to embark on a captivating journey that will redefine the way you think about the future of content creation.\n",
+       "You can read more at https://play.google.com/store/books/details?id=4iH-EAAAQBAJ&source=gbs_api\n",
+       "\n",
+       "2. \"AI Strategies For Web Development\" by Anderson Soares Furtado Oliveira: From fundamental to advanced strategies, unlock useful insights for creating innovative, user-centric websites while navigating the evolving landscape of AI ethics and security Key Features Explore AI's role in web development, from shaping projects to architecting solutions Master advanced AI strategies to build cutting-edge applications Anticipate future trends by exploring next-gen development environments, emerging interfaces, and security considerations in AI web development Purchase of the print or Kindle book includes a free PDF eBook Book Description If you're a web developer looking to leverage the power of AI in your projects, then this book is for you. Written by an AI and ML expert with more than 15 years of experience, AI Strategies for Web Development takes you on a transformative journey through the dynamic intersection of AI and web development, offering a hands-on learning experience.The first part of the book focuses on uncovering the profound impact of AI on web projects, exploring fundamental concepts, and navigating popular frameworks and tools. As you progress, you'll learn how to build smart AI applications with design intelligence, personalized user journeys, and coding assistants. Later, you'll explore how to future-proof your web development projects using advanced AI strategies and understand AI's impact on jobs. Toward the end, you'll immerse yourself in AI-augmented development, crafting intelligent web applications and navigating the ethical landscape.Packed with insights into next-gen development environments, AI-augmented practices, emerging realities, interfaces, and security governance, this web development book acts as your roadmap to staying ahead in the AI and web development domain. What you will learn Build AI-powered web projects with optimized models Personalize UX dynamically with AI, NLP, chatbots, and recommendations Explore AI coding assistants and other tools for advanced web development Craft data-driven, personalized experiences using pattern recognition Architect effective AI solutions while exploring the future of web development Build secure and ethical AI applications following TRiSM best practices Explore cutting-edge AI and web development trends Who this book is for This book is for web developers with experience in programming languages and an interest in keeping up with the latest trends in AI-powered web development. Full-stack, front-end, and back-end developers, UI/UX designers, software engineers, and web development enthusiasts will also find valuable information and practical guidelines for developing smarter websites with AI. To get the most out of this book, it is recommended that you have basic knowledge of programming languages such as HTML, CSS, and JavaScript, as well as a familiarity with machine learning concepts.\n",
+       "You can read more at https://play.google.com/store/books/details?id=FzYZEQAAQBAJ&source=gbs_api\n",
+       "\n",
+       "3. \"Artificial Intelligence for Students\" by Vibha Pandey: A multifaceted approach to develop an understanding of AI and its potential applications KEY FEATURES ● AI-informed focuses on AI foundation, applications, and methodologies. ● AI-inquired focuses on computational thinking and bias awareness. ● AI-innovate focuses on creative and critical thinking and the Capstone project. DESCRIPTION AI is a discipline in Computer Science that focuses on developing intelligent machines, machines that can learn and then teach themselves. If you are interested in AI, this book can definitely help you prepare for future careers in AI and related fields. The book is aligned with the CBSE course, which focuses on developing employability and vocational competencies of students in skill subjects. The book is an introduction to the basics of AI. It is divided into three parts – AI-informed, AI-inquired and AI-innovate. It will help you understand AI's implications on society and the world. You will also develop a deeper understanding of how it works and how it can be used to solve complex real-world problems. Additionally, the book will also focus on important skills such as problem scoping, goal setting, data analysis, and visualization, which are essential for success in AI projects. Lastly, you will learn how decision trees, neural networks, and other AI concepts are commonly used in real-world applications. By the end of the book, you will develop the skills and competencies required to pursue a career in AI. WHAT YOU WILL LEARN ● Get familiar with the basics of AI and Machine Learning. ● Understand how and where AI can be applied. ● Explore different applications of mathematical methods in AI. ● Get tips for improving your skills in Data Storytelling. ● Understand what is AI bias and how it can affect human rights. WHO THIS BOOK IS FOR This book is for CBSE class XI and XII students who want to learn and explore more about AI. Basic knowledge of Statistical concepts, Algebra, and Plotting of equations is a must. TABLE OF CONTENTS 1. Introduction: AI for Everyone 2. AI Applications and Methodologies 3. Mathematics in Artificial Intelligence 4. AI Values (Ethical Decision-Making) 5. Introduction to Storytelling 6. Critical and Creative Thinking 7. Data Analysis 8. Regression 9. Classification and Clustering 10. AI Values (Bias Awareness) 11. Capstone Project 12. Model Lifecycle (Knowledge) 13. Storytelling Through Data 14. AI Applications in Use in Real-World\n",
+       "You can read more at https://play.google.com/store/books/details?id=ptq1EAAAQBAJ&source=gbs_api\n",
+       "\n",
+       "4. \"The AI Book\" by Ivana Bartoletti, Anne Leslie and Shân M. Millie: Written by prominent thought leaders in the global fintech space, The AI Book aggregates diverse expertise into a single, informative volume and explains what artifical intelligence really means and how it can be used across financial services today. Key industry developments are explained in detail, and critical insights from cutting-edge practitioners offer first-hand information and lessons learned. Coverage includes: · Understanding the AI Portfolio: from machine learning to chatbots, to natural language processing (NLP); a deep dive into the Machine Intelligence Landscape; essentials on core technologies, rethinking enterprise, rethinking industries, rethinking humans; quantum computing and next-generation AI · AI experimentation and embedded usage, and the change in business model, value proposition, organisation, customer and co-worker experiences in today’s Financial Services Industry · The future state of financial services and capital markets – what’s next for the real-world implementation of AITech? · The innovating customer – users are not waiting for the financial services industry to work out how AI can re-shape their sector, profitability and competitiveness · Boardroom issues created and magnified by AI trends, including conduct, regulation & oversight in an algo-driven world, cybersecurity, diversity & inclusion, data privacy, the ‘unbundled corporation’ & the future of work, social responsibility, sustainability, and the new leadership imperatives · Ethical considerations of deploying Al solutions and why explainable Al is so important\n",
+       "You can read more at http://books.google.ca/books?id=oE3YDwAAQBAJ&dq=ai&hl=&source=gbs_api\n",
+       "\n",
+       "5. \"Artificial Intelligence in Society\" by OECD: The artificial intelligence (AI) landscape has evolved significantly from 1950 when Alan Turing first posed the question of whether machines can think. Today, AI is transforming societies and economies. It promises to generate productivity gains, improve well-being and help address global challenges, such as climate change, resource scarcity and health crises.\n",
+       "You can read more at https://play.google.com/store/books/details?id=eRmdDwAAQBAJ&source=gbs_api'"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "tool.run(\"ai\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### [Invoke directly with args](/docs/concepts/tools)\n",
+    "\n",
+    "See below for an direct invocation example."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "from langchain_community.tools.google_books import GoogleBooksQueryRun\n",
+    "from langchain_community.utilities.google_books import GoogleBooksAPIWrapper\n",
+    "\n",
+    "os.environ[\"GOOGLE_BOOKS_API_KEY\"] = \"<your Google Books API key>\"\n",
+    "tool = GoogleBooksQueryRun(api_wrapper=GoogleBooksAPIWrapper())\n",
+    "\n",
+    "tool.run(\"ai\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### [Invoke with ToolCall](/docs/concepts/tools)\n",
+    "\n",
+    "See below for a tool call example."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "from langchain_community.tools.google_books import GoogleBooksQueryRun\n",
+    "from langchain_community.utilities.google_books import GoogleBooksAPIWrapper\n",
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import PromptTemplate\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass()\n",
+    "os.environ[\"GOOGLE_BOOKS_API_KEY\"] = \"<your Google Books API key>\"\n",
+    "\n",
+    "tool = GoogleBooksQueryRun(api_wrapper=GoogleBooksAPIWrapper())\n",
+    "llm = ChatOpenAI(model=\"gpt-4o-mini\")\n",
+    "prompt = PromptTemplate.from_template(\n",
+    "    \"Return the keyword, and only the keyword, that the user is looking for from this text: {text}\"\n",
+    ")\n",
+    "\n",
+    "\n",
+    "def suggest_books(query):\n",
+    "    chain = prompt | llm | StrOutputParser()\n",
+    "    keyword = chain.invoke({\"text\": query})\n",
+    "    return tool.run(keyword)\n",
+    "\n",
+    "\n",
+    "suggestions = suggest_books(\"I need some information on AI\")\n",
+    "print(suggestions)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Chaining\n",
+    "\n",
+    "See the below example for chaining."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "from langchain import hub\n",
+    "from langchain.agents import AgentExecutor, create_tool_calling_agent\n",
+    "from langchain_community.tools.google_books import GoogleBooksQueryRun\n",
+    "from langchain_community.utilities.google_books import GoogleBooksAPIWrapper\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass()\n",
+    "os.environ[\"GOOGLE_BOOKS_API_KEY\"] = \"<your Google Books API key>\"\n",
+    "\n",
+    "tool = GoogleBooksQueryRun(api_wrapper=GoogleBooksAPIWrapper())\n",
+    "llm = ChatOpenAI(model=\"gpt-4o-mini\")\n",
+    "\n",
+    "instructions = \"\"\"You are a book suggesting assistant.\"\"\"\n",
+    "base_prompt = hub.pull(\"langchain-ai/openai-functions-template\")\n",
+    "prompt = base_prompt.partial(instructions=instructions)\n",
+    "\n",
+    "tools = [tool]\n",
+    "agent = create_tool_calling_agent(llm, tools, prompt)\n",
+    "agent_executor = AgentExecutor(\n",
+    "    agent=agent,\n",
+    "    tools=tools,\n",
+    "    verbose=True,\n",
+    ")\n",
+    "\n",
+    "agent_executor.invoke({\"input\": \"Can you recommend me some books related to ai?\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "The Google Books API can be found here: [https://developers.google.com/books](https://developers.google.com/books)"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/docs/integrations/tools/playwright.ipynb

@@ -101,7 +101,7 @@
    "source": [
     "## Instantiating a Browser Toolkit\n",
     "\n",
-    "It's always recommended to instantiate using the `from_browser` method so that the "
+    "It's always recommended to instantiate using the from_browser method so that the browser context is properly initialized and managed, ensuring seamless interaction and resource optimization."
    ]
   },
   {

docs/docs/integrations/tools/tavily_search.ipynb

@@ -186,7 +186,7 @@
     }
    ],
    "source": [
-    "# This is usually generated by a model, but we'll create a tool call directly for demon purposes.\n",
+    "# This is usually generated by a model, but we'll create a tool call directly for demo purposes.\n",
     "model_generated_tool_call = {\n",
     "    \"args\": {\"query\": \"euro 2024 host nation\"},\n",
     "    \"id\": \"1\",\n",

docs/docs/integrations/tools/zapier.ipynb

@@ -110,19 +110,19 @@
      "text": [
       "\n",
       "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3m I need to find the email and summarize it.\n",
+      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
+      "\u001B[32;1m\u001B[1;3m I need to find the email and summarize it.\n",
       "Action: Gmail: Find Email\n",
-      "Action Input: Find the latest email from Silicon Valley Bank\u001b[0m\n",
-      "Observation: \u001b[31;1m\u001b[1;3m{\"from__name\": \"Silicon Valley Bridge Bank, N.A.\", \"from__email\": \"sreply@svb.com\", \"body_plain\": \"Dear Clients, After chaotic, tumultuous & stressful days, we have clarity on path for SVB, FDIC is fully insuring all deposits & have an ask for clients & partners as we rebuild. Tim Mayopoulos <https://eml.svb.com/NjEwLUtBSy0yNjYAAAGKgoxUeBCLAyF_NxON97X4rKEaNBLG\", \"reply_to__email\": \"sreply@svb.com\", \"subject\": \"Meet the new CEO Tim Mayopoulos\", \"date\": \"Tue, 14 Mar 2023 23:42:29 -0500 (CDT)\", \"message_url\": \"https://mail.google.com/mail/u/0/#inbox/186e393b13cfdf0a\", \"attachment_count\": \"0\", \"to__emails\": \"ankush@langchain.dev\", \"message_id\": \"186e393b13cfdf0a\", \"labels\": \"IMPORTANT, CATEGORY_UPDATES, INBOX\"}\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I need to summarize the email and send it to the #test-zapier channel in Slack.\n",
+      "Action Input: Find the latest email from Silicon Valley Bank\u001B[0m\n",
+      "Observation: \u001B[31;1m\u001B[1;3m{\"from__name\": \"Silicon Valley Bridge Bank, N.A.\", \"from__email\": \"sreply@svb.com\", \"body_plain\": \"Dear Clients, After chaotic, tumultuous & stressful days, we have clarity on path for SVB, FDIC is fully insuring all deposits & have an ask for clients & partners as we rebuild. Tim Mayopoulos <https://eml.svb.com/NjEwLUtBSy0yNjYAAAGKgoxUeBCLAyF_NxON97X4rKEaNBLG\", \"reply_to__email\": \"sreply@svb.com\", \"subject\": \"Meet the new CEO Tim Mayopoulos\", \"date\": \"Tue, 14 Mar 2023 23:42:29 -0500 (CDT)\", \"message_url\": \"https://mail.google.com/mail/u/0/#inbox/186e393b13cfdf0a\", \"attachment_count\": \"0\", \"to__emails\": \"ankush@langchain.dev\", \"message_id\": \"186e393b13cfdf0a\", \"labels\": \"IMPORTANT, CATEGORY_UPDATES, INBOX\"}\u001B[0m\n",
+      "Thought:\u001B[32;1m\u001B[1;3m I need to summarize the email and send it to the #test-zapier channel in Slack.\n",
       "Action: Slack: Send Channel Message\n",
-      "Action Input: Send a slack message to the #test-zapier channel with the text \"Silicon Valley Bank has announced that Tim Mayopoulos is the new CEO. FDIC is fully insuring all deposits and they have an ask for clients and partners as they rebuild.\"\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3m{\"message__text\": \"Silicon Valley Bank has announced that Tim Mayopoulos is the new CEO. FDIC is fully insuring all deposits and they have an ask for clients and partners as they rebuild.\", \"message__permalink\": \"https://langchain.slack.com/archives/C04TSGU0RA7/p1678859932375259\", \"channel\": \"C04TSGU0RA7\", \"message__bot_profile__name\": \"Zapier\", \"message__team\": \"T04F8K3FZB5\", \"message__bot_id\": \"B04TRV4R74K\", \"message__bot_profile__deleted\": \"false\", \"message__bot_profile__app_id\": \"A024R9PQM\", \"ts_time\": \"2023-03-15T05:58:52Z\", \"message__bot_profile__icons__image_36\": \"https://avatars.slack-edge.com/2022-08-02/3888649620612_f864dc1bb794cf7d82b0_36.png\", \"message__blocks[]block_id\": \"kdZZ\", \"message__blocks[]elements[]type\": \"['rich_text_section']\"}\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
-      "Final Answer: I have sent a summary of the last email from Silicon Valley Bank to the #test-zapier channel in Slack.\u001b[0m\n",
+      "Action Input: Send a slack message to the #test-zapier channel with the text \"Silicon Valley Bank has announced that Tim Mayopoulos is the new CEO. FDIC is fully insuring all deposits and they have an ask for clients and partners as they rebuild.\"\u001B[0m\n",
+      "Observation: \u001B[36;1m\u001B[1;3m{\"message__text\": \"Silicon Valley Bank has announced that Tim Mayopoulos is the new CEO. FDIC is fully insuring all deposits and they have an ask for clients and partners as they rebuild.\", \"message__permalink\": \"https://langchain.slack.com/archives/C04TSGU0RA7/p1678859932375259\", \"channel\": \"C04TSGU0RA7\", \"message__bot_profile__name\": \"Zapier\", \"message__team\": \"T04F8K3FZB5\", \"message__bot_id\": \"B04TRV4R74K\", \"message__bot_profile__deleted\": \"false\", \"message__bot_profile__app_id\": \"A024R9PQM\", \"ts_time\": \"2023-03-15T05:58:52Z\", \"message__bot_profile__icons__image_36\": \"https://avatars.slack-edge.com/2022-08-02/3888649620612_f864dc1bb794cf7d82b0_36.png\", \"message__blocks[]block_id\": \"kdZZ\", \"message__blocks[]elements[]type\": \"['rich_text_section']\"}\u001B[0m\n",
+      "Thought:\u001B[32;1m\u001B[1;3m I now know the final answer.\n",
+      "Final Answer: I have sent a summary of the last email from Silicon Valley Bank to the #test-zapier channel in Slack.\u001B[0m\n",
       "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
+      "\u001B[1m> Finished chain.\u001B[0m\n"
      ]
     },
     {
@@ -286,18 +286,18 @@
      "text": [
       "\n",
       "\n",
-      "\u001b[1m> Entering new SimpleSequentialChain chain...\u001b[0m\n",
-      "\u001b[36;1m\u001b[1;3m{\"from__name\": \"Silicon Valley Bridge Bank, N.A.\", \"from__email\": \"sreply@svb.com\", \"body_plain\": \"Dear Clients, After chaotic, tumultuous & stressful days, we have clarity on path for SVB, FDIC is fully insuring all deposits & have an ask for clients & partners as we rebuild. Tim Mayopoulos <https://eml.svb.com/NjEwLUtBSy0yNjYAAAGKgoxUeBCLAyF_NxON97X4rKEaNBLG\", \"reply_to__email\": \"sreply@svb.com\", \"subject\": \"Meet the new CEO Tim Mayopoulos\", \"date\": \"Tue, 14 Mar 2023 23:42:29 -0500 (CDT)\", \"message_url\": \"https://mail.google.com/mail/u/0/#inbox/186e393b13cfdf0a\", \"attachment_count\": \"0\", \"to__emails\": \"ankush@langchain.dev\", \"message_id\": \"186e393b13cfdf0a\", \"labels\": \"IMPORTANT, CATEGORY_UPDATES, INBOX\"}\u001b[0m\n",
-      "\u001b[33;1m\u001b[1;3m\n",
+      "\u001B[1m> Entering new SimpleSequentialChain chain...\u001B[0m\n",
+      "\u001B[36;1m\u001B[1;3m{\"from__name\": \"Silicon Valley Bridge Bank, N.A.\", \"from__email\": \"sreply@svb.com\", \"body_plain\": \"Dear Clients, After chaotic, tumultuous & stressful days, we have clarity on path for SVB, FDIC is fully insuring all deposits & have an ask for clients & partners as we rebuild. Tim Mayopoulos <https://eml.svb.com/NjEwLUtBSy0yNjYAAAGKgoxUeBCLAyF_NxON97X4rKEaNBLG\", \"reply_to__email\": \"sreply@svb.com\", \"subject\": \"Meet the new CEO Tim Mayopoulos\", \"date\": \"Tue, 14 Mar 2023 23:42:29 -0500 (CDT)\", \"message_url\": \"https://mail.google.com/mail/u/0/#inbox/186e393b13cfdf0a\", \"attachment_count\": \"0\", \"to__emails\": \"ankush@langchain.dev\", \"message_id\": \"186e393b13cfdf0a\", \"labels\": \"IMPORTANT, CATEGORY_UPDATES, INBOX\"}\u001B[0m\n",
+      "\u001B[33;1m\u001B[1;3m\n",
       "Dear Silicon Valley Bridge Bank, \n",
       "\n",
       "Thank you for your email and the update regarding your new CEO Tim Mayopoulos. We appreciate your dedication to keeping your clients and partners informed and we look forward to continuing our relationship with you. \n",
       "\n",
       "Best regards, \n",
-      "[Your Name]\u001b[0m\n",
-      "\u001b[38;5;200m\u001b[1;3m{\"message__text\": \"Dear Silicon Valley Bridge Bank, \\n\\nThank you for your email and the update regarding your new CEO Tim Mayopoulos. We appreciate your dedication to keeping your clients and partners informed and we look forward to continuing our relationship with you. \\n\\nBest regards, \\n[Your Name]\", \"message__permalink\": \"https://langchain.slack.com/archives/D04TKF5BBHU/p1678859968241629\", \"channel\": \"D04TKF5BBHU\", \"message__bot_profile__name\": \"Zapier\", \"message__team\": \"T04F8K3FZB5\", \"message__bot_id\": \"B04TRV4R74K\", \"message__bot_profile__deleted\": \"false\", \"message__bot_profile__app_id\": \"A024R9PQM\", \"ts_time\": \"2023-03-15T05:59:28Z\", \"message__blocks[]block_id\": \"p7i\", \"message__blocks[]elements[]elements[]type\": \"[['text']]\", \"message__blocks[]elements[]type\": \"['rich_text_section']\"}\u001b[0m\n",
+      "[Your Name]\u001B[0m\n",
+      "\u001B[38;5;200m\u001B[1;3m{\"message__text\": \"Dear Silicon Valley Bridge Bank, \\n\\nThank you for your email and the update regarding your new CEO Tim Mayopoulos. We appreciate your dedication to keeping your clients and partners informed and we look forward to continuing our relationship with you. \\n\\nBest regards, \\n[Your Name]\", \"message__permalink\": \"https://langchain.slack.com/archives/D04TKF5BBHU/p1678859968241629\", \"channel\": \"D04TKF5BBHU\", \"message__bot_profile__name\": \"Zapier\", \"message__team\": \"T04F8K3FZB5\", \"message__bot_id\": \"B04TRV4R74K\", \"message__bot_profile__deleted\": \"false\", \"message__bot_profile__app_id\": \"A024R9PQM\", \"ts_time\": \"2023-03-15T05:59:28Z\", \"message__blocks[]block_id\": \"p7i\", \"message__blocks[]elements[]elements[]type\": \"[['text']]\", \"message__blocks[]elements[]type\": \"['rich_text_section']\"}\u001B[0m\n",
       "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
+      "\u001B[1m> Finished chain.\u001B[0m\n"
      ]
     },
     {
@@ -325,7 +325,7 @@
    "id": "09ff954e-45f2-4595-92ea-91627abde4a0",
    "metadata": {},
    "source": [
-    "## <a id=\"oauth\">Example Using OAuth Access Token</a>\n",
+    "## Example Using OAuth Access Token{#oauth}\n",
     "The below snippet shows how to initialize the wrapper with a procured OAuth access token. Note the argument being passed in as opposed to setting an environment variable. Review the [authentication docs](https://nla.zapier.com/docs/authentication/#oauth-credentials) for full user-facing oauth developer support.\n",
     "\n",
     "The developer is tasked with handling the OAuth handshaking to procure and refresh the access token."

docs/docs/integrations/vectorstores/kinetica.ipynb

@@ -33,35 +33,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.2.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.0\u001b[0m\n",
-      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
-      "Note: you may need to restart the kernel to use updated packages.\n",
-      "Requirement already satisfied: gpudb==7.2.0.0b in /home/anindyam/kinetica/kinetica-github/langchain/libs/langchain/.venv/lib/python3.8/site-packages (7.2.0.0b0)\n",
-      "Requirement already satisfied: future in /home/anindyam/kinetica/kinetica-github/langchain/libs/langchain/.venv/lib/python3.8/site-packages (from gpudb==7.2.0.0b) (0.18.3)\n",
-      "Requirement already satisfied: pyzmq in /home/anindyam/kinetica/kinetica-github/langchain/libs/langchain/.venv/lib/python3.8/site-packages (from gpudb==7.2.0.0b) (25.1.2)\n",
-      "\n",
-      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.2.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.0\u001b[0m\n",
-      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
-      "Note: you may need to restart the kernel to use updated packages.\n",
-      "\n",
-      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.2.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.0\u001b[0m\n",
-      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
-      "Note: you may need to restart the kernel to use updated packages.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "# Pip install necessary package\n",
     "%pip install --upgrade --quiet  langchain-openai langchain-community\n",
-    "%pip install gpudb==7.2.0.9\n",
+    "%pip install gpudb>=7.2.2.0 \n",
     "%pip install --upgrade --quiet  tiktoken"
    ]
   },
@@ -74,7 +52,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -87,7 +65,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
@@ -96,7 +74,7 @@
        "False"
       ]
      },
-     "execution_count": 25,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -110,38 +88,30 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores import (\n",
-    "    DistanceStrategy,\n",
     "    Kinetica,\n",
     "    KineticaSettings,\n",
     ")\n",
-    "from langchain_core.documents import Document\n",
-    "from langchain_openai import OpenAIEmbeddings\n",
-    "from langchain_text_splitters import CharacterTextSplitter"
+    "from langchain_openai import OpenAIEmbeddings"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
-    "loader = TextLoader(\"../../how_to/state_of_the_union.txt\")\n",
-    "documents = loader.load()\n",
-    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
-    "docs = text_splitter.split_documents(documents)\n",
-    "\n",
-    "embeddings = OpenAIEmbeddings()"
+    "embeddings = OpenAIEmbeddings(model=\"text-embedding-3-large\")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -157,6 +127,81 @@
     "    return KineticaSettings(host=HOST, username=USERNAME, password=PASSWORD)"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from uuid import uuid4\n",
+    "\n",
+    "from langchain_core.documents import Document\n",
+    "\n",
+    "document_1 = Document(\n",
+    "    page_content=\"I had chocalate chip pancakes and scrambled eggs for breakfast this morning.\",\n",
+    "    metadata={\"source\": \"tweet\"},\n",
+    ")\n",
+    "\n",
+    "document_2 = Document(\n",
+    "    page_content=\"The weather forecast for tomorrow is cloudy and overcast, with a high of 62 degrees.\",\n",
+    "    metadata={\"source\": \"news\"},\n",
+    ")\n",
+    "\n",
+    "document_3 = Document(\n",
+    "    page_content=\"Building an exciting new project with LangChain - come check it out!\",\n",
+    "    metadata={\"source\": \"tweet\"},\n",
+    ")\n",
+    "\n",
+    "document_4 = Document(\n",
+    "    page_content=\"Robbers broke into the city bank and stole $1 million in cash.\",\n",
+    "    metadata={\"source\": \"news\"},\n",
+    ")\n",
+    "\n",
+    "document_5 = Document(\n",
+    "    page_content=\"Wow! That was an amazing movie. I can't wait to see it again.\",\n",
+    "    metadata={\"source\": \"tweet\"},\n",
+    ")\n",
+    "\n",
+    "document_6 = Document(\n",
+    "    page_content=\"Is the new iPhone worth the price? Read this review to find out.\",\n",
+    "    metadata={\"source\": \"website\"},\n",
+    ")\n",
+    "\n",
+    "document_7 = Document(\n",
+    "    page_content=\"The top 10 soccer players in the world right now.\",\n",
+    "    metadata={\"source\": \"website\"},\n",
+    ")\n",
+    "\n",
+    "document_8 = Document(\n",
+    "    page_content=\"LangGraph is the best framework for building stateful, agentic applications!\",\n",
+    "    metadata={\"source\": \"tweet\"},\n",
+    ")\n",
+    "\n",
+    "document_9 = Document(\n",
+    "    page_content=\"The stock market is down 500 points today due to fears of a recession.\",\n",
+    "    metadata={\"source\": \"news\"},\n",
+    ")\n",
+    "\n",
+    "document_10 = Document(\n",
+    "    page_content=\"I have a bad feeling I am going to get deleted :(\",\n",
+    "    metadata={\"source\": \"tweet\"},\n",
+    ")\n",
+    "\n",
+    "documents = [\n",
+    "    document_1,\n",
+    "    document_2,\n",
+    "    document_3,\n",
+    "    document_4,\n",
+    "    document_5,\n",
+    "    document_6,\n",
+    "    document_7,\n",
+    "    document_8,\n",
+    "    document_9,\n",
+    "    document_10,\n",
+    "]\n",
+    "uuids = [str(uuid4()) for _ in range(len(documents))]"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -166,207 +211,92 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 8,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['05e5a484-0273-49d1-90eb-1276baca31de',\n",
+       " 'd98b808f-dc0b-4328-bdbf-88f6b2ab6040',\n",
+       " 'ba0968d4-e344-4285-ae0f-f5199b56f9d6',\n",
+       " 'a25393b8-6539-45b5-993e-ea16d01941ec',\n",
+       " '804a37e3-1278-4b60-8b02-36b159ee8c1a',\n",
+       " '9688b594-3dc6-41d2-a937-babf8ff24c2f',\n",
+       " '40f7b8fe-67c7-489a-a5a5-7d3965e33bba',\n",
+       " 'b4fc1376-c113-41e9-8f16-f9320517bedd',\n",
+       " '4d94d089-fdde-442b-84ab-36d9fe0670c8',\n",
+       " '66fdb79d-49ce-4b06-901a-fda6271baf2a']"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "# The Kinetica Module will try to create a table with the name of the collection.\n",
     "# So, make sure that the collection name is unique and the user has the permission to create a table.\n",
     "\n",
-    "COLLECTION_NAME = \"state_of_the_union_test\"\n",
+    "COLLECTION_NAME = \"langchain_example\"\n",
     "connection = create_config()\n",
     "\n",
-    "db = Kinetica.from_documents(\n",
-    "    embedding=embeddings,\n",
-    "    documents=docs,\n",
+    "db = Kinetica(\n",
+    "    connection,\n",
+    "    embeddings,\n",
     "    collection_name=COLLECTION_NAME,\n",
-    "    config=connection,\n",
-    ")"
+    ")\n",
+    "\n",
+    "db.add_documents(documents=documents, ids=uuids)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
-    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
-    "docs_with_score = db.similarity_search_with_score(query)"
+    "# query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "# docs_with_score = db.similarity_search_with_score(query)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "--------------------------------------------------------------------------------\n",
-      "Score:  0.6077010035514832\n",
-      "Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
       "\n",
-      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
+      "Similarity Search\n",
+      "* Building an exciting new project with LangChain - come check it out! [{'source': 'tweet'}]\n",
+      "* LangGraph is the best framework for building stateful, agentic applications! [{'source': 'tweet'}]\n",
       "\n",
-      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
-      "\n",
-      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n",
-      "--------------------------------------------------------------------------------\n",
-      "--------------------------------------------------------------------------------\n",
-      "Score:  0.6077010035514832\n",
-      "Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
-      "\n",
-      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
-      "\n",
-      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
-      "\n",
-      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n",
-      "--------------------------------------------------------------------------------\n",
-      "--------------------------------------------------------------------------------\n",
-      "Score:  0.6596046090126038\n",
-      "A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \n",
-      "\n",
-      "And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \n",
-      "\n",
-      "We can do both. At our border, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling.  \n",
-      "\n",
-      "We’ve set up joint patrols with Mexico and Guatemala to catch more human traffickers.  \n",
-      "\n",
-      "We’re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. \n",
-      "\n",
-      "We’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.\n",
-      "--------------------------------------------------------------------------------\n",
-      "--------------------------------------------------------------------------------\n",
-      "Score:  0.6597143411636353\n",
-      "A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \n",
-      "\n",
-      "And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \n",
-      "\n",
-      "We can do both. At our border, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling.  \n",
-      "\n",
-      "We’ve set up joint patrols with Mexico and Guatemala to catch more human traffickers.  \n",
-      "\n",
-      "We’re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. \n",
-      "\n",
-      "We’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.\n",
-      "--------------------------------------------------------------------------------\n"
+      "Similarity search with score\n",
+      "* [SIM=0.945397] The weather forecast for tomorrow is cloudy and overcast, with a high of 62 degrees. [{'source': 'news'}]\n"
      ]
     }
    ],
    "source": [
-    "for doc, score in docs_with_score:\n",
-    "    print(\"-\" * 80)\n",
-    "    print(\"Score: \", score)\n",
-    "    print(doc.page_content)\n",
-    "    print(\"-\" * 80)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Maximal Marginal Relevance Search (MMR)\n",
-    "Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 32,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "docs_with_score = db.max_marginal_relevance_search_with_score(query)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 33,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "--------------------------------------------------------------------------------\n",
-      "Score:  0.6077010035514832\n",
-      "Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
-      "\n",
-      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
-      "\n",
-      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
-      "\n",
-      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n",
-      "--------------------------------------------------------------------------------\n",
-      "--------------------------------------------------------------------------------\n",
-      "Score:  0.6852865219116211\n",
-      "It is going to transform America and put us on a path to win the economic competition of the 21st Century that we face with the rest of the world—particularly with China.  \n",
-      "\n",
-      "As I’ve told Xi Jinping, it is never a good bet to bet against the American people. \n",
-      "\n",
-      "We’ll create good jobs for millions of Americans, modernizing roads, airports, ports, and waterways all across America. \n",
-      "\n",
-      "And we’ll do it all to withstand the devastating effects of the climate crisis and promote environmental justice. \n",
-      "\n",
-      "We’ll build a national network of 500,000 electric vehicle charging stations, begin to replace poisonous lead pipes—so every child—and every American—has clean water to drink at home and at school, provide affordable high-speed internet for every American—urban, suburban, rural, and tribal communities. \n",
-      "\n",
-      "4,000 projects have already been announced. \n",
-      "\n",
-      "And tonight, I’m announcing that this year we will start fixing over 65,000 miles of highway and 1,500 bridges in disrepair.\n",
-      "--------------------------------------------------------------------------------\n",
-      "--------------------------------------------------------------------------------\n",
-      "Score:  0.6866700053215027\n",
-      "We can’t change how divided we’ve been. But we can change how we move forward—on COVID-19 and other issues we must face together. \n",
-      "\n",
-      "I recently visited the New York City Police Department days after the funerals of Officer Wilbert Mora and his partner, Officer Jason Rivera. \n",
-      "\n",
-      "They were responding to a 9-1-1 call when a man shot and killed them with a stolen gun. \n",
-      "\n",
-      "Officer Mora was 27 years old. \n",
-      "\n",
-      "Officer Rivera was 22. \n",
-      "\n",
-      "Both Dominican Americans who’d grown up on the same streets they later chose to patrol as police officers. \n",
-      "\n",
-      "I spoke with their families and told them that we are forever in debt for their sacrifice, and we will carry on their mission to restore the trust and safety every community deserves. \n",
-      "\n",
-      "I’ve worked on these issues a long time. \n",
-      "\n",
-      "I know what works: Investing in crime prevention and community police officers who’ll walk the beat, who’ll know the neighborhood, and who can restore trust and safety.\n",
-      "--------------------------------------------------------------------------------\n",
-      "--------------------------------------------------------------------------------\n",
-      "Score:  0.6936529278755188\n",
-      "But cancer from prolonged exposure to burn pits ravaged Heath’s lungs and body. \n",
-      "\n",
-      "Danielle says Heath was a fighter to the very end. \n",
-      "\n",
-      "He didn’t know how to stop fighting, and neither did she. \n",
-      "\n",
-      "Through her pain she found purpose to demand we do better. \n",
-      "\n",
-      "Tonight, Danielle—we are. \n",
-      "\n",
-      "The VA is pioneering new ways of linking toxic exposures to diseases, already helping more veterans get benefits. \n",
-      "\n",
-      "And tonight, I’m announcing we’re expanding eligibility to veterans suffering from nine respiratory cancers. \n",
-      "\n",
-      "I’m also calling on Congress: pass a law to make sure veterans devastated by toxic exposures in Iraq and Afghanistan finally get the benefits and comprehensive health care they deserve. \n",
-      "\n",
-      "And fourth, let’s end cancer as we know it. \n",
-      "\n",
-      "This is personal to me and Jill, to Kamala, and to so many of you. \n",
-      "\n",
-      "Cancer is the #2 cause of death in America–second only to heart disease.\n",
-      "--------------------------------------------------------------------------------\n"
-     ]
-    }
-   ],
-   "source": [
-    "for doc, score in docs_with_score:\n",
-    "    print(\"-\" * 80)\n",
-    "    print(\"Score: \", score)\n",
-    "    print(doc.page_content)\n",
-    "    print(\"-\" * 80)"
+    "print()\n",
+    "print(\"Similarity Search\")\n",
+    "results = db.similarity_search(\n",
+    "    \"LangChain provides abstractions to make working with LLMs easy\",\n",
+    "    k=2,\n",
+    "    filter={\"source\": \"tweet\"},\n",
+    ")\n",
+    "for res in results:\n",
+    "    print(f\"* {res.page_content} [{res.metadata}]\")\n",
+    "\n",
+    "print()\n",
+    "print(\"Similarity search with score\")\n",
+    "results = db.similarity_search_with_score(\n",
+    "    \"Will it be hot tomorrow?\", k=1, filter={\"source\": \"news\"}\n",
+    ")\n",
+    "for res, score in results:\n",
+    "    print(f\"* [SIM={score:3f}] {res.page_content} [{res.metadata}]\")"
    ]
   },
   {
@@ -381,7 +311,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -402,16 +332,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 35,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "['b94dc67c-ce7e-11ee-b8cb-b940b0e45762']"
+       "['68c4c679-c4d9-4f2d-bf01-f6c4f2181503']"
       ]
      },
-     "execution_count": 35,
+     "execution_count": 12,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -422,7 +352,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -431,16 +361,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 37,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "(Document(page_content='foo'), 0.0)"
+       "(Document(metadata={}, page_content='foo'), 0.0015394920483231544)"
       ]
      },
-     "execution_count": 37,
+     "execution_count": 14,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -451,17 +381,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "(Document(page_content='A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \\n\\nAnd if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \\n\\nWe can do both. At our border, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling.  \\n\\nWe’ve set up joint patrols with Mexico and Guatemala to catch more human traffickers.  \\n\\nWe’re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. \\n\\nWe’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.', metadata={'source': '../../how_to/state_of_the_union.txt'}),\n",
-       " 0.6946534514427185)"
+       "(Document(metadata={'source': 'tweet'}, page_content='Building an exciting new project with LangChain - come check it out!'),\n",
+       " 1.2609431743621826)"
       ]
      },
-     "execution_count": 38,
+     "execution_count": 15,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -481,12 +411,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [],
    "source": [
     "db = Kinetica.from_documents(\n",
-    "    documents=docs,\n",
+    "    documents=documents,\n",
     "    embedding=embeddings,\n",
     "    collection_name=COLLECTION_NAME,\n",
     "    config=connection,\n",
@@ -496,7 +426,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 40,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -505,17 +435,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 41,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "(Document(page_content='A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \\n\\nAnd if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \\n\\nWe can do both. At our border, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling.  \\n\\nWe’ve set up joint patrols with Mexico and Guatemala to catch more human traffickers.  \\n\\nWe’re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. \\n\\nWe’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.', metadata={'source': '../../how_to/state_of_the_union.txt'}),\n",
-       " 0.6946534514427185)"
+       "(Document(metadata={'source': 'tweet'}, page_content='Building an exciting new project with LangChain - come check it out!'),\n",
+       " 1.260920763015747)"
       ]
      },
-     "execution_count": 41,
+     "execution_count": 18,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -533,7 +463,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 42,
+   "execution_count": 19,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -542,14 +472,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 43,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "tags=['Kinetica', 'OpenAIEmbeddings'] vectorstore=<langchain_community.vectorstores.kinetica.Kinetica object at 0x7f1644375e20>\n"
+      "tags=['Kinetica', 'OpenAIEmbeddings'] vectorstore=<langchain_community.vectorstores.kinetica.Kinetica object at 0x7a48142b2230> search_kwargs={}\n"
      ]
     }
    ],
@@ -574,7 +504,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.10"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/docs/integrations/vectorstores/vectara.ipynb

@@ -7,15 +7,15 @@
    "source": [
     "# Vectara\n",
     "\n",
-    "[Vectara](https://vectara.com/) provides a Trusted Generative AI platform, allowing organizations to rapidly create a ChatGPT-like experience (an AI assistant) which is grounded in the data, documents, and knowledge that they have (technically, it is Retrieval-Augmented-Generation-as-a-service). \n",
+    "[Vectara](https://vectara.com/) is the trusted AI Assistant and Agent platform which focuses on enterprise readiness for mission-critical applications.\n",
     "\n",
     "Vectara serverless RAG-as-a-service provides all the components of RAG behind an easy-to-use API, including:\n",
     "1. A way to extract text from files (PDF, PPT, DOCX, etc)\n",
     "2. ML-based chunking that provides state of the art performance.\n",
     "3. The [Boomerang](https://vectara.com/how-boomerang-takes-retrieval-augmented-generation-to-the-next-level-via-grounded-generation/) embeddings model.\n",
     "4. Its own internal vector database where text chunks and embedding vectors are stored.\n",
-    "5. A query service that automatically encodes the query into embedding, and retrieves the most relevant text segments (including support for [Hybrid Search](https://docs.vectara.com/docs/api-reference/search-apis/lexical-matching) and [MMR](https://vectara.com/get-diverse-results-and-comprehensive-summaries-with-vectaras-mmr-reranker/))\n",
-    "7. An LLM to for creating a [generative summary](https://docs.vectara.com/docs/learn/grounded-generation/grounded-generation-overview), based on the retrieved documents (context), including citations.\n",
+    "5. A query service that automatically encodes the query into embedding, and retrieves the most relevant text segments (including support for [Hybrid Search](https://docs.vectara.com/docs/api-reference/search-apis/lexical-matching) as well as multiple reranking options such as the [multi-lingual relevance reranker](https://www.vectara.com/blog/deep-dive-into-vectara-multilingual-reranker-v1-state-of-the-art-reranker-across-100-languages), [MMR](https://vectara.com/get-diverse-results-and-comprehensive-summaries-with-vectaras-mmr-reranker/), [UDF reranker](https://www.vectara.com/blog/rag-with-user-defined-functions-based-reranking). \n",
+    "6. An LLM to for creating a [generative summary](https://docs.vectara.com/docs/learn/grounded-generation/grounded-generation-overview), based on the retrieved documents (context), including citations.\n",
     "\n",
     "See the [Vectara API documentation](https://docs.vectara.com/docs/) for more information on how to use the API.\n",
     "\n",
@@ -32,7 +32,7 @@
     "# Getting Started\n",
     "\n",
     "To get started, use the following steps:\n",
-    "1. If you don't already have one, [Sign up](https://www.vectara.com/integrations/langchain) for your free Vectara account. Once you have completed your sign up you will have a Vectara customer ID. You can find your customer ID by clicking on your name, on the top-right of the Vectara console window.\n",
+    "1. If you don't already have one, [Sign up](https://www.vectara.com/integrations/langchain) for your free Vectara trial. Once you have completed your sign up you will have a Vectara customer ID. You can find your customer ID by clicking on your name, on the top-right of the Vectara console window.\n",
     "2. Within your account you can create one or more corpora. Each corpus represents an area that stores text data upon ingest from input documents. To create a corpus, use the **\"Create Corpus\"** button. You then provide a name to your corpus as well as a description. Optionally you can define filtering attributes and apply some advanced options. If you click on your created corpus, you can see its name and corpus ID right on the top.\n",
     "3. Next you'll need to create API keys to access the corpus. Click on the **\"Access Control\"** tab in the corpus view and then the **\"Create API Key\"** button. Give your key a name, and choose whether you want query-only or query+index for your key. Click \"Create\" and you now have an active API key. Keep this key confidential. \n",
     "\n",

docs/docs/introduction.mdx

@@ -19,8 +19,8 @@ import useBaseUrl from '@docusaurus/useBaseUrl';
 <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'),
   }}
   style={{ width: "100%" }}
   title="LangChain Framework Overview"
@@ -29,9 +29,9 @@ import useBaseUrl from '@docusaurus/useBaseUrl';
 Concretely, the framework consists of the following open-source libraries:
 
 - **`langchain-core`**: Base abstractions and LangChain Expression Language.
-- **`langchain-community`**: Third party integrations.
-  - Partner packages (e.g. **`langchain-openai`**, **`langchain-anthropic`**, etc.): Some integrations have been further split into their own lightweight packages that only depend on **`langchain-core`**.
+- Integration packages (e.g. **`langchain-openai`**, **`langchain-anthropic`**, etc.): Important integrations have been split into lightweight packages that are co-maintained by the LangChain team and the integration developers.
 - **`langchain`**: Chains, agents, and retrieval strategies that make up an application's cognitive architecture.
+- **`langchain-community`**: Third-party integrations that are community maintained.
 - **[LangGraph](https://langchain-ai.github.io/langgraph)**: Build robust and stateful multi-actor applications with LLMs by modeling steps as edges and nodes in a graph. Integrates smoothly with LangChain, but can be used without it.
 - **[LangServe](/docs/langserve)**: Deploy LangChain chains as REST APIs.
 - **[LangSmith](https://docs.smith.langchain.com)**: A developer platform that lets you debug, test, evaluate, and monitor LLM applications.
@@ -62,7 +62,8 @@ Explore the full list of LangChain tutorials [here](/docs/tutorials), and check
 
 [Here](/docs/how_to) you’ll find short answers to “How do I….?” types of questions.
 These how-to guides don’t cover topics in depth – you’ll find that material in the [Tutorials](/docs/tutorials) and the [API Reference](https://python.langchain.com/api_reference/).
-However, these guides will help you quickly accomplish common tasks.
+However, these guides will help you quickly accomplish common tasks using [chat models](/docs/how_to/#chat-models),
+[vector stores](/docs/how_to/#vector-stores), and other common LangChain components.
 
 Check out [LangGraph-specific how-tos here](https://langchain-ai.github.io/langgraph/how-tos/).
 
@@ -72,6 +73,13 @@ Introductions to all the key parts of LangChain you’ll need to know! [Here](/d
 
 For a deeper dive into LangGraph concepts, check out [this page](https://langchain-ai.github.io/langgraph/concepts/).
 
+## [Integrations](integrations/providers/index.mdx)
+
+LangChain is part of a rich ecosystem of tools that integrate with our framework and build on top of it.
+If you're looking to get up and running quickly with [chat models](/docs/integrations/chat/), [vector stores](/docs/integrations/vectorstores/),
+or other LangChain components from a specific provider, check out our growing list of [integrations](/docs/integrations/providers/).
+
+
 ## [API reference](https://python.langchain.com/api_reference/)
 Head to the reference section for full documentation of all classes and methods in the LangChain Python packages.
 
@@ -91,8 +99,5 @@ See what changed in v0.3, learn how to migrate legacy code, read up on our versi
 ### [Security](/docs/security)
 Read up on [security](/docs/security) best practices to make sure you're developing safely with LangChain.
 
-### [Integrations](integrations/providers/index.mdx)
-LangChain is part of a rich ecosystem of tools that integrate with our framework and build on top of it. Check out our growing list of [integrations](/docs/integrations/providers/).
-
 ### [Contributing](contributing/index.mdx)
 Check out the developer's guide for guidelines on contributing and help getting your dev environment set up.

docs/docs/troubleshooting/errors/INVALID_TOOL_RESULTS.ipynb

@@ -6,7 +6,7 @@
    "source": [
     "# INVALID_TOOL_RESULTS\n",
     "\n",
-    "You are passing too many, too few, or mismatched [`ToolMessages`](https://api.js.langchain.com/classes/_langchain_core.messages_tool.ToolMessage.html) to a model.\n",
+    "You are passing too many, too few, or mismatched [`ToolMessages`](https://python.langchain.com/api_reference/core/messages/langchain_core.messages.tool.ToolMessage.html#toolmessage) to a model.\n",
     "\n",
     "When [using a model to call tools](/docs/concepts/tool_calling), the [`AIMessage`](https://api.js.langchain.com/classes/_langchain_core.messages.AIMessage.html)\n",
     "the model responds with will contain a `tool_calls` array. To continue the flow, the next messages you pass back to the model must\n",

docs/docs/tutorials/index.mdx

@@ -4,28 +4,35 @@ sidebar_class_name: hidden
 ---
 # Tutorials
 
-New to LangChain or LLM app development in general? Read this material to quickly get up and running.
+New to LangChain or LLM app development in general? Read this material to quickly get up and running building your first applications.
+
+If you're looking to get up and running quickly with [chat models](/docs/integrations/chat/), [vector stores](/docs/integrations/vectorstores/),
+or other LangChain components from a specific provider, check out our supported [integrations](/docs/integrations/providers/).
+
+Refer to the [how-to guides](/docs/how_to) for more detail on using common LangChain components.
+
+See the [conceptual documentation](/docs/concepts) for high level explanations of all LangChain concepts.
 
 ## Basics
-- [Build a Simple LLM Application with LCEL](/docs/tutorials/llm_chain)
-- [Build a Chatbot](/docs/tutorials/chatbot)
-- [Build vector stores and retrievers](/docs/tutorials/retrievers)
-- [Build an Agent](/docs/tutorials/agents)
+- [LLM applications](/docs/tutorials/llm_chain): Build and deploy a simple LLM application.
+- [Chatbots](/docs/tutorials/chatbot): Build a chatbot that incorporates memory.
+- [Vector stores](/docs/tutorials/retrievers): Build vector stores and use them to retrieve data.
+- [Agents](/docs/tutorials/agents): Build an agent that interacts with external tools.
 
 ## Working with external knowledge
-- [Build a Retrieval Augmented Generation (RAG) Application](/docs/tutorials/rag)
-- [Build a Conversational RAG Application](/docs/tutorials/qa_chat_history)
-- [Build a Question/Answering system over SQL data](/docs/tutorials/sql_qa)
-- [Build a Query Analysis System](/docs/tutorials/query_analysis)
-- [Build a local RAG application](/docs/tutorials/local_rag)
-- [Build a Question Answering application over a Graph Database](/docs/tutorials/graph)
-- [Build a PDF ingestion and Question/Answering system](/docs/tutorials/pdf_qa/)
+- [Retrieval Augmented Generation (RAG)](/docs/tutorials/rag): Build an application that uses your own documents to inform its responses.
+- [Conversational RAG](/docs/tutorials/qa_chat_history): Build a RAG application that incorporates a memory of its user interactions.
+- [Question-Answering with SQL](/docs/tutorials/sql_qa): Build a question-answering system that executes SQL queries to inform its responses.
+- [Query Analysis](/docs/tutorials/query_analysis): Build a RAG application that analyzes questions to generate filters and other structured queries.
+- [Local RAG](/docs/tutorials/local_rag): Build a RAG application using LLMs running locally on your machine.
+- [Question-Answering with Graph Databases](/docs/tutorials/graph): Build a question-answering system that queries a graph database to inform its responses.
+- [Question-Answering with PDFs](/docs/tutorials/pdf_qa/): Build a question-answering system that ingests PDFs and uses them to inform its responses.
 
 ## Specialized tasks
-- [Build an Extraction Chain](/docs/tutorials/extraction)
-- [Generate synthetic data](/docs/tutorials/data_generation)
-- [Classify text into labels](/docs/tutorials/classification)
-- [Summarize text](/docs/tutorials/summarization)
+- [Extraction](/docs/tutorials/extraction): Extract structured data from text and other unstructured media.
+- [Synthetic data](/docs/tutorials/data_generation): Generate synthetic data using LLMs.
+- [Classification](/docs/tutorials/classification): Classify text into categories or labels.
+- [Summarization](/docs/tutorials/summarization): Generate summaries of (potentially long) texts.
 
 ## LangGraph
 

docs/docs/tutorials/llm_chain.ipynb

@@ -93,7 +93,7 @@
    "source": [
     "## Using Language Models\n",
     "\n",
-    "First up, let's learn how to use a language model by itself. LangChain supports many different language models that you can use interchangeably - select the one you want to use below!\n",
+    "First up, let's learn how to use a language model by itself. LangChain supports many different language models that you can use interchangeably. For details on getting started with a specific model, refer to [supported integrations](/docs/integrations/chat/).\n",
     "\n",
     "import ChatModelTabs from \"@theme/ChatModelTabs\";\n",
     "\n",

docs/docs/tutorials/rag.ipynb

@@ -502,7 +502,7 @@
     "\n",
     "- [Docs](/docs/how_to/vectorstores): Detailed documentation on how to use vector stores.\n",
     "- [Integrations](/docs/integrations/vectorstores/): 40+ integrations to choose from.\n",
-    "- [Interface](https://python.langchain.com/api_reference/core/vectorstores/langchain_core.vectorstores.VectorStore.html): API reference for the base interface.\n",
+    "- [Interface](https://python.langchain.com/api_reference/core/vectorstores/langchain_core.vectorstores.base.VectorStore.html): API reference for the base interface.\n",
     "\n",
     "This completes the **Indexing** portion of the pipeline. At this point\n",
     "we have a query-able vector store containing the chunked contents of our\n",

docs/docs/tutorials/retrievers.ipynb

@@ -151,13 +151,13 @@
    "id": "ff0f0b43-e5b8-4c79-b782-a02f17345487",
    "metadata": {},
    "source": [
-    "Calling `.from_documents` here will add the documents to the vector store. [VectorStore](https://python.langchain.com/api_reference/core/vectorstores/langchain_core.vectorstores.VectorStore.html) implements methods for adding documents that can also be called after the object is instantiated. Most implementations will allow you to connect to an existing vector store--  e.g., by providing a client, index name, or other information. See the documentation for a specific [integration](/docs/integrations/vectorstores) for more detail.\n",
+    "Calling `.from_documents` here will add the documents to the vector store. [VectorStore](https://python.langchain.com/api_reference/core/vectorstores/langchain_core.vectorstores.base.VectorStore.html) implements methods for adding documents that can also be called after the object is instantiated. Most implementations will allow you to connect to an existing vector store--  e.g., by providing a client, index name, or other information. See the documentation for a specific [integration](/docs/integrations/vectorstores) for more detail.\n",
     "\n",
-    "Once we've instantiated a `VectorStore` that contains documents, we can query it. [VectorStore](https://python.langchain.com/api_reference/core/vectorstores/langchain_core.vectorstores.VectorStore.html) includes methods for querying:\n",
+    "Once we've instantiated a `VectorStore` that contains documents, we can query it. [VectorStore](https://python.langchain.com/api_reference/core/vectorstores/langchain_core.vectorstores.base.VectorStore.html) includes methods for querying:\n",
     "- Synchronously and asynchronously;\n",
     "- By string query and by vector;\n",
     "- With and without returning similarity scores;\n",
-    "- By similarity and [maximum marginal relevance](https://python.langchain.com/api_reference/core/vectorstores/langchain_core.vectorstores.VectorStore.html#langchain_core.vectorstores.VectorStore.max_marginal_relevance_search) (to balance similarity with query to diversity in retrieved results).\n",
+    "- By similarity and [maximum 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) (to balance similarity with query to diversity in retrieved results).\n",
     "\n",
     "The methods will generally include a list of [Document](https://python.langchain.com/api_reference/core/documents/langchain_core.documents.base.Document.html#langchain_core.documents.base.Document) objects in their outputs.\n",
     "\n",
@@ -303,7 +303,7 @@
    "source": [
     "Learn more:\n",
     "\n",
-    "- [API reference](https://python.langchain.com/api_reference/core/vectorstores/langchain_core.vectorstores.VectorStore.html)\n",
+    "- [API reference](https://python.langchain.com/api_reference/core/vectorstores/langchain_core.vectorstores.base.VectorStore.html)\n",
     "- [How-to guide](/docs/how_to/vectorstores)\n",
     "- [Integration-specific docs](/docs/integrations/vectorstores)\n",
     "\n",
@@ -348,7 +348,7 @@
    "id": "a36d3f64-a8bc-4baa-b2ea-07e324a0143e",
    "metadata": {},
    "source": [
-    "Vectorstores implement an `as_retriever` method that will generate a Retriever, specifically a [VectorStoreRetriever](https://python.langchain.com/api_reference/core/vectorstores/langchain_core.vectorstores.VectorStoreRetriever.html). These retrievers include specific `search_type` and `search_kwargs` attributes that identify what methods of the underlying vector store to call, and how to parameterize them. For instance, we can replicate the above with the following:"
+    "Vectorstores implement an `as_retriever` method that will generate a Retriever, specifically a [VectorStoreRetriever](https://python.langchain.com/api_reference/core/vectorstores/langchain_core.vectorstores.base.VectorStoreRetriever.html). These retrievers include specific `search_type` and `search_kwargs` attributes that identify what methods of the underlying vector store to call, and how to parameterize them. For instance, we can replicate the above with the following:"
    ]
   },
   {

docs/docs/tutorials/sql_qa.ipynb

@@ -28,7 +28,7 @@
     "\n",
     "At a high-level, the steps of these systems are:\n",
     "\n",
-    "1. **Convert question to DSL query**: Model converts user input to a SQL query.\n",
+    "1. **Convert question to SQL query**: Model converts user input to a SQL query.\n",
     "2. **Execute SQL query**: Execute the query.\n",
     "3. **Answer the question**: Model responds to user input using the query results.\n",
     "\n",