chore(infra): further docs build cleanup (#33057)

Reorganize the requirements for better clarity and consistency. Improve documentation on scripts and workflows.
2025-09-24 12:01:54 +00:00 · 2025-09-23 17:29:58 -04:00
parent b5720ff17a
commit 79e536b0d6
9 changed files with 368 additions and 58 deletions
--- a/.github/scripts/prep_api_docs_build.py
+++ b/.github/scripts/prep_api_docs_build.py
@@ -1,5 +1,8 @@
 #!/usr/bin/env python
-"""Sync libraries from various repositories into this monorepo."""
+"""Sync libraries from various repositories into this monorepo.
+
+Moves cloned partner packages into libs/partners structure.
+"""

 import os
 import shutil
@@ -10,7 +13,7 @@ import yaml


 def load_packages_yaml() -> Dict[str, Any]:
-    """Load and parse the packages.yml file."""
+    """Load and parse packages.yml."""
    with open("langchain/libs/packages.yml", "r") as f:
        return yaml.safe_load(f)

@@ -61,12 +64,15 @@ def move_libraries(packages: list) -> None:


 def main():
-    """Main function to orchestrate the library sync process."""
+    """Orchestrate the library sync process."""
    try:
        # Load packages configuration
        package_yaml = load_packages_yaml()

-        # Clean target directories
+        # Clean/empty target directories in preparation for moving new ones
+        #
+        # Only for packages in the langchain-ai org or explicitly included via
+        # include_in_api_ref, excluding 'langchain' itself and 'langchain-ai21'
        clean_target_directories(
            [
                p
@@ -80,7 +86,9 @@ def main():
            ]
        )

-        # Move libraries to their new locations
+        # Move cloned libraries to their new locations, only for packages in the
+        # langchain-ai org or explicitly included via include_in_api_ref,
+        # excluding 'langchain' itself and 'langchain-ai21'
        move_libraries(
            [
                p
@@ -95,7 +103,7 @@ def main():
            ]
        )

-        # Delete ones without a pyproject.toml
+        # Delete partner packages without a pyproject.toml
        for partner in Path("langchain/libs/partners").iterdir():
            if partner.is_dir() and not (partner / "pyproject.toml").exists():
                print(f"Removing {partner} as it does not have a pyproject.toml")
--- a/.github/workflows/api_doc_build.yml
+++ b/.github/workflows/api_doc_build.yml
@@ -1,6 +1,11 @@
 # Build the API reference documentation.
 #
 # Runs daily. Can also be triggered manually for immediate updates.
+#
+# Built HTML pushed to langchain-ai/langchain-api-docs-html.
+#
+# Looks for langchain-ai org repos in packages.yml and checks them out.
+# Calls prep_api_docs_build.py.

 name: '📚 API Docs'
 run-name: 'Build & Deploy API Reference'
@@ -34,6 +39,8 @@ jobs:
        uses: mikefarah/yq@master
        with:
          cmd: |
+            # Extract repos from packages.yml that are in the langchain-ai org
+            # (excluding 'langchain' itself)
            yq '
              .packages[]
              | select(
@@ -80,24 +87,31 @@ jobs:
        with:
          python-version: ${{ env.PYTHON_VERSION }}

-      - name: '📦 Install Initial Python Dependencies'
+      - name: '📦 Install Initial Python Dependencies using uv'
        working-directory: langchain
        run: |
          python -m pip install -U uv
          python -m uv pip install --upgrade --no-cache-dir pip setuptools pyyaml

      - name: '📦 Organize Library Directories'
+        # Places cloned partner packages into libs/partners structure
        run: python langchain/.github/scripts/prep_api_docs_build.py

-      - name: '🧹 Remove Old HTML Files'
+      - name: '🧹 Clear Prior Build'
        run:
+          # Remove artifacts from prior docs build
          rm -rf langchain-api-docs-html/api_reference_build/html

-      - name: '📦 Install Documentation Dependencies'
+      - name: '📦 Install Documentation Dependencies using uv'
        working-directory: langchain
        run: |
+          # Install all partner packages in editable mode with overrides
          python -m uv pip install $(ls ./libs/partners | xargs -I {} echo "./libs/partners/{}") --overrides ./docs/vercel_overrides.txt
+
+          # Install core langchain and other main packages
          python -m uv pip install libs/core libs/langchain libs/text-splitters libs/community libs/experimental libs/standard-tests
+
+          # Install Sphinx and related packages for building docs
          python -m uv pip install -r docs/api_reference/requirements.txt

      - name: '🔧 Configure Git Settings'
@@ -109,14 +123,29 @@ jobs:
      - name: '📚 Build API Documentation'
        working-directory: langchain
        run: |
+          # Generate the API reference RST files
          python docs/api_reference/create_api_rst.py
+
+          # Build the HTML documentation using Sphinx
+          # -T: show full traceback on exception
+          # -E: don't use cached environment (force rebuild, ignore cached doctrees)
+          # -b html: build HTML docs (vs PDS, etc.)
+          # -d: path for the cached environment (parsed document trees / doctrees)
+          #     - Separate from output dir for faster incremental builds
+          # -c: path to conf.py
+          # -j auto: parallel build using all available CPU cores
          python -m sphinx -T -E -b html -d ../langchain-api-docs-html/_build/doctrees -c docs/api_reference docs/api_reference ../langchain-api-docs-html/api_reference_build/html -j auto
+
+          # Post-process the generated HTML
          python docs/api_reference/scripts/custom_formatter.py ../langchain-api-docs-html/api_reference_build/html
+
          # Default index page is blank so we copy in the actual home page.
          cp ../langchain-api-docs-html/api_reference_build/html/{reference,index}.html
+
+          # Removes Sphinx's intermediate build artifacts after the build is complete.
          rm -rf ../langchain-api-docs-html/_build/

-      # https://github.com/marketplace/actions/add-commit
+      # Commit and push changes to langchain-api-docs-html repo
      - uses: EndBug/add-and-commit@v9
        with:
          cwd: langchain-api-docs-html
--- a/docs/README.md
+++ b/docs/README.md
@@ -1,3 +1,159 @@
 # LangChain Documentation

-For more information on contributing to our documentation, see the [Documentation Contributing Guide](https://python.langchain.com/docs/contributing/how_to/documentation)
+For more information on contributing to our documentation, see the [Documentation Contributing Guide](https://python.langchain.com/docs/contributing/how_to/documentation).
+
+## Structure
+
+The primary documentation is located in the `docs/` directory. This directory contains
+both the source files for the main documentation as well as the API reference doc
+build process.
+
+### API Reference
+
+API reference documentation is located in `docs/api_reference/` and is generated from
+the codebase using Sphinx.
+
+The API reference have additional build steps that differ from the main documentation.
+
+#### Deployment Process
+
+Currently, the build process roughly follows these steps:
+
+1. Using the `api_doc_build.yml` GitHub workflow, the API reference docs are
+    [built](#build-technical-details) and copied to the `langchain-api-docs-html`
+    repository. This workflow is triggered either (1) on a cron routine interval or (2)
+    triggered manually.
+
+    In short, the workflow extracts all `langchain-ai`-org-owned repos defined in
+    `langchain/libs/packages.yml`, clones them locally (in the workflow runner's file
+    system), and then builds the API reference RST files (using `create_api_rst.py`).
+    Following post-processing, the HTML files are pushed to the
+    `langchain-api-docs-html` repository.
+2. After the HTML files are in the `langchain-api-docs-html` repository, they are **not**
+    automatically published to the [live docs site](https://python.langchain.com/api_reference/).
+
+    The docs site is served by Vercel. The Vercel deployment process copies the HTML
+    files from the `langchain-api-docs-html` repository and deploys them to the live
+    site. Deployments are triggered on each new commit pushed to `master`.
+
+#### Build Technical Details
+
+The build process creates a virtual monorepo by syncing multiple repositories, then generates comprehensive API documentation:
+
+1. **Repository Sync Phase:**
+   - `.github/scripts/prep_api_docs_build.py` - Clones external partner repos and organizes them into the `libs/partners/` structure to create a virtual monorepo for documentation building
+
+2. **RST Generation Phase:**
+   - `docs/api_reference/create_api_rst.py` - Main script that **generates RST files** from Python source code
+     - Scans `libs/` directories and extracts classes/functions from each module (using `inspect`)
+     - Creates `.rst` files using specialized templates for different object types
+     - Templates in `docs/api_reference/templates/` (`pydantic.rst`, `runnable_pydantic.rst`, etc.)
+
+3. **HTML Build Phase:**
+   - Sphinx-based, uses `sphinx.ext.autodoc` (auto-extracts docstrings from the codebase)
+     - `docs/api_reference/conf.py` (sphinx config) configures `autodoc` and other extensions
+   - `sphinx-build` processes the generated `.rst` files into HTML using autodoc
+   - `docs/api_reference/scripts/custom_formatter.py` - Post-processes the generated HTML
+   - Copies `reference.html` to `index.html` to create the default landing page (artifact? might not need to do this - just put everyhing in index directly?)
+
+4. **Deployment:**
+   - `.github/workflows/api_doc_build.yml` - Workflow responsible for orchestrating the entire build and deployment process
+   - Built HTML files are committed and pushed to the `langchain-api-docs-html` repository
+
+#### Local Build
+
+For local development and testing of API documentation, use the Makefile targets in the repository root:
+
+```bash
+# Full build
+make api_docs_build
+```
+
+Like the CI process, this target:
+
+- Installs the CLI package in editable mode
+- Generates RST files for all packages using `create_api_rst.py`
+- Builds HTML documentation with Sphinx
+- Post-processes the HTML with `custom_formatter.py`
+- Opens the built documentation (`reference.html`) in your browser
+
+**Quick Preview:**
+
+```bash
+make api_docs_quick_preview API_PKG=openai
+```
+
+- Generates RST files for only the specified package (default: `text-splitters`)
+- Builds and post-processes HTML documentation
+- Opens the preview in your browser
+
+Both targets automatically clean previous builds and handle the complete build pipeline locally, mirroring the CI process but for faster iteration during development.
+
+#### Documentation Standards
+
+**Docstring Format:**
+The API reference uses **Google-style docstrings** with reStructuredText markup. Sphinx processes these through the `sphinx.ext.napoleon` extension to generate documentation.
+
+**Required format:**
+
+```python
+def example_function(param1: str, param2: int = 5) -> bool:
+    """Brief description of the function.
+
+    Longer description can go here. Use reStructuredText syntax for
+    rich formatting like **bold** and *italic*.
+
+    TODO: code: figure out what works?
+
+    Args:
+        param1: Description of the first parameter.
+        param2: Description of the second parameter with default value.
+
+    Returns:
+        Description of the return value.
+
+    Raises:
+        ValueError: When param1 is empty.
+        TypeError: When param2 is not an integer.
+
+    .. warning::
+        This function is experimental and may change.
+
+    .. deprecated:: 0.2.0
+        Use :func:`new_function` instead.
+    """
+```
+
+**Special Markers:**
+
+- `:private:` in docstrings excludes members from documentation
+- `.. deprecated::` creates deprecation notices
+- `.. warning::` adds warning admonitions
+- `.. beta::` (custom directive) marks beta features
+
+#### Site Styling and Assets
+
+**Theme and Styling:**
+
+- Uses [**PyData Sphinx Theme**](https://pydata-sphinx-theme.readthedocs.io/en/stable/index.html) (`pydata_sphinx_theme`)
+- Custom CSS in `docs/api_reference/_static/css/custom.css` with LangChain-specific:
+  - Color palette
+  - Inter font family
+  - Custom navbar height and sidebar formatting
+  - Deprecated/beta feature styling
+
+**Static Assets:**
+
+- Logos: `_static/wordmark-api.svg` (light) and `_static/wordmark-api-dark.svg` (dark mode)
+- Favicon: `_static/img/brand/favicon.png`
+- Custom CSS: `_static/css/custom.css`
+
+**Post-Processing:**
+
+- `scripts/custom_formatter.py` cleans up generated HTML:
+  - Shortens TOC entries from `ClassName.method()` to `method()`
+
+**Analytics and Integration:**
+
+- GitHub integration (source links, edit buttons)
+- Example backlinking through custom `ExampleLinksDirective`
--- a/docs/api_reference/conf.py
+++ b/docs/api_reference/conf.py
@@ -1,7 +1,5 @@
 """Configuration file for the Sphinx documentation builder."""

-# Configuration file for the Sphinx documentation builder.
-#
 # This file only contains a selection of the most common options. For a full
 # list see the documentation:
 # https://www.sphinx-doc.org/en/master/usage/configuration.html
@@ -20,16 +18,18 @@ from docutils.parsers.rst.directives.admonitions import BaseAdmonition
 from docutils.statemachine import StringList
 from sphinx.util.docutils import SphinxDirective

-# If extensions (or modules to document with autodoc) are in another directory,
-# add these directories to sys.path here. If the directory is relative to the
-# documentation root, use os.path.abspath to make it absolute, like shown here.
-
+# Add paths to Python import system so Sphinx can import LangChain modules
+# This allows autodoc to introspect and document the actual code
 _DIR = Path(__file__).parent.absolute()
-sys.path.insert(0, os.path.abspath("."))
-sys.path.insert(0, os.path.abspath("../../libs/langchain"))
+sys.path.insert(0, os.path.abspath("."))  # Current directory
+sys.path.insert(0, os.path.abspath("../../libs/langchain"))  # LangChain main package

+# Load package metadata from pyproject.toml (for version info, etc.)
 with (_DIR.parents[1] / "libs" / "langchain" / "pyproject.toml").open("r") as f:
    data = toml.load(f)
+
+# Load mapping of classes to example notebooks for backlinking
+# This file is generated by scripts that scan our tutorial/example notebooks
 with (_DIR / "guide_imports.json").open("r") as f:
    imported_classes = json.load(f)

@@ -86,6 +86,7 @@ class Beta(BaseAdmonition):


 def setup(app):
+    """Register custom directives and hooks with Sphinx."""
    app.add_directive("example_links", ExampleLinksDirective)
    app.add_directive("beta", Beta)
    app.connect("autodoc-skip-member", skip_private_members)
@@ -258,7 +259,20 @@ html_static_path = ["_static"]
 html_css_files = ["css/custom.css"]
 html_use_index = False

-myst_enable_extensions = ["colon_fence"]
+myst_enable_extensions = [
+    "colon_fence",  # ::: directive blocks (existing prior to LangGraph support)
+    # LangGraph compatibility extensions added for consolidation
+    # TODO: check for presence of each in LangGraph and only enable if needed
+    # "deflist",  # Definition lists
+    # "tasklist",  # - [ ] checkboxes (common in examples)
+    # "attrs_inline",  # {.class} inline attributes (MkDocs style)
+    # "attrs_block",  # Block-level attributes
+    # "substitution",  # Variable substitution
+    # "linkify",  # Auto-link URLs in text
+    # Math extensions (uncomment if LangGraph uses mathematical notation)
+    # "dollarmath",     # $ math $ inline math
+    # "amsmath",        # Advanced math environments
+]

 # generate autosummary even if no references
 autosummary_generate = True
@@ -268,11 +282,11 @@ autosummary_ignore_module_all = False
 html_copy_source = False
 html_show_sourcelink = False

+googleanalytics_id = "G-9B66JQQH2F"
+
 # Set canonical URL from the Read the Docs Domain
 html_baseurl = os.environ.get("READTHEDOCS_CANONICAL_URL", "")

-googleanalytics_id = "G-9B66JQQH2F"
-
 # Tell Jinja2 templates the build is running on Read the Docs
 if os.environ.get("READTHEDOCS", "") == "True":
    html_context["READTHEDOCS"] = True
--- a/docs/api_reference/create_api_rst.py
+++ b/docs/api_reference/create_api_rst.py
@@ -1,4 +1,41 @@
-"""Script for auto-generating api_reference.rst."""
+"""Auto-generate API reference documentation (RST files) for LangChain packages.
+
+* Automatically discovers all packages in `libs/` and `libs/partners/`
+* For each package, recursively walks the filesystem to:
+    * Load Python modules using importlib
+    * Extract classes and functions using Python's inspect module
+    * Classify objects by type (Pydantic models, Runnables, TypedDicts, etc.)
+    * Filter out private members (names starting with '_') and deprecated items
+* Creates structured RST files with:
+    * Module-level documentation pages with autosummary tables
+    * Different Sphinx templates based on object type (see templates/ directory)
+    * Proper cross-references and navigation structure
+    * Separation of current vs deprecated APIs
+* Generates a directory tree like:
+    ```
+    docs/api_reference/
+    ├── index.md              # Main landing page with package gallery
+    ├── reference.md          # Package overview and navigation
+    ├── core/                 # langchain-core documentation
+    │   ├── index.rst
+    │   ├── callbacks.rst
+    │   └── ...
+    ├── langchain/            # langchain documentation
+    │   ├── index.rst
+    │   └── ...
+    └── partners/             # Integration packages
+        ├── openai/
+        ├── anthropic/
+        └── ...
+    ```
+
+## Key Features
+
+* Respects privacy markers:
+    * Modules with `:private:` in docstring are excluded entirely
+    * Objects with `:private:` in docstring are filtered out
+    * Names starting with '_' are treated as private
+"""

 import importlib
 import inspect
@@ -178,11 +215,12 @@ def _load_package_modules(
    of the modules/packages are part of the package vs. 3rd party or built-in.

    Parameters:
-        package_directory (Union[str, Path]): Path to the package directory.
-        submodule (Optional[str]): Optional name of submodule to load.
+        package_directory: Path to the package directory.
+        submodule: Optional name of submodule to load.

    Returns:
-        Dict[str, ModuleMembers]: A dictionary where keys are module names and values are ModuleMembers objects.
+        A dictionary where keys are module names and values are `ModuleMembers`
+        objects.
    """
    package_path = (
        Path(package_directory)
@@ -199,12 +237,13 @@ def _load_package_modules(
        package_path = package_path / submodule

    for file_path in package_path.rglob("*.py"):
+        # Skip private modules
        if file_path.name.startswith("_"):
            continue

+        # Skip integration_template and project_template directories (for libs/cli)
        if "integration_template" in file_path.parts:
            continue
-
        if "project_template" in file_path.parts:
            continue

@@ -215,8 +254,13 @@ def _load_package_modules(
            continue

        # Get the full namespace of the module
+        # Example: langchain_core/schema/output_parsers.py ->
+        #          langchain_core.schema.output_parsers
        namespace = str(relative_module_name).replace(".py", "").replace("/", ".")
+
        # Keep only the top level namespace
+        # Example: langchain_core.schema.output_parsers ->
+        #          langchain_core
        top_namespace = namespace.split(".")[0]

        try:
@@ -253,16 +297,16 @@ def _construct_doc(
    members_by_namespace: Dict[str, ModuleMembers],
    package_version: str,
 ) -> List[typing.Tuple[str, str]]:
-    """Construct the contents of the reference.rst file for the given package.
+    """Construct the contents of the `reference.rst` for the given package.

    Args:
        package_namespace: The package top level namespace
-        members_by_namespace: The members of the package, dict organized by top level
-                              module contains a list of classes and functions
-                              inside of the top level namespace.
+        members_by_namespace: The members of the package dict organized by top level.
+            Module contains a list of classes and functions inside of the top level
+            namespace.

    Returns:
-        The contents of the reference.rst file.
+        The string contents of the reference.rst file.
    """
    docs = []
    index_doc = f"""\
@@ -465,10 +509,13 @@ def _construct_doc(


 def _build_rst_file(package_name: str = "langchain") -> None:
-    """Create a rst file for building of documentation.
+    """Create a rst file for a given package.

    Args:
-        package_name: Can be either "langchain" or "core"
+        package_name: Name of the package to create the rst file for.
+
+    Returns:
+        The rst file is created in the same directory as this script.
    """
    package_dir = _package_dir(package_name)
    package_members = _load_package_modules(package_dir)
@@ -500,7 +547,10 @@ def _package_namespace(package_name: str) -> str:


 def _package_dir(package_name: str = "langchain") -> Path:
-    """Return the path to the directory containing the documentation."""
+    """Return the path to the directory containing the documentation.
+
+    Attempts to find the package in `libs/` first, then `libs/partners/`.
+    """
    if (ROOT_DIR / "libs" / package_name).exists():
        return ROOT_DIR / "libs" / package_name / _package_namespace(package_name)
    else:
@@ -514,7 +564,7 @@ def _package_dir(package_name: str = "langchain") -> Path:


 def _get_package_version(package_dir: Path) -> str:
-    """Return the version of the package."""
+    """Return the version of the package by reading the `pyproject.toml`."""
    try:
        with open(package_dir.parent / "pyproject.toml", "r") as f:
            pyproject = toml.load(f)
@@ -540,6 +590,15 @@ def _out_file_path(package_name: str) -> Path:


 def _build_index(dirs: List[str]) -> None:
+    """Build the index.md file for the API reference.
+
+    Args:
+        dirs: List of package directories to include in the index.
+
+    Returns:
+        The index.md file is created in the same directory as this script.
+    """
+
    custom_names = {
        "aws": "AWS",
        "ai21": "AI21",
@@ -647,9 +706,14 @@ See the full list of integrations in the Section Navigation.
 {integration_tree}
 ```
 """
+    # Write the reference.md file
    with open(HERE / "reference.md", "w") as f:
        f.write(doc)

+    # Write a dummy index.md file that points to reference.md
+    # Sphinx requires an index file to exist in each doc directory
+    # TODO: investigate why we don't just put everything in index.md directly?
+    # if it works it works I guess
    dummy_index = """\
 # API reference

@@ -665,8 +729,11 @@ Reference<reference>


 def main(dirs: Optional[list] = None) -> None:
-    """Generate the api_reference.rst file for each package."""
-    print("Starting to build API reference files.")
+    """Generate the `api_reference.rst` file for each package.
+
+    If dirs is None, generate for all packages in `libs/` and `libs/partners/`.
+    Otherwise generate only for the specified package(s).
+    """
    if not dirs:
        dirs = [
            p.parent.name
@@ -675,18 +742,17 @@ def main(dirs: Optional[list] = None) -> None:
            if p.parent.parent.name in ("libs", "partners")
        ]
    for dir_ in sorted(dirs):
-        # Skip any hidden directories
+        # Skip any hidden directories prefixed with a dot
        # Some of these could be present by mistake in the code base
-        # e.g., .pytest_cache from running tests from the wrong location.
+        # (e.g., .pytest_cache from running tests from the wrong location)
        if dir_.startswith("."):
            print("Skipping dir:", dir_)
            continue
        else:
-            print("Building package:", dir_)
+            print("Building:", dir_)
            _build_rst_file(package_name=dir_)

    _build_index(sorted(dirs))
-    print("API reference files built.")


 if __name__ == "__main__":
--- a/docs/api_reference/requirements.txt
+++ b/docs/api_reference/requirements.txt
@@ -1,12 +1,12 @@
 autodoc_pydantic>=2,<3
 sphinx>=8,<9
-myst-parser>=3
 sphinx-autobuild>=2024
+sphinx-design
+sphinx-copybutton
+sphinxcontrib-googleanalytics
 pydata-sphinx-theme>=0.15
+myst-parser>=3
 toml>=0.10.2
 myst-nb>=1.1.1
 pyyaml
-sphinx-design
-sphinx-copybutton
 beautifulsoup4
-sphinxcontrib-googleanalytics
--- a/docs/api_reference/scripts/custom_formatter.py
+++ b/docs/api_reference/scripts/custom_formatter.py
@@ -1,3 +1,10 @@
+"""Post-process generated HTML files to clean up table-of-contents headers.
+
+Runs after Sphinx generates the API reference HTML. It finds TOC entries like
+"ClassName.method_name()" and shortens them to just "method_name()" for better
+readability in the sidebar navigation.
+"""
+
 import sys
 from glob import glob
 from pathlib import Path
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -54,6 +54,7 @@ test = [
 ]
 docs = [
    "toml>=0.10.2,<0.11.0",
+    "types-toml>=0.10.8.20240310",
    "autodoc-pydantic>=2.0.0,<3.0.0",
    "sphinx>=6.0.0,<8.0.0",
    "myst-parser>=3.0.0,<4.0.0",
@@ -65,6 +66,8 @@ docs = [
    "sphinx-copybutton",
    "beautifulsoup4",
    "sphinxcontrib-googleanalytics",
+    "docutils>=0.21.2,<1.0.0",
+    "types-docutils>=0.22.1.20250923",
 ]

 [tool.uv.sources]
--- a/uv.lock
+++ b/uv.lock
@@ -1476,8 +1476,8 @@ name = "html5lib"
 version = "1.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "six" },
-    { name = "webencodings" },
+    { name = "six", marker = "python_full_version < '3.13'" },
+    { name = "webencodings", marker = "python_full_version < '3.13'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/ac/b6/b55c3f49042f1df3dcd422b7f224f939892ee94f22abcf503a9b7339eaf2/html5lib-1.1.tar.gz", hash = "sha256:b2e5b40261e20f354d198eae92afc10d750afb487ed5e50f9c4eaf07c184146f", size = 272215, upload-time = "2020-06-22T23:32:38.834Z" }
 wheels = [
@@ -2364,6 +2364,7 @@ test = [
    { name = "onnxruntime", marker = "python_full_version >= '3.10'" },
    { name = "pytest", specifier = ">=7.3.0,<8.0.0" },
    { name = "pytest-asyncio", specifier = ">=0.21.1,<1.0.0" },
+    { name = "pytest-benchmark" },
    { name = "pytest-mock", specifier = ">=3.10.0,<4.0.0" },
    { name = "pytest-socket", specifier = ">=0.7.0,<1.0.0" },
    { name = "pytest-watcher", specifier = ">=0.3.4,<1.0.0" },
@@ -2484,7 +2485,7 @@ requires-dist = [
    { name = "aiohttp", specifier = ">=3.9.1,<4.0.0" },
    { name = "fireworks-ai", specifier = ">=0.13.0,<1.0.0" },
    { name = "langchain-core", editable = "libs/core" },
-    { name = "openai", specifier = ">=1.10.0,<2.0.0" },
+    { name = "openai", specifier = ">=1.0.0,<1.108.0" },
    { name = "requests", specifier = ">=2.0.0,<3.0.0" },
 ]

@@ -2621,6 +2622,7 @@ dev = [
 docs = [
    { name = "autodoc-pydantic" },
    { name = "beautifulsoup4" },
+    { name = "docutils" },
    { name = "myst-nb" },
    { name = "myst-parser" },
    { name = "pydata-sphinx-theme" },
@@ -2631,6 +2633,8 @@ docs = [
    { name = "sphinx-design" },
    { name = "sphinxcontrib-googleanalytics" },
    { name = "toml" },
+    { name = "types-docutils" },
+    { name = "types-toml" },
 ]
 lint = [
    { name = "ruff" },
@@ -2680,6 +2684,7 @@ dev = [
 docs = [
    { name = "autodoc-pydantic", specifier = ">=2.0.0,<3.0.0" },
    { name = "beautifulsoup4" },
+    { name = "docutils", specifier = ">=0.21.2" },
    { name = "myst-nb", specifier = ">=1.1.1" },
    { name = "myst-parser", specifier = ">=3.0.0,<4.0.0" },
    { name = "pydata-sphinx-theme", specifier = ">=0.15.0" },
@@ -2690,6 +2695,8 @@ docs = [
    { name = "sphinx-design" },
    { name = "sphinxcontrib-googleanalytics" },
    { name = "toml", specifier = ">=0.10.2,<0.11.0" },
+    { name = "types-docutils", specifier = ">=0.22.1.20250923" },
+    { name = "types-toml", specifier = ">=0.10.8.20240310" },
 ]
 lint = [{ name = "ruff", specifier = ">=0.12.2,<0.13.0" }]
 test = [
@@ -2737,7 +2744,7 @@ dependencies = [
 [package.metadata]
 requires-dist = [
    { name = "langchain-core", editable = "libs/core" },
-    { name = "openai", specifier = ">=1.104.2,<2.0.0" },
+    { name = "openai", specifier = ">=1.104.2,<1.108.0" },
    { name = "tiktoken", specifier = ">=0.7.0,<1.0.0" },
 ]

@@ -2822,6 +2829,8 @@ test = [
 test-integration = [
    { name = "en-core-web-sm", url = "https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.8.0/en_core_web_sm-3.8.0-py3-none-any.whl" },
    { name = "nltk", specifier = ">=3.9.1,<4.0.0" },
+    { name = "scipy", marker = "python_full_version == '3.12.*'", specifier = ">=1.7.0,<2.0.0" },
+    { name = "scipy", marker = "python_full_version >= '3.13'", specifier = ">=1.14.1,<2.0.0" },
    { name = "sentence-transformers", specifier = ">=3.0.1,<4.0.0" },
    { name = "spacy", specifier = ">=3.8.7,<4.0.0" },
    { name = "thinc", specifier = ">=8.3.6,<9.0.0" },
@@ -2862,7 +2871,7 @@ name = "langdetect"
 version = "1.0.9"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "six" },
+    { name = "six", marker = "python_full_version < '3.13'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/0e/72/a3add0e4eec4eb9e2569554f7c70f4a3c27712f40e3284d483e88094cc0e/langdetect-1.0.9.tar.gz", hash = "sha256:cbc1fef89f8d062739774bd51eda3da3274006b3661d199c2655f6b3f6d605a0", size = 981474, upload-time = "2021-05-07T07:54:13.562Z" }

@@ -3630,10 +3639,10 @@ name = "nltk"
 version = "3.9.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "click" },
-    { name = "joblib" },
-    { name = "regex" },
-    { name = "tqdm" },
+    { name = "click", marker = "python_full_version < '3.13'" },
+    { name = "joblib", marker = "python_full_version < '3.13'" },
+    { name = "regex", marker = "python_full_version < '3.13'" },
+    { name = "tqdm", marker = "python_full_version < '3.13'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/3c/87/db8be88ad32c2d042420b6fd9ffd4a149f9a0d7f0e86b3f543be2eeeedd2/nltk-3.9.1.tar.gz", hash = "sha256:87d127bd3de4bd89a4f81265e5fa59cb1b199b27440175370f7417d2bc7ae868", size = 2904691, upload-time = "2024-08-18T19:48:37.769Z" }
 wheels = [
@@ -4944,9 +4953,9 @@ name = "python-oxmsg"
 version = "0.0.2"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "click" },
-    { name = "olefile" },
-    { name = "typing-extensions" },
+    { name = "click", marker = "python_full_version < '3.13'" },
+    { name = "olefile", marker = "python_full_version < '3.13'" },
+    { name = "typing-extensions", marker = "python_full_version < '3.13'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/a2/4e/869f34faedbc968796d2c7e9837dede079c9cb9750917356b1f1eda926e9/python_oxmsg-0.0.2.tar.gz", hash = "sha256:a6aff4deb1b5975d44d49dab1d9384089ffeec819e19c6940bc7ffbc84775fad", size = 34713, upload-time = "2025-02-03T17:13:47.415Z" }
 wheels = [
@@ -6127,6 +6136,15 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/d0/cc/0a838ba5ca64dc832aa43f727bd586309846b0ffb2ce52422543e6075e8a/typer-0.15.1-py3-none-any.whl", hash = "sha256:7994fb7b8155b64d3402518560648446072864beefd44aa2dc36972a5972e847", size = 44908, upload-time = "2024-12-04T17:44:57.291Z" },
 ]

+[[package]]
+name = "types-docutils"
+version = "0.22.1.20250923"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/80/76/3b2b841d2ea3b59685c59cfcfeddd439146287319c1566099796507ee866/types_docutils-0.22.1.20250923.tar.gz", hash = "sha256:f7754c7eeab44144095e287bb3afcb96d6936dc3fa332cff4e5ef5533baa198f", size = 56652, upload-time = "2025-09-23T02:51:20.573Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/29/22/c762f76ace7de3c8d469f9f25a8b8870bff47fb31ecc15453ac96426f36a/types_docutils-0.22.1.20250923-py3-none-any.whl", hash = "sha256:a01a8036b373dd578ec1a170db04f4159be1282ca92f0a085e50f4afbeb8d0bc", size = 91872, upload-time = "2025-09-23T02:51:19.305Z" },
+]
+
 [[package]]
 name = "types-python-dateutil"
 version = "2.9.0.20241206"
@@ -6136,6 +6154,15 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/0f/b3/ca41df24db5eb99b00d97f89d7674a90cb6b3134c52fb8121b6d8d30f15c/types_python_dateutil-2.9.0.20241206-py3-none-any.whl", hash = "sha256:e248a4bc70a486d3e3ec84d0dc30eec3a5f979d6e7ee4123ae043eedbb987f53", size = 14384, upload-time = "2024-12-06T02:56:39.412Z" },
 ]

+[[package]]
+name = "types-toml"
+version = "0.10.8.20240310"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/86/47/3e4c75042792bff8e90d7991aa5c51812cc668828cc6cce711e97f63a607/types-toml-0.10.8.20240310.tar.gz", hash = "sha256:3d41501302972436a6b8b239c850b26689657e25281b48ff0ec06345b8830331", size = 4392, upload-time = "2024-03-10T02:18:37.518Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/da/a2/d32ab58c0b216912638b140ab2170ee4b8644067c293b170e19fba340ccc/types_toml-0.10.8.20240310-py3-none-any.whl", hash = "sha256:627b47775d25fa29977d9c70dc0cbab3f314f32c8d8d0c012f2ef5de7aaec05d", size = 4777, upload-time = "2024-03-10T02:18:36.568Z" },
+]
+
 [[package]]
 name = "typing-extensions"
 version = "4.12.2"