Merge branch 'master' into feature/azure_face

.github/CODEOWNERS

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

.github/DISCUSSION_TEMPLATE/q-a.yml

@@ -22,7 +22,7 @@ body:
         if there's another way to solve your problem:
         
         [LangChain documentation with the integrated search](https://python.langchain.com/docs/get_started/introduction),
-        [API Reference](https://api.python.langchain.com/en/stable/),
+        [API Reference](https://python.langchain.com/api_reference/),
         [GitHub search](https://github.com/langchain-ai/langchain),
         [LangChain Github Discussions](https://github.com/langchain-ai/langchain/discussions),
         [LangChain Github Issues](https://github.com/langchain-ai/langchain/issues?q=is%3Aissue),

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -16,7 +16,7 @@ body:
         if there's another way to solve your problem:
         
         [LangChain documentation with the integrated search](https://python.langchain.com/docs/get_started/introduction),
-        [API Reference](https://api.python.langchain.com/en/stable/),
+        [API Reference](https://python.langchain.com/api_reference/),
         [GitHub search](https://github.com/langchain-ai/langchain),
         [LangChain Github Discussions](https://github.com/langchain-ai/langchain/discussions),
         [LangChain Github Issues](https://github.com/langchain-ai/langchain/issues?q=is%3Aissue),

.github/ISSUE_TEMPLATE/documentation.yml

@@ -21,7 +21,7 @@ body:
       place to ask your question:
       
       [LangChain documentation with the integrated search](https://python.langchain.com/docs/get_started/introduction),
-      [API Reference](https://api.python.langchain.com/en/stable/),
+      [API Reference](https://python.langchain.com/api_reference/),
       [GitHub search](https://github.com/langchain-ai/langchain),
       [LangChain Github Discussions](https://github.com/langchain-ai/langchain/discussions),
       [LangChain Github Issues](https://github.com/langchain-ai/langchain/issues?q=is%3Aissue),

.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

@@ -32,6 +32,10 @@
     "huggingface",
 ]
 
+PY_312_MAX_PACKAGES = [
+    "libs/partners/huggingface",  # https://github.com/pytorch/pytorch/issues/130249
+]
+
 
 def all_package_dirs() -> Set[str]:
     return {
@@ -110,23 +114,30 @@ def _get_configs_for_single_dir(job: str, dir_: str) -> List[Dict[str, str]]:
         return _get_pydantic_test_configs(dir_)
 
     if dir_ == "libs/core":
-        py_versions = ["3.9", "3.10", "3.11", "3.12"]
+        py_versions = ["3.9", "3.10", "3.11", "3.12", "3.13"]
     # custom logic for specific directories
     elif dir_ == "libs/partners/milvus":
         # milvus poetry doesn't allow 3.12 because they
         # declare deps in funny way
         py_versions = ["3.9", "3.11"]
 
-    elif dir_ in ["libs/community", "libs/langchain"] and job == "extended-tests":
-        # community extended test resolution in 3.12 is slow
-        # even in uv
-        py_versions = ["3.9", "3.11"]
+    elif dir_ in PY_312_MAX_PACKAGES:
+        py_versions = ["3.9", "3.12"]
+
+    elif dir_ == "libs/langchain" and job == "extended-tests":
+        py_versions = ["3.9", "3.13"]
+
+    elif dir_ == "libs/community" and job == "extended-tests":
+        py_versions = ["3.9", "3.12"]
 
     elif dir_ == "libs/community" and job == "compile-integration-tests":
         # community integration deps are slow in 3.12
         py_versions = ["3.9", "3.11"]
-    else:
+    elif dir_ == ".":
+        # unable to install with 3.13 because tokenizers doesn't support 3.13 yet
         py_versions = ["3.9", "3.12"]
+    else:
+        py_versions = ["3.9", "3.13"]
 
     return [{"working-directory": dir_, "python-version": py_v} for py_v in py_versions]
 
@@ -261,15 +272,19 @@ def _get_configs_for_multi_dirs(
             # TODO: update to include all packages that rely on standard-tests (all partner packages)
             # note: won't run on external repo partners
             dirs_to_run["lint"].add("libs/standard-tests")
+            dirs_to_run["test"].add("libs/standard-tests")
+            dirs_to_run["lint"].add("libs/cli")
+            dirs_to_run["test"].add("libs/cli")
             dirs_to_run["test"].add("libs/partners/mistralai")
             dirs_to_run["test"].add("libs/partners/openai")
             dirs_to_run["test"].add("libs/partners/anthropic")
             dirs_to_run["test"].add("libs/partners/fireworks")
             dirs_to_run["test"].add("libs/partners/groq")
 
         elif file.startswith("libs/cli"):
-            # todo: add cli makefile
-            pass
+            dirs_to_run["lint"].add("libs/cli")
+            dirs_to_run["test"].add("libs/cli")
+
         elif file.startswith("libs/partners"):
             partner_dir = file.split("/")[2]
             if os.path.isdir(f"libs/partners/{partner_dir}") and [
@@ -279,12 +294,14 @@ def _get_configs_for_multi_dirs(
             ] != ["README.md"]:
                 dirs_to_run["test"].add(f"libs/partners/{partner_dir}")
             # Skip if the directory was deleted or is just a tombstone readme
+        elif file == "libs/packages.yml":
+            continue
         elif file.startswith("libs/"):
             raise ValueError(
                 f"Unknown lib: {file}. check_diff.py likely needs "
                 "an update for this new library!"
             )
-        elif any(file.startswith(p) for p in ["docs/", "templates/", "cookbook/"]):
+        elif any(file.startswith(p) for p in ["docs/", "cookbook/"]):
             if file.startswith("docs/"):
                 docs_edited = True
             dirs_to_run["lint"].add(".")

.github/scripts/get_min_versions.py

@@ -7,17 +7,23 @@
     # for python 3.10 and below, which doesnt have stdlib tomllib
     import tomli as tomllib
 
-from packaging.version import parse as parse_version
 from packaging.specifiers import SpecifierSet
 from packaging.version import Version
 
+
+import requests
+from packaging.version import parse
+from typing import List
+
 import re
 
+
 MIN_VERSION_LIBS = [
     "langchain-core",
     "langchain-community",
     "langchain",
     "langchain-text-splitters",
+    "numpy",
     "SQLAlchemy",
 ]
 
@@ -31,29 +37,61 @@
 ]
 
 
-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.
+
+    Args:
+        package_name (str): Name of the package
+
+    Returns:
+        List[str]: List of all available versions
 
-    # 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
+    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())
 
-    # case x.x.x
-    _match = re.match(f"^({vstring})$", version)
-    if _match:
-        return _match.group(1)
 
-    raise ValueError(f"Unrecognized version format: {version}")
+def get_minimum_version(package_name: str, spec_string: str) -> Optional[str]:
+    """
+    Find the minimum published version that satisfies the given constraints.
+
+    Args:
+        package_name (str): Name of the package
+        spec_string (str): Version specification string (e.g., ">=0.2.43,<0.4.0,!=0.3.0")
+
+    Returns:
+        Optional[str]: Minimum compatible version or None if no compatible version found
+    """
+    # rewrite occurrences of ^0.0.z to 0.0.z (can be anywhere in constraint string)
+    spec_string = re.sub(r"\^0\.0\.(\d+)", r"0.0.\1", spec_string)
+    # rewrite occurrences of ^0.y.z to >=0.y.z,<0.y+1 (can be anywhere in constraint string)
+    for y in range(1, 10):
+        spec_string = re.sub(rf"\^0\.{y}\.(\d+)", rf">=0.{y}.\1,<0.{y+1}", spec_string)
+    # rewrite occurrences of ^x.y.z to >=x.y.z,<x+1.0.0 (can be anywhere in constraint string)
+    for x in range(1, 10):
+        spec_string = re.sub(
+            rf"\^{x}\.(\d+)\.(\d+)", rf">={x}.\1.\2,<{x+1}", spec_string
+        )
+
+    spec_set = SpecifierSet(spec_string)
+    all_versions = get_pypi_versions(package_name)
+
+    valid_versions = []
+    for version_str in all_versions:
+        try:
+            version = parse(version_str)
+            if spec_set.contains(version):
+                valid_versions.append(version)
+        except ValueError:
+            continue
+
+    return str(min(valid_versions)) if valid_versions else None
 
 
 def get_min_version_from_toml(
@@ -96,7 +134,7 @@ def get_min_version_from_toml(
                 ][0]["version"]
 
             # Use parse_version to get the minimum supported version from version_string
-            min_version = get_min_version(version_string)
+            min_version = get_minimum_version(lib, version_string)
 
             # Store the minimum version in the min_versions dictionary
             min_versions[lib] = min_version
@@ -112,6 +150,20 @@ def check_python_version(version_string, constraint_string):
     :param constraint_string: A string representing the package's Python version constraints (e.g. ">=3.6, <4.0").
     :return: True if the version matches the constraints, False otherwise.
     """
+
+    # rewrite occurrences of ^0.0.z to 0.0.z (can be anywhere in constraint string)
+    constraint_string = re.sub(r"\^0\.0\.(\d+)", r"0.0.\1", constraint_string)
+    # rewrite occurrences of ^0.y.z to >=0.y.z,<0.y+1.0 (can be anywhere in constraint string)
+    for y in range(1, 10):
+        constraint_string = re.sub(
+            rf"\^0\.{y}\.(\d+)", rf">=0.{y}.\1,<0.{y+1}.0", constraint_string
+        )
+    # rewrite occurrences of ^x.y.z to >=x.y.z,<x+1.0.0 (can be anywhere in constraint string)
+    for x in range(1, 10):
+        constraint_string = re.sub(
+            rf"\^{x}\.0\.(\d+)", rf">={x}.0.\1,<{x+1}.0.0", constraint_string
+        )
+
     try:
         version = Version(version_string)
         constraints = SpecifierSet(constraint_string)

.github/scripts/prep_api_docs_build.py

@@ -0,0 +1,89 @@
+#!/usr/bin/env python
+"""Script to sync libraries from various repositories into the main langchain repository."""
+
+import os
+import shutil
+import yaml
+from pathlib import Path
+from typing import Dict, Any
+
+
+def load_packages_yaml() -> Dict[str, Any]:
+    """Load and parse the packages.yml file."""
+    with open("langchain/libs/packages.yml", "r") as f:
+        return yaml.safe_load(f)
+
+
+def get_target_dir(package_name: str) -> Path:
+    """Get the target directory for a given package."""
+    package_name_short = package_name.replace("langchain-", "")
+    base_path = Path("langchain/libs")
+    if package_name_short == "experimental":
+        return base_path / "experimental"
+    return base_path / "partners" / package_name_short
+
+
+def clean_target_directories(packages: list) -> None:
+    """Remove old directories that will be replaced."""
+    for package in packages:
+
+        target_dir = get_target_dir(package["name"])
+        if target_dir.exists():
+            print(f"Removing {target_dir}")
+            shutil.rmtree(target_dir)
+
+
+def move_libraries(packages: list) -> None:
+    """Move libraries from their source locations to the target directories."""
+    for package in packages:
+
+        repo_name = package["repo"].split("/")[1]
+        source_path = package["path"]
+        target_dir = get_target_dir(package["name"])
+
+        # Handle root path case
+        if source_path == ".":
+            source_dir = repo_name
+        else:
+            source_dir = f"{repo_name}/{source_path}"
+
+        print(f"Moving {source_dir} to {target_dir}")
+
+        # Ensure target directory exists
+        os.makedirs(os.path.dirname(target_dir), exist_ok=True)
+
+        try:
+            # Move the directory
+            shutil.move(source_dir, target_dir)
+        except Exception as e:
+            print(f"Error moving {source_dir} to {target_dir}: {e}")
+
+
+def main():
+    """Main function to orchestrate the library sync process."""
+    try:
+        # Load packages configuration
+        package_yaml = load_packages_yaml()
+        packages = [
+            p
+            for p in package_yaml["packages"]
+            if not p.get("disabled", False)
+            and p["repo"].startswith("langchain-ai/")
+            and p["repo"] != "langchain-ai/langchain"
+        ]
+
+        # Clean target directories
+        clean_target_directories(packages)
+
+        # Move libraries to their new locations
+        move_libraries(packages)
+
+        print("Library sync completed successfully!")
+
+    except Exception as e:
+        print(f"Error during library sync: {e}")
+        raise
+
+
+if __name__ == "__main__":
+    main()

.github/workflows/_compile_integration_test.yml

@@ -13,14 +13,15 @@ on:
         description: "Python version to use"
 
 env:
-  POETRY_VERSION: "1.7.1"
+  POETRY_VERSION: "1.8.4"
 
 jobs:
   build:
     defaults:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
+    timeout-minutes: 20
     name: "poetry run pytest -m compile tests/integration_tests #${{ inputs.python-version }}"
     steps:
       - uses: actions/checkout@v4