Merge branch 'LindormIntegration' of github.com:AlwaysBluer/langchain…

… into LindormIntegration

* 'LindormIntegration' of github.com:AlwaysBluer/langchain:
  docs: more standard test stubs (langchain-ai#28202)
  docs: links in integration contrib (langchain-ai#28200)
  standard-tests: rename langchain_standard_tests to langchain_tests, release 0.3.2 (langchain-ai#28203)
  infra: allow non-langchainai packages (langchain-ai#28199)
  openai: release 0.2.9, o1 streaming (langchain-ai#28197)
  docs: efficient rebuild (langchain-ai#28195)
  docs: fix embeddings tabs (langchain-ai#28193)
  docs: fixed a typo (langchain-ai#28191)
  docs[patch]: Add missing link to streaming concepts page (langchain-ai#28189)
  docs: add component tabs to integration landing pages (langchain-ai#28142)
  docs: community integration guide clarification (langchain-ai#28186)
  docs: standard test update (langchain-ai#28185)
  docs: fix grammatical error in delegation to sync methods (langchain-ai#28165)
  langchain: add missing punctuation in react_single_input.py (langchain-ai#28161)

.github/scripts/prep_api_docs_build.py

@@ -11,7 +11,9 @@
 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)
+        all_packages = yaml.safe_load(f)
+
+    return {k: v for k, v in all_packages.items() if k["repo"]}
 
 
 def get_target_dir(package_name: str) -> Path:
@@ -23,24 +25,19 @@ def get_target_dir(package_name: str) -> Path:
     return base_path / "partners" / package_name_short
 
 
-def clean_target_directories(packages: Dict[str, Any]) -> None:
+def clean_target_directories(packages: list) -> None:
     """Remove old directories that will be replaced."""
-    for package in packages["packages"]:
-        if package["repo"] != "langchain-ai/langchain":
-            target_dir = get_target_dir(package["name"])
-            if target_dir.exists():
-                print(f"Removing {target_dir}")
-                shutil.rmtree(target_dir)
+    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: Dict[str, Any]) -> None:
+def move_libraries(packages: list) -> None:
     """Move libraries from their source locations to the target directories."""
-    for package in packages["packages"]:
-        # Skip if it's the main langchain repo or disabled
-        if package["repo"] == "langchain-ai/langchain" or package.get(
-            "disabled", False
-        ):
-            continue
+    for package in packages:
 
         repo_name = package["repo"].split("/")[1]
         source_path = package["path"]
@@ -68,7 +65,14 @@ def main():
     """Main function to orchestrate the library sync process."""
     try:
         # Load packages configuration
-        packages = load_packages_yaml()
+        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)

.github/workflows/_release.yml

@@ -219,11 +219,7 @@ jobs:
 
           # Replace all dashes in the package name with underscores,
           # since that's how Python imports packages with dashes in the name.
-          if [ "$PKG_NAME" == "langchain-tests" ]; then
-            IMPORT_NAME="langchain_standard_tests"
-          else
-            IMPORT_NAME="$(echo "$PKG_NAME" | sed s/-/_/g)"
-          fi
+          IMPORT_NAME="$(echo "$PKG_NAME" | sed s/-/_/g)"
 
           poetry run python -c "import $IMPORT_NAME; print(dir($IMPORT_NAME))"
 

.github/workflows/api_doc_build.yml

@@ -37,9 +37,9 @@ jobs:
           # Get unique repositories
           REPOS=$(echo "$REPOS_UNSORTED" | sort -u)
           
-          # Checkout each unique repository
+          # Checkout each unique repository that is in langchain-ai org
           for repo in $REPOS; do
-            if [ "$repo" != "langchain-ai/langchain" ]; then
+            if [[ "$repo" != "langchain-ai/langchain" && "$repo" == langchain-ai/* ]]; then
               REPO_NAME=$(echo $repo | cut -d'/' -f2)
               echo "Checking out $repo to $REPO_NAME"
               git clone --depth 1 https://github.com/$repo.git $REPO_NAME

docs/Makefile

@@ -38,7 +38,7 @@ install-py-deps:
 
 generate-files:
 	mkdir -p $(INTERMEDIATE_DIR)
-	cp -r $(SOURCE_DIR)/* $(INTERMEDIATE_DIR)
+	cp -rp $(SOURCE_DIR)/* $(INTERMEDIATE_DIR)
 
 	$(PYTHON) scripts/tool_feat_table.py $(INTERMEDIATE_DIR)
 

docs/docs/concepts/async.mdx

@@ -46,7 +46,7 @@ Most popular LangChain integrations implement asynchronous support of their APIs
 When an asynchronous implementation is not available, LangChain tries to provide a default implementation, even if it incurs
 a **slight** overhead.
 
-By default, LangChain will delegate the execution of a unimplemented asynchronous methods to the synchronous counterparts. LangChain almost always assumes that the synchronous method should be treated as a blocking operation and should be run in a separate thread.
+By default, LangChain will delegate the execution of unimplemented asynchronous methods to the synchronous counterparts. LangChain almost always assumes that the synchronous method should be treated as a blocking operation and should be run in a separate thread.
 This is done using [asyncio.loop.run_in_executor](https://docs.python.org/3/library/asyncio-eventloop.html#asyncio.loop.run_in_executor) functionality provided by the `asyncio` library. LangChain uses the default executor provided by the `asyncio` library, which lazily initializes a thread pool executor with a default number of threads that is reused in the given event loop. While this strategy incurs a slight overhead due to context switching between threads, it guarantees that every asynchronous method has a default implementation that works out of the box.
 
 ## Performance

docs/docs/concepts/index.mdx

@@ -22,6 +22,7 @@ The conceptual guide does not cover step-by-step instructions or specific implem
 - **[Memory](https://langchain-ai.github.io/langgraph/concepts/memory/)**: Information about a conversation that is persisted so that it can be used in future conversations.
 - **[Multimodality](/docs/concepts/multimodality)**: The ability to work with data that comes in different forms, such as text, audio, images, and video.
 - **[Runnable interface](/docs/concepts/runnables)**: The base abstraction that many LangChain components and the LangChain Expression Language are built on.
+- **[Streaming](/docs/concepts/streaming)**: LangChain streaming APIs for surfacing results as they are generated.
 - **[LangChain Expression Language (LCEL)](/docs/concepts/lcel)**: A syntax for orchestrating LangChain components. Most useful for simpler applications.
 - **[Document loaders](/docs/concepts/document_loaders)**: Load a source as a list of documents.
 - **[Retrieval](/docs/concepts/retrieval)**: Information retrieval systems can retrieve structured or unstructured data from a datasource in response to a query.

docs/docs/contributing/how_to/index.mdx

@@ -2,4 +2,8 @@
 
 - [**Documentation**](documentation/index.mdx): Help improve our docs, including this one!
 - [**Code**](code/index.mdx): Help us write code, fix bugs, or improve our infrastructure.
-- [**Integrations**](integrations/index.mdx): Help us integrate with your favorite vendors and tools.
+
+## Integrations
+
+- [**Start Here**](integrations/index.mdx): Help us integrate with your favorite vendors and tools.
+- [**Standard Tests**](integrations/standard_tests): Ensure your integration passes an expected set of tests.

docs/docs/contributing/how_to/integrations/community.mdx

@@ -1,10 +1,11 @@
-## How to add a community integration (deprecated)
+## How to add a community integration (not recommended)
 
 :::danger
 
-We are no longer accepting new community integrations. Please see the
-[main integration guide](./index.mdx) for more information on contributing new
-integrations.
+We recommend following the [main integration guide](./index.mdx) to add new integrations instead.
+
+If you follow this guide, there is a high likelihood we will close your PR with the above
+guide linked without much discussion.
 
 :::
 

docs/docs/contributing/how_to/integrations/index.mdx

@@ -65,10 +65,10 @@ that will render on this site (https://python.langchain.com/).
 
 As a prerequisite to adding your integration to our documentation, you must:
 
-1. Confirm that your integration is in the list of components we are currently accepting.
+1. Confirm that your integration is in the [list of components](#components-to-integrate) we are currently accepting.
 2. Ensure that your integration is in a separate package that can be installed with `pip install <your-package>`.
-3. Implement the standard tests for your integration and successfully run them.
-3. Write documentation for your integration in the `docs/docs/integrations` directory of the LangChain monorepo.
+3. [Implement the standard tests](/docs/contributing/how_to/integrations/standard_tests) for your integration and successfully run them.
+3. Write documentation for your integration in the `docs/docs/integrations/<component_type>` directory of the LangChain monorepo.
 4. Add a provider page for your integration in the `docs/docs/integrations/providers` directory of the LangChain monorepo.
 
 Once you have completed these steps, you can submit a PR to the LangChain monorepo to add your integration to the documentation.