core[minor]: Add aload to document loader (langchain-ai#19936)

Add aload to document loader

Author: eyurtsev

libs/community/langchain_community/document_loaders/web_base.py

@@ -251,7 +251,7 @@ def lazy_load(self) -> Iterator[Document]:
             metadata = _build_metadata(soup, path)
             yield Document(page_content=text, metadata=metadata)
 
-    def aload(self) -> List[Document]:
+    def aload(self) -> List[Document]:  # type: ignore
         """Load text from the urls in web_path async into Documents."""
 
         results = self.scrape_all(self.web_paths)

libs/core/langchain_core/document_loaders/base.py

@@ -28,6 +28,10 @@ def load(self) -> List[Document]:
         """Load data into Document objects."""
         return list(self.lazy_load())
 
+    async def aload(self) -> List[Document]:
+        """Load data into Document objects."""
+        return [document async for document in self.alazy_load()]
+
     def load_and_split(
         self, text_splitter: Optional[TextSplitter] = None
     ) -> List[Document]:

libs/core/tests/unit_tests/document_loaders/test_base.py

@@ -64,3 +64,4 @@ def lazy_load(self) -> Iterator[Document]:
     docs = loader.load()
     assert docs == [Document(page_content="foo"), Document(page_content="bar")]
     assert docs == [doc async for doc in loader.alazy_load()]
+    assert docs == await loader.aload()