community[minor]: Implement lazy_load() for WikipediaLoader

libs/community/langchain_community/document_loaders/wikipedia.py

@@ -1,4 +1,4 @@
-from typing import List, Optional
+from typing import Iterator, Optional
 
 from langchain_core.documents import Document
 
@@ -42,12 +42,12 @@ def __init__(
         self.load_all_available_meta = load_all_available_meta
         self.doc_content_chars_max = doc_content_chars_max
 
-    def load(self) -> List[Document]:
+    def lazy_load(self) -> Iterator[Document]:
         """
         Loads the query result from Wikipedia into a list of Documents.
 
         Returns:
-            List[Document]: A list of Document objects representing the loaded
+            A list of Document objects representing the loaded
                 Wikipedia pages.
         """
         client = WikipediaAPIWrapper(
@@ -56,5 +56,4 @@ def load(self) -> List[Document]:
             load_all_available_meta=self.load_all_available_meta,
             doc_content_chars_max=self.doc_content_chars_max,
         )
-        docs = client.load(self.query)
-        return docs
+        yield from client.load(self.query)

libs/community/langchain_community/utilities/wikipedia.py

@@ -1,6 +1,6 @@
 """Util that calls Wikipedia."""
 import logging
-from typing import Any, Dict, List, Optional
+from typing import Any, Dict, Iterator, List, Optional
 
 from langchain_core.documents import Document
 from langchain_core.pydantic_v1 import BaseModel, root_validator
@@ -104,13 +104,21 @@ def load(self, query: str) -> List[Document]:
 
         Returns: a list of documents.
 
+        """
+        return list(self.lazy_load(query))
+
+    def lazy_load(self, query: str) -> Iterator[Document]:
+        """
+        Run Wikipedia search and get the article text plus the meta information.
+        See
+
+        Returns: a list of documents.
+
         """
         page_titles = self.wiki_client.search(
             query[:WIKIPEDIA_MAX_QUERY_LENGTH], results=self.top_k_results
         )
-        docs = []
         for page_title in page_titles[: self.top_k_results]:
             if wiki_page := self._fetch_page(page_title):
                 if doc := self._page_to_document(page_title, wiki_page):
-                    docs.append(doc)
-        return docs
+                    yield doc