lint fixes

libs/langchain/langchain/vectorstores/base.py

@@ -88,35 +88,47 @@ class VectorStore(ABC):
     ) -> List[str]:
         """Run more texts through the embeddings and add to the vectorstore."""
         raise NotImplementedError
-
+    
-    def add_documents(self, documents: List[Document], **kwargs: Any) -> List[str]:
+    def add_documents(self, documents: List[Document], batch_size: int = 100, **kwargs: Any
-        """Run more documents through the embeddings and add to the vectorstore.
+    ) -> List[str]:
+        """Run more documents through the embeddings and add to the vectorstore
+        in batches.
 
         Args:
             documents (List[Document]: Documents to add to the vectorstore.
+            batch_size (int): Size of the batch to add to the vectorstore.
 
         Returns:
             List[str]: List of IDs of the added texts.
         """
         # TODO: Handle the case where the user doesn't provide ids on the Collection
-        texts = [doc.page_content for doc in documents]
+        ids = []
-        metadatas = [doc.metadata for doc in documents]
+        for i in range(0, len(documents), batch_size):
-        return self.add_texts(texts, metadatas, **kwargs)
+            batch = documents[i:i+batch_size]
+            texts = [doc.page_content for doc in batch]
+            metadatas = [doc.metadata for doc in batch]
+            ids.extend(self.add_texts(texts, metadatas, **kwargs))
+        return ids
 
     async def aadd_documents(
-        self, documents: List[Document], **kwargs: Any
+        self, documents: List[Document], batch_size: int = 100, **kwargs: Any
     ) -> List[str]:
-        """Run more documents through the embeddings and add to the vectorstore.
+        """Run more documents through the embeddings and add to the vectorstore
-
+        in batches.
+        
         Args:
             documents (List[Document]: Documents to add to the vectorstore.
 
         Returns:
             List[str]: List of IDs of the added texts.
         """
-        texts = [doc.page_content for doc in documents]
+        ids = []
-        metadatas = [doc.metadata for doc in documents]
+        for i in range(0, len(documents), batch_size):
-        return await self.aadd_texts(texts, metadatas, **kwargs)
+            batch = documents[i:i+batch_size]
+            texts = [doc.page_content for doc in batch]
+            metadatas = [doc.metadata for doc in batch]
+            ids.extend(await self.aadd_texts(texts, metadatas, **kwargs))
+        return ids
 
     def search(self, query: str, search_type: str, **kwargs: Any) -> List[Document]:
         """Return docs most similar to query using specified search type."""