Support GCS Objects with / in GCS Loaders (langchain-ai#3356)

So, this is basically fixing the same things as langchain-ai#1517 but for GCS.

### Problem
When loading GCS Objects with `/` in the object key (eg.
folder/some-document.txt) using `GCSFileLoader`, the objects are
downloaded into a temporary directory and saved as a file.

This errors out when the parent directory does not exist within the
temporary directory.

### What this pr does
Creates parent directories based on object key.

This also works with deeply nested keys:
folder/subfolder/some-document.txt

langchain/document_loaders/gcs_directory.py

@@ -27,6 +27,10 @@ def load(self) -> List[Document]:
         client = storage.Client(project=self.project_name)
         docs = []
         for blob in client.list_blobs(self.bucket, prefix=self.prefix):
+            # we shall just skip directories since GCSFileLoader creates
+            # intermediate directories on the fly
+            if blob.name.endswith("/"):
+                continue
             loader = GCSFileLoader(self.project_name, self.bucket, blob.name)
             docs.extend(loader.load())
         return docs

langchain/document_loaders/gcs_file.py

@@ -1,4 +1,5 @@
 """Loading logic for loading documents from a GCS file."""
+import os
 import tempfile
 from typing import List
 
@@ -34,6 +35,7 @@ def load(self) -> List[Document]:
         blob = bucket.blob(self.blob)
         with tempfile.TemporaryDirectory() as temp_dir:
             file_path = f"{temp_dir}/{self.blob}"
+            os.makedirs(os.path.dirname(file_path), exist_ok=True)
             # Download the file to a destination
             blob.download_to_filename(file_path)
             loader = UnstructuredFileLoader(file_path)