[Community][minor]: Updating metadata with full_path in SharePoint lo…

…ader (#25593) - **Description:** Updating metadata for sharepoint loader with full path i.e., webUrl - **Issue:** NA - **Dependencies:** NA - **Tests:** NA - **Docs** NA Co-authored-by: dristy.cd <[email protected]> Co-authored-by: ccurme <[email protected]>
langchain-ai · Aug 21, 2024 · b002702 · b002702
1 parent 34d0417
commit b002702
Showing 1 changed file with 5 additions and 0 deletions.
diff --git a/libs/community/langchain_community/document_loaders/sharepoint.py b/libs/community/langchain_community/document_loaders/sharepoint.py
@@ -78,6 +78,7 @@ def lazy_load(self) -> Iterator[Document]:
                     auth_identities = self.authorized_identities(file_id)
                 if self.load_extended_metadata is True:
                     extended_metadata = self.get_extended_metadata(file_id)
+                    extended_metadata.update({"source_full_url": target_folder.web_url})
                 for parsed_blob in blob_parser.lazy_parse(blob):
                     if self.load_auth is True:
                         parsed_blob.metadata["authorized_identities"] = auth_identities
@@ -94,6 +95,7 @@ def lazy_load(self) -> Iterator[Document]:
                     auth_identities = self.authorized_identities(file_id)
                 if self.load_extended_metadata is True:
                     extended_metadata = self.get_extended_metadata(file_id)
+                    extended_metadata.update({"source_full_url": target_folder.web_url})
                 for parsed_blob in blob_parser.lazy_parse(blob):
                     if self.load_auth is True:
                         parsed_blob.metadata["authorized_identities"] = auth_identities
@@ -130,6 +132,9 @@ def lazy_load(self) -> Iterator[Document]:
                         blob_part.metadata["authorized_identities"] = auth_identities
                     if self.load_extended_metadata is True:
                         blob_part.metadata.update(extended_metadata)
+                        blob_part.metadata.update(
+                            {"source_full_url": target_folder.web_url}
+                        )
                     yield blob_part
 
     def authorized_identities(self, file_id: str) -> List: