Archives/langchain
2
0
Fork 1
mirror of https://github.com/hwchase17/langchain synced 2024-11-10 01:10:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

community[minor]: [SharePointLoader] Load extended metadata for the root folder (#24872)

Browse Source 
- **Title:** [SharePointLoader] Load extended metadata for the root
folder
- **Description:** 
    - Ensure extended metadata loads correctly for the root folder.
- Cleanup: Refactor SharePointLoader to remove unused fields(`file_id` &
`site_id`).
- **Dependencies:** NA
- **Add tests and docs:** NA
This commit is contained in:
Rajendra Kadam 2024-08-09 00:09:16 +05:30 committed by GitHub
parent 2f209d84fa
commit 663638d6a8
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 9 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
libs/community/langchain_community/document_loaders/sharepoint.py
View File

@ -33,10 +33,6 @@ class SharePointLoader(O365BaseLoader, BaseLoader):
""" Whether to load authorization identities.""" """ Whether to load authorization identities."""
token_path: Path = Path.home() / ".credentials" / "o365_token.txt" token_path: Path = Path.home() / ".credentials" / "o365_token.txt"
""" The path to the token to make api calls""" """ The path to the token to make api calls"""
file_id: Optional[str] = None
""" The ID of the file for which we need auth identities"""
site_id: Optional[str] = None
""" The ID of the Sharepoint site of the user where the file is present """
load_extended_metadata: Optional[bool] = False load_extended_metadata: Optional[bool] = False
""" Whether to load extended metadata. Size, Owner and full_path.""" """ Whether to load extended metadata. Size, Owner and full_path."""
@ -123,8 +119,17 @@ class SharePointLoader(O365BaseLoader, BaseLoader):
if not isinstance(target_folder, Folder): if not isinstance(target_folder, Folder):
raise ValueError("Unable to fetch root folder") raise ValueError("Unable to fetch root folder")
for blob in self._load_from_folder(target_folder): for blob in self._load_from_folder(target_folder):
file_id = str(blob.metadata.get("id"))
if self.load_auth is True:
auth_identities = self.authorized_identities(file_id)
if self.load_extended_metadata is True:
extended_metadata = self.get_extended_metadata(file_id)
for blob_part in blob_parser.lazy_parse(blob): for blob_part in blob_parser.lazy_parse(blob):
blob_part.metadata.update(blob.metadata) blob_part.metadata.update(blob.metadata)
if self.load_auth is True:
blob_part.metadata["authorized_identities"] = auth_identities
if self.load_extended_metadata is True:
blob_part.metadata.update(extended_metadata)
yield blob_part yield blob_part
def authorized_identities(self, file_id: str) -> List: def authorized_identities(self, file_id: str) -> List: