github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-08-19 01:21:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

[Community][Minor]: Fetch loader_source of GoogleDriveLoader in PebbloSafeLoader. (#21314)

Browse Source 
Description: This PR includes fix for loader_source to be fetched from
metadata in case of GdriveLoaders.
Documentation: NA
Unit Test: NA

Signed-off-by: Rahul Tripathi <rauhl.psit.ec@gmail.com>
Co-authored-by: Rahul Tripathi <rauhl.psit.ec@gmail.com>
This commit is contained in:
Rahul Triptahi 2024-05-08 03:15:58 +05:30 committed by GitHub
parent 7cbf1c31aa
commit 7994cba18d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 21 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
libs/community/langchain_community/utilities/pebblo.py
View File

@ -236,6 +236,27 @@ def get_loader_full_path(loader: BaseLoader) -> str:
location = "in-memory"
elif isinstance(loader, NotionDBLoader):
location = f"notiondb://{loader.database_id}"
elif loader.__class__.__name__ == "GoogleDriveLoader":
if loader_dict.get("folder_id"):
folder_id = loader_dict.get("folder_id")
location = f"https://drive.google.com/drive/u/2/folders/{folder_id}"
elif loader_dict.get("file_ids"):
file_ids = loader_dict.get("file_ids", [])
location = ", ".join(
[
f"https://drive.google.com/file/d/{file_id}/view"
for file_id in file_ids
]
)
elif loader_dict.get("document_ids"):
document_ids = loader_dict.get("document_ids", [])
location = ", ".join(
[
f"https://docs.google.com/document/d/{doc_id}/edit"
for doc_id in document_ids
]
)
except Exception:
pass
return get_full_path(str(location))