github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-07-14 17:07:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

add error message to the google drive document loader (#2186)

Browse Source 
When downloading a google doc, if the document is not a google doc type,
for example if you uploaded a .DOCX file to your google drive, the error
you get is not informative at all. I added a error handler which print
the exact error occurred during downloading the document from google
docs.
This commit is contained in:
Kevin Kermani Nejad 2023-03-31 04:58:27 +01:00 committed by GitHub
parent 2eeaccf01c
commit 6c66f51fb8
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 11 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
langchain/document_loaders/googledrive.py
View File

@ -142,6 +142,7 @@ class GoogleDriveLoader(BaseLoader, BaseModel):
from io import BytesIO from io import BytesIO
from googleapiclient.discovery import build from googleapiclient.discovery import build
from googleapiclient.errors import HttpError
from googleapiclient.http import MediaIoBaseDownload from googleapiclient.http import MediaIoBaseDownload
creds = self._load_credentials() creds = self._load_credentials()
@ -151,8 +152,16 @@ class GoogleDriveLoader(BaseLoader, BaseModel):
fh = BytesIO() fh = BytesIO()
downloader = MediaIoBaseDownload(fh, request) downloader = MediaIoBaseDownload(fh, request)
done = False done = False
while done is False: try:
status, done = downloader.next_chunk() while done is False:
status, done = downloader.next_chunk()
except HttpError as e:
if e.resp.status == 404:
print("File not found: {}".format(id))
else:
print("An error occurred: {}".format(e))
text = fh.getvalue().decode("utf-8") text = fh.getvalue().decode("utf-8")
metadata = {"source": f"https://docs.google.com/document/d/{id}/edit"} metadata = {"source": f"https://docs.google.com/document/d/{id}/edit"}
return Document(page_content=text, metadata=metadata) return Document(page_content=text, metadata=metadata)