highperfocused/danswer
1
0
Fork 0
mirror of https://github.com/danswer-ai/danswer.git synced 2025-03-26 17:51:54 +01:00
Code Issues Packages Projects Releases Wiki Activity

Google Drive connector - txt and markdown support (#1469)

Browse Source
This commit is contained in:
lombax85 2024-09-08 05:28:23 +02:00 committed by GitHub
parent b43e5735d7
commit c1735fcd3a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 9 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
backend/danswer/connectors/google_drive/connector.py
View File

@ -62,6 +62,8 @@ class GDriveMimeType(str, Enum):
POWERPOINT = (
"application/vnd.openxmlformats-officedocument.presentationml.presentation"
)
PLAIN_TEXT = "text/plain"
MARKDOWN = "text/markdown"
GoogleDriveFileType = dict[str, Any]
@ -315,12 +317,19 @@ def extract_text(file: dict[str, str], service: discovery.Resource) -> str:
GDriveMimeType.DOC.value,
GDriveMimeType.PPT.value,
GDriveMimeType.SPREADSHEET.value,
GDriveMimeType.PLAIN_TEXT.value,
GDriveMimeType.MARKDOWN.value,
]:
export_mime_type = "text/plain"
if mime_type == GDriveMimeType.SPREADSHEET.value:
export_mime_type = "text/csv"
elif mime_type == GDriveMimeType.PPT.value:
export_mime_type = "text/plain"
elif mime_type in [
GDriveMimeType.PLAIN_TEXT.value,
GDriveMimeType.MARKDOWN.value
]:
export_mime_type = mime_type
response = (
service.files()