highperfocused/danswer
1
0
Fork 0
mirror of https://github.com/danswer-ai/danswer.git synced 2025-07-25 12:23:49 +02:00
Code Issues Packages Projects Releases Wiki Activity

Fix semantic id for web pdfs (#1823)

Browse Source
This commit is contained in:
Moshe Zada
2024-07-14 21:38:11 +03:00
committed by GitHub
parent 017af052be
commit 6ee1292757
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
backend/danswer/connectors/web/connector.py
View File

@@ -264,7 +264,7 @@ class WebConnector(LoadConnector):
id=current_url, id=current_url,
sections=[Section(link=current_url, text=page_text)], sections=[Section(link=current_url, text=page_text)],
source=DocumentSource.WEB, source=DocumentSource.WEB,
semantic_identifier=current_url.split(".")[-1], semantic_identifier=current_url.split("/")[-1],
metadata={}, metadata={},
) )
) )