ti.sil/open-webui
1
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2025-12-13 04:45:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

Merge pull request #15548 from expruc/fix/docling_ignore_html

Browse source 
fix: text/html files being detected as text when loaded with docling/tika
This commit is contained in:
Tim Jaeryang Baek 2025-07-08 13:16:01 +04:00 committed by GitHub
commit a748f19ac2
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 4 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
backend/open_webui/retrieval/loaders/main.py
View file

@ -226,7 +226,10 @@ class Loader:
def _is_text_file(self, file_ext: str, file_content_type: str) -> bool:
return file_ext in known_source_ext or (
file_content_type and file_content_type.find("text/") >= 0
file_content_type
and file_content_type.find("text/") >= 0
# Avoid text/html files being detected as text
and not file_content_type.find("html") >= 0
)
def _get_loader(self, filename: str, file_content_type: str, file_path: str):