scriptoriumadmin/open-webui
1
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-10-09 03:18:18 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

refac

Browse source
This commit is contained in:
Timothy Jaeryang Baek 2026-08-23 13:33:51 -04:00
parent d16d62d1f1
commit 886248de36
1 changed files with 12 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
backend/open_webui/retrieval/utils.py
View file

@ -197,14 +197,24 @@ def _extract_text_from_binary_response(
os.remove(tmp_path)
TEXT_APPLICATION_CONTENT_TYPES = {
'application/javascript',
'application/json',
'application/xml',
'application/x-javascript',
}
def _is_text_content_type(content_type: str) -> bool:
"""Return True if the content type should be handled by the web loader."""
ct = content_type.split(';')[0].strip().lower()
if not ct:
return True
if ct.startswith('text/'):
return True
if any(t in ct for t in ['xml', 'json', 'javascript']):
if ct in TEXT_APPLICATION_CONTENT_TYPES:
return True
return not ct # empty / missing → assume HTML
return ct.endswith(('+xml', '+json'))
async def get_content_from_url(request, url: str) -> str: