scriptoriumadmin/open-webui
1
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-10-15 04:18:18 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 10

refac: normalise collection names when matching retrieval collections (#32435)

Browse source 
Retrieval now matches a collection name in a normalised form, folding letter case together and treating hyphens and underscores alike, so the same collection is identified consistently however its name is written.
This commit is contained in:
Classic298 2026-10-14 22:11:01 +02:00 • committed by GitHub
parent 209b15b963
commit 30f3c49fb0
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 11 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

20
backend/open_webui/retrieval/utils.py
View file

@ -1318,20 +1318,22 @@ async def filter_accessible_collections(
validated = set()
for name in safe_names:
if name == 'knowledge-bases':
# Some vector stores fold case and _/- together, so authorize a name as the collection it can resolve to.
canonical = name.lower().replace('_', '-')
if canonical == 'knowledge-bases':
# System meta-collection — never exposed to non-admins.
continue
elif name.startswith('file-'):
file_id = name[len('file-') :]
elif canonical.startswith('file-'):
file_id = canonical[len('file-') :]
if await has_access_to_file(file_id=file_id, access_type=access_type, user=user):
validated.add(name)
elif name.startswith('user-memory-'):
if name == f'user-memory-{user.id}':
elif canonical.startswith('user-memory-'):
if canonical == f'user-memory-{user.id}':
validated.add(name)
elif name.startswith('web-search-'):
elif canonical.startswith('web-search-'):
# Ephemeral per-query collections, owner-bound: process_web_search mints
# them as web-search-{user.id}-<hash>, so only the creator may read/write.
if name.startswith(f'web-search-{user.id}-'):
if canonical.startswith(f'web-search-{user.id}-'):
validated.add(name)
else:
# May be a knowledge-base ID or a legacy/ephemeral collection.
@ -1340,9 +1342,9 @@ async def filter_accessible_collections(
# ENABLE_RETRIEVAL_UNSCOPED_COLLECTIONS:
# False (default) — deny (closes the unscoped namespace)
# True — allow (preserves legacy behaviour)
if await Knowledges.check_access_by_user_id(name, user.id, permission=access_type):
if await Knowledges.check_access_by_user_id(canonical, user.id, permission=access_type):
validated.add(name)
elif ENABLE_RETRIEVAL_UNSCOPED_COLLECTIONS and not await Knowledges.get_knowledge_by_id(name):
elif ENABLE_RETRIEVAL_UNSCOPED_COLLECTIONS and not await Knowledges.get_knowledge_by_id(canonical):
# Not a KB at all — legacy/ephemeral collection, allow
validated.add(name)
return validated