ti.sil/open-webui
1
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2025-12-12 04:15:25 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

Merge pull request #17049 from rgaricano/dev-FIX_lex-sem

Browse source 
FIX: Hybrid Search
This commit is contained in:
Tim Jaeryang Baek 2025-09-01 00:00:25 +04:00 committed by GitHub
commit 719d115d49
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 4 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
backend/open_webui/retrieval/utils.py
View file

@ -128,8 +128,6 @@ def query_doc_with_hybrid_search(
log.warning(f"query_doc_with_hybrid_search:no_docs {collection_name}") log.warning(f"query_doc_with_hybrid_search:no_docs {collection_name}")
return {"documents": [], "metadatas": [], "distances": []} return {"documents": [], "metadatas": [], "distances": []}
# BM_25 required only if weight is greater than 0
if hybrid_bm25_weight > 0:
log.debug(f"query_doc_with_hybrid_search:doc {collection_name}") log.debug(f"query_doc_with_hybrid_search:doc {collection_name}")
bm25_retriever = BM25Retriever.from_texts( bm25_retriever = BM25Retriever.from_texts(
texts=collection_result.documents[0], texts=collection_result.documents[0],
@ -343,8 +341,7 @@ def query_collection_with_hybrid_search(
# Fetch collection data once per collection sequentially # Fetch collection data once per collection sequentially
# Avoid fetching the same data multiple times later # Avoid fetching the same data multiple times later
collection_results = {} collection_results = {}
# Only retrieve entire collection if bm_25 calculation is required
if hybrid_bm25_weight > 0:
for collection_name in collection_names: for collection_name in collection_names:
try: try:
log.debug( log.debug(
@ -356,9 +353,7 @@ def query_collection_with_hybrid_search(
except Exception as e: except Exception as e:
log.exception(f"Failed to fetch collection {collection_name}: {e}") log.exception(f"Failed to fetch collection {collection_name}: {e}")
collection_results[collection_name] = None collection_results[collection_name] = None
else:
for collection_name in collection_names:
collection_results[collection_name] = []
log.info( log.info(
f"Starting hybrid search for {len(queries)} queries in {len(collection_names)} collections..." f"Starting hybrid search for {len(queries)} queries in {len(collection_names)} collections..."
) )

4
src/lib/components/admin/Settings/Documents.svelte
View file

@ -1104,10 +1104,10 @@
<div class="py-0.5"> <div class="py-0.5">
<div class="flex w-full justify-between"> <div class="flex w-full justify-between">
<div class=" text-left text-xs font-small"> <div class=" text-left text-xs font-small">
{$i18n.t('lexical')} {$i18n.t('semantic')}
</div> </div>
<div class=" text-right text-xs font-small"> <div class=" text-right text-xs font-small">
{$i18n.t('semantic')} {$i18n.t('lexical')}
</div> </div>
</div> </div>
</div> </div>