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 #16523 from expruc/perf/hybrid_search_bm_25

Browse source 
perf: disable collection retrieval and bm_25 calculation if bm_25 weight is 0
This commit is contained in:
Tim Jaeryang Baek 2025-08-12 23:55:26 +04:00 committed by GitHub
commit 1e67035bd3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 24 additions and 18 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
backend/open_webui/retrieval/utils.py
View file

@ -124,6 +124,8 @@ def query_doc_with_hybrid_search(
hybrid_bm25_weight: float, hybrid_bm25_weight: float,
) -> dict: ) -> dict:
try: try:
# 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],
@ -337,6 +339,8 @@ 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(
@ -348,7 +352,9 @@ 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..."
) )