Emil_Shanaty/open-webui-ai4me
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

perf: 50x performance improvement for external embeddings (#19296)

Browse Source 
* Update utils.py (#77)

Co-authored-by: Claude <noreply@anthropic.com>

* refactor: address code review feedback for embedding performance improvements (#92)

Co-authored-by: Claude <noreply@anthropic.com>

* fix: prevent sentence transformers from blocking async event loop (#95)

Co-authored-by: Claude <noreply@anthropic.com>

---------

Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
Classic298
2025-11-22 20:54:59 -05:00
committed by GitHub
co-authored by Claude
parent bb3e222e09
commit 902c6cfbea
4 changed files with 289 additions and 118 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/open_webui/utils/middleware.py
+26 -31
View File
@@ -993,37 +993,32 @@ async def chat_completion_files_handler(
queries = [get_last_user_message(body["messages"])]
try:
# Offload get_sources_from_items to a separate thread
loop = asyncio.get_running_loop()
with ThreadPoolExecutor() as executor:
sources = await loop.run_in_executor(
executor,
lambda: get_sources_from_items(
request=request,
items=files,
queries=queries,
embedding_function=lambda query, prefix: request.app.state.EMBEDDING_FUNCTION(
query, prefix=prefix, user=user
),
k=request.app.state.config.TOP_K,
reranking_function=(
(
lambda query, documents: request.app.state.RERANKING_FUNCTION(
query, documents, user=user
)
)
if request.app.state.RERANKING_FUNCTION
else None
),
k_reranker=request.app.state.config.TOP_K_RERANKER,
r=request.app.state.config.RELEVANCE_THRESHOLD,
hybrid_bm25_weight=request.app.state.config.HYBRID_BM25_WEIGHT,
hybrid_search=request.app.state.config.ENABLE_RAG_HYBRID_SEARCH,
full_context=all_full_context
or request.app.state.config.RAG_FULL_CONTEXT,
user=user,
),
)
# Directly await async get_sources_from_items (no thread needed - fully async now)
sources = await get_sources_from_items(
request=request,
items=files,
queries=queries,
embedding_function=lambda query, prefix: request.app.state.EMBEDDING_FUNCTION(
query, prefix=prefix, user=user
),
k=request.app.state.config.TOP_K,
reranking_function=(
(
lambda query, documents: request.app.state.RERANKING_FUNCTION(
query, documents, user=user
)
)
if request.app.state.RERANKING_FUNCTION
else None
),
k_reranker=request.app.state.config.TOP_K_RERANKER,
r=request.app.state.config.RELEVANCE_THRESHOLD,
hybrid_bm25_weight=request.app.state.config.HYBRID_BM25_WEIGHT,
hybrid_search=request.app.state.config.ENABLE_RAG_HYBRID_SEARCH,
full_context=all_full_context
or request.app.state.config.RAG_FULL_CONTEXT,
user=user,
)
except Exception as e:
log.exception(e)