feat: Apply WEB_SEARCH_CONCURRENT_REQUESTS to all search engines using semaphore (#20070)

* sequential

* zero default

* fix
This commit is contained in:
Classic298
2025-12-21 07:18:00 -05:00
committed by GitHub
parent ae203d8952
commit 4fd790f7dd
3 changed files with 49 additions and 24 deletions
+1 -1
View File
@@ -2994,7 +2994,7 @@ WEB_SEARCH_DOMAIN_FILTER_LIST = PersistentConfig(
WEB_SEARCH_CONCURRENT_REQUESTS = PersistentConfig(
"WEB_SEARCH_CONCURRENT_REQUESTS",
"rag.web.search.concurrent_requests",
int(os.getenv("WEB_SEARCH_CONCURRENT_REQUESTS", "10")),
int(os.getenv("WEB_SEARCH_CONCURRENT_REQUESTS", "0")),
)
+32 -10
View File
@@ -2103,16 +2103,38 @@ async def process_web_search(
f"trying to web search with {request.app.state.config.WEB_SEARCH_ENGINE, form_data.queries}"
)
search_tasks = [
run_in_threadpool(
search_web,
request,
request.app.state.config.WEB_SEARCH_ENGINE,
query,
user,
)
for query in form_data.queries
]
# Use semaphore to limit concurrent requests based on WEB_SEARCH_CONCURRENT_REQUESTS
# 0 or None = unlimited (previous behavior), positive number = limited concurrency
# Set to 1 for sequential execution (rate-limited APIs like Brave free tier)
concurrent_limit = request.app.state.config.WEB_SEARCH_CONCURRENT_REQUESTS
if concurrent_limit:
# Limited concurrency with semaphore
semaphore = asyncio.Semaphore(concurrent_limit)
async def search_with_limit(query):
async with semaphore:
return await run_in_threadpool(
search_web,
request,
request.app.state.config.WEB_SEARCH_ENGINE,
query,
user,
)
search_tasks = [search_with_limit(query) for query in form_data.queries]
else:
# Unlimited parallel execution (previous behavior)
search_tasks = [
run_in_threadpool(
search_web,
request,
request.app.state.config.WEB_SEARCH_ENGINE,
query,
user,
)
for query in form_data.queries
]
search_results = await asyncio.gather(*search_tasks)