Oliver/semblance-dev
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Fix Gemini LLM AssertionError: force httpx transport over aiohttp

Browse source 
google-genai SDK uses aiohttp when it's available in the environment
(installed via llama-index-core), causing AssertionError (connector is None)
on async requests. Pass httpx_async_client in HttpOptions to bypass aiohttp.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Vadym Samoilenko 2026-03-23 13:05:27 +00:00
parent 2c6505f472
commit c00728f375
1 changed files with 10 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
backend/app/services/llm_service.py
View file

@ -36,8 +36,17 @@ def get_gemini_client():
Creating a new client per call avoids event loop mismatch issues that occur
when caching clients in ASGI environments where requests may come on different
event loops. The overhead is minimal compared to the LLM API call.
Force httpx transport to avoid aiohttp AssertionError (connector is None)
that occurs when aiohttp is installed in the environment via other packages.
"""
return genai.Client(api_key=GEMINI_API_KEY)
from google.genai import types as genai_types
return genai.Client(
api_key=GEMINI_API_KEY,
http_options=genai_types.HttpOptions(
httpx_async_client=httpx.AsyncClient(timeout=600.0)
)
)
def get_openai_client():