phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 18:54:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

(feat) proxy: embedding add OTEL collector

Browse source
This commit is contained in:
ishaan-jaff 2023-12-02 09:41:29 -08:00
parent 4830aa08ee
commit 5edb529891
1 changed files with 2 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
litellm/proxy/proxy_server.py
View file

@ -901,7 +901,7 @@ async def chat_completion(request: Request, model: Optional[str] = None, user_ap
@router.post("/v1/embeddings", dependencies=[Depends(user_api_key_auth)], response_class=ORJSONResponse)
@router.post("/embeddings", dependencies=[Depends(user_api_key_auth)], response_class=ORJSONResponse)
async def embeddings(request: Request, user_api_key_dict: dict = Depends(user_api_key_auth)):
async def embeddings(request: Request, user_api_key_dict: dict = Depends(user_api_key_auth), background_tasks: BackgroundTasks = BackgroundTasks()):
try:
# Use orjson to parse JSON data, orjson speeds up requests significantly
@ -926,6 +926,7 @@ async def embeddings(request: Request, user_api_key_dict: dict = Depends(user_ap
response = await llm_router.aembedding(**data)
else:
response = await litellm.aembedding(**data)
background_tasks.add_task(log_input_output, request, response) # background task for logging to OTEL
return response
except Exception as e:
traceback.print_exc()