phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

(fix) proxy: /chat/cmp - check 1 deployment

Browse source
This commit is contained in:
ishaan-jaff 2023-12-05 17:19:39 -08:00
parent a532cf14ae
commit 3af4f7fb0f
1 changed files with 3 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

4
litellm/proxy/proxy_server.py
View file

@ -863,7 +863,9 @@ async def chat_completion(request: Request, model: Optional[str] = None, user_ap
router_model_names = [m["model_name"] for m in llm_model_list] if llm_model_list is not None else [] router_model_names = [m["model_name"] for m in llm_model_list] if llm_model_list is not None else []
if llm_router is not None and data["model"] in router_model_names: # model in router model list if llm_router is not None and data["model"] in router_model_names: # model in router model list
response = await llm_router.acompletion(**data) response = await llm_router.acompletion(**data)
else: elif llm_router is not None and data["model"] in llm_router.deployment_names: # model in router deployments, calling a specific deployment on the router
response = await llm_router.acompletion(**data)
else: # router is not set
response = await litellm.acompletion(**data) response = await litellm.acompletion(**data)
if 'stream' in data and data['stream'] == True: # use generate_responses to stream responses if 'stream' in data and data['stream'] == True: # use generate_responses to stream responses
return StreamingResponse(async_data_generator(response), media_type='text/event-stream') return StreamingResponse(async_data_generator(response), media_type='text/event-stream')