phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 03:34:10 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(ollama.py): fix async completion calls for ollama

Browse source
This commit is contained in:
Krrish Dholakia 2023-12-13 13:10:25 -08:00
parent aa649a8599
commit 2231601d5a
7 changed files with 35 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

1
litellm/proxy/proxy_server.py
View file

@ -1004,6 +1004,7 @@ async def chat_completion(request: Request, model: Optional[str] = None, user_ap
### ROUTE THE REQUEST ###
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
print(f"ENTERS LLM ROUTER ACOMPLETION")
response = await llm_router.acompletion(**data)
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, specific_deployment = True)