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

(fix) router - allow users to call a specific_model explicit

Browse source
This commit is contained in:
ishaan-jaff 2023-12-05 21:55:07 -08:00
parent acef6bd58d
commit 8e6c4c5310
2 changed files with 27 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

4
litellm/proxy/proxy_server.py
View file

@ -861,7 +861,7 @@ async def chat_completion(request: Request, model: Optional[str] = None, user_ap
if llm_router is not None and data["model"] in router_model_names: # model in router model list
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)
response = await llm_router.acompletion(**data, specific_deployment = True)
else: # router is not set
response = await litellm.acompletion(**data)
if 'stream' in data and data['stream'] == True: # use generate_responses to stream responses
@ -923,7 +923,7 @@ async def embeddings(request: Request, user_api_key_dict: UserAPIKeyAuth = Depen
if llm_router is not None and data["model"] in router_model_names: # model in router model list
response = await llm_router.aembedding(**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.aembedding(**data)
response = await llm_router.aembedding(**data, specific_deployment = True)
else:
response = await litellm.aembedding(**data)
background_tasks.add_task(log_input_output, request, response) # background task for logging to OTEL