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

fix using pass_through_all_models

Browse source
This commit is contained in:
Ishaan Jaff 2024-07-25 19:32:49 -07:00
parent af1cd9e06f
commit 693bcfac39
2 changed files with 22 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

33
litellm/proxy/proxy_server.py
View file

@ -2882,14 +2882,15 @@ async def chat_completion(
elif (
llm_router is not None
and data["model"] not in router_model_names
and llm_router.default_deployment is not None
): # model in router deployments, calling a specific deployment on the router
tasks.append(llm_router.acompletion(**data))
elif (
llm_router is not None
and llm_router.router_general_settings.pass_through_all_models is True
):
tasks.append(litellm.acompletion(**data))
elif (
llm_router is not None
and data["model"] not in router_model_names
and llm_router.default_deployment is not None
): # model in router deployments, calling a specific deployment on the router
tasks.append(llm_router.acompletion(**data))
elif user_model is not None: # `litellm --model <your-model-name>`
tasks.append(litellm.acompletion(**data))
else:
@ -3144,6 +3145,12 @@ async def completion(
llm_router is not None and data["model"] in llm_router.get_model_ids()
): # model in router model list
llm_response = asyncio.create_task(llm_router.atext_completion(**data))
elif (
llm_router is not None
and data["model"] not in router_model_names
and llm_router.router_general_settings.pass_through_all_models is True
):
llm_response = asyncio.create_task(litellm.atext_completion(**data))
elif (
llm_router is not None
and data["model"] not in router_model_names
@ -3152,11 +3159,6 @@ async def completion(
llm_response = asyncio.create_task(llm_router.atext_completion(**data))
elif user_model is not None: # `litellm --model <your-model-name>`
llm_response = asyncio.create_task(litellm.atext_completion(**data))
elif (
llm_router is not None
and llm_router.router_general_settings.pass_through_all_models is True
):
llm_response = asyncio.create_task(litellm.atext_completion(**data))
else:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
@ -3412,14 +3414,15 @@ async def embeddings(
elif (
llm_router is not None
and data["model"] not in router_model_names
and llm_router.default_deployment is not None
): # model in router deployments, calling a specific deployment on the router
tasks.append(llm_router.aembedding(**data))
elif (
llm_router is not None
and llm_router.router_general_settings.pass_through_all_models is True
):
tasks.append(litellm.aembedding(**data))
elif (
llm_router is not None
and data["model"] not in router_model_names
and llm_router.default_deployment is not None
): # model in router deployments, calling a specific deployment on the router
tasks.append(llm_router.aembedding(**data))
elif user_model is not None: # `litellm --model <your-model-name>`
tasks.append(litellm.aembedding(**data))
else: