From ddf77656fb5d0e89059c22fc25059677cce7fa4c Mon Sep 17 00:00:00 2001 From: Marc Abramowitz Date: Wed, 15 May 2024 17:36:11 -0700 Subject: [PATCH] Allow non-admins to use OpenAI routes The problem we were having is non-admin users trying to use `/engines/{model}/chat/completions` were getting an HTTP 401 error. ```shell $ curl -sSL 'http://localhost:4000/engines/gpt-35-turbo-0125/chat/completions' \ --header "Authorization: Bearer ${LITELLM_KEY}" \ --header 'Content-Type: application/json' \ --data ' { "model": "gpt-35-turbo-0125", "messages": [ { "role": "user", "content": "Write a poem about LiteLLM" } ] }' \ | jq '.' { "error": { "message": "Authentication Error, Only proxy admin can be used to generate, delete, update info for new keys/users/teams. Route=/engines/gpt-35-turbo-0125/chat/completions. Your role=unknown. Your user_id=someone@company.com", "type": "auth_error", "param": "None", "code": 401 } } ``` This seems to be related to code in `user_api_key_auth` that checks that the URL matches a list of routes that are allowed for non-admin users, where the list of routes is in `LiteLLMRoutes.openai_routes.value`. The problem is that the route `/engines/{model}/chat/completions` is not in that list and furthermore, that wouldn't even work if it were, because the comparison is done with `request.url.path` and that will have the actual model name in it (e.g.: `gpt-35-turbo-0125`), rather than `{model}`. I added a new list `LiteLLMRoutes.openai_route_names` and added the route **names** to that list. Then I added a check in `user_api_key_auth` to see if the route name is in the list of route names. --- litellm/proxy/_types.py | 10 ++++++++++ litellm/proxy/proxy_server.py | 2 ++ 2 files changed, 12 insertions(+) diff --git a/litellm/proxy/_types.py b/litellm/proxy/_types.py index b1af153e81..204405cbfd 100644 --- a/litellm/proxy/_types.py +++ b/litellm/proxy/_types.py @@ -77,6 +77,16 @@ class LiteLLM_UpperboundKeyGenerateParams(LiteLLMBase): class LiteLLMRoutes(enum.Enum): + openai_route_names: List = [ + "chat_completion", + "completion", + "embeddings", + "image_generation", + "audio_transcriptions", + "moderations", + "model_info_v1", + "model_info_v2", + ] openai_routes: List = [ # chat completions "/openai/deployments/{model}/chat/completions", diff --git a/litellm/proxy/proxy_server.py b/litellm/proxy/proxy_server.py index cc5327b758..edfe69fa6e 100644 --- a/litellm/proxy/proxy_server.py +++ b/litellm/proxy/proxy_server.py @@ -1073,6 +1073,8 @@ async def user_api_key_auth( if not _is_user_proxy_admin(user_id_information): # if non-admin if route in LiteLLMRoutes.openai_routes.value: pass + elif request['route'].name in LiteLLMRoutes.openai_route_names.value: + pass elif ( route in LiteLLMRoutes.info_routes.value ): # check if user allowed to call an info route