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

fix(proxy_server.py): restrict model access for /v1/completions endpoint

Browse source
This commit is contained in:
Krrish Dholakia 2024-02-16 11:49:59 -08:00 • committed by ishaan-jaff
parent 936e460a30
commit 01077b20b9
2 changed files with 10 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

8
litellm/model_prices_and_context_window_backup.json
View file

@ -965,15 +965,15 @@
}, },
"dolphin": { "dolphin": {
"max_tokens": 4096, "max_tokens": 4096,
"input_cost_per_token": 0.00002, "input_cost_per_token": 0.0000005,
"output_cost_per_token": 0.00002, "output_cost_per_token": 0.0000005,
"litellm_provider": "nlp_cloud", "litellm_provider": "nlp_cloud",
"mode": "completion" "mode": "completion"
}, },
"chatdolphin": { "chatdolphin": {
"max_tokens": 4096, "max_tokens": 4096,
"input_cost_per_token": 0.00002, "input_cost_per_token": 0.0000005,
"output_cost_per_token": 0.00002, "output_cost_per_token": 0.0000005,
"litellm_provider": "nlp_cloud", "litellm_provider": "nlp_cloud",
"mode": "chat" "mode": "chat"
}, },

7
litellm/proxy/proxy_server.py
View file

@ -2259,8 +2259,13 @@ async def completion(
response = await llm_router.atext_completion( response = await llm_router.atext_completion(
**data, specific_deployment=True **data, specific_deployment=True
) )
else: # router is not set elif user_model is not None: # `litellm --model <your-model-name>`
response = await litellm.atext_completion(**data) response = await litellm.atext_completion(**data)
else:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail={"error": "Invalid model name passed in"},
)
if hasattr(response, "_hidden_params"): if hasattr(response, "_hidden_params"):
model_id = response._hidden_params.get("model_id", None) or "" model_id = response._hidden_params.get("model_id", None) or ""