phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 11:14:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(proxy_server.py): accept max tokens as int

Browse source
This commit is contained in:
Krrish Dholakia 2023-12-01 15:19:34 -08:00
parent 6fd50177e8
commit 923f90aed2
2 changed files with 3 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

4
litellm/proxy/proxy_server.py
View file

@ -126,7 +126,7 @@ class ProxyChatCompletionRequest(BaseModel):
n: Optional[int] = None
stream: Optional[bool] = None
stop: Optional[List[str]] = None
max_tokens: Optional[float] = None
max_tokens: Optional[Union[float, int]] = None
presence_penalty: Optional[float] = None
frequency_penalty: Optional[float] = None
logit_bias: Optional[Dict[str, float]] = None
@ -752,7 +752,7 @@ async def completion(request: Request, model: Optional[str] = None, user_api_key
@router.post("/v1/chat/completions", dependencies=[Depends(user_api_key_auth)], tags=["chat/completions"])
@router.post("/chat/completions", dependencies=[Depends(user_api_key_auth)], tags=["chat/completions"])
@router.post("/openai/deployments/{model:path}/chat/completions", dependencies=[Depends(user_api_key_auth)], tags=["chat/completions"]) # azure compatible endpoint
async def chat_completion(request: ProxyChatCompletionRequest, model: Optional[str] = None, user_api_key_dict: dict = Depends(user_api_key_auth)) -> Union[litellm.ModelResponse, StreamingResponse]:
async def chat_completion(request: ProxyChatCompletionRequest, model: Optional[str] = None, user_api_key_dict: dict = Depends(user_api_key_auth)):
global general_settings, user_debug
try:
data = {}