phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 19:24:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

(feat) proxy-pydantic,swagger for chat/completion

Browse source
This commit is contained in:
ishaan-jaff 2023-12-01 13:50:51 -08:00
parent 9750c6f2e1
commit 42f9f35ac1
1 changed files with 45 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

51
litellm/proxy/proxy_server.py
View file

@ -113,6 +113,46 @@ app.add_middleware(
allow_headers=["*"],
)
from typing import Dict
from pydantic import BaseModel, Extra
######### Request Class Definition ######
class ChatCompletionRequest(BaseModel):
model: str
messages: List[Dict[str, str]]
temperature: Optional[float] = None
top_p: Optional[float] = None
n: Optional[int] = None
stream: Optional[bool] = None
stop: Optional[List[str]] = None
max_tokens: Optional[float] = None
presence_penalty: Optional[float] = None
frequency_penalty: Optional[float] = None
logit_bias: Optional[Dict[str, float]] = None
user: Optional[str] = None
response_format: Optional[Dict[str, str]] = None
seed: Optional[int] = None
tools: Optional[List[str]] = None
tool_choice: Optional[str] = None
functions: List[str] = None # soon to be deprecated
function_call: Optional[str] = None # soon to be deprecated
# Optional LiteLLM params
caching: Optional[bool] = None
api_base: Optional[str] = None
api_version: Optional[str] = None
api_key: Optional[str] = None
num_retries: Optional[int] = None
context_window_fallback_dict: Optional[Dict[str, str]] = None
fallbacks: Optional[List[str]] = None
metadata: Optional[Dict[str, str]] = {}
deployment_id: Optional[str] = None
request_timeout: Optional[int] = None
class Config:
extra='allow' # allow params not defined here, these fall in litellm.completion(**kwargs)
user_api_base = None
user_model = None
user_debug = False
@ -712,16 +752,13 @@ 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: Request, model: Optional[str] = None, user_api_key_dict: dict = Depends(user_api_key_auth)) -> litellm.ModelResponse:
async def chat_completion(request: ChatCompletionRequest, model: Optional[str] = None, user_api_key_dict: dict = Depends(user_api_key_auth)) -> litellm.ModelResponse:
global general_settings, user_debug
try:
data = {}
body = await request.body()
body_str = body.decode()
try:
data = ast.literal_eval(body_str)
except:
data = json.loads(body_str)
request_items = request.model_dump()
data = {key: value for key, value in request_items.items() if value is not None} # pydantic sets all values to None, filter out None values here
print_verbose(f"receiving data: {data}")
data["model"] = (
general_settings.get("completion_model", None) # server default