Spaces:
Paused
Paused
File size: 3,282 Bytes
e3c38b5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 |
import json
from fastapi import APIRouter, Depends, HTTPException, Request, Response
from fastapi.responses import StreamingResponse, JSONResponse
from api.auth import verify_app_secret
from api.config import ALLOWED_MODELS
from api.models import ChatRequest
from api.utils import process_non_streaming_response, process_streaming_response
from api.logger import setup_logger
logger = setup_logger(__name__)
router = APIRouter()
@router.options("/v1/chat/completions")
@router.options("/api/v1/chat/completions")
async def chat_completions_options():
return Response(
status_code=200,
headers={
"Access-Control-Allow-Origin": "*",
"Access-Control-Allow-Methods": "POST, OPTIONS",
"Access-Control-Allow-Headers": "Content-Type, Authorization",
},
)
@router.get("/v1/models")
@router.get("/api/v1/models")
async def list_models():
return {"object": "list", "data": ALLOWED_MODELS}
async def stream_wrapper(request: ChatRequest):
"""包装流式响应，处理可能的错误"""
try:
async for chunk in process_streaming_response(request):
yield chunk
except Exception as e:
logger.error(f"Error in stream_wrapper: {str(e)}")
error_response = {
"error": {
"message": "抱歉，处理请求时出现错误，请重试",
"type": "stream_error",
"code": 500
}
}
yield f"data: {json.dumps(error_response)}\n\n"
yield "data: [DONE]\n\n"
@router.post("/v1/chat/completions")
@router.post("/api/v1/chat/completions")
async def chat_completions(
request: ChatRequest, app_secret: str = Depends(verify_app_secret)
):
logger.info("Entering chat_completions route")
logger.info(f"Received request: {request}")
logger.info(f"App secret: {app_secret}")
logger.info(f"Received chat completion request for model: {request.model}")
if request.model not in [model["id"] for model in ALLOWED_MODELS]:
raise HTTPException(
status_code=400,
detail=f"Model {request.model} is not allowed. Allowed models are: {', '.join(model['id'] for model in ALLOWED_MODELS)}",
)
try:
if request.stream:
logger.info("Streaming response")
return StreamingResponse(
stream_wrapper(request),
media_type="text/event-stream",
headers={
"Cache-Control": "no-cache",
"Connection": "keep-alive",
"Transfer-Encoding": "chunked"
}
)
else:
logger.info("Non-streaming response")
return await process_non_streaming_response(request)
except Exception as e:
logger.error(f"Error in chat_completions: {str(e)}")
return JSONResponse(
status_code=500,
content={"error": "处理请求时出现错误，请重试"}
)
@router.route('/')
@router.route('/healthz')
@router.route('/ready')
@router.route('/alive')
@router.route('/status')
@router.get("/health")
def health_check(request: Request):
return Response(content=json.dumps({"status": "ok"}), media_type="application/json")
|