jpmschweitzerandClaude Opus 4.6
f49c5ac02c
exclude_none was too aggressive — it stripped finish_reason: null from intermediate chunks (which OpenAI includes). exclude_unset correctly omits only fields never passed to the constructor (like reasoning_content on content-only chunks) while preserving explicitly-set finish_reason: null. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
73 lines
1.9 KiB
Python
73 lines
1.9 KiB
Python
"""
|
|
Chat completion router.
|
|
OpenAI-compatible /v1/chat/completions endpoint.
|
|
"""
|
|
import json
|
|
import logging
|
|
from typing import AsyncGenerator
|
|
|
|
from fastapi import APIRouter
|
|
from starlette.responses import StreamingResponse
|
|
|
|
from src.chat import service
|
|
from src.chat.schemas import (
|
|
ChatCompletionRequest,
|
|
ChatCompletionResponse,
|
|
)
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
router = APIRouter(prefix="/chat", tags=["chat"])
|
|
|
|
|
|
async def _stream_response(
|
|
request: ChatCompletionRequest,
|
|
) -> AsyncGenerator[str, None]:
|
|
"""
|
|
Generate SSE stream for chat completion.
|
|
|
|
Yields raw SSE-formatted strings matching OpenAI's format exactly:
|
|
data: {json}\n\n
|
|
"""
|
|
try:
|
|
async for chunk in service.create_chat_completion_stream(request):
|
|
yield f"data: {chunk.model_dump_json(exclude_unset=True)}\n\n"
|
|
|
|
yield "data: [DONE]\n\n"
|
|
|
|
except Exception as e:
|
|
logger.error(f"Error in streaming response: {e}")
|
|
error_data = json.dumps({"error": {"message": str(e), "type": "internal_error"}})
|
|
yield f"data: {error_data}\n\n"
|
|
|
|
|
|
@router.post("/completions", response_model=ChatCompletionResponse)
|
|
async def create_chat_completion(
|
|
request: ChatCompletionRequest,
|
|
) -> ChatCompletionResponse | StreamingResponse:
|
|
"""
|
|
Create chat completion (OpenAI-compatible).
|
|
|
|
Supports both regular and streaming responses.
|
|
|
|
Args:
|
|
request: Chat completion request
|
|
|
|
Returns:
|
|
Chat completion response or SSE stream
|
|
"""
|
|
logger.info(f"Chat completion request for model: {request.model}")
|
|
|
|
if request.stream:
|
|
logger.info("Streaming response requested")
|
|
return StreamingResponse(
|
|
_stream_response(request),
|
|
media_type="text/event-stream",
|
|
headers={
|
|
"Cache-Control": "no-store",
|
|
"X-Accel-Buffering": "no",
|
|
},
|
|
)
|
|
|
|
return await service.create_chat_completion(request)
|