3794afff95
GPU 서버 중앙 AI 라우팅 서비스 초기 구현: - OpenAI 호환 API (/v1/chat/completions, /v1/models, /v1/embeddings) - 모델 레지스트리 + 백엔드 헬스체크 (30초 루프) - Ollama SSE 프록시 (NDJSON → OpenAI SSE 변환) - JWT 인증 이중 경로 (httpOnly 쿠키 + Bearer 토큰) - owner/guest 역할 분리, 로그인 rate limiting - 백엔드별 rate limiting (NanoClaude 대비) - SQLite 스키마 사전 정의 (aiosqlite + WAL) - Docker Compose + Caddy 리버스 프록시 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
47 lines
1.1 KiB
Python
47 lines
1.1 KiB
Python
from contextlib import asynccontextmanager
|
|
|
|
from fastapi import FastAPI
|
|
from fastapi.middleware.cors import CORSMiddleware
|
|
|
|
from config import settings
|
|
from middleware.auth import AuthMiddleware
|
|
from routers import auth, chat, embeddings, gpu, health, models
|
|
from services.registry import registry
|
|
|
|
|
|
@asynccontextmanager
|
|
async def lifespan(app: FastAPI):
|
|
await registry.load_backends(settings.backends_config)
|
|
registry.start_health_loop()
|
|
yield
|
|
registry.stop_health_loop()
|
|
|
|
|
|
app = FastAPI(
|
|
title="AI Gateway",
|
|
version="0.1.0",
|
|
lifespan=lifespan,
|
|
)
|
|
|
|
app.add_middleware(
|
|
CORSMiddleware,
|
|
allow_origins=settings.cors_origins.split(","),
|
|
allow_credentials=True,
|
|
allow_methods=["*"],
|
|
allow_headers=["*"],
|
|
)
|
|
|
|
app.add_middleware(AuthMiddleware)
|
|
|
|
app.include_router(auth.router)
|
|
app.include_router(chat.router)
|
|
app.include_router(models.router)
|
|
app.include_router(embeddings.router)
|
|
app.include_router(health.router)
|
|
app.include_router(gpu.router)
|
|
|
|
|
|
@app.get("/")
|
|
async def root():
|
|
return {"service": "AI Gateway", "version": "0.1.0"}
|