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>
48 lines
1.1 KiB
YAML
48 lines
1.1 KiB
YAML
services:
|
|
caddy:
|
|
image: caddy:2-alpine
|
|
container_name: gpu-caddy
|
|
restart: unless-stopped
|
|
ports:
|
|
- "80:80"
|
|
- "443:443"
|
|
volumes:
|
|
- ./caddy/Caddyfile:/etc/caddy/Caddyfile
|
|
- caddy_data:/data
|
|
depends_on:
|
|
- hub-api
|
|
networks:
|
|
- gateway-net
|
|
|
|
hub-api:
|
|
build: ./hub-api
|
|
container_name: gpu-hub-api
|
|
restart: unless-stopped
|
|
environment:
|
|
- OWNER_PASSWORD=${OWNER_PASSWORD}
|
|
- GUEST_PASSWORD=${GUEST_PASSWORD}
|
|
- JWT_SECRET=${JWT_SECRET}
|
|
- BACKENDS_CONFIG=/app/config/backends.json
|
|
- CORS_ORIGINS=${CORS_ORIGINS:-http://localhost:5173}
|
|
- DB_PATH=/app/data/gateway.db
|
|
volumes:
|
|
- hub_data:/app/data
|
|
- ./backends.json:/app/config/backends.json:ro
|
|
extra_hosts:
|
|
- "host.docker.internal:host-gateway"
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
|
|
interval: 15s
|
|
timeout: 5s
|
|
retries: 3
|
|
networks:
|
|
- gateway-net
|
|
|
|
volumes:
|
|
caddy_data:
|
|
hub_data:
|
|
|
|
networks:
|
|
gateway-net:
|
|
name: gpu-gateway-network
|