hyungi_document_server/docker-compose.yml

services:
  postgres:
    image: pgvector/pgvector:pg16
    volumes:
      - pgdata:/var/lib/postgresql/data
      - ./migrations:/docker-entrypoint-initdb.d
    environment:
      POSTGRES_DB: pkm
      POSTGRES_USER: pkm
      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD}
    ports:
      - "15432:5432"
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U pkm"]
      interval: 5s
      timeout: 5s
      retries: 5
    restart: unless-stopped

  kordoc-service:
    build: ./services/kordoc
    ports:
      - "3100:3100"
    volumes:
      - ${NAS_NFS_PATH:-/mnt/nas/Document_Server}:/documents:ro
    mem_limit: 4g
    memswap_limit: 4g
    healthcheck:
      test: ["CMD", "node", "-e", "fetch('http://localhost:3100/health').then(r=>{process.exit(r.ok?0:1)}).catch(()=>process.exit(1))"]
      interval: 10s
      timeout: 5s
      retries: 3
    restart: unless-stopped

  ocr-service:
    build: ./services/ocr
    expose:
      - "3200"
    volumes:
      - ${NAS_NFS_PATH:-/mnt/nas/Document_Server}:/documents:ro
      - ocr_models:/root/.cache
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    healthcheck:
      test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:3200/health')"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 180s
    restart: unless-stopped

  stt-service:
    build: ./services/stt
    expose:
      - "3300"
    volumes:
      - ${NAS_NFS_PATH:-/mnt/nas/Document_Server}:/documents:ro
      - stt_models:/root/.cache
    environment:
      - WHISPER_MODEL=${WHISPER_MODEL:-large-v3}
      - WHISPER_DEVICE=${WHISPER_DEVICE:-cuda}
      - WHISPER_COMPUTE_TYPE=${WHISPER_COMPUTE_TYPE:-float16}
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    healthcheck:
      # /ready: CUDA 디바이스 + 모델 적재 둘 다 확인. ready=true 만 healthy 처리.
      # /health 는 단순 liveness 라 모델 미적재 상태도 healthy 로 잡혀 운영 신호로 부적합.
      test: ["CMD", "python3", "-c", "import json,urllib.request,sys; r=urllib.request.urlopen('http://localhost:3300/ready'); sys.exit(0 if json.load(r).get('ready') else 1)"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 300s
    restart: unless-stopped

  ollama:
    image: ollama/ollama
    volumes:
      - ollama_data:/root/.ollama
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    ports:
      - "127.0.0.1:11434:11434"
    restart: unless-stopped

  # Phase 1.3: bge-reranker-v2-m3 (TEI) — internal only, fastapi에서 reranker:80으로 호출
  # fastapi가 depends_on 안 함 → 단독 시작 가능, 없어도 fastapi 동작 (rerank=false fallback)
  reranker:
    image: ghcr.io/huggingface/text-embeddings-inference:1.7
    container_name: hyungi_document_server-reranker-1
    expose:
      - "80"
    environment:
      - MODEL_ID=BAAI/bge-reranker-v2-m3
      - MAX_BATCH_TOKENS=8192
      - MAX_CONCURRENT_REQUESTS=4
    volumes:
      - reranker_cache:/data
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    restart: unless-stopped

  ai-gateway:
    build: ./gpu-server/services/ai-gateway
    ports:
      - "127.0.0.1:8081:8080"
    environment:
      - PRIMARY_ENDPOINT=http://100.76.254.116:8801/v1/chat/completions
      - FALLBACK_ENDPOINT=http://ollama:11434/v1/chat/completions
      - CLAUDE_API_KEY=${CLAUDE_API_KEY:-}
      - DAILY_BUDGET_USD=${DAILY_BUDGET_USD:-5.00}
    depends_on:
      - ollama
    restart: unless-stopped

  fastapi:
    build: ./app
    ports:
      - "8000:8000"
    volumes:
      - ${NAS_NFS_PATH:-/mnt/nas/Document_Server}:/documents
      - ./config.yaml:/app/config.yaml:ro
      - ./scripts:/app/scripts:ro
      - ./logs:/app/logs
      - ./migrations:/app/migrations:ro
    depends_on:
      postgres:
        condition: service_healthy
      kordoc-service:
        condition: service_healthy
    env_file:
      - credentials.env
    environment:
      - DATABASE_URL=postgresql+asyncpg://pkm:${POSTGRES_PASSWORD}@postgres:5432/pkm
      - KORDOC_ENDPOINT=http://kordoc-service:3100
      - OCR_ENDPOINT=http://ocr-service:3200
      - STT_ENDPOINT=http://stt-service:3300
    restart: unless-stopped

  frontend:
    build: ./frontend
    ports:
      - "3000:3000"
    depends_on:
      - fastapi
    restart: unless-stopped

  caddy:
    image: caddy:2
    ports:
      - "8080:80"
    volumes:
      - ./Caddyfile:/etc/caddy/Caddyfile
      - caddy_data:/data
    depends_on:
      - fastapi
      - frontend
    restart: unless-stopped

volumes:
  pgdata:
  caddy_data:
  ollama_data:
  reranker_cache:
  ocr_models:
  stt_models: