docker-compose.yml

version: "3.9"

services:
  # ─── AI Gateway API ────────────────────────────────────────────────────────
  api:
    build:
      context: .
      dockerfile: Dockerfile
    ports:
      - "${API_PORT:-8000}:8000"
    env_file:
      - .env
    environment:
      - WORKERS=${WORKERS:-2}
      - LOG_LEVEL=${LOG_LEVEL:-info}
      - CHROMA_PERSIST_DIR=/data/chroma_db
    volumes:
      - ./chroma_db:/data/chroma_db
      - ./logs:/app/logs
    depends_on:
      - redis
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3

  # ─── Redis (session store, rate limiting, token budget cache) ───────────────
  redis:
    image: redis:7-alpine
    ports:
      - "6379:6379"
    command: redis-server --maxmemory 256mb --maxmemory-policy allkeys-lru
    volumes:
      - redis_data:/data
    restart: unless-stopped

  # ─── Prometheus ────────────────────────────────────────────────────────────
  prometheus:
    image: prom/prometheus:latest
    ports:
      - "9090:9090"
    volumes:
      - ./monitoring/prometheus.yml:/etc/prometheus/prometheus.yml:ro
    restart: unless-stopped

  # ─── Grafana ───────────────────────────────────────────────────────────────
  grafana:
    image: grafana/grafana:latest
    ports:
      - "3000:3000"
    environment:
      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_PASSWORD:-admin}
      - GF_USERS_ALLOW_SIGN_UP=false
    volumes:
      - grafana_data:/var/lib/grafana
    depends_on:
      - prometheus
    restart: unless-stopped

  # ─── Ollama (local models, no API key needed) ───────────────────────────────
  ollama:
    image: ollama/ollama:latest
    ports:
      - "11434:11434"
    volumes:
      - ollama_models:/root/.ollama
    restart: unless-stopped
    # GPU support (uncomment if NVIDIA GPU available):
    # deploy:
    #   resources:
    #     reservations:
    #       devices:
    #         - capabilities: [gpu]

volumes:
  redis_data:
  grafana_data:
  ollama_models: