services:
  litellm:
    build: .
    restart: unless-stopped
    environment:
      - LITELLM_MASTER_KEY=${LITELLM_MASTER_KEY:?required}
      - UI_USERNAME=${UI_USERNAME:-admin}
      - UI_PASSWORD=${UI_PASSWORD:?required}
      - DATABASE_URL=postgresql://${POSTGRES_USER:-litellm}:${POSTGRES_PASSWORD:?required}@db:5432/${POSTGRES_DB:-litellm}
      - REDIS_HOST=cache
      - REDIS_PORT=6379
      - OPENROUTER_API_KEY=${OPENROUTER_API_KEY:-}
      - GEMINI_API_KEY=${GEMINI_API_KEY:-}
      - STORE_MODEL_IN_DB=${STORE_MODEL_IN_DB:-True}
      - LITELLM_MODE=${LITELLM_MODE:-PRODUCTION}
      - LITELLM_LOG=${LITELLM_LOG:-ERROR}
      # - TOKENROUTER_API_KEY=${TOKENROUTER_API_KEY:-}
      # - ORCAROUTER_API_KEY=${ORCAROUTER_API_KEY:-}
      # - KIMI_API_KEY=${KIMI_API_KEY:-}
      # - MINIMAX_API_KEY=${MINIMAX_API_KEY:-}
      # - KILO_API_KEY=${KILO_API_KEY:-}
      # - OPENCODE_API_KEY=${OPENCODE_API_KEY:-}
      # - NVIDIA_NIM_API_KEY=${NVIDIA_NIM_API_KEY:-}
      # - OLLAMA_API_KEY=${OLLAMA_API_KEY:-}
      # - CLOUDFLARE_API_KEY=${CLOUDFLARE_API_KEY:-}
      # - CLOUDFLARE_ACCOUNT_ID=${CLOUDFLARE_ACCOUNT_ID:-}
    command:
      - --config
      - /app/config.yaml
      - --port
      - "4000"
      - --run_gunicorn
      - --num_workers
      - "2"
      - --max_requests_before_restart
      - "1000"
    depends_on:
      db:
        condition: service_healthy
      cache:
        condition: service_healthy
    healthcheck:
      test: ["CMD", "python", "-c", "import urllib.request;urllib.request.urlopen('http://127.0.0.1:4000/health/liveliness',timeout=5)"]
      interval: 30s
      timeout: 5s
      retries: 3
      start_period: 30s
    deploy:
      resources:
        limits:
          memory: 4G

  # PostgreSQL for keys, teams, budgets and spend logs.
  db:
    image: postgres:16-alpine
    restart: unless-stopped
    environment:
      - POSTGRES_USER=${POSTGRES_USER:-litellm}
      - POSTGRES_PASSWORD=${POSTGRES_PASSWORD:?required}
      - POSTGRES_DB=${POSTGRES_DB:-litellm}
    volumes:
      - db-data:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -h localhost -U $${POSTGRES_USER} -d $${POSTGRES_DB}"]
      interval: 5s
      timeout: 5s
      retries: 3

  # Redis for the response cache and router state.
  cache:
    image: redis:7-alpine
    restart: unless-stopped
    command: redis-server --appendonly yes
    volumes:
      - cache-data:/data
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 5s
      timeout: 5s
      retries: 3

volumes:
  db-data:
  cache-data: