docker-compose.prod.yml

version: '3.8'

services:
  # PostgreSQL Database for LangGraph (Production)
  postgres:
    image: postgres:15-alpine
    environment:
      - POSTGRES_DB=${POSTGRES_DB:-langgraph}
      - POSTGRES_USER=${POSTGRES_USER:-langgraph}
      - POSTGRES_PASSWORD=${POSTGRES_PASSWORD}
      - POSTGRES_INITDB_ARGS="--encoding=UTF8 --lc-collate=C --lc-ctype=C"
      - POSTGRES_MAX_CONNECTIONS=500  # Increased for high concurrency production workloads
      - POSTGRES_SHARED_BUFFERS=512MB
      - POSTGRES_EFFECTIVE_CACHE_SIZE=2GB
      - POSTGRES_WORK_MEM=16MB
      - POSTGRES_MAINTENANCE_WORK_MEM=256MB
    volumes:
      - postgres_data:/var/lib/postgresql/data
      - ./postgres/postgresql.conf:/etc/postgresql/postgresql.conf
    ports:
      - "127.0.0.1:5432:5432"  # Only bind to localhost in production
    restart: unless-stopped
    deploy:
      resources:
        limits:
          memory: 2G
          cpus: '2.0'
        reservations:
          memory: 1G
          cpus: '1.0'
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-langgraph} -d ${POSTGRES_DB:-langgraph}"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 30s
    logging:
      driver: "json-file"
      options:
        max-size: "100m"
        max-file: "3"

  # Redis for LangGraph task queue (Production)
  redis:
    image: redis:7-alpine
    command: redis-server --appendonly yes --maxmemory 1G --maxmemory-policy allkeys-lru --tcp-keepalive 60 --timeout 300
    ports:
      - "127.0.0.1:6379:6379"  # Only bind to localhost in production
    volumes:
      - redis_data:/data
      - ./redis/redis.conf:/usr/local/etc/redis/redis.conf
    restart: unless-stopped
    deploy:
      resources:
        limits:
          memory: 1G
          cpus: '1.0'
        reservations:
          memory: 512M
          cpus: '0.5'
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 15s
    logging:
      driver: "json-file"
      options:
        max-size: "50m"
        max-file: "3"

  # LangGraph Backend (Production)
  langgraph-backend:
    build:
      context: ./examples/langgraph-backend
      dockerfile: Dockerfile
      args:
        - ENVIRONMENT=production
    ports:
      - "127.0.0.1:8000:8000"  # Only bind to localhost, accessed via nginx
    environment:
      - OPENAI_API_KEY=${OPENAI_API_KEY}
      - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}
      - TAVILY_API_KEY=${TAVILY_API_KEY}
      - LANGSMITH_API_KEY=${LANGSMITH_API_KEY}
      - LANGGRAPH_DB_URL=postgresql://${POSTGRES_USER:-langgraph}:${POSTGRES_PASSWORD}@postgres:5432/${POSTGRES_DB:-langgraph}
      - REDIS_URL=redis://redis:6379
      - ENVIRONMENT=production
      - HOST=0.0.0.0
      - PORT=8000
      - LOG_LEVEL=${LOG_LEVEL:-info}
      - SECRET_KEY=${SECRET_KEY}
      - ACCESS_TOKEN_EXPIRE_MINUTES=${ACCESS_TOKEN_EXPIRE_MINUTES:-60}
      - ALLOW_ORIGINS=${ALLOW_ORIGINS:-https://yourdomain.com}
      - RATE_LIMIT_REQUESTS_PER_MINUTE=${RATE_LIMIT_REQUESTS_PER_MINUTE:-200}
      - ENABLE_METRICS=${ENABLE_METRICS:-true}
    depends_on:
      postgres:
        condition: service_healthy
      redis:
        condition: service_healthy
    restart: unless-stopped
    deploy:
      resources:
        limits:
          memory: 4G
          cpus: '4.0'
        reservations:
          memory: 2G
          cpus: '2.0'
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 15s
      retries: 5
      start_period: 60s
    logging:
      driver: "json-file"
      options:
        max-size: "200m"
        max-file: "5"

  # SvelteKit Frontend (Production)
  svelte-frontend:
    build:
      context: .
      dockerfile: ./examples/dashboard/Dockerfile
      args:
        - NODE_ENV=production
    ports:
      - "127.0.0.1:3000:3000"  # Only bind to localhost, accessed via nginx
    environment:
      - NODE_ENV=production
      - PUBLIC_LANGGRAPH_CHATBOT_URL=https://yourdomain.com/api/chatbot
      - PUBLIC_LANGGRAPH_CHATBOT_PERSISTENT_URL=https://yourdomain.com/api/chatbot-persistent
      - PUBLIC_LANGGRAPH_CODE_URL=https://yourdomain.com/api/code-assistant
      - PUBLIC_LANGGRAPH_DATA_URL=https://yourdomain.com/api/data-analyst
      - PUBLIC_LANGGRAPH_CREATIVE_URL=https://yourdomain.com/api/creative-writer
      - PUBLIC_LANGGRAPH_RESEARCH_URL=https://yourdomain.com/api/research-assistant
      - PUBLIC_SOCKET_IO_URL=https://yourdomain.com
    depends_on:
      langgraph-backend:
        condition: service_healthy
    restart: unless-stopped
    deploy:
      resources:
        limits:
          memory: 2G
          cpus: '2.0'
        reservations:
          memory: 1G
          cpus: '1.0'
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:3000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 30s
    logging:
      driver: "json-file"
      options:
        max-size: "100m"
        max-file: "3"

  # Nginx reverse proxy (Production)
  nginx:
    image: nginx:alpine
    ports:
      - "80:80"
      - "443:443"
    volumes:
      - ./nginx/nginx.prod.conf:/etc/nginx/nginx.conf
      - ./nginx/ssl:/etc/nginx/ssl
      - ./nginx/logs:/var/log/nginx
    depends_on:
      svelte-frontend:
        condition: service_healthy
      langgraph-backend:
        condition: service_healthy
    restart: unless-stopped
    deploy:
      resources:
        limits:
          memory: 512M
          cpus: '1.0'
        reservations:
          memory: 256M
          cpus: '0.5'
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:80/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 20s
    logging:
      driver: "json-file"
      options:
        max-size: "100m"
        max-file: "5"

  # Prometheus for monitoring (Production)
  prometheus:
    image: prom/prometheus:latest
    ports:
      - "127.0.0.1:9090:9090"
    volumes:
      - ./monitoring/prometheus.yml:/etc/prometheus/prometheus.yml
      - prometheus_data:/prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--web.console.libraries=/etc/prometheus/console_libraries'
      - '--web.console.templates=/etc/prometheus/consoles'
      - '--storage.tsdb.retention.time=30d'
      - '--web.enable-lifecycle'
    restart: unless-stopped
    deploy:
      resources:
        limits:
          memory: 1G
          cpus: '1.0'
        reservations:
          memory: 512M
          cpus: '0.5'

  # Grafana for dashboards (Production)
  grafana:
    image: grafana/grafana:latest
    ports:
      - "127.0.0.1:3001:3000"
    environment:
      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_PASSWORD:-admin}
      - GF_USERS_ALLOW_SIGN_UP=false
    volumes:
      - grafana_data:/var/lib/grafana
      - ./monitoring/grafana/dashboards:/etc/grafana/provisioning/dashboards
      - ./monitoring/grafana/datasources:/etc/grafana/provisioning/datasources
    depends_on:
      - prometheus
    restart: unless-stopped
    deploy:
      resources:
        limits:
          memory: 512M
          cpus: '0.5'
        reservations:
          memory: 256M
          cpus: '0.25'

volumes:
  postgres_data:
    driver: local
  redis_data:
    driver: local
  prometheus_data:
    driver: local
  grafana_data:
    driver: local

networks:
  default:
    driver: bridge
    ipam:
      config:
        - subnet: 172.20.0.0/16