docker-compose.yml

version: '3.8'

services:
  backend:
    build:
      context: .
      dockerfile: Dockerfile.backend
      args:
        BUILDKIT_INLINE_CACHE: 1
      cache_from:
        - type=local,src=/tmp/.buildx-cache
        - type=local,src=/tmp/.buildx-cache-new
    ports:
      - "8000:8000"
    environment:
      - IN_DOCKER=true
      - POSTGRES_SERVER=postgres
      - POSTGRES_USER=postgres
      - POSTGRES_PASSWORD=postgres
      - POSTGRES_DB=file_upload_embeddings
      - REDIS_URL=redis://redis:6379/0
      - OPENAI_API_KEY=${OPENAI_API_KEY}
      - AZURE_OPENAI_API_KEY=${AZURE_OPENAI_API_KEY:-}
      - AZURE_OPENAI_API_BASE=${AZURE_OPENAI_API_BASE:-}
      - AZURE_OPENAI_API_VERSION=${AZURE_OPENAI_API_VERSION:-}
      - AZURE_OPENAI_DEPLOYMENT_NAME=${AZURE_OPENAI_DEPLOYMENT_NAME:-}
      - REDIS_POOL_SIZE=20
      - REDIS_POOL_TIMEOUT=30
      - SQLALCHEMY_POOL_SIZE=10
      - SQLALCHEMY_MAX_OVERFLOW=20
      - MODEL_CACHE_DIR=/app/.cache
      - TRANSFORMERS_CACHE=/app/.cache/huggingface
      - SENTENCE_TRANSFORMERS_HOME=/app/.cache/sentence_transformers
      - TORCH_HOME=/app/.cache/torch
      - PYTHONPATH=/app
    deploy:
      resources:
        limits:
          cpus: '1.0'
          memory: 2G
        reservations:
          cpus: '0.5'
          memory: 1G
    volumes:
      - ./app:/app/app
      - ./config:/app/config
      - ./logs:/app/logs
      - ./uploads:/app/uploads
      - ./temp:/app/temp
      - ml-model-cache:/app/.cache
    depends_on:
      postgres:
        condition: service_healthy
      redis:
        condition: service_healthy
    networks:
      - app-network
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 30s

  frontend:
    build:
      context: .
      dockerfile: Dockerfile.frontend
    ports:
      - "8501:8501"
    environment:
      - BACKEND_URL=http://backend:8000
    deploy:
      resources:
        limits:
          cpus: '0.5'
          memory: 1G
        reservations:
          cpus: '0.25'
          memory: 512M
    volumes:
      - ./app:/app/app
      - ./config:/app/config
    depends_on:
      - backend
    networks:
      - app-network
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8501/healthz"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 10s

  postgres:
    build:
      context: ./postgres
      dockerfile: Dockerfile
    environment:
      - POSTGRES_USER=postgres
      - POSTGRES_PASSWORD=postgres
      - POSTGRES_DB=file_upload_embeddings
    volumes:
      - postgres-data:/var/lib/postgresql/data
      - ./scripts:/docker-entrypoint-initdb.d
    ports:
      - "5432:5432"
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U postgres"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 30s
    deploy:
      resources:
        limits:
          cpus: '2.0'
          memory: 4G
        reservations:
          cpus: '1.0'
          memory: 2G
    networks:
      - app-network

  redis:
    image: redis:7-alpine
    command: redis-server --maxmemory 768mb --maxmemory-policy allkeys-lru --save 900 1 --save 300 10
    volumes:
      - redis-data:/data
    deploy:
      resources:
        limits:
          cpus: '0.5'
          memory: 768M
        reservations:
          cpus: '0.25'
          memory: 384M
    networks:
      - app-network
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 5s

  prometheus:
    image: prom/prometheus:latest
    volumes:
      - ./monitoring/prometheus:/etc/prometheus
      - prometheus-data:/prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--web.console.libraries=/usr/share/prometheus/console_libraries'
      - '--web.console.templates=/usr/share/prometheus/consoles'
    ports:
      - "9090:9090"
    deploy:
      resources:
        limits:
          cpus: '0.5'
          memory: 512M
        reservations:
          cpus: '0.25'
          memory: 256M
    networks:
      - app-network
    healthcheck:
      test: ["CMD", "wget", "-q", "--tries=1", "--spider", "http://localhost:9090/-/healthy"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 30s

  grafana:
    image: grafana/grafana:latest
    ports:
      - "3001:3000"
    deploy:
      resources:
        limits:
          cpus: '0.5'
          memory: 512M
        reservations:
          cpus: '0.25'
          memory: 256M
    volumes:
      - ./monitoring/grafana/provisioning:/etc/grafana/provisioning
      - grafana-data:/var/lib/grafana
    networks:
      - app-network
    healthcheck:
      test: ["CMD", "wget", "-q", "--tries=1", "--spider", "http://localhost:3000/api/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 30s

networks:
  app-network:
    driver: bridge

volumes:
  postgres-data:
  redis-data:
  prometheus-data:
  grafana-data:
  ml-model-cache:
    driver: local