docker-compose.yml

# =============================================================================
# HireLens — Docker Compose  (lives at project root alongside .env)
# Services: FastAPI backend, React frontend, PostgreSQL, MLflow
# =============================================================================

x-logging: &default-logging
  driver: json-file
  options:
    max-size: "50m"
    max-file: "5"

networks:
  hirelens-net:
    driver: bridge

volumes:
  postgres_data:
  mlflow_data:
  upload_data:
  model_cache:
  redis_data:

services:

  # ── Redis (embedding cache) ─────────────────────────────────────────────────
  redis:
    image: redis:7.2-alpine
    container_name: hirelens-redis
    restart: unless-stopped
    command: redis-server --maxmemory 256mb --maxmemory-policy allkeys-lru --save ""
    volumes:
      - redis_data:/data
    ports:
      - "${REDIS_PORT:-6379}:6379"
    networks:
      - hirelens-net
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 10s
      timeout: 3s
      retries: 5
      start_period: 5s
    logging: *default-logging

  # ── PostgreSQL ──────────────────────────────────────────────────────────────
  postgres:
    image: postgres:16.3-alpine
    container_name: hirelens-postgres
    restart: unless-stopped
    environment:
      POSTGRES_DB: ${POSTGRES_DB:-hirelens}
      POSTGRES_USER: ${POSTGRES_USER:-hirelens_user}
      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:?POSTGRES_PASSWORD is required}
      PGDATA: /var/lib/postgresql/data/pgdata
    volumes:
      - postgres_data:/var/lib/postgresql/data
      - ./docker/postgres/init.sql:/docker-entrypoint-initdb.d/init.sql:ro
    ports:
      - "${POSTGRES_PORT:-5432}:5432"
    networks:
      - hirelens-net
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-hirelens_user} -d ${POSTGRES_DB:-hirelens}"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 10s
    logging: *default-logging

  # ── MLflow Tracking Server ──────────────────────────────────────────────────
  mlflow:
    build:
      context: .
      dockerfile: docker/Dockerfile.mlflow
    container_name: hirelens-mlflow
    restart: unless-stopped
    command:
      - "--host=0.0.0.0"
      - "--port=5000"
      - "--backend-store-uri=postgresql://${POSTGRES_USER:-hirelens_user}:${POSTGRES_PASSWORD}@postgres:5432/${POSTGRES_DB:-hirelens}_mlflow"
      - "--default-artifact-root=${MLFLOW_ARTIFACT_ROOT:-/mlflow/artifacts}"
      - "--serve-artifacts"
    environment:
      AWS_ACCESS_KEY_ID: ${AWS_ACCESS_KEY_ID:-}
      AWS_SECRET_ACCESS_KEY: ${AWS_SECRET_ACCESS_KEY:-}
      AWS_DEFAULT_REGION: ${AWS_DEFAULT_REGION:-us-east-1}
      MLFLOW_S3_ENDPOINT_URL: ${MLFLOW_S3_ENDPOINT_URL:-}
    volumes:
      - mlflow_data:/mlflow/artifacts
    ports:
      - "${MLFLOW_PORT:-5000}:5000"
    networks:
      - hirelens-net
    depends_on:
      postgres:
        condition: service_healthy
    healthcheck:
      test: ["CMD", "curl", "-sf", "http://0.0.0.0:5000/health"]
      interval: 15s
      timeout: 5s
      retries: 5
      start_period: 20s
    logging: *default-logging

  # ── FastAPI Backend ─────────────────────────────────────────────────────────
  backend:
    build:
      context: .
      dockerfile: docker/Dockerfile.backend
      args:
        PYTHON_VERSION: "3.12.3"
    container_name: hirelens-backend
    restart: unless-stopped
    env_file:
      - .env
    environment:
      DATABASE_URL: postgresql+asyncpg://${POSTGRES_USER:-hirelens_user}:${POSTGRES_PASSWORD}@postgres:5432/${POSTGRES_DB:-hirelens}
      MLFLOW_TRACKING_URI: http://mlflow:5000
      MODEL_CACHE_DIR: /app/models/cache
      REDIS_URL: redis://redis:6379/0
    volumes:
      - upload_data:/app/uploads
      - model_cache:/app/models/cache
      - ./logs:/app/logs
    ports:
      - "${API_PORT:-8000}:8000"
    networks:
      - hirelens-net
    depends_on:
      postgres:
        condition: service_healthy
      mlflow:
        condition: service_healthy
      redis:
        condition: service_healthy
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 20s
      timeout: 10s
      retries: 5
      start_period: 40s
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    logging: *default-logging

  # ── React Frontend ──────────────────────────────────────────────────────────
  frontend:
    build:
      context: .
      dockerfile: docker/Dockerfile.frontend
      args:
        VITE_API_URL: http://localhost:8000
    container_name: hirelens-frontend
    restart: unless-stopped
    environment:
      VITE_API_BASE_URL: ${VITE_API_BASE_URL:-http://localhost:8000}
      VITE_APP_ENV: ${APP_ENV:-development}
    ports:
      - "${FRONTEND_PORT:-3000}:3000"
    networks:
      - hirelens-net
    depends_on:
      backend:
        condition: service_healthy
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:3000"]
      interval: 20s
      timeout: 10s
      retries: 3
      start_period: 20s
    logging: *default-logging