IPSExtractor/docker-compose.yml

services:
  database:
    image: postgres:16-alpine
    container_name: ipsextractor-db
    environment:
      POSTGRES_DB: ipsextractor
      POSTGRES_USER: ipsextractor
      POSTGRES_PASSWORD: ipsextractor
    volumes:
      - ipsextractor_db:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U ipsextractor -d ipsextractor"]
      interval: 5s
      timeout: 5s
      retries: 15
      start_period: 90s

  redis:
    image: redis:7-alpine
    container_name: ipsextractor-redis
    command: redis-server --maxmemory 512mb --maxmemory-policy allkeys-lru --save ""
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 5s
      timeout: 3s
      retries: 10

  db-migrations:
    build:
      context: ./services/db
      dockerfile: Dockerfile
    container_name: ipsextractor-db-migrations
    depends_on:
      database:
        condition: service_healthy
    environment:
      DATABASE_URL: postgresql+psycopg://ipsextractor:ipsextractor@database:5432/ipsextractor
    restart: on-failure

  extraction:
    build:
      context: ./services/extraction
      dockerfile: Dockerfile
    container_name: ipsextractor-extraction
    depends_on:
      database:
        condition: service_healthy
      redis:
        condition: service_healthy
      db-migrations:
        condition: service_completed_successfully
    environment:
      DATABASE_URL: postgresql+psycopg://ipsextractor:ipsextractor@database:5432/ipsextractor
      REDIS_URL: redis://redis:6379/0
      EXTRACTOR_BASE_URL: https://api.openai.com/v1
      EXTRACTOR_API_KEY: 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
      EXTRACTOR_MODEL: ${EXTRACTOR_MODEL:-gpt-5.4-mini}
      NORMALIZER_BASE_URL: https://api.openai.com/v1
      NORMALIZER_API_KEY: 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
      NORMALIZER_MODEL: gpt-5.4-mini
      EXTRACTOR_TIMEOUT_S: ${EXTRACTOR_TIMEOUT_S:-120}
      PDF_DPI: ${PDF_DPI:-150}
      PDF_THREAD_COUNT: ${PDF_THREAD_COUNT:-4}
      CONCURRENCY_LIMIT: ${CONCURRENCY_LIMIT:-50}
      ALLOWED_DOCUMENT_TYPES: ${ALLOWED_DOCUMENT_TYPES:-CC,TI,CE,RC,PA,PPT,PEP,EPT,NUIP}
    volumes:
      - ${IPS_DOCUMENT_ROOT:-./data}:/data
      - ips_queue:/tmp/ips_queue
    healthcheck:
      test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8001/health', timeout=5)"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 30s

  # Escala horizontalmente: docker compose up --scale worker=4
  worker:
    build:
      context: ./services/extraction
      dockerfile: Dockerfile
    command: python -m worker.main
    depends_on:
      database:
        condition: service_healthy
      redis:
        condition: service_healthy
      db-migrations:
        condition: service_completed_successfully
    deploy:
      replicas: ${WORKER_REPLICAS:-2}
    environment:
      DATABASE_URL: postgresql+psycopg://ipsextractor:ipsextractor@database:5432/ipsextractor
      REDIS_URL: redis://redis:6379/0
      EXTRACTOR_BASE_URL: https://api.openai.com/v1
      EXTRACTOR_API_KEY: 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
      EXTRACTOR_MODEL: ${EXTRACTOR_MODEL:-gpt-5.4-mini}
      NORMALIZER_BASE_URL: https://api.openai.com/v1
      NORMALIZER_API_KEY: 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
      NORMALIZER_MODEL: gpt-5.4-mini
      EXTRACTOR_TIMEOUT_S: ${EXTRACTOR_TIMEOUT_S:-120}
      PDF_DPI: ${PDF_DPI:-150}
      PDF_THREAD_COUNT: ${PDF_THREAD_COUNT:-4}
      WORKER_CONCURRENCY: ${WORKER_CONCURRENCY:-25}
      ALLOWED_DOCUMENT_TYPES: ${ALLOWED_DOCUMENT_TYPES:-CC,TI,CE,RC,PA,PPT,PEP,EPT,NUIP}
    volumes:
      - ips_queue:/tmp/ips_queue

  cleaning:
    build:
      context: ./services/cleaning
      dockerfile: Dockerfile
    container_name: ipsextractor-cleaning
    depends_on:
      database:
        condition: service_healthy
      db-migrations:
        condition: service_completed_successfully
    environment:
      DATABASE_URL: postgresql+psycopg://ipsextractor:ipsextractor@database:5432/ipsextractor

  count-api:
    build:
      context: ./services/services-count-facturas-medicas-serving
      dockerfile: Dockerfile
    container_name: ipsextractor-count-api
    restart: unless-stopped
    depends_on:
      db-migrations:
        condition: service_completed_successfully
    environment:
      PORT: "8080"
      # OCR_DPI: 150 reduce RAM (~4×) frente a 300; suficiente para contar facturas.
      OCR_DPI: ${OCR_DPI:-150}
      OCR_LANG: ${OCR_LANG:-spa}
      # Con varios lotes paralelos desde el desktop, limitar goroutines evita OOM.
      OCR_POOL_SIZE: ${OCR_POOL_SIZE:-4}
      SYNC_MAX_FILES: ${SYNC_MAX_FILES:-50}
      SYNC_PROCESS_CONCURRENCY: ${SYNC_PROCESS_CONCURRENCY:-4}
      MAX_PDF_SIZE_MB: ${MAX_PDF_SIZE_MB:-20}
      LOG_PIPELINE_TIMING: ${LOG_PIPELINE_TIMING:-false}
    volumes:
      - ./services/services-count-facturas-medicas-serving/models/latest:/app/models:ro
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8080/health"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 90s
    deploy:
      resources:
        limits:
          memory: ${COUNT_API_MEMORY:-4g}

  bot-descarga:
    build:
      context: ./services/bot_descarga
      dockerfile: Dockerfile
    container_name: ipsextractor-bot-descarga
    restart: unless-stopped
    depends_on:
      database:
        condition: service_healthy
    environment:
      BOT_API_TOKEN: ${BOT_API_TOKEN:-dev-token-change-me}
      BOT_API_HOST: 0.0.0.0
      BOT_API_PORT: "8200"
      DATABASE_URL: postgresql+psycopg://ipsextractor:ipsextractor@database:5432/ipsextractor
      MINIO_ENDPOINT: ${MINIO_ENDPOINT:-https://s3.builker.xyz}
      MINIO_BUCKET: ${MINIO_BUCKET:-pys-cuentas-medicas}
      MINIO_ANONYMOUS: ${MINIO_ANONYMOUS:-1}
      MINIO_ACCESS_KEY: ${MINIO_ACCESS_KEY:-}
      MINIO_SECRET_KEY: ${MINIO_SECRET_KEY:-}
      MINIO_REGION: ${MINIO_REGION:-us-east-1}
    healthcheck:
      test: ["CMD", "curl", "-f", "http://127.0.0.1:8200/health"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 20s

  api_gateway:
    build:
      context: ./services/api_gateway
      dockerfile: Dockerfile
    container_name: ipsextractor-api
    depends_on:
      extraction:
        condition: service_healthy
      cleaning:
        condition: service_started
      count-api:
        condition: service_healthy
      bot-descarga:
        condition: service_healthy
    environment:
      EXTRACTION_URL: http://extraction:8001
      CLEANING_URL: http://cleaning:8002
      COUNT_URL: http://count-api:8080
      BOT_DESCARGA_URL: http://bot-descarga:8200
    ports:
      # Único puerto expuesto al host. Los demás servicios solo son accesibles en la red Docker.
      - "0.0.0.0:8189:8000"
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health/live"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 15s

volumes:
  ipsextractor_db:
  ips_queue: