HHostingByteSoftware
Ctrl K
ComunidadGuías…

docker-compose.yml

Rama main · réplica de lectura del repositorio original.

Archivo original ↗Preguntar a KiBot
services:
  postgres:
    image: postgres:15-alpine
    environment:
      POSTGRES_USER: postgres
      POSTGRES_PASSWORD: password
      POSTGRES_DB: corpus
    command:
      - "postgres"
      - "-c"
      - "log_statement=all"
      - "-c"
      - "log_duration=on"
      - "-c"
      - "log_min_duration_statement=0"
      - "-c"
      - "log_line_prefix=%t [%p]: [%l-1] user=%u,db=%d,app=%a,client=%h "
      - "-c"
      - "log_connections=on"
      - "-c"
      - "log_disconnections=on"
    ports:
      - "5437:5432"
    volumes:
      - postgres_data:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U postgres"]
      interval: 10s
      timeout: 5s
      retries: 5

  postgres_temporal:
    image: postgres:15-alpine
    environment:
      POSTGRES_USER: postgres
      POSTGRES_PASSWORD: password
      POSTGRES_DB: temporal
    ports:
      - "5438:5432"
    volumes:
      - postgres_temporal_data:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U postgres"]
      interval: 10s
      timeout: 5s
      retries: 5

  rabbitmq:
    image: rabbitmq:3.12-management-alpine
    ports:
      - "5672:5672"
      - "15672:15672"
    environment:
      RABBITMQ_DEFAULT_USER: guest
      RABBITMQ_DEFAULT_PASS: guest
    volumes:
      - rabbitmq_data:/var/lib/rabbitmq
    healthcheck:
      test: ["CMD", "rabbitmq-diagnostics", "ping"]
      interval: 10s
      timeout: 5s
      retries: 5

  corpus-redis:
    image: redis/redis-stack:latest
    ports:
      - "6380:6379"
      - "8001:8001" # RedisInsight web UI
    volumes:
      - corpus_redis_data:/data
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 10s
      timeout: 5s
      retries: 5

  elasticsearch:
    image: docker.elastic.co/elasticsearch/elasticsearch:9.1.0
    environment:
      - discovery.type=single-node
      - xpack.security.enabled=false
      - xpack.security.http.ssl.enabled=false
      - xpack.security.transport.ssl.enabled=false
      - "ES_JAVA_OPTS=-Xms512m -Xmx512m"
    ports:
      - "9200:9200"
      - "9300:9300"
    volumes:
      - elasticsearch_data:/usr/share/elasticsearch/data
    healthcheck:
      test:
        ["CMD-SHELL", "curl -f http://localhost:9200/_cluster/health || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 5

  localstack:
    image: localstack/localstack:latest
    ports:
      - "4566:4566"
      - "4571:4571"
    environment:
      - SERVICES=s3
      - DEBUG=1
      - PERSISTENCE=1
      - DOCKER_HOST=unix:///var/run/docker.sock
      - AWS_ACCESS_KEY_ID=test
      - AWS_SECRET_ACCESS_KEY=test
      - AWS_DEFAULT_REGION=us-east-1
    volumes:
      - localstack_data:/var/lib/localstack
      - /var/run/docker.sock:/var/run/docker.sock

  temporal:
    image: temporalio/auto-setup:1.22.0
    ports:
      - "7233:7233"
      - "8233:8233"
    environment:
      - DB=postgresql
      - DB_PORT=5432
      - POSTGRES_USER=postgres
      - POSTGRES_PWD=password
      - POSTGRES_SEEDS=postgres_temporal
    depends_on:
      postgres_temporal:
        condition: service_healthy
    volumes:
      - temporal_data:/etc/temporal

  temporal-ui:
    image: temporalio/ui:2.21.3
    ports:
      - "8080:8080"
    environment:
      - TEMPORAL_ADDRESS=temporal:7233
      - TEMPORAL_CORS_ORIGINS=http://localhost:3000
    depends_on:
      - temporal

  corpus-migrate:
    build:
      context: .
      dockerfile: backend/alembic/Dockerfile
      target: production
    env_file:
      - ./backend/.env
    environment:
      # Docker-specific overrides
      - DB_HOST=postgres
    depends_on:
      postgres:
        condition: service_healthy
    command: alembic upgrade head

  backend:
    build:
      context: .
      dockerfile: backend/api/Dockerfile
      target: development
    ports:
      - "8000:8000"
    env_file:
      - ./backend/.env
    environment:
      # Docker-specific overrides
      - ENVIRONMENT=local
      - STORAGE_PROVIDER=s3
      - DB_HOST=postgres
      - RABBITMQ_HOST=rabbitmq
      - REDIS_HOST=corpus-redis
      - S3_ENDPOINT_URL=http://localstack:4566
      - AWS_ACCESS_KEY_ID=test
      - AWS_SECRET_ACCESS_KEY=test
      - ELASTICSEARCH_HOST=elasticsearch
      - GOOGLE_APPLICATION_CREDENTIALS=/app/gen-lang-client-creds.json
      - DEBUG=0
    depends_on:
      postgres:
        condition: service_healthy
      rabbitmq:
        condition: service_healthy
      corpus-redis:
        condition: service_healthy
      elasticsearch:
        condition: service_healthy
      localstack:
        condition: service_started
      temporal:
        condition: service_started
      corpus-migrate:
        condition: service_completed_successfully
    volumes:
      - ./backend/api:/app/api
      - ./backend/common:/app/common
      - ./backend/packages:/app/packages
      - ./libs:/app/libs
      - ./prompts:/app/prompts
      - ./gen-lang-client-creds.json:/app/gen-lang-client-creds.json
    command: uvicorn api.main:app --host 0.0.0.0 --port 8000 --reload
    #healthcheck:
    #  test: ["CMD", "curl", "-f", "http://backend:8000/api/v1/health"]
    #  interval: 10s
    #  timeout: 5s
    #  retries: 5

  vite:
    build:
      context: ./vite
      dockerfile: Dockerfile
      target: development
    ports:
      - "3001:3000"
    volumes:
      - ./vite/.env.development:/app/.env.development
      - ./vite/src:/app/src
      - ./vite/public:/app/public
      - ./vite/index.html:/app/index.html
      - ./vite/vite.config.ts:/app/vite.config.ts
      - ./vite/tsconfig.json:/app/tsconfig.json
      - ./vite/tsconfig.app.json:/app/tsconfig.app.json
      - ./vite/tsconfig.node.json:/app/tsconfig.node.json
    depends_on:
      backend:
        condition: service_started

  qa_worker:
    build:
      context: .
      dockerfile: backend/workers/Dockerfile
      target: development
    env_file:
      - ./backend/.env
    environment:
      # Docker-specific overrides
      - ENVIRONMENT=local
      - STORAGE_PROVIDER=s3
      - DB_HOST=postgres
      - RABBITMQ_HOST=rabbitmq
      - REDIS_HOST=corpus-redis
      - S3_ENDPOINT_URL=http://localstack:4566
      - AWS_ACCESS_KEY_ID=test
      - AWS_SECRET_ACCESS_KEY=test
      - ELASTICSEARCH_HOST=elasticsearch
      - GOOGLE_APPLICATION_CREDENTIALS=/app/gen-lang-client-creds.json
      - PYTHONUNBUFFERED=1
      - PYTHONDONTWRITEBYTECODE=1
      - DEBUG=0
    depends_on:
      postgres:
        condition: service_healthy
      rabbitmq:
        condition: service_healthy
      corpus-redis:
        condition: service_healthy
      elasticsearch:
        condition: service_healthy
      localstack:
        condition: service_started
      corpus-migrate:
        condition: service_completed_successfully
    volumes:
      - ./backend/api:/app/api
      - ./prompts:/app/prompts
      - ./backend/packages:/app/packages
      - ./backend/workers:/app/workers
      - ./gen-lang-client-creds.json:/app/gen-lang-client-creds.json
    command: python -m workers.run_qa_worker
    restart: unless-stopped
    # Deploy configuration for scaling
    deploy:
      replicas: 1 # Change this to scale workers

  document_indexing_worker:
    build:
      context: .
      dockerfile: backend/workers/Dockerfile
      target: development
    env_file:
      - ./backend/.env
    environment:
      # Docker-specific overrides
      - ENVIRONMENT=local
      - STORAGE_PROVIDER=s3
      - DB_HOST=postgres
      - RABBITMQ_HOST=rabbitmq
      - REDIS_HOST=corpus-redis
      - S3_ENDPOINT_URL=http://localstack:4566
      - AWS_ACCESS_KEY_ID=test
      - AWS_SECRET_ACCESS_KEY=test
      - ELASTICSEARCH_HOST=elasticsearch
      - GOOGLE_APPLICATION_CREDENTIALS=/app/gen-lang-client-creds.json
      - PYTHONUNBUFFERED=1
      - PYTHONDONTWRITEBYTECODE=1
      - DEBUG=0
    depends_on:
      postgres:
        condition: service_healthy
      rabbitmq:
        condition: service_healthy
      corpus-redis:
        condition: service_healthy
      elasticsearch:
        condition: service_healthy
      localstack:
        condition: service_started
      corpus-migrate:
        condition: service_completed_successfully
    volumes:
      - ./backend/api:/app/api
      - ./backend/common:/app/common
      - ./backend/packages:/app/packages
      - ./backend/workers:/app/workers
      - ./gen-lang-client-creds.json:/app/gen-lang-client-creds.json
    command: python -m workers.run_document_indexing_worker
    restart: unless-stopped
    # Deploy configuration for scaling
    deploy:
      replicas: 1 # Change this to scale workers

  # Temporal worker for document routing (main queue)
  temporal_worker_routing:
    build:
      context: .
      dockerfile: backend/workers/Dockerfile
      target: development
    env_file:
      - ./backend/.env
    environment:
      # Database Components
      - ENVIRONMENT=local
      - STORAGE_PROVIDER=s3
      - DB_HOST=postgres
      - RABBITMQ_HOST=rabbitmq
      - REDIS_HOST=corpus-redis
      - S3_ENDPOINT_URL=http://localstack:4566
      - AWS_ACCESS_KEY_ID=test
      - AWS_SECRET_ACCESS_KEY=test
      - ELASTICSEARCH_HOST=elasticsearch
      - GOOGLE_APPLICATION_CREDENTIALS=/app/gen-lang-client-creds.json
      - PYTHONUNBUFFERED=1
      - PYTHONDONTWRITEBYTECODE=1
      - DEBUG=0
    depends_on:
      postgres:
        condition: service_healthy
      temporal:
        condition: service_started
      elasticsearch:
        condition: service_healthy
      localstack:
        condition: service_started
      corpus-migrate:
        condition: service_completed_successfully
    volumes:
      - ./backend/api:/app/api
      - ./backend/packages:/app/packages
      - ./backend/workers:/app/workers
      - ./gen-lang-client-creds.json:/app/gen-lang-client-creds.json
    command: python -m workers.run_temporal_worker --queue document-routing-queue
    restart: unless-stopped
    # Deploy configuration for scaling
    deploy:
      replicas: 1 # Main routing workers

  # Temporal worker for PDF processing
  temporal_worker_pdf:
    build:
      context: .
      dockerfile: backend/workers/Dockerfile
      target: development
    env_file:
      - ./backend/.env
    environment:
      # Database Components
      - ENVIRONMENT=local
      - STORAGE_PROVIDER=s3
      - DB_HOST=postgres
      - RABBITMQ_HOST=rabbitmq
      - REDIS_HOST=corpus-redis
      - S3_ENDPOINT_URL=http://localstack:4566
      - AWS_ACCESS_KEY_ID=test
      - AWS_SECRET_ACCESS_KEY=test
      - ELASTICSEARCH_HOST=elasticsearch
      - GOOGLE_APPLICATION_CREDENTIALS=/app/gen-lang-client-creds.json
      # Python settings
      - PYTHONUNBUFFERED=1
      - PYTHONDONTWRITEBYTECODE=1
      - DEBUG=0
    depends_on:
      postgres:
        condition: service_healthy
      temporal:
        condition: service_started
      elasticsearch:
        condition: service_healthy
      localstack:
        condition: service_started
      corpus-migrate:
        condition: service_completed_successfully
    volumes:
      - ./backend/api:/app/api
      - ./backend/packages:/app/packages
      - ./backend/workers:/app/worker
      - ./gen-lang-client-creds.json:/app/gen-lang-client-creds.json
    command: python -m workers.run_temporal_worker --queue pdf-processing-queue
    restart: unless-stopped
    # Deploy configuration for scaling
    deploy:
      replicas: 1 # PDF processing workers

  # Temporal worker for page conversion (highest parallelism)
  temporal_worker_page:
    build:
      context: .
      dockerfile: backend/workers/Dockerfile
      target: development
    env_file:
      - ./backend/.env
    environment:
      - ENVIRONMENT=local
      - STORAGE_PROVIDER=s3
      - DB_HOST=postgres
      - RABBITMQ_HOST=rabbitmq
      - REDIS_HOST=corpus-redis
      - S3_ENDPOINT_URL=http://localstack:4566
      - AWS_ACCESS_KEY_ID=test
      - AWS_SECRET_ACCESS_KEY=test
      - ELASTICSEARCH_HOST=elasticsearch
      - GOOGLE_APPLICATION_CREDENTIALS=/app/gen-lang-client-creds.json
      - PYTHONUNBUFFERED=1
      - PYTHONDONTWRITEBYTECODE=1
      - DEBUG=0
    depends_on:
      postgres:
        condition: service_healthy
      temporal:
        condition: service_started
      elasticsearch:
        condition: service_healthy
      localstack:
        condition: service_started
      corpus-migrate:
        condition: service_completed_successfully
    volumes:
      - ./backend/api:/app/api
      - ./backend/packages:/app/packages
      - ./backend/workers:/app/workers
      - ./gen-lang-client-creds.json:/app/gen-lang-client-creds.json
    command: python -m workers.run_temporal_worker --queue page-conversion-queue
    restart: unless-stopped
    # Deploy configuration for scaling
    deploy:
      replicas: 1 # High parallelism for page processing

  # Temporal worker for generic document extraction
  temporal_worker_generic:
    build:
      context: .
      dockerfile: backend/workers/Dockerfile
      target: development
    env_file:
      - ./backend/.env
    environment:
      # Database Components
      - ENVIRONMENT=local
      - STORAGE_PROVIDER=s3
      - DB_HOST=postgres
      - RABBITMQ_HOST=rabbitmq
      - REDIS_HOST=corpus-redis
      - S3_ENDPOINT_URL=http://localstack:4566
      - AWS_ACCESS_KEY_ID=test
      - AWS_SECRET_ACCESS_KEY=test
      - ELASTICSEARCH_HOST=elasticsearch
      - GOOGLE_APPLICATION_CREDENTIALS=/app/gen-lang-client-creds.json
      - PYTHONUNBUFFERED=1
      - PYTHONDONTWRITEBYTECODE=1
      - DEBUG=0
    depends_on:
      postgres:
        condition: service_healthy
      temporal:
        condition: service_started
      elasticsearch:
        condition: service_healthy
      localstack:
        condition: service_started
      corpus-migrate:
        condition: service_completed_successfully
    volumes:
      - ./backend/api:/app/api
      - ./backend/packages:/app/packages
      - ./backend/workers:/app/workers
      - ./gen-lang-client-creds.json:/app/gen-lang-client-creds.json
    command: python -m workers.run_temporal_worker --queue generic-extraction-queue
    restart: unless-stopped
    # Deploy configuration for scaling
    deploy:
      replicas: 1 # Generic document processing workers

  # Temporal worker for document chunking (manages chunking agent jobs)
  temporal_worker_chunking:
    build:
      context: .
      dockerfile: backend/workers/Dockerfile
      target: development
    env_file:
      - ./backend/.env
    environment:
      - ENVIRONMENT=local
      - STORAGE_PROVIDER=s3
      - DB_HOST=postgres
      - S3_ENDPOINT_URL=http://localstack:4566
      - AWS_ACCESS_KEY_ID=test
      - AWS_SECRET_ACCESS_KEY=test
      - API_ENDPOINT=http://backend:8000
      - PYTHONUNBUFFERED=1
      - PYTHONDONTWRITEBYTECODE=1
      - DEBUG=0
    depends_on:
      postgres:
        condition: service_healthy
      temporal:
        condition: service_started
      corpus-migrate:
        condition: service_completed_successfully
    volumes:
      - ./backend/packages:/app/packages
      - ./backend/workers:/app/workers
      - ./backend/common:/app/common
      - /var/run/docker.sock:/var/run/docker.sock:rw
    command: python -m workers.run_temporal_worker --queue document-chunking-queue
    restart: unless-stopped
    # Deploy configuration for scaling
    deploy:
      replicas: 1 # Chunking workers

  # Temporal worker for workflow execution (manages workflow agents)
  temporal_worker_workflows:
    build:
      context: .
      dockerfile: backend/workers/Dockerfile
      target: development
    env_file:
      - ./backend/.env
    environment:
      - ENVIRONMENT=local
      - STORAGE_PROVIDER=s3
      - DB_HOST=postgres
      - S3_ENDPOINT_URL=http://localstack:4566
      - AWS_ACCESS_KEY_ID=test
      - AWS_SECRET_ACCESS_KEY=test
      - API_ENDPOINT=http://backend:8000
      - PYTHONUNBUFFERED=1
      - PYTHONDONTWRITEBYTECODE=1
      - DEBUG=0
    depends_on:
      postgres:
        condition: service_healthy
      temporal:
        condition: service_started
      corpus-migrate:
        condition: service_completed_successfully
    volumes:
      - ./backend/packages:/app/packages
      - ./backend/workers:/app/workers
      - ./backend/common:/app/common
      - /var/run/docker.sock:/var/run/docker.sock:rw
    command: python -m workers.run_workflow_worker
    restart: unless-stopped

  # Temporal worker for agent QA (manages agent QA jobs)
  temporal_worker_agent_qa:
    build:
      context: .
      dockerfile: backend/workers/Dockerfile
      target: development
    env_file:
      - ./backend/.env
    environment:
      - DB_HOST=postgres
      - S3_ENDPOINT_URL=http://localstack:4566
      - AWS_ACCESS_KEY_ID=test
      - AWS_SECRET_ACCESS_KEY=test
      - WORKFLOW_EXECUTION_MODE=docker
      - API_ENDPOINT=http://backend:8000
      - PYTHONUNBUFFERED=1
      - PYTHONDONTWRITEBYTECODE=1
      - DEBUG=0
    depends_on:
      postgres:
        condition: service_healthy
      temporal:
        condition: service_started
      corpus-migrate:
        condition: service_completed_successfully
    volumes:
      - ./backend/packages:/app/packages
      - ./backend/workers:/app/workers
      - ./backend/common:/app/common
      - /var/run/docker.sock:/var/run/docker.sock:rw
    command: python -m workers.run_agent_qa_worker
    restart: unless-stopped

  agent-qa:
    build:
      context: .
      dockerfile: agents/qa/Dockerfile
    image: corpus/agent-qa:latest
    profiles:
      - build-only

  document-chunker:
    build:
      context: .
      dockerfile: agents/chunking/Dockerfile
    image: corpus/document-chunker:latest
    profiles:
      - build-only

  workflow-agent:
    build:
      context: .
      dockerfile: agents/workflow/Dockerfile
    image: corpus/workflow-agent:latest
    profiles:
      - build-only

volumes:
  postgres_data:
  postgres_temporal_data:
  rabbitmq_data:
  corpus_redis_data:
  elasticsearch_data:
  localstack_data:
  temporal_data: