LegacyHUB/docker-compose.yml

name: legacyhub

x-common-env: &common-env
  POSTGRES_HOST: ${POSTGRES_HOST:-postgres}
  POSTGRES_PORT: ${POSTGRES_PORT:-5432}
  POSTGRES_DB: ${POSTGRES_DB:-legacyhub}
  POSTGRES_USER: ${POSTGRES_USER:-legacyhub}
  POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-legacyhub}
  MINIO_ENDPOINT: ${MINIO_ENDPOINT:-minio:9000}
  MINIO_ACCESS_KEY: ${MINIO_ACCESS_KEY:-legacyhub}
  MINIO_SECRET_KEY: ${MINIO_SECRET_KEY:-legacyhub-secret}
  MINIO_BUCKET_ORIGINALS: ${MINIO_BUCKET_ORIGINALS:-teamhub-legacyhub-originals}
  MINIO_BUCKET_DERIVED: ${MINIO_BUCKET_DERIVED:-teamhub-legacyhub-derived}
  MINIO_SECURE: ${MINIO_SECURE:-false}
  OPENSEARCH_HOST: ${OPENSEARCH_HOST:-opensearch}
  OPENSEARCH_PORT: ${OPENSEARCH_PORT:-9200}
  OPENSEARCH_USE_SSL: ${OPENSEARCH_USE_SSL:-false}
  OPENSEARCH_VERIFY_CERTS: ${OPENSEARCH_VERIFY_CERTS:-false}
  OPENSEARCH_INDEX_CHUNKS: ${OPENSEARCH_INDEX_CHUNKS:-legacy_chunks}
  QDRANT_HOST: ${QDRANT_HOST:-qdrant}
  QDRANT_PORT: ${QDRANT_PORT:-6333}
  QDRANT_COLLECTION_CHUNKS: ${QDRANT_COLLECTION_CHUNKS:-legacy_chunks}
  REDIS_URL: ${REDIS_URL:-redis://redis:6379/0}
  OCR_LANGUAGES: ${OCR_LANGUAGES:-rus+eng}
  OCR_ENABLED: ${OCR_ENABLED:-true}
  DOCLING_OCR_ENABLED: ${DOCLING_OCR_ENABLED:-false}
  MAX_DOCUMENT_TIMEOUT_SECONDS: ${MAX_DOCUMENT_TIMEOUT_SECONDS:-180}
  EMBEDDING_MODEL: ${EMBEDDING_MODEL:-BAAI/bge-m3}
  EMBEDDING_DEVICE: ${EMBEDDING_DEVICE:-cpu}
  RERANKER_MODEL: ${RERANKER_MODEL:-BAAI/bge-reranker-v2-m3}
  RERANKER_DEVICE: ${RERANKER_DEVICE:-cpu}
  RERANKER_ENABLED: ${RERANKER_ENABLED:-true}
  APP_ENV: ${APP_ENV:-dev}
  APP_LOG_LEVEL: ${APP_LOG_LEVEL:-INFO}
  APP_INPUT_DIR: /data/input
  APP_WORK_DIR: /data/work
  CORS_ALLOWED_ORIGINS: ${CORS_ALLOWED_ORIGINS:-http://localhost:5273,http://localhost:4173}
  API_KEY: ${API_KEY:-}
  INGEST_API_KEY: ${INGEST_API_KEY:-}
  # Dispatch participant (D4 bus): values come from the gitignored .env.
  DISPATCH_ENABLED: ${DISPATCH_ENABLED:-false}
  DISPATCH_API_URL: ${DISPATCH_API_URL:-}
  DISPATCH_API_KEY: ${DISPATCH_API_KEY:-}
  DISPATCH_PARTICIPANT_CODE: ${DISPATCH_PARTICIPANT_CODE:-legacyhub}
  DISPATCH_TIMEOUT_SECONDS: ${DISPATCH_TIMEOUT_SECONDS:-5}

# Module-contract isolation: data services live on the internal-only
# legacyhub_db network (the same name docker-compose.teamhub.yml uses, so the
# federation overlay composes without a parallel network). In dev they also
# join edge so host-published ports keep working; the prod overlay pins them
# to legacyhub_db only. api/worker need edge for the published API port and
# HuggingFace model downloads.
networks:
  legacyhub_db:
    internal: true
  edge: {}

services:
  postgres:
    image: postgres:16-alpine
    restart: unless-stopped
    networks: [legacyhub_db, edge]
    environment:
      POSTGRES_DB: ${POSTGRES_DB:-legacyhub}
      POSTGRES_USER: ${POSTGRES_USER:-legacyhub}
      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-legacyhub}
    ports:
      - "5440:5432"
    volumes:
      - postgres_data:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-legacyhub} -d ${POSTGRES_DB:-legacyhub}"]
      interval: 10s
      timeout: 5s
      retries: 10

  minio:
    image: minio/minio:RELEASE.2024-08-29T01-40-52Z
    restart: unless-stopped
    networks: [legacyhub_db, edge]
    command: server /data --console-address ":9001"
    environment:
      MINIO_ROOT_USER: ${MINIO_ACCESS_KEY:-legacyhub}
      MINIO_ROOT_PASSWORD: ${MINIO_SECRET_KEY:-legacyhub-secret}
    ports:
      - "9000:9000"
      - "9001:9001"
    volumes:
      - minio_data:/data
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:9000/minio/health/live"]
      interval: 10s
      timeout: 5s
      retries: 10

  opensearch:
    image: opensearchproject/opensearch:2.15.0
    restart: unless-stopped
    networks: [legacyhub_db, edge]
    environment:
      - discovery.type=single-node
      - bootstrap.memory_lock=true
      - "OPENSEARCH_JAVA_OPTS=-Xms1g -Xmx1g"
      - DISABLE_SECURITY_PLUGIN=true
      - DISABLE_INSTALL_DEMO_CONFIG=true
    ulimits:
      memlock:
        soft: -1
        hard: -1
      nofile:
        soft: 65536
        hard: 65536
    ports:
      - "9200:9200"
      - "9600:9600"
    volumes:
      - opensearch_data:/usr/share/opensearch/data
    healthcheck:
      test: ["CMD-SHELL", "curl -fsS http://localhost:9200/_cluster/health | grep -q '\"status\":\"\\(green\\|yellow\\)\"'"]
      interval: 15s
      timeout: 10s
      retries: 20

  qdrant:
    image: qdrant/qdrant:v1.11.3
    restart: unless-stopped
    networks: [legacyhub_db, edge]
    ports:
      - "6333:6333"
      - "6334:6334"
    volumes:
      - qdrant_data:/qdrant/storage
    healthcheck:
      test: ["CMD-SHELL", "bash -c '</dev/tcp/127.0.0.1/6333'"]
      interval: 15s
      timeout: 5s
      retries: 10

  redis:
    image: redis:7-alpine
    restart: unless-stopped
    networks: [legacyhub_db, edge]
    ports:
      - "6379:6379"
    volumes:
      - redis_data:/data
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 10s
      timeout: 5s
      retries: 10

  api:
    build:
      context: .
      dockerfile: docker/Dockerfile
    image: legacyhub/api:latest
    restart: unless-stopped
    networks: [legacyhub_db, edge]
    environment:
      <<: *common-env
      APP_HOST: 0.0.0.0
      APP_PORT: 8000
    command: ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]
    healthcheck:
      # /api/v1/health is liveness: it answers HTTP 200 even when a dependency
      # is degraded, so the container is not restart-looped on data-store issues.
      test: ["CMD", "curl", "-fsS", "http://localhost:8000/api/v1/health"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 60s
    ports:
      # Host port 8050 avoids the 8000 collision (SalesHUB / old dispatch dev).
      # Container still listens on 8000. Overridden by ${API_HOST_PORT}.
      - "${API_HOST_PORT:-8050}:8000"
    depends_on:
      postgres:
        condition: service_healthy
      minio:
        condition: service_healthy
      opensearch:
        condition: service_healthy
      qdrant:
        condition: service_healthy
      redis:
        condition: service_healthy
    volumes:
      - ./data/input:/data/input
      - ./data/work:/data/work
      - hf_cache:/root/.cache/huggingface

  worker:
    build:
      context: .
      dockerfile: docker/Dockerfile
    image: legacyhub/api:latest
    restart: unless-stopped
    networks: [legacyhub_db, edge]
    environment:
      <<: *common-env
    command: ["celery", "-A", "app.workers.celery_app", "worker", "--loglevel=INFO", "--concurrency=2"]
    depends_on:
      postgres:
        condition: service_healthy
      minio:
        condition: service_healthy
      opensearch:
        condition: service_healthy
      qdrant:
        condition: service_healthy
      redis:
        condition: service_healthy
    volumes:
      - ./data/input:/data/input
      - ./data/work:/data/work
      - hf_cache:/root/.cache/huggingface

volumes:
  postgres_data:
  minio_data:
  opensearch_data:
  qdrant_data:
  redis_data:
  hf_cache: