ai-tools-searxng-firecrawl-hhem-api/Portainer-Stack.yaml

services:

  # ===========================================================================
  # 1. SearXNG — meta-search with JSON API
  # ===========================================================================
  searxng:
    image: docker.io/searxng/searxng:latest
    container_name: searxng-8889
    restart: unless-stopped
    ports:
      - "8889:8080"
    volumes:
      - /home/sparky/Docker/searXNG Firecrawl HHEM  /searxng:/etc/searxng:rw
      - searxng-cache:/var/cache/searxng:rw
    environment:
      - SEARXNG_BASE_URL=http://localhost:8889/
    cap_drop:
      - ALL
    cap_add:
      - CHOWN
      - SETGID
      - SETUID
    healthcheck:
      test: ["CMD-SHELL", "wget -qO- http://localhost:8080/healthz || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 20s
    networks:
      - dgx_net

  # ===========================================================================
  # 2. Firecrawl — web scraper (self-hosted, no API key required)
  #    Images must be pre-built: run build-images.sh before deploying this stack
  # ===========================================================================

  firecrawl-redis:
    image: redis:7-alpine
    container_name: firecrawl-redis
    restart: unless-stopped
    command: redis-server --bind 0.0.0.0 --save 60 1 --loglevel warning
    volumes:
      - firecrawl-redis-data:/data
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 10s
      timeout: 5s
      retries: 3
    networks:
      - dgx_net

  firecrawl-postgres:
    image: firecrawl-postgres:local
    container_name: firecrawl-postgres
    restart: unless-stopped
    environment:
      - POSTGRES_USER=postgres
      - POSTGRES_PASSWORD=postgres
      - POSTGRES_DB=postgres
    volumes:
      - firecrawl-pg-data:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD", "pg_isready", "-U", "postgres"]
      interval: 10s
      timeout: 5s
      retries: 5
    networks:
      - dgx_net

  firecrawl-playwright:
    image: firecrawl-playwright:local
    container_name: firecrawl-playwright
    restart: unless-stopped
    environment:
      - PORT=3000
    shm_size: "2gb"
    networks:
      - dgx_net

  firecrawl-api:
    image: firecrawl-api:local
    container_name: firecrawl-api-3002
    restart: unless-stopped
    ports:
      - "3002:3002"
    environment:
      - USE_DB_AUTHENTICATION=false
      - REDIS_URL=redis://firecrawl-redis:6379
      - REDIS_RATE_LIMIT_URL=redis://firecrawl-redis:6379
      - PLAYWRIGHT_MICROSERVICE_URL=http://firecrawl-playwright:3000/scrape
      - NUQ_DATABASE_URL=postgres://postgres:postgres@firecrawl-postgres:5432/postgres
      - HOST=0.0.0.0
      - PORT=3002
      - NODE_ENV=production
      - BULL_AUTH_KEY=aitools-bull-changeme
      - SEARXNG_ENDPOINT=http://searxng:8080
    command: node dist/src/harness.js --start-docker
    extra_hosts:
      - "host.docker.internal:host-gateway"
    ulimits:
      nofile:
        soft: 65535
        hard: 65535
    depends_on:
      - firecrawl-redis
      - firecrawl-postgres
      - firecrawl-playwright
    healthcheck:
      test: ["CMD-SHELL", "wget -qO- http://localhost:3002/health || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 60s
    networks:
      - dgx_net

  # ===========================================================================
  # 3. HHEM API — Vectara hallucination evaluator (CPU-only, ARM64)
  #    Images must be pre-built: run build-images.sh before deploying this stack
  # ===========================================================================
  hhem-api:
    image: hhem-api:local
    container_name: hhem-api-8881
    restart: unless-stopped
    ports:
      - "8881:8881"
    volumes:
      # Bind-mount the shared HF model cache so the HHEM model is only
      # downloaded once and lives alongside all other LLMs on this host.
      - /home/sparky/LLMs/huggingface:/hf-cache
    environment:
      - HF_HOME=/hf-cache
    healthcheck:
      test: ["CMD-SHELL", "wget -qO- http://localhost:8881/health || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 120s
    networks:
      - dgx_net

volumes:
  searxng-cache:
  firecrawl-redis-data:
  firecrawl-pg-data:

networks:
  dgx_net:
    external: true