ai-tools-searxng-firecrawl-hhem-api/docker-compose.yml

name: ai-tools-stack

# ---------------------------------------------------------------------------
# Shared build env for Firecrawl services (all built from local source)
# ---------------------------------------------------------------------------
x-firecrawl-build: &firecrawl-build
  build:
    context: /home/sparky/Docker/firecrawl/git/firecrawl/apps/api
    dockerfile: Dockerfile

x-firecrawl-env: &firecrawl-env
  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
  BULL_AUTH_KEY: "aitools-bull-changeme"
  HOST: "0.0.0.0"
  PORT: "3002"
  NODE_ENV: production
  # Wire SearXNG so Firecrawl's /search uses it instead of direct Google
  SEARXNG_ENDPOINT: http://searxng:8080

networks:
  ai-tools:
    name: ai-tools
    driver: bridge

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

services:

  # =========================================================================
  # 1. SearXNG — meta-search engine with JSON API
  # =========================================================================
  searxng:
    image: docker.io/searxng/searxng:latest
    container_name: searxng
    restart: unless-stopped
    ports:
      - "8888:8080"
    volumes:
      - ./searxng:/etc/searxng:rw
      - searxng-cache:/var/cache/searxng:rw
    environment:
      - SEARXNG_BASE_URL=http://localhost:8888/
    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:
      - ai-tools

  # =========================================================================
  # 2. Firecrawl — web scraper (self-hosted, no external API key)
  #    Built from local source at /home/sparky/Docker/firecrawl/git/firecrawl/
  # =========================================================================

  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:
      - ai-tools

  firecrawl-postgres:
    build:
      context: /home/sparky/Docker/firecrawl/git/firecrawl/apps/nuq-postgres
      dockerfile: Dockerfile
    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:
      - ai-tools

  firecrawl-playwright:
    build:
      context: /home/sparky/Docker/firecrawl/git/firecrawl/apps/playwright-service-ts
      dockerfile: Dockerfile
    container_name: firecrawl-playwright
    restart: unless-stopped
    environment:
      PORT: 3000
    shm_size: "2gb"
    healthcheck:
      test: ["CMD-SHELL", "wget -qO- http://localhost:3000/health || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 30s
    networks:
      - ai-tools

  firecrawl-api:
    <<: *firecrawl-build
    container_name: firecrawl-api
    restart: unless-stopped
    ports:
      - "3002:3002"
    environment:
      <<: *firecrawl-env
    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:
        condition: service_healthy
      firecrawl-postgres:
        condition: service_healthy
      firecrawl-playwright:
        condition: service_started
    healthcheck:
      test: ["CMD-SHELL", "wget -qO- http://localhost:3002/health || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 60s
    networks:
      - ai-tools

  # =========================================================================
  # 3. HHEM API — hallucination evaluator (Vectara, CPU-only)
  # =========================================================================
  hhem-api:
    build:
      context: ./hhem-api
      dockerfile: Dockerfile
    container_name: hhem-api
    restart: unless-stopped
    ports:
      - "8881:8881"
    volumes:
      # Cache downloaded model weights across restarts
      - hhem-model-cache:/root/.cache/huggingface
    environment:
      - HF_HOME=/root/.cache/huggingface
    healthcheck:
      test: ["CMD-SHELL", "wget -qO- http://localhost:8881/health || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 120s   # model download on first start
    networks:
      - ai-tools