docker-compose-s.yml

---

services:

  weaviate:
    command:
      - --host
      - 0.0.0.0
      - --port
      - '8080'
      - --scheme
      - http
    image: cr.weaviate.io/semitechnologies/weaviate:1.27.0
    ports:
      - 8080:8080
      - 3000:8080
      - 50051:50051
    volumes:
      - weaviate_data:/var/lib/weaviate
    restart: on-failure:0
    healthcheck:
      test: wget --no-verbose --tries=3 --spider http://127.0.0.1:8080/v1/.well-known/ready || exit 1
      interval: 5s
      timeout: 10s
      retries: 5
      start_period: 10s
    environment:
      QUERY_DEFAULTS_LIMIT: 50
      AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED: 'true'
      PERSISTENCE_DATA_PATH: '/var/lib/weaviate'
      DEFAULT_VECTORIZER_MODULE: 'text2vec-ollama'
      ENABLE_API_BASED_MODULES: 'true'
      ENABLE_MODULES: 'generative-ollama,text2vec-ollama'
      CLUSTER_HOSTNAME: 'node1'

  updater:
    build:
      context: .
      dockerfile: Dockerfile
    environment:
      - WEAVIATE_URL=http://weaviate:8080
      - OLLAMA_URL=http://ollama:11434
      - OLLAMA_MODEL=llama3.2
    ports:
      - 8000:8000
    depends_on:
      weaviate:
        condition: service_healthy
    volumes:
      - updater:/data/
    healthcheck:
      test: wget --no-verbose --tries=3 --spider http://127.0.0.1:8000 || exit 1
      interval: 5s
      timeout: 10s
      retries: 5
      start_period: 10s

  ollama:
    image: ollama/ollama
    ports:
      - "11434:11434"  # Expose the port for Ollama
    volumes:
      - ollama:/root/.ollama  # Persistent storage for Ollama data
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              capabilities: [gpu]
              count: all  # Use 'all' for all available GPUs or specify a number
    restart: always

volumes:
  weaviate_data:
    external: true
  ollama:
    external: true
  updater:
    external: true
...