services:
  jina-embeddings:
    image: ghcr.io/ggml-org/llama.cpp:server-cuda12-b8914
    container_name: jina-embeddings
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    ports:
      - "127.0.0.1:${JINA_HTTP_PORT:-8081}:8080"
    volumes:
      - ./models:/root/.cache/huggingface
    command:
      - -hf
      - jinaai/jina-embeddings-v5-omni-small-clustering-GGUF:Q2_M
      - --embedding
      - --host
      - "0.0.0.0"
      - --port
      - "8080"
    restart: unless-stopped

  openviking:
    image: ghcr.io/volcengine/openviking:latest
    container_name: openviking
    depends_on:
      - jina-embeddings
    ports:
      - "${OPENVIKING_HTTP_PORT:-1933}:1933"
      - "${OPENVIKING_UI_PORT:-8020}:8020"
    volumes:
      - ./data:/app/.openviking
    environment:
      - OPENVIKING_CONFIG_FILE=/app/.openviking/ov.conf
      - OPENVIKING_CLI_CONFIG_FILE=/app/.openviking/ovcli.conf
      - OPENVIKING_WITH_BOT=${OPENVIKING_WITH_BOT:-1}
    restart: unless-stopped