services:
  gemma3-vllm:
    image: vllm/vllm-openai-rocm:latest
    container_name: gemma3-vllm
    restart: unless-stopped
    env_file:
      - ./backend/config/model.env
    environment:
      HUGGING_FACE_HUB_TOKEN: ${HF_TOKEN}
      HF_TOKEN: ${HF_TOKEN}
      PYTORCH_ROCM_ARCH: gfx1103
    command:
      - --model
      - ${GEMMA_MODEL_ID:-google/gemma-3-1b-it}
      - --host
      - 0.0.0.0
      - --port
      - "8000"
      - --dtype
      - float16
      - --max-model-len
      - ${VLLM_MAX_MODEL_LEN:-4096}
      - --gpu-memory-utilization
      - ${VLLM_GPU_MEMORY_UTILIZATION:-0.88}
      - --api-key
      - ${VLLM_API_KEY:-local-dev-key}
    devices:
      - /dev/kfd
      - /dev/dri
    group_add:
      - video
    cap_add:
      - SYS_PTRACE
    security_opt:
      - seccomp=unconfined
    ports:
      - "${BACKEND_PORT:-8000}:8000"
    volumes:
      - ${HUGGINGFACE_CACHE_DIR:-/home/${USER}/.cache/huggingface}:/root/.cache/huggingface
      - ./models:/models
    healthcheck:
      test: ["CMD-SHELL", "curl -sf http://localhost:8000/health >/dev/null || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 10
      start_period: 120s

  chat-ui:
    image: ghcr.io/open-webui/open-webui:main
    container_name: gemma3-chat-ui
    restart: unless-stopped
    depends_on:
      gemma3-vllm:
        condition: service_started
    env_file:
      - ./frontend/config/frontend.env
    environment:
      WEBUI_AUTH: "False"
      OPENAI_API_BASE_URL: ${OPENAI_API_BASE_URL:-http://gemma3-vllm:8000/v1}
      OPENAI_API_KEY: ${VLLM_API_KEY:-local-dev-key}
      ENABLE_OPENAI_API: "True"
      ENABLE_OLLAMA_API: "False"
      DEFAULT_MODELS: ${GEMMA_MODEL_ID:-google/gemma-3-1b-it}
      GLOBAL_LOG_LEVEL: INFO
      WEBUI_NAME: Gemma 3 via vLLM
    ports:
      - "${FRONTEND_PORT:-3000}:8080"
    volumes:
      - ${OPEN_WEBUI_DATA_DIR:-./frontend/data/open-webui}:/app/backend/data