services:
  notediscovery:
    image: ghcr.io/gamosoft/notediscovery:latest
    container_name: notediscovery
    restart: unless-stopped
    ports:
      - "8000:8000"
    environment:
      - TZ=UTC
    volumes:
      - ./data:/app/data
      # Uncomment to customize (files/folders must exist first):
      # - ./config.yaml:/app/config.yaml
      # - ./plugins:/app/plugins
      # - ./themes:/app/themes
    healthcheck:
      test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:8000/health')"]
      interval: 30s
      timeout: 5s
      retries: 3
      start_period: 10s

  ollama:
    image: ollama/ollama:latest
    container_name: ollama
    restart: unless-stopped
    ports:
      - "11434:11434"
    environment:
      - OLLAMA_HOST=0.0.0.0:11434
      - OLLAMA_KEEP_ALIVE=30m
    volumes:
      - ollama-models:/root/.ollama
    healthcheck:
      test: ["CMD", "ollama", "--version"]
      interval: 30s
      timeout: 5s
      retries: 3
      start_period: 15s

  # ChatGPT-style browser UI for Ollama.
  # Available at http://localhost:3000 after startup.
  open-webui:
    image: ghcr.io/open-webui/open-webui:main
    container_name: open-webui
    restart: unless-stopped
    ports:
      - "3000:8080"
    environment:
      - OLLAMA_BASE_URL=http://ollama:11434
      # Skip account creation on first launch (single-user local mode).
      # Set to "true" for the login flow if you're exposing this beyond localhost.
      - WEBUI_AUTH=false
      # We only use Ollama, so disable the external OpenAI integration.
      - ENABLE_OPENAI_API=false
    volumes:
      - open-webui-data:/app/backend/data
    depends_on:
      ollama:
        condition: service_healthy

  # One-shot service: pulls the model on first startup, then exits.
  # No-op on subsequent runs if the model is already present.
  # To change the model, edit MODEL below (any tag from https://ollama.com/library):
  #   qwen2.5:0.5b        ~400 MB   fastest, minimal capability
  #   qwen2.5:1.5b        ~1.0 GB   balanced (default)
  #   qwen2.5-coder:1.5b  ~1.0 GB   code-focused
  #   qwen2.5-coder:3b    ~2.0 GB   better code, still small
  #   llama3.2:3b         ~2.0 GB   general-purpose
  ollama-init:
    image: ollama/ollama:latest
    container_name: ollama-init
    depends_on:
      ollama:
        condition: service_healthy
    environment:
      - OLLAMA_HOST=ollama:11434
      - MODEL=qwen2.5:1.5b
    entrypoint:
      - /bin/sh
      - -c
      - |
        echo "Pulling model: $$MODEL"
        ollama pull "$$MODEL"
        echo "Model ready."
    restart: "no"

volumes:
  ollama-models:
  open-webui-data: