x-defaults: &defaults
  restart: unless-stopped
  logging:
    driver: json-file
    options:
      max-size: 100m
      max-file: "3"

x-mineru-vllm: &mineru-vllm
  <<: *defaults
  image: ${GLOBAL_REGISTRY:-}alexsuntop/mineru:${MINERU_VERSION:-2.6.5}
  build:
    context: .
    dockerfile: Dockerfile
  environment:
    TZ: ${TZ:-UTC}
    MINERU_MODEL_SOURCE: local
  ulimits:
    memlock: -1
    stack: 67108864
  ipc: host
  deploy:
    resources:
      limits:
        cpus: '16.0'
        memory: 32G
      reservations:
        cpus: '8.0'
        memory: 16G
        devices:
          - driver: nvidia
            device_ids: [ '0' ]
            capabilities: [ gpu ]

services:
  mineru-openai-server:
    <<: *mineru-vllm
    profiles: ["openai-server"]
    ports:
      - ${MINERU_PORT_OVERRIDE_VLLM:-30000}:30000
    entrypoint: mineru-openai-server
    command:
      # ==================== Engine Selection ====================
      # WARNING: Only ONE engine can be enabled at a time!
      # Choose 'vllm' OR 'lmdeploy' (uncomment one line below)
      - --engine vllm
      # --engine lmdeploy

      # ==================== vLLM Engine Parameters ====================
      # Uncomment if using --engine vllm
      - --host 0.0.0.0
      - --port 30000
      # Multi-GPU configuration (increase throughput)
      # --data-parallel-size 2
      # Single GPU memory optimization (reduce if VRAM insufficient)
      # --gpu-memory-utilization 0.5  # Try 0.4 or lower if issues persist

      # ==================== LMDeploy Engine Parameters ====================
      # Uncomment if using --engine lmdeploy
      # --server-name 0.0.0.0
      # --server-port 30000
      # Multi-GPU configuration (increase throughput)
      # --dp 2
      # Single GPU memory optimization (reduce if VRAM insufficient)
      # --cache-max-entry-count 0.5  # Try 0.4 or lower if issues persist
    healthcheck:
      test: ["CMD-SHELL", "curl -f http://localhost:30000/health || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 60s


  mineru-api:
    <<: *mineru-vllm
    profiles: ["api"]
    ports:
      - ${MINERU_PORT_OVERRIDE_API:-8000}:8000
    entrypoint: mineru-api
    command:
      # ==================== Server Configuration ====================
      - --host 0.0.0.0
      - --port 8000

      # ==================== vLLM Engine Parameters ====================
      # Multi-GPU configuration
      # --data-parallel-size 2
      # Single GPU memory optimization
      # --gpu-memory-utilization 0.5  # Try 0.4 or lower if VRAM insufficient

      # ==================== LMDeploy Engine Parameters ====================
      # Multi-GPU configuration
      # --dp 2
      # Single GPU memory optimization
      # --cache-max-entry-count 0.5  # Try 0.4 or lower if VRAM insufficient
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 60s

  mineru-gradio:
    <<: *mineru-vllm
    profiles: ["gradio"]
    ports:
      - ${MINERU_PORT_OVERRIDE_GRADIO:-7860}:7860
    entrypoint: mineru-gradio
    command:
      # ==================== Gradio Server Configuration ====================
      - --server-name 0.0.0.0
      - --server-port 7860

      # ==================== Gradio Feature Settings ====================
      # --enable-api false  # Disable API endpoint
      # --max-convert-pages 20  # Limit conversion page count

      # ==================== Engine Selection ====================
      # WARNING: Only ONE engine can be enabled at a time!

      # Option 1: vLLM Engine (recommended for most users)
      - --enable-vllm-engine true
      # Multi-GPU configuration
      # --data-parallel-size 2
      # Single GPU memory optimization
      # --gpu-memory-utilization 0.5  # Try 0.4 or lower if VRAM insufficient

      # Option 2: LMDeploy Engine
      # --enable-lmdeploy-engine true
      # Multi-GPU configuration
      # --dp 2
      # Single GPU memory optimization
      # --cache-max-entry-count 0.5  # Try 0.4 or lower if VRAM insufficient
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:7860/"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 60s