Dockerfile

# Hugging Face Spaces Dockerfile for MinerU Document Parser API
# Based on official MinerU Docker deployment
# Optimized for L40S GPU (Ada Lovelace architecture, 48GB VRAM)
# Build: v1.4.0 - Using mineru[core] for full backend support

# Use official vLLM image as base (includes CUDA, PyTorch, vLLM properly configured)
# v0.14.1 includes security patches (CVE-2025-66448/CVE-2025-30165) and memory leak fixes
# Supports Ampere, Ada Lovelace, Hopper architectures (L40S is Ada Lovelace)
FROM vllm/vllm-openai:v0.14.1

USER root

RUN echo "========== BUILD STARTED at $(date -u '+%Y-%m-%d %H:%M:%S UTC') =========="

# Install system dependencies (fonts required by MinerU, curl for health checks)
RUN echo "========== STEP 1: Installing system dependencies ==========" && \
    apt-get update && apt-get install -y --no-install-recommends \
    fonts-noto-core \
    fonts-noto-cjk \
    fontconfig \
    libgl1 \
    curl \
    poppler-utils \
    && fc-cache -fv && \
    rm -rf /var/lib/apt/lists/* && \
    echo "========== System dependencies installed =========="

# Create non-root user for HF Spaces (required by HuggingFace)
RUN useradd -m -u 1000 user

# Set environment variables (MINERU_MODEL_SOURCE set later after download)
# LD_LIBRARY_PATH includes pip nvidia packages for cuDNN (libcudnn.so.9)
ENV PYTHONUNBUFFERED=1 \
    PYTHONDONTWRITEBYTECODE=1 \
    MINERU_BACKEND=pipeline \
    MINERU_LANG=en \
    MAX_FILE_SIZE_MB=1024 \
    HF_HOME=/home/user/.cache/huggingface \
    TORCH_HOME=/home/user/.cache/torch \
    MODELSCOPE_CACHE=/home/user/.cache/modelscope \
    XDG_CACHE_HOME=/home/user/.cache \
    HOME=/home/user \
    PATH=/home/user/.local/bin:/usr/local/bin:/usr/bin:$PATH \
    LD_LIBRARY_PATH=/home/user/.local/lib/python3.12/site-packages/nvidia/cudnn/lib:$LD_LIBRARY_PATH \
    VLLM_GPU_MEMORY_UTILIZATION=0.4

# Create cache directories with correct ownership
RUN mkdir -p /home/user/.cache/huggingface \
    /home/user/.cache/torch \
    /home/user/.cache/modelscope \
    /home/user/app && \
    chown -R user:user /home/user

# Switch to non-root user
USER user
WORKDIR /home/user/app

# Copy requirements first for better caching
COPY --chown=user:user requirements.txt .

# Install Python dependencies
# Note: nvidia-cudnn-cu12 provides libcudnn.so.9 required by torch
RUN echo "========== STEP 2: Installing Python dependencies ==========" && \
    pip install --user --upgrade pip && \
    pip install --user nvidia-cudnn-cu12 && \
    pip install --user -r requirements.txt && \
    echo "Reinstalling modelscope in user space for torch compatibility..." && \
    pip install --user --force-reinstall modelscope && \
    echo "Installed packages:" && \
    pip list --user | grep -E "(mineru|fastapi|uvicorn|httpx|pydantic|modelscope|torch|cudnn|doclayout)" && \
    echo "========== Python dependencies installed =========="

# Create MinerU config file (required BEFORE downloading models)
# The mineru-models-download command reads ~/mineru.json to know where to store models
RUN echo "========== STEP 3a: Creating MinerU config ==========" && \
    mkdir -p /home/user/.cache/mineru/models && \
    echo '{"models-dir": {"pipeline": "/home/user/.cache/mineru/models", "vlm": "/home/user/.cache/mineru/models"}, "config_version": "1.3.1"}' > /home/user/mineru.json && \
    cat /home/user/mineru.json && \
    echo "========== MinerU config created =========="

# Download MinerU models using official tool
RUN echo "========== STEP 3b: Downloading MinerU models ==========" && \
    echo "This downloads all required models (~4-5GB)..." && \
    echo "Cache directories before download:" && \
    ls -la /home/user/.cache/ && \
    echo "Downloading all models from huggingface..." && \
    mineru-models-download --source huggingface --model_type all && \
    echo "" && \
    echo "========== Model cache summary ==========" && \
    echo "MinerU models cache:" && \
    du -sh /home/user/.cache/mineru 2>/dev/null || echo "  (empty)" && \
    ls -la /home/user/.cache/mineru/models 2>/dev/null || echo "  (no files)" && \
    find /home/user/.cache/mineru -type f 2>/dev/null | head -20 || echo "  (no files found)" && \
    echo "HuggingFace cache:" && \
    du -sh /home/user/.cache/huggingface 2>/dev/null || echo "  (empty)" && \
    echo "Total cache size:" && \
    du -sh /home/user/.cache 2>/dev/null || echo "  (empty)" && \
    echo "========== Models downloaded =========="

# Set model source to local AFTER downloading (prevents re-download at runtime)
ENV MINERU_MODEL_SOURCE=local

# Copy application code
COPY --chown=user:user . .

RUN echo "Files in app directory:" && ls -la /home/user/app/ && \
    echo "========== BUILD COMPLETED at $(date -u '+%Y-%m-%d %H:%M:%S UTC') =========="

# Expose the port
EXPOSE 7860

# Health check
HEALTHCHECK --interval=30s --timeout=30s --start-period=300s --retries=5 \
    CMD curl -f http://localhost:7860/ || exit 1

# Override vLLM entrypoint and run our FastAPI server
ENTRYPOINT []
CMD ["/usr/bin/python3", "-m", "uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860", "--workers", "1", "--timeout-keep-alive", "300"]