Dockerfile

FROM nvidia/cuda:11.8.0-devel-ubuntu22.04

ENV DEBIAN_FRONTEND=noninteractive

# Install base dependencies
RUN apt-get update && \
    apt-get install -y software-properties-common && \
    add-apt-repository ppa:deadsnakes/ppa && \
    apt-get update && \
    apt-get install -y \
        python3.10 \
        python3.10-venv \
        python3.10-distutils \
        python3-pip \
        wget \
        git \
        libgl1 \
        libreoffice \
        fonts-noto-cjk \
        fonts-wqy-zenhei \
        fonts-wqy-microhei \
        ttf-mscorefonts-installer \
        fontconfig \
        libglib2.0-0 \
        libxrender1 \
        libsm6 \
        libxext6 \
        poppler-utils && \
    rm -rf /var/lib/apt/lists/*

RUN update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.10 1

# Set up a non-root user
RUN useradd -m -u 1000 user

# Set home directory and update PATH
ENV HOME=/home/user \
	PATH=/home/user/.local/bin:$PATH

# Set the working directory
WORKDIR $HOME/app

# Copy requirements first (as user)
COPY --chown=user requirements.txt .

# Install Python dependencies (as root to manage venv properly)
# Note: Ensure PyTorch installed picks up CUDA from the base image
RUN python3 -m venv /opt/mineru_venv && \
    . /opt/mineru_venv/bin/activate && \
    pip install --upgrade pip && \
    pip install -r requirements.txt

# Download model script and config template, set permissions (as root)
RUN wget https://github.com/opendatalab/MinerU/raw/master/scripts/download_models_hf.py -O $HOME/app/download_models.py && \
    chmod +x $HOME/app/download_models.py && \
    wget https://github.com/opendatalab/MinerU/raw/master/magic-pdf.template.json -O $HOME/app/magic-pdf.json && \
    chown user:user $HOME/app/download_models.py $HOME/app/magic-pdf.json

# Create output directory and set ownership (as root)
RUN mkdir -p $HOME/app/output/images && \
    chown -R user:user $HOME/app/output

# Switch to non-root user
USER user

# Run model download script and configure magic-pdf for CUDA
RUN . /opt/mineru_venv/bin/activate && \
    python3 $HOME/app/download_models.py && \
    cp $HOME/app/magic-pdf.json $HOME/magic-pdf.json && \
    sed -i 's|"device": "cpu"|"device": "cuda"|g' $HOME/magic-pdf.json

# Copy the rest of the application code as the user
COPY --chown=user . .

# Ensure the output dir still has correct permissions
RUN chmod -R 755 $HOME/app/output

# Expose the port (optional but good practice)
EXPOSE 7860

# Run the application
CMD ["/opt/mineru_venv/bin/uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]