Dockerfile

FROM ubuntu:22.04

ENV DEBIAN_FRONTEND=noninteractive

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

WORKDIR /app

COPY requirements.txt .

RUN python3 -m venv /opt/mineru_venv && \
    . /opt/mineru_venv/bin/activate && \
    pip install --upgrade pip && \
    pip install -r requirements.txt

# Download model + setup config
RUN wget https://github.com/opendatalab/MinerU/raw/master/scripts/download_models_hf.py -O download_models.py && \
    . /opt/mineru_venv/bin/activate && \
    python3 download_models.py && \
    wget https://github.com/opendatalab/MinerU/raw/master/magic-pdf.template.json -O /root/magic-pdf.json && \
    sed -i 's|"device": "cpu"|"device": "cpu"|g' /root/magic-pdf.json

COPY app.py .

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