Dockerfile

FROM ubuntu:22.04

ENV DEBIAN_FRONTEND=noninteractive

# Install dependencies
RUN apt-get update && apt-get install -y \
    wget fontconfig libfontconfig1 libfreetype6 libjpeg8 libpng16-16 \
    libpoppler-glib8 libxml2 zlib1g libxrender1 libpangocairo-1.0-0 \
    python3 python3-pip && \
    apt-get clean

# Download and install pdf2htmlEX
RUN wget https://github.com/pdf2htmlEX/pdf2htmlEX/releases/download/v0.18.8.rc1/pdf2htmlEX-0.18.8.rc1-master-20200630-Ubuntu-bionic-x86_64.deb && \
    dpkg -i pdf2htmlEX-0.18.8.rc1-master-20200630-Ubuntu-bionic-x86_64.deb && \
    rm pdf2htmlEX-0.18.8.rc1-master-20200630-Ubuntu-bionic-x86_64.deb

# Install Gradio
RUN pip3 install gradio==4.24.0

COPY app.py .

CMD ["python3", "app.py"]