Dockerfile

FROM python:3.10
RUN apt update && apt install -y default-jdk default-jre git ffmpeg libsm6 libxext6 software-properties-common build-essential cmake gfortran libopenblas-dev liblapack-dev
ENV JAVA_HOME=/usr/lib/jvm/default-java
RUN pip install pybind11
RUN pip install "py-data-juicer[all] @ git+https://github.com/alibaba/data-juicer.git"
RUN useradd -m -u 1000 dj
USER dj
ENV HOME=/home/dj 
RUN cd $HOME/ && git clone https://github.com/alibaba/data-juicer.git && cd ../
WORKDIR $HOME/data-juicer/demos/data_visualization_op_effect
RUN chown -R dj $HOME/
CMD ["streamlit", "run",  "app.py"]