datajuicer/data_process_loop
1
1FROM python:3.82RUN apt update && apt install -y default-jdk default-jre git 3ENV JAVA_HOME=/usr/lib/jvm/default-java4RUN pip install "py-data-juicer[all] @ git+https://github.com/alibaba/data-juicer.git"5RUN pip install fsspec==2023.3.06RUN useradd -m -u 1000 dj7USER dj8ENV HOME=/home/dj 9RUN cd $HOME/ && git clone https://github.com/alibaba/data-juicer.git && cd ../10WORKDIR $HOME/data-juicer/demos/data_process_loop11RUN chown -R dj $HOME/12CMD ["streamlit", "run", "app.py"]