You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
52 lines
2.3 KiB
Docker
52 lines
2.3 KiB
Docker
# Use the official Ubuntu base image
|
|
FROM swr.cn-central-221.ovaijisuan.com/mindformers/mindformers1.2_mindspore2.3:20240722
|
|
|
|
USER root
|
|
|
|
# Set environment variables to non-interactive to avoid prompts during installation
|
|
ENV DEBIAN_FRONTEND=noninteractive
|
|
|
|
# Update the package list and install necessary packages
|
|
RUN apt-get update && \
|
|
apt-get install -y \
|
|
software-properties-common && \
|
|
add-apt-repository -y ppa:deadsnakes/ppa && \
|
|
apt-get update && \
|
|
apt-get install -y \
|
|
python3.10 \
|
|
python3.10-venv \
|
|
python3.10-distutils \
|
|
python3.10-dev \
|
|
python3-pip \
|
|
wget \
|
|
git \
|
|
libgl1 \
|
|
libglib2.0-0 \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
# Set Python 3.10 as the default python3
|
|
RUN update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.10 1
|
|
|
|
# Create a virtual environment for MinerU
|
|
RUN python3 -m venv /opt/mineru_venv
|
|
|
|
# Copy the configuration file template and install magic-pdf latest
|
|
RUN /bin/bash -c "wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/magic-pdf.template.json && \
|
|
cp magic-pdf.template.json /root/magic-pdf.json && \
|
|
source /opt/mineru_venv/bin/activate && \
|
|
pip3 install --upgrade pip -i https://mirrors.aliyun.com/pypi/simple && \
|
|
pip3 install torch==2.3.1 torchvision==0.18.1 -i https://mirrors.aliyun.com/pypi/simple && \
|
|
pip3 install -U magic-pdf[full] 'numpy<2' decorator attrs absl-py cloudpickle ml-dtypes tornado einops -i https://mirrors.aliyun.com/pypi/simple && \
|
|
wget https://gitee.com/ascend/pytorch/releases/download/v6.0.rc2-pytorch2.3.1/torch_npu-2.3.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl && \
|
|
pip3 install torch_npu-2.3.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl"
|
|
|
|
# Download models and update the configuration file
|
|
RUN /bin/bash -c "source /opt/mineru_venv/bin/activate && \
|
|
pip3 install modelscope -i https://mirrors.aliyun.com/pypi/simple && \
|
|
wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/scripts/download_models.py -O download_models.py && \
|
|
python3 download_models.py && \
|
|
sed -i 's|cpu|npu|g' /root/magic-pdf.json"
|
|
|
|
# Set the entry point to activate the virtual environment and run the command line tool
|
|
ENTRYPOINT ["/bin/bash", "-c", "source /opt/mineru_venv/bin/activate && exec \"$@\"", "--"]
|