|
@@ -18,37 +18,19 @@ RUN apt-get update && \
|
|
|
wget \
|
|
wget \
|
|
|
git \
|
|
git \
|
|
|
libgl1 \
|
|
libgl1 \
|
|
|
- libreoffice \
|
|
|
|
|
- fonts-noto-cjk \
|
|
|
|
|
- fonts-wqy-zenhei \
|
|
|
|
|
- fonts-wqy-microhei \
|
|
|
|
|
- ttf-mscorefonts-installer \
|
|
|
|
|
- fontconfig \
|
|
|
|
|
libglib2.0-0 \
|
|
libglib2.0-0 \
|
|
|
- libxrender1 \
|
|
|
|
|
- libsm6 \
|
|
|
|
|
- libxext6 \
|
|
|
|
|
- poppler-utils \
|
|
|
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
|
|
|
|
# Set Python 3.10 as the default python3
|
|
# Set Python 3.10 as the default python3
|
|
|
RUN update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.10 1
|
|
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 -U magic-pdf[full] -i https://mirrors.aliyun.com/pypi/simple"
|
|
|
|
|
|
|
+# install mineru latest
|
|
|
|
|
+RUN /bin/bash -c "pip3 install --upgrade pip -i https://mirrors.aliyun.com/pypi/simple && \
|
|
|
|
|
+ pip3 install uv -i https://mirrors.aliyun.com/pypi/simple && \
|
|
|
|
|
+ uv pip install 'mineru[all]>=2.0.0' -i https://mirrors.aliyun.com/pypi/simple"
|
|
|
|
|
|
|
|
# Download models and update the configuration file
|
|
# Download models and update the configuration file
|
|
|
-RUN /bin/bash -c "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|cuda|g' /root/magic-pdf.json"
|
|
|
|
|
|
|
+RUN /bin/bash -c "mineru-models-download -s modelscope -m all"
|
|
|
|
|
|
|
|
# Set the entry point to activate the virtual environment and run the command line tool
|
|
# 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 \"$@\"", "--"]
|
|
|
|
|
|
|
+ENTRYPOINT ["/bin/bash", "-c", "export MINERU_MODEL_SOURCE=local && exec \"$@\"", "--"]
|