kevisual-awesome/mark/pdf/mineru/download.md

安装环境

conda create -n mineru 'python>=3.10' -y
conda activate mineru
pip install -U "magic-pdf[full]" -i https://mirrors.aliyun.com/pypi/simple

下载模型

pip install modelscope


curl -o download_models.py https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/scripts/download_models.py

python download_models.py

配置文件在 magic-pdf.json

使用

magic-pdf -p {some_pdf} -o {some_output_dir} -m auto
magic-pdf -p test.pdf -o test -m auto