mineru

name	mineru
description	PDF文档高保真提取 - 混合VLM架构，保留阅读顺序，解析公式表格
category	vision
emoji	📑
github_url	https://github.com/opendatalab/MinerU
triggers	["PDF提取","文档解析","表格提取","公式识别","mineru"]
inputs	["pdf","epub"]
outputs	["json","markdown","html"]
use_cases	["PDF文档提取","表格解析","公式识别"]

MinerU

高保真PDF文档提取工具。

安装

pip install magic-pdf

使用

magic-pdf -p your_pdf_file.pdf -o output/