Convert your documents for AI
MinerU converts complex document formats such as PDF and Office into markdown or JSON format suitable for large language models. This tool aims to make unstructured data available in agent-based workflows.
Updates
- September 19, 2026: Stars 80,175 → 80,233, latest release mineru-4.0.3-released (September 18, 2026).
- September 18, 2026: Stars 80,091 → 80,175, latest release mineru-4.0.2-released (September 17, 2026).
- September 17, 2026: Stars 77,695 → 80,091, latest release mineru-4.0.0-released (September 16, 2026).
- August 15, 2026: Stars 76,547 → 77,695, latest release mineru-3.4.5-released (August 14, 2026).
What you get
- Converts PDF and Office files to markup language
- Prepares unstructured data for agent workflows
- Converts complex document formats to JSON output
Installation
pip install --upgrade pip
pip install uv
uv pip install -U "mineru[all]"git clone https://github.com/opendatalab/MinerU.git
cd MinerU
uv pip install -e .[all]If you don't write code
I want to convert the complex PDF and Office documents I have into a format that my artificial intelligence agent can understand. I need to convert these files to markdown or JSON format using the MinerU tool. How can I start this transformation process and use the outputs most efficiently in my agent-based workflows?
Related dictionary terms
Links
TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-06-26: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. This page was machine-translated from the Turkish original · the Turkish version prevails.