# MinerU: PDF to Markdown with OCR, Fully Local

> Convert PDFs to Markdown with LaTeX formulas and extracted images on your own machine. MinerU runs offline with OCR for 109 languages.

- Author: AI Kai
- Published: 2026-07-03
- Updated: 2026-08-24
- Topic: AI Dev Tools
- Tags: ocr, mineru, pdf, local-tools
- Canonical: https://hqman.me/blog/mineru-ocr-local/

I'm building an AI education project. I need to convert PDFs into Markdown, extract images from pages, and preserve math formulas as LaTeX. Most tools I tried choke on the formulas or lose the images. Many require uploading to someone else's server. MinerU does all three and runs on my machine. Nothing gets uploaded anywhere.

## What It Does

- Converts PDF, DOCX, PPTX, XLSX, and images into Markdown or structured JSON
- Turns math formulas into LaTeX, tables into HTML
- Extracts images from documents with their positions preserved
- OCR support for 109 languages, handles scanned pages, handwriting, multi-column layouts
- Runs offline on CPU or GPU (Apple Silicon MPS works)
- Licensed under a custom Apache 2.0-based open source license

Formulas come out as real LaTeX, not garbled text. Tables keep their structure. Images land as separate files referenced in the Markdown.

## Install

One command:

```bash
pip install uv
uv pip install -U "mineru[all]"
```

First run downloads models (~10GB). After that, everything is local.

## Usage (CLI)

```bash
mineru -p test.pdf -o ./output --return_images true
```

`--return_images true` pulls all images out of the PDF as separate files. The Markdown references them with relative paths.

For CPU-only machines, add `-b pipeline`:

```bash
mineru -p test.pdf -o ./output -b pipeline --return_images true
```

Output:

```
output/
└── document/
    ├── document.md          # Markdown
    ├── images/              # extracted images
    └── document_content_list.json
```

## Web UI (Gradio)

MinerU also has a browser interface. Start the API server first, then launch Gradio.

Terminal 1 (keep running):

```bash
cd mineru
source .venv/bin/activate
export NO_PROXY=127.0.0.1,localhost
mineru-api --host 127.0.0.1 --port 8000
```

Terminal 2:

```bash
cd mineru
source .venv/bin/activate
export NO_PROXY=127.0.0.1,localhost
mineru-gradio --server-name 127.0.0.1 --server-port 8808 --api-url http://127.0.0.1:8000
```

Open http://127.0.0.1:8808, upload a PDF, hit convert, done.

## MCP Server

MinerU ships an MCP server. You can hook it into Claude Desktop or Cursor and parse documents from your AI coding workflow. Details in their [docs](https://opendatalab.github.io/MinerU/usage/).

## Demo

I feed a math-heavy PDF in, Markdown with LaTeX and extracted images comes out.

## Links

- GitHub: https://github.com/opendatalab/MinerU
- Documentation: https://opendatalab.github.io/MinerU/
- Online demo (no install needed): https://mineru.net