Converts PDFs, Office documents, and scanned pages into LLM-ready Markdown or JSON, preserving tables, formulas, and reading order for agent pipelines.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your coding agent:
- Layout Parsing
Use MinerU to detect columns, headers, and figures to reconstruct correct reading order: ‹what you need›
- Table and Formula Extraction
Use MinerU to recover tables as structured markup and mathematical formulas as LaTeX: ‹what you need›
- Batch Conversion
Use MinerU to process large document sets into Markdown or JSON: ‹what you need›
Install the CLI
Install it as its own instructions say.
Its page: opendatalab.github.io/MinerU
Call the API
Auth An API key from OpenDataLab
Its page: opendatalab.github.io/MinerU
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- APICLI
- Auth
- API Key
- Skills
- 3
Skills
Layout Parsing
Detects columns, headers, and figures to reconstruct correct reading order from complex multi-column documents.
Table and Formula Extraction
Recovers tables as structured markup and mathematical formulas as LaTeX rather than flattening them into text.
Batch Conversion
Processes large document sets into Markdown or JSON through the CLI or hosted API for retrieval pipelines.