skills.rest
opendatalab
opendatalabOFFICIAL
Explore all skills by this author →
WebsiteGitHub

MinerU Document Extractor

Convert PDFs, images, and Office files into Markdown, HTML, or JSON.

185|14|Updated Mar 18, 2026
Search Tags:#ocr#pdf#markdown#rag#parsing#mineru
One-click install
npx skills add https://github.com/opendatalab/MinerU-Ecosystem --skill mineru-document-extractor-opendatalab
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: MinerU Document Extractor
Source: https://github.com/opendatalab/MinerU-Ecosystem/tree/main/skills
Command: npx skills add https://github.com/opendatalab/MinerU-Ecosystem --skill mineru-document-extractor-opendatalab

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires mineru-open-api.

What problem does it solve?

This skill solves the challenge of converting complex, unstructured documents like PDFs, scanned images, and Office files into clean, machine-readable formats like Markdown or JSON, ensuring high accuracy for LLM and RAG pipelines.

Core Features & Use Cases

  • Dual-Engine Extraction: Leverages both VLM and OCR engines to handle complex layouts, tables, formulas, and 109 languages.
  • Flexible Modes: Offers a zero-setup flash mode for quick tasks and a precision mode for batch processing and advanced formatting.
  • Use Case: Researchers can use this to parse academic papers with complex multi-column layouts and formulas, while developers can integrate it into RAG pipelines to ensure high-quality document ingestion.

Quick Start

Use the MinerU Document Extractor to convert the file named report.pdf into Markdown format using the flash extraction mode.

Frequently Asked Questions about MinerU Document Extractor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert PDF documents with complex layouts and formulas to Markdown for RAG pipelines?▼

You can convert complex PDFs to Markdown by using the flash mode for quick extraction or precision mode for batch processing, ensuring high-fidelity layout reconstruction for your RAG pipelines.

What is the best way to parse scanned images and Office files into machine-readable formats?▼

Dual-engine extraction handles complex layouts and formulas in scanned images and Office files, converting them into clean Markdown, HTML, or JSON for LLM-based agentic workflows.

Does MinerU Document Extractor require any specific CLI tools to process PDF files?▼

Yes, processing PDF files requires the mineru-open-api CLI tool to interface with the MinerU API for document processing and extraction tasks.

Can I extract tables and formulas from multi-column academic papers into HTML or JSON?▼

Yes, the skill supports high-accuracy table recognition and formula parsing for multi-column academic papers, outputting the extracted data into HTML or JSON formats.

What is the difference between flash mode and precision mode for document parsing?▼

Flash mode provides a zero-setup approach for quick document parsing tasks, while precision mode handles batch processing and advanced formatting for higher fidelity extraction.

Related Skills

Explore More Data & Analytics Skills→
letta-ailetta-ai
134

financial-document-processor

Extract structured data from financial documents via OCR and PDF text extraction.

Official
Advanced
FilipcsupkaFilipcsupka

AgentDB Vector Search

Enable semantic vector search across large document collections with HNSW indexing.

Community
Advanced
imMamdouhaboammarimMamdouhaboammar

agency-rag-pipeline-engineer

Design and implement retrieval-augmented generation pipelines with vector databases and LLM frameworks.

Community
Advanced
sheawinklersheawinkler
78

ocr-and-documents

Extract text from PDFs, scans, and images via pymupdf and marker-pdf.

Community
Intermediate