MinerU

Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.

View on GitHub↗Upstream opendatalab/MinerU↗

Builder

opendatalab

opendatalab • individual

Stars

57,939

Using upstream star count

Forks

4,793

Using upstream fork count

Open Issues

Activity Score

0/100

190 commits in 30d

Created

Feb 29, 2024

Project creation date

README Summary

MinerU is a Python tool that transforms complex documents like PDFs into clean, structured markdown and JSON formats optimized for Large Language Model workflows. It provides robust document parsing capabilities to extract text, tables, images, and other elements from various document types. The tool is designed to prepare documents for AI agent workflows and LLM processing pipelines.

AI Dev Skills

Unmapped

Tags

Document ProcessingComputer Vision for Document UnderstandingOCR (Optical Character Recognition)Layout AnalysisText ExtractionDocument Structure RecognitionData Pipeline EngineeringMultimodal Document ParsingContract AnalysisLegal Document ReviewRegulatory Document ComplianceMultimodalAcademic Literature MiningResearch Paper ProcessingAgentic AIOn-premiseDocument Question AnsweringCloudTextDocument AIFinancial ServicesPublishingMultimodal ReasoningEducationIntelligent Document ProcessingFinancial Report AnalysisRetrieval-Augmented GenerationHealthcareImageSelf-hostedGovernmentLegal TechPython

Recent Activity

Updated 1 months ago

7 Days

30 Days

190

90 Days

414

Quality

beta

Quality: medium
Maturity: beta

PM Skills

Scale & ReliabilityDeveloper Platform

Languages

Python100.0%

Timeline

Project created: Feb 29, 2024
Forked: Mar 16, 2026
Your last push: 1 months ago
Upstream last push: 10 days ago
Tracked since: Mar 7, 2026

Similar Repos

pgvector cosine similarity · $0

Loading…