Last released Jul 6, 2026
A practical document parsing tool for converting PDF, images, DOCX, PPTX, and XLSX into Markdown and JSON
Last released Jun 11, 2026
Utilities for MinerU Vision-Language models
Last released Apr 13, 2026
OCR for The Truth
Last released Apr 9, 2026
Storage for documents
Last released Oct 28, 2025
Benchmark for document extraction tasks.
Supported by