MonkeyOCRv2: Document AI Parsing Demo

Upload a document image (receipts, papers, forms, tables, formulas, etc.) and the model will detect the layout, extract text, tables (as HTML), formulas (as LaTeX), and pictures — returning structured Markdown.

Model: zenosai/MonkeyOCRv2-B-Parsing | Paper: MonkeyOCRv2 | GitHub: Yuliang-Liu/MonkeyOCRv2