PaddlePaddle publishes skills that let an AI agent extract text from images, photos, screenshots and scanned PDFs, including CJK characters, small print and handwriting. Its document parsing skill turns complex PDFs and scans into structured Markdown or JSON, preserving tables, LaTeX formulas, figures, multi-column layout and reading order, which suits invoices and financial reports.
Paddleocr
2 skills · 92,371 stars · Apache-2.0
Paddleocr Doc Parsing Use this skill to extract structured Markdown/JSON from PDFs and document images—tables with cell…
Paddleocr Text Recognition Use this skill whenever the user wants text extracted from images, photos, scans, screenshots, or…