BigHugger
sk Skill · PaddlePaddle

paddleocr-doc-parsing

Use this skill to extract structured Markdown/JSON from PDFs and document images—tables with cell-level precision, formulas as LaTeX, figures, seals, charts, headers/footers, multi-column layout and correct reading order. Trigger terms: 文档解析, 版面分析, 版面还原, 表格提取, 公式识别, 多栏排版, 扫描件结构化, 发票, 财报, 复杂 PDF, PDF转Markdown, 图表, 阅读顺序; reading order, formula, LaTeX, layout parsing, structure extraction, PP-StructureV3, PaddleOCR-VL.

installs 8w
75
30-day movement
starts with the next reading
Related entries
2
Connections
0
jsonbashPython

This is a PaddlePaddle agent skill (a SKILL.md) that guides an AI coding agent in using PaddleOCR's document parsing pipeline (PP-StructureV3 / PaddleOCR-VL) via the `paddleocr` CLI. It covers extracting structured Markdown/JSON from PDFs and document images, including tables, formulas as LaTeX, figures, seals, charts, headers/footers, multi-column layouts, and reading order.

Reach for it when you need to convert complex PDFs or scans into structured Markdown/JSON with layout, tables, and formulas preserved.

Use it to

  • Convert complex PDFs to Markdown
  • Extract tables with cell-level precision from scans
  • Recognize formulas as LaTeX
  • Parse multi-column documents in correct reading order
  • Structure invoices and financial reports

For Developers parsing PDFs and scanned documents via AI agents

Host repository
PaddlePaddle/PaddleOCR
Installs, lifetime
427
Installs, 8 weeks
75
Licence
Apache-2.0
Host stars
90k
Host language
Python
topicspaddleocrdocument-parsingpdfocrlayout-analysismarkdown-extraction