About
IBM open-source document parsing library. Convert PDF, DOCX, PPTX into structured formats with layout preservation.
Features
- Deep learning layout analysis (DocTR + custom layout models)
- Table structure recognition with cell-level extraction
- Figure detection and bounding box export
- Reading order recovery and heading hierarchy detection
- Multi-format output: Markdown, DocTags, JSON, HTML
Links
Categories
Reviews
4
Write a Review
Get new AI tools weekly
Subscribe to our newsletter and never miss a tool.
Get new AI tools weekly
Subscribe to our newsletter and never miss a tool.