Data Science & Analytics
Doc Parser
Parse complex documents with IBM's open-source Docling library, which turns PDFs and Office files into structured Markdown or JSON. Use when a user asks to parse a document with tables, extract figures from a document, handle multi-column layouts, convert a complex PDF to structured data, extract content from academic papers, or process documents with mixed layouts. Handles tables, figures, headers, footers, and multi-column text.
- Publisher / source
- TerminalSkills Library
- Upstream record
- TerminalSkills/skills
- Version
- Version 5
- Published
- Publication review
- Approved for publication
- Content fingerprint
53ffd8a7ebc2ad0b8873afd5e929fa0a1b77fd9193c98fc4301a8599f281d298