Appendix B: Tools

A curated collection of tools organized by category to help you build production AI applications.

Data Preparation

Tool	Description
Docling	IBM's document conversion tool that transforms PDFs, Word docs, and other formats into clean, structured Markdown. Supports complex layouts, tables, and multi-column documents.
MarkItDown	Microsoft's lightweight document converter supporting PDF, DOCX, XLSX, PPTX, HTML, images (with OCR), audio transcription, and more. Simple Python API for converting any document to Markdown.