doclingr

MaRDI QIDQ7375255CRANFDO

Authors Andre Leite, Marcos Wasilew, Hugo Vasconcelos, Carlos Amorim, Diogo Bezerra

Last update 10 July 2026

Copyright license MIT license, File License

Software version identifier 0.1.0

Description

An interface to 'Docling', a document-understanding library that converts 'PDF', 'DOCX', 'PPTX', 'HTML' and image documents into structured, AI-ready data. The package wraps the 'Docling' 'Python' package through 'reticulate' to extract layout-aware text, tables and metadata, export to 'Markdown' or 'JSON', and split documents into context-rich chunks suitable for retrieval-augmented generation (RAG) and embedding pipelines.

This page was built for software: doclingr