Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Docling Technical Report

About

This technical report introduces Docling, an easy to use, self-contained, MIT-licensed open-source package for PDF document conversion. It is powered by state-of-the-art specialized AI models for layout analysis (DocLayNet) and table structure recognition (TableFormer), and runs efficiently on commodity hardware in a small resource budget. The code interface allows for easy extensibility and addition of new features and models.

Christoph Auer, Maksym Lysak, Ahmed Nassar, Michele Dolfi, Nikolaos Livathinos, Panos Vagenas, Cesar Berrospi Ramis, Matteo Omenetti, Fabian Lindlbauer, Kasper Dinkla, Lokesh Mishra, Yusik Kim, Shubham Gupta, Rafael Teixeira de Lima, Valery Weber, Lucas Morin, Ingmar Meijer, Viktor Kuropiatnyk, Peter W. J. Staar• 2024

Related benchmarks

TaskDatasetResultRank
Document Text GenerationOHR-Bench Generation
Text Score46.6
14
Textual RAGOHR-Bench (Overall)
TXT Score0.43
14
Document RetrievalOHR-Bench Retrieval
Accuracy (Text)73.3
14
Visual RAGBizMMRAG
Score (TXT)66.7
5
Textual RAGBizMMRAG Japanese (test)
TXT Score70
5
Textual RAGAllganize Japanese (test)
TXT Score61.3
5
Visual RAGOHR-Bench (test)
TXT Score73.2
5
Visual RAGAllganize
TXT Score66
5
Showing 8 of 8 rows

Other info

Follow for update