Docling Technical Report
Auer, Christoph, Lysak, Maksym, Nassar, Ahmed, Dolfi, Michele, Livathinos, Nikolaos, Vagenas, Panos, Ramis, Cesar Berrospi, Omenetti, Matteo, Lindlbauer, Fabian, Dinkla, Kasper, Mishra, Lokesh, Kim, Yusik, Gupta, Shubham, de Lima, Rafael Teixeira, Weber, Valery, Morin, Lucas, Meijer, Ingmar, Kuropiatnyk, Viktor, Staar, Peter W. J.
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Aug-30-2024
- Country:
- Genre:
- Research Report (0.40)
- Industry:
- Information Technology (0.49)
- Transportation (0.70)
- Technology:
- Information Technology
- Artificial Intelligence
- Machine Learning > Neural Networks
- Deep Learning (0.68)
- Natural Language (1.00)
- Machine Learning > Neural Networks
- Data Science > Data Mining (0.94)
- Information Management (0.93)
- Software (0.88)
- Artificial Intelligence
- Information Technology