Most organizational knowledge is still locked inside complex documents, making it difficult to extract and use the information effectively. Traditional tools often fail when working with real-world document formats, particularly PDFs. Tables lose their structure, figures get separated from captions, and multi-column layouts become unreadable text. These failures make it difficult to bring AI to document-heavy workflows.
Docling is an open-source project that takes a different approach, using deep learning models to parse documents the way humans read them. It preserves hierarchy, extracts structured data through a consistent API, and supports over ten common file formats out of the box. Most importantly, all of Docling is open-source and under an MIT license, which allows for fully local execution with low latency to reduce data privacy exposure.
In this talk, I'll walk through Docling's architecture, demonstrate how to build document processing pipelines that can be leveraged for various applications, and share how the IBM CIO team used Docling to unlock complex attachment data from webpages for askIBM, content that was previously inaccessible and expanded their vector database by 6%. You'll leave with practical ideas for bringing Docling into your own projects.
