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.

In this talk, I'll be introducing Docling, 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. We will walk through Docling's architecture and its unique DoclingDocument data structure, demonstrate how Docling's features help build document processing pipelines that can be leveraged for various applications. Lastly, I'll share how teams have leveraged Docling to ingest previously inaccessible data while reducing document processing costs.

And of course 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.