Introducing Ingestum :

the extensible, scalable,
easy-to-use content ingestion framework

Now with BioPortal and

Ingestion is always adding new sources thanks to our community of contributors. Join the community to benefit from the best ingestion framework for AI data preprocessing.

#1 challenge

Ingestum facilitates writing scripts to extract unstructured content from arbitrary file formats and streams.

#2 challenge

Ingestum provides a framework for extraction from a diverse universe of sources.

#3 challenge

Ingestum allows integration with Python scripts and services at many levels of granularity.

Join our community for code, support, and tips.

We're building the last ingestion software you'll ever need. Develop with our open-source framework of content ingestion now.

Ingestum: A FOSS NLP document ingestion library

a LibrePlanet 2021 address by Sorcero’s Walter Bender, Martín Abente Lahaye, & Juan Pablo Ugarte

Download the white paper: Ingestum: A Unified Content Ingestion Framework.

Learn more about how to use Ingestum to enhance your project.