Open Source Software for E-Discovery and Information Retrieval

FreeDiscovery is build on top of existing machine learning libraries (scikit-learn) and provides REST web services for information retrieval applications. It aims to benefit existing e-discovery platforms with a focus on the following functionality,

• binary text categorization
• document clustering
• duplicate detection
• e-mail threading

In addition, FreeDiscovery can be used as Python package and aims to expose a scikit-learn compatible API.

The first release is expected for January 1, 2017, but we would very much appreciate feedback on the existing functionality. Feel free to open new issues on Github or send any comments to grossman@ir.cs.georgetown.edu.

For more information see the documentation and API Reference.

FreeDiscovery is released under the 3-clause BSD licence.