Welcome to EuclidesDB !

_images/arch.png

EuclidesDB is a multi-model machine learning feature database that is tight coupled with PyTorch and provides a backend for including and querying data on the model feature space. Some features of EuclidesDB are listed below:

  • Written in C++ for performance;
  • Uses protobuf for data serialization;
  • Uses gRPC for communication;
  • LevelDB integration for database serialization;
  • Many indexing methods implemented (Annoy, Faiss, etc);
  • Tight PyTorch integration through libtorch;
  • Easy integration for new custom fine-tuned models;
  • Easy client language binding generation;
  • Free and open-source with permissive license;

Note

EuclidesDB is still in its initial release and many new features are going to come in the next versions. The client API might change in the upcoming releases before we stabilize on a robust API design. Contributions are also welcome ! If you want to contribute, please refer to the Contributing to EuclidesDB section.

Indices and tables