Benjamin Clavié
Benjamin Clavié
I'm not sure if the problem is related to Colab, I also have an error using Jupyter locally on my Ubuntu server. The basic `readme.md` example doesn't work and the...
Basic support for utilities to export a model from a path on disk to Huggingface Hub, as well as convert the safe tensors to VespaColBERT onnx.
Ongoing project. The goal is for RAGatouille to support more than just ColBERT, and build our way to UDAPDR support. Integrating DSPy is the next big milestone. No current definite...
Indexing is time consuming, and oftentimes people would like to be able to easily share pre-built index for various common datasets, for general domain application (wikipedia, code documentation...) and evaluation...
Testing is currently very sparse. It's essentially just ensuring model loading works properly (not tested in all cases yet) and reproducing the notebooks as end2end tests to make sure a...
Self-explanatory, currently very barebones. Any contribution, be it documentation, more examples, or deeper tutorials, is very welcome.
Putting this out there as a way to alleviate the _many_ dependencies issues. I'll soon be shipping a PLAID (&compression, that will come later)-free indexing method, which will alleviate the...
Currently, we only use the ColBERT optimised indexes, or index-free in-memory encodings. For low-to-medium volumes of documents, not using the ColBERT optimisation can have advantages: easier CRUD, potentially better performance,...
Currently, Indexing is handled by upstream ColBERT completely, and only accepts ColBERT outputs. We want to decouple the indexing stage and the document encoding stage, so that we can take...