Viewing profile — perone

I share the same feeling, I think filesystems will have to reinvent themselves given the pace of how useful ML models became in the past years.

I'm planning to support MacOS, the only issue is with the encoders that I'm using now, I will probably work more on it next week to try to make a release that works on MacOS as wel…

Hi, there are no LLMs involved, it is all local and an embedding (vector representation) of the data is created and then that is used for search later, nothing is sent to cloud fro…

This is quite different than LanceDB. In VectorVFS I'm using the inodes directly to store the embeddings, there is no external file with metadata and db, the db is your filesystem …

Hi, I think Rust won't bring much benefit here to be honest, the bottleneck is mainly the model and model loading. It would probably be a nightmare to load these models from Rust, …

Hi, not sure if I understood what you meant by opaque embeddings as well, but the reason why files surface or not is due to the similarity score (which is basically the dot product…

Hi, it is quite different, there is no LLM involved, we can certainly use it for a RAG for example, but what is currently implemented is basically a way to generate embeddings (vec…

Thanks, I'm working on implementing the commands to clean the embeddings (you can now do that with Linux xattr command-line tool). I'm supporting CPU or GPU (NVIDIA) for the encode…

Thanks. There is a bit of a nuance there, for example: you can build an index in first pass which will indeed be linear, but then later keep it in an open prompt for subsequent que…

I'm not sure I agree about the data manifolds being too rigid. When we look at the quality score-based generative models and diffusion we can see a clear evidence of how flexible t…

I wrote an article about it and S2 some time ago as well for those interested: https://blog.christianperone.com/2015/08/googles-s2-geometry...

I find it interesting how everyone ignore EuclidesDB ( https://euclidesdb.readthedocs.io ) which came before Milvus and others in 2018, it is free and open-source. Same for all pre…

https://feste.readthedocs.io/en/latest/design.html , this seems to be what Feste already does, and it offers automatic batching as well.