Birbla

Join the discussion

Write your take first — we'll ask for email only when you're ready to publish.

Sign in
  • Hacker News
  • I am not convinced that Turbovec yields better retrieval than the same amount of bits of a Matryoshka embedding.
    by OutOfHere
  • Interestingly, while we don't fine-tune generative models for Louie.ai, we found fine-tuning embedding models to be a major $ saver. Instead of 1K-2K wide frontier embedding vector lens... Just 64. Huge savings on vector DB $$$.

    I'm curious how that works with something like turboquant. Not needed any more, still dominant, better together, ... .

    by lmeyerov
  • This looks perfect for local, privacy first search, but since it's built in Rust, has anyone tried compiling it to WASM to run directly inside a browser extension?
    by anishvarghese
  • If anyone is looking to retrofit to an existing pipeline, I use similar ideas to compress vectors for job search, getting roughly 8x compression with about a 3.5% drop in quality. My experiment: https://corvi.careers/blog/vector-search-embedding-compressi...
    by _tgxm
  • people should read turboquant's open review comments: https://openreview.net/forum?id=tO3ASKZlok
    by bobmarleybiceps
  • It would be nice to have the README be a little more human written for a project where you actually want people to adopt it
    by nharada
  • Wow! 4GB for 10 million documents. This means one could build a reverse index much faster than before and devx processes like debugging, performance testing would become much smoother. Can't wait for the sqlite bindings to come out!
    by ghm2199
  • FAISS is no longer close to SoTA:

    https://ann-benchmarks.com/index.html https://vector-index-bench.github.io/ https://big-ann-benchmarks.com/neurips23.html

    by Eridrus

Explore Birbla archives