News for hackers. Stuff that matters.

A comment on Semantic search engine for ArXiv, biorxiv and medrxiv. Parent comment

Re:Semantic search engine for ArXiv, biorxiv and medrxiv by forrestp on Wednesday May 21, 2025 @04:02AM (#44049302)
My understanding is that your levers are roughly better / more diverse embeddings or computing more embeddings (embed chunks / groups / etc) + aggregating more cosine similarities / scores. More flops = better search w/ steep diminishing returns

Colbert being a good google-able application of utilizing more embeddings.

Search ends up often being a funnel of techniques. Cheap and high recall for phase 1 and ratchet up the flops and precision in subsequent passes on the previous result set.

[ Parent | on HN ]
Re:Semantic search engine for ArXiv, biorxiv and medrxiv by 0101111101 on Wednesday May 21, 2025 @10:25AM (#44051769)
Exactly! A near property of the matryoshka embeddings is that you can compute a low dimension embedding similarity really fast and then refine afterwards.
[ Parent | on HN ]