okapi bm25 site hotshops pp site dlmultimedia era in site:dylancastillo.co

1 result(s) for “okapi bm25 site hotshops pp site dlmultimedia era in site:dylancastillo.co” · 325 ms

Scope: Nishi’s own index (our crawl + Common Crawl) — not the whole live web. Some sites block all automated crawlers (anti-bot walls), so their pages may be absent here even though we never filter lawful content.

Freshness: no result on this page carries a fetch time yet (indexed before the fetch epoch was stored beside the doc)

A real deployment would use an approximate index, apply its own compression, rescore with full-precision vectors, and often mix in BM25 and a reranker

from the top result below

Honey, I shrunk the embeddings: Matryoshka vs. PCA – Dylan Castillo

https://dylancastillo.co/posts/matryoshka-vs-pca

AI labs responded with a technique called Matryoshka Representation Learning (MRL), which lets you use fewer embedding dimensions without sacrificing much accuracy in your retrieval