flâneur — a map of the web's best reading

Building a web search engine from scratch in two months with 3 billion neural embeddings

blog.wilsonl.in · 8,712 words · saved by 14 readers

End-to-end deep dive of the project, spanning a large GPU cluster, distributed RocksDB, and terabytes of sharded HNSW.

A while back, I decided to undertake a project to challenge myself: build a web search engine from scratch. Aside from the fun deep dive opportunity, there were two motivators: Search engines seemed to be getting worse, with more SEO spam and less relevant quality content. Transformer-based text embedding models were taking off and showing amazing natural comprehension of language. A simple question I had was: why couldn't a search engine always result in top quality content? Such content may be rare, but the Internet's tail is long , and better quality results should rank higher than the prol

Explore this link on the map →

saved by

related reading