FRESH

Hacker News

Using Vectorize to build an unreasonably good search engine in 160 lines of code

142 points by ColinWright

by simonw

5 subcomments

by ____tom____

1 subcomments

You didn't build a search engine in 160 lines of code. You build a client for a search engine in 160 lines of code. The vector database is providing the search.

by mips_avatar

3 subcomments

There’s a lot of previously intractable problems that are getting solved with these new embeddings models. I’ve been building a geocoder for the past few months and it’s been remarkable how close to google places I can get with just slightly enriched open street maps plus embedding vectors

by RomanPushkin

0 subcomment

You might be getting a good _recall_ rate, since vectorize search is ANN, but the _precision_ can be low, because reranker piece is missing. So I would slightly improve it by adding 10 more lines of code and introducing reranker after the search (slightly increasing topK). Query expansion in the beginning can be also added to improve recall.

by repeekad

2 subcomments

What about re-ranking? In my limited experience, adding fast+cheap re-ranking with something like Cohere to the query results took an okay vector based search and made top 1-5 results much stronger

by Supermancho

4 subcomments

Site has a neat feature where you can see the pointers of other people, marked by regional? notations, scrolling through the content.

by yuzhun

0 subcomment

While embeddings are generally not required in the context of code, I am interested in how they perform in the legal and regulatory domain, where documents are substantially longer. Specifically, how do embeddings compare with approaches such as ripgrep in terms of effectiveness?

by abhinavb05

1 subcomments

At my workplace we are using vector embedding to build recommendation system and the results are amazing

by alansaber

0 subcomment

Good to see the article touching on the performance impact of a niche vs general embedding model/aggressive subword tokenization

by sa-code

0 subcomment

Models like bge are small and quantized versions will fit in browser or on a tiny machine. Not sure why everyone reaches for an API as their first choice

by croemer

1 subcomments

by daquisu

0 subcomment

Now it is even easier. Cloudflare has a beta product called AI Search that implements most of these 160 lines of code

by ballpug

0 subcomment