Live data from Hacker News

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

blog.partykit.io

11–20 of 28 posts

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

#11

is there an easy way to disable the multiplayer cursors on that page?

tbh I think it is very funny. Sent it to a few friends because of that. Was chased by a cursor for a minute and then did the same to him/her. Childish, but funny.

It only works well when the site is busy. The frontpage of HN makes it work very very well.

No idea what the article is about though.

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

#12
I had a discussion at work today about completely replacing the old search engine with vector embeddings because they work so well.

I think google needs to be very afraid in the coming few years because this use of AI is relatively cheap to run, simple to deploy and the models are small enough that you can build one customized based on your personal ranking of several thousand pieces of text.

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

#14

is there an easy way to disable the multiplayer cursors on that page?

What can compel a person to think something like this could be a good idea?

I think the website itself has that product. But why would it be enabled on their blog... I don't know.

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

#18

I'm confused about the "AI" part. Are vector databases, in themselves, AI? Are embeddings?

Embeddings are generated by neural networks, so yes, I would consider them as AI

Only indirectly. A lot of popular models used for generating vectors are nowhere near as smart as LLMs. Also, the vectors themselves are not machine learning models. They are just lists of numbers intended for comparing to other lists of numbers. Typically using some similarity algorithm like cosine similarity.

Vector search embeddings are only as good as the models you use, the content you have, and the questions you ask.

This is a bit of a pitfall when you use them for search. Especially if you have mobile users because most of them are not going to thumb in full sentences in a search box. I.e. the questions the ask are going to be a few letters or words at best and not have a lot of context. And users will still expect good results. Vector search is not great for those type of use cases because there just isn't a whole lot of semantics in these short queries. Sometimes, all you need is just a simple prefix search.

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

#19
post #12

I had a discussion at work today about completely replacing the old search engine with vector embeddings because they work so well. I think google needs to be very afraid in the coming few years because this use of AI is relatively cheap to run, simple to deploy and the models are small enough that you can build one customized based on your personal ranking of several thousand pieces of text.

Why does Google need to be afraid? They index the entire web!

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

#20
post #17

So under the hood this relies on Cloudflare, if I understand it? Is it making calls to a CF API in the cloud, or running locally? That part isn't clear to me.

partykit was recently acqui-hired by cloudflare.

https://blog.cloudflare.com/cloudflare-acquires-partykit

Post reply on HN