Build a search engine, not a vector DB

Re:Build a search engine, not a vector DB by sroussey on Wednesday December 20, 2023 @12:36PM (#38711250)

You can use llama2 to do embedding and summaries and chat.

Turning the docs into questions is something I will test on stuff (just learning and getting a feel).

I am intrigued... what makes a good vector index??

[ Parent | on HN ]

Re:Build a search engine, not a vector DB by deckar01 on Wednesday December 20, 2023 @05:03PM (#38714247)

My heuristic is how much noise is in the closest vectors. Even if the top k matches seem good, if the following noise has practically identical distance scores, it is going to fail a lot in practice. Ideally you could calculate some constant threshold so that everything closer is relevant and everything further is irrelevant.

[ Parent | on HN ]

Re:Build a search engine, not a vector DB by sroussey on Friday December 22, 2023 @12:04PM (#38736147)

Apologies for being naive, but how do you calculate noise?

[ Parent | on HN ]