[hdlothia]

So the part of RAG that's tripping me up right now is vector search and familiarity scores. Does anyone have a good resource to learn more about this?

I've been using this as a starter. https://developers.cloudflare.com/workers-ai/tutorials/build... I put in text but I feel like my conception of what should get high relevancy scorrs doesn't match the percentages that come out.

The article talks about full text search and meta data so maybe that's the path I should be taking instead of vector search? Where would I store the Metadata in this case? A regular db?

I wish articles like this would go into more details about the nitty gritty. But I appreciate high level overview in the article as well.

[PheonixPharts]

Once you have vector representations the "similarity" scores are just basic linear algebra. It's fundamentally no different than any other IR/recsys task.

A good overview is chapter 6 of the Stanford NLP group's IR book [0].

Engineering LLMs still requires a good foundation in the basics of ML/NLP so it's worth the time to catch up a bit.

0. https://web.archive.org/web/20231207074155/https://nlp.stanf...

[hdlothia]

This is exactly what I was looking for. Thank you so much!

[jxnlco]

thanks! this was based on a 30 minute 'crash course on what things they need to look out fo'

I'd recommend taking a look at lancedb as they support text, vectors, and sql.

high relevancy scores are not percentages, they only make sense in 'ordering' but 0.7 does not mean relevant.

but .9 vs .7 means 'maybe more relevant.