[pabe]

Thanks for contributing your work as OSS and writing a comprehensive blog post about it :)

I like the simplicity of your approach without vector DB etc. In case you want to add one, Typesense seems to be a good OSS fit.

[tomhazledine]

My default approach is to use as few dependencies as possible for Proof of Concept experiments like this one, but it DOES favour convenience over long-term efficiency and performance.

I think a single-author blog is about the limit for what can be handled by my flat-file + working memory approach. Any dataset that's much larger would almost certainly need a vector-friendly DB. Typesense looks like it might be a good fit, and so does the pgvector extension of postgres