[ansonhw]

Hmm i think the issue with any large data set is indexing + querying. At https://usefind.ai/ this is a fundamental problem we've been trying to tackle. What kind of structure do you think would work?

[albertdessaint]

You’re right, did you check CircleMind? Could it be useful in your case? https://www.ycombinator.com/companies/circlemind

[albertdessaint]

I checked your project, that’s really good and I saw that you’re working on Q&A that will be very useful!

[ansonhw]

Hmm i'll check out the pagerank stuff, IMO RAG isn't super great. I think RAG overall has been oversold since embeddings KNN hasn't proven to be super accurate.