Oh, no need to wait for LLMs. Apache Solr should be really good at it. We used it at a company I was working at to build the most kickass search into our platform, that would actually find the stuff you were looking for…and that was back in 2018 :D
Honestly, I think this was probably the initial product idea for this Microsoft Recall shit. If I could have something like that running locally, open-source and with a non-insane security architecture, I’d never again use a folder in my life.
Dump it all to ~/mytrashpile and let the AI figure out what I want I’m looking for 😄
Yeeeah for me it’s https://readeck.org/en/ …but same :D
These ideas are getting refined by fermenting in my tab stack!
Don’t get me wrong though… throwing an LLM at it would be a lot easier and faster. Just a mind boggling use of resources for a task that could probably be done more efficiently :D
Setting this up with Apache Solr and a suitable search frontend runs a high risk of becoming an abandoned side project itself^^