This is really cool. Do you mind sharing a bit about your process for coming up with the scoring system? Like, what was the process like when you were working with the AI to develop it?
Also, have you ever considered the ability to provide the site with, say, a name and some links to social media or a blog or any other websites associated with that person, and it provides a score on demand?
I recently watched a video talking about how much censorship there is currently with everything on the internet and how massive web pages and databases of information are just completely evaporating. I am not personally one of those "everything is burning to the ground" people, but it's getting hard to not at least see where those people are coming from, given recent events. Honestly, if you have the space available, getting this is probably not the worst idea ever.
I'm not a developer at all, but is using something like Voyage and ChromaDB able to get most of the way there? I've implemented those for semantic search in a project I'm working on, but I'm wondering if rebuilding based on this would be better.
I'm not certain I'm the right market for this, but it's really cool! Is the idea basically to lower token utilization by piggybacking on someone else that is doing a thing as well?
Also, have you ever considered the ability to provide the site with, say, a name and some links to social media or a blog or any other websites associated with that person, and it provides a score on demand?