Any idea how it was made? I'd like to do the same.

Mix of some GCP natural language understanding and some coding from some of ny colleagues (I have some really smart colleagues).

I can't remember exactly, but I know it was a couple of years or more ago so pre ChatGPT / Bard and all that.

To be fair, if the alternative was "searching confluence", almost anything is better than that, whether it's a chatbot or a third party search engine slapped on top of your confluence data. Confluence's search is an absolute joke, and a bad one at that.

Confluence search isn't that bad. What is bad is the data that is fed into it. It has no way of understanding what is more relevant: some doc from 10 years ago or something related from recently.

So what you're saying is that Confluence search is bad, because it has no understanding of relevance, something we figured how to do even before the PageRank algorithm got published in 1998?

Search is meant to help humans find what they need to find. If your search function doesn't (and Confluence's sure as hell doesn't) then it's bad. And arguably, plain mislabeled because it's not performing searches. At best, it's grepping.

PageRank is based people linking using huge scale of the entire internet.

It’s difficult to infer importance based on a couple of thousand documents at most.

No, it isn't. It was, back in the 90s. But full text linked document indexing was a fully solved problem by 2012, and Confluence put genuine effort into not using any of the existing solutions and instead went with "You get grep. Not search. Sucks to be you".