News for hackers. Stuff that matters.
Re:Build a search engine, not a vector DB by mariarmestre on Wednesday December 20, 2023 @06:36AM (#38707511)
I think a fundamental issue with search, and the reason why many companies do not invest in tuning a good search experience, is that the main metric usually is to minimise embarrassing/irrelevant results, rather than get the best possible set of results. How can you even know what is the best answer to your query? Systematic evaluation is very hard.
Re:Build a search engine, not a vector DB by TimPC on Wednesday December 20, 2023 @08:27AM (#38708403)
If you control the browser your results are in you can monitor clicks and time spent on document to generate pretty good signal. If someone opens a document and looks at it for fifteen minutes you should be fairly convinced it was useful.