News for hackers. Stuff that matters.
Re:voyage-code-3 by serjester on Monday January 13, 2025 @10:20PM (#42693147)
I don’t understand why we have so many companies working on vector databases when the real value is in fine tuned embeddings. Having recently evaluated vector DB’s to handle 100M+ nodes, everything will run you $1 - 8k per month. Yet using embeddings fine tuned on a specific use case, will lower that 10X since you can get away with way coarser vectors.

This makes so much intuitive sense - voyage please release an insurance focused model.

Re:voyage-code-3 by digdugdirk on Monday January 13, 2025 @11:04PM (#42693470)
Can you explain more about this, or point someone in the right direction with a few resources for reading more about it?
Re:voyage-code-3 by apricot0 on Tuesday January 14, 2025 @03:24AM (#42694986)
Can you recommend any resources/tutorials about fine-tuning embedding models? Which base model did you fine-tune?
Re:voyage-code-3 by ghxst on Tuesday January 14, 2025 @05:38AM (#42695772)
What's an insurance focused model in this context? Sorry if it's a stupid question.
Re:voyage-code-3 by parentheses on Tuesday January 14, 2025 @05:55PM (#42705059)
The answer is obvious. Vector DBs have clear line of sight. Experimental embeddings do not.