News for hackers. Stuff that matters.
Re:Introducing GPTs by lazzlazzlazz on Monday November 06, 2023 @02:54PM (#38167967)
OP is incorrect. Embeddings are still needed since (1) context windows can't contain all data and (2) data memorization and continuous retraining is not yet viable.
Re:Introducing GPTs by zwily on Monday November 06, 2023 @03:16PM (#38168323)
But the common use case of using a vector DB to pull in augmentation appears to now be handled by the Assistants API. I haven't dug into the details yet but it appears you can upload files and the contents will be used (likely with some sort of vector searching happening behind the scenes).
Re:Introducing GPTs by nextworddev on Monday November 06, 2023 @03:13PM (#38168274)
"yet"
Re:Introducing GPTs by coding123 on Monday November 06, 2023 @03:18PM (#38168348)
It's also much slower. LLMs are generating text token at a time. That's not very good for search.

Pre-search tokenization however, probably a good fit for LLMs.