News for hackers. Stuff that matters.
Re:Introducing GPTs by oezi on Monday November 06, 2023 @04:36PM (#38169369)
OpenAI is still way too expensive to run a corporate knowledge base on top
Re:Introducing GPTs by m3kw9 on Monday November 06, 2023 @09:19PM (#38172362)
It’s more reliable than chatpdfs that relies on vector search. With vector db all you are doing is doing a fuzzy search and then sending in that relevant portion near that text and send it to a LLM model as part of a prompt. It misses info.
Re:Introducing GPTs by dragonwriter on Monday November 06, 2023 @11:57PM (#38173415)
I'd be very surprised if the Assistants API is not doing RAG with a vector DB behind the scenes with the supplied files.