Well you wouldn't input the whole Vault to the model, you would use embeddings t... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		rolisz on May 22, 2023 \| parent \| context \| favorite \| on: PrivateGPT Well you wouldn't input the whole Vault to the model, you would use embeddings to find the content that is most relevant to the question being asked.

moffkalast on May 22, 2023 [–]

Is that actually a thing yet? Proper vector DB integration? I sure would like to see some demos of that, as it's been hyped up a lot but I haven't really seen anyone deploy anything proper with it yet.

rolisz on May 23, 2023 | [–]

Even PrivateGPT does that, using Chroma as vector DB

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact