> it handles queries and documents differently to embed them in the same vector ... | Hacker News

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

		teaearlgraycold on Jan 7, 2024 \| parent \| context \| favorite \| on: Retro on Viberary > it handles queries and documents differently to embed them in the same vector space I assume this might be behind the state of the art, then. As of a year ago OpenAI managed to get an embeddings model that can do both without any special flag or dual model to treat queries and documents differently.

mahjongmen1998 on Jan 18, 2024 [–]

handling queries and documents differently leads to an increase in overall retrieval.

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