Re:I want flexible queries, not RAG
by bambax on Wednesday May 22, 2024 @03:15AM
(#40438182)
You're right and I was imprecise. 2. is how RAG is implemented in most cases. (I wouldn't call 1. 'RAG' exactly, though?)
[ Parent
| on HN ]
HYDE is a related technique. Ask the model to generate a response with no context, then use this for semantic search agains actual data and respond by summarising these documents.
I'd definitely call 1 (the FTS version) RAG. It's how Bing and Google Gemini and ChatGPT Browse work - they don't have a full vector index of the Web to work with (at least as far as I know), they use the model's best guess at an appropriate FTS query instead.