A Comprehensive Guide for Building Rag-Based LLM Applications

Re:A Comprehensive Guide for Building Rag-Based LLM Applicat... by simonw on Thursday September 14, 2023 @07:26AM (#37507500)

No, you don't need a vector database. You can get OK results by prompting "give me ten search terms that are relevant to this question", then running those searches against a regular full-text search engine and pasting those results back into the LLM as context along with the original question.

You're likely to get better results from vector-based semantic search though, just because it takes you beyond needing exact matches on search terms.

[ Parent | on HN ]

Re:A Comprehensive Guide for Building Rag-Based LLM Applicat... by clharman on Thursday September 14, 2023 @11:02AM (#37509976)

Vector is better for some use cases (open-domain, more conversational data) and term-based search is better for others (closed-domain, more keyword-based).

I've found that internal enterprise projects tend to be very keyword based, and vector search often produces weird, head-scratcher results that users hate - whereas term-based search does a better job of capturing the right terms, if you do the proper synonym/abbreviation expansions.

That said, I use them both, usually with vector search as a fallback after the initial keyword-based RAG pass

[ Parent | on HN ]