News for hackers. Stuff that matters.
Re:Patterns for Building LLM-Based Systems and Products by gk1 on Wednesday August 02, 2023 @09:16AM (#36970461)
Our blog post on the topic shows test results: https://www.pinecone.io/blog/hybrid-search/

TL;DR - doing hybrid vector + keyword search provides more relevant results for text searches than vector search alone. And using sparse vector embeddings for the “keyword” part provides even more relevant results than using BM25.

There are no comments on this comment yet.