Home / Companies / Weaviate / Blog / Post Details
Content Deep Dive

Unlocking the Power of Hybrid Search - A Deep Dive into Weaviate's Fusion Algorithms

Blog post from Weaviate

Post Details
Company
Date Published
Author
Dirk Kulawiak, Joon-Pil (JP) Hwang
Word Count
2,063
Language
English
Hacker News Points
24
Summary

Weaviate offers hybrid search capabilities that combine vector and keyword search results using two fusion algorithms: rankedFusion and relativeScoreFusion. The newer algorithm, relativeScoreFusion, is likely to be the better choice for most users as it retains more information from the original searches than rankedFusion. Hybrid search provides semantically rich results while respecting the precision of keyword searches. Weaviate also introduced AutoCut in v1.20, which can intelligently retrieve groups of objects from a search and works well with relativeScoreFusion.