Qdrant calculates hybrid search results using k=2 and k=61 as tunable parameters, with the paper citing RRF using 60.
Published
Signal category
Research & Knowledge
Quote
“At k=2, rank 1 in a prefetch carries 5.5x the weight of rank 10 once fused. At k=61 (the zero-based equivalent of the paper's 60), that drops to 1.15x, so just getting retrieved by dense or sparse starts to matter almost as much as where it landed.”
— Andre Zayarni|Qdrant team
Company
Qdrant
Composable high-performance vector search
- Industry
- Software Development
- Location
- Berlin, DE
- Company size
- 153 employees
Powering the next generation of AI applications with advanced and high-performant vector similarity search technology. Qdrant is an open-source vector search engine. It deploys as an API service providing a search for the nearest high-dimensional vectors. With Qdrant, embeddings or neural network encoders can be turned into full-fledged applications for matching, searching, recommending, and much more. Make the most of your Unstructured Data!
Founded 2021