Speaker Details
Trey Grainger
Founder, Searchkernel
Trey Grainger is lead author of the book [AI-Powered Search](https://aipoweredsearch.com) (Manning 2025) and founder of Searchkernel, a software consultancy building the next generation of AI-powered search. He also serves as a technical advisor at OpenSource Connections.
He previously served as CTO of Presearch, a decentralized web search engine, and as Chief Algorithms Officer and SVP of Engineering at Lucidworks, a search company whose technology powers hundreds of the world's leading organizations. Trey is also co-author of the book _Solr in Action_ (Manning 2014), as well as over a dozen other publications including books, journals, and research papers. Trey has 18 years of experience in search and data science focused on building self-learning search platforms integrating the most successful AI Search techniques.
Trey teaches AI Search in the course [AI-Powered Search: Modern Retrieval for Humans & Agents](https://aipoweredsearch.com/live-course) with Doug Turnbull
Talk Details
Extending Vespa’s Hybrid Search with Wormhole Vectors
In this talk, we introduce “wormhole vectors” and how to use them in Vespa to outperform today's hybrid search approaches. Wormhole vectors are an emerging technique that enables jumping between corresponding regions of disparate vector spaces (sparse lexical, dense semantic, dense behavioral, etc.) at query time to discover relationships that better inform query understanding and ranking.
Most hybrid search today blends results from two or more independent query approaches (usually lexical/BM25 and semantic/dense vector) using a post-query fusion algorithm. While this is typically better than a single query approach alone, it unnecessarily limits search to a partitioned ranking problem that misses out on a crucial query understanding phase.
Wormhole vectors, in contrast, serve as a form of pseudo-relevance feedback that provides a way to unify queries across lexical, semantic, and other vector spaces (like user-behavioral embedding spaces, which we’ll demonstrate how to generate and traverse).
You’ll learn how to construct wormhole vectors to traverse between sparse and dense vector spaces (and vice versa), to create better query understanding, and to ultimately generate more relevant results. We’ll also share benchmarks and examples of how wormhole vectors compare to other query approaches like SPLADE and hybrid fusion algorithms.