Query Understanding with Late Interaction & Wormhole Vectors

Query Understanding is one of the most important, yet usually overlooked, steps in information retrieval. Most search teams focus entirely on “algorithmic ranking”, hoping that the math (BM25, Vector Similarity, Hybrid Fusion) will magically rank the best results without first contextually understanding the queries. It often doesn’t.

In this talk, we walk through why Query Understanding is critical for a search pipeline, and why ranking alone is usually insufficient for optimal search. We’ll then show off a Query Understanding implementation using modern techniques like Wormhole Vectors (hopping back and forth between sparse and dense vector spaces) and late interaction (multivector representations per token) to significantly improve what was historically possible with more traditional query understanding approaches (like a knowledge graph + a text tagger).

The improvements aren’t just theoretical. We’ll show code examples (on several datasets) for interpreting query intent and rewriting queries prior to the final search request. We’ll then walk through our recent benchmarks of this approach that blow away today’s popular hybrid search techniques.

Trey Grainger

Searchkernel

Trey Grainger is lead author of the book AI-Powered Search (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 with Doug Turnbull.