Beyond Hybrid Search with "Wormhole Vectors"

Lightning Lessons

Practical skills & tools to accelerate your career

Beyond Hybrid Search with "Wormhole Vectors"

Hosted by Trey Grainger and Dmitry Kan

Tue, Oct 21, 2025

4:00 PM UTC (1 hour)

Virtual (Zoom)

Free to join

By continuing, you agree to Maven's Terms and Privacy Policy.

56 students

By continuing, you agree to Maven's Terms and Privacy Policy.

Invite your network

Go deeper with a course

AI-Powered Search

Doug Turnbull and Trey Grainger

View syllabus

Tue, Oct 21, 2025

4:00 PM UTC (1 hour)

Virtual (Zoom)

Free to join

56 students

Invite your network

Go deeper with a course

AI-Powered Search

Doug Turnbull and Trey Grainger

View syllabus

What you'll learn

What are "Wormhole Vectors"?

Learn how wormhole vectors work & how to use them to traverse between disparate vector spaces for better hybrid search.

Building a behavioral vector space from click stream data

Learn to generate behavioral embeddings to be integrated with dense/semantic and sparse/lexical vector queries.

Traverse lexical, semantic, & behavioral vectors spaces

Jump back and forth between multiple dense and sparse vector spaces in the same query

Advanced hybrid search techniques (beyond fusion algorithms)

Hybrid search is more than mixing lexical + semantic search. See advanced techniques and where wormhole vectors fit in.

Why this topic matters

"Wormhole Vectors" are an experimental approach for hybrid search that enables traversal across disparate vector spaces (lexical, semantic, behavioral, etc.), rather than merging separate sparse/lexical and dense/semantic search results using a fusion algorithm. Learn how to construct wormhole vectors to jump between separate indexes and how this new technique could be the future of hybrid search.

You'll learn from

Trey Grainger

Founder @ Searchkernel, Author, "AI-Powered Search"

TREY GRAINGER is author of the book AI-Powered Search and is the founder of Searchkernel, a software company building the next generation of AI-powered search. He is an advisor to several startups and adjunct professor of computer science at Furman University. He previously served as CTO of Presearch, a decentralized web search engine, and as chief algorithms officer and SVP of engineering at Lucidworks, an search company whose search technology powers hundreds of the world’s leading organizations.

Trey is an instructor of Maven's AI-Powered Search course.

Dmitry Kan

Founder & Host: Vector Podcast

DMITRY KAN is the Founder & Host of the Vector Podcast. He is also Product Director for Search at Aiven and is a hands-on IT professional with a PhD in Computer Science and 16+ years of combined experience in search engine algorithms, search relevancy, query interpretation, speed of search and scalability. Dmitry has a strong background in Machine Learning and Natural Language Understanding algorithms and systems.

Built Search At