From Vectors to Tensors Expanding the Possibilities of AI Search

Vector embeddings transformed how we build search and retrieval systems, and if you’ve shipped production applications on top of them, you already know what they can do—and may also be starting to discover what they can’t. Vectors are powerful, but they represent a single point in space, while complex search problems involving multiple signals, multimodal data, or nuanced relevance ranking require something more expressive. Tensors extend what’s possible, enabling richer representations, more sophisticated scoring, and retrieval that can reason across dimensions that vector search simply wasn’t built to handle. In this session, Vespa.ai’s Bonnie Chase, Director of Product Marketing, and Zohar Nissare-Houssen, Strategic Presales Lead Engineer, will offer a practical primer on what tensors are, why they matter, and what they make possible in real-world applications, along with concrete use cases across retail, life sciences, and financial services.