Building Relevance Formulas with LLMs

“E-commerce search is often about exploring options and providing good recommendations. Say I want to buy a car and I have some hard filters (e.g. budget) but most criteria are weights: cheaper is better, more reliable is also better (these two tend to collide). I prefer orange, but other colors are OK.

I want to tell the LLM what I want - like in RAG - but I want sorted results with previews and facets - like in traditional E-commerce search - so I can see what’s available and refine my filters manually. In short, I want a chatbot instead of a search box.

This session covers a PoC of this approach. We express product attributes as tensors, then compute the score as a dot-product of these tensors and those representing user preferences. We’ll combine these dot-products with other criteria - like distance or price - into an overall score with weights that can be tuned by chatting with an LLM. Because I want a cheap AND reliable car and I’m willing to discuss what that means for me :)”

Kristian Aune

Vespa

Kristian Aune - co-founder and Head of Customer Success, Vespa.ai. Expert in Search, Recommendation and Personalization use cases, with over two decades of experience in the field. Passionate about performance, operations, cost, and serving quality! His expertise spans from e-commerce product search, real-time IoT applications, to content personalization for media platforms. Kristian is known for his ability to bridge the gap between complex technical concepts and practical business applications.