Vespa.ai Live: Speaker and Session Details

Return to Program Overview
Get Tickets

Speaker Details

Dainius Jocas

Senior ML Architect, Ravenpack

Over the last decade I've built many search systems ranging from small prototypes to the billion-scale multi-modal behemoths. Recently I'm mostly focusing on the scale and performance side of search. 

linkedinConnect

 

1-2

Talk Details

Nuances of Binarized Embeddings Based Retrieval

Can we get away without an HNSW index in our billion-scale search system for financial data? This was the starting question in the journey that led to digging deep inside Vespa's internals. 

In this talk I'll focus on the Vespa setup nuances such as:

Does binarized embeddings need HNSW index?

  • How many matches does exact nearest neighbor search expose for the first phase ranking?

  • How does the match-phase limiter change the query execution?

  • How to combine lexical matching and nearest neighbor search?

Finally, I'll present how far you did we go without HNSW for binarized embeddings based retrieval.

Join us at Vespa.ai Live

Get TicketsReturn to Program Overview