This talk goes into details of how Intercom implemented Semantic search for Fin, their AI Agent, and how their implementation has evolved. Ketan shares practical lessons from his experience on avoiding unnecessary complexity when possible.

Apache Lucene was never built for AI-scale vector search. In this talk, I’ll show how USearch bridges the JVM–native gap, pairing Spark’s horizontal scale with native vertical speed.

Vector search is typically associated with embeddings - sequences of floating-point numbers. However, semantic search isn’t limited to dense_vector. In this talk, I’ll introduce you to sparse vectors, semantic text, and more.