For years, Elasticsearch was known as a powerful engine for traditional text ingestion, processing, and search - for example, logs. In this talk, we’ll cover the capabilities introduced since then that make Elasticsearch (and the rest of the Elastic Stack) a strong choice for going beyond log analysis and classic BM25 search. Topics include dense vectors, sparse vectors, and hybrid search, along with features that improve effectiveness in modern retrieval scenarios.

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.