Vector Search in Elasticsearch 8

Similarity between elements in a dataset has traditionally been measured based on appearance - simple measures such as word counts and other lexical similarities have been the state of the practice. Vector Search goes beyond appearances and lets you define similarity based on meanings and deeper representations of content. Image recognition and comparisons, audio comparisons and recommendations, and relevance ranking based on Natural Language Processing (NLP) are just a few of the applications that Vector Search enables. The Elastic Platform equips you with the tools you need to create novel applications based on this approach.
Highlights
- Understand the basics of Vector Search
- Define indexes to hold vectorized data using Elastic’s dense_vector field type
- Perform efficient Approximate Nearest Neighbor search of vectorized data data using the Hierarchical Navigable Small World (HNSW) search algorithm
- Understand how to import machine learning models into Elasticsearch and use them for inference
Agenda
Introduction and Overview of Vector Search
Use Cases
Measuring Vector Similarity
Vector Search at Scale
Getting Started Hands On
Additional Information
Q&A
Presenter: Robert Statsinger - Principal Solution Architect @ Elastic

[@mrbean8837]

Extremely helpful a year later as it matters to me now. Thank you!

[@ramdaneoualitsen1323]

Thanx a lot

[@julesguisse6345]

Thank you !

[@Jorres-qx1lu]

It's a bit pitiful that the presenter mentioned vector search and importing models being free, while as of this moment they are a platinum\enterprise feature.