Architecture

Vector search and vector databases

Vector search finds items by closeness in meaning, and a vector database stores those representations and returns similar results fast.

How to use the term

What to read alongside

This term is worth reading together with the neighbouring concepts in its section and the Gravity AI launch scenarios it belongs to.

Glossary section

The architecture patterns behind search by meaning, answers grounded in store data and the quality of the top results in the list.

What it is

A practical definition

Vector search finds items by closeness in meaning, and a vector database stores those representations and returns similar results fast.

Example in ecommerce

That is how open-ended queries such as "a gift for a man who runs in winter" still surface products and catalog fragments.

Business impact

Delivers more relevant results for complex, unstructured queries, especially across a large assortment.

Need a working scenario for your catalog, not just a dictionary?

We will show which scenario to start with, how to tie it to metrics and where measurable results come fastest.