# What is ScaNN? Definition and meaning

A library that uses anisotropic quantization to give accurate maximum-inner-product search.

## Definition

**ScaNN**: A library that uses anisotropic quantization to give accurate maximum-inner-product search.

In short: Google's approximate nearest-neighbour library.

## When it is used

High-throughput embedding retrieval.

## Where it fits

ScaNN belongs to **Vector indexes** in the [Generative AI and LLMs](/topics/generative-ai-llms) topic. These are the other terms in the same group:

- **[IVF-PQ](/glossary/ivf-pq)**: Partitions vectors into clusters and compresses them with product quantization to save memory.
- **[DiskANN](/glossary/diskann)**: A graph-based index designed to serve very large vector collections from disk with low memory.

## Learn more

The full guide to **[ScaNN](/tools/scann)** explains how it works, when to use it and how it compares with the alternatives, with examples. The [glossary](/glossary) lists every term on the site from A to Z.

Previous term: [Sandboxing](/glossary/sandboxing) · Next term: [Schema evolution](/glossary/schema-evolution)
