product
Data quality: Editorially ReviewedFree
Retrieval & data layer
Vector Databases
Software & technology
Workflow orchestration
Self-hosted / on-premises
Retrieval & semantic search
ScaNN
Vector Databases
Overview
ScaNN (Scalable Nearest Neighbors) is Google's open-source library for efficient vector similarity search. It uses anisotropic vector quantization and provides state-of-the-art performance on billion-scale datasets. ScaNN supports multiple distance metrics, partitioning strategies, and is optimized for both memory and speed in production retrieval pipelines.
- Pricing model
- Free
- Deployment
- Self-hosted / on-premises
- Regions served
- Global
- Categories
- Free, Retrieval & data layer, Vector Databases, Software & technology, Workflow orchestration, Self-hosted / on-premises, Retrieval & semantic search
- Last updated
- 2 October 2026
- Published
- 2 October 2026
Use cases
Workflow orchestration
Deployment options
Self-hosted / on-premises
Data sources & provenance
Where this information came from, how it was checked and when it was last looked at. “Last updated” records a change to the record — it does not mean the record was verified.
- Data quality
- Data quality: Editorially Reviewed
- Primary source
- github.com
- Sources cited
- 2
- Last reviewed
- 28 September 2026
- Last updated
- 2 October 2026
Spotted something out of date?
Anyone can suggest a correction — you don't need an account. An editor checks every suggestion against the sources before the record changes.