Introduction

Start here to learn the main concepts behind NVIDIA cuVS, how they fit together, and which guide to read next.

Vector Search: learn the main index families, how they trade recall for performance, and where to start when choosing an index.
Clustering: compare clustering methods, including why K-Means is often the preferred partitioning method for large vector search systems.
Vector Compression: compare quantization and dimensionality reduction methods for reducing vector storage, bandwidth, and search cost.
Vector Database: understand the difference between a vector index and a vector database, including local, global, and hybrid partitioning.
Tuning Indexes: tune standalone indexes and vector databases for recall, latency, throughput, build time, and memory.

Start here to learn the main concepts behind NVIDIA cuVS, how they fit together, and which guide to read next.

Vector Search: learn the main index families, how they trade recall for performance, and where to start when choosing an index.
Clustering: compare clustering methods, including why K-Means is often the preferred partitioning method for large vector search systems.
Vector Compression: compare quantization and dimensionality reduction methods for reducing vector storage, bandwidth, and search cost.
Vector Database: understand the difference between a vector index and a vector database, including local, global, and hybrid partitioning.
Tuning Indexes: tune standalone indexes and vector databases for recall, latency, throughput, build time, and memory.