> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/cuvs/llms.txt.
> For full documentation content, see https://docs.nvidia.com/cuvs/llms-full.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/cuvs/_mcp/server.

# Getting Started

Use these pages to learn what cuVS does, where it fits in a vector-search system, and which guide to read next.

## Introduction

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

## Explore cuVS in context

- [Integrations](/cuvs/getting-started/integrations): see databases, libraries, and data platforms that expose cuVS-backed workflows.
- [Use-cases](/cuvs/getting-started/use-cases): review common vector-search, vector-database, clustering, preprocessing, and exploratory-analysis use-cases.