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

# User Guide

Use these guides when you are ready to apply NVIDIA cuVS APIs, benchmark algorithms, or integrate NVIDIA cuVS into a larger product.

## Guides

- [API Guide](/user-guide/api-guides): find task-focused NVIDIA cuVS API examples for clustering, vector indexing, preprocessing, common types, and supporting routines.
- [Benchmarking Guide](/user-guide/benchmarking-guide): learn how to compare vector indexes fairly and use cuVS Bench for reproducible benchmark workflows.
- [Field Guide](/user-guide/field-guide): find practical material for compatibility, integration patterns, runtime compilation, and extension points.
- [Lucene Integration](/user-guide/lucene): accelerate Apache Lucene vector index builds and search on GPUs with the NVIDIA cuVS Lucene codecs.
- [References](/cuvs/user-guide/references): cite the research papers behind NVIDIA cuVS vector search, preprocessing, clustering, and GPU primitives.

## Docs

- [API Guide](https://docs.nvidia.com/cuvs/user-guide/api-guides.md)
- [Common Types](https://docs.nvidia.com/cuvs/user-guide/api-guides/core-types.md)
- [Array Types](https://docs.nvidia.com/cuvs/user-guide/api-guides/core-types/array-types.md)
- [Dense Arrays](https://docs.nvidia.com/cuvs/user-guide/api-guides/core-types/array-types/dense-arrays.md)
- [Sparse Arrays](https://docs.nvidia.com/cuvs/user-guide/api-guides/core-types/array-types/sparse-arrays.md)
- [Memory Management](https://docs.nvidia.com/cuvs/user-guide/api-guides/core-types/memory-management.md)
- [Multi-GPU](https://docs.nvidia.com/cuvs/user-guide/api-guides/core-types/multi-gpu.md)
- [Resources](https://docs.nvidia.com/cuvs/user-guide/api-guides/core-types/resources.md)
- [Clustering Guide](https://docs.nvidia.com/cuvs/user-guide/api-guides/clustering-guide.md)
- [K-Means](https://docs.nvidia.com/cuvs/user-guide/api-guides/clustering-guide/k-means.md)
- [Gaussian Mixture Model](https://docs.nvidia.com/cuvs/user-guide/api-guides/clustering-guide/gaussian-mixture-model.md)
- [Single-linkage](https://docs.nvidia.com/cuvs/user-guide/api-guides/clustering-guide/single-linkage.md)
- [Spectral Clustering](https://docs.nvidia.com/cuvs/user-guide/api-guides/clustering-guide/spectral-clustering.md)
- [Indexing Guide](https://docs.nvidia.com/cuvs/user-guide/api-guides/indexing-guide.md)
- [All-neighbors](https://docs.nvidia.com/cuvs/user-guide/api-guides/indexing-guide/all-neighbors.md)
- [Brute-force](https://docs.nvidia.com/cuvs/user-guide/api-guides/indexing-guide/brute-force.md)
- [CAGRA](https://docs.nvidia.com/cuvs/user-guide/api-guides/indexing-guide/cagra.md)
- [IVF-Flat](https://docs.nvidia.com/cuvs/user-guide/api-guides/indexing-guide/ivf-flat.md)
- [IVF-PQ](https://docs.nvidia.com/cuvs/user-guide/api-guides/indexing-guide/ivf-pq.md)
- [Multi-GPU](https://docs.nvidia.com/cuvs/user-guide/api-guides/indexing-guide/multi-gpu.md)
- [NN-Descent](https://docs.nvidia.com/cuvs/user-guide/api-guides/indexing-guide/nn-descent.md)
- [ScaNN](https://docs.nvidia.com/cuvs/user-guide/api-guides/indexing-guide/sca-nn.md)
- [Vamana](https://docs.nvidia.com/cuvs/user-guide/api-guides/indexing-guide/vamana.md)
- [Preprocessing Guide](https://docs.nvidia.com/cuvs/user-guide/api-guides/preprocessing-guide.md)
- [Binary Quantizer](https://docs.nvidia.com/cuvs/user-guide/api-guides/preprocessing-guide/binary-quantizer.md)
- [PCA](https://docs.nvidia.com/cuvs/user-guide/api-guides/preprocessing-guide/pca.md)
- [Product Quantization](https://docs.nvidia.com/cuvs/user-guide/api-guides/preprocessing-guide/product-quantization.md)
- [Scalar Quantizer](https://docs.nvidia.com/cuvs/user-guide/api-guides/preprocessing-guide/scalar-quantizer.md)
- [Spectral Embedding](https://docs.nvidia.com/cuvs/user-guide/api-guides/preprocessing-guide/spectral-embedding.md)
- [Other APIs](https://docs.nvidia.com/cuvs/user-guide/api-guides/other-ap-is.md)
- [Dynamic Batching](https://docs.nvidia.com/cuvs/user-guide/api-guides/other-ap-is/dynamic-batching.md)
- [K-selection](https://docs.nvidia.com/cuvs/user-guide/api-guides/other-ap-is/k-selection.md)
- [Pairwise Distances](https://docs.nvidia.com/cuvs/user-guide/api-guides/other-ap-is/pairwise-distances.md)
- [Benchmarking Guide](https://docs.nvidia.com/cuvs/user-guide/benchmarking-guide.md)
- [Methodologies](https://docs.nvidia.com/cuvs/user-guide/benchmarking-guide/methodologies.md)
- [cuVS Bench Tool](https://docs.nvidia.com/cuvs/user-guide/benchmarking-guide/cu-vs-bench-tool.md)
- [Introduction](https://docs.nvidia.com/cuvs/user-guide/benchmarking-guide/cu-vs-bench-tool/introduction.md)
- [Installation](https://docs.nvidia.com/cuvs/user-guide/benchmarking-guide/cu-vs-bench-tool/installation.md)
- [Usage](https://docs.nvidia.com/cuvs/user-guide/benchmarking-guide/cu-vs-bench-tool/usage.md)
- [Datasets](https://docs.nvidia.com/cuvs/user-guide/benchmarking-guide/cu-vs-bench-tool/datasets.md)
- [Synthetic Dataset Generation](https://docs.nvidia.com/cuvs/user-guide/benchmarking-guide/cu-vs-bench-tool/synthetic-dataset-generation.md)
- [Backends](https://docs.nvidia.com/cuvs/user-guide/benchmarking-guide/cu-vs-bench-tool/backends.md)
- [Field Guide](https://docs.nvidia.com/cuvs/user-guide/field-guide.md)
- [Compatibility](https://docs.nvidia.com/cuvs/user-guide/field-guide/compatibility.md)
- [Integration Patterns](https://docs.nvidia.com/cuvs/user-guide/field-guide/integration-patterns.md)
- [JIT Compilation](https://docs.nvidia.com/cuvs/user-guide/field-guide/jit-compilation.md)
- [UDF Usage](https://docs.nvidia.com/cuvs/user-guide/field-guide/udf-usage.md)
- [Lucene Integration](https://docs.nvidia.com/cuvs/user-guide/lucene.md)
- [References](https://docs.nvidia.com/cuvs/user-guide/references.md)