Indexing Guide

Use these guides for cuVS nearest-neighbor indexing APIs, from exact search baselines to GPU-accelerated approximate indexes.

• All-neighbors: compute all-neighbors graph structures.
• Brute-force: compare every query against every vector for exact nearest-neighbor search.
• CAGRA: build and search GPU-optimized graph indexes.
• IVF-Flat: partition vectors into inverted-file lists while storing full-precision vectors.
• IVF-PQ: combine inverted-file partitioning with product quantization for compact indexes.
• Multi-GPU: distribute supported nearest-neighbor indexes across multiple GPUs.
• NN-Descent: build approximate nearest-neighbor graphs with an iterative algorithm.
• ScaNN: combine partitioning, quantization, and refinement for high-quality approximate search.
• Vamana: build graph indexes designed for large-scale and disk-backed search workflows.