Module hnsw 

HNSW (Hierarchical Navigable Small World) Index Implementation

HNSW is a graph-based approximate nearest neighbor search algorithm that provides excellent query performance with high recall. It builds a multi-layer graph where:

• Each layer contains a subset of nodes from the layer below
• Top layers enable fast coarse navigation
• Bottom layers provide fine-grained search

Key parameters:

• M: Maximum number of connections per node (default: 16)
• ef_construction: Search width during index building (default: 200)
• ef_search: Search width during query (default: 50)

Structs

HnswConfig

HNSW index configuration

HnswIndex

HNSW Index for approximate nearest neighbor search

HnswStats

Statistics about the HNSW index