In-Memory Neighbor Graph Vector Index

Hierarchical Navigable Small World (HNSW) is the only type of In-Memory Neighbor Graph vector index supported. HNSW graphs are very efficient indexes for vector approximate similarity search. HNSW graphs are structured using principles from small world networks along with layered hierarchical organization.

• Understand Hierarchical Navigable Small World Indexes
  The default type of index created for an In-Memory Neighbor Graph vector index is Hierarchical Navigable Small World (HNSW). Use these examples to understand how to create HNSW indexes for vector approximate similarity searches.
• Hierarchical Navigable Small World Index Syntax and Parameter
  Syntax for Hierarchical Navigable Small World Index
• HNSW Support in RAC Environments
  In a RAC environment using Autonomous Database Serverless (ADB-S) services, it is possible to use Hierarchical Navigable Small World (HNSW) indexes with SELECT statements to run approximate similarity searches.