GitHub user suppersam1 added a comment to the discussion: Vector Search HNSW Indexing Encoding
node_id -> node_data(like neighbors、vector_data、level), neighbors data contain the neighbors of each layer of the node in the hnsw graph, and only store node id. You can refer to implementations such as pgvector or hnswlib. Implementing pure in-memory HNSW using RocksDB's block cache. When block cache enough, the all kv data load in memory. When block cache not enough, queries will also degenerate into disk queries. GitHub link: https://github.com/apache/kvrocks/discussions/2316#discussioncomment-9812681 ---- This is an automatically sent email for [email protected]. To unsubscribe, please send an email to: [email protected]
