HFresh: Memory-Efficient Vector Search | Weaviate

This post details the implementation of HFresh, Weaviate's disk-based vector index. It explains the two-stage search strategy using an in-memory HNSW centroid index (with RQ8 quantization for 4x memory reduction) to route queries to disk-based postings (using RQ1 quantization for up to 32x data reduction). It also elaborates on the background maintenance operations (splitting, merging, reassigning postings) that ensure index freshness and balance without full rebuilds, and the rationale for using HNSW as the centroid index.