Single Store Vector Search Index: Architecture and Memory Efficiency

Hi all - I’m Marko, CTO at Memgraph. The author of this post, David, also works at Memgraph.

This post explains how our vector index is implemented within the same storage engine as the graph (eliminating the need for a separate vector store), how we avoid double vector storage, and how scalar type choices (f32/f16/etc) affect memory usage. It also covers some implementation details (USearch-backed index, concurrency, and recovery behavior).

We included a benchmark on 1M nodes with 1024-dim embeddings comparing versions 3.7.2 and 3.8.0, and saw large RAM reductions in the newer version while keeping load and response times similar. Happy to answer technical questions.