HyperspaceDB 3.1 claims much lower RAM use for AI search
HyperspaceDB 3.1.0 is a new release aimed at reducing memory problems in used for and . A common problem is that large 1536-dimension vectors plus JSON metadata can take a lot of RAM, and very large collections can run out of memory. The new engine does not keep each full vector in RAM.
It keeps a smaller 129-dimension navigation core in fast RAM, then loads the heavier 672-dimension semantic part from NVMe storage when it needs to re-rank the final top results. In the published stress test with 100,000 vectors, HyperspaceDB used about 72 MB of RAM, compared with more than 3,000 MB for Chroma and about 1,700 MB for Milvus. It also adds an 801-dimension hybrid vector design for data with hierarchy, such as legal codes or medical trees.
That design combines Lorentz and Euclidean methods.
Key points
- HyperspaceDB 3.1.0 targets search for and .
- It keeps only a 129-dimension navigation core in RAM.
- It loads the heavier 672-dimension semantic part from NVMe storage for final re-ranking.
- Its own test reports about 72 MB of RAM for 100,000 vectors.
- The release compares that with more than 3,000 MB for Chroma and about 1,700 MB for Milvus.