In our 9.1 release, SingleStore has approximately halved storage costs and reduced compute costs by almost 40%, while maintaining similar recall!

SingleStore Blog offers insights, tutorials, and updates on SingleStore, a distributed SQL database used for real-time analytics and data warehousing. Covering topics such as database architecture, performance tuning, and SQL queries, SingleStore Blog provides resources for developers and database administrators. Developers can learn about building scalable and high-performance applications with SingleStore by following their blog.

SingleStore

SingleStore 9.1 introduces the VECTOR(<N>, F16) data type, enabling 16-bit floating point storage for vector embeddings. Benchmarks on the GIST 1M dataset show F16 cuts storage by ~50% (1.79GB vs 3.58GB) and speeds up exact kNN queries by ~38% compared to F32, while maintaining statistically equivalent recall (~96-98%). ANN index search times also improve slightly due to better cache utilization. The post explains why F16 precision is sufficient for most vector search use cases (semantic search, RAG), covers migration steps from F32 to F16, and notes that F32 remains preferable for high-precision domains like finance or medical imaging.

Float16 Vector Type Support in SingleStore: Cheaper, Faster, Better