Tokyo: Kioxia Corporation, a leader in memory solutions, has announced an update to its KIOXIA All-in-Storage ANNS with Product Quantisation (AiSAQ) software. The update aims to enhance the usability of artificial intelligence (AI) vector database searches within retrieval-augmented generation (RAG) systems by optimizing the use of solid-state drives (SSDs).

According to BERNAMA News Agency, this new open-source release introduces flexible controls that allow system architects to define the balance between search performance and the number of vectors, which are opposing factors in the fixed capacity of SSD storage in the system. Kioxia stated that the update enables architects of RAG systems to fine-tune the optimal balance of specific workloads and their requirements without any hardware modifications.

First introduced in January, KIOXIA AiSAQ software employs a novel approximate nearest neighbour search (ANNS) algorithm optimized for SSDs, eliminating the need to store index data in dynamic random-access memory (DRAM). By enabling vector searches directly on SSDs and reducing host memory requirements, the technology allows vector databases to scale largely without the restrictions caused by limited DRAM capacity.

This update makes KIOXIA AiSAQ technology a suitable SSD-based ANNS for not only RAG applications but also other vector-intensive applications such as offline semantic searches. With growing demand for scalable AI services, SSDs offer a practical alternative to DRAM for managing the high throughput and low latency that RAG systems require.

KIOXIA AiSAQ software efficiently meets these demands, enabling large-scale generative AI without being constrained by limited memory resources. With the release of KIOXIA AiSAQ software as open-source, Kioxia reinforces its commitment to the AI community by promoting SSD-centric architectures for scalable AI.