Tokyo: Kioxia Corporation, a leader in memory solutions, has announced the open-source release of its All-in-Storage ANNS with Product Quantization (AiSAQ) technology. This innovative "approximate nearest neighbor" search algorithm is designed for SSDs, aiming to enhance scalable performance for retrieval-augmented generation (RAG) without the need for DRAM storage, by enabling direct searches on SSDs.

According to BERNAMA News Agency, generative AI systems require considerable compute, memory, and storage resources. While these systems hold potential for significant advancements across industries, their deployment is often associated with high costs. RAG plays a vital role in refining large language models (LLMs) with data tailored to specific companies or applications.