Research Article: Latency-Aware RAG with Freshness-Constrained Caches
Abstract
We design a RAG controller that routes between cache hits, stale-but-usable snippets, and live retrieval using freshness SLAs, cutting mean cost by 17% at stable accuracy.
Cite this article
Hill, E. (2024). Research Article: Latency-Aware RAG with Freshness-Constrained Caches. Research Explorations in Global Knowledge & Technology (REGKT), 3 (10). Retrieved from https://regkt.com/article.php?id=281&slug=latency-aware-rag-freshness-constrained-caches