Review: Cost-Aware RAG�Caching, Pruning, and Budgeted Calls
Abstract
We review RAG cost levers: snippet caching, pruning, and budgeted reranking; we report CSAT-neutral savings across 4 deployments.
Cite this article
Li, D. & Rao, W. (2023). Review: Cost-Aware RAG�Caching, Pruning, and Budgeted Calls. Research Explorations in Global Knowledge & Technology (REGKT), 2 (10). Retrieved from https://regkt.com/article.php?id=547&slug=review-cost-aware-rag-caching-pruning-budgeted-calls