Perspective: Cost Governance for RAG Systems�Index, Cache, or Call
Abstract
We propose policies that decide between retrieval, local cache, or direct LLM calls using confidence, decay, and cost curves.
Cite this article
Perez, M. (2024). Perspective: Cost Governance for RAG Systems�Index, Cache, or Call. Research Explorations in Global Knowledge & Technology (REGKT), 3 (6). Retrieved from https://regkt.com/article.php?id=258&slug=perspective-cost-governance-rag-index-cache-call