提出RAG-Stack框架，协同优化检索生成系统的质量和性能。
RAG-Stack: Co-Optimizing RAG Quality and Performance From the Vector Database Perspective
- 设计中间表示RAG-IR，解耦质量与性能优化
- 构建成本模型RAG-CM，预估不同配置的系统性能
- 开发搜索算法RAG-PE，自动寻找高质量高效率配置
检索增强生成（RAG）已成为向量数据库最重要的应用之一。通过将从数据库中检索到的文档融入大语言模型（LLM）的提示中，RAG能够生成更可靠、信息更丰富的内容。尽管向量数据库已有大量研究，但在端到端RAG流水线的背景下仍存在诸多未解难题。其中一个实际而关键的挑战是如何在系统性能与生成质量之间实现联合优化，这远比表面复杂，涉及算法（模型与数据库）和系统（软硬件）层面的多重可调参数。本文提出RAG-Stack，一个三支柱的协同优化蓝图：(1) RAG-IR，一种中间表示，作为抽象层解耦质量与性能；(2) RAG-CM，用于根据RAG-IR估算系统性能的成本模型；(3) RAG-PE，一种计划探索算法，用于搜索高质量且高性能的RAG配置。我们相信该三支柱框架将成为未来几年RAG质量-性能协同优化的行业标准。
原文摘要 · Abstract (English)
Retrieval-augmented generation (RAG) has emerged as one of the most prominent applications of vector databases. By integrating documents retrieved from a database into the prompt of a large language model (LLM), RAG enables more reliable and informative content generation. While there has been extensive research on vector databases, many open research problems remain once they are considered in the wider context of end-to-end RAG pipelines. One practical yet challenging problem is how to jointly optimize both system performance and generation quality in RAG, which is significantly more complex than it appears due to the numerous knobs on both the algorithmic side (spanning models and databases) and the systems side (from software to hardware). In this paper, we present RAG-Stack, a three-pillar blueprint for quality-performance co-optimization in RAG systems. RAG-Stack comprises: (1) RAG-IR, an intermediate representation that serves as an abstraction layer to decouple quality and performance aspects; (2) RAG-CM, a cost model for estimating system performance given an RAG-IR; and (3) RAG-PE, a plan exploration algorithm that searches for high-quality, high-performance RAG configurations. We believe this three-pillar blueprint will become the de facto paradigm for RAG quality-performance co-optimization in the years to come.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。