RAG-Stack: Co-Optimizing RAG Quality and Performance From the Vector Database Perspective
This addresses a practical challenge for developers and researchers building efficient and high-quality RAG systems, though it appears incremental as it builds on existing vector database and RAG research.
The paper tackles the problem of jointly optimizing system performance and generation quality in retrieval-augmented generation (RAG) pipelines, proposing RAG-Stack, a three-pillar blueprint that includes an intermediate representation, cost model, and plan exploration algorithm to decouple and co-optimize these aspects.
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.