ScalableRAG: High-Quality RAG at Zero Ingestion Cost
This work addresses the trade-off between performance and scalability in traditional retrieval-augmented generation (RAG) approaches, which often rely on costly knowledge ingestion processes such as constructing knowledge graphs or SQL tables. The authors propose Zero-Ingestion ScalableRAG, a novel framework that enables real-time aggregative reasoning over readable and writable document and value-set workspaces without requiring vector databases or preprocessing. They further introduce Limited-Ingestion ScalableRAG, which integrates a lightweight vector store with automated schema discovery to enhance accuracy at scale. This approach achieves high-quality RAG inference with zero ingestion cost and ensures scalability through a constant-level LLM invocation mechanism. Evaluated on six benchmark datasets, the method significantly outperforms all baselines—including knowledge graph–based approaches—on three datasets and matches near-optimal performance on the rest, surpassing the second-best baseline by an average accuracy margin of 7.36%.