Article:Darren Edge, Ha Trinh, Jonathan Larson
LazyGraphRAG: Graph-Enabled RAG Without Costly Upfront Summarisation
Microsoft Research has unveiled LazyGraphRAG, an architecture combining graph and vector RAG while eliminating expensive upfront LLM summarisation during data indexing. By deferring language model calls to query time, indexing costs drop to standard vector RAG levels.
From Video: Weekly AI Updates: Vulkan, Mojo, Kimi K3, and Emerging Agent Frameworks