Your RAG can't answer 'why' -- GraphRAG finds what vector search misses

This article explores the limitations of conventional RAG (Retrieval-Augmented Generation) systems, which struggle to answer 'why' questions because vector search only finds similar documents, not related ones. It introduces GraphRAG as a solution to overcome this 'structural ceiling' by connecting the dots between pieces of information. The author shares a personal anecdote about realizing this architectural bottleneck after failed attempts to rewrite prompts.