#206
The use of retrieval-augmented generation (RAG) to retrieve relevant information from an external knowledge source enables large language models (LLMs) to answer questions over private and/or previously unseen document collections. However, RAG fails on global questions directed at an entire text corpus, such as "What are the main themes in the dataset?", since this is inherently a query-focused summarization (QFS) task, rather than an explicit retrieval task. Prior QFS methods, meanwhile, fail to scale to the quantities of text indexed by typical RAG systems. To combine the strengths of these contrasting methods, Graph RAG is proposed for question answering over private text corpora that scales with both the generality of user questions and the quantity of source text to be indexed. Graph RAG uses an LLM to build a graph-based text index in two stages: first to derive an entity knowledge graph from the source documents, then to pregenerate community summaries for all groups of closely-related entities. Given a question, each community summary is used to generate a partial response, before all partial responses are again summarized in a final response to the user. For a class of global sense-making questions over datasets in the 1 million token range, Graph RAG leads to substantial improvements over a naive RAG baseline for both the comprehensiveness and diversity of generated answers.
In this video, I talk about the following: How does the GraphRAG pipeline look like? How does GraphRAG perform?
For more details, please look at https://arxiv.org/pdf/2404.16130 and https://aka.ms/graphrag
Edge, Darren, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, and Jonathan Larson. "From local to global: A graph rag approach to query-focused summarization." arXiv preprint arXiv:2404.16130 (2024).