提升知识图谱检索效率，速度比现有方法快100倍
E^2GraphRAG: Streamlining Graph-based RAG for High Efficiency and Effectiveness
- 用大模型生成摘要树，用SpaCy构建实体图并双向索引
- 检索时自适应选择局部或全局模式，速度提升100倍
- 适合需要快速精准回答的实时问答场景
基于图的RAG方法如GraphRAG通过构建分层实体图展现出对知识库的全局理解能力，但常因效率低下且依赖人工预设查询模式而限制实际应用。本文提出E^2GraphRAG，一种高效高效果的图结构RAG框架。索引阶段，利用大语言模型构建摘要树，基于SpaCy构建实体图，并在实体与文本块之间建立双向索引，以捕捉多对多关系，实现本地和全局检索的快速查找。检索阶段设计自适应策略，结合图结构动态选择局部或全局检索模式。实验表明，E^2GraphRAG的索引速度相比GraphRAG提升最高达10倍，检索速度相较LightRAG提速100倍，同时保持了具有竞争力的问答性能。
原文摘要 · Abstract (English)
Graph-based RAG methods like GraphRAG have shown promising global understanding of the knowledge base by constructing hierarchical entity graphs. However, they often suffer from inefficiency and rely on manually pre-defined query modes, limiting practical use. In this paper, we propose E^2GraphRAG, a streamlined graph-based RAG framework that improves both Efficiency and Effectiveness. During the indexing stage, E^2GraphRAG constructs a summary tree with large language models and an entity graph with SpaCy based on document chunks. We then construct bidirectional indexes between entities and chunks to capture their many-to-many relationships, enabling fast lookup during both local and global retrieval. For the retrieval stage, we design an adaptive retrieval strategy that leverages the graph structure to retrieve and select between local and global modes. Experiments show that E^2GraphRAG achieves up to 10 times faster indexing than GraphRAG and 100 times speedup over LightRAG in retrieval while maintaining competitive QA performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。