E^2GraphRAG: Streamlining Graph-based RAG for High Efficiency and Effectiveness
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918047278694400 |
|---|---|
| author | Zhao, Yibo Zhu, Jiapeng Guo, Ye He, Kangkang Li, Xiang |
| author_facet | Zhao, Yibo Zhu, Jiapeng Guo, Ye He, Kangkang Li, Xiang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_24226 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | E^2GraphRAG: Streamlining Graph-based RAG for High Efficiency and Effectiveness Zhao, Yibo Zhu, Jiapeng Guo, Ye He, Kangkang Li, Xiang Artificial Intelligence 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. |
| title | E^2GraphRAG: Streamlining Graph-based RAG for High Efficiency and Effectiveness |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2505.24226 |