LightRAG: Simple and Fast Retrieval-Augmented Generation

Papers with Code Trending 10/08/24, 08:00 AM Papers

Summary

The article introduces LightRAG, an open-source framework that enhances Retrieval-Augmented Generation by integrating graph structures for improved contextual awareness and efficient information retrieval.

Retrieval-Augmented Generation (RAG) systems enhance large language models (LLMs) by integrating external knowledge sources, enabling more accurate and contextually relevant responses tailored to user needs. However, existing RAG systems have significant limitations, including reliance on flat data representations and inadequate contextual awareness, which can lead to fragmented answers that fail to capture complex inter-dependencies. To address these challenges, we propose LightRAG, which incorporates graph structures into text indexing and retrieval processes. This innovative framework employs a dual-level retrieval system that enhances comprehensive information retrieval from both low-level and high-level knowledge discovery. Additionally, the integration of graph structures with vector representations facilitates efficient retrieval of related entities and their relationships, significantly improving response times while maintaining contextual relevance. This capability is further enhanced by an incremental update algorithm that ensures the timely integration of new data, allowing the system to remain effective and responsive in rapidly changing data environments. Extensive experimental validation demonstrates considerable improvements in retrieval accuracy and efficiency compared to existing approaches. We have made our LightRAG open-source and available at the link: https://github.com/HKUDS/LightRAG.

Original Article

View Cached Full Text

Cached at: 05/08/26, 08:50 AM

Paper page - LightRAG: Simple and Fast Retrieval-Augmented Generation

Source: https://huggingface.co/papers/2410.05779

Abstract

LightRAG improves Retrieval-Augmented Generation by integrating graph structures for enhanced contextual awareness and efficient information retrieval, achieving better accuracy and response times.

Retrieval-Augmented Generation(RAG) systems enhancelarge language models(LLMs) by integratingexternal knowledge sources, enabling more accurate and contextually relevant responses tailored to user needs. However, existingRAGsystems have significant limitations, including reliance on flat data representations and inadequate contextual awareness, which can lead to fragmented answers that fail to capture complex inter-dependencies. To address these challenges, we propose LightRAG, which incorporatesgraph structuresinto text indexing and retrieval processes. This innovative framework employs adual-level retrievalsystem that enhances comprehensive information retrieval from both low-level and high-level knowledge discovery. Additionally, the integration ofgraph structureswithvector representationsfacilitates efficient retrieval of related entities and their relationships, significantly improving response times while maintaining contextual relevance. This capability is further enhanced by anincremental update algorithmthat ensures the timely integration of new data, allowing the system to remain effective and responsive in rapidly changing data environments. Extensive experimental validation demonstrates considerable improvements in retrieval accuracy and efficiency compared to existing approaches. We have made our LightRAGopen-source and available at the link: https://github.com/HKUDS/LightRAG.