MiniRAG: Towards Extremely Simple Retrieval-Augmented Generation
This addresses the challenge of deploying efficient RAG systems in resource-constrained scenarios, representing a strong specific gain rather than a foundational advancement.
The paper tackles the problem of performance degradation in Retrieval-Augmented Generation (RAG) systems when using Small Language Models (SLMs) by introducing MiniRAG, which achieves comparable performance to LLM-based methods while using only 25% of the storage space.
The growing demand for efficient and lightweight Retrieval-Augmented Generation (RAG) systems has highlighted significant challenges when deploying Small Language Models (SLMs) in existing RAG frameworks. Current approaches face severe performance degradation due to SLMs' limited semantic understanding and text processing capabilities, creating barriers for widespread adoption in resource-constrained scenarios. To address these fundamental limitations, we present MiniRAG, a novel RAG system designed for extreme simplicity and efficiency. MiniRAG introduces two key technical innovations: (1) a semantic-aware heterogeneous graph indexing mechanism that combines text chunks and named entities in a unified structure, reducing reliance on complex semantic understanding, and (2) a lightweight topology-enhanced retrieval approach that leverages graph structures for efficient knowledge discovery without requiring advanced language capabilities. Our extensive experiments demonstrate that MiniRAG achieves comparable performance to LLM-based methods even when using SLMs while requiring only 25\% of the storage space. Additionally, we contribute a comprehensive benchmark dataset for evaluating lightweight RAG systems under realistic on-device scenarios with complex queries. We fully open-source our implementation and datasets at: https://github.com/HKUDS/MiniRAG.