In this paper, we investigate the integration of Retrieval Augmented Generation (RAG) with large language models (LLMs) such as ChatGPT, Gemini, and Llama to enhance the accuracy and specificity of responses to complex questions about electricity datasets. Recognizing the limitations of LLMs in generating precise and contextually relevant answers due to their dependency on the patterns in training data rather than factual understanding, we propose a solution that leverages a specialized electricity knowledge graph. This approach facilitates the retrieval of accurate, real-time data which is then synthesized with the generative capabilities of LLMs. Our findings illustrate that the RAG approach not only reduces the incidence of incorrect information typically generated by LLMs but also significantly improves the quality of the output by grounding responses in verifiable data. This paper details our methodology, presents a comparative analysis of responses with and without RAG, and discusses the implications of our findings for future applications of AI in specialized sectors like energy data analysis.

通过结合Retrieval Augmented Generation (RAG)与ChatGPT、Gemini和Llama等大型语言模型 (LLMs)，利用特殊的电力知识图来提高对电力数据集的复杂问题的响应的准确性和特异性。我们的研究结果表明，RAG方法不仅可以减少由LLMs生成的不正确信息的发生，还可以通过以可验证的数据为基础来显著提高输出的质量。

基于RAG的家庭电力监测会话