https://doi.org/10.1051/epjconf/202532605011
Generative AI at the heart of the concerns of the renewable energy sector in Morocco: Development of AI assistants and analysis between vector database and rag using knowledge graph
1 Professor at Abdelmalek Essaadi University, Research laboratory Innovative Systems Engineering, Morocco.
2 Doctoral Student at Abdelmalek Essaadi University, Research team in Management & Dynamics of organizations, Morocco.
3 Professor at Abdelmalek Essaadi University, Information and Communication Technologies Laboratory, Morocco.
4 Professor at Abdelmalek Essaadi University, Research team in Management & Dynamics of organizations, Morocco.
* Corresponding author: abennani@uae.ac.ma
Published online: 21 May 2025
The Continuous progress in the field of generative artificial intelligence is now helping to change our behavior. It’s pushing us to think about how best to leverage this technology. The renewable energy sector in Morocco is attracting particular attention from the King and the government. In this context, the idea is to develop an expert AI assistant in this field in Morocco. This assistant will be able to answer questions relating to this sector by providing precise answers. In this sense, and in order to make the right choice about the technology we’re going to adopt for this project of creating an expert AI assistant, the idea of this paper revolves around implementing a comparison between two assistants: one using RAG and working with a vector database, and the second using another RAG-based technology exploiting the knowledge graph. Having developed both assistants. We’ll implement them using the same data relating to government renewable energy strategies and the recommendations of the new development model report published in 2021 in the energy sector and others. We will then compare the responses of each assistant and evaluate the relevance of each using the BERTScore parameter.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
