Knowledge Graphs (KGs) are essential for the functionality of GraphRAGs, a form of Retrieval-Augmented Generative Systems (RAGs) that excel in tasks requiring structured reasoning and semantic understanding. However, creating KGs for GraphRAGs remains a significant challenge due to accuracy and scalability limitations of traditional methods. This paper introduces a novel approach leveraging large language models (LLMs) like GPT-4, LLaMA 2 (13B), and BERT to generate KGs directly from unstructured data, bypassing traditional pipelines. Using metrics such as Precision, Recall, F1-Score, Graph Edit Distance, and Semantic Similarity, we evaluate the models' ability to generate high-quality KGs. Results demonstrate that GPT-4 achieves superior semantic fidelity and structural accuracy, LLaMA 2 excels in lightweight, domain-specific graphs, and BERT provides insights into challenges in entity-relationship modeling. This study underscores the potential of LLMs to streamline KG creation and enhance GraphRAG accessibility for real-world applications, while setting a foundation for future advancements.

Knowledge graphs enable us to comprehend how different points of knowledge relate, giving us an extensive understanding of a field or topic. These graphs help us to discern how individual pieces of knowledge come together to form the larger picture. Clearly, constructing and visualising knowledge graphs can be an effective approach to many fields. In this article, we describe a process to generate new knowledge graphs by leveraging the largest publicly available graph that deals with human knowledge: Wikipedia. We will fully automate the generation process with Python, allowing us to create a scalable approach to generating knowledge graphs for any field of interest.