This research project investigates the application of Large Language Models (LLMs) to automate the creation of Knowledge Graphs (KGs) from textual data across various domains. The primary goal is to develop a versatile solution for constructing KGs using LLMs and visualizing them in an interactive network format, which enables users to explore the knowledge graph interactively. This research has the potential to significantly benefit researchers by streamlining the integration of multiple knowledge sources into a coherent framework with minimal manual intervention. The research findings demonstrate the feasibility of using a pretrained LLM (Google Palm 2) for knowledge extraction in conjunction with prompt engineering techniques for knowledge graph construction. The prototype successfully constructs a comprehensive knowledge graph representing research content. Evaluation of the system with research papers reveals its ability to capture key information and establish meaningful relationships, which are visualized through the generated knowledge graphs. Despite promising results, limitations exist in the LLM's understanding of highly specialized content, particularly regarding transitive logic in research papers. Future work includes refining prompt engineering methods and collaborating with domain experts to improve the process. Additionally, methods for error detection within knowledge graphs should be explored to further advance this automated knowledge graph construction system.