Recent advancements in generative artificial intelligence (AI) have opened up new opportunities in higher education. A large number of studies have explored the use of educational chatbots in the fields of science, technology, engineering, and mathematics. Although some research has incorporated elements for personalized or adaptive learning, there is still a need for further study on the design and evaluation of personalized adaptive learning chatbots. The focus of this study is the development of an educational chatbot using large language models (LLMs) and retrieval augmented generation (RAG) for the Project 1A module at Esprit (Private Engineering and Technology School). The goal is to improve the learning experience through personalized educational support. The chatbot provides customized assistance, real-time feedback, and adaptive learning paths, acting as an additional tutor for first year engineering students, guiding them through their projects and providing immediate answers and explanations based on course content. This research highlights the potential of enhanced RAG methods to advance the use of LLMs in the module and represents a promising approach to overcoming current challenges in the field.