In the evolving landscape of educational technology, students face ongoing challenges in accessing timely and accurate academic information. Traditional query resolution systems-ranging from FAQs to administrative desks-are often inefficient. This review paper explores the application of Retrieval-Augmented Generation (RAG) and the LangChain framework to build intelligent, responsive, and domain-specific chatbots for academic institutions. Through the integration of a vector database, retriever modules, and large language models (LLMs), RAG-based systems ensure contextual relevance and data-grounded responses. This paper surveys existing literature, evaluates methodologies, and highlights the significance, implementation strategies, and expected outcomes of such systems in the educational sector.