Universities frequently face challenges in delivering timely, accurate information across key domains such as academics, admissions, and campus resources, leading to confusion and inefficiencies for students, faculty, and parents. Outdated or fragmented data on courses, exams, and essential services exacerbates this issue, making it difficult to navigate admissions processes and access critical resources, including faculty information. This project develops a chatbot driven by a retrieval-augmented generation (RAG) large language model (LLM) to address the difficulties of increasing accessibility and accuracy in offering academic and administrative help. The study investigates how this system can efficiently provide trustworthy, up-to-date information on subjects including faculty, admissions, academics, and campus amenities. By sourcing up-to-date information from trusted university databases and external sources, the chatbot offers detailed academic support, including courses, syllabi, exam schedules, and grading policies. It simplifies admissions by guiding prospective students through eligibility, deadlines, and application procedures. Additionally, it centralized access to information about key campus resources like libraries, labs, and research centers, while offering comprehensive faculty profiles, including specialization insights. In order to continuously improve results and guarantee accuracy and relevance, the methodology incorporates interactive elements and user input. According to preliminary results, the chatbot optimizes the entire campus experience by increasing user engagement and decreasing inefficiencies.