Implementasi Retrieval-Augmented Generation dan Semantic Search pada Chatbot Artificial Intelligence Berbasis Web untuk Optimalisasi Layanan Akademik

Abstract

Academic information services in higher education institutions still face various obstacles, such as delays in information delivery, limited access to services, and high administrative burdens due to repetitive student inquiries. This study aims to implement Retrieval-Augmented Generation (RAG) and Semantic Search technology in a web-based Artificial Intelligence chatbot to optimize academic services at the Faculty of Engineering, Hamzanwadi University. The research method used is Design Science Research (DSR), which includes data collection, system requirements analysis, design, implementation, testing, and system evaluation. The chatbot's knowledge base is built from academic documents such as academic guidelines, service SOPs, academic calendars, scholarship information, and other administrative documents. The system was developed using an integration of LangChain, Azure OpenAI Service, Azure AI Search, FastAPI, Next.js, and Supabase. Semantic Search techniques are used to perform vector embedding-based searches, while RAG is utilized to generate contextual answers based on relevant documents. Test results show that all key system features performed well with a 100% success rate in unit testing. A user satisfaction evaluation using the Customer Satisfaction Index (CSI) method with 54 respondents yielded a score of 89.34%, categorized as "Very Satisfied," with a Mean Satisfaction Score above 4.37 on a maximum scale of 5.0. The AI ​​chatbot successfully addressed traditional academic information service issues by providing 24/7 service, reducing the workload of campus staff, and ensuring information consistency through RAG technology.