Design and Development of a Web-Based Library Chatbot with Integration of a Local Database (MySQL) and Artificial Intelligence Services (OpenAI API)
Academic libraries increasingly require intelligent digital services to improve information accessibility, responsiveness, and service efficiency. However, conventional FAQ-based chatbots often suffer from limited semantic understanding, while fully AI-based systems may introduce higher latency and inconsistent institutional responses. This study aims to design and evaluate a hybrid web-based library chatbot integrating a local MySQL FAQ database with OpenAI API services to support digital library services at Universitas Negeri Padang (UNP). The system was developed using a hybrid architecture combining semantic FAQ retrieval and AI-based fallback generation. The implementation utilized HTML, CSS, JavaScript, Node.js, and MySQL, while Bahasa Indonesia Natural Language Processing (NLP) techniques, including normalization, tokenization, stopword removal, and stemming, were applied to improve semantic query matching. Evaluation was conducted using 100 library-related queries, validated by three experts: senior librarians and an information systems lecturer. Experimental results demonstrated that the proposed hybrid chatbot achieved 92% response correctness accuracy with a 95% confidence interval ranging from 86.7% to 97.3%. Routing evaluation also confirmed effective query classification between local FAQ retrieval and AI fallback mechanisms, while benchmarking experiments showed that the proposed architecture outperformed keyword-based FAQ systems, semantic retrieval-only models, and pure LLM-based chatbots in terms of response accuracy and balanced response latency. The findings indicate that integrating semantic retrieval with AI-based fallback mechanisms can improve response quality, scalability, and contextual relevance in academic library services. Future research may focus on adaptive threshold optimization, multilingual support, and domain-specific prompt engineering to further enhance routing precision and the generation of contextual responses.