<![CDATA[Chatbot is a technology designed to assist humans by simulating text or voice based conversations to provide efficient information services powered by Artificial Intelligence. This study addresses the difficulties prospective interns face in finding internship information at the Central Java Regional Police and the lack of prompt responses from office staff, which often results in delays in information delivery due to manual processing. Many prospective applicants also feel confused about how to inquire regarding the registration process, required qualifications, and other important details. To address these issues, this research was conducted to develop a web-based internship system equipped with an advanced chatbot implementing the Retrieval Augmented Generation (RAG) method and integrated with a vector database for semantic retrieval. This platform ensures that all information provided is relevant and accurate by providing real-time responses based on the agency’s official documents. Based on functional testing, the system achieves an accuracy rate of 93.3% with and average response latency of 1.8 seconds. This research significantly improves access to information and demonstrates how the RAG framework effectively mitigates LLM hallucinations, ensuring data integrity within highly regulated public service.]]>
Copyrights © 2026
