<![CDATA[The rapid advancement of artificial intelligence, particularly Large Language Models (LLMs), has driven the development of chatbots capable of generating more natural and interactive conversations. However, general-purpose chatbots still have limitations in providing personalized interactions that meet users' specific needs. This study aims to design and implement an open-domain chatbot based on a Large Language Model (LLM) and Retrieval-Augmented Generation (RAG) with mood personalization and response tone features. The system was developed as a web-based application using an LLM as the response generator and a keyword-based RAG mechanism to provide additional context from a knowledge base. The novelty of this research lies in the integration of the RAG mechanism, mood personalization, response tone selection, and a safety layer within a single chatbot system designed to deliver a more personalized and secure conversational experience. System evaluation was conducted through response time testing and user acceptance testing using the Technology Acceptance Model (TAM). The results indicate that all designed features were successfully implemented and that the system was capable of generating responses across various conversational scenarios. Furthermore, the evaluation demonstrated a high level of user acceptance in terms of perceived usefulness, perceived ease of use, attitude toward using, and behavioral intention to use. Therefore, the developed chatbot was successfully implemented and can serve as a digital interaction medium that leverages LLM and RAG technologies to provide a more personalized conversational experience for users.]]>
