Creation of RAG Chatbot in Answering Queries Related to Banking Terms Using Microsoft Azure

This study investigates the use of Natural Language Processing (NLP), specifically Large Language Models (LLM), to implement technology intelligence as a solution for supporting developers in understanding information-related terms, abbreviations, and business processes in the banking sector. The aim is to explore the effectiveness of integrating AI-powered chatbots, particularly through Retrieval Augmented Generation (RAG), to enhance software development in banking by providing fast, accurate responses. The methodology involves profiling data analysis and the development of a RAG based AI chatbot using the Microsoft Azure platform, integrating advanced NLP and LLM techniques to assist developers in navigating complex banking terms and processes efficiently. The results demonstrate that the RAG chatbot significantly improves operational efficiency by offering real-time, context-aware responses, enabling faster decision-making and reducing time spent on manual searches for information, which leads to faster software development cycles. This study contributes to the fields of NLP and LLM, particularly in the banking sector, by showcasing the benefits of RAG chatbots in improving operational efficiency and software development quality. The use of AI technologies provides substantial improvements in the development process, leading to enhanced productivity in the banking industry.