Chatbots have become the de facto interface for many of the web portals to facilitate user interactions. While the large language models are being integrated to organizational knowledge sources to develop chatbots, providing the most relevant and up-to-date information to the satisfaction of users always remains a challenge. In this paper, an attempt has been made to develop an AI-powered chatbot by augmenting a recommender system for personalized, context-aware assistance. Utilizing machine learning (ML), retrieval-augmented generation (RAG), and natural language processing (NLP), the chatbot dynamically adapts to user interactions. It enhances support by integrating OpenAI’s GPT-4, semantic search, vector databases, and knowledge graphs. Experimental results demonstrate improved response accuracy, reduced “no information available” instances, and enhanced user satisfaction. This research contributes to AI-driven automation across various domains, including customer service, healthcare, and business operations.