The rise of platforms, with multimedia content has driven the advancement of conversational AI systems expanding beyond just text based interactions to include a wide range of media such as PDFs, audio ?les, web links and images. In our study we explore in detail the creation, enhancement and assessment of a chatbot that can handle questions across media formats. By utilizing cutting edge techniques in natural language processing (NLP) information retrieval and processing multimodal data our chatbot sets a standard for improving interactions between humans and computers using types of media. Our primary goal is to examine how effective and user friendly a chatbot that deals with multimedia questions can be in real world situations. We conduct tests to evaluate how well our chatbot interprets user queries retrieves relevant information from various media sources and provides contextually appropriate responses across different formats. Additionally we explore techniques for combining types of media to help the chatbot better understand and synthesize information from various sources creating a more engaging experience, for users.