Warehouse Chatbot

This paper presents a chatbot system designed to simplify warehouse inventory checks using a combination of rule-based item search and natural language fallback responses. The system is built using the Streamlit framework for the user interface, Pandas for stock data processing, and OpenAI’s GPT-3.5 model to handle queries beyond item matching. Stock quantities are loaded from a CSV file, and queries such as "How many laptops are in stock?" are matched against known inventory items. If no direct match is found, the chatbot leverages GPT-3.5 to provide a relevant, conversational fallback response. A dark-themed, responsive UI ensures ease of interaction. The project emphasizes real-time usability, scalability, and minimal system resource usage.