Published Paper Details:

In today's data-centric landscape, effective database interaction is vital for informed decision-making. However, traditional querying methods require technical expertise in Structured Query Language (SQL), creating a barrier for non-technical users. This project proposes a user-friendly solution that enables natural language interaction with SQL databases, thereby democratizing access to structured data. We present a Streamlit-based web application that integrates LangChain agents with a large language model (LLM). This architecture allows users to input conversational prompts, which are interpreted and translated into executable SQL queries. The system removes the need for SQL proficiency, offering a simplified, scalable, and intuitive interface for data retrieval. Amid rapid advancements in AI and natural language processing (NLP), this solution exemplifies practical application by transforming complex database interactions into accessible tasks. It serves both technical and non-technical users, such as data analysts, decision-makers, and business professionals, enabling them to derive insights independently and efficiently. By reducing reliance on IT specialists and facilitating rapid data access, the proposed system contributes to more agile and datadriven business processes. Its design prioritizes usability, flexibility, and real-world applicability, addressing a growing need for intelligent, inclusive database tools in modern digital environments.