International Journal of Scientific Research and Engineering Development

The increasing demand for data-driven decision-making has created a need for tools that simplify data analysis for non-technical users. This paper presents the design and implementation of an AI Data Analyst system that enables users to interact with CSV datasets using natural language. The system is built using a Retrieval- Augmented Generation (RAG) architecture, integrating Natural Language Processing (NLP), Machine Learning, and data visualization techniques. The proposed system allows users to upload CSV files and query them conversationally without writing code. It leverages embeddings and vector databases to retrieve relevant data and generates responses using a large language model. Additionally, it supports data visualization and statistical analysis. The system is developed using Python, Streamlit, LangChain, and OpenAI models, ensuring a user-friendly interface and efficient processing. The results demonstrate that the system significantly reduces the complexity of data analysis and enhances accessibility for users with minimal technical expertise.

Shifa Bilal Tamboli, Simeen Phiroj Mulani, Arman Tajuddin Shiakh,"AI Data Analyst: Conversational Data Analysis using Retrieval-Augmented" International Journal of Scientific Research and Engineering Development, V9(2): Page(2346-2347) Mar-Apr 2026. ISSN: 2581-7175. www.ijsred.com. Published by Scientific and Academic Research Publishing.