Proceedings of the International Conference on Intelligent Systems and Digital Transformation (ICISD 2025)

<Previous Article In Volume
Next Article In Volume>

AI-powered Document Chatbot for data retrieval

Authors
Meera Raj1, *, R. Srinivasan2
1Student, Dept of Data Science and Business Systems, SRM Institute of Science and Technology, Chennai, India
2Associate Professor, Dept of Computing Technologies, SRM Institute of Science and Technology, Chennai, India
*Corresponding author. Email: meera.kiran85@gmail.com
Corresponding Author
Meera Raj
Available Online 31 October 2025.
DOI
10.2991/978-94-6463-866-0_55How to use a DOI?
Abstract

With the increasing volume of structured data across enterprises, efficient data retrieval and analysis have become critical challenges. This paper presents an AI-powered document chatbot that enables seamless data access using a Retrieval-Augmented Generation (RAG) architecture. The chatbot leverages GPT-4 Omni for natural language understanding and query generation, while FAISS vector database is employed for efficient metadata retrieval. An AI Agent orchestrates the retrieval and execution of SQL queries and Python scripts based on user input. The system supports user-based authentication and authorization, implemented via DB2, ensuring secure access to structured data stored in DB2 for SQL queries and Excel files for Python-based operations. Users interact through a Streamlit-based frontend, where the chatbot dynamically generates SQL queries for DB2 database execution or Python scripts for Excel data processing. The integration of LangChain enhances context awareness, improving query accuracy. Experimental results demonstrate that the chatbot streamlines data retrieval, reducing technical barriers for users with limited SQL or Python expertise. Hence unlike traditional RAG-based chatbots, Data Chatbot integrates hybrid execution support (SQL via DB2, Python via Excel), role-based metadata restriction with FAISS vector loading, LangChain-based contextual awareness and real-time query execution with error handling. This approach offers a scalable and intelligent solution for enterprise data access, enhancing operational efficiency and decision-making.

Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the International Conference on Intelligent Systems and Digital Transformation (ICISD 2025)
Series
Atlantis Highlights in Intelligent Systems
Publication Date
31 October 2025
ISBN
978-94-6463-866-0
ISSN
2589-4919
DOI
10.2991/978-94-6463-866-0_55How to use a DOI?
Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Meera Raj
AU  - R. Srinivasan
PY  - 2025
DA  - 2025/10/31
TI  - AI-powered Document Chatbot for data retrieval
BT  - Proceedings of the International Conference on Intelligent Systems and Digital Transformation (ICISD 2025)
PB  - Atlantis Press
SP  - 668
EP  - 681
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6463-866-0_55
DO  - 10.2991/978-94-6463-866-0_55
ID  - Raj2025
ER  -