Data Analyst Agent with Flowise using PS-SQL

Pragati Fatinge; Nitin Mahesh Diwewar; Nikhil kumar; Paras Bhupendra Tembhare; Mitesh Vijay Baryekar

Data Analyst Agent with Flowise using PS-SQL

Author(s)	Dr. Pragati Fatinge, Mr. Nitin Mahesh Diwewar, Mr. Nikhil kumar, Mr. Paras Bhupendra Tembhare, Mr. Mitesh Vijay Baryekar
Country	India
Abstract	Traditionally, gaining access to relational databases has required a knowledge of Structured Query Language (SQL) and a clear understanding of the underlying database schemas, which presents a significant operational hurdle for people who are not technical. Although conversational Text-to-SQL systems based on Large Language Models (LLMs) provide a way of allowing natural language queries to be sent to databases, conventional implementations generally suffer from schema hallucination, ambiguous mappings between tokens and attributes, and failures when carrying out complex relational joins. In this paper, a conversational Data Analyst Agent is presented, the agent having been developed using the Flowise visual orchestration framework together with Phrase-based Schema Linking (PS-SQL). The architecture in question makes use of an autonomous Thought-Action-Observation loop which correctly matches natural language expressions to the various elements of the relational schema (such as tables, views, and attributes) in order to produce SQL queries that are both syntactically valid and ready for execution. The framework includes Retrieval-Augmented Generation (RAG) so that it can refer to auxiliary unstructured enterprise documentation (for example, data dictionaries, PDFs, and CSV records) and makes use of Python libraries (Pandas, Matplotlib, Seaborn) to automate the process of analytical synthesis as well as the production of graphical dashboards. By maintaining conversational memory throughout multiple turns of interaction and by offering transparent and verifiable query execution, the proposed agent greatly reduces inaccuracies in schema linking, removes the need to rely on a dedicated database engineering team for regular reporting, and thus brings intelligent data exploration within reach of a wider audience.eliminates reliance on dedicated database engineering teams for routine reporting, and democratizes intelligent data exploration.
Keywords	Text-to-SQL, LLM Agent, Flowise, PS-SQL, Schema Linking, Retrieval-Augmented Generation (RAG), Automated Data Analytics
Field	Computer > Data / Information
Published In	Volume 8, Issue 5, September-October 2026
Published On	2026-10-26

View / Download PDF File

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Data Analyst Agent with Flowise using PS-SQL

Share this