TiInsight: A SQL-based Automated Exploratory Data Analysis System through Large Language Models

2026-01-14

AI Summary

This work proposes TiChart, an LLM-based automated system for cross-domain exploratory data analysis (EDA) that addresses the limited generalization of existing SQL-driven approaches and better harnesses the capabilities of large language models. Through natural language interaction, TiChart enables end-to-end data understanding, SQL generation, and visualization. The system introduces a novel hierarchical data context construction mechanism along with question clarification and decomposition strategies, significantly enhancing cross-domain adaptability and user accessibility. Integrating Text-to-SQL (TiSQL), natural language processing, and a graphical user interface, TiChart has been successfully deployed in PingCAP’s production environment, demonstrating its practicality and effectiveness across multiple real-world datasets.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: Question Answering
• Humans and AI: Explainable AI (XAI) for Human Understanding

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

The SQL-based exploratory data analysis has garnered significant attention within the data analysis community. The emergence of large language models (LLMs) has facilitated the paradigm shift from manual to automated data exploration. However, existing methods generally lack the ability for cross-domain analysis, and the exploration of LLMs capabilities remains insufficient. This paper presents TiInsight, an SQL-based automated cross-domain exploratory data analysis system. First, TiInsight offers a user-friendly GUI enabling users to explore data using natural language queries. Second, TiInsight offers a robust cross-domain exploratory data analysis pipeline: hierarchical data context (i.e., HDC) generation, question clarification and decomposition, text-to-SQL (i.e., TiSQL), and data visualization (i.e., TiChart). Third, we have implemented and deployed TiInsight in the production environment of PingCAP and demonstrated its capabilities using representative datasets. The demo video is available at https://youtu.be/JzYFyYd-emI.

Problem

• exploratory data analysis
• cross-domain analysis
• large language models
• SQL-based analysis
• automated data exploration

Innovation

• cross-domain exploratory data analysis
• large language models
• text-to-SQL
• hierarchical data context
• automated data visualization