Text-to-SQL for Enterprise Data Analytics

TL;DR

This paper presents an enterprise-focused Text-to-SQL system that leverages a knowledge graph, context retrieval, and an interactive chatbot to enable non-expert users to access and analyze data effectively within a large organization.

Contribution

It introduces a practical, multi-component enterprise Text-to-SQL solution combining knowledge graphs, context-aware query generation, and interactive UI, tailored for internal organizational use.

Findings

53% of responses are correct or close to correct on internal benchmark

Over 300 weekly users of the chatbot demonstrate practical adoption

Ablation studies highlight key components for effective enterprise Text-to-SQL

Abstract

The introduction of large language models has brought rapid progress on Text-to-SQL benchmarks, but it is not yet easy to build a working enterprise solution. In this paper, we present insights from building an internal chatbot that enables LinkedIn's product managers, engineers, and operations teams to self-serve data insights from a large, dynamic data lake. Our approach features three components. First, we construct a knowledge graph that captures up-to-date semantics by indexing database metadata, historical query logs, wikis, and code. We apply clustering to identify relevant tables for each team or product area. Second, we build a Text-to-SQL agent that retrieves and ranks context from the knowledge graph, writes a query, and automatically corrects hallucinations and syntax errors. Third, we build an interactive chatbot that supports various user intents, from data discovery to query writing to debugging, and displays responses in rich UI elements to encourage follow-up chats. Our chatbot has over 300 weekly users. Expert review shows that 53% of its responses are correct or close to correct on an internal benchmark set. Through ablation studies, we identify the most important knowledge graph and modeling components, offering a practical path for developing enterprise Text-to-SQL solutions.