Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Natural Language Query Engine for Relational Databases using Generative AI

Steve Tueno Fotso

TL;DR

This article introduces an innovative solution that leverages Generative AI to bridge this gap, enabling users to query databases using natural language, ensuring both syntactic and semantic correctness and generating clear, natural language responses from the retrieved data.

Abstract

The growing reliance on data-driven decision-making highlights the need for more intuitive ways to access and analyze information stored in relational databases. However, the requirement of SQL knowledge has long been a significant barrier for non-technical users. This article introduces an innovative solution that leverages Generative AI to bridge this gap, enabling users to query databases using natural language. Our approach automatically translates natural language queries into SQL, ensuring both syntactic and semantic correctness, while also generating clear, natural language responses from the retrieved data. By streamlining the interaction between users and databases, this method empowers individuals without technical expertise to engage with data directly and efficiently, democratizing access to valuable insights and enhancing productivity.

Natural Language Query Engine for Relational Databases using Generative AI

TL;DR

This article introduces an innovative solution that leverages Generative AI to bridge this gap, enabling users to query databases using natural language, ensuring both syntactic and semantic correctness and generating clear, natural language responses from the retrieved data.

Abstract

The growing reliance on data-driven decision-making highlights the need for more intuitive ways to access and analyze information stored in relational databases. However, the requirement of SQL knowledge has long been a significant barrier for non-technical users. This article introduces an innovative solution that leverages Generative AI to bridge this gap, enabling users to query databases using natural language. Our approach automatically translates natural language queries into SQL, ensuring both syntactic and semantic correctness, while also generating clear, natural language responses from the retrieved data. By streamlining the interaction between users and databases, this method empowers individuals without technical expertise to engage with data directly and efficiently, democratizing access to valuable insights and enhancing productivity.

Paper Structure

This paper contains 26 sections, 5 figures.

Table of Contents

  1. Background
  2. Relational Databases
  3. Structured Query Language (SQL)
  4. Large Language Models (LLMs)
  5. Vector Databases
  6. IBM watsonx.data
  7. IBM watsonx.ai
  8. Business Rules and Domain-Specific Knowledge
  9. Existing Solutions and Their Drawbacks
  10. Overview of existing products, publications, and patents
  11. Synthesis of common drawbacks
  12. Proposed Method: A Natural Language Assistant for Relational Databases
  13. Overview of the Method
  14. Database Structure Scanning
  15. Business Rules Integration
  16. ...and 11 more sections

Figures (5)

  • Figure 1: Architecture of the Natural Language Assistant for Relational Databases
  • Figure 2: Preview of a prototype of the approach: query on structure
  • Figure 3: Preview of a prototype of the approach: query on data
  • Figure 4: Architecture of the Prototype of the Natural Language Assistant for Relational Databases
  • Figure 5: Bird Dev Bench Initial Results