Schema Aware AI SQL Agent

Abstract

1. Introduction

The Schema-Aware AI SQL Agent bridges the gap between LLMs and production databases. It turns plain English into SQL — safely — with full guardrails in place.

Built entirely in Python with open-source tools, it’s designed for environments where security, compliance, and accuracy matter.

2. Objective

This project enables users to **generate SQL queries from natural language** using **LLM** of their choice while enforcing **Role-Based Access Control (RBAC)** and **Row-Level Security (RLS)**. It also includes **SQL injection detection** and **sensitive data logging** for compliance and security.

This project demonstrates how Python, LangChain can be applied to a real-world Cybersecurity & Ethical Hacking problem.

3. Key Features / Modules

• Natural language to SQL with LLMs (OpenAI, OpenRouter, Ollama)
• Role-based access control (RBAC) and row-level security (RLS)
• Schema-aware validation and SQL sanitization
• Memory-aware chat agent with clarification flow
• REST API + Streamlit front-end
• Sample PostgreSQL database (Northwind) included for testing

4. Technology Stack

5. System Requirements

General requirements for this technology stack — check the README for exact versions.

• Python 3.8 or later
• pip / virtualenv for dependencies
• VS Code, PyCharm or Jupyter Notebook
• Git (to clone the repository)

6. Installation & Setup

git clone https://github.com/raedmajid/schema-aware-ai-sql-agent.git
cd schema-aware-ai-sql-agent

git clone https://github.com/raedmajid/schema-aware-ai-sql-agent
cd schema-aware-ai-sql-agent
python -m venv venv
source venv/bin/activate
pip install -r requirements.txt
cp .env.example .env  # then edit with your values

uvicorn backend.api.api:app --host 127.0.0.1 --port 8000 --reload

python3 -m streamlit run frontend/chat_UI.py

Full setup instructions are in the project README.

7. Future Enhancements

Suggested extensions you can add to make this your own project.

• Add logging and alert notifications (email / Telegram)
• Write a threat model document for the tool
• Package it with Docker for safe lab testing

8. Viva / Review Questions

Common questions examiners ask for projects in this domain.

1. Which threat or attack does this project defend against?
2. What detection or protection technique is used and what are its limits?
3. How are false positives and false negatives handled?
4. Which cryptographic algorithms or security standards are involved?
5. What legal and ethical rules apply when testing a tool like this?

9. Source Code & License

This project is developed by raedmajid and published on GitHub under the MIT License. Please follow the license terms and credit the original author when you use or modify this code.