QueryMind – AI SQL Assistant (CLI)

Convert Natural Language into SQL Queries from Your Terminal

Python • Google Gemini / OpenAI • MySQL • Oracle • SQLite • Rich CLI

---

Overview

QueryMind is an AI-powered command-line SQL assistant that allows users to interact with databases using natural language instead of writing SQL manually.

Simply ask questions like:

"Show all students whose CGPA is above 8."

QueryMind automatically:

• Understands your request using an LLM
• Discovers your database schema
• Generates SQL for the correct database dialect
• Validates the query for safety
• Executes it on the connected database
• Displays beautifully formatted results inside the terminal

It supports MySQL, Oracle, and SQLite, making it useful for learning SQL, database administration, analytics, and rapid querying.

---

Features

• Natural Language → SQL conversion
• Supports MySQL, Oracle, and SQLite
• Automatic database schema discovery
• AI understands tables, columns and relationships
• Read-only SQL safety validation
• Interactive terminal interface powered by Rich
• SQL syntax highlighting
• Query execution timing
• AI-generated SQL explanations
• Persistent query history
• Built-in slash commands
• Environment-based configuration
• Easy database switching

---

Demo

==================================================
            QueryMind AI SQL Assistant
==================================================

Database : SQLite (college.db)
Status   : Connected

You > Show all students whose CGPA is above 8

Generated SQL

SELECT *
FROM students
WHERE cgpa > 8;

Executing...

┏━━━━┳━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━┓
┃ ID ┃ Name          ┃ Department ┃ CGPA ┃
┣━━━━╋━━━━━━━━━━━━━━━╋━━━━━━━━━━━━╋━━━━━━┫
┃ 1  ┃ Rahul Sharma  ┃ CSE        ┃ 8.4  ┃
┃ 2  ┃ Anjali Verma  ┃ ECE        ┃ 9.1  ┃
┃ 4  ┃ Priya Nair    ┃ CSE        ┃ 9.5  ┃
┗━━━━┻━━━━━━━━━━━━━━━┻━━━━━━━━━━━━┻━━━━━━┛

Rows Returned : 3
Execution Time : 4.2 ms

---

Key Features

Natural Language to SQL

Ask questions in plain English.

Examples:

• Show all students
• List employees earning more than 50000
• Display customers from Kerala
• Count total orders this month
• Show departments ordered alphabetically

---

Multi-Database Support

QueryMind works seamlessly with:

• SQLite
• MySQL
• Oracle Database

The AI automatically generates SQL based on the connected database.

---

Automatic Schema Discovery

Before generating SQL, QueryMind reads:

• Tables
• Columns
• Data types
• Primary Keys
• Foreign Keys

This enables more accurate SQL generation.

---

SQL Safety Validation

Every generated query is validated before execution.

Blocked statements include:

• DROP
• DELETE
• UPDATE
• INSERT
• ALTER
• CREATE
• TRUNCATE
• EXEC
• CALL

Only safe SELECT queries are executed.

---

Rich Terminal Interface

Built using the Rich library.

Features include:

• Syntax highlighting
• Beautiful tables
• Status panels
• Execution timers
• Colourful banners
• Interactive prompts

---

AI Query Explanation

Use:

/explain

The assistant explains the generated SQL in simple English.

---

Persistent Query History

Every session records:

• Natural language prompt
• Generated SQL
• Execution time
• Returned rows
• Timestamp

History is stored locally inside:

history/history.json

---

Built-in Commands

Command	Description
/help	Show all available commands
/connect	Connect to a database
/disconnect	Disconnect current session
/schema	Display discovered schema
/tables	List all tables
/history	View previous queries
/explain	Explain the last SQL query
/clear	Clear terminal
/exit	Exit QueryMind

---

Project Structure

querymind/
│
├── main.py
├── config.py
├── database.py
├── schema.py
├── ai.py
├── validator.py
├── executor.py
├── history.py
├── prompts.py
├── utils.py
├── sample_db.py
├── requirements.txt
├── .env
│
├── history/
│   └── history.json
│
└── README.md

---

Installation

Clone the Repository

git clone https://github.com/yourusername/querymind.git

cd querymind

---

Create Virtual Environment

Windows

python -m venv venv

venv\Scripts\activate

Linux / macOS

python3 -m venv venv

source venv/bin/activate

---

Install Dependencies

pip install -r requirements.txt

---

Environment Variables

Create a .env file.

LLM_PROVIDER=gemini

GEMINI_API_KEY=YOUR_GEMINI_API_KEY

OPENAI_API_KEY=YOUR_OPENAI_API_KEY

DB_TYPE=sqlite

DB_HOST=localhost

DB_PORT=3306

DB_USER=root

DB_PASSWORD=

DB_NAME=college.db

---

Sample Database

Generate a demo SQLite database.

python sample_db.py

This creates:

college.db

containing:

• students
• departments
• courses
• enrollments

---

Running the Application

python main.py

Then simply ask:

Show all students

List employees from HR

Count all courses

Show students with CGPA above 8

---

Technologies Used

• Python 3.12+
• Google Gemini API
• OpenAI API
• Rich
• SQLParse
• SQLite
• MySQL Connector
• OracleDB
• python-dotenv

---

Security

QueryMind is designed with database safety in mind.

• Read-only query execution
• SQL parsing and validation
• Dangerous statements blocked
• Encourages read-only database accounts
• Prevents accidental destructive operations

---

Future Improvements

• Export results to CSV, Excel and JSON
• Query auto-completion
• Database connection profiles
• Voice-to-SQL
• Docker support
• Local LLM support (Ollama)
• PostgreSQL support
• Interactive charts
• Web dashboard
• Query optimisation suggestions

---

Contributing

Contributions are welcome.

1. Fork the repository
2. Create a new feature branch

git checkout -b feature/NewFeature

3. Commit your changes

git commit -m "Add new feature"

4. Push to your branch

git push origin feature/NewFeature

5. Open a Pull Request

---

License

This project is licensed under the MIT License.

---

Author

Mahinsha E.A.

If you found this project helpful, consider giving it a ⭐ on GitHub.