Querion is a full-stack AI data analyst platform that bridges the gap between your PostgreSQL database and business users who don't know SQL. Simply type a question in plain English — Querion uses a large language model to generate the SQL, validates and executes it safely, and renders the results as interactive tables, charts, or raw JSON — all in real-time.

"Show me top customers by total spending" → Querion generates SQL → Executes on your DB → Displays an interactive bar chart in seconds.

The main dashboard gives you a bird's-eye view of your key metrics, a live revenue trend chart, AI-generated insights, and a panel of your most recent queries — all in one glance.

Type any business question. Querion generates the SQL, displays it transparently, executes it, and renders the data in a clean, exportable table.

Switch to Chart view to visualize your query results as a bar, area, or line chart — rendered with Recharts and auto-configured from your query output.

Querion/
├── frontend/                   # Next.js 16 application
│   └── src/
│       ├── app/
│       │   ├── page.tsx        # Main dashboard & view router
│       │   ├── layout.tsx      # Root layout with sidebar
│       │   └── globals.css     # Global design tokens
│       ├── components/
│       │   ├── layout/         # Sidebar, TopBar
│       │   └── ui/             # AskBar, MetricCard, DataTable,
│       │                       # ChartViewer, InsightStrip, SQLBlock,
│       │                       # QueryHistory, SavedReports,
│       │                       # ScheduledQueries, ResultCard
│       └── lib/
│           ├── api.ts          # HTTP client for backend
│           └── NavContext.tsx  # Global navigation state
│
├── backend/                    # FastAPI application
│   ├── app/
│   │   ├── api/
│   │   │   └── routes.py       # POST /query endpoint
│   │   ├── services/
│   │   │   ├── llm_service.py  # Groq NL→SQL generation
│   │   │   ├── sql_validator.py# SQL safety checks
│   │   │   └── query_service.py# DB query execution
│   │   ├── db/
│   │   │   └── database.py     # SQLAlchemy engine & sessions
│   │   ├── schemas/
│   │   │   └── query_schema.py # Pydantic request/response models
│   │   └── utils/
│   │       └── formatter.py    # Response formatting
│   ├── seed.py                 # Sample data seeder
│   └── requirements.txt
│
└── assets/                     # README screenshots & banner

• Node.js ≥ 18
• Python ≥ 3.10
• PostgreSQL running locally (or a connection string)
• A Groq API key (free tier available)

git clone https://github.com/Anubhx/Querion.git
cd Querion

cd backend

# Create and activate a virtual environment
python -m venv venv
source venv/bin/activate        # Windows: venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

# Configure environment variables
cp .env.example .env

Edit backend/.env:

DATABASE_URL=postgresql://user:password@localhost:5432/querion
LLM_API_KEY=your_groq_api_key_here

# Seed the database with sample data
python seed.py

# Start the API server
uvicorn app.main:app --reload --port 8000

The backend will be available at http://localhost:8000

cd ../frontend

# Install dependencies
npm install

# Configure environment
echo "NEXT_PUBLIC_API_URL=http://localhost:8000" > .env.local

# Start the dev server
npm run dev

Open http://localhost:3000 in your browser. 🎉

Accepts a natural language question and returns structured query results.

Request Body

{
  "question": "Show top 5 customers by total order amount"
}

Response

{
  "sql": "SELECT c.name, SUM(o.amount) AS total FROM customers c JOIN orders o ON c.id = o.customer_id GROUP BY c.name ORDER BY total DESC LIMIT 5",
  "data": [
    { "name": "Alice Smith", "total": 12400 },
    { "name": "Bob Johnson", "total": 9800 }
  ],
  "chart": {
    "labels": ["Alice Smith", "Bob Johnson"],
    "values": [12400, 9800]
  },
  "explanation": "Generated results for: Show top 5 customers by total order amount"
}

Error Responses

User types a question
        │
        ▼
  [Frontend AskBar]
        │  HTTP POST /query
        ▼
  [FastAPI Route]
        │
        ├─► [LLM Service] ──► Groq Llama 3.3 70B
        │       │  Returns raw SQL
        │       ▼
        ├─► [SQL Validator] ── Block non-SELECT, inject LIMIT
        │
        ├─► [Query Service] ── Execute on PostgreSQL via SQLAlchemy
        │
        └─► [Formatter] ──────► JSON response with data + chart hints
                                        │
                                        ▼
                          [Frontend] renders Table / Chart / JSON

• Read-only enforcement — only SELECT statements are permitted; any DML or DDL raises a 400 immediately.
• Automatic LIMIT injection — every query is capped at 100 rows to prevent runaway queries.
• No raw user input reaches the DB — all SQL is LLM-generated and validator-checked before execution.

• Multi-database support (MySQL, SQLite, BigQuery)
• User authentication & team workspaces
• Shareable report links
• Slack / email delivery for scheduled queries
• Fine-tuned SQL model for domain-specific schemas
• Natural language chart customization ("make this a pie chart")

Contributions are welcome! Please open an issue first to discuss what you'd like to change.

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

This project is licensed under the MIT License — see the LICENSE file for details.