A full-stack application that allows users to query a database using natural language and visualize the results through interactive charts.
- Natural language queries to database
- Interactive data visualization using various chart types
- Real-time query processing
- Responsive UI with dark mode
- Support for multiple chart types (Bar, Line, Pie, Scatter)
- AI-powered query understanding and data analysis
- FastAPI: REST API framework
- SQLAlchemy: Database ORM
- Phidata: AI agent framework for natural language processing
- PostgreSQL: Database
- Python 3.11+: Programming language
- Next.js 14: React framework
- TypeScript: Type-safe JavaScript
- Recharts: Chart visualization
- Tailwind CSS: Styling
- React Markdown: Markdown rendering
- Docker and Docker Compose
- Node.js 18+
- Python 3.11+
- PostgreSQL (will be run in Docker)
- Clone the repository:
git clone https://github.com/gauravdhiman/chat2db.git
- Install the Docker desktop and build the containers for first time.
docker compose up --build
For subsequent runs, you can start the containers without building them.
docker compose up
-
- You can see in requirements.txt that we are installing phidata from a specific branch. This is temporary until this PR gets merged. Once this is merged, we will switch to the official phidata package.
- Open the browser and navigate to http://localhost:3000.
Markdown output
Bar chart output
Line chart output
Pie chart output
Comparison chart output
- Docker - Containerization
- Node.js - JavaScript runtime
- Python - Programming language
- PostgreSQL - Database
- Phidata - AI agent framework
- FastAPI - REST API framework
- Next.js - React framework
- Recharts - Chart visualization
- Tailwind CSS - Styling
This project is not open source and is only for professional use. Any commercial without written permission is prohibited.