Forget complex charting libraries and endless documentation. ChartGPT lets you create stunning, interactive visualizations by simply asking for what you want in plain English. Upload your CSV, ask a question, and watch as AI generates the perfect chart for your data.

You: "Show me a correlation heatmap of all numeric columns"
ChartGPT: *generates beautiful visualization + Python code*

No coding required. No chart selection headaches. Just data insights at the speed of thought.

graph LR
    A[📄 Upload CSV] --> B[💭 Ask Question]
    B --> C[🤖 AI Generates Code]
    C --> D[📊 Beautiful Chart]
    D --> E[🔄 Refine or Export]

Drag and drop any CSV file (up to 5MB). Instantly preview your data in an interactive table.

Type naturally:

• "Show me monthly revenue trends as a line chart"
• "Create a bar chart comparing product categories"
• "Plot the distribution of customer ages"
• "Make a scatter plot of price vs. quantity sold"

ChartGPT analyzes your data, writes the visualization code, and renders your chart in seconds. View the generated Python code anytime.

Built with cutting-edge technologies for the best developer and user experience:

• 🎯 Dash — Reactive web application framework
• 🤖 ChartGPT Library — AI-powered chart generation engine
• 🎨 Dash Mantine Components — Beautiful, modern UI components
• 📊 Plotly — Interactive, publication-quality visualizations
• 📈 Dash AG Grid — Professional data tables
• 🧠 Hugging Face Qwen2.5-Coder — State-of-the-art code generation LLM

Clone and run in under 2 minutes:

# Clone the repository
git clone https://github.com/yourusername/chartgpt.git
cd chartgpt

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

# Install dependencies
pip install -r requirements.txt

# Set up your Hugging Face token
echo "HUGGINGFACE_API_KEY=your_token_here" > .env

# Launch the app
python app.py

🎉 Open your browser to http://localhost:8050

Even easier with Docker:

# Build the image
docker build -t chartgpt .

# Run the container
docker run -p 7860:7860 chartgpt

🎉 Access at http://localhost:7860

chartgpt/
├── 🐍 app.py                   # Main Dash application
├── 📦 requirements.txt         # Python dependencies
├── 🐳 Dockerfile              # Container configuration
├── 📂 assets/
│   ├── 🌙 logo_dark.svg       # Logo for light theme
│   ├── ☀️  logo_light.svg      # Logo for dark theme
│   └── 🎨 custom.css          # Custom styling
└── 📖 README.md               # You are here!

Customize the AI model in app.py (line 464):

# Switch to different models
chart = cg.Chart(df, model="huggingface/Qwen/Qwen2.5-Coder-32B-Instruct")

# Try other options:
# model="openai/gpt-4"
# model="anthropic/claude-3-sonnet"

Perfect for sharing with the world:

1. Create a new Space on Hugging Face
2. Select Docker as the SDK
3. Push your code to the Space repository
4. Add your HUGGINGFACE_API_KEY in Settings → Repository secrets
5. Your app goes live automatically!

Deploy anywhere containers run:

We love contributions! Here's how to get started:

# Fork the repo, then clone your fork
git clone https://github.com/YOUR_USERNAME/chartgpt.git

# Create a feature branch
git checkout -b feature/amazing-feature

# Make your changes and commit
git commit -m '✨ Add amazing feature'

# Push to your fork
git push origin feature/amazing-feature

# Open a Pull Request

This project is licensed under the MIT License — feel free to use it however you'd like!

Standing on the shoulders of giants:

• 🎯 ChartGPT Library — Core AI chart generation
• ⚡ Plotly Dash Team — Amazing web framework
• 🎨 Mantine Dev — Beautiful component library
• 🧠 Qwen Team — Powerful open-source LLM