Conversational AI for Enterprise Analytics — talk to your business data instead of building dashboards.
Talking Rabbitt is an AI-powered conversational data interface. Instead of navigating complex dashboards in PowerBI or Tableau, business leaders can simply ask a question in plain English and get an instant answer with an auto-generated chart.
The magic moment: Replace a 10-minute Excel filter session with a 5-second conversation.
Upload any sales CSV → Ask a question → Get an answer + visualization instantly.
Example queries you can try:
Which region had the highest revenue?What is the average deal value?Show me the revenue trend over timeWhich product had the lowest sales?
- Python 3.9+
- pip
# Clone the repository
git clone https://github.com/your-username/talking-rabbitt.git
cd talking-rabbitt
# Install dependencies
pip install -r requirements.txt
# Run the app
streamlit run app.pyThe app will open at http://localhost:8501
talking-rabbitt/
├── app.py # Main Streamlit application
├── requirements.txt # Python dependencies
├── sample_data/
│ └── sales_sample.csv # Sample dataset to test with
└── README.md
A sample CSV is included in sample_data/sales_sample.csv. It contains:
| Column | Description |
|---|---|
| Region | Sales region (North, South…) |
| Product | Product line name |
| Revenue | Revenue in USD |
| Quarter | Reporting quarter |
| Rep | Sales representative name |
streamlit>=1.28.0
pandas>=2.0.0
matplotlib>=3.7.0
- Upload — User uploads a standard sales CSV file
- Ask — User types a plain-English question
- Analyze — The app detects intent (highest, average, trend, lowest) and maps it to the right columns
- Deliver — An answer + chart is returned in under 5 seconds