CSVision: AI-Powered Data Analysis with Groq LLM

CSVision is a web-based tool that allows users to analyze CSV datasets using AI-powered natural language queries. It utilizes Groq's large language models to generate insights and visualizations based on user queries.

🚀 Features

• Upload your own CSV files or choose from example datasets.
• Ask questions in natural language to extract insights from your data.
• Get AI-generated responses powered by Groq LLM.
• Automatically generate enhanced visualizations for better data analysis.
• Simple and intuitive Gradio-based user interface.

🛠️ Technologies Used

• Gradio: For building the web interface.
• Pandas: For data manipulation and analysis.
• Matplotlib: For generating visualizations.
• Groq LLM: For AI-powered query processing.
• LlamaIndex: For executing queries in a structured pipeline.
• Hugging Face Spaces: For easy deployment and accessibility.

🔗 Live Demo

Check out the deployed application on Hugging Face Spaces:
CSVision on Hugging Face

📌 How to Use

1. Upload Data: Upload your CSV file or select an example dataset.
2. Enter API Key: Provide your Groq API key to enable AI-powered analysis.
3. Ask Questions: Type queries like "What is the trend of monthly bookings over time?"
4. View Insights: Get text-based AI responses and visualizations.

🔥 Example Queries

• "What is the distribution of stay duration?"
• "Which country has the most bookings?"
• "Is there a correlation between lead time and cancellations?"
• "Show me bookings by month and year."

📌 Installation (Local Setup)

If you want to run the project locally, follow these steps:

# Clone the repository
git clone https://github.com/SHASWATSINGH3101/CSVision.git
cd csvision

# Install dependencies
pip install -r requirements.txt

# Run the application
python CSV_rag_.py

---

🤝 Contributing

We welcome contributions! Fork the repo, create a new branch, and submit a pull request.

---

License

This project is licensed under the MIT License.

---

Citing the Project

To cite this repository in publications:

@misc{CSVision,
  author = {SHASWATSINGH3101},
  title = {CSVision},
  year = {2025},
  howpublished = {\url{https://github.com/SHASWATSINGH3101/CSVision}},
  note = {GitHub repository},
}

---

Contact

For inquiries or support, connect via:

• 💬 Discord: shaswat_singh

---