Ewen2015/BICat

AI-powered BI.

BI-Chatbot: AI-Powered BI

A project utilizing OpenAI ChatGPT, PyGWalker, and ydata-profiling for interactive data analysis and visualization using Streamlit.

Pain points to solve

1. Exploratory Data Analysis (EDA) requires coding
2. Unable to talk to your data with natural language
3. PowerBI and Excel are too complicated and time-consuming

🍓 Preview

🍪 Usage

Cloud

Just click bi-chatbot.

Local

1. Clone the repository:

   git clone https://github.com/ewen2015/bi-chatbot.git

2. Navigate to the project directory:

   cd bi-chatbot

3. Install dependencies:

   pip install -r requirements.txt

4. Start the Streamlit application:

   streamlit run app/bi-chatbot.py

Once the Streamlit application is running, open it in your browser to play and talk to your data!

🍔 Tech Stack

🥛 Thinking

Challenges

1. Prompt Engineering: to build a bridge between the LLM and domain knowledge.
2. Data Preparation: data is still the key to a better BI.
3. Presentation: great charts talk.

Reflections

1. This time, AI is really eating the world.
2. The LLM is fundamentally changing the way people develop applications. Just take a look at pandas-ai.
3. Presenting meaningful work is more important than ever.

🍻 Contributing

Contributions are welcome! To contribute to this project, follow these steps:

1. Fork the repository.
2. Create a new branch.
3. Make your changes and commit them.
4. Push your changes to your forked repository.
5. Submit a pull request.

🍭 License

This project is licensed under the MIT License.