Certainly! Here's a README file for your Streamlit MineBot project:

---

PowerBot

chatbot for power substations

Installation

1. Clone the repository:

   git clone https://github.com/yourusername/minebot.git
   cd minebot

2. Create a virtual environment and activate it:

   python -m venv env
   source env/bin/activate  # On Windows use `env\Scripts\activate`

3. Install the required packages:

   pip install -r requirements.txt

4. Set up environment variables: Create a .env file in the root directory and add your OpenAI and SerpAPI keys:

   OPENAI_API_KEY=your_openai_api_key
   SERPAPI_API_KEY=your_serpapi_api_key
   

5. Download the embedding model and index:

   • Ensure the embedding model BAAI/bge-large-en-v1.5 is available in the model_cache folder.
   • Ensure the FAISS index clean_total_index_bge_large is available in the root directory.

Usage

1. Run the Streamlit app:

   streamlit run app.py

2. Activate the system:

   • Go to the sidebar and click on "Activate" to load the models and tools.

3. Start chatting:

   • Use the chat input at the bottom of the page to ask questions related to mining regulations, and the bot will respond accordingly.

Project Structure

minebot/
├── .env.example          # Example environment file
├── app.py                # Main application file
├── requirements.txt      # List of Python dependencies
├── model_cache/          # Directory for embedding model cache
└── clean_total_index_bge_large  # FAISS index file

Customization

• CSS and HTML Templates:

  • Customize the look and feel of the chat interface by modifying the CSS, bot_template, and user_template variables in app.py.

• Tools and Memory:

  • Add or modify tools in the get_tools function.
  • Change memory settings in the get_memory function.

Contributing

1. Fork the repository.
2. Create a new branch:

   git checkout -b feature/your-feature-name

3. Make your changes.
4. Commit your changes:

   git commit -m "Add some feature"

5. Push to the branch:

   git push origin feature/your-feature-name

6. Open a pull request.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgements

• Streamlit
• Langchain
• OpenAI
• HuggingFace

---

Feel free to customize the README further to fit your specific needs.