/Mobile-Phone-Recommender-Chatbot

Data Quest competition

Primary LanguageJupyter NotebookMIT LicenseMIT

Mobile Phone Recommender Chatbot

This project is a mobile phone recommender chatbot built using React JS and FAST API. It incorporates various technologies such as Langchain, OpenAI GPT-3.5, Deep Gram Aura, and Nova model for speech-to-text and text-to-speech conversions. Additionally, it integrates Twilio for WhatsApp chat feature integration.

The chatbot has the following features:

  • Ability to interact through both audio and text queries.
  • WhatsApp chat integration for seamless communication.
  • Option to add additional mobile data for future updates.

Usage

To run the project, follow these steps:

  1. Install the required dependencies:

    pip install -r requirements.txt
    
  2. Navigate to the backend directory:

    cd src/app
    
  3. Run the following command:

    uvicorn main:app --reload --port 8080
    

To change frontend, you need to run the React frontend seperatly and build again.

Instructions for Improvement/Updates

If you wish to improve or update the project, consider the following guidelines:

  • Enhance Chatbot Responses: Utilize advanced natural language processing techniques to improve the chatbot's responses.
  • Integrate More Features: Explore additional features such as product recommendations based on user preferences or budget constraints.
  • Improve User Interface: Enhance the user interface for better user experience across different devices.
  • Optimize Performance: Optimize the codebase and algorithms for improved performance and scalability.

Authors

License

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

Acknowledgements

Thanks to OpenAI, DeepGram, and Twilio for providing the APIs and services that power this chatbot. Special thanks to the LangChain community for support and resources.

Feel free to contribute to the project by forking and submitting pull requests. If you encounter any issues or have suggestions for improvement, please open an issue on GitHub. We appreciate your support!