Welcome to the Smart India Hackathon Chatbot Project! This project aims to create a chatbot using the GPT-2 transformer model to assist users with their inquiries and engage in conversations. The chatbot is built using Streamlit, a Python library for creating web applications with minimal effort.
The core of this project consists of two main components:
-
chatbot.py: This is the Streamlit-based chatbot application. It leverages the Hugging Face Transformers library to load a pre-trained GPT-2 model and generate responses based on user input. Users can have interactive conversations with the chatbot through the web interface.
-
model_generation.ipynb: This Jupyter Notebook demonstrates how to generate a custom version of the GPT-2 model, fine-tuned for specific use cases. The generated model can be used to enhance the chatbot's capabilities.
- Execute the model_generation.ipynb notebook to generate and save the transformer so that it can be used later. This is important because it takes a really long time to do it.
Time taken in my case: 16.5 min for 10 GB, approx.
System specs: M2 Macbook Air - 16GB RAM - Now, execute the chatbot.py file using the following command in the command prompt:
streamlit run chatbot.py
Ensure you have the following dependencies installed to run the project:
- Python (3.6+)
- Streamlit
- Hugging Face Transformers library
- Jupyter Notebook (for model generation)
Contributions are welcome! If you'd like to contribute to this project, please follow these guidelines:
- Fork the repository.
- Create a new branch for your feature or bug fix.
- Make your changes and commit them.
- Push your changes onto your fork.
- Submit a pull request to the main repository. Please ensure that your code adheres to coding standards and includes appropriate documentation.
This project is licensed under the MIT License. You are free to use, modify, and distribute the code as per the terms of this license.