slfagrouche / brooklyn-college-rag-qa-bot

AG QA Application based on Brooklyn College Student Handbook 2023-2024: A semantic search and question-answering system utilizing MongoDB, Weaviate, and GPT-3.5. This application provides accurate answers to queries using the Brooklyn College Student Handbook as a data source, integrated with Gradio for an interactive user experience.

---

Brooklyn College RAG QA BOT

Brooklyn College RAG QA BOT is an interactive web application that provides question-answering capabilities based on the Brooklyn College Student Handbook 2023-2024. Utilizing MongoDB and Weaviate vector databases for document indexing and search, the application leverages the Gradio web interface and Hugging Face's transformers for model inference.

Features

• Question Answering: Users can query the application with questions related to the Brooklyn College Student Handbook, and the BOT provides precise answers.
• Document Search: Leverages advanced vector search technologies to retrieve information directly from the indexed documents.
• Interactive Web Interface: Offers a user-friendly web interface developed with Gradio, making it accessible for non-technical users.

Installation

To run the Brooklyn College RAG QA BOT locally, follow these steps:

1. Clone the repository:

   git clone https://huggingface.co/spaces/Slfagrouche/Brooklyn-College-RAG-QA-BOT

2. Navigate to the project directory:

   cd Brooklyn-College-RAG-QA-BOT

3. Install dependencies:

   pip install -r requirements.txt

4. Run the application:

   python your_gradio_script.py

   Or refer to setup instructions for more details on setting up on Windows or macOS.

Usage

1. Open the application in your web browser.
2. Enter a question related to the Brooklyn College Student Handbook.
3. The application will provide the answer, leveraging its advanced document search capabilities.

Try it Out

You can try out the live version of the Brooklyn College RAG QA BOT by visiting the following link:

Please note that the live app may have limited functionality compared to running the application locally.

Contributing

Contributions are welcome! If you'd like to contribute to the Brooklyn College RAG QA BOT, please feel free!

License

This project is licensed under the MIT License - Hugging Face.

Acknowledgements

• This project makes use of Gradio for building the interactive interface.
• Document indexing and search is powered by MongoDB and Weaviate.
• Model inference is facilitated by Hugging Face.

Support

For any questions or issues, please open an issue on GitHub.

---