Llama2 RAG System with Hugging Face

This repository contains a Jupyter Notebook that demonstrates the implementation of a Retrieval-Augmented Generation (RAG) system using the Llama2 model through the Hugging Face platform. The .py file is the RAG implementation with a Graphical User Interface (GUI) using the streamlit python library.

Overview

The notebook provides an example of setting up a RAG system which utilizes Llama2 for enhancing text generation capabilities with the power of external knowledge retrieval.

Features

• Implementation of the RAG system using Llama2.
• Integration with Hugging Face libraries.
• Demonstrations of setup and basic usage.

Requirements

• Python 3.x
• Hugging Face Transformers
• Other dependencies listed in requirements.txt

Setup

1. Clone the repository:

   git clone <repository-url>

2. Create a conda environment: ''' conda create -n myenv python=3.x '''

3. Install the required packages:

   pip install -r requirements.txt

4. Activate your environemt:

   conda activate myenv

5. Open the notebook in Jupyter Lab or Jupyter Notebook:

   jupyter lab

Usage

Follow the instructions in the notebook to learn how to initialize the system, prepare data, and generate responses using the RAG model.

Running the .py file

1. Clone the repository:

   git clone <repository-url>

2. Create a conda environment: ''' conda create -n myenv python=3.9 '''

3. Activate your environemt:

   conda activate myenv

4. Run Streamlit:

   streamlit run llama_app.py

Contributing

Contributions are welcome! For major changes, please open an issue first to discuss what you would like to change.

License

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