Installation Instructions

Follow these steps to install and run the RAG - Retrieval-Augmented Generation application locally:

  1. Clone the repository:
    2. git clone https://github.com/imadmaalouf02/RAG.git
  2. Install the dependencies:

    3. Make sure you have Python installed. You can install the required dependencies using the following command:

    pip install -r requirements.txt
  3. Alternative Conda installation:

    4. If you are using Conda as your environment manager, you can install Streamlit with:

    conda install -c conda-forge streamlit
  4. Run the application:

    5. Once all dependencies are installed, run the Streamlit app using:

    streamlit run app.py
  5. Access the app in your browser:

    6. After running the command, Streamlit will open the application in your default browser. If not, you can access it by navigating to:

    http://localhost:8501

Step-by-Step Guide for Using the Application

  1. Upload your document:

    2. On the main page of the application, you will see an option to upload a PDF file. Use the file upload widget to select your document.

  2. Select the language model:

    3. Choose one of the available language models from the dropdown menu. The models include:

    • Llama 2: Ideal for general text generation and comprehension.
    • Mistral: Fast and efficient for text generation.
    • CodeLlama: Specialized for generating and understanding code.
    • Llama 3.1: Advanced model for more complex language tasks.
  3. Choose the task:

    4. Select the task you want to perform from the available options:

    • Summarization: Get a concise summary of the document.
    • Translation: Translate the document content to another language.
    • Question-Answering: Ask questions about the document and receive detailed responses.
  4. View the results:

    5. Once the task is complete, the output will be displayed on the same page. Depending on the task, you'll either see a summary, translation, or answers to your questions.