Untitled

# Install required libraries
!pip install transformers torch datasets

from transformers import pipeline

def load_model():
    """
    Load the DistilBERT model and tokenizer for question answering.
    Returns a Hugging Face pipeline for question answering.
    """
    print("Loading model...")
    qa_pipeline = pipeline("question-answering", model="distilbert-base-uncased-distilled-squad")
    print("Model loaded successfully!")
    return qa_pipeline

def answer_question(qa_pipeline, context, question):
    """
    Use the model to answer a question based on the provided context.
    
    Args:
    - qa_pipeline: Hugging Face pipeline object for question answering
    - context: The context in which to search for the answer
    - question: The question to answer
    
    Returns:
    - Answer text generated by the model
    """
    result = qa_pipeline(question=question, context=context)
    return result['answer']

def main():
    # Load the model
    qa_pipeline = load_model()

    # Sample context for testing
    context = """
    OpenAI is an AI research and deployment company. Our mission is to ensure that artificial general intelligence 
    benefits all of humanity. OpenAI conducts research in a variety of fields, including natural language processing,
    machine learning, and artificial intelligence safety.
    """

    print("Welcome to the Question-Answering Model!")
    print("You can ask questions based on the provided context.")
    print("\nContext:")
    print(context)

    while True:
        # Get user input
        question = input("\nEnter your question (or type 'exit' to quit): ")

        if question.lower() == 'exit':
            print("Goodbye!")
            break

        # Answer the question
        answer = answer_question(qa_pipeline, context, question)
        print(f"Answer: {answer}")

if __name__ == "__main__":
    main()