import gradio as gr
from transformers import pipeline

# Load the summarization pipeline
# You can replace "sshleifer/distilbart-cnn-12-6" with another summarization model
# from the Hugging Face Hub if you prefer.
# A popular alternative is "bart-large-cnn".
# See https://huggingface.co/models?pipeline_tag=summarization&sort=downloads for more options.
try:
    summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")
except Exception as e:
    print(f"Error loading model: {e}")
    print("Please ensure you have the 'torch' library installed (`pip install torch`) or try a different model.")
    summarizer = None # Set summarizer to None if model loading fails


def summarize_text(text):
    """Summarizes the input text."""
    if not summarizer:
        return "Model not loaded. Please check the console for errors."
    if not text:
        return "Please enter some text to summarize."

    try:
        # You can adjust max_length and min_length as needed
        summary = summarizer(text, max_length=150, min_length=40, do_sample=False)[0]['summary_text']
        return summary
    except Exception as e:
        return f"An error occurred during summarization: {e}"


# Create the Gradio interface
if summarizer:
    interface = gr.Interface(
        fn=summarize_text,
        inputs=gr.Textbox(lines=10, label="Enter Text Here"),
        outputs=gr.Textbox(label="Summary"),
        title="Text Summarizer using Hugging Face and Gradio",
        description="Enter a long text and get a concise summary using a pre-trained model from Hugging Face."
    )

    if __name__ == "__main__":
        interface.launch()
else:
    print("Gradio interface not launched due to model loading error.")