app.py

# app.py
import gradio as gr
from transformers import pipeline

# --- 1. Load the Text Summarization Model ---
# We're using a pre-trained summarization model from Hugging Face.
# 'sshleifer/distilbart-cnn-12-6' is a good balance of speed and quality.
# The 'pipeline' function simplifies using these models.
print("Loading summarization model... This may take a moment.")
try:
    summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")
    print("Model loaded successfully!")
except Exception as e:
    print(f"Error loading model: {e}")
    # Fallback or exit if the model can't be loaded, or handle gracefully.
    # For this demo, we'll let it fail for simplicity in error handling.
    summarizer = None # Ensure summarizer is None if loading fails

# --- 2. Define the Summarization Function ---
# This function will be called when the user clicks the 'Summarize' button.
def summarize_text(input_text):
    """
    Takes an input string and returns a concise summary.
    """
    if not input_text.strip(): # Check if the input text is empty or just whitespace
        return "Please enter some text to summarize."

    if summarizer is None:
        return "Summarization model failed to load. Please try again later or check server logs."

    try:
        # The summarizer pipeline returns a list of dictionaries.
        # We're interested in the 'summary_text' key from the first item.
        summary = summarizer(input_text, max_length=150, min_length=30, do_sample=False)
        return summary[0]['summary_text']
    except Exception as e:
        # Basic error handling for summarization issues
        return f"An error occurred during summarization: {e}"

# --- 3. Create the Gradio Interface ---
# Gradio makes it easy to build a web UI for machine learning models.
# `fn`: The function to call when the interface is used.
# `inputs`: The type of input component (here, a Textbox).
# `outputs`: The type of output component (here, a Textbox).
# `title` and `description` are used for the app's heading and explanation.
iface = gr.Interface(
    fn=summarize_text,
    inputs=gr.Textbox(lines=10, placeholder="Paste your text here to get a summary...", label="Input Text"),
    outputs=gr.Textbox(lines=7, label="Summary"),
    title="Simple AI Text Summarizer",
    description=(
        "This demo application uses a Hugging Face pre-trained model (DistilBART) "
        "to generate a concise summary of your input text. "
        "Simply type or paste your text into the box below and click 'Submit'."
    ),
    live=False # Set to True if you want real-time summarization as you type
)

# --- 4. Launch the Gradio App ---
# This line starts the web server for the Gradio app.
# share=True generates a public link (useful for sharing demos temporarily).
# debug=True provides more detailed logging in the console.
if __name__ == "__main__":
    iface.launch(share=False, debug=False)