import streamlit as st
from transformers import pipeline
import nltk
from nltk.tokenize import sent_tokenize

# Download NLTK data
nltk.download('punkt')

# Load summarization pipeline with PyTorch
summarizer = pipeline("summarization", model="facebook/bart-large-cnn", framework="pt")

# Function to summarize text
def summarize(text):
    sentences = sent_tokenize(text)
    summary = ""
    for i in range(0, len(sentences), 3):
        chunk = " ".join(sentences[i:i+3])
        # Dynamically adjust max_length based on input length
        max_length = min(len(chunk) // 2, 130)  # Ensure max_length does not exceed 130
        min_length = max_length // 2
        summary_chunk = summarizer(chunk, max_length=max_length, min_length=min_length, do_sample=False)[0]['summary_text']
        summary += summary_chunk + " "
    return summary.strip()

# Streamlit app
st.title("Text Summarization with Hugging Face Transformers")

user_input = st.text_area("Enter text to summarize")
if st.button("Summarize"):
    summary = summarize(user_input)
    st.write(f"Summary: {summary}")