app.py

import streamlit as st
import transformers
from transformers import pipeline

# Load models
text_classification = pipeline("text-classification", model="cardiffnlp/twitter-roberta-base-sentiment-latest")
ques_ans = pipeline("question-answering", model="deepset/roberta-base-squad2")
summarization = pipeline("summarization", model="facebook/bart-large-cnn")

st.title("NLP Task Reading ")

# Task selector
task = st.radio("Select NLP Task", ("Sentiment Analysis", "Question & Answer", "Summarization"))

# Sentiment Analysis
if task == "Sentiment Analysis":
    st.subheader("Sentiment Analysis")
    user_text = st.text_input("Enter text:")
    if user_text:
        prediction = text_classification(user_text)[0]
        confidence_percentage = prediction["score"] * 100
        label = prediction["label"]
        statement = f"The model is {confidence_percentage:.2f}% confident that the sentiment is **{label}**."
        st.write(statement)

# Question Answering
elif task == "Question & Answer":
    st.subheader("Question & Answer")
    question = st.text_input("Question:")
    context = st.text_area("Context:")
    if question and context:
        result = ques_ans(question=question, context=context)
        answer = result["answer"]
        confidence = result["score"] * 100
        st.write(f"The answer is: **{answer}**")
        st.write(f"The model is {confidence:.2f}% confident in this answer.")

# Summarization
elif task == "Summarization":
    st.subheader("Summarization")
    text_to_summarize = st.text_area("Enter text to summarize:")
    if text_to_summarize:
        summary = summarization(text_to_summarize)[0]["summary_text"]
        st.write(f"**Summary:** {summary}")