app.py

import streamlit as st
from transformers import pipeline
import PyPDF2

# Function to extract text from PDF
def extract_text_from_pdf(pdf_file):
    text = ""
    pdf_reader = PyPDF2.PdfReader(pdf_file)
    for page_num in range(len(pdf_reader.pages)):
        page = pdf_reader.getPage(page_num)
        text += page.extractText()
    return text

# Streamlit app
def main():
    st.title('PDF Text Extraction')
    
    uploaded_file = st.file_uploader("Upload a PDF file", type="pdf")
    if uploaded_file is not None:
        st.write("File uploaded successfully!")

        # Extract text when file is uploaded
        text = extract_text_from_pdf(uploaded_file)

        st.write("### Extracted Text:")
        st.write(text)

        # Use Hugging Face's pipeline for further NLP tasks
        st.write("### NLP Analysis:")
        nlp_task = st.selectbox("Select NLP Task", ["Named Entity Recognition", "Sentiment Analysis"])

        if nlp_task == "Named Entity Recognition":
            ner = pipeline("ner")
            entities = ner(text)
            st.write(entities)
        
        if nlp_task == "Sentiment Analysis":
            sentiment_analysis = pipeline("sentiment-analysis")
            sentiment = sentiment_analysis(text)
            st.write(sentiment)

if __name__ == "__main__":
    main()