app.py

import streamlit as st
import subprocess
import sys

# Install pdfplumber if it's not already installed
try:
    import pdfplumber
except ModuleNotFoundError:
    subprocess.check_call([sys.executable, "-m", "pip", "install", "pdfplumber"])
    import pdfplumber  # Re-import after installation

from transformers import pipeline

# Function to extract text from PDFs using pdfplumber
def extract_text_from_pdfs(pdf_files):
    pdf_texts = {}
    for pdf_file in pdf_files:
        with pdfplumber.open(pdf_file) as pdf:
            text = ""
            for page in pdf.pages:
                text += page.extract_text()
            pdf_texts[pdf_file.name] = text
    return pdf_texts

# Load pre-trained QA model
qa_pipeline = pipeline('question-answering', model='distilbert-base-uncased-distilled-squad')

# Function to answer questions based on extracted text
def answer_question(pdf_texts, question):
    context = " ".join(pdf_texts.values())
    result = qa_pipeline(question=question, context=context)
    return result['answer']

# Streamlit application
st.title("PDF Question Answering App")

# File uploader for PDF files
uploaded_files = st.file_uploader("Upload PDF files", type="pdf", accept_multiple_files=True)

# Display uploaded files
if uploaded_files:
    # Extract text from PDFs
    pdf_texts = extract_text_from_pdfs(uploaded_files)
    st.write("PDFs Uploaded Successfully!")

    # Question input
    question = st.text_input("Enter your question:")
    
    if st.button("Get Answer"):
        if question:
            answer = answer_question(pdf_texts, question)
            st.write(f"Answer: {answer}")
        else:
            st.write("Please enter a question.")
else:
    st.write("Please upload PDF files to continue.")