import os import streamlit as st from transformers import pipeline from PyPDF2 import PdfReader # Function to perform question-answering def question_answering(question, pdf_path): pdf_reader = PdfReader(pdf_path) pdf_text_with_pages = [] for page_num, pdf_page in enumerate(pdf_reader.pages, start=1): pdf_text = pdf_page.extract_text() pdf_text_with_pages.append((page_num, pdf_text)) pdf_text = "\n".join([text for _, text in pdf_text_with_pages]) # Perform question-answering using Hugging Face's Transformers question_answerer = pipeline("question-answering", model="distilbert-base-cased-distilled-squad", tokenizer="distilbert-base-cased-distilled-squad") answer = question_answerer(question=question, context=pdf_text) return answer def main(): st.title("Question Answering on a PDF File") uploaded_file = st.file_uploader("Upload a PDF file:", type=["pdf"]) question = st.text_input("Ask your question:") if st.button("Answer") and uploaded_file is not None: pdf_path = os.path.join(os.getcwd(), uploaded_file.name) with open(pdf_path, "wb") as f: f.write(uploaded_file.read()) answer = question_answering(question, pdf_path) # Delete the uploaded file after processing os.remove(pdf_path) st.write(f"Question: '{question}'") st.write("Answer:", answer['answer']) st.write("Score:", answer['score']) if __name__ == "__main__": main()