Spaces:
Sleeping
Sleeping
| from pathlib import Path | |
| from typing import Union | |
| import PyPDF2 | |
| from transformers import pipeline | |
| import gradio as gr | |
| # Initialize question-answering pipeline | |
| nlp = pipeline('question-answering', model='deepset/roberta-base-squad2') | |
| # Function to extract text from PDF | |
| def extract_text_from_pdf(pdf_file: Union[str, Path]) -> str: | |
| with open(pdf_file, 'rb') as pdf_file_obj: | |
| pdf_reader = PyPDF2.PdfReader(pdf_file_obj) | |
| text = ''.join(page.extract_text() for page in pdf_reader.pages) | |
| return text | |
| def answer_doc_question(pdf_file, question): | |
| # Extract text from PDF | |
| context = extract_text_from_pdf(pdf_file.name) | |
| # Prepare question-answering input | |
| QA_input = { | |
| 'question': question, | |
| 'context': context | |
| } | |
| # Get answer | |
| res = nlp(QA_input, max_answer_length=500) | |
| return res['answer'] | |
| # Define Gradio interface | |
| pdf_input = gr.File(type="filepath", label="Upload a PDF document and ask a question about it.") | |
| question = gr.Textbox(label="Type a question regarding the uploaded document here.") | |
| iface = gr.Interface(fn=answer_doc_question, inputs=[pdf_input, question], outputs="text") | |
| # Launch the interface | |
| iface.launch() | |