app.py

import torch
import gradio as gr 
from transformers import AutoTokenizer, AutoModelForQuestionAnswering

tokenizer = AutoTokenizer.from_pretrained("bert-large-uncased-whole-word-masking-finetuned-squad")

model = AutoModelForQuestionAnswering.from_pretrained("bert-large-uncased-whole-word-masking-finetuned-squad")

def QA_function(context, question):
    inputs = tokenizer(question, context, add_special_tokens=True, return_tensors="pt")
    input_ids = inputs["input_ids"].tolist()[0]

    outputs = model(**inputs)
    answer_start_scores = outputs.start_logits
    answer_end_scores = outputs.end_logits

    # Get the most likely beginning of answer with the argmax of the score
    answer_start = torch.argmax(answer_start_scores)
    # Get the most likely end of answer with the argmax of the score
    answer_end = torch.argmax(answer_end_scores) + 1

    answer = tokenizer.convert_tokens_to_string(tokenizer.convert_ids_to_tokens(input_ids[answer_start:answer_end]))

    return answer
    
gradio_ui = gr.Interface(QA_function, [gr.inputs.Textbox(lines=7, label="Context"), gr.inputs.Textbox(label="Question")], gr.outputs.Textbox(label="Answer"))
gradio_ui.launch()