app.py

from transformers import AutoTokenizer, pipeline
from optimum.onnxruntime import ORTModelForQuestionAnswering
import gradio as gr
model = ORTModelForQuestionAnswering.from_pretrained("optimum/roberta-base-squad2")
tokenizer = AutoTokenizer.from_pretrained("deepset/roberta-base-squad2")

onnx_qa = pipeline("question-answering", model=model, tokenizer=tokenizer)

# question = "What's my name??"
# context = "My name is Philipp and I live in Nuremberg."
def get_answer(context, question):
    # question, context = inputs
    pred = onnx_qa(question, context)
    return pred


examples = [
  ["""In supervised learning, input data is provided to the model along with the output. In unsupervised learning, only input data is provided to the model. The goal of supervised learning is to train the model so that it can predict the output when it is given new data.""", "Explain supervised learning",],
  # []  # You can add context examples without questions
]


demo = gr.Blocks()

with demo:
    with gr.Row():
        context = gr.Textbox(label='Document', lines=10)
        question = gr.Textbox(label='Question', lines= 3)
        b1 = gr.Button('Get Answer')
        answer = gr.Textbox(label='Answer', lines=4)
    gr.Examples(examples= examples, inputs=[context, question], outputs=answer)
    b1.click(fn = get_answer, inputs=[context, question], outputs=answer)

demo.launch()