app.py

import os
import gradio as gr
import torch
from transformers import pipeline

print(f"Is CUDA available: {torch.cuda.is_available()}")
print(f"CUDA device: {torch.cuda.get_device_name(torch.cuda.current_device())}")

examples = [['question: Should chest wall irradiation be included after mastectomy and negative node breast cancer? context: This study aims to evaluate local failure patterns in node negative breast cancer patients treated with post-mastectomy radiotherapy including internal mammary chain only. Retrospective analysis of 92 internal or central-breast node-negative tumours with mastectomy and external irradiation of the internal mammary chain at the dose of 50 Gy, from 1994 to 1998. Local recurrence rate was 5 % (five cases). Recurrence sites were the operative scare and chest wall. Factors associated with increased risk of local failure were age<or = 40 years and tumour size greater than 20mm, without statistical significance. answer: Post-mastectomy radiotherapy should be discussed for a sub-group of node-negative patients with predictors factors of local failure such as age<or = 40 years and larger tumour size.']] 

pipe_biogpt = pipeline("text-generation", model="microsoft/biogpt-large-pubmedqa", device="cuda:0")

title = "BioGPT Q&A Demo"
description = """
Check out the [BioGPT-Large-PubMedQA model card](https://huggingface.co/microsoft/biogpt-large-pubmedqa) for more info. 
**Disclaimer:** this demo was made for research purposes only and should not be used for medical purposes.
"""

def inference(text):
  output_biogpt = pipe_biogpt(text, max_length=100)[0]["generated_text"]
  return [
      output_biogpt, 
  ]

io = gr.Interface(
  inference,
  gr.Textbox(lines=3),
  outputs=[
    gr.Textbox(lines=3, label="BioGPT-Large"),
  ],
  title=title,
  description=description,
  examples=examples
)
io.launch()