app.py

import gradio as gr
from transformers import pipeline
import os
hf_token = os.getenv("HF_TOKEN")
# Set up the pipeline
med_pipe = pipeline("text-generation", model="OpenBioLLM-70B", trust_remote_code=True)


# Define the function for generating responses
def generate_response(input_text):
    if not input_text.strip():
        return "Please enter some text to generate a response."
    
    response = pipe(input_text, max_new_tokens=150, do_sample=True)[0]["generated_text"]
    return response

# Gradio interface
iface = gr.Interface(fn=generate_response, inputs="text", outputs="text", title="Flmc/DISC-MedLLM")

if __name__ == "__main__":
    iface.launch()