app.py

import gradio as gr
from transformers import AutoModel
from PIL import Image
import torch
import os
from huggingface_hub import login
import spaces

# Load the model
model = AutoModel.from_pretrained("jcsagar/CXR-LLAVA-v2", trust_remote_code=True)
model = model.to("cuda")

# Define the function to generate the report
@spaces.GPU
def ask_question(question, image):
    image = Image.open(image).convert("RGB")
    response = model.ask_question(question, image)
    return response

# Create the Gradio interface
interface = gr.Interface(
    fn=ask_question,
    inputs=[gr.Textbox(lines=1, placeholder="Enter your question here", label="Question"),
            gr.Image(type="filepath", label="Upload Image")],
    outputs=gr.Textbox(label="Report"),
    title="CXR Report Creator",
    description="Upload an image and enter a question to use with the CXR-LLAVA-v2 model."
)

# Launch the interface with API enabled
interface.launch()