app.py

import gradio as gr
from PIL import Image

# Define the prediction function for Gradio
def predict(image, question):
    inputs = processor(text=[question], images=[image], return_tensors="pt", padding=True).to(device)
    outputs = model.generate(**inputs)
    return processor.tokenizer.decode(outputs[0], skip_special_tokens=True)

# Create the Gradio interface
interface = gr.Interface(
    fn=predict,
    inputs=["image", "text"],
    outputs="text",
    title="Florence 2 VQA - Engineering Drawings",
    description="Upload an engineering drawing and ask a related question."
)

# Launch the Gradio interface
interface.launch()