app.py

import torch
from PIL import Image
from transformers import AutoModel, AutoTokenizer
import gradio as gr

# Check if GPU is available and set the device
device = 'cuda' if torch.cuda.is_available() else 'cpu'

# Load the model and tokenizer
model = AutoModel.from_pretrained(
    'openbmb/MiniCPM-V',
    trust_remote_code=True,
    torch_dtype=torch.bfloat16 if device == 'cuda' else torch.float32
)
model = model.eval().to(device)
tokenizer = AutoTokenizer.from_pretrained('openbmb/MiniCPM-V', trust_remote_code=True)

# Function to process the image and question
def predict(image, question):
    image = image.convert('RGB')
    msgs = [{'role': 'user', 'content': [image, question]}]
    
    res = model.chat(image=None, msgs=msgs, tokenizer=tokenizer)
    
    generated_text = ""
    for new_text in res:
        generated_text += new_text
    return generated_text

# Set up the Gradio interface
iface = gr.Interface(
    fn=predict,
    inputs=[
        gr.Image(type="pil", label="Upload an Image"),
        gr.Textbox(label="Ask a Question")
    ],
    outputs="text",
    title="Image Question Answering",
    description="Upload an image and ask a question about its content."
)

# Launch the Gradio app
iface.launch()