import gradio as gr
from PIL import Image
import requests
from transformers import CLIPProcessor, CLIPModel

model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")

def image_feature(url):
    image = Image.open(requests.get(url, stream=True).raw)
    inputs = processor(images=image, return_tensors="pt")
    image_features = model.get_image_features(**inputs)
    return image_features.detach().numpy().tolist()[0]

iface = gr.Interface(fn=image_feature, inputs="text", outputs="text")
iface.launch()