app.py

import gradio as gr
import numpy as np
from PIL import Image
from sentence_transformers import SentenceTransformer

model = SentenceTransformer('clip-ViT-B-32')


def image_to_embedding(img: np.ndarray):
    embedding = model.encode(sentences=[Image.fromarray(img)], batch_size=128)
    return embedding


iface = gr.Interface(fn=image_to_embedding, inputs="image", outputs="textbox", cache_examples=True)
iface.launch()