app.py

from sentence_transformers import SentenceTransformer, util
from PIL import Image
from io import BytesIO
import gradio as gr
import requests

def get_image_embedding(image):
    image_model = SentenceTransformer('clip-ViT-B-32')

    # Load and preprocess the image
    img_emb = image_model.encode(image)
    print(img_emb)
    print(type(img_emb))
    return {"embedding": img_emb.tolist()}

def get_text_embedding(text):
    multilingual_text_model = SentenceTransformer('clip-ViT-B-32-multilingual-v1')
    text_emb = multilingual_text_model.encode(text)
    return {"embedding": text_emb}

image_embedding = gr.Interface(fn=get_image_embedding, inputs=gr.Image(type="pil"), outputs=gr.JSON())
text_embedding = gr.Interface(fn=get_text_embedding, inputs=gr.Textbox(), outputs=gr.JSON())

space = gr.TabbedInterface([image_embedding, text_embedding], ["Image Embedding", "Text Embedding"])
space.launch()