import gradio as gr
import torch
import clip
from PIL import Image

device = "cuda" if torch.cuda.is_available() else "cpu"
model, preprocess = clip.load("ViT-B/32", device=device)

def process_image_and_text(image, text):
    
    text = text.split(",")
    image = Image.fromarray(image)
    image = preprocess(image).unsqueeze(0).to(device)

    text_tokens = clip.tokenize(text).to(device)

    with torch.no_grad():
        image_features = model.encode_image(image)
        print(image_features.size())
        text_features = model.encode_text(text_tokens)
        
        logits_per_image, logits_per_text = model(image, text_tokens)
        probs = logits_per_image.softmax(dim=-1)
        
    return probs.cpu().numpy()[0]

demo = gr.Interface(fn=process_image_and_text, inputs=['image', 'text'], outputs="text")
demo.launch()