app.py

import gradio as gr
import spaces
import torch
from transformers import AutoProcessor, AutoModelForZeroShotImageClassification
from datasets import load_dataset

dataset = load_dataset("not-lain/embedded-pokemon", split="train")
dataset = dataset.add_faiss_index("embeddings")

device = "cuda" if torch.cuda.is_available() else "cpu"

processor = AutoProcessor.from_pretrained("openai/clip-vit-large-patch14")
model = AutoModelForZeroShotImageClassification.from_pretrained(
    "openai/clip-vit-large-patch14", device_map=device
)


@spaces.GPU
def search(query: str, k: int = 4 ):
    """a function that embeds a new image and returns the most probable results"""

    pixel_values = processor(images = query, return_tensors="pt")['pixel_values'] # embed new image
    pixel_values = pixel_values.to(device)
    img_emb = model.get_image_features(pixel_values)[0] # because 1 element
    img_emb = img_emb.cpu().detach().numpy() # because datasets only works with numpy

    scores, retrieved_examples = dataset.get_nearest_examples( # retrieve results
        "embeddings", img_emb, # compare our new embedded query with the dataset embeddings
        k=k # get only top k results
    )

    return retrieved_examples["image"]


demo = gr.Interface(search, inputs="image", outputs=["gallery"])

demo.launch(debug=True)