| from PIL import Image | |
| from transformers import CLIPProcessor, CLIPModel | |
| import torch | |
| clip_model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32") | |
| clip_processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32") | |
| async def get_clip_embedding(image: Image.Image): | |
| inputs = clip_processor(images=image, return_tensors="pt") | |
| with torch.no_grad(): | |
| embedding = clip_model.get_image_features(**inputs) | |
| embedding = embedding / embedding.norm(p=2, dim=-1) | |
| return embedding.squeeze().tolist() | |