Update README.md

README.md

@@ -55,19 +55,13 @@ from PIL import Image
 
 cos_sim = lambda a,b: (a @ b.T) / (norm(a)*norm(b))
 
-tokenizer = AutoTokenizer.from_pretrained('jinaai/jina-clip-v1', trust_remote_code=True)
-image_processor = AutoImageProcessor.from_pretrained('jinaai/jina-clip-v1', trust_remote_code=True)
 model = AutoModel.from_pretrained('jinaai/jina-clip-v1', trust_remote_code=True)
 
-text_inputs = tokenizer(
-    ['How is the weather today?', 'What is the current weather like today?'],
-    return_tensors='pt',
-    padding='longest',
-)
-image_inputs = image_processor([Image.open('raindrop.png').load()])
+sentences = ['How is the weather today?', 'What is the current weather like today?']
+images = ['raindrop.jpg', 'sunny.jpg']
 
-text_embeddings = model.get_text_features(text_inputs)
-image_embeddings = model.get_image_features(image_inputs)
+text_embeddings = model.encode_text(sentences)
+image_embeddings = model.encode_image(images)
 
 print(cos_sim(text_embeddings[0], text_embeddings[1])) # text embedding similarity
 print(cos_sim(text_embeddings[0], image_embeddings[0])) # text-image cross-modal similarity