Update README.md

README.md

@@ -38,16 +38,28 @@ from numpy.linalg import norm
 
 cos_sim = lambda a,b: (a @ b.T) / (norm(a)*norm(b))
 
+# Initialize the model
 model = AutoModel.from_pretrained('jinaai/jina-clip-v1', trust_remote_code=True)
 
-sentences = ['The Eiffel Tower is in Paris.', 'The capital of France is Paris.']
-images = ['tower.jpg', 'paris.jpg']  # here we use filenames, but it also accepts URL, PIL.Image objects and dataURI strings
+# New meaningful sentences
+sentences = ['Bridge close-shot', 'Bridge in far away']
 
-text_embeddings = model.encode_text(sentences)  # encode_text and encode_image are helper function made by us to easily get embeddings
-image_embeddings = model.encode_image(images)
+# Public image URLs
+image_urls = [
+    'https://fastly.picsum.photos/id/74/4288/2848.jpg?hmac=q02MzzHG23nkhJYRXR-_RgKTr6fpfwRgcXgE0EKvNB8',
+    'https://fastly.picsum.photos/id/84/1280/848.jpg?hmac=YFRYDI4UsfbeTzI8ZakNOR98wVU7a-9a2tGF542539s'
+]
 
+# Encode text and images
+text_embeddings = model.encode_text(sentences)
+image_embeddings = model.encode_image(image_urls)  # also accepts PIL.image, local filenames, dataURI
+
+# Compute similarities
 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
+print(cos_sim(text_embeddings[0], image_embeddings[1])) # text-image cross-modal similarity
+print(cos_sim(text_embeddings[1], image_embeddings[0])) # text-image cross-modal similarity
+print(cos_sim(text_embeddings[1], image_embeddings[1])) # text-image cross-modal similarity
 ```