docs: update usage in README

README.md

@@ -48,14 +48,19 @@ Jina CLIP V1 [technical report]() coming soon.
 You can use Jina CLIP directly from transformers package.
 
 ```python
-!pip install transformers
-from transformers import AutoModel
+!pip install transformers einops timm
+from transformers import AutoModel, AutoTokenizer, AutoImageProcessor
 from numpy.linalg import norm
 
 cos_sim = lambda a,b: (a @ b.T) / (norm(a)*norm(b))
-model = AutoModel.from_pretrained('jinaai/jina-clip-v1')
+
+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_embeddings = model.encode_text(['How is the weather today?', 'What is the current weather like today?'])
 image_embeddings = model.encode_image(['raindrop.png'])
+
 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
 ```