adjust readme

Signed-off-by: [email protected] <[email protected]>

README.md

@@ -21683,7 +21683,10 @@ embeddings = model.encode(
 )
 ```
 
-Furthermore, you can use ONNX for efficient inference with `jina-embeddings-v3`:
+**<details><summary>ONNX Inference.</summary>**
+<p>
+
+You can use ONNX for efficient inference with `jina-embeddings-v3`:
 ```python
 import onnxruntime
 import numpy as np
@@ -21713,6 +21716,8 @@ inputs = {
 outputs = session.run(None, inputs)
 ```
 
+</p>
+</details>
 
 
 ## Contact