Update examples/apps/ai_remote_infer_app/README.md

Co-authored-by: Copilot <[email protected]>
Signed-off-by: Ming M Qin <[email protected]>

Author: MMelQin

examples/apps/ai_remote_infer_app/README.md

@@ -6,7 +6,7 @@ This example application demonstrates how to perform medical image segmentation
 
 This application showcases:
 - **Remote inference using Triton Inference Server**: The app connects to a Triton server to perform model inference remotely rather than loading models locally, by sending and receiving input/output tensors corresponding to the model dimensions including channels
-- **Triton client integration**: The built-in `TritonRemoteModel` class in the [triton_model.py](https://github.com/Project-MONAI/monai-deploy-app-sdk/blob/137ac32d647843579f52060c8f72f9d9e8b51c38/monai/deploy/core/models/triton_model.py) module contains and acts as a Triton inference client, communicating with an already loaded model network on the server. It supports the same API as the in-process model class (e.g., a loaded TorchScript model network), so that the application inference operator does not need to change when switching between in-process and remote inference  
+- **Triton client integration**: The built-in `TritonRemoteModel` class is provided in the [triton_model.py](https://github.com/Project-MONAI/monai-deploy-app-sdk/blob/137ac32d647843579f52060c8f72f9d9e8b51c38/monai/deploy/core/models/triton_model.py) module. This class acts as a Triton inference client, communicating with an already loaded model network on the server. It supports the same API as the in-process model class (e.g., a loaded TorchScript model network). As a result, the application inference operator does not need to change when switching between in-process and remote inference.
 - **Model metadata parsing**: Uses Triton's model folder structure, which contains the `config.pbtxt` configuration file, to extract model specifications including name, input/output dimensions, and other metadata.
 - **Model path requirement**: The parent folder of the Triton model folder needs to be used as the model path for the application.