[Deploy] Refactor the quick start example, use public ip as default.

python/examples/deploy/quick_start/config.yaml

@@ -1,21 +1,8 @@
-workspace: "./src"
+workspace: "."
 entry_point: "main_entry.py"
+
 # If you want to install some packages
 # Please write the command in the bootstrap.sh
 bootstrap: |
-  echo "Bootstrap start..."
-  sh ./config/bootstrap.sh
-  echo "Bootstrap finished"
-
-# If you do not have any GPU resource but want to serve the model
-# Try FedML® Nexus AI Platform, and Uncomment the following lines.
-# ------------------------------------------------------------
-computing:
-  minimum_num_gpus: 1           # minimum # of GPUs to provision
-  maximum_cost_per_hour: $3000   # max cost per hour for your job per gpu card
-  #allow_cross_cloud_resources: true # true, false
-  #device_type: CPU              # options: GPU, CPU, hybrid
-  resource_type: A100-80G       # e.g., A100-80G,
-  # please check the resource type list by "fedml show-resource-type"
-  # or visiting URL: https://open.fedml.ai/accelerator_resource_type
-# ------------------------------------------------------------
+  echo "Install some packages..."
+  echo "Install finished!"

python/examples/deploy/quick_start/main_entry.py

@@ -0,0 +1,27 @@
+from fedml.serving import FedMLPredictor
+from fedml.serving import FedMLInferenceRunner
+
+
+class Bot(FedMLPredictor):  # Inherit FedMLClientPredictor
+    def __init__(self):
+        super().__init__()
+
+        # --- Your model initialization code here ---
+
+        # -------------------------------------------
+
+    def predict(self, request: dict):
+        input_dict = request
+        question: str = input_dict.get("text", "").strip()
+
+        # --- Your model inference code here ---
+        response = "I do not know the answer to your question."
+        # ---------------------------------------
+
+        return {"generated_text": f"The answer to your question {question} is: {response}"}
+
+
+if __name__ == "__main__":
+    chatbot = Bot()
+    fedml_inference_runner = FedMLInferenceRunner(chatbot)
+    fedml_inference_runner.run()