Update app.py

app.py

@@ -1,5 +1,6 @@
 #refer llama recipes for more info https://github.com/huggingface/huggingface-llama-recipes/blob/main/inference-api.ipynb
 #huggingface-llama-recipes : https://github.com/huggingface/huggingface-llama-recipes/tree/main
+
 import gradio as gr
 from openai import OpenAI
 import os
@@ -22,11 +23,13 @@ def respond(
     max_tokens,
     temperature,
     top_p,
+    model_name,  # Added a parameter for model selection
 ):
     print(f"Received message: {message}")
     print(f"History: {history}")
     print(f"System message: {system_message}")
     print(f"Max tokens: {max_tokens}, Temperature: {temperature}, Top-P: {top_p}")
+    print(f"Selected model: {model_name}")
 
     messages = [{"role": "system", "content": system_message}]
 
@@ -44,7 +47,7 @@ def respond(
     print("Sending request to OpenAI API.")
     
     for message in client.chat.completions.create(
-        model="PowerInfer/SmallThinker-3B-Preview",
+        model=model_name,  # Use the selected model here
         max_tokens=max_tokens,
         stream=True,
         temperature=temperature,
@@ -62,9 +65,20 @@ chatbot = gr.Chatbot(height=600)
 
 print("Chatbot interface created.")
 
+# Define a list of models for the dropdown
+model_options = [
+    "microsoft/phi-4",
+    "PowerInfer/SmallThinker-3B-Preview",
+]
+
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
+        gr.Dropdown(
+            choices=model_options,
+            value="microsoft/phi-4",
+            label="Select Model",
+        ),
         gr.Textbox(value="", label="System message"),
         gr.Slider(minimum=1, maximum=4096, value=1024, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=1.0, value=0.3, step=0.1, label="Temperature"),
@@ -75,7 +89,6 @@ demo = gr.ChatInterface(
             step=0.05,
             label="Top-P",
         ),
-        
     ],
     fill_height=True,
     chatbot=chatbot,
@@ -85,4 +98,4 @@ print("Gradio interface initialized.")
 
 if __name__ == "__main__":
     print("Launching the demo application.")
-    demo.launch()
+    demo.launch()