Update app.py

app.py

@@ -2,14 +2,31 @@ import gradio as gr
 from openai import OpenAI
 import os
 
+# A helper function to show pop-up (toast) messages in the Gradio interface
+# and also keep them in the console for debugging. 
+# Note: gr.toast() only works during or after a Gradio event has started.
+#       If this code runs at the global level (on import), the pop-ups may 
+#       not appear. They *will* appear for any messages triggered during 
+#       a Gradio event (e.g. when the user sends a message).
+
+def show_loading_status(msg):
+    # Attempt to show pop-up via gr.toast (works when called inside a running Gradio event).
+    try:
+        gr.toast(msg)
+    except:
+        # If gr.toast() fails (e.g. called outside of an event), just ignore or pass
+        pass
+    # Also print to console for debugging
+    print(msg)
+
 ACCESS_TOKEN = os.getenv("HF_TOKEN")
-print("Access token loaded.")
+show_loading_status("Access token loaded.")
 
 client = OpenAI(
     base_url="https://api-inference.huggingface.co/v1/",
     api_key=ACCESS_TOKEN,
 )
-print("OpenAI client initialized.")
+show_loading_status("OpenAI client initialized.")
 
 
 def respond(
@@ -24,19 +41,19 @@ def respond(
     custom_model
 ):
 
-    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"Frequency Penalty: {frequency_penalty}, Seed: {seed}")
-    print(f"Selected model (custom_model): {custom_model}")
+    show_loading_status(f"Received message: {message}")
+    show_loading_status(f"History: {history}")
+    show_loading_status(f"System message: {system_message}")
+    show_loading_status(f"Max tokens: {max_tokens}, Temperature: {temperature}, Top-P: {top_p}")
+    show_loading_status(f"Frequency Penalty: {frequency_penalty}, Seed: {seed}")
+    show_loading_status(f"Selected model (custom_model): {custom_model}")
 
     # Convert seed to None if -1 (meaning random)
     if seed == -1:
         seed = None
 
     messages = [{"role": "system", "content": system_message}]
-    print("Initial messages array constructed.")
+    show_loading_status("Initial messages array constructed.")
 
     # Add conversation history to the context
     for val in history:
@@ -44,22 +61,22 @@ def respond(
         assistant_part = val[1]
         if user_part:
             messages.append({"role": "user", "content": user_part})
-            print(f"Added user message to context: {user_part}")
+            show_loading_status(f"Added user message to context: {user_part}")
         if assistant_part:
             messages.append({"role": "assistant", "content": assistant_part})
-            print(f"Added assistant message to context: {assistant_part}")
+            show_loading_status(f"Added assistant message to context: {assistant_part}")
 
     # Append the latest user message
     messages.append({"role": "user", "content": message})
-    print("Latest user message appended.")
+    show_loading_status("Latest user message appended.")
 
     # If user provided a model, use that; otherwise, fall back to a default model
     model_to_use = custom_model.strip() if custom_model.strip() != "" else "meta-llama/Llama-3.3-70B-Instruct"
-    print(f"Model selected for inference: {model_to_use}")
+    show_loading_status(f"Model selected for inference: {model_to_use}")
 
     # Start with an empty string to build the response as tokens stream in
     response = ""
-    print("Sending request to OpenAI API.")
+    show_loading_status("Sending request to OpenAI API.")
 
     for message_chunk in client.chat.completions.create(
         model=model_to_use,
@@ -72,16 +89,16 @@ def respond(
         messages=messages,
     ):
         token_text = message_chunk.choices[0].delta.content
-        print(f"Received token: {token_text}")
+        show_loading_status(f"Received token: {token_text}")
         response += token_text
         yield response
 
-    print("Completed response generation.")
+    show_loading_status("Completed response generation.")
 
 # GRADIO UI
 
-chatbot = gr.Chatbot(height=600, show_copy_button=True, placeholder="Select a model and begin chatting", layout="panel")
-print("Chatbot interface created.")
+chatbot = gr.Chatbot(height=600, show_copy_button=True, placeholder="Select a model and begin chatting", likeable=True, layout="panel")
+show_loading_status("Chatbot interface created.")
 
 system_message_box = gr.Textbox(value="", placeholder="You are a helpful assistant.", label="System Prompt")
 
@@ -130,11 +147,7 @@ custom_model_box = gr.Textbox(
 )
 
 def set_custom_model_from_radio(selected):
-    """
-    This function will get triggered whenever someone picks a model from the 'Featured Models' radio.
-    We will update the Custom Model text box with that selection automatically.
-    """
-    print(f"Featured model selected: {selected}")
+    show_loading_status(f"Featured model selected: {selected}")
     return selected
 
 demo = gr.ChatInterface(
@@ -152,7 +165,7 @@ demo = gr.ChatInterface(
     chatbot=chatbot,
     theme="Nymbo/Nymbo_Theme",
 )
-print("ChatInterface object created.")
+show_loading_status("ChatInterface object created.")
 
 with demo:
     with gr.Accordion("Model Selection", open=False):
@@ -161,7 +174,7 @@ with demo:
             placeholder="Search for a featured model...",
             lines=1
         )
-        print("Model search box created.")
+        show_loading_status("Model search box created.")
 
         models_list = [
             "meta-llama/Llama-3.3-70B-Instruct",
@@ -182,7 +195,7 @@ with demo:
             "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
             "microsoft/Phi-3.5-mini-instruct",
         ]
-        print("Models list initialized.")
+        show_loading_status("Models list initialized.")
 
         featured_model_radio = gr.Radio(
             label="Select a model below",
@@ -190,12 +203,12 @@ with demo:
             value="meta-llama/Llama-3.3-70B-Instruct",
             interactive=True
         )
-        print("Featured models radio button created.")
+        show_loading_status("Featured models radio button created.")
 
         def filter_models(search_term):
-            print(f"Filtering models with search term: {search_term}")
+            show_loading_status(f"Filtering models with search term: {search_term}")
             filtered = [m for m in models_list if search_term.lower() in m.lower()]
-            print(f"Filtered models: {filtered}")
+            show_loading_status(f"Filtered models: {filtered}")
             return gr.update(choices=filtered)
 
         model_search_box.change(
@@ -203,17 +216,17 @@ with demo:
             inputs=model_search_box,
             outputs=featured_model_radio
         )
-        print("Model search box change event linked.")
+        show_loading_status("Model search box change event linked.")
 
         featured_model_radio.change(
             fn=set_custom_model_from_radio,
             inputs=featured_model_radio,
             outputs=custom_model_box
         )
-        print("Featured model radio button change event linked.")
+        show_loading_status("Featured model radio button change event linked.")
 
-print("Gradio interface initialized.")
+show_loading_status("Gradio interface initialized.")
 
 if __name__ == "__main__":
-    print("Launching the demo application.")
+    show_loading_status("Launching the demo application.")
     demo.launch()