Update app.py

app.py

@@ -1,41 +1,32 @@
-import gradio as gr
 from huggingface_hub import InferenceClient
+import gradio as gr
+import json
 
-""" 
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference 
-"""
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
-
-def respond(
-	message, 
-    history: list[tuple[str, str]], 
-    system_message, 
-    max_tokens, 
-    temperature, 
-    top_p
-):
+def respond(message, chat_history, system_message, max_tokens, temperature, top_p):
     try:
-        import json # Import json inside the function to avoid global import errors on spaces
+        # 1. Log received data (for debugging)
         data_received = {
             "message": message,
-            "history": history,
+            "chat_history": chat_history,  # Correct name
             "system_message": system_message,
             "max_tokens": max_tokens,
             "temperature": temperature,
             "top_p": top_p,
         }
-        print(json.dumps(data_received, indent=4))  # Pretty print it to the logs
+        print(json.dumps(data_received, indent=4))
 
+        # 2. Convert chat_history to messages format
         messages = [{"role": "system", "content": system_message}]
-        for val in history:
-            if val[0]:
-                messages.append({"role": "user", "content": val[0]})
-            if val[1]:
-                messages.append({"role": "assistant", "content": val[1]})
-
+        for user_msg, bot_msg in chat_history: #unpack the chat history
+            if user_msg:
+                messages.append({"role": "user", "content": user_msg})
+            if bot_msg:
+                messages.append({"role": "assistant", "content": bot_msg})
         messages.append({"role": "user", "content": message})
 
+        # 3. Call Inference API
         response = ""
         for message in client.chat_completion(
             messages,
@@ -49,18 +40,15 @@ def respond(
             yield response
 
     except Exception as e:
-        print(f"An error occurred: {e}")  # Log any errors
-        return "An error occurred during processing." # Return an error message to Gradio
+        print(f"An error occurred: {e}")
+        yield "An error occurred during processing."  # Important: Yield an error message
+
 
 
-""" 
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface 
-"""
-import gradio as gr # Import gradio here
-demo = gr.ChatInterface(
+demo = gr.Chatbot(  # Use gr.Chatbot
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are an AI assistant to respond to missed calls using text messaging. Keep responses short and specific.", label="System message"),
+        gr.Textbox(value="You are an AI assistant for missed calls. Keep responses short and specific.", label="System message"),
         gr.Slider(minimum=1, maximum=2048, value=100, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.2, step=0.1, label="Temperature"),
         gr.Slider(minimum=0.1, maximum=1.0, value=0.50, step=0.05, label="Top-p (nucleus sampling)"),