Update app.py

app.py

@@ -1,49 +1,67 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-"""
-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")
-
+# Initialize the InferenceClient with the model ID from Hugging Face
+client = InferenceClient(model="HuggingFaceH4/zephyr-7b-beta")
 
 def respond(
-    message,
+    message: str,
     history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
+    system_message: str,
+    max_tokens: int,
+    temperature: float,
+    top_p: float,
 ):
-    messages = [{"role": "system", "content": system_message}]
+    """
+    Generates a response from the AI model based on the user's message and chat history.
+    
+    Args:
+        message (str): The user's input message.
+        history (list): A list of tuples representing the conversation history (user, assistant).
+        system_message (str): A system-level message guiding the AI's behavior.
+        max_tokens (int): The maximum number of tokens for the output.
+        temperature (float): Sampling temperature for controlling the randomness.
+        top_p (float): Top-p (nucleus sampling) for controlling diversity.
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    Yields:
+        str: The AI's response as it is generated.
+    """
+    
+    # Prepare the conversation history for the API call
+    messages = [{"role": "system", "content": system_message}]
+    
+    for user_input, assistant_response in history:
+        if user_input:
+            messages.append({"role": "user", "content": user_input})
+        if assistant_response:
+            messages.append({"role": "assistant", "content": assistant_response})
 
+    # Add the latest user message to the conversation
     messages.append({"role": "user", "content": message})
 
+    # Initialize an empty response
     response = ""
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+    try:
+        # Generate a response from the model with streaming
+        for message in client.chat_completion(
+            messages=messages,
+            max_tokens=max_tokens,
+            stream=True,
+            temperature=temperature,
+            top_p=top_p,
+        ):
+            token = message.choices[0].delta.content
+            response += token
+            yield response
+
+    except Exception as e:
+        yield f"An error occurred: {str(e)}"
+
+
+# Define the ChatInterface with additional input components for user customization
 demo = gr.ChatInterface(
-    respond,
+    fn=respond,
     additional_inputs=[
         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
@@ -56,8 +74,10 @@ demo = gr.ChatInterface(
             label="Top-p (nucleus sampling)",
         ),
     ],
+    title="Chatbot Interface",
+    description="A customizable chatbot interface using Hugging Face's Inference API.",
 )
 
-
+# Launch the Gradio interface
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()