Update app.py

app.py

@@ -1,64 +1,82 @@
 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("hemhemoh/Gemma-2-2b-it-wazobia-wellness-bot")
+class ChatBot:
+    def __init__(self, model_name="hemhemoh/Gemma-2-2b-it-wazobia-wellness-bot"):
+        self.client = InferenceClient(model_name)
+        
+    def format_messages(self, message, history):
+        # Gemma doesn't support system messages, so we'll only include chat history
+        formatted_messages = []
+        for user_msg, assistant_msg in history:
+            if user_msg:
+                formatted_messages.append({"role": "user", "content": user_msg})
+            if assistant_msg:
+                formatted_messages.append({"role": "assistant", "content": assistant_msg})
+        
+        # Add the current message
+        formatted_messages.append({"role": "user", "content": message})
+        return formatted_messages
 
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    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]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
+    def generate_response(
+        self,
+        message,
+        history,
+        max_tokens=512,
+        temperature=0.7,
+        top_p=0.95,
     ):
-        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
-"""
-demo = gr.ChatInterface(
-    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"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
+        messages = self.format_messages(message, history)
+        response = ""
+        
+        try:
+            for chunk in self.client.chat_completion(
+                messages,
+                max_tokens=max_tokens,
+                stream=True,
+                temperature=temperature,
+                top_p=top_p,
+            ):
+                if chunk.choices and chunk.choices[0].delta.content is not None:
+                    token = chunk.choices[0].delta.content
+                    response += token
+                    yield response
+        except Exception as e:
+            yield f"Error: {str(e)}"
 
+def main():
+    chatbot = ChatBot()
+    
+    demo = gr.ChatInterface(
+        chatbot.generate_response,
+        additional_inputs=[
+            gr.Slider(
+                minimum=1,
+                maximum=2048,
+                value=512,
+                step=1,
+                label="Max new tokens"
+            ),
+            gr.Slider(
+                minimum=0.1,
+                maximum=4.0,
+                value=0.7,
+                step=0.1,
+                label="Temperature"
+            ),
+            gr.Slider(
+                minimum=0.1,
+                maximum=1.0,
+                value=0.95,
+                step=0.05,
+                label="Top-p (nucleus sampling)"
+            ),
+        ],
+        title="Gemma Chat Interface",
+        description="Chat with the Gemma model. Note: System messages are not supported."
+    )
+    
+    demo.launch()
 
 if __name__ == "__main__":
-    demo.launch()
+    main()