Update app.py

app.py

@@ -6,40 +6,38 @@ from huggingface_hub import login
 # Fetch token from environment (automatically loaded from secrets)
 hf_token = os.getenv("gemma3")
 login(hf_token)
-
+# Initialize the client with your model
 client = InferenceClient("hackergeek98/gemma-finetuned")
 
 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,
 ):
+    # Build a prompt from the system message and conversation history
     prompt = f"{system_message}\n"
-    
-    # Add conversation history if needed
-    for val in history:
-        if val[0]:
-            prompt += f"User: {val[0]}\n"
-        if val[1]:
-            prompt += f"Assistant: {val[1]}\n"
-
-    prompt += f"User: {message}\nAssistant:"
-
-    # Request generation from Hugging Face Inference API
+    for user_msg, assistant_msg in history:
+        if user_msg:
+            prompt += f"User: {user_msg}\n"
+        if assistant_msg:
+            prompt += f"Assistant: {assistant_msg}\n"
+    prompt += f"User: {message}\nAssistant: "
+
+    # Call the text generation API with the correct 'prompt' parameter
     response = client.text_generation(
         model="hackergeek98/gemma-finetuned",
-        inputs=prompt,
+        prompt=prompt,
         max_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
     )
 
-    return response['generated_text']
+    return response["generated_text"]
 
-# Gradio interface setup
+# Set up the Gradio Chat Interface
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -50,7 +48,7 @@ demo = gr.ChatInterface(
     ],
 )
 
-# Run the app
 if __name__ == "__main__":
     demo.launch()
 
+