Update app.py

app.py

@@ -5,10 +5,10 @@ from huggingface_hub import InferenceClient
 def respond(
     message,
     history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
+    system_message="Your are an helpful assistant",
+    max_tokens=2048,
+    temperature=0.0,
+    top_p=None,
     hf_token: gr.OAuthToken,
 ):
     """
@@ -18,7 +18,7 @@ def respond(
 
     messages = [{"role": "system", "content": system_message}]
 
-    messages.extend(history)
+    # messages.extend(history)
 
     messages.append({"role": "user", "content": message})
 
@@ -46,18 +46,18 @@ For information on how to customize the ChatInterface, peruse the gradio docs: h
 chatbot = gr.ChatInterface(
     respond,
     type="messages",
-    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)",
-        ),
-    ],
+    #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)",
+    #    ),
+    #],
 )
 
 with gr.Blocks() as demo: