Update app.py

app.py

@@ -14,9 +14,12 @@ COHERE_MODEL = "command-r-plus"
 def respond(
     message,
     history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+    use_cohere_api,
 ):
-    use_cohere_api = False
-    system_message = "You are a friendly Chatbot."
     messages = [{"role": "system", "content": system_message}]
 
     for val in history:
@@ -33,15 +36,18 @@ def respond(
         cohere_response = client_cohere.chat(
             message=message,
             model=COHERE_MODEL,
-            max_tokens=512
+            temperature=temperature,
+            max_tokens=max_tokens
         )
         response = cohere_response.text
         yield response
     else:
         for message in client.chat_completion(
             messages,
-            max_tokens=512,
+            max_tokens=max_tokens,
             stream=True,
+            temperature=temperature,
+            top_p=top_p,
         ):
             token = message.choices[0].delta.content
             response += token
@@ -53,8 +59,21 @@ For information on how to customize the ChatInterface, peruse the gradio docs: h
 """
 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)",
+        ),
+        gr.Checkbox(label="Use Cohere API."),
+    ],
 )
 
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()