Update app.py

app.py

@@ -29,6 +29,10 @@ def respond(message, history, model, approach, system_message, max_tokens, tempe
 
     if approach == "none":
         response = client.chat.completions.create(
+            extra_headers={
+            "HTTP-Referer": "https://github.com/codelion/optillm",
+            "X-Title": "optillm"    
+            },
             model=model,
             messages=messages,
             max_tokens=max_tokens,
@@ -84,7 +88,7 @@ def create_approach_dropdown():
     )
 
 with gr.Blocks() as demo:
-    gr.Markdown("# optillm - LLM Inference Comparison")
+    gr.Markdown("# LLM Optimization Comparison")
     
     with gr.Row():
         system_message = gr.Textbox(value="", label="System message")
@@ -93,12 +97,14 @@ with gr.Blocks() as demo:
         top_p = gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)")
     
     with gr.Tabs():
-        with gr.TabItem("Chat"):
+        with gr.TabItem("Single Chat"):
             model = create_model_dropdown()
             approach = create_approach_dropdown()
             chatbot = gr.Chatbot()
             msg = gr.Textbox()
-            clear = gr.Button("Clear")
+            with gr.Row():
+                submit = gr.Button("Submit")
+                clear = gr.Button("Clear")
 
             def user(user_message, history):
                 return "", history + [[user_message, None]]
@@ -112,6 +118,9 @@ with gr.Blocks() as demo:
             msg.submit(user, [msg, chatbot], [msg, chatbot]).then(
                 bot, [chatbot, model, approach, system_message, max_tokens, temperature, top_p], chatbot
             )
+            submit.click(user, [msg, chatbot], [msg, chatbot]).then(
+                bot, [chatbot, model, approach, system_message, max_tokens, temperature, top_p], chatbot
+            )
             clear.click(lambda: None, None, chatbot, queue=False)
 
         with gr.TabItem("Compare"):