Update app.py

app.py

@@ -97,24 +97,25 @@ def process_vision_query(image, text_input):
     response = vision_processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
     return response
 
-# Gradio interface
 with gr.Blocks() as demo:
     gr.HTML(TITLE)
     gr.Markdown(DESCRIPTION)
 
     with gr.Tab("Text Model (Phi-3.5-mini)"):
         chatbot = gr.Chatbot(height=600)
-        gr.ChatInterface(
-            fn=stream_text_chat,
-            chatbot=chatbot,
-            additional_inputs=[
-                gr.Textbox(value="You are a helpful assistant", label="System Prompt"),
-                gr.Slider(minimum=0, maximum=1, step=0.1, value=0.8, label="Temperature"),
-                gr.Slider(minimum=128, maximum=8192, step=1, value=1024, label="Max new tokens"),
-                gr.Slider(minimum=0.0, maximum=1.0, step=0.1, value=1.0, label="top_p"),
-                gr.Slider(minimum=1, maximum=20, step=1, value=20, label="top_k"),
-            ],
-        )
+        msg = gr.Textbox(label="Message")
+        with gr.Accordion("Advanced Options", open=False):
+            system_prompt = gr.Textbox(value="You are a helpful assistant", label="System Prompt")
+            temperature = gr.Slider(minimum=0, maximum=1, step=0.1, value=0.8, label="Temperature")
+            max_new_tokens = gr.Slider(minimum=128, maximum=8192, step=1, value=1024, label="Max new tokens")
+            top_p = gr.Slider(minimum=0.0, maximum=1.0, step=0.1, value=1.0, label="top_p")
+            top_k = gr.Slider(minimum=1, maximum=20, step=1, value=20, label="top_k")
+        
+        submit_btn = gr.Button("Submit")
+        clear_btn = gr.Button("Clear")
+
+        submit_btn.click(stream_text_chat, [msg, chatbot, system_prompt, temperature, max_new_tokens, top_p, top_k], [chatbot])
+        clear_btn.click(lambda: None, None, chatbot, queue=False)
 
     with gr.Tab("Vision Model (Phi-3.5-vision)"):
         with gr.Row():