Update app.py

app.py

@@ -27,24 +27,21 @@ def chat_with_assistant(message, history):
         role="user",
         content=message
     )
-    
-    # Run the assistant
-    run = client.beta.threads.runs.create(
-        thread_id=thread.id,
-        assistant_id=assistant_id
+
+    # Run the assistant with streaming
+    response = client.chat.completions.create(
+        model='gpt-4o-mini',
+        messages=[{'role': 'user', 'content': message}],
+        stream=True
     )
     
-    # Wait for the assistant's response
-    while True:
-        run_status = client.beta.threads.runs.retrieve(thread_id=thread.id, run_id=run.id)
-        if run_status.status == 'completed':
-            # Retrieve the assistant's response
-            messages = client.beta.threads.messages.list(thread_id=thread.id)
-            assistant_response = messages.data[0].content[0].text.value
-            break
-        time.sleep(1)
-    
-    return assistant_response
+    # Handle the streaming response
+    response_text = ""
+    for chunk in response:
+        delta = chunk['choices'][0]['delta']
+        if 'content' in delta:
+            response_text += delta['content']
+            yield response_text
 
 # Custom CSS for chat bubbles and colors
 custom_css = """
@@ -72,12 +69,14 @@ with gr.Blocks(css=custom_css) as demo:
 
     def bot(history):
         user_message = history[-1][0]
-        bot_message = chat_with_assistant(user_message, history)
-        history[-1][1] = bot_message
+        bot_message = ""
+        for response_text in chat_with_assistant(user_message, history):
+            history[-1][1] = response_text
+            chatbot.update(history)
         return history
 
     msg.submit(user, [msg, chatbot], [msg, chatbot], queue=False).then(
         bot, chatbot, chatbot
     )
 
-demo.launch(auth=(username, password))
+demo.launch(auth=(username, password))