Update app.py

app.py

@@ -12,15 +12,16 @@ model = AutoModelForCausalLM.from_pretrained(
     device_map="auto"
 )
 
-# Streaming response function
+# Streaming response generator
 def chat_with_dudea(message, history):
-    messages = [{"role": "system", "content": "You are DUDEAIBeta1.1, a fun and smart AI assistant."}]
+    messages = [{"role": "system", "content": "You are DUDEAIBeta1.1, a futuristic, smooth-talking assistant."}]
     for user_msg, bot_msg in history:
         messages.append({"role": "user", "content": user_msg})
         if bot_msg:
             messages.append({"role": "assistant", "content": bot_msg})
     messages.append({"role": "user", "content": message})
 
+    # Tokenize
     inputs = tokenizer.apply_chat_template(
         messages,
         add_generation_prompt=True,
@@ -29,48 +30,53 @@ def chat_with_dudea(message, history):
         return_tensors="pt"
     ).to(model.device)
 
+    # Create streamer
     streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
-    generation_kwargs = dict(inputs, max_new_tokens=250, streamer=streamer)
+    generation_kwargs = dict(inputs, max_new_tokens=300, streamer=streamer)
+
+    # Run model.generate in a background thread
     thread = threading.Thread(target=model.generate, kwargs=generation_kwargs)
     thread.start()
 
+    # Build response incrementally
     partial_response = ""
     for new_text in streamer:
         partial_response += new_text
-        yield partial_response
+        history[-1] = (message, partial_response)  # update last message
+        yield history  # 🔥 this yields live typing updates
 
 # Custom UI
 with gr.Blocks(css="""
-    #chatbox {height: 600px; overflow-y: auto;}
-    .message {display: flex; align-items: flex-start; margin: 10px;}
+    body {background: linear-gradient(135deg, #1e1e2f, #2c2c54); color: white; font-family: 'Inter', sans-serif;}
+    #chatbox {height: 600px; overflow-y: auto; background: rgba(255,255,255,0.05); border-radius: 20px; padding: 20px;}
+    .message {display: flex; align-items: flex-start; margin: 12px;}
     .user {flex-direction: row-reverse;}
-    .avatar {width: 50px; height: 50px; border-radius: 50%; margin: 5px;}
-    .bubble {padding: 12px 16px; border-radius: 16px; max-width: 70%;}
-    .user .bubble {background-color: #4f46e5; color: white; border-bottom-right-radius: 4px;}
-    .bot .bubble {background-color: #f3f4f6; color: black; border-bottom-left-radius: 4px;}
+    .avatar {width: 45px; height: 45px; border-radius: 50%; margin: 8px;}
+    .bubble {padding: 14px 18px; border-radius: 18px; max-width: 70%; animation: fadeIn 0.3s ease;}
+    .user .bubble {background: linear-gradient(135deg, #4f46e5, #6366f1); color: white; border-bottom-right-radius: 6px;}
+    .bot .bubble {background: rgba(255,255,255,0.1); color: #f3f4f6; border-bottom-left-radius: 6px; backdrop-filter: blur(8px);}
+    @keyframes fadeIn {from {opacity:0; transform: translateY(10px);} to {opacity:1; transform: translateY(0);}}
 """) as demo:
     gr.Markdown(
-        "<h1 style='text-align: center;'>🤖 DUDEAIBeta1.1</h1>"
-        "<p style='text-align:center;'>Next-gen AI with live typing ✨</p>"
+        "<h1 style='text-align: center; color:#9f9fff;'>🤖 DUDEAIBeta1.1</h1>"
+        "<p style='text-align:center; opacity:0.8;'>A smooth, next-gen AI chat with <b>live typing</b> ✨</p>"
     )
 
-    # 👇 put your avatar files in the Space repo (user.png, ai.png)
     chatbot = gr.Chatbot(
         elem_id="chatbox",
-        avatar_images=("user.png", "ai.png")  # first is USER, second is AI
+        avatar_images=("user.png", "ai.png")  # put these files in your repo
     )
 
-    msg = gr.Textbox(placeholder="Type your message...", container=False)
-    clear = gr.Button("🧹 Clear Chat")
+    with gr.Row():
+        msg = gr.Textbox(placeholder="Type your message...", container=False, scale=10)
+        clear = gr.Button("🧹", scale=1)
 
+    # Live streaming respond
     def respond(message, history):
-        response_stream = chat_with_dudea(message, history)
-        history.append((message, ""))
-        for partial in response_stream:
-            history[-1] = (message, partial)
-            yield "", history
+        history.append((message, ""))  # add user message
+        return chat_with_dudea(message, history)
 
-    msg.submit(respond, [msg, chatbot], [msg, chatbot])
+    msg.submit(respond, [msg, chatbot], [chatbot])
     clear.click(lambda: None, None, chatbot, queue=False)
 
 demo.launch()