Update app.py

app.py

@@ -1,19 +1,10 @@
 import gradio as gr
-from inference_fine_tune import generate_response  # generator-based inference code
-print("Gradio version:", gr.__version__)
-
-
-def chat_interface(prompt):
-    return generate_response(prompt)  # returns a generator
-
-with gr.Blocks() as demo:
-    gr.Markdown("## Chat with the Model")
-    with gr.Row():
-        inp = gr.Textbox(label="Your Prompt", placeholder="Enter your message...", lines=3)
-    out = gr.Textbox(label="Model Response", lines=10)
-
-    btn = gr.Button("Send")
-    # ✅ Enable streaming to allow generator output to be rendered step-by-step
-    btn.click(chat_interface, inputs=inp, outputs=out, streaming=True)
-
-demo.launch(share=True)
+from inference_fine_tune import generate_response
+
+with gr.ChatInterface(
+    fn=generate_response,
+    title="🧠 Chat with Fine-Tuned Model",
+    description="Ask me anything using your custom fine-tuned LLM.",
+    theme="soft",
+) as demo:
+    demo.launch(share=True)