Update app.py

app.py

@@ -1,7 +1,6 @@
 import gradio as gr
-from inference_fine_tune import generate_response  # your generator-based inference code
+from inference_fine_tune import generate_response  # generator-based inference code
 
-# This function streams the response
 def chat_interface(prompt):
     return generate_response(prompt)  # returns a generator
 
@@ -12,7 +11,7 @@ with gr.Blocks() as demo:
     out = gr.Textbox(label="Model Response", lines=10)
 
     btn = gr.Button("Send")
-    btn.click(chat_interface, inputs=inp, outputs=out)  # ✅ Set streaming=True)
+    # ✅ Enable streaming to allow generator output to be rendered step-by-step
+    btn.click(chat_interface, inputs=inp, outputs=out, streaming=True)
 
-# Launch for Hugging Face Spaces
 demo.launch(share=True)