Update app.py

app.py

@@ -484,8 +484,8 @@ with gr.Blocks(title="LLM Inference with ZeroGPU") as demo:
             p = gr.Slider(0.1, 1.0, value=0.9, step=0.05, label="Top-P")
             rp = gr.Slider(1.0, 2.0, value=1.2, step=0.1, label="Repetition Penalty")
             gr.Markdown("### Web Search Settings")
-            mr = gr.Number(value=6, precision=0, label="Max Results")
-            mc = gr.Number(value=600, precision=0, label="Max Chars/Result")
+            mr = gr.Number(value=4, precision=0, label="Max Results")
+            mc = gr.Number(value=50, precision=0, label="Max Chars/Result")
             st = gr.Slider(minimum=0.0, maximum=30.0, step=0.5, value=5.0, label="Search Timeout (s)")
             clr = gr.Button("Clear Chat")
             cnl = gr.Button("Cancel Generation")