Update app.py

app.py

@@ -1,7 +1,7 @@
 import time
 import logging
 import gradio as gr
-
+from src.llm_boilers import llm_boiler
 
 
 logging.basicConfig(format="%(asctime)s - %(message)s", level=logging.INFO)
@@ -110,18 +110,11 @@ def call_inf_server(prompt, openai_key):
         return response
 
 
- 
-
-theme = gr.themes.Glass(
-    primary_hue="amber",
-    secondary_hue="neutral",
-    neutral_hue="rose",
-    text_size="text_lg",
-   
-)
-with gr.Blocks(theme=theme) as demo:
-
- gr.Markdown(
+with gr.Blocks(
+    theme=gr.themes.Soft(),
+    css=".disclaimer {font-variant-caps: all-small-caps;}",
+) as demo:
+    gr.Markdown(
         """<h1><center>Chat with gpt-3.5-turbo</center></h1>
         This is a lightweight demo of gpt-3.5-turbo conversation completion. It was designed as a template for in-context learning applications to be built on top of.
 """
@@ -224,3 +217,6 @@ with gr.Blocks(theme=theme) as demo:
         outputs=[system],
         queue=False,
     )
+
+
+demo.queue(max_size=36, concurrency_count=14).launch(debug=True)