Update app.py

app.py

@@ -3,37 +3,7 @@ from huggingface_hub import InferenceClient
 from sentence_transformers import SentenceTransformer
 import torch
 import gradio as gr
-import random
-
-def respond(message, history):
-    messages = [{"role":"system", "content":"You are a friendly chatbot :)"}]
-    if history:
-        messages.extend(history)
-    messages.append({"role":"user", "content":message})
-    response = client.chat_completion(messages, max_tokens=100, temperature=1.3, top_p=0.2)
-    # temperature and top_p control randomness
-    return response["choices"][0]["message"]["content"].strip()
-
-chat_theme = gr.themes.Soft(
-    primary_hue="indigo",
-    secondary_hue="purple",
-    neutral_hue="gray",
-    spacing_size="lg",
-    radius_size="lg"
-).set(
-    # Input area
-    input_background_fill="*neutral_50",
-    input_border_color_focus="*primary_300",
-    # Button styling
-    button_primary_background_fill="*primary_500",
-    button_primary_background_fill_hover="*primary_400"
-)
-
-chatbot = gr.ChatInterface(respond, type="messages", theme=chat_theme)
-
-chatbot.launch(ssr_mode=False)
-
-    
+import random 
 
 # Making requests to the model to generate responses:
 client = InferenceClient('Qwen/Qwen2.5-72B-Instruct') 
@@ -163,7 +133,24 @@ def respond(message, history):
     
     return response['choices'][0]['message']['content'].strip()
 
+chat_theme = gr.themes.Soft(
+    primary_hue="indigo",
+    secondary_hue="purple",
+    neutral_hue="gray",
+    spacing_size="lg",
+    radius_size="lg"
+).set(
+    # Input area
+    input_background_fill="*neutral_50",
+    input_border_color_focus="*primary_300",
+    # Button styling
+    button_primary_background_fill="*primary_500",
+    button_primary_background_fill_hover="*primary_400"
+)
 
+chatbot = gr.ChatInterface(respond, type="messages", theme=chat_theme)
+
+chatbot.launch(ssr_mode=False)
     
 chatbot = gr.ChatInterface(respond, type="messages")
 chatbot.launch()