Update app.py

app.py

@@ -4,12 +4,12 @@ import gradio as gr
 client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
 
 def format_prompt(message, history):
-  prompt = "<s>"
-  for user_prompt, bot_response in history:
-    prompt += f"[INST] {user_prompt} [/INST]"
-    prompt += f" {bot_response}</s> "
-  prompt += f"[INST] {message} [/INST]"
-  return prompt
+    prompt = "<s>"
+    for user_prompt, bot_response in history:
+        prompt += f"[INST] {user_prompt} [/INST]"
+        prompt += f" {bot_response}</s> "
+    prompt += f"[INST] {message} [/INST]"
+    return prompt
 
 def generate(
     prompt, history, temperature=0.2, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,
@@ -35,18 +35,19 @@ def generate(
 
     for response in stream:
         output += response.token.text
+        print(output)  # Print the response to the console
         yield output
     return output
 
-    
+
 mychatbot = gr.Chatbot(
     avatar_images=["./user.png", "./Ember Logo.png"], bubble_full_width=False, show_label=False, show_copy_button=True, likeable=True,)
 
-demo = gr.ChatInterface(fn=generate, 
+demo = gr.ChatInterface(fn=generate,
                         chatbot=mychatbot,
                         title="Ember_Chat_25",
                         retry_btn=None,
                         undo_btn=None
                        )
 
-demo.queue().launch(show_api=False)
+demo.queue().launch(show_api=False)