Update app.py

app.py

@@ -15,7 +15,14 @@ hf_hub_download(repo_id=repo_id,
                 filename=model_name,local_dir =".")
 
 
-
+llm = LlamaCpp(
+        model_path=model_name,
+        temperature=temperature,
+        max_tokens=2000,
+        top_p=top_p,
+        callback_manager=callback_manager, 
+        verbose=True, # Verbose is required to pass to the callback manager
+    )
 def format_prompt(message, history):
   prompt = "<s>"
   for user_prompt, bot_response in history:
@@ -36,17 +43,11 @@ def generate(
  
     formatted_prompt = format_prompt(prompt, history)
     
-    llm = LlamaCpp(
-        model_path=model_name,
-        temperature=temperature,
-        max_tokens=2000,
-        top_p=top_p,
-        callback_manager=callback_manager, 
-        verbose=True, # Verbose is required to pass to the callback manager
-    )
+
     # stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
     output = ""
     output=llm(formatted_prompt)
+    output="ans:"+output
     # for response in stream:
     #     output += response.token.text
     #     yield output