Update app.py

app.py

@@ -23,14 +23,7 @@ chat_model = ChatNVIDIA(model="llama2_13b") | StrOutputParser()
 response_prompt = ChatPromptTemplate.from_messages([("system", "{system}"), ("user", "{input}")])
 
 
-class Timer():
-    '''Useful timing utilities (%%time is great, but doesn't work for async)'''
-    def __enter__(self):
-      self.start = time.perf_counter()
 
-    def __exit__(self, *args, **kwargs):
-        elapsed = time.perf_counter() - self.start
-        print("\033[1m" + f"Executed in {elapsed:0.2f} seconds." + "\033[0m")
 
         
 def train_model_neural_network(class0, class1):
@@ -120,7 +113,7 @@ responses_4 = (gen_prompt | instruct_llm).invoke(
 good_responses = responses_1 + responses_2
 poor_responses = responses_3 + responses_4
     
-with Timer():
+async def embeding():
     good_tasks = [embed(query) for query in good_responses]
     poor_tasks = [embed(query) for query in poor_responses]
     all_tasks = good_tasks + poor_tasks
@@ -128,6 +121,8 @@ with Timer():
     good_embeds = embeds[:len(good_tasks)]
     poor_embeds = embeds[len(good_tasks):]
 
+embeding()
+
 model1 = train_model_neural_network(poor_embeds, good_embeds)
 
 def RPrint(preface=""):