diff --git a/06_gpu_and_ml/llm-serving/chat_with_pdf_vision.py b/06_gpu_and_ml/llm-serving/chat_with_pdf_vision.py
index eb91d1ef5..696537e76 100644
--- a/06_gpu_and_ml/llm-serving/chat_with_pdf_vision.py
+++ b/06_gpu_and_ml/llm-serving/chat_with_pdf_vision.py
@@ -110,7 +110,6 @@ def append_to_messages(message, user_type="user"):
 
         def generate_response(message, image):
             chatbot_message = get_chatbot_message_with_image(message, image)
-            print(chatbot_message, self.messages)
             query = self.qwen_processor.apply_chat_template(
                 [chatbot_message, *self.messages], tokenize=False, add_generation_prompt=True
             )
@@ -144,7 +143,6 @@ def generate_response(message, image):
         output_text = generate_response(message, relevant_image)
         append_to_messages(message, user_type="user")
         append_to_messages(output_text, user_type="assistant")
-        print("Response", type(output_text), output_text)
         return output_text
 
 web_app = FastAPI()