Changes to support benchmarking

examples/mask_app/app.py

@@ -1,8 +1,9 @@
 import cv2
-import streamlit as st
 from PIL import Image
 from streamlit_drawable_canvas import st_canvas
 
+import streamlit as st
+
 st.title("Image Segmentation Mask App")
 
 uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "png"])

vision_agent/agent/vision_agent_prompts.py

@@ -179,6 +179,8 @@ def find_text(image_path: str, text: str) -> str:
 8. DO NOT use try except block to handle the error, let the error be raised if the code is incorrect.
 9. DO NOT import the testing function as it will available in the testing environment.
 10. Print the output of the function that is being tested.
+11. Use the output of the function that is being tested as the return value of the testing function.
+12. Run the testing function in the end and don't assign a variable to its output.
 """
 
 

vision_agent/utils/execute.py

@@ -2,6 +2,7 @@
 import atexit
 import base64
 import copy
+import json
 import logging
 import os
 import platform
@@ -309,6 +310,21 @@ def success(self) -> bool:
  """
  return self.error is None
 
+ def get_main_result(self) -> Optional[Result]:
+ """
+ Get the main result of the execution.
+ An execution may have multiple results, e.g. intermediate outputs. The main result is the last output of the cell execution.
+ """
+ if not self.success:
+ _LOGGER.info("Result is not available as the execution was not successful.")
+ return None
+ if not self.results or not any(res.is_main_result for res in self.results):
+ _LOGGER.info("Execution was successful but there is no main result.")
+ return None
+ main_result = self.results[-1]
+ assert main_result.is_main_result, "The last result should be the main result."
+ return main_result
+
  def to_json(self) -> str:
  """
  Returns the JSON representation of the Execution object.