Merge branch 'zdy'

mm_agents/gpt_4v_agent.py

@@ -22,6 +22,10 @@ from mm_agents.prompts import SYS_PROMPT_IN_SCREENSHOT_OUT_CODE, SYS_PROMPT_IN_S
     SYS_PROMPT_IN_SOM_A11Y_OUT_TAG, \
     SYS_PROMPT_SEEACT, ACTION_DESCRIPTION_PROMPT_SEEACT, ACTION_GROUNDING_PROMPT_SEEACT
 
+import logging
+
+logger = logging.getLogger("desktopenv.agent")
+
 
 # Function to encode the image
 def encode_image(image_path):
@@ -252,6 +256,7 @@ class GPT4v_Agent:
             if self.exp == "both":
                 _screenshot = previous_obs["screenshot"]
                 _linearized_accessibility_tree = previous_obs["accessibility_tree"]
+                logger.debug("LINEAR AT: %s", _linearized_accessibility_tree)
 
                 messages.append({
                     "role": "user",
@@ -456,7 +461,7 @@ class GPT4v_Agent:
             "max_tokens": self.max_tokens
         })
 
-        print(response)
+        logger.debug("RESPONSE: %s", response)
 
         if self.exp == "seeact":
             messages.append({