init

llava/conversation.py

@@ -195,7 +195,7 @@ class Conversation:
                         image_format='JPEG')
                     img_str = f'<img src="data:image/jpeg;base64,{img_b64_str}" alt="user upload image" />'
                     msg=img_str
-                    if not extra_coordinates:
+                    if extra_coordinates:
                         ret.append(["The element is at {extra_coordinates} on the screen:",None])
                     ret.append([msg, None])
                 break

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "uground_demo_test"
-version = "4.0"
+version = "4.1"
 description = "Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents"
 readme = "README.md"
 requires-python = ">=3.8"