vision-agent 0.2.105__tar.gz → 0.2.107__tar.gz

{vision_agent-0.2.105 → vision_agent-0.2.107}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vision-agent
-Version: 0.2.105
+Version: 0.2.107
 Summary: Toolset for Vision Agent
 Author: Landing AI
 Author-email: dev@landing.ai
@@ -10,8 +10,8 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Requires-Dist: anthropic (>=0.31.0,<0.32.0)
-Requires-Dist: e2b (>=0.17.1,<0.18.0)
-Requires-Dist: e2b-code-interpreter (==0.0.11a27)
+Requires-Dist: e2b (>=0.17.2a50,<0.18.0)
+Requires-Dist: e2b-code-interpreter (==0.0.11a37)
 Requires-Dist: ipykernel (>=6.29.4,<7.0.0)
 Requires-Dist: langsmith (>=0.1.58,<0.2.0)
 Requires-Dist: moviepy (>=1.0.0,<2.0.0)

{vision_agent-0.2.105 → vision_agent-0.2.107}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "vision-agent"
-version = "0.2.105"
+version = "0.2.107"
 description = "Toolset for Vision Agent"
 authors = ["Landing AI <dev@landing.ai>"]
 readme = "README.md"
@@ -35,8 +35,8 @@ nbformat = "^5.10.4"
 rich = "^13.7.1"
 langsmith = "^0.1.58"
 ipykernel = "^6.29.4"
-e2b = "^0.17.1"
-e2b-code-interpreter = "0.0.11a27"
+e2b = "^0.17.2a50"
+e2b-code-interpreter = "0.0.11a37"
 tenacity = "^8.3.0"
 pillow-heif = "^0.16.0"
 pytube = "15.0.0"

{vision_agent-0.2.105 → vision_agent-0.2.107}/vision_agent/tools/tools.py

@@ -607,12 +607,13 @@ def florencev2_image_caption(image: np.ndarray, detail_caption: bool = True) ->
     return answer[task]  # type: ignore
 
 
-def florencev2_object_detection(image: np.ndarray, prompt: str) -> List[Dict[str, Any]]:
+def florencev2_object_detection(prompt: str, image: np.ndarray) -> List[Dict[str, Any]]:
     """'florencev2_object_detection' is a tool that can detect objects given a text
     prompt such as a phrase or class names separated by commas. It returns a list of
     detected objects as labels and their location as bounding boxes with score of 1.0.
 
     Parameters:
+        prompt (str): The prompt to ground to the image.
         image (np.ndarray): The image to used to detect objects
 
     Returns:
@@ -624,7 +625,7 @@ def florencev2_object_detection(image: np.ndarray, prompt: str) -> List[Dict[str
 
     Example
     -------
-        >>> florencev2_object_detection(image, 'person looking at a coyote')
+        >>> florencev2_object_detection('person looking at a coyote', image)
         [
             {'score': 1.0, 'label': 'person', 'bbox': [0.1, 0.11, 0.35, 0.4]},
             {'score': 1.0, 'label': 'coyote', 'bbox': [0.34, 0.21, 0.85, 0.5},