vision-agent 0.2.104__py3-none-any.whl → 0.2.106__py3-none-any.whl

vision_agent/tools/tools.py

@@ -148,7 +148,7 @@ def owl_v2(
 
     Example
     -------
-        >>> owl_v2("car. dinosaur", image)
+        >>> owl_v2("car, dinosaur", image)
         [
             {'score': 0.99, 'label': 'dinosaur', 'bbox': [0.1, 0.11, 0.35, 0.4]},
             {'score': 0.98, 'label': 'car', 'bbox': [0.2, 0.21, 0.45, 0.5},
@@ -157,7 +157,7 @@ def owl_v2(
     image_size = image.shape[:2]
     image_b64 = convert_to_b64(image)
     request_data = {
-        "prompts": prompt.split("."),
+        "prompts": prompt.split(","),
         "image": image_b64,
         "confidence": box_threshold,
         "function_name": "owl_v2",
@@ -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},

{vision_agent-0.2.104.dist-info → vision_agent-0.2.106.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vision-agent
-Version: 0.2.104
+Version: 0.2.106
 Summary: Toolset for Vision Agent
 Author: Landing AI
 Author-email: dev@landing.ai

{vision_agent-0.2.104.dist-info → vision_agent-0.2.106.dist-info}/RECORD

@@ -19,7 +19,7 @@ vision_agent/tools/meta_tools.py,sha256=v2FrLl0YwM7JwsVRfgfnryd9qorbPRiObestexbn
 vision_agent/tools/meta_tools_types.py,sha256=aU4knXEhm0AnDYW958T6Q6qPwN4yq8pQzQOxqFaOjzg,596
 vision_agent/tools/prompts.py,sha256=V1z4YJLXZuUl_iZ5rY0M5hHc_2tmMEUKr0WocXKGt4E,1430
 vision_agent/tools/tool_utils.py,sha256=ZhZ9oEcOvRSuWPy-gV0rx3pvaaXzBW-ZC3YQanXrq1g,4733
-vision_agent/tools/tools.py,sha256=fgPE0VHfBiQPJKkslBm_hugTOyRT-Hnw7eztvC-l4_o,44661
+vision_agent/tools/tools.py,sha256=4RooFWZvXPLgA9EA8tmMpFtgfbZIzZhxc0u3507_msA,44718
 vision_agent/utils/__init__.py,sha256=CW84HnhqI6XQVuxf2KifkLnSuO7EOhmuL09-gAymAak,219
 vision_agent/utils/exceptions.py,sha256=isVH-SVL4vHj3q5kK4z7cy5_aOapAqHXWkpibfSNbUs,1659
 vision_agent/utils/execute.py,sha256=ZRxztUfZwvMvPnFbKx5W_LZzTuKl8Zf5dP3Y8P2-3nk,25093
@@ -27,7 +27,7 @@ vision_agent/utils/image_utils.py,sha256=c_g5i_cFC0C-Yw9gU_NaVgQdmBlyumw3bLIDtCU
 vision_agent/utils/sim.py,sha256=7JvtWGN0Ik5ife3qQYWs7Fm3T8AnAXGFd5HnvDC15mQ,4433
 vision_agent/utils/type_defs.py,sha256=BE12s3JNQy36QvauXHjwyeffVh5enfcvd4vTzSwvEZI,1384
 vision_agent/utils/video.py,sha256=rNmU9KEIkZB5-EztZNlUiKYN0mm_55A_2VGUM0QpqLA,8779
-vision_agent-0.2.104.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-vision_agent-0.2.104.dist-info/METADATA,sha256=aSP8goyL8RZS_6SZSzrJZCsIzySrN_domJ2vvvbedQg,10729
-vision_agent-0.2.104.dist-info/WHEEL,sha256=7Z8_27uaHI_UZAc4Uox4PpBhQ9Y5_modZXWMxtUi4NU,88
-vision_agent-0.2.104.dist-info/RECORD,,
+vision_agent-0.2.106.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+vision_agent-0.2.106.dist-info/METADATA,sha256=sXXjGtL175BZlm2TGwyukzMMVJHBQrBdYqltK2X5mwM,10729
+vision_agent-0.2.106.dist-info/WHEEL,sha256=7Z8_27uaHI_UZAc4Uox4PpBhQ9Y5_modZXWMxtUi4NU,88
+vision_agent-0.2.106.dist-info/RECORD,,