vision-agent 0.2.197__py3-none-any.whl → 0.2.199__py3-none-any.whl

vision_agent/.sim_tools/df.csv

@@ -80,24 +80,6 @@ desc,doc,name
             {'label': 'hello world', 'bbox': [0.1, 0.11, 0.35, 0.4], 'score': 0.99},
         ]
     ",ocr
-'clip' is a tool that can classify an image or a cropped detection given a list of input classes or tags. It returns the same list of the input classes along with their probability scores based on image content.,"clip(image: numpy.ndarray, classes: List[str]) -> Dict[str, Any]:
-'clip' is a tool that can classify an image or a cropped detection given a list
-    of input classes or tags. It returns the same list of the input classes along with
-    their probability scores based on image content.
-
-    Parameters:
-        image (np.ndarray): The image to classify or tag
-        classes (List[str]): The list of classes or tags that is associated with the image
-
-    Returns:
-        Dict[str, Any]: A dictionary containing the labels and scores. One dictionary
-            contains a list of given labels and other a list of scores.
-
-    Example
-    -------
-        >>> clip(image, ['dog', 'cat', 'bird'])
-        {""labels"": [""dog"", ""cat"", ""bird""], ""scores"": [0.68, 0.30, 0.02]},
-    ",clip
 'vit_image_classification' is a tool that can classify an image. It returns a list of classes and their probability scores based on image content.,"vit_image_classification(image: numpy.ndarray) -> Dict[str, Any]:
 'vit_image_classification' is a tool that can classify an image. It returns a
     list of classes and their probability scores based on image content.
@@ -488,6 +470,24 @@ desc,doc,name
         ... )
         >>> save_image(result, ""inpainted_room.png"")
     ",flux_image_inpainting
+'siglip_classification' is a tool that can classify an image or a cropped detection given a list of input labels or tags. It returns the same list of the input labels along with their probability scores based on image content.,"siglip_classification(image: numpy.ndarray, labels: List[str]) -> Dict[str, Any]:
+'siglip_classification' is a tool that can classify an image or a cropped detection given a list
+    of input labels or tags. It returns the same list of the input labels along with
+    their probability scores based on image content.
+
+    Parameters:
+        image (np.ndarray): The image to classify or tag
+        labels (List[str]): The list of labels or tags that is associated with the image
+
+    Returns:
+        Dict[str, Any]: A dictionary containing the labels and scores. One dictionary
+            contains a list of given labels and other a list of scores.
+
+    Example
+    -------
+        >>> siglip_classification(image, ['dog', 'cat', 'bird'])
+        {""labels"": [""dog"", ""cat"", ""bird""], ""scores"": [0.68, 0.30, 0.02]},
+    ",siglip_classification
 "'extract_frames_and_timestamps' extracts frames and timestamps from a video which can be a file path, url or youtube link, returns a list of dictionaries with keys ""frame"" and ""timestamp"" where ""frame"" is a numpy array and ""timestamp"" is the relative time in seconds where the frame was captured. The frame is a numpy array.","extract_frames_and_timestamps(video_uri: Union[str, pathlib.Path], fps: float = 1) -> List[Dict[str, Union[numpy.ndarray, float]]]:
 'extract_frames_and_timestamps' extracts frames and timestamps from a video
     which can be a file path, url or youtube link, returns a list of dictionaries

vision_agent/tools/tools.py

@@ -2453,7 +2453,6 @@ FUNCTION_TOOLS = [
     owl_v2_image,
     owl_v2_video,
     ocr,
-    clip,
     vit_image_classification,
     vit_nsfw_classification,
     countgd_counting,
@@ -2471,6 +2470,7 @@ FUNCTION_TOOLS = [
     qwen2_vl_video_vqa,
     video_temporal_localization,
     flux_image_inpainting,
+    siglip_classification,
 ]
 
 UTIL_TOOLS = [

{vision_agent-0.2.197.dist-info → vision_agent-0.2.199.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vision-agent
-Version: 0.2.197
+Version: 0.2.199
 Summary: Toolset for Vision Agent
 Author: Landing AI
 Author-email: dev@landing.ai

{vision_agent-0.2.197.dist-info → vision_agent-0.2.199.dist-info}/RECORD

@@ -1,5 +1,5 @@
-vision_agent/.sim_tools/df.csv,sha256=IPYWrI8W8r7zs2-QRjGsAzlg1O3wqngGRSyz9F-BOpo,34008
-vision_agent/.sim_tools/embs.npy,sha256=ItJgcBpT0--0HeZjUV30INzFXNQh-12HoUVevNY38dc,356480
+vision_agent/.sim_tools/df.csv,sha256=0fmLwTDjnRTiqYwamTOdCPjruE6wZz0AVrONIPTHxZY,34086
+vision_agent/.sim_tools/embs.npy,sha256=xF8Cg7Xd09QCTySj831aL1O2_0kRNaaH8XRJIRjgWzQ,356480
 vision_agent/__init__.py,sha256=EAb4-f9iyuEYkBrX4ag1syM8Syx8118_t0R6_C34M9w,57
 vision_agent/agent/__init__.py,sha256=j4W3zHXKE96o93ZziY62ZBWgicLYEink1rIU3gPsfwM,548
 vision_agent/agent/agent.py,sha256=2cjIOxEuSJrqbfPXYoV0qER5ihXsPFCoEFJa4jpqan0,597
@@ -27,7 +27,7 @@ vision_agent/tools/meta_tools.py,sha256=by7TIbH7lsLIayX_Pe2mS1iw8aeLn2T8yqAo8SkB
 vision_agent/tools/planner_tools.py,sha256=FROahw_6Taqvytv6pOjCHUEypOfjsi_f8Vo1c5vz6Mw,8823
 vision_agent/tools/prompts.py,sha256=V1z4YJLXZuUl_iZ5rY0M5hHc_2tmMEUKr0WocXKGt4E,1430
 vision_agent/tools/tool_utils.py,sha256=GDGOmBCo4UfYz-DJ-olREJHPsqs5mzHu0YXiAnpNE8E,10179
-vision_agent/tools/tools.py,sha256=Q8QSuOUk0df_XueU856vi21GOolp2TB3_f0WvMayjIA,87835
+vision_agent/tools/tools.py,sha256=wXDs0m_Yb601FQVp5fPYYVtt4lHUeMnuqIbfDZhsE4Q,87852
 vision_agent/tools/tools_types.py,sha256=8hYf2OZhI58gvf65KGaeGkt4EQ56nwLFqIQDPHioOBc,2339
 vision_agent/utils/__init__.py,sha256=7fMgbZiEwbNS0fBOS_hJI5PuEYBblw36zLi_UjUzvj4,244
 vision_agent/utils/exceptions.py,sha256=booSPSuoULF7OXRr_YbC4dtKt6gM_HyiFQHBuaW86C4,2052
@@ -36,7 +36,7 @@ vision_agent/utils/image_utils.py,sha256=rRWcxKggPXIRXIY_XT9rZt30ECDRq8zq7FDeXRD
 vision_agent/utils/sim.py,sha256=NZc9QGD6BTY5O29NVbHH7oxDePL_QMnylT1lYcDUn1Y,7437
 vision_agent/utils/type_defs.py,sha256=BE12s3JNQy36QvauXHjwyeffVh5enfcvd4vTzSwvEZI,1384
 vision_agent/utils/video.py,sha256=tRcGp4vEnaDycigL1hBO9k0FBPtDH35fCQciVr9GqYI,6013
-vision_agent-0.2.197.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-vision_agent-0.2.197.dist-info/METADATA,sha256=b_qATdG-j1o9ksVxISHe_-NcUdd0HMgZAVF9r6Y10ek,19026
-vision_agent-0.2.197.dist-info/WHEEL,sha256=7Z8_27uaHI_UZAc4Uox4PpBhQ9Y5_modZXWMxtUi4NU,88
-vision_agent-0.2.197.dist-info/RECORD,,
+vision_agent-0.2.199.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+vision_agent-0.2.199.dist-info/METADATA,sha256=NbaPI49uOha3uZXbfOokpji32pilLujBz7DcmhaXW1M,19026
+vision_agent-0.2.199.dist-info/WHEEL,sha256=7Z8_27uaHI_UZAc4Uox4PpBhQ9Y5_modZXWMxtUi4NU,88
+vision_agent-0.2.199.dist-info/RECORD,,