vision-agent 0.2.188__py3-none-any.whl → 0.2.190__py3-none-any.whl

vision_agent/tools/__init__.py

@@ -69,6 +69,7 @@ from .tools import (
     qwen2_vl_video_vqa,
     video_temporal_localization,
     flux_image_inpainting,
+    siglip_classification,
 )
 
 __new_tools__ = [

vision_agent/tools/tools.py

@@ -1845,6 +1845,48 @@ def flux_image_inpainting(
     return output_image
 
 
+def siglip_classification(image: np.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]},
+    """
+
+    if image.shape[0] < 1 or image.shape[1] < 1:
+        return {"labels": [], "scores": []}
+
+    image_file = numpy_to_bytes(image)
+
+    files = [("image", image_file)]
+
+    payload = {
+        "model": "siglip",
+        "labels": labels,
+    }
+
+    response: dict[str, Any] = send_inference_request(
+        payload=payload,
+        endpoint_name="classification",
+        files=files,
+        v2=True,
+        metadata_payload={"function_name": "siglip_classification"},
+    )
+
+    return response
+
+
 # Utility and visualization functions
 
 
@@ -2362,6 +2404,7 @@ FUNCTION_TOOLS = [
     qwen2_vl_images_vqa,
     qwen2_vl_video_vqa,
     video_temporal_localization,
+    flux_image_inpainting,
 ]
 
 UTIL_TOOLS = [

{vision_agent-0.2.188.dist-info → vision_agent-0.2.190.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vision-agent
-Version: 0.2.188
+Version: 0.2.190
 Summary: Toolset for Vision Agent
 Author: Landing AI
 Author-email: dev@landing.ai

{vision_agent-0.2.188.dist-info → vision_agent-0.2.190.dist-info}/RECORD

@@ -16,11 +16,11 @@ vision_agent/fonts/default_font_ch_en.ttf,sha256=1YM0Z3XqLDjSNbF7ihQFSAIUdjF9m1r
 vision_agent/lmm/__init__.py,sha256=jyY1sJb_tYKg5-Wzs3p1lvwFkc-aUNZfMcLy3TOC4Zg,100
 vision_agent/lmm/lmm.py,sha256=B5ClgwvbybVCWkf9opDMLjTtJZemUU4KUkQoRxGh43I,16787
 vision_agent/lmm/types.py,sha256=ZEXR_ptBL0ZwDMTDYkgxUCmSZFmBYPQd2jreNzr_8UY,221
-vision_agent/tools/__init__.py,sha256=KVP4_6qxOb2lpFdQgQtyDfdkMLL1O6wVZNK19MXp-xo,2798
+vision_agent/tools/__init__.py,sha256=uhqE2bo9q1F7andb2zEzp-OYVmYOElPdapIGK9bQ63U,2825
 vision_agent/tools/meta_tools.py,sha256=by7TIbH7lsLIayX_Pe2mS1iw8aeLn2T8yqAo8SkB9Kg,32074
 vision_agent/tools/prompts.py,sha256=V1z4YJLXZuUl_iZ5rY0M5hHc_2tmMEUKr0WocXKGt4E,1430
 vision_agent/tools/tool_utils.py,sha256=VPGqGJ2ZYEJA6AW7K9X7hQv6vRlMtAQcybE4izdToCw,8196
-vision_agent/tools/tools.py,sha256=lIRQals2WLkV01pXDwFwkZdMmEa2xf7Jnv8g3UNrdOQ,83582
+vision_agent/tools/tools.py,sha256=nTeWePteTltKEvDcr2t3nSDtdUL0xdXEIjeolvXNxGg,84945
 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
@@ -29,7 +29,7 @@ vision_agent/utils/image_utils.py,sha256=rm9GfXvD4JrjnqKrP_f2gfq4SzmqYC0IdC1kKwd
 vision_agent/utils/sim.py,sha256=ZuSS07TUXFGjipmiQoY8TKRmSes7XXCdtU9PI8PC1sw,5609
 vision_agent/utils/type_defs.py,sha256=BE12s3JNQy36QvauXHjwyeffVh5enfcvd4vTzSwvEZI,1384
 vision_agent/utils/video.py,sha256=tRcGp4vEnaDycigL1hBO9k0FBPtDH35fCQciVr9GqYI,6013
-vision_agent-0.2.188.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-vision_agent-0.2.188.dist-info/METADATA,sha256=CoqVIiF9B_0k4j9NQtyR8RLQ6cRPByvP0CWfmALRz4A,18328
-vision_agent-0.2.188.dist-info/WHEEL,sha256=7Z8_27uaHI_UZAc4Uox4PpBhQ9Y5_modZXWMxtUi4NU,88
-vision_agent-0.2.188.dist-info/RECORD,,
+vision_agent-0.2.190.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+vision_agent-0.2.190.dist-info/METADATA,sha256=AvlPUByWfCJlMgl2ZvWDfnp9ila0lsCv6x3tZ41DY8k,18328
+vision_agent-0.2.190.dist-info/WHEEL,sha256=7Z8_27uaHI_UZAc4Uox4PpBhQ9Y5_modZXWMxtUi4NU,88
+vision_agent-0.2.190.dist-info/RECORD,,