vision-agent 0.2.37__py3-none-any.whl → 0.2.39__py3-none-any.whl

vision_agent/tools/tools.py

@@ -198,7 +198,7 @@ def extract_frames(
 
 def ocr(image: np.ndarray) -> List[Dict[str, Any]]:
     """'ocr' extracts text from an image. It returns a list of detected text, bounding
-    boxes, and confidence scores.
+    boxes, and confidence scores. The results are sorted from top-left to bottom right
 
     Parameters:
         image (np.ndarray): The image to extract text from.
@@ -211,7 +211,7 @@ def ocr(image: np.ndarray) -> List[Dict[str, Any]]:
     -------
     >>> ocr(image)
     [
-        {'label': 'some text', 'bbox': [0.1, 0.11, 0.35, 0.4], 'score': 0.99},
+        {'label': 'hello world', 'bbox': [0.1, 0.11, 0.35, 0.4], 'score': 0.99},
     ]
     """
 
@@ -245,7 +245,8 @@ def ocr(image: np.ndarray) -> List[Dict[str, Any]]:
         box = normalize_bbox(box, image_size)
         output.append({"label": label, "bbox": box, "score": round(det["score"], 2)})
 
-    return output
+    ocr_results = sorted(output, key=lambda x: (x["bbox"][1], x["bbox"][0]))
+    return ocr_results
 
 
 def zero_shot_counting(image: np.ndarray) -> Dict[str, Any]:

{vision_agent-0.2.37.dist-info → vision_agent-0.2.39.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vision-agent
-Version: 0.2.37
+Version: 0.2.39
 Summary: Toolset for Vision Agent
 Author: Landing AI
 Author-email: dev@landing.ai
@@ -160,6 +160,7 @@ You can also add custom tools to the agent:
 
 ```python
 import vision_agent as va
+import numpy as np
 
 @va.tools.register_tool(imports=["import numpy as np"])
 def custom_tool(image_path: str) -> str:
@@ -176,7 +177,6 @@ def custom_tool(image_path: str) -> str:
     >>> custom_tool("image.jpg")
     """
 
-    import numpy as np
     return np.zeros((10, 10))
 ```
 

{vision_agent-0.2.37.dist-info → vision_agent-0.2.39.dist-info}/RECORD

@@ -23,14 +23,14 @@ vision_agent/tools/__init__.py,sha256=oZa_sslb1UqEgpdWROChDcz5JHdB475ejJX78FMLYv
 vision_agent/tools/easytool_tools.py,sha256=pZc5dQlYINlV4nYbbzsDi3-wauA-fCeD2iGmJUMoUfE,47373
 vision_agent/tools/prompts.py,sha256=V1z4YJLXZuUl_iZ5rY0M5hHc_2tmMEUKr0WocXKGt4E,1430
 vision_agent/tools/tool_utils.py,sha256=wzRacbUpqk9hhfX_Y08rL8qP0XCN2w-8IZoYLi3Upn4,869
-vision_agent/tools/tools.py,sha256=RVBuaP8KZrBVppEPaqP0Tey3Am6O5zoNIaZpBSW125c,23523
+vision_agent/tools/tools.py,sha256=DoVmuGF7WoU6BREaCocb0SwN2q8Szs25KfT5bUgy6cU,23660
 vision_agent/utils/__init__.py,sha256=Ce4yPhoWanRsnTy3X7YzZNBYYRJsrJeT7N59WUf8GZM,209
 vision_agent/utils/execute.py,sha256=OOix_tDoX1hUacGhszZcMl2D9IWSTwXBox-6DhEKGFA,19079
 vision_agent/utils/image_utils.py,sha256=_cdiS5YrLzqkq_ZgFUO897m5M4_SCIThwUy4lOklfB8,7700
 vision_agent/utils/sim.py,sha256=oUZ-6eu8Io-UNt9GXJ0XRKtP-Wc0sPWVzYGVpB2yDFk,3001
 vision_agent/utils/type_defs.py,sha256=BlI8ywWHAplC7kYWLvt4AOdnKpEW3qWEFm-GEOSkrFQ,1792
 vision_agent/utils/video.py,sha256=xTElFSFp1Jw4ulOMnk81Vxsh-9dTxcWUO6P9fzEi3AM,7653
-vision_agent-0.2.37.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-vision_agent-0.2.37.dist-info/METADATA,sha256=uwSwFslC71mMZC-eo34JlIcTdrGeV7IzW-JBlLmvy1Y,6830
-vision_agent-0.2.37.dist-info/WHEEL,sha256=7Z8_27uaHI_UZAc4Uox4PpBhQ9Y5_modZXWMxtUi4NU,88
-vision_agent-0.2.37.dist-info/RECORD,,
+vision_agent-0.2.39.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+vision_agent-0.2.39.dist-info/METADATA,sha256=hgiRU-muujo5x9faImu6Mnd0Lzl97OIzyY6BLHoVAHc,6826
+vision_agent-0.2.39.dist-info/WHEEL,sha256=7Z8_27uaHI_UZAc4Uox4PpBhQ9Y5_modZXWMxtUi4NU,88
+vision_agent-0.2.39.dist-info/RECORD,,