vision-agent 0.2.37__tar.gz → 0.2.39__tar.gz

{vision_agent-0.2.37 → vision_agent-0.2.39}/PKG-INFO

@@ -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 → vision_agent-0.2.39}/README.md

@@ -124,6 +124,7 @@ 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:
@@ -140,7 +141,6 @@ 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 → vision_agent-0.2.39}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "vision-agent"
-version = "0.2.37"
+version = "0.2.39"
 description = "Toolset for Vision Agent"
 authors = ["Landing AI <dev@landing.ai>"]
 readme = "README.md"

{vision_agent-0.2.37 → vision_agent-0.2.39}/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]: