vision-agent 0.2.38__tar.gz → 0.2.40__tar.gz

{vision_agent-0.2.38 → vision_agent-0.2.40}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vision-agent
-Version: 0.2.38
+Version: 0.2.40
 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-0.2.38 → vision_agent-0.2.40}/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-0.2.38 → vision_agent-0.2.40}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "vision-agent"
-version = "0.2.38"
+version = "0.2.40"
 description = "Toolset for Vision Agent"
 authors = ["Landing AI <dev@landing.ai>"]
 readme = "README.md"

{vision_agent-0.2.38 → vision_agent-0.2.40}/vision_agent/agent/vision_agent_prompts.py

@@ -68,7 +68,7 @@ This is the documentation for the functions you have access to. You may call any
 1. **Understand and Clarify**: Make sure you understand the task.
 2. **Algorithm/Method Selection**: Decide on the most efficient way.
 3. **Pseudocode Creation**: Write down the steps you will follow in pseudocode.
-4. **Code Generation**: Translate your pseudocode into executable Python code.
+4. **Code Generation**: Translate your pseudocode into executable Python code. Ensure you use correct arguments, remember coordinates are always returned normalized from `vision_agent.tools`.
 5. **Logging**: Log the output of the custom functions that were provided to you from `from vision_agent.tools import *`. Use a debug flag in the function parameters to toggle logging on and off.
 """
 

{vision_agent-0.2.38 → vision_agent-0.2.40}/vision_agent/tools/tools.py

@@ -60,8 +60,8 @@ def grounding_dino(
 ) -> List[Dict[str, Any]]:
     """'grounding_dino' is a tool that can detect and count multiple objects given a text
     prompt such as category names or referring expressions. The categories in text prompt
-    are separated by commas or periods. It returns a list and count of bounding boxes,
-    label names and associated probability scores.
+    are separated by commas or periods. It returns a list of bounding boxes with
+    normalized coordinates, label names and associated probability scores.
 
     Parameters:
         prompt (str): The prompt to ground to the image.
@@ -73,7 +73,7 @@ def grounding_dino(
 
     Returns:
         List[Dict[str, Any]]: A list of dictionaries containing the score, label, and
-        bounding box of the detected objects with normalized coordinates
+        bounding box of the detected objects with normalized coordinates between 0 and 1
         (xmin, ymin, xmax, ymax). xmin and ymin are the coordinates of the top-left and
         xmax and ymax are the coordinates of the bottom-right of the bounding box.