vision-agent 0.2.39__py3-none-any.whl → 0.2.40__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -68,7 +68,7 @@ This is the documentation for the functions you have access to. You may call any
68
68
  1. **Understand and Clarify**: Make sure you understand the task.
69
69
  2. **Algorithm/Method Selection**: Decide on the most efficient way.
70
70
  3. **Pseudocode Creation**: Write down the steps you will follow in pseudocode.
71
- 4. **Code Generation**: Translate your pseudocode into executable Python code.
71
+ 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`.
72
72
  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.
73
73
  """
74
74
 
@@ -60,8 +60,8 @@ def grounding_dino(
60
60
  ) -> List[Dict[str, Any]]:
61
61
  """'grounding_dino' is a tool that can detect and count multiple objects given a text
62
62
  prompt such as category names or referring expressions. The categories in text prompt
63
- are separated by commas or periods. It returns a list and count of bounding boxes,
64
- label names and associated probability scores.
63
+ are separated by commas or periods. It returns a list of bounding boxes with
64
+ normalized coordinates, label names and associated probability scores.
65
65
 
66
66
  Parameters:
67
67
  prompt (str): The prompt to ground to the image.
@@ -73,7 +73,7 @@ def grounding_dino(
73
73
 
74
74
  Returns:
75
75
  List[Dict[str, Any]]: A list of dictionaries containing the score, label, and
76
- bounding box of the detected objects with normalized coordinates
76
+ bounding box of the detected objects with normalized coordinates between 0 and 1
77
77
  (xmin, ymin, xmax, ymax). xmin and ymin are the coordinates of the top-left and
78
78
  xmax and ymax are the coordinates of the bottom-right of the bounding box.
79
79
 
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: vision-agent
3
- Version: 0.2.39
3
+ Version: 0.2.40
4
4
  Summary: Toolset for Vision Agent
5
5
  Author: Landing AI
6
6
  Author-email: dev@landing.ai
@@ -12,7 +12,7 @@ vision_agent/agent/easytool_v2_prompts.py,sha256=MZSIwovYgB-f-kdJ6btaNDVXptJn47b
12
12
  vision_agent/agent/reflexion.py,sha256=AlM5AvBJvCslXlYQdZiadq4oVHsNBm3IF_03DglTxRo,10506
13
13
  vision_agent/agent/reflexion_prompts.py,sha256=G7UAeNz_g2qCb2yN6OaIC7bQVUkda4m3z42EG8wAyfE,9342
14
14
  vision_agent/agent/vision_agent.py,sha256=fL2KN7iTD1VHiMoYFt4bQHNd3I9RKbGD65XXmQHRAT0,17267
15
- vision_agent/agent/vision_agent_prompts.py,sha256=0YbiS59IEWbiE43gCvOqfWrpudIAhTn8FHzXW0Y-Gaw,8201
15
+ vision_agent/agent/vision_agent_prompts.py,sha256=FnIYF2Fe3joRvFnOJD9ZyWXMihMyL606nXxWJ0adTZ8,8314
16
16
  vision_agent/fonts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
17
17
  vision_agent/fonts/default_font_ch_en.ttf,sha256=1YM0Z3XqLDjSNbF7ihQFSAIUdjF9m1rtHiNC_6QosTE,1594400
18
18
  vision_agent/llm/__init__.py,sha256=BoUm_zSAKnLlE8s-gKTSQugXDqVZKPqYlWwlTLdhcz4,48
@@ -23,14 +23,14 @@ vision_agent/tools/__init__.py,sha256=oZa_sslb1UqEgpdWROChDcz5JHdB475ejJX78FMLYv
23
23
  vision_agent/tools/easytool_tools.py,sha256=pZc5dQlYINlV4nYbbzsDi3-wauA-fCeD2iGmJUMoUfE,47373
24
24
  vision_agent/tools/prompts.py,sha256=V1z4YJLXZuUl_iZ5rY0M5hHc_2tmMEUKr0WocXKGt4E,1430
25
25
  vision_agent/tools/tool_utils.py,sha256=wzRacbUpqk9hhfX_Y08rL8qP0XCN2w-8IZoYLi3Upn4,869
26
- vision_agent/tools/tools.py,sha256=DoVmuGF7WoU6BREaCocb0SwN2q8Szs25KfT5bUgy6cU,23660
26
+ vision_agent/tools/tools.py,sha256=Rz6WU27zDczKAlBJzou7l6V6UzEX3G15dgyWt55FFSE,23694
27
27
  vision_agent/utils/__init__.py,sha256=Ce4yPhoWanRsnTy3X7YzZNBYYRJsrJeT7N59WUf8GZM,209
28
28
  vision_agent/utils/execute.py,sha256=OOix_tDoX1hUacGhszZcMl2D9IWSTwXBox-6DhEKGFA,19079
29
29
  vision_agent/utils/image_utils.py,sha256=_cdiS5YrLzqkq_ZgFUO897m5M4_SCIThwUy4lOklfB8,7700
30
30
  vision_agent/utils/sim.py,sha256=oUZ-6eu8Io-UNt9GXJ0XRKtP-Wc0sPWVzYGVpB2yDFk,3001
31
31
  vision_agent/utils/type_defs.py,sha256=BlI8ywWHAplC7kYWLvt4AOdnKpEW3qWEFm-GEOSkrFQ,1792
32
32
  vision_agent/utils/video.py,sha256=xTElFSFp1Jw4ulOMnk81Vxsh-9dTxcWUO6P9fzEi3AM,7653
33
- vision_agent-0.2.39.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
34
- vision_agent-0.2.39.dist-info/METADATA,sha256=hgiRU-muujo5x9faImu6Mnd0Lzl97OIzyY6BLHoVAHc,6826
35
- vision_agent-0.2.39.dist-info/WHEEL,sha256=7Z8_27uaHI_UZAc4Uox4PpBhQ9Y5_modZXWMxtUi4NU,88
36
- vision_agent-0.2.39.dist-info/RECORD,,
33
+ vision_agent-0.2.40.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
34
+ vision_agent-0.2.40.dist-info/METADATA,sha256=lCwC34MZiN1lnEHOVl2BEzp9Cgs4PErYPeemGU7DnS8,6826
35
+ vision_agent-0.2.40.dist-info/WHEEL,sha256=7Z8_27uaHI_UZAc4Uox4PpBhQ9Y5_modZXWMxtUi4NU,88
36
+ vision_agent-0.2.40.dist-info/RECORD,,