vision-agent 0.2.39__tar.gz → 0.2.41__tar.gz
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.
- {vision_agent-0.2.39 → vision_agent-0.2.41}/PKG-INFO +1 -1
- {vision_agent-0.2.39 → vision_agent-0.2.41}/pyproject.toml +1 -1
- {vision_agent-0.2.39 → vision_agent-0.2.41}/vision_agent/agent/vision_agent_prompts.py +1 -1
- {vision_agent-0.2.39 → vision_agent-0.2.41}/vision_agent/tools/tools.py +3 -3
- {vision_agent-0.2.39 → vision_agent-0.2.41}/LICENSE +0 -0
- {vision_agent-0.2.39 → vision_agent-0.2.41}/README.md +0 -0
- {vision_agent-0.2.39 → vision_agent-0.2.41}/vision_agent/__init__.py +0 -0
- {vision_agent-0.2.39 → vision_agent-0.2.41}/vision_agent/agent/__init__.py +0 -0
- {vision_agent-0.2.39 → vision_agent-0.2.41}/vision_agent/agent/agent.py +0 -0
- {vision_agent-0.2.39 → vision_agent-0.2.41}/vision_agent/agent/agent_coder.py +0 -0
- {vision_agent-0.2.39 → vision_agent-0.2.41}/vision_agent/agent/agent_coder_prompts.py +0 -0
- {vision_agent-0.2.39 → vision_agent-0.2.41}/vision_agent/agent/data_interpreter.py +0 -0
- {vision_agent-0.2.39 → vision_agent-0.2.41}/vision_agent/agent/data_interpreter_prompts.py +0 -0
- {vision_agent-0.2.39 → vision_agent-0.2.41}/vision_agent/agent/easytool.py +0 -0
- {vision_agent-0.2.39 → vision_agent-0.2.41}/vision_agent/agent/easytool_prompts.py +0 -0
- {vision_agent-0.2.39 → vision_agent-0.2.41}/vision_agent/agent/easytool_v2.py +0 -0
- {vision_agent-0.2.39 → vision_agent-0.2.41}/vision_agent/agent/easytool_v2_prompts.py +0 -0
- {vision_agent-0.2.39 → vision_agent-0.2.41}/vision_agent/agent/reflexion.py +0 -0
- {vision_agent-0.2.39 → vision_agent-0.2.41}/vision_agent/agent/reflexion_prompts.py +0 -0
- {vision_agent-0.2.39 → vision_agent-0.2.41}/vision_agent/agent/vision_agent.py +0 -0
- {vision_agent-0.2.39 → vision_agent-0.2.41}/vision_agent/fonts/__init__.py +0 -0
- {vision_agent-0.2.39 → vision_agent-0.2.41}/vision_agent/fonts/default_font_ch_en.ttf +0 -0
- {vision_agent-0.2.39 → vision_agent-0.2.41}/vision_agent/llm/__init__.py +0 -0
- {vision_agent-0.2.39 → vision_agent-0.2.41}/vision_agent/llm/llm.py +0 -0
- {vision_agent-0.2.39 → vision_agent-0.2.41}/vision_agent/lmm/__init__.py +0 -0
- {vision_agent-0.2.39 → vision_agent-0.2.41}/vision_agent/lmm/lmm.py +0 -0
- {vision_agent-0.2.39 → vision_agent-0.2.41}/vision_agent/tools/__init__.py +0 -0
- {vision_agent-0.2.39 → vision_agent-0.2.41}/vision_agent/tools/easytool_tools.py +0 -0
- {vision_agent-0.2.39 → vision_agent-0.2.41}/vision_agent/tools/prompts.py +0 -0
- {vision_agent-0.2.39 → vision_agent-0.2.41}/vision_agent/tools/tool_utils.py +0 -0
- {vision_agent-0.2.39 → vision_agent-0.2.41}/vision_agent/utils/__init__.py +0 -0
- {vision_agent-0.2.39 → vision_agent-0.2.41}/vision_agent/utils/execute.py +0 -0
- {vision_agent-0.2.39 → vision_agent-0.2.41}/vision_agent/utils/image_utils.py +0 -0
- {vision_agent-0.2.39 → vision_agent-0.2.41}/vision_agent/utils/sim.py +0 -0
- {vision_agent-0.2.39 → vision_agent-0.2.41}/vision_agent/utils/type_defs.py +0 -0
- {vision_agent-0.2.39 → vision_agent-0.2.41}/vision_agent/utils/video.py +0 -0
@@ -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
|
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
|
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|