vision-agent 0.2.197__tar.gz → 0.2.199__tar.gz
Sign up to get free protection for your applications and to get access to all the features.
- {vision_agent-0.2.197 → vision_agent-0.2.199}/PKG-INFO +1 -1
- {vision_agent-0.2.197 → vision_agent-0.2.199}/pyproject.toml +1 -1
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/.sim_tools/df.csv +18 -18
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/.sim_tools/embs.npy +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/tools/tools.py +1 -1
- {vision_agent-0.2.197 → vision_agent-0.2.199}/LICENSE +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/README.md +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/__init__.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/agent/__init__.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/agent/agent.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/agent/agent_utils.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/agent/vision_agent.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/agent/vision_agent_coder.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/agent/vision_agent_coder_prompts.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/agent/vision_agent_coder_prompts_v2.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/agent/vision_agent_coder_v2.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/agent/vision_agent_planner.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/agent/vision_agent_planner_prompts.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/agent/vision_agent_planner_prompts_v2.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/agent/vision_agent_planner_v2.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/agent/vision_agent_prompts.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/clients/__init__.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/clients/http.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/clients/landing_public_api.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/fonts/__init__.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/fonts/default_font_ch_en.ttf +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/lmm/__init__.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/lmm/lmm.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/lmm/types.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/tools/__init__.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/tools/meta_tools.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/tools/planner_tools.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/tools/prompts.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/tools/tool_utils.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/tools/tools_types.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/utils/__init__.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/utils/exceptions.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/utils/execute.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/utils/image_utils.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/utils/sim.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/utils/type_defs.py +0 -0
- {vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/utils/video.py +0 -0
@@ -80,24 +80,6 @@ desc,doc,name
|
|
80
80
|
{'label': 'hello world', 'bbox': [0.1, 0.11, 0.35, 0.4], 'score': 0.99},
|
81
81
|
]
|
82
82
|
",ocr
|
83
|
-
'clip' is a tool that can classify an image or a cropped detection given a list of input classes or tags. It returns the same list of the input classes along with their probability scores based on image content.,"clip(image: numpy.ndarray, classes: List[str]) -> Dict[str, Any]:
|
84
|
-
'clip' is a tool that can classify an image or a cropped detection given a list
|
85
|
-
of input classes or tags. It returns the same list of the input classes along with
|
86
|
-
their probability scores based on image content.
|
87
|
-
|
88
|
-
Parameters:
|
89
|
-
image (np.ndarray): The image to classify or tag
|
90
|
-
classes (List[str]): The list of classes or tags that is associated with the image
|
91
|
-
|
92
|
-
Returns:
|
93
|
-
Dict[str, Any]: A dictionary containing the labels and scores. One dictionary
|
94
|
-
contains a list of given labels and other a list of scores.
|
95
|
-
|
96
|
-
Example
|
97
|
-
-------
|
98
|
-
>>> clip(image, ['dog', 'cat', 'bird'])
|
99
|
-
{""labels"": [""dog"", ""cat"", ""bird""], ""scores"": [0.68, 0.30, 0.02]},
|
100
|
-
",clip
|
101
83
|
'vit_image_classification' is a tool that can classify an image. It returns a list of classes and their probability scores based on image content.,"vit_image_classification(image: numpy.ndarray) -> Dict[str, Any]:
|
102
84
|
'vit_image_classification' is a tool that can classify an image. It returns a
|
103
85
|
list of classes and their probability scores based on image content.
|
@@ -488,6 +470,24 @@ desc,doc,name
|
|
488
470
|
... )
|
489
471
|
>>> save_image(result, ""inpainted_room.png"")
|
490
472
|
",flux_image_inpainting
|
473
|
+
'siglip_classification' is a tool that can classify an image or a cropped detection given a list of input labels or tags. It returns the same list of the input labels along with their probability scores based on image content.,"siglip_classification(image: numpy.ndarray, labels: List[str]) -> Dict[str, Any]:
|
474
|
+
'siglip_classification' is a tool that can classify an image or a cropped detection given a list
|
475
|
+
of input labels or tags. It returns the same list of the input labels along with
|
476
|
+
their probability scores based on image content.
|
477
|
+
|
478
|
+
Parameters:
|
479
|
+
image (np.ndarray): The image to classify or tag
|
480
|
+
labels (List[str]): The list of labels or tags that is associated with the image
|
481
|
+
|
482
|
+
Returns:
|
483
|
+
Dict[str, Any]: A dictionary containing the labels and scores. One dictionary
|
484
|
+
contains a list of given labels and other a list of scores.
|
485
|
+
|
486
|
+
Example
|
487
|
+
-------
|
488
|
+
>>> siglip_classification(image, ['dog', 'cat', 'bird'])
|
489
|
+
{""labels"": [""dog"", ""cat"", ""bird""], ""scores"": [0.68, 0.30, 0.02]},
|
490
|
+
",siglip_classification
|
491
491
|
"'extract_frames_and_timestamps' extracts frames and timestamps from a video which can be a file path, url or youtube link, returns a list of dictionaries with keys ""frame"" and ""timestamp"" where ""frame"" is a numpy array and ""timestamp"" is the relative time in seconds where the frame was captured. The frame is a numpy array.","extract_frames_and_timestamps(video_uri: Union[str, pathlib.Path], fps: float = 1) -> List[Dict[str, Union[numpy.ndarray, float]]]:
|
492
492
|
'extract_frames_and_timestamps' extracts frames and timestamps from a video
|
493
493
|
which can be a file path, url or youtube link, returns a list of dictionaries
|
Binary file
|
@@ -2453,7 +2453,6 @@ FUNCTION_TOOLS = [
|
|
2453
2453
|
owl_v2_image,
|
2454
2454
|
owl_v2_video,
|
2455
2455
|
ocr,
|
2456
|
-
clip,
|
2457
2456
|
vit_image_classification,
|
2458
2457
|
vit_nsfw_classification,
|
2459
2458
|
countgd_counting,
|
@@ -2471,6 +2470,7 @@ FUNCTION_TOOLS = [
|
|
2471
2470
|
qwen2_vl_video_vqa,
|
2472
2471
|
video_temporal_localization,
|
2473
2472
|
flux_image_inpainting,
|
2473
|
+
siglip_classification,
|
2474
2474
|
]
|
2475
2475
|
|
2476
2476
|
UTIL_TOOLS = [
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
{vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/agent/vision_agent_coder_prompts.py
RENAMED
File without changes
|
{vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/agent/vision_agent_coder_prompts_v2.py
RENAMED
File without changes
|
File without changes
|
File without changes
|
{vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/agent/vision_agent_planner_prompts.py
RENAMED
File without changes
|
{vision_agent-0.2.197 → vision_agent-0.2.199}/vision_agent/agent/vision_agent_planner_prompts_v2.py
RENAMED
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
|