vision-agent 0.0.45__py3-none-any.whl → 0.0.47__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.
- {vision_agent-0.0.45.dist-info → vision_agent-0.0.47.dist-info}/METADATA +5 -3
- {vision_agent-0.0.45.dist-info → vision_agent-0.0.47.dist-info}/RECORD +4 -4
- {vision_agent-0.0.45.dist-info → vision_agent-0.0.47.dist-info}/LICENSE +0 -0
- {vision_agent-0.0.45.dist-info → vision_agent-0.0.47.dist-info}/WHEEL +0 -0
@@ -1,6 +1,6 @@
|
|
1
1
|
Metadata-Version: 2.1
|
2
2
|
Name: vision-agent
|
3
|
-
Version: 0.0.
|
3
|
+
Version: 0.0.47
|
4
4
|
Summary: Toolset for Vision Agent
|
5
5
|
Author: Landing AI
|
6
6
|
Author-email: dev@landing.ai
|
@@ -69,7 +69,7 @@ export OPENAI_API_KEY="your-api-key"
|
|
69
69
|
You can interact with the agents as you would with any LLM or LMM model:
|
70
70
|
|
71
71
|
```python
|
72
|
-
>>>
|
72
|
+
>>> from vision_agent.agent import VisionAgent
|
73
73
|
>>> agent = VisionAgent()
|
74
74
|
>>> agent("What percentage of the area of this jar is filled with coffee beans?", image="jar.jpg")
|
75
75
|
"The percentage of area of the jar filled with coffee beans is 25%."
|
@@ -132,7 +132,9 @@ you. For example:
|
|
132
132
|
| Crop | Crop crops an image given a bounding box and returns a file name of the cropped image. |
|
133
133
|
| BboxArea | BboxArea returns the area of the bounding box in pixels normalized to 2 decimal places. |
|
134
134
|
| SegArea | SegArea returns the area of the segmentation mask in pixels normalized to 2 decimal places. |
|
135
|
-
|
|
135
|
+
| BboxIoU | BboxIoU returns the intersection over union of two bounding boxes normalized to 2 decimal places. |
|
136
|
+
| SegIoU | SegIoU returns the intersection over union of two segmentation masks normalized to 2 decimal places. |
|
137
|
+
| ExtractFrames | ExtractFrames extracts frames with motion from a video. |
|
136
138
|
|
137
139
|
|
138
140
|
It also has a basic set of calculate tools such as add, subtract, multiply and divide.
|
@@ -20,7 +20,7 @@ vision_agent/tools/__init__.py,sha256=AKN-T659HpwVearRnkCd6wWNoJ6K5kW9gAZwb8IQSL
|
|
20
20
|
vision_agent/tools/prompts.py,sha256=9RBbyqlNlExsGKlJ89Jkph83DAEJ8PCVGaHoNbyN7TM,1416
|
21
21
|
vision_agent/tools/tools.py,sha256=aMTBxxaXQp33HwplOS8xrgfbsTJ8e1pwO6byR7HcTJI,23447
|
22
22
|
vision_agent/tools/video.py,sha256=40rscP8YvKN3lhZ4PDcOK4XbdFX2duCRpHY_krmBYKU,7476
|
23
|
-
vision_agent-0.0.
|
24
|
-
vision_agent-0.0.
|
25
|
-
vision_agent-0.0.
|
26
|
-
vision_agent-0.0.
|
23
|
+
vision_agent-0.0.47.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
|
24
|
+
vision_agent-0.0.47.dist-info/METADATA,sha256=C8a6O_M73qNxhzy9N-6CUIoQyzMkLbkGaJWk6XqZ6Gc,5581
|
25
|
+
vision_agent-0.0.47.dist-info/WHEEL,sha256=7Z8_27uaHI_UZAc4Uox4PpBhQ9Y5_modZXWMxtUi4NU,88
|
26
|
+
vision_agent-0.0.47.dist-info/RECORD,,
|
File without changes
|
File without changes
|