vision-agent 0.2.13__py3-none-any.whl → 0.2.14__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/agent/vision_agent_prompts.py +3 -3
- {vision_agent-0.2.13.dist-info → vision_agent-0.2.14.dist-info}/METADATA +1 -2
- {vision_agent-0.2.13.dist-info → vision_agent-0.2.14.dist-info}/RECORD +5 -5
- {vision_agent-0.2.13.dist-info → vision_agent-0.2.14.dist-info}/LICENSE +0 -0
- {vision_agent-0.2.13.dist-info → vision_agent-0.2.14.dist-info}/WHEEL +0 -0
@@ -70,7 +70,7 @@ These are the tools you can select to solve the question:
|
|
70
70
|
|
71
71
|
Please note that:
|
72
72
|
1. You should only choose one tool from the Tool List to solve this question and it should have maximum chance of solving the question.
|
73
|
-
2. You should only choose the tool whose parameters are most relevant to the user's question and are
|
73
|
+
2. You should only choose the tool whose parameters are most relevant to the user's question and are available as part of the question.
|
74
74
|
3. You should choose the tool whose return type is most relevant to the answer of the user's question.
|
75
75
|
4. You must ONLY output the ID of the tool you chose in a parsible JSON format. Two example outputs look like:
|
76
76
|
|
@@ -88,7 +88,7 @@ This is a reflection from a previous failed attempt:
|
|
88
88
|
|
89
89
|
Please note that:
|
90
90
|
1. You should only choose one tool from the Tool List to solve this question and it should have maximum chance of solving the question.
|
91
|
-
2. You should only choose the tool whose parameters are most relevant to the user's question and are
|
91
|
+
2. You should only choose the tool whose parameters are most relevant to the user's question and are available as part of the question.
|
92
92
|
3. You should choose the tool whose return type is most relevant to the answer of the user's question.
|
93
93
|
4. You must ONLY output the ID of the tool you chose in a parsible JSON format. Two example outputs look like:
|
94
94
|
|
@@ -100,7 +100,7 @@ Output: """
|
|
100
100
|
CHOOSE_PARAMETER_DEPENDS = """Given a user's question and an API tool documentation, you need to output parameters according to the API tool documentation to successfully call the API to solve the user's question.
|
101
101
|
Please note that:
|
102
102
|
1. The Example in the API tool documentation can help you better understand the use of the API. Pay attention to the examples which show how to parse the question and extract tool parameters such as prompts and visual inputs.
|
103
|
-
2. Ensure the parameters you output are correct. The output must contain the required parameters, and can contain the optional parameters based on the question. If there are no
|
103
|
+
2. Ensure the parameters you output are correct. The output must contain the required parameters, and can contain the optional parameters based on the question. If there are no parameters in the required parameters and optional parameters, just leave it as {{"Parameters":{{}}}}
|
104
104
|
3. If the user's question mentions other APIs, you should ONLY consider the API tool documentation I give and do not consider other APIs.
|
105
105
|
4. The question may have dependencies on answers of other questions, so we will provide logs of previous questions and answers for your reference.
|
106
106
|
5. If you need to use this API multiple times, please set "Parameters" to a list.
|
@@ -1,6 +1,6 @@
|
|
1
1
|
Metadata-Version: 2.1
|
2
2
|
Name: vision-agent
|
3
|
-
Version: 0.2.
|
3
|
+
Version: 0.2.14
|
4
4
|
Summary: Toolset for Vision Agent
|
5
5
|
Author: Landing AI
|
6
6
|
Author-email: dev@landing.ai
|
@@ -181,7 +181,6 @@ find an example that creates a custom tool for template matching [here](examples
|
|
181
181
|
| GroundingDINO | GroundingDINO is a tool that can detect arbitrary objects with inputs such as category names or referring expressions. |
|
182
182
|
| GroundingSAM | GroundingSAM is a tool that can detect and segment arbitrary objects with inputs such as category names or referring expressions. |
|
183
183
|
| DINOv | DINOv is a tool that can detect arbitrary objects with using a referring mask. |
|
184
|
-
| ExtractFrames | ExtractFrames extracts frames with motion from a video. |
|
185
184
|
| Crop | Crop crops an image given a bounding box and returns a file name of the cropped image. |
|
186
185
|
| BboxArea | BboxArea returns the area of the bounding box in pixels normalized to 2 decimal places. |
|
187
186
|
| SegArea | SegArea returns the area of the segmentation mask in pixels normalized to 2 decimal places. |
|
@@ -9,7 +9,7 @@ vision_agent/agent/execution.py,sha256=wX8LwXDq_0g_bTPikNiaW6nz5bUC7fUlNQsQHe_7W
|
|
9
9
|
vision_agent/agent/reflexion.py,sha256=4gz30BuFMeGxSsTzoDV4p91yE0R8LISXp28IaOI6wdM,10506
|
10
10
|
vision_agent/agent/reflexion_prompts.py,sha256=G7UAeNz_g2qCb2yN6OaIC7bQVUkda4m3z42EG8wAyfE,9342
|
11
11
|
vision_agent/agent/vision_agent.py,sha256=5W5Xr_h4yDMsFvIk2JWcfMlYoPYmTv3JZnrDDumuZgM,26842
|
12
|
-
vision_agent/agent/vision_agent_prompts.py,sha256=
|
12
|
+
vision_agent/agent/vision_agent_prompts.py,sha256=MZSIwovYgB-f-kdJ6btaNDVXptJn47bfOL3-Zn6NiC0,8573
|
13
13
|
vision_agent/fonts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
14
14
|
vision_agent/fonts/default_font_ch_en.ttf,sha256=1YM0Z3XqLDjSNbF7ihQFSAIUdjF9m1rtHiNC_6QosTE,1594400
|
15
15
|
vision_agent/image_utils.py,sha256=1dggPBhW8_hUXDItCRLa23h-hdBwS50cjL4v1hsoUbg,7586
|
@@ -24,7 +24,7 @@ vision_agent/tools/tools.py,sha256=8JzNtn_uKTyc-bztjnaGCY7ctRnfW5dRS-ppxaP-1RE,4
|
|
24
24
|
vision_agent/tools/tools_v2.py,sha256=RxeaBTTkhqvATQGuYKiopeU4L2m0GbpPo-ypDmQ9UfY,5407
|
25
25
|
vision_agent/tools/video.py,sha256=xTElFSFp1Jw4ulOMnk81Vxsh-9dTxcWUO6P9fzEi3AM,7653
|
26
26
|
vision_agent/type_defs.py,sha256=4LTnTL4HNsfYqCrDn9Ppjg9bSG2ZGcoKSSd9YeQf4Bw,1792
|
27
|
-
vision_agent-0.2.
|
28
|
-
vision_agent-0.2.
|
29
|
-
vision_agent-0.2.
|
30
|
-
vision_agent-0.2.
|
27
|
+
vision_agent-0.2.14.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
|
28
|
+
vision_agent-0.2.14.dist-info/METADATA,sha256=P4mOwafNaTHHf5GMoe-spAfPUmQHNWT7UKSBZ5LU-Vo,8997
|
29
|
+
vision_agent-0.2.14.dist-info/WHEEL,sha256=7Z8_27uaHI_UZAc4Uox4PpBhQ9Y5_modZXWMxtUi4NU,88
|
30
|
+
vision_agent-0.2.14.dist-info/RECORD,,
|
File without changes
|
File without changes
|