browsergym-workarena 0.2.0__py3-none-any.whl → 0.2.1__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.
- browsergym/workarena/__init__.py +1 -1
- browsergym/workarena/data_files/task_configs/all_menu.json +94 -94
- browsergym/workarena/data_files/task_configs/filter_service_catalog_item_list_task.json +7985 -7981
- browsergym/workarena/data_files/task_configs/impersonation_users.json +2 -2
- {browsergym_workarena-0.2.0.dist-info → browsergym_workarena-0.2.1.dist-info}/METADATA +12 -6
- {browsergym_workarena-0.2.0.dist-info → browsergym_workarena-0.2.1.dist-info}/RECORD +9 -9
- {browsergym_workarena-0.2.0.dist-info → browsergym_workarena-0.2.1.dist-info}/WHEEL +0 -0
- {browsergym_workarena-0.2.0.dist-info → browsergym_workarena-0.2.1.dist-info}/entry_points.txt +0 -0
- {browsergym_workarena-0.2.0.dist-info → browsergym_workarena-0.2.1.dist-info}/licenses/LICENSE +0 -0
|
@@ -591,12 +591,12 @@
|
|
|
591
591
|
"Vince Ettel",
|
|
592
592
|
"Viola Mcsorley",
|
|
593
593
|
"Virgil Chinni",
|
|
594
|
-
"Virtual Agent",
|
|
595
594
|
"Vivian Brzostowski",
|
|
596
595
|
"Waldo Edberg",
|
|
597
596
|
"Waldo Sisk",
|
|
598
597
|
"Walton Schwallie",
|
|
599
598
|
"Warren Hacher",
|
|
600
599
|
"Warren Speach",
|
|
601
|
-
"Wayne Webb"
|
|
600
|
+
"Wayne Webb",
|
|
601
|
+
"Winnie Reich"
|
|
602
602
|
]
|
|
@@ -1,9 +1,9 @@
|
|
|
1
1
|
Metadata-Version: 2.3
|
|
2
2
|
Name: browsergym-workarena
|
|
3
|
-
Version: 0.2.
|
|
3
|
+
Version: 0.2.1
|
|
4
4
|
Summary: WorkArena benchmark for BrowserGym
|
|
5
5
|
Project-URL: homepage, https://github.com/ServiceNow/WorkArena
|
|
6
|
-
Author: Léo Boisvert, Alex Drouin, Maxime Gasse, Alex Lacoste, Manuel Del Verme
|
|
6
|
+
Author: Léo Boisvert, Alex Drouin, Maxime Gasse, Alex Lacoste, Manuel Del Verme, Megh Thakkar
|
|
7
7
|
License: Apache-2.0
|
|
8
8
|
License-File: LICENSE
|
|
9
9
|
Classifier: Development Status :: 2 - Pre-Alpha
|
|
@@ -13,7 +13,7 @@ Classifier: Operating System :: OS Independent
|
|
|
13
13
|
Classifier: Programming Language :: Python :: 3
|
|
14
14
|
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
|
|
15
15
|
Requires-Python: >3.7
|
|
16
|
-
Requires-Dist: browsergym-core
|
|
16
|
+
Requires-Dist: browsergym-core>=0.2
|
|
17
17
|
Requires-Dist: english-words>=2.0.1
|
|
18
18
|
Requires-Dist: faker>=24.11.0
|
|
19
19
|
Requires-Dist: numpy>=1.14
|
|
@@ -35,11 +35,11 @@ WorkArena is included in [BrowserGym](https://github.com/ServiceNow/BrowserGym),
|
|
|
35
35
|
https://github.com/ServiceNow/WorkArena/assets/2374980/68640f09-7d6f-4eb1-b556-c294a6afef70
|
|
36
36
|
|
|
37
37
|
## ⚠️ Pre-Release warning ⚠️
|
|
38
|
-
Please note that the WorkArena benchmark is still undergoing minor bug fixes and updates, which may cause discrepancies with results reported in our latest arXiv preprint. We plan to release soon a stable version of WorkArena
|
|
38
|
+
Please note that the WorkArena benchmark is still undergoing minor bug fixes and updates, which may cause discrepancies with results reported in our latest arXiv preprint. We plan to release soon a stable version of WorkArena with enhanced stability, and a final version v1.0.0 with a new suite of tasks.
|
|
39
39
|
|
|
40
40
|
## Benchmark Contents
|
|
41
41
|
|
|
42
|
-
At the moment, WorkArena includes `18,050` task instances drawn from `
|
|
42
|
+
At the moment, WorkArena includes `18,050` task instances drawn from `33` tasks that cover the main components of the ServiceNow user interface. The following videos show an agent built on `GPT-4-vision` interacting with every such component. As emphasized by our results, this benchmark is not solved and thus, the performance of the agent is not always on point.
|
|
43
43
|
|
|
44
44
|
### Knowledge Bases
|
|
45
45
|
|
|
@@ -75,6 +75,12 @@ https://github.com/ServiceNow/WorkArena/assets/1726818/7538b3ef-d39b-4978-b9ea-8
|
|
|
75
75
|
|
|
76
76
|
https://github.com/ServiceNow/WorkArena/assets/1726818/ca26dfaf-2358-4418-855f-80e482435e6e
|
|
77
77
|
|
|
78
|
+
### Dashboards
|
|
79
|
+
|
|
80
|
+
**Goal:** The agent must extract information from a dashboard.
|
|
81
|
+
|
|
82
|
+
|
|
83
|
+
|
|
78
84
|
## Getting Started
|
|
79
85
|
|
|
80
86
|
To setup WorkArena, you will need to get your own ServiceNow instance, install our Python package, and upload some data to your instance. Follow the steps below to achieve this.
|
|
@@ -82,7 +88,7 @@ To setup WorkArena, you will need to get your own ServiceNow instance, install o
|
|
|
82
88
|
### a) Create a ServiceNow Developer Instance
|
|
83
89
|
|
|
84
90
|
1. Go to https://developer.servicenow.com/ and create an account.
|
|
85
|
-
2. Click on `Request an instance` and select the `
|
|
91
|
+
2. Click on `Request an instance` and select the `Washington` release (initializing the instance will take a few minutes)
|
|
86
92
|
3. Once the instance is ready, you should see your instance URL and credentials. If not, click _Return to the Developer Portal_, then navigate to _Manage instance password_ and click _Reset instance password_.
|
|
87
93
|
4. You should now see your URL and credentials. Based on this information, set the following environment variables:
|
|
88
94
|
* `SNOW_INSTANCE_URL`: The URL of your ServiceNow developer instance
|
|
@@ -1,4 +1,4 @@
|
|
|
1
|
-
browsergym/workarena/__init__.py,sha256=
|
|
1
|
+
browsergym/workarena/__init__.py,sha256=vw13GfG79RNGM8KGpRKHxqmnEywwb-fDmYoi32wgbTg,699
|
|
2
2
|
browsergym/workarena/config.py,sha256=Jl9Ht_98Qs8KlEC-HVGrV1Cy12PyrOfRgJsSlGtc9Jk,7761
|
|
3
3
|
browsergym/workarena/install.py,sha256=HO_f1Ba2_3A4sSjj-SwMTs7iS-QUHFAkN05pn65Js-k,36358
|
|
4
4
|
browsergym/workarena/instance.py,sha256=Qw4lzHhgnl8IuiWOelsmzCJce3jXYivYYwtfTPt2H-s,4314
|
|
@@ -22,7 +22,7 @@ browsergym/workarena/data_files/setup_files/lists/expected_incident_list_columns
|
|
|
22
22
|
browsergym/workarena/data_files/setup_files/lists/expected_service_catalog_list_columns.json,sha256=sncClj2ekwQr3WQSwBX18N2Dd4TvUlhWQrne0vtEgAA,538
|
|
23
23
|
browsergym/workarena/data_files/setup_files/lists/expected_user_list_columns.json,sha256=L4yWNhOczhgC4gKOikrRgX2p2jFxaJ5XSsMM20zwjV4,1068
|
|
24
24
|
browsergym/workarena/data_files/setup_files/ui_themes/workarena_themes.xml,sha256=P0Tqm9TnmHTrgu2FBh-vWPviOHQa_ZkG2Z9-4iwPENY,1970309
|
|
25
|
-
browsergym/workarena/data_files/task_configs/all_menu.json,sha256=
|
|
25
|
+
browsergym/workarena/data_files/task_configs/all_menu.json,sha256=RubFsmrmubJRstViHPc4x2ckPycB43OcXNvlbGp1dJ8,270424
|
|
26
26
|
browsergym/workarena/data_files/task_configs/create_change_request_task.json,sha256=LMxS2YiG8_eH0fhXBis1fyAXE_XYZPwMmMuD2QuzdDY,6306733
|
|
27
27
|
browsergym/workarena/data_files/task_configs/create_hardware_asset_task.json,sha256=koP4OC3ot1ic8ybjCp1fev8X0JxIy_giZ7CyLPdE4qI,4971385
|
|
28
28
|
browsergym/workarena/data_files/task_configs/create_incident_task.json,sha256=BRaM61NMsOs9lrw5n1oT1GsYll0-8HpxYmi-Ry-PpBU,5812616
|
|
@@ -34,9 +34,9 @@ browsergym/workarena/data_files/task_configs/filter_asset_list_task.json,sha256=
|
|
|
34
34
|
browsergym/workarena/data_files/task_configs/filter_change_request_list_task.json,sha256=kL7xiQxSfXZgwEZhrnj_oMV_W0wBLo3QVwb3dHUkv7k,12812288
|
|
35
35
|
browsergym/workarena/data_files/task_configs/filter_hardware_list_task.json,sha256=9e5vxd2uQNTjOCXGSRg2PfZAsc5aGR52jt3m1kbiLdQ,12785357
|
|
36
36
|
browsergym/workarena/data_files/task_configs/filter_incident_list_task.json,sha256=prBD3rQWeq2_PLeBIZ_stC7GRf4s4APXXRy_8bL4wbg,11773863
|
|
37
|
-
browsergym/workarena/data_files/task_configs/filter_service_catalog_item_list_task.json,sha256=
|
|
37
|
+
browsergym/workarena/data_files/task_configs/filter_service_catalog_item_list_task.json,sha256=YEOvoY4N33AjzskzWfy36NLGWYSUJGkEO40jrx5BqYM,9231786
|
|
38
38
|
browsergym/workarena/data_files/task_configs/filter_user_list_task.json,sha256=K_06lJZGLVd63hEo-pG6IRTdXFBdcMsFeo_ROaBGwfs,55965665
|
|
39
|
-
browsergym/workarena/data_files/task_configs/impersonation_users.json,sha256=
|
|
39
|
+
browsergym/workarena/data_files/task_configs/impersonation_users.json,sha256=yER6sg6rRUtnI5z-xiPxGsKtXzfqgvcw_8j054Ta-2U,13020
|
|
40
40
|
browsergym/workarena/data_files/task_configs/knowledge_base_configs.json,sha256=1-7AFvLR7v2RXcpKqDmbKGYHwRIOL0FtHjOv5mjBhtg,617853
|
|
41
41
|
browsergym/workarena/data_files/task_configs/order_apple_mac_book_pro15_task.json,sha256=uHUcHJP7YiIuP7_-L5dXopSouRNfWRWMUD57kHjquNw,1483
|
|
42
42
|
browsergym/workarena/data_files/task_configs/order_apple_watch_task.json,sha256=Fql1AGlrTB4ZQGDnC_Fu2XPtvsW1h1WbhoCKproHzLQ,1673
|
|
@@ -78,8 +78,8 @@ browsergym/workarena/tasks/utils/form.py,sha256=egWzXH9A5eDmu08VSD1npNG32sttOc59
|
|
|
78
78
|
browsergym/workarena/tasks/utils/js_utils.js,sha256=n97fmY2Jkr59rEcQSuSbCnn1L2ZNwM3Nrg-p4TAkdUU,5199
|
|
79
79
|
browsergym/workarena/tasks/utils/string.py,sha256=ir5_ASD9QSFMZ9kuHo2snSXRuSfv_wROH6nxBLOTP4I,330
|
|
80
80
|
browsergym/workarena/tasks/utils/utils.py,sha256=kgpok2LHFaLprgiH0AIan4-Iy492EqpGQnBuzyFdrGg,669
|
|
81
|
-
browsergym_workarena-0.2.
|
|
82
|
-
browsergym_workarena-0.2.
|
|
83
|
-
browsergym_workarena-0.2.
|
|
84
|
-
browsergym_workarena-0.2.
|
|
85
|
-
browsergym_workarena-0.2.
|
|
81
|
+
browsergym_workarena-0.2.1.dist-info/METADATA,sha256=P2mnszMDVFfWa0TvoJQLtmtM5WYUYWnUosHP71_FXwg,7734
|
|
82
|
+
browsergym_workarena-0.2.1.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
|
|
83
|
+
browsergym_workarena-0.2.1.dist-info/entry_points.txt,sha256=rjnc1GaWB89r1PO0P_Uwriv-iVzWMhRM7EqUtXluDPs,72
|
|
84
|
+
browsergym_workarena-0.2.1.dist-info/licenses/LICENSE,sha256=sZLFiZHo_1hcxXRhXUDnQYVATUuWwRCdQjBxqxNnNEs,579
|
|
85
|
+
browsergym_workarena-0.2.1.dist-info/RECORD,,
|
|
File without changes
|
{browsergym_workarena-0.2.0.dist-info → browsergym_workarena-0.2.1.dist-info}/entry_points.txt
RENAMED
|
File without changes
|
{browsergym_workarena-0.2.0.dist-info → browsergym_workarena-0.2.1.dist-info}/licenses/LICENSE
RENAMED
|
File without changes
|