lzy/sci-gui-agent-benchmark
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

ver Jan18th

Browse Source 
completed all the incomplete tasks stored under libreoffice_calc before
added metric check_data_validations
This commit is contained in:
David Chang
2024-01-18 17:54:53 +08:00
parent 19214f2107
commit a97c865c0c
8 changed files with 457 additions and 88 deletions
Download Patch File Download Diff File Expand all files Collapse all files

73
evaluation_examples/examples/libreoffice_calc/d681960f-7bc3-4286-9913-a8812ba3261a.json
View File

@@ -1,34 +1,67 @@
{
"id": "d681960f-7bc3-4286-9913-a8812ba3261a",
"snapshot": "libreoffice_calc",
"instruction": "According to the green table shown above, calculate and give each student a grade",
"instruction": "According to the scale table shown above, calculate and give each student a grade in the table below",
"source": "https://www.youtube.com/shorts/d7U1S_IsTVM",
"config": {
"download": [
[
"https://drive.usercontent.google.com/download?id=1wodZjx1KjThUsrtF6ZJaCTy1fQX4E9vA&export=download&authuser=0&confirm=t&uuid=d07ca312-1abc-40f2-81cd-d06e27119854&at=APZUnTWwjnxsHQYapSvpLR8NmlfV:1701785087048",
"C:\\Users\\tianbaox\\Desktop\\Student_Grades_and_Remarks.xlsx"
]
],
"open": [
"C:\\Users\\tianbaox\\Desktop\\Student_Grades_and_Remarks.xlsx"
]
},
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1wodZjx1KjThUsrtF6ZJaCTy1fQX4E9vA&export=download&authuser=0&confirm=t&uuid=d07ca312-1abc-40f2-81cd-d06e27119854&at=APZUnTWwjnxsHQYapSvpLR8NmlfV:1701785087048",
"path": "/home/user/Student_Grades_and_Remarks.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/Student_Grades_and_Remarks.xlsx"
}
}
],
"trajectory": "trajectories/d681960f-7bc3-4286-9913-a8812ba3261a",
"related_apps": [
"libreoffice calc"
],
"evaluator": {
"func": "compare_table(expected, actual)",
"paths": {
"expected": {
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=1kfEHJH1n0yCsQp443IIFvdD9uWv0DWMr&export=download&authuser=0&confirm=t&uuid=d9907f65-8d39-4ecc-8747-b4ed7e6011f5&at=APZUnTXpPAnlh5sD6q-R8oQtqL6g:1702362952170"
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "Student_Grades_and_Remarks.xlsx - LibreOffice Calc",
"strict": true
}
},
"actual": {
"type": "vm_file",
"path": "C:\\Users\\tianbaox\\Desktop\\Student_Grades_and_Remarks.xlsx"
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.press([\"ctrl\", \"s\"]);"
]
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=1kfEHJH1n0yCsQp443IIFvdD9uWv0DWMr&export=download&authuser=0&confirm=t&uuid=d9907f65-8d39-4ecc-8747-b4ed7e6011f5&at=APZUnTXpPAnlh5sD6q-R8oQtqL6g:1702362952170",
"dest": "Student_Grades_and_Remarks_gold.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/Student_Grades_and_Remarks.xlsx",
"dest": "Student_Grades_and_Remarks.xlsx"
}
}
}