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

Merge branch 'main' into zdy

Browse Source
This commit is contained in:
David Chang
2023-12-25 20:29:20 +08:00
parent ba77c276e6 e891eedfde
commit ade9002da4
80 changed files with 835 additions and 90 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
evaluation_examples/examples/libreoffice_calc/0bf05a7d-b28b-44d2-955a-50b41e24012a.json Normal file
View File

@@ -0,0 +1,22 @@
{
"id": "0bf05a7d-b28b-44d2-955a-50b41e24012a",
"snapshot": "libreoffice_calc",
"instruction": "I would like to pad all the numbers in the 'Old ID' column with zeros in front, to fill them up to seven digits in the 'New 7 Digit ID' column.",
"source": "https://www.youtube.com/shorts/FPAQaDTS8VY",
"config": {
"download": [
[
"",
"C:\\Users\\tianbaox\\Desktop\\Customers_New_7digit_Id.xlsx"
]
],
"open": [
"C:\\Users\\tianbaox\\Desktop\\Customers_New_7digit_Id.xlsx"
]
},
"trajectory": "trajectories/0bf05a7d-b28b-44d2-955a-50b41e24012a",
"related_apps": [
"libreoffice calc"
],
"evaluator": "evaluation_dir"
}

40
evaluation_examples/examples/libreoffice_calc/2bd59342-0664-4ccb-ba87-79379096cc08.json Normal file
View File

@@ -0,0 +1,40 @@
{
"id": "2bd59342-0664-4ccb-ba87-79379096cc08",
"snapshot": "libreoffice_calc",
"instruction": "Make sparkline chart line by line",
"source": "https://www.youtube.com/shorts/L3Z-F1QTQFY",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://101.43.24.67/s/wrEyMi8HsmFjQrZ/download/OrderId_Month_Chart.xlsx",
"path": "/home/david/OrderId_Month_Chart.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/david/OrderId_Month_Chart.xlsx"
]
},
"trajectory": "trajectories/2bd59342-0664-4ccb-ba87-79379096cc08",
"related_apps": [
"libreoffice calc"
],
"evaluator": {
"expected": {
"type": "cloud_file",
"path": "https://101.43.24.67/s/t7pgJxNoAGFQWEM/download/OrderId_Month_Chart_gold.xlsx",
"dest": "OrderId_Month_Chart_gold.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/david/OrderId_Month_Chart.xlsx",
"dest": "OrderId_Month_Chart.xlsx"
}
}
}

42
evaluation_examples/examples/libreoffice_calc/37608790-6147-45d0-9f20-1137bb35703d.json Normal file
View File

@@ -0,0 +1,42 @@
{
"id": "37608790-6147-45d0-9f20-1137bb35703d",
"snapshot": "libreoffice_calc",
"instruction": "Help me fill the columns of First Name, Last Name and Rank",
"source": "https://www.youtube.com/shorts/uzPo_CPCHH8",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://101.43.24.67/s/FBip5fXoR4KEJaa",
"path": "/home/david/Employee_Roles_and_Ranks.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/david/Employee_Roles_and_Ranks.xlsx"
}
}
],
"trajectory": "trajectories/37608790-6147-45d0-9f20-1137bb35703d",
"related_apps": [
"libreoffice calc"
],
"evaluator": {
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://101.43.24.67/s/wr7B4GeotNNoeHD",
"dest": "Employee_Roles_and_Ranks_gold.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/david/Employee_Roles_and_Ranks.xlsx",
"dest": "Employee_Roles_and_Ranks.xlsx"
}
}
}

22
evaluation_examples/examples/libreoffice_calc/7a4e4bc8-922c-4c84-865c-25ba34136be1.json Normal file
View File

@@ -0,0 +1,22 @@
{
"id": "7a4e4bc8-922c-4c84-865c-25ba34136be1",
"snapshot": "libreoffice_calc",
"instruction": "Reorder the columns to be \"Data\", \"First Name\", \"Last Name\", \"Order ID\", \"Sales\"",
"source": "https://www.youtube.com/shorts/bvUhr1AHs44",
"config": {
"download": [
[
"",
"C:\\Users\\tianbaox\\Desktop\\Name_Order_Id_move_column.xlsx"
]
],
"open": [
"C:\\Users\\tianbaox\\Desktop\\Name_Order_Id_move_column.xlsx"
]
},
"trajectory": "trajectories/7a4e4bc8-922c-4c84-865c-25ba34136be1",
"related_apps": [
"libreoffice calc"
],
"evaluator": "evaluation_dir"
}

22
evaluation_examples/examples/libreoffice_calc/7b802dad-6e0f-4204-9815-d4e3f57627d8.json Normal file
View File

@@ -0,0 +1,22 @@
{
"id": "7b802dad-6e0f-4204-9815-d4e3f57627d8",
"snapshot": "libreoffice_calc",
"instruction": "I would like to sort this table based on cell color, placing all the rows marked with pink at the beginning, while keeping their order among themselves unchanged.",
"source": "https://www.youtube.com/shorts/Of-lzeP1usE",
"config": {
"download": [
[
"",
"C:\\Users\\tianbaox\\Desktop\\Customer_Sort_by_cell_color.xlsx"
]
],
"open": [
"C:\\Users\\tianbaox\\Desktop\\Customer_Sort_by_cell_color.xlsx"
]
},
"trajectory": "trajectories/7b802dad-6e0f-4204-9815-d4e3f57627d8",
"related_apps": [
"libreoffice calc"
],
"evaluator": "evaluation_dir"
}

22
evaluation_examples/examples/libreoffice_calc/7efeb4b1-3d19-4762-b163-63328d66303b.json Normal file
View File

@@ -0,0 +1,22 @@
{
"id": "7efeb4b1-3d19-4762-b163-63328d66303b",
"snapshot": "libreoffice_calc",
"instruction": "Fill in the Serieal Numbers in \"Serial #\" column",
"source": "https://www.youtube.com/shorts/4jzXfZNhfmk",
"config": {
"download": [
[
"",
"C:\\Users\\tianbaox\\Desktop\\Order_Sales_Serial#.xlsx"
]
],
"open": [
"C:\\Users\\tianbaox\\Desktop\\Order_Sales_Serial#.xlsx"
]
},
"trajectory": "trajectories/",
"related_apps": [
"libreoffice calc"
],
"evaluator": "evaluation_dir"
}

22
evaluation_examples/examples/libreoffice_calc/a9f325aa-8c05-4e4f-8341-9e4358565f4f.json Normal file
View File

@@ -0,0 +1,22 @@
{
"id": "a9f325aa-8c05-4e4f-8341-9e4358565f4f",
"snapshot": "libreoffice_calc",
"instruction": "Clean the messy movie titles and put them in the cleaned column",
"source": "https://www.youtube.com/shorts/A0gmEBRKXWs",
"config": {
"download": [
[
"",
"C:\\Users\\tianbaox\\Desktop\\"
]
],
"open": [
"C:\\Users\\tianbaox\\Desktop\\"
]
},
"trajectory": "trajectories/a9f325aa-8c05-4e4f-8341-9e4358565f4f",
"related_apps": [
"libreoffice calc"
],
"evaluator": "evaluation_dir"
}

34
evaluation_examples/examples/libreoffice_calc/d681960f-7bc3-4286-9913-a8812ba3261a.json Normal file
View File

@@ -0,0 +1,34 @@
{
"id": "d681960f-7bc3-4286-9913-a8812ba3261a",
"snapshot": "libreoffice_calc",
"instruction": "According to the green table shown above, calculate and give each student a grade",
"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"
]
},
"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"
},
"actual": {
"type": "vm_file",
"path": "C:\\Users\\tianbaox\\Desktop\\Student_Grades_and_Remarks.xlsx"
}
}
}
}

22
evaluation_examples/examples/libreoffice_calc/eb03d19a-b88d-4de4-8a64-ca0ac66f426b.json Normal file
View File

@@ -0,0 +1,22 @@
{
"id": "eb03d19a-b88d-4de4-8a64-ca0ac66f426b",
"snapshot": "libreoffice_calc",
"instruction": "Traverse the table and paste it below",
"source": "https://www.youtube.com/shorts/t9JLUaT55UQ",
"config": {
"download": [
[
"",
"C:\\Users\\tianbaox\\Desktop\\"
]
],
"open": [
"C:\\Users\\tianbaox\\Desktop\\"
]
},
"trajectory": "trajectories/eb03d19a-b88d-4de4-8a64-ca0ac66f426b",
"related_apps": [
"libreoffice calc"
],
"evaluator": "evaluation_dir"
}

22
evaluation_examples/examples/libreoffice_calc/ecb0df7a-4e8d-4a03-b162-053391d3afaf.json Normal file
View File

@@ -0,0 +1,22 @@
{
"id": "ecb0df7a-4e8d-4a03-b162-053391d3afaf",
"snapshot": "libreoffice_calc",
"instruction": "Enable each cell in the column\"Pass/Fail/Held\" is a drop down list",
"source": "https://www.youtube.com/shorts/tXOovKn0H68",
"config": {
"download": [
[
"",
"C:\\Users\\tianbaox\\Desktop\\"
]
],
"open": [
"C:\\Users\\tianbaox\\Desktop\\"
]
},
"trajectory": "trajectories/ecb0df7a-4e8d-4a03-b162-053391d3afaf",
"related_apps": [
"libreoffice calc"
],
"evaluator": "evaluation_dir"
}

42
evaluation_examples/examples/libreoffice_calc/f9584479-3d0d-4c79-affa-9ad7afdd8850.json Normal file
View File

@@ -0,0 +1,42 @@
{
"id": "f9584479-3d0d-4c79-affa-9ad7afdd8850",
"snapshot": "libreoffice_calc",
"instruction": "Fill the missing row and column which show the total value",
"source": "https://youtube.com/shorts/feldd-Pn48c?si=9xJiem2uAHm6Jshb",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "http://101.43.24.67/s/DbaHsQpPA7dxrA8/download/Quarterly_Product_Sales_by_Zone.xlsx",
"path": "/home/david/Quarterly_Product_Sales_by_Zone.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/david/Quarterly_Product_Sales_by_Zone.xlsx"
}
}
],
"trajectory": "trajectories/f9584479-3d0d-4c79-affa-9ad7afdd8850",
"related_apps": [
"libreoffice calc"
],
"evaluator": {
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "http://101.43.24.67/s/BAfFwa3689XTYoo/download/Quarterly_Product_Sales_by_Zone_gold.xlsx",
"dest": "Quarterly_Product_Sales_by_Zone_gold.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/david/Quarterly_Product_Sales_by_Zone.xlsx",
"dest": "Quarterly_Product_Sales_by_Zone.xlsx"
}
}
}