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

Fix Duplicate ids; Remove unused JSON files across multiple applications

Browse Source
This commit is contained in:
Timothyxxx
2025-02-10 15:49:54 +08:00
parent f4750701d4
commit 2f0f3f31aa
139 changed files with 17 additions and 4711 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
evaluation_examples/examples/chrome/1c114e4f-5f2f-4862-9e92-bac2fdd285b9.json
View File

@@ -1,18 +0,0 @@
{
"id": "1c114e4f-5f2f-4862-9e92-bac2fdd285b9",
"snapshot": "chrome",
"instruction": "Could you please display the list of the most popular science fiction movies on IMDB? I want to make sure I haven't missed any that I should watch.",
"source": "https://help.imdb.com/article/imdb/general-information/you-have-so-much-information-where-should-i-start/G47FFV4PZE6GTZ75?ref_=helpart_nav_29#",
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
}
}
}

18
evaluation_examples/examples/chrome/3d1682a7-0fb0-49ae-a4dc-a73afd2d06d5.json
View File

@@ -1,18 +0,0 @@
{
"id": "3d1682a7-0fb0-49ae-a4dc-a73afd2d06d5",
"snapshot": "chrome",
"instruction": "Computer, could you set up Chrome so it automatically fills in forms with my address, say, 123 Main Street, Anytown, USA, for me?",
"source": "https://in5stepstutorials.com/google-chrome/add-change-delete-autofill-address.php",
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
}
}
}

18
evaluation_examples/examples/chrome/94760984-3ff5-41ee-8347-cf1af709fea0.json
View File

@@ -1,18 +0,0 @@
{
"id": "94760984-3ff5-41ee-8347-cf1af709fea0",
"snapshot": "chrome",
"instruction": "Can you enable the reading mode in Chrome so I can read articles without distractions?",
"source": "https://support.google.com/chrome/answer/14218344?hl=en",
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
}
}
}

18
evaluation_examples/examples/chrome/b5ebc8c6-6329-4373-85b4-9421c97375e9.json
View File

@@ -1,18 +0,0 @@
{
"id": "b5ebc8c6-6329-4373-85b4-9421c97375e9",
"snapshot": "chrome",
"instruction": "I am trying to find the first three websites that I looked at three days ago, but it looks like it has disappeared off the face of the planet. I thought I would have better luck looking through my Google Chrome browsing history, but I just cannot find it. Could you help me access the first three websites that I entered three days ago?",
"source": "https://superuser.com/questions/364470/is-there-a-way-to-view-google-chrome-browsing-history-past-three-months-ago?rq=1",
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
}
}
}

18
evaluation_examples/examples/chrome/b63059a2-53bc-4163-a89f-3ac948c74081.json
View File

@@ -1,18 +0,0 @@
{
"id": "b63059a2-53bc-4163-a89f-3ac948c74081",
"snapshot": "chrome",
"instruction": "Harmful websites are very annoying because they trick the browser into thinking that I voluntarily cause pop-ups to open. Like when I click the play button on a video, an advertisement for an adult game opens in a separate window. I want to stop this. Could you help me block all possible pop-ups?",
"source": "https://superuser.com/questions/1303418/how-do-i-make-chrome-block-absolutely-all-pop-ups?rq=1",
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
}
}
}

18
evaluation_examples/examples/chrome/c9e7eaf2-b1a1-4efc-a982-721972fa9f02.json
View File

@@ -1,18 +0,0 @@
{
"id": "c9e7eaf2-b1a1-4efc-a982-721972fa9f02",
"snapshot": "chrome",
"instruction": "Navigate to the website of one-way flights tomorrow to Singpore on Expedia please.",
"source": "https://www.youtube.com/watch?v=t6qvLhZ_zc4",
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
}
}
}

18
evaluation_examples/examples/chrome/d088f539-cab4-4f9a-ac92-9999fc3a656e.json
View File

@@ -1,18 +0,0 @@
{
"id": "d088f539-cab4-4f9a-ac92-9999fc3a656e",
"snapshot": "chrome",
"instruction": "I've got a bunch of fun stuff open right now. Can you group all these tabs at the top of Chrome and name it 'Leisure' for me? It'll help me get back to them quickly when I want to relax.",
"source": "https://medium.com/@inkverseuk2/useful-tips-and-tricks-for-the-google-chrome-browser-ac7d0d24b3cc",
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
}
}
}

82
evaluation_examples/examples/libreoffice_calc/01b269ae-2111-4a07-81fd-3fcd711993b0-win.json
View File

@@ -1,82 +0,0 @@
{
"id": "01b269ae-2111-4a07-81fd-3fcd711993b0",
"snapshot": "libreoffice_calc",
"instruction": "Fill all the blank cells with the value in the cell above it",
"source": "https://www.youtube.com/shorts/VrUzPTIwQ04",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1FuOZ-5YoKgLLwl_oZd4R3D8pZACf_ukS&export=download&authuser=0&confirm=t&uuid=2051e7a6-5930-4cef-8d77-20ebf66ec6e6&at=APZUnTX1fXqlxy6rluq-Kw-LUhS5:1705919461032",
"path": "C:\\Users\\user\\Student_Level_Fill_Blank.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "C:\\Users\\user\\Student_Level_Fill_Blank.xlsx"
}
}
],
"trajectory": "trajectories/01b269ae-2111-4a07-81fd-3fcd711993b0",
"related_apps": [
"msoffice_excel"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "Student_Level_Fill_Blank.xlsx - Excel",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=1HTle3vgdZSjJIK_wjXyjtWwbiYJeguwv&export=download&authuser=0&confirm=t&uuid=c5d0868b-bed2-48fb-949b-8a9f3f61e8cf&at=APZUnTVqS9CTZFJ1rPqCGQPDCv3p:1705919542916",
"dest": "Student_Level_Fill_Blank_gold.xlsx"
},
"result": {
"type": "vm_file",
"path": "C:\\Users\\user\\Student_Level_Fill_Blank.xlsx",
"dest": "Student_Level_Fill_Blank.xlsx"
},
"options": {
"rules": [
{
"type": "sheet_data",
"sheet_idx0": 0,
"sheet_idx1": "EI0"
}
]
}
}
}

82
evaluation_examples/examples/libreoffice_calc/0acbd372-ca7a-4507-b949-70673120190f.json
View File

@@ -1,82 +0,0 @@
{
"id": "0acbd372-ca7a-4507-b949-70673120190f",
"snapshot": "libreoffice_calc",
"instruction": "Calculate Net Income in a new column with header \"Net Income\" and format all data as accounting number type.",
"source": "SheetCopilot@121",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1VoEpRbXGxxrxIp-a2iGPqgVPQNdswQB-&export=download",
"path": "/home/user/NetIncome.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/NetIncome.xlsx"
}
}
],
"trajectory": "trajectories/0acbd372-ca7a-4507-b949-70673120190f",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "NetIncome.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1NGZNpzoB3YDdDiWZy4eZtZMwM9Fw1vw2&export=download",
"dest": "1_NetIncome_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/NetIncome.xlsx",
"dest": "NetIncome.xlsx"
},
"options": {
"rules": [
{
"type": "sheet_data",
"sheet_idx0": 0,
"sheet_idx1": "EI0"
}
]
}
}
}

98
evaluation_examples/examples/libreoffice_calc/163789f0-c895-4a50-8207-17cbdd56ec38.json
View File

@@ -1,98 +0,0 @@
{
"id": "163789f0-c895-4a50-8207-17cbdd56ec38",
"snapshot": "libreoffice_calc",
"instruction": "Create a pivot table in a new sheet (Sheet2) to calculate the sum of revenue for each product. In this new sheet, plot a horizontal bar chart illustrating the revenue sums in the pivot table. Turn off the legend and then set the chart tile as \"Revenue of each product\".",
"source": "SheetCopilot@176",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1bNHlYdEXNBBHab1kiYaD35Xc3hNIyR8J&export=download",
"path": "/home/user/SummerSales.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/SummerSales.xlsx"
}
}
],
"trajectory": "trajectories/163789f0-c895-4a50-8207-17cbdd56ec38",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "SummerSales.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=14xDNTxqVEpnoi1FmYgfOH0Osevl3Sx6X&export=download",
"dest": "1_SummerSales_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/SummerSales.xlsx",
"dest": "SummerSales.xlsx"
},
"options": {
"rules": [
{
"type": "chart",
"sheet_idx0": "RNSheet2",
"sheet_idx1": "ENSheet2",
"chart_props": [
"type",
"legend",
"title"
]
},
{
"type": "pivot_table",
"sheet_idx0": "RNSheet2",
"sheet_idx1": "ENSheet2",
"pivot_props": [
"col_fields",
"filter",
"row_fields",
"data_fields"
]
}
]
}
}
}

96
evaluation_examples/examples/libreoffice_calc/28047f4a-d877-4bea-95f7-e42b1c919957.json
View File

@@ -1,96 +0,0 @@
{
"id": "28047f4a-d877-4bea-95f7-e42b1c919957",
"snapshot": "libreoffice_calc",
"instruction": "Summarize the sales for each product and illustrate it with a bar chart in a new sheet (Sheet2).",
"source": "SheetCopilot@108",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1ydRPxPp5Cy1RIpURMwbgxE0ieAvCgQgC&export=download",
"path": "/home/user/Invoices.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/Invoices.xlsx"
}
}
],
"trajectory": "trajectories/28047f4a-d877-4bea-95f7-e42b1c919957",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "Invoices.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 2.0
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1y-MObA1CgcDBM8KLU-9n546E7ZQbouQJ&export=download",
"dest": "12_Invoices_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/Invoices.xlsx",
"dest": "Invoices.xlsx"
},
"options": {
"rules": [
{
"type": "chart",
"sheet_idx0": "RNSheet2",
"sheet_idx1": "ENSheet2",
"chart_props": [
"type"
]
},
{
"type": "pivot_table",
"sheet_idx0": "RNSheet2",
"sheet_idx1": "ENSheet2",
"pivot_props": [
"col_fields",
"filter",
"row_fields",
"data_fields"
]
}
]
}
}
}

79
evaluation_examples/examples/libreoffice_calc/39aa4e37-dc91-482e-99af-132a612d40f3.json
View File

@@ -1,79 +0,0 @@
{
"id": "39aa4e37-dc91-482e-99af-132a612d40f3",
"snapshot": "libreoffice_calc",
"instruction": "Help me rename sheet1 \"LARS_Science_Assessment\"",
"source": "https://www.libreofficehelp.com/add-insert-delete-copy-move-rename-a-worksheet-in-libreoffice-calc/",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1Y9KUHsACajMU1kWz_XjW0VBO3RleDBXw&export=download&authuser=0&confirm=t&uuid=73fe859e-7fe1-449b-83cd-2ddaab067f90&at=APZUnTW-Gp9kn8VhJVCXi5VWxjMT:1706099595303",
"path": "/home/user/LARS_Science_Assessment_Resource_List_7-30-21.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/LARS_Science_Assessment_Resource_List_7-30-21.xlsx"
}
}
],
"trajectory": "trajectories/39aa4e37-dc91-482e-99af-132a612d40f3",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "LARS_Science_Assessment_Resource_List_7-30-21.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
}
],
"func": "compare_table",
"result": {
"type": "vm_file",
"path": "/home/user/LARS_Science_Assessment_Resource_List_7-30-21.xlsx",
"dest": "LARS_Science_Assessment_Resource_List_7-30-21.xlsx"
},
"expected": {
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=1JC8iKt5_XjhksBDSePi0THwrfM5oF-5A&export=download&authuser=0&confirm=t&uuid=6124298b-1487-4a85-b7d9-d9ba133c26e0&at=APZUnTVfW7o4XruPUft-Dph7um6J:1706099593830",
"dest": "LARS_Science_Assessment_Resource_List_7-30-21_gold.xlsx"
},
"options": {
"rules": [
{
"type": "sheet_name"
},
{
"type": "sheet_data",
"sheet_idx0": 0,
"sheet_idx1": "EI0"
}
]
}
}
}

83
evaluation_examples/examples/libreoffice_calc/447b9505-7a2f-4863-9dd1-69395482eb4b.json
View File

@@ -1,83 +0,0 @@
{
"id": "447b9505-7a2f-4863-9dd1-69395482eb4b",
"snapshot": "libreoffice_calc",
"instruction": "Divide the values through column C to P by 1 million and put the results along with the year headers in a new sheet.",
"source": "SheetCopilot@28",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1v2Hfrd5fE2JG7H_ED6NbtC8G7hd8aOrM&export=download",
"path": "/home/user/EasyGDPBreakdown.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/EasyGDPBreakdown.xlsx"
}
}
],
"trajectory": "trajectories/447b9505-7a2f-4863-9dd1-69395482eb4b",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "EasyGDPBreakdown.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 10
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1cx0tSCOEGbsjVWhHJB1W_z15gAReEzIk&export=download",
"dest": "5_EasyGDPBreakdown_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/EasyGDPBreakdown.xlsx",
"dest": "EasyGDPBreakdown.xlsx"
},
"options": {
"rules": [
{
"type": "sheet_data",
"sheet_idx0": "RNSheet2",
"sheet_idx1": "ENSheet2",
"precision": 2
}
]
}
}
}

88
evaluation_examples/examples/libreoffice_calc/5549c616-3cec-478e-940e-0c92fe9a10e3.json
View File

@@ -1,88 +0,0 @@
{
"id": "5549c616-3cec-478e-940e-0c92fe9a10e3",
"snapshot": "libreoffice_calc",
"instruction": "Calculate the sum of \"Sales\" and \"COGS\" for each week in a new sheet.",
"source": "SheetCopilot@202",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1gRFurvUFCy-MpU7PQS_rMo9HUk5ZiDRj&export=download",
"path": "/home/user/WeeklySales.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/WeeklySales.xlsx"
}
}
],
"trajectory": "trajectories/5549c616-3cec-478e-940e-0c92fe9a10e3",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "WeeklySales.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1KUXBg3LRRP9Iefuv0G0vwuHDz-28DWy6&export=download",
"dest": "5_WeeklySales_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/WeeklySales.xlsx",
"dest": "WeeklySales.xlsx"
},
"options": {
"rules": [
{
"type": "pivot_table",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"pivot_props": [
"col_fields",
"filter",
"row_fields",
"data_fields"
]
}
]
}
}
}

103
evaluation_examples/examples/libreoffice_calc/5780a545-4e20-4230-95b4-cac135ef119f.json
View File

@@ -1,103 +0,0 @@
{
"id": "5780a545-4e20-4230-95b4-cac135ef119f",
"snapshot": "libreoffice_calc",
"instruction": "In a new sheet, merge cells A1:B1 and write bold text \"Summer sales ($)\" with blue fill color and white text color. Then create a pivot table starting in this new sheet for my data in Sheet 1 to calculate the sum of revenue for each promotion. Plot a 3D pie chart illustrating the results. Set the chart title as \"Revenue of Each Promotion ($)\" and move the legends to the bottom. Don't forget to add outside end data labels for the chart.",
"source": "SheetCopilot@53",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1I29YyV7zFdNqbsQw0SWD9pDuLz3oHlge&export=download",
"path": "/home/user/EntireSummerSales.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/EntireSummerSales.xlsx"
}
}
],
"trajectory": "trajectories/5780a545-4e20-4230-95b4-cac135ef119f",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "EntireSummerSales.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1zHi--HRZwHvyMyvSXx62qO6Laiql7zG3&export=download",
"dest": "4_EntireSummerSales_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/EntireSummerSales.xlsx",
"dest": "EntireSummerSales.xlsx"
},
"options": {
"rules": [
{
"type": "sheet_data",
"sheet_idx0": 0,
"sheet_idx1": "EI0"
},
{
"type": "chart",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"chart_props": [
"type",
"legend",
"title"
]
},
{
"type": "pivot_table",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"pivot_props": [
"col_fields",
"filter",
"row_fields",
"data_fields"
]
}
]
}
}
}

92
evaluation_examples/examples/libreoffice_calc/5b5434c6-560c-47a1-a89f-929c688448f5.json
View File

@@ -1,92 +0,0 @@
{
"id": "5b5434c6-560c-47a1-a89f-929c688448f5",
"snapshot": "libreoffice_calc",
"instruction": "I would like you to extract a breakdown of the data and place it into a new sheet. The requirements are as follows: (1) Keep only \"Gross Domestic Product (GDP)\" from the IndicatorName field, (2) I don't need the data from 2000 to 2002. In the new sheet, create a stacked area chart to display the GDP growth against the years for the countries whose 2013 GDP ranked top 10 (do not delete other countries' data). Display the legends as the top 10 country names on the right and set the chart title as \"Top 10 GDP",
"source": "SheetCopilot@24",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1v2Hfrd5fE2JG7H_ED6NbtC8G7hd8aOrM&export=download",
"path": "/home/user/EasyGDPBreakdown.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/EasyGDPBreakdown.xlsx"
}
}
],
"trajectory": "trajectories/5b5434c6-560c-47a1-a89f-929c688448f5",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "EasyGDPBreakdown.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=17jnaMdPBh6jXr231QAJGQS9j2QI19KWA&export=download",
"dest": "1_EasyGDPBreakdown_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/EasyGDPBreakdown.xlsx",
"dest": "EasyGDPBreakdown.xlsx"
},
"options": {
"rules": [
{
"type": "sheet_data",
"sheet_idx0": 0,
"sheet_idx1": "EI0"
},
{
"type": "chart",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"chart_props": [
"type",
"legend",
"title"
]
}
]
}
}
}

97
evaluation_examples/examples/libreoffice_calc/5d353deb-c4b0-4126-a99e-5490817b48cb.json
View File

@@ -1,97 +0,0 @@
{
"id": "5d353deb-c4b0-4126-a99e-5490817b48cb",
"snapshot": "libreoffice_calc",
"instruction": "Create a summary table in a new sheet named \"Indicator Summary\" showing the values summed over all countries of each indicator from the years 2010 to 2013. Then, create a clustered bar chart in this sheet to visualize the table with the legends at the bottom",
"source": "SheetCopilot@32",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1v2Hfrd5fE2JG7H_ED6NbtC8G7hd8aOrM&export=download",
"path": "/home/user/EasyGDPBreakdown.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/EasyGDPBreakdown.xlsx"
}
}
],
"trajectory": "trajectories/5d353deb-c4b0-4126-a99e-5490817b48cb",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "EasyGDPBreakdown.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1HOOwYo4Z6DOxz6SKBIgqL_YFll_eSikS&export=download",
"dest": "9_EasyGDPBreakdown_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/EasyGDPBreakdown.xlsx",
"dest": "EasyGDPBreakdown.xlsx"
},
"options": {
"rules": [
{
"type": "chart",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"chart_props": [
"type",
"legend"
]
},
{
"type": "pivot_table",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"pivot_props": [
"col_fields",
"filter",
"row_fields",
"data_fields"
]
}
]
}
}
}

96
evaluation_examples/examples/libreoffice_calc/5f8601f8-6e90-4d2c-91bb-eb5836ad1d5c.json
View File

@@ -1,96 +0,0 @@
{
"id": "5f8601f8-6e90-4d2c-91bb-eb5836ad1d5c",
"snapshot": "libreoffice_calc",
"instruction": "Summarize the total subtotals for each Expense Account in a new sheet. Display the results in a bar chart.",
"source": "SheetCopilot@68",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1tluy-8N0QgRYavQeit61f2b7DuoxXxol&export=download",
"path": "/home/user/ExpenseReport.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/ExpenseReport.xlsx"
}
}
],
"trajectory": "trajectories/5f8601f8-6e90-4d2c-91bb-eb5836ad1d5c",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "ExpenseReport.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1DaZHqX7uKZ7iN_EACRwRHBxGrJ2RARPD&export=download",
"dest": "6_ExpenseReport_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/ExpenseReport.xlsx",
"dest": "ExpenseReport.xlsx"
},
"options": {
"rules": [
{
"type": "chart",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"chart_props": [
"type"
]
},
{
"type": "pivot_table",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"pivot_props": [
"col_fields",
"filter",
"row_fields",
"data_fields"
]
}
]
}
}
}

96
evaluation_examples/examples/libreoffice_calc/64db6b55-06de-451d-b325-17c487fdfee5.json
View File

@@ -1,96 +0,0 @@
{
"id": "64db6b55-06de-451d-b325-17c487fdfee5",
"snapshot": "libreoffice_calc",
"instruction": "Summarize the total Units for each Date in a new sheet and show their relation with a column chart.",
"source": "SheetCopilot@109",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1ydRPxPp5Cy1RIpURMwbgxE0ieAvCgQgC&export=download",
"path": "/home/user/Invoices.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/Invoices.xlsx"
}
}
],
"trajectory": "trajectories/64db6b55-06de-451d-b325-17c487fdfee5",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "Invoices.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1jJ0uaoQ4HiP46qfSscIg_ZS424l1GLm2&export=download",
"dest": "13_Invoices_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/Invoices.xlsx",
"dest": "Invoices.xlsx"
},
"options": {
"rules": [
{
"type": "chart",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"chart_props": [
"type"
]
},
{
"type": "pivot_table",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"pivot_props": [
"col_fields",
"filter",
"row_fields",
"data_fields"
]
}
]
}
}
}

82
evaluation_examples/examples/libreoffice_calc/65551792-4c32-4904-983d-7c68c189b474.json
View File

@@ -1,82 +0,0 @@
{
"id": "65551792-4c32-4904-983d-7c68c189b474",
"snapshot": "libreoffice_calc",
"instruction": "Copy the Year column to column A of a new sheet. Calculate the corresponding gross profits for the years in column B named \"Gross Profit\" of this new sheet.",
"source": "SheetCopilot@90",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1im3XRe64ka2wjlBDkKcpek_1fzC8fP9U&export=download",
"path": "/home/user/IncomeStatement2.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/IncomeStatement2.xlsx"
}
}
],
"trajectory": "trajectories/65551792-4c32-4904-983d-7c68c189b474",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "IncomeStatement2.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1MHhgM6irsS6kpe62_apHgQ_nDNAJUmaZ&export=download",
"dest": "3_IncomeStatement2_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/IncomeStatement2.xlsx",
"dest": "IncomeStatement2.xlsx"
},
"options": {
"rules": [
{
"type": "sheet_data",
"sheet_idx0": 0,
"sheet_idx1": "EI0"
}
]
}
}
}

15
evaluation_examples/examples/libreoffice_calc/7b802dad-6e0f-4204-9815-d4e3f57627d8.json
View File

@@ -1,15 +0,0 @@
{
"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": [
],
"trajectory": "trajectories/7b802dad-6e0f-4204-9815-d4e3f57627d8",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"func": "infeasible"
}
}

97
evaluation_examples/examples/libreoffice_calc/82a95e94-6344-415d-b212-37241610c7fd.json
View File

@@ -1,97 +0,0 @@
{
"id": "82a95e94-6344-415d-b212-37241610c7fd",
"snapshot": "libreoffice_calc",
"instruction": "Sum up the number of rolls sold for each date in a new sheet and display the summarized data in a pie chart in the new sheet. Set the chart title as \"Roll number of each date\".",
"source": "SheetCopilot@143",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1qSoApRNbONzv1wUHLq_jujgKB65bmwgx&export=download",
"path": "/home/user/PricingTable.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/PricingTable.xlsx"
}
}
],
"trajectory": "trajectories/82a95e94-6344-415d-b212-37241610c7fd",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "PricingTable.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1kLoJkIZUg4s3w1wytoZjSXXo44Qk0F7t&export=download",
"dest": "9_PricingTable_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/PricingTable.xlsx",
"dest": "PricingTable.xlsx"
},
"options": {
"rules": [
{
"type": "chart",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"chart_props": [
"type",
"title"
]
},
{
"type": "pivot_table",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"pivot_props": [
"col_fields",
"filter",
"row_fields",
"data_fields"
]
}
]
}
}
}

82
evaluation_examples/examples/libreoffice_calc/852527e8-1b97-466c-a12f-b6b095df59bc.json
View File

@@ -1,82 +0,0 @@
{
"id": "852527e8-1b97-466c-a12f-b6b095df59bc",
"snapshot": "libreoffice_calc",
"instruction": "In a new column named \"Week Sales COGS Summary\", concatenate each cell value in Week, Sales, and COGS columns into the pattern \"Week: [Week Value], Sales: [Sales Value], COGS: [COGS Value]\". Do this for all rows.",
"source": "SheetCopilot@206",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1gRFurvUFCy-MpU7PQS_rMo9HUk5ZiDRj&export=download",
"path": "/home/user/WeeklySales.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/WeeklySales.xlsx"
}
}
],
"trajectory": "trajectories/852527e8-1b97-466c-a12f-b6b095df59bc",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "WeeklySales.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1xJBACBEhTRinZx3kZRMhJa12i468P55u&export=download",
"dest": "9_WeeklySales_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/WeeklySales.xlsx",
"dest": "WeeklySales.xlsx"
},
"options": {
"rules": [
{
"type": "sheet_data",
"sheet_idx0": 0,
"sheet_idx1": "EI0"
}
]
}
}
}

82
evaluation_examples/examples/libreoffice_calc/8909d1cb-5877-44c7-a908-9f1875302441.json
View File

@@ -1,82 +0,0 @@
{
"id": "8909d1cb-5877-44c7-a908-9f1875302441",
"snapshot": "libreoffice_calc",
"instruction": "Copy the \"Date\" and \"Revenue ($)\" values to a new sheet for the rows whose \"Sales Channel\" is \"E-mail Coupon\".",
"source": "SheetCopilot@177",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1bNHlYdEXNBBHab1kiYaD35Xc3hNIyR8J&export=download",
"path": "/home/user/SummerSales.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/SummerSales.xlsx"
}
}
],
"trajectory": "trajectories/8909d1cb-5877-44c7-a908-9f1875302441",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "SummerSales.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1_KlsYyVzWbp9r6ZAHxNPeHozk04Ksryv&export=download",
"dest": "2_SummerSales_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/SummerSales.xlsx",
"dest": "SummerSales.xlsx"
},
"options": {
"rules": [
{
"type": "sheet_data",
"sheet_idx0": 0,
"sheet_idx1": "EI0"
}
]
}
}
}

105
evaluation_examples/examples/libreoffice_calc/8fa9072b-ea9b-4679-84c6-420f3fe4c697.json
View File

@@ -1,105 +0,0 @@
{
"id": "8fa9072b-ea9b-4679-84c6-420f3fe4c697",
"snapshot": "libreoffice_calc",
"instruction": "In a new sheet, merge cells A1:B1 and write bold text \"Summer sales ($)\" with yellow fill color and white text color. Then create a pivot table starting in this new sheet for my data in Sheet 1 to calculate the sum of revenue for each week. Plot a line chart illustrating the trend of the results with chart title \"Revenue of Each Week\". Set the horizontal axis title as \"Week\" and remove the vertical axis title as well as legend.",
"source": "SheetCopilot@51",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1I29YyV7zFdNqbsQw0SWD9pDuLz3oHlge&export=download",
"path": "/home/user/EntireSummerSales.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/EntireSummerSales.xlsx"
}
}
],
"trajectory": "trajectories/8fa9072b-ea9b-4679-84c6-420f3fe4c697",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "EntireSummerSales.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1VZP8zkroAoDZC4fxDfLR5HcnuOUChuh1&export=download",
"dest": "2_EntireSummerSales_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/EntireSummerSales.xlsx",
"dest": "EntireSummerSales.xlsx"
},
"options": {
"rules": [
{
"type": "sheet_data",
"sheet_idx0": 0,
"sheet_idx1": "EI0"
},
{
"type": "chart",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"chart_props": [
"xtitle",
"ytitle",
"type",
"legend",
"title"
]
},
{
"type": "pivot_table",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"pivot_props": [
"col_fields",
"filter",
"row_fields",
"data_fields"
]
}
]
}
}
}

101
evaluation_examples/examples/libreoffice_calc/96042ca2-6ea0-461c-8ba8-81efdc07bbf5.json
View File

@@ -1,101 +0,0 @@
{
"id": "96042ca2-6ea0-461c-8ba8-81efdc07bbf5",
"snapshot": "libreoffice_calc",
"instruction": "Sort the data by the Date column in an ascending order. Then summarize the total roll numbers for each date in a new sheet. Then create a line chart in the new sheet that displays the trend over time.",
"source": "SheetCopilot@142",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1qSoApRNbONzv1wUHLq_jujgKB65bmwgx&export=download",
"path": "/home/user/PricingTable.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/PricingTable.xlsx"
}
}
],
"trajectory": "trajectories/96042ca2-6ea0-461c-8ba8-81efdc07bbf5",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "PricingTable.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=12dmUZiWmBtq8pzsnKCnZKqIGjISRzSAj&export=download",
"dest": "8_PricingTable_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/PricingTable.xlsx",
"dest": "PricingTable.xlsx"
},
"options": {
"rules": [
{
"type": "chart",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"chart_props": [
"type"
]
},
{
"type": "pivot_table",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"pivot_props": [
"col_fields",
"filter",
"row_fields",
"data_fields"
]
},
{
"type": "sheet_data",
"sheet_idx0": 1,
"sheet_idx1": "EI1"
}
]
}
}
}

95
evaluation_examples/examples/libreoffice_calc/97dd78c1-4ba3-4bfd-bbd4-c938532dbcc6.json
View File

@@ -1,95 +0,0 @@
{
"id": "97dd78c1-4ba3-4bfd-bbd4-c938532dbcc6",
"snapshot": "libreoffice_calc",
"instruction": "Calculate the total sales for each employee in a new column named \"Total\" and the total for each month in a new row named \"Total\". Then highlight the employee with the largest total sales with blue fill while the lowest with red fill.",
"source": "SheetCopilot@150",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1Non152JxCxXJI2jL-nVf58YlxoTQXOhw&export=download",
"path": "/home/user/SalesRep.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/SalesRep.xlsx"
}
}
],
"trajectory": "trajectories/97dd78c1-4ba3-4bfd-bbd4-c938532dbcc6",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "SalesRep.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1csjMkqqs_6Few5TySjFVHBuW4jVOJDdq&export=download",
"dest": "1_SalesRep_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/SalesRep.xlsx",
"dest": "SalesRep.xlsx"
},
"options": {
"rules": [
{
"type": "sheet_data",
"sheet_idx0": 0,
"sheet_idx1": "EI0"
},
{
"type": "style",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"props": [
"font_bold",
"font_color",
"bgcolor",
"font_name",
"font_italic",
"font_underline"
]
}
]
}
}
}

82
evaluation_examples/examples/libreoffice_calc/9b534cd8-d497-4ca8-8444-82105b87d6f4.json
View File

@@ -1,82 +0,0 @@
{
"id": "9b534cd8-d497-4ca8-8444-82105b87d6f4",
"snapshot": "libreoffice_calc",
"instruction": "Calculate profit for each week in a new column with header \"Profit\". Then format all numbers with Accounting Number Format.",
"source": "SheetCopilot@198",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1gRFurvUFCy-MpU7PQS_rMo9HUk5ZiDRj&export=download",
"path": "/home/user/WeeklySales.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/WeeklySales.xlsx"
}
}
],
"trajectory": "trajectories/9b534cd8-d497-4ca8-8444-82105b87d6f4",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "WeeklySales.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1w96DtYUzjnsBsBuFUYVK8PabzLUAzoJB&export=download",
"dest": "1_WeeklySales_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/WeeklySales.xlsx",
"dest": "WeeklySales.xlsx"
},
"options": {
"rules": [
{
"type": "sheet_data",
"sheet_idx0": 0,
"sheet_idx1": "EI0"
}
]
}
}
}

103
evaluation_examples/examples/libreoffice_calc/9b6c0b72-3ecc-482d-a240-8ceab861d46e.json
View File

@@ -1,103 +0,0 @@
{
"id": "9b6c0b72-3ecc-482d-a240-8ceab861d46e",
"snapshot": "libreoffice_calc",
"instruction": "Help me calculate the revenue for each product in the sales table considering corresponding retail price and discount. Do this in column G titled \"Revenue\". Then create a pivot table in a new sheet to show the sum of revenue for each product sold. Finally, plot a column chart in the new sheet illustrating this pivot table with chart title \"Revenue of each product\" and without legends.",
"source": "SheetCopilot@1",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1P_8BeCgFJXQwUizF3eFYAeMS4YIw6dmA&export=download",
"path": "/home/user/BoomerangSales.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/BoomerangSales.xlsx"
}
}
],
"trajectory": "trajectories/9b6c0b72-3ecc-482d-a240-8ceab861d46e",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "BoomerangSales.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1Vd6lSKnVk3chk8AxqDn3XwnwkCZCxtyL&export=download",
"dest": "2_BoomerangSales_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/BoomerangSales.xlsx",
"dest": "BoomerangSales.xlsx"
},
"options": {
"rules": [
{
"type": "sheet_data",
"sheet_idx0": 1,
"sheet_idx1": "EI1"
},
{
"type": "chart",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"chart_props": [
"type",
"legend",
"title"
]
},
{
"type": "pivot_table",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"pivot_props": [
"col_fields",
"filter",
"row_fields",
"data_fields"
]
}
]
}
}
}

103
evaluation_examples/examples/libreoffice_calc/9ed02102-6b28-4946-8339-c028166e9512.json
View File

@@ -1,103 +0,0 @@
{
"id": "9ed02102-6b28-4946-8339-c028166e9512",
"snapshot": "libreoffice_calc",
"instruction": "I want to calculate the revenue for each transaction in the sales table considering corresponding retail price and discount. Please help me do this in a new column with header \"Revenue\". Then create a pivot table in a new sheet to show the counts of the websites on which boomerangs were sold. Finally, plot a bar chart in this new sheet for the pivot table with chart title \"Sales frequency by website\" and without legends.",
"source": "SheetCopilot@0",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1P_8BeCgFJXQwUizF3eFYAeMS4YIw6dmA&export=download",
"path": "/home/user/BoomerangSales.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/BoomerangSales.xlsx"
}
}
],
"trajectory": "trajectories/9ed02102-6b28-4946-8339-c028166e9512",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "BoomerangSales.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1XNTnZ1fxMX5xfIAZPqu9m1QuNlxEWQxj&export=download",
"dest": "1_BoomerangSales_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/BoomerangSales.xlsx",
"dest": "BoomerangSales.xlsx"
},
"options": {
"rules": [
{
"type": "sheet_data",
"sheet_idx0": 1,
"sheet_idx1": "EI1"
},
{
"type": "chart",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"chart_props": [
"type",
"legend",
"title"
]
},
{
"type": "pivot_table",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"pivot_props": [
"col_fields",
"filter",
"row_fields",
"data_fields"
]
}
]
}
}
}

96
evaluation_examples/examples/libreoffice_calc/a16d1eb7-941b-4edd-8c08-344213f939ad.json
View File

@@ -1,96 +0,0 @@
{
"id": "a16d1eb7-941b-4edd-8c08-344213f939ad",
"snapshot": "libreoffice_calc",
"instruction": "I would like you to extract a breakdown of the data based on three criteria and place it into a new sheet. The criteria are as follows: (1) \"Gross Domestic Product (GDP)\" from the IndicatorName field, (2) only the countries listed in sheet 2 should be included, and (3) Data from 2000 to 2002 are not needed. In the new sheet, create a stacked area chart with title \"GDP Growth\" to display the GDP over time for the listed countries. Finally, freeze the first two columns.",
"source": "SheetCopilot@76",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1vdXYHCk66mZG-03VeKL9saiPkr7ykMZG&export=download",
"path": "/home/user/GDPBreakdown.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/GDPBreakdown.xlsx"
}
}
],
"trajectory": "trajectories/a16d1eb7-941b-4edd-8c08-344213f939ad",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "GDPBreakdown.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1S_x_aPXel7IzsxkQt0brcicQT2LqoF5M&export=download",
"dest": "1_GDPBreakdown_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/GDPBreakdown.xlsx",
"dest": "GDPBreakdown.xlsx"
},
"options": {
"rules": [
{
"type": "sheet_data",
"sheet_idx0": 0,
"sheet_idx1": "EI0"
},
{
"type": "chart",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"chart_props": [
"type",
"title"
]
},
{
"type": "freeze",
"sheet_idx0": 0,
"sheet_idx1": "EI0"
}
]
}
}
}

88
evaluation_examples/examples/libreoffice_calc/b6da532f-9c4c-4e47-a302-a2c51972134f.json
View File

@@ -1,88 +0,0 @@
{
"id": "b6da532f-9c4c-4e47-a302-a2c51972134f",
"snapshot": "libreoffice_calc",
"instruction": "Display the average annual rate corresponding to each period per year in a new sheet named \"Sheet2\".",
"source": "SheetCopilot@126",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1zejyjqheZOyLaYXS2X8ds6QrZCj3P096&export=download",
"path": "/home/user/PeriodRate.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/PeriodRate.xlsx"
}
}
],
"trajectory": "trajectories/b6da532f-9c4c-4e47-a302-a2c51972134f",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "PeriodRate.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1J-1yO83vTuleYBnF8n6f5ykGju4U1CvS&export=download",
"dest": "3_PeriodRate_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/PeriodRate.xlsx",
"dest": "PeriodRate.xlsx"
},
"options": {
"rules": [
{
"type": "pivot_table",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"pivot_props": [
"col_fields",
"filter",
"row_fields",
"data_fields"
]
}
]
}
}
}

97
evaluation_examples/examples/libreoffice_calc/b6e9778c-11b3-455f-b720-655048787484.json
View File

@@ -1,97 +0,0 @@
{
"id": "b6e9778c-11b3-455f-b720-655048787484",
"snapshot": "libreoffice_calc",
"instruction": "Summarize the revenue sum for each product in a new sheet and plot a pie chart that displays the summarized data. Show the product names as the legend on the right and revenues as the outside-end data labels.",
"source": "SheetCopilot@60",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1I29YyV7zFdNqbsQw0SWD9pDuLz3oHlge&export=download",
"path": "/home/user/EntireSummerSales.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/EntireSummerSales.xlsx"
}
}
],
"trajectory": "trajectories/b6e9778c-11b3-455f-b720-655048787484",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "EntireSummerSales.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1Dt26i2GhgJrPaHvCp11L842Ofjj8qpf5&export=download",
"dest": "11_EntireSummerSales_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/EntireSummerSales.xlsx",
"dest": "EntireSummerSales.xlsx"
},
"options": {
"rules": [
{
"type": "chart",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"chart_props": [
"type",
"legend"
]
},
{
"type": "pivot_table",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"pivot_props": [
"col_fields",
"filter",
"row_fields",
"data_fields"
]
}
]
}
}
}

93
evaluation_examples/examples/libreoffice_calc/c038008d-848a-4e20-abdb-a3e65a71a6cc.json
View File

@@ -1,93 +0,0 @@
{
"id": "c038008d-848a-4e20-abdb-a3e65a71a6cc",
"snapshot": "libreoffice_calc",
"instruction": "Fill out the rest rows for column B using B2. Create a new sheet named \"Sheet2\" and display the data with a line chart showing column A as X values and column B as Y values with the column headers as axis titles. Set the chat title as \"Acc. Vs. Up Block\".",
"source": "SheetCopilot@149",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1UCgvgMej5ToSyKzLBrn9wm1vz3k3sLvB&export=download",
"path": "/home/user/RampUpAndDown.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/RampUpAndDown.xlsx"
}
}
],
"trajectory": "trajectories/c038008d-848a-4e20-abdb-a3e65a71a6cc",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "RampUpAndDown.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1rlXuzKlFxFFaDYNaHF163SJwBMGm8UuZ&export=download",
"dest": "5_RampUpAndDown_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/RampUpAndDown.xlsx",
"dest": "RampUpAndDown.xlsx"
},
"options": {
"rules": [
{
"type": "chart",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"chart_props": [
"xtitle",
"ytitle",
"type",
"title"
]
},
{
"type": "sheet_data",
"sheet_idx0": 1,
"sheet_idx1": "EI1"
}
]
}
}
}

88
evaluation_examples/examples/libreoffice_calc/cb074a90-17ca-4f2a-be85-6f3c354040be.json
View File

@@ -1,88 +0,0 @@
{
"id": "cb074a90-17ca-4f2a-be85-6f3c354040be",
"snapshot": "libreoffice_calc",
"instruction": "Create a Pivot Table in a new sheet named to calculate the total Operating Expenses for each year.",
"source": "SheetCopilot@86",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1mXsdnVfTwJGUeErnDPi00-qet-OoUCKP&export=download",
"path": "/home/user/IncomeStatement.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/IncomeStatement.xlsx"
}
}
],
"trajectory": "trajectories/cb074a90-17ca-4f2a-be85-6f3c354040be",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "IncomeStatement.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1pcIlTRX3Y9lbAehS6u6el8sCUAQt8af_&export=download",
"dest": "4_IncomeStatement_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/IncomeStatement.xlsx",
"dest": "IncomeStatement.xlsx"
},
"options": {
"rules": [
{
"type": "pivot_table",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"pivot_props": [
"col_fields",
"filter",
"row_fields",
"data_fields"
]
}
]
}
}
}

96
evaluation_examples/examples/libreoffice_calc/cd159658-fff3-4f94-a518-fad4007a152a.json
View File

@@ -1,96 +0,0 @@
{
"id": "cd159658-fff3-4f94-a518-fad4007a152a",
"snapshot": "libreoffice_calc",
"instruction": "Create a table in a new sheet showing the total revenue for each month and then plot a line chart with the months as the x-axis labels.",
"source": "SheetCopilot@181",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1bNHlYdEXNBBHab1kiYaD35Xc3hNIyR8J&export=download",
"path": "/home/user/SummerSales.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/SummerSales.xlsx"
}
}
],
"trajectory": "trajectories/cd159658-fff3-4f94-a518-fad4007a152a",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "SummerSales.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1L_ZbEAdbTubB6pcXFoM4N-qjiXLJ2KCp&export=download",
"dest": "6_SummerSales_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/SummerSales.xlsx",
"dest": "SummerSales.xlsx"
},
"options": {
"rules": [
{
"type": "chart",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"chart_props": [
"type"
]
},
{
"type": "pivot_table",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"pivot_props": [
"col_fields",
"filter",
"row_fields",
"data_fields"
]
}
]
}
}
}

103
evaluation_examples/examples/libreoffice_calc/cd3c4994-b9e2-426b-8157-f7978ff55501.json
View File

@@ -1,103 +0,0 @@
{
"id": "cd3c4994-b9e2-426b-8157-f7978ff55501",
"snapshot": "libreoffice_calc",
"instruction": "In a new sheet, merge cells A1:B1 and write bold text \"Summer sales ($)\" with blue fill color and white text color. Then create a pivot table in this new sheet for my data in Sheet 1 and summarize the monthly revenue for each sales channel. Plot a stacked column chart illustrating the results. Set the chart titles as \"Revenue of Each Channel ($)\" and move the legends to the bottom.",
"source": "SheetCopilot@52",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1I29YyV7zFdNqbsQw0SWD9pDuLz3oHlge&export=download",
"path": "/home/user/EntireSummerSales.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/EntireSummerSales.xlsx"
}
}
],
"trajectory": "trajectories/cd3c4994-b9e2-426b-8157-f7978ff55501",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "EntireSummerSales.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1MDqRVCrhUq_FKI0ZspIxcEyww_BZ-4Lb&export=download",
"dest": "3_EntireSummerSales_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/EntireSummerSales.xlsx",
"dest": "EntireSummerSales.xlsx"
},
"options": {
"rules": [
{
"type": "sheet_data",
"sheet_idx0": 0,
"sheet_idx1": "EI0"
},
{
"type": "chart",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"chart_props": [
"type",
"legend",
"title"
]
},
{
"type": "pivot_table",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"pivot_props": [
"col_fields",
"filter",
"row_fields",
"data_fields"
]
}
]
}
}
}

105
evaluation_examples/examples/libreoffice_calc/de7a24c3-7f47-45c7-bba9-ba1aaaf015f8.json
View File

@@ -1,105 +0,0 @@
{
"id": "de7a24c3-7f47-45c7-bba9-ba1aaaf015f8",
"snapshot": "libreoffice_calc",
"instruction": "In a new sheet, merge cells A1:B1 and write bold text \"Summer sales ($)\" with blue fill color and white text color. Then create a pivot table in this new sheet for the Sheet 1 data to calculate the revenue sum for each product. Plot a horizontal bar chart illustrating the results. Set the chart title as \"Revenue of Each Product\" and remove the axis titles and legend.",
"source": "SheetCopilot@50",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1I29YyV7zFdNqbsQw0SWD9pDuLz3oHlge&export=download",
"path": "/home/user/EntireSummerSales.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/EntireSummerSales.xlsx"
}
}
],
"trajectory": "trajectories/de7a24c3-7f47-45c7-bba9-ba1aaaf015f8",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "EntireSummerSales.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=12QQfwtxURMSMJlP9IRvKJzSCAWu0TqsB&export=download",
"dest": "1_EntireSummerSales_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/EntireSummerSales.xlsx",
"dest": "EntireSummerSales.xlsx"
},
"options": {
"rules": [
{
"type": "sheet_data",
"sheet_idx0": 0,
"sheet_idx1": "EI0"
},
{
"type": "chart",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"chart_props": [
"xtitle",
"ytitle",
"type",
"legend",
"title"
]
},
{
"type": "pivot_table",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"pivot_props": [
"col_fields",
"filter",
"row_fields",
"data_fields"
]
}
]
}
}
}

97
evaluation_examples/examples/libreoffice_calc/f13c9e86-3d6d-475f-b2bc-9557fe355236.json
View File

@@ -1,97 +0,0 @@
{
"id": "f13c9e86-3d6d-475f-b2bc-9557fe355236",
"snapshot": "libreoffice_calc",
"instruction": "Calculate the gross profits for all years. Copy the Year, Sales, and Gross Profit columns to a new sheet and then plot a clustered column chart displaying the sales and profits vs. the years. Set the X and Y-axis titles as \"Year\" and \"Amount\" respectively.",
"source": "SheetCopilot@96",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1im3XRe64ka2wjlBDkKcpek_1fzC8fP9U&export=download",
"path": "/home/user/IncomeStatement2.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/IncomeStatement2.xlsx"
}
}
],
"trajectory": "trajectories/f13c9e86-3d6d-475f-b2bc-9557fe355236",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "IncomeStatement2.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1yeSyR89nw6aYLXfsb1xUB94pOzK0z7VK&export=download",
"dest": "9_IncomeStatement2_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/IncomeStatement2.xlsx",
"dest": "IncomeStatement2.xlsx"
},
"options": {
"rules": [
{
"type": "sheet_data",
"sheet_idx0": 0,
"sheet_idx1": "EI0"
},
{
"type": "chart",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"chart_props": [
"xtitle",
"ytitle",
"type"
]
},
{
"type": "sheet_data",
"sheet_idx0": 1,
"sheet_idx1": "EI1"
}
]
}
}
}

96
evaluation_examples/examples/libreoffice_calc/f654bf9a-dea2-472d-a877-edeeb12d7462.json
View File

@@ -1,96 +0,0 @@
{
"id": "f654bf9a-dea2-472d-a877-edeeb12d7462",
"snapshot": "libreoffice_calc",
"instruction": "Summarize revenue by week in a new sheet and display it as a line chart in the new sheet.",
"source": "SheetCopilot@182",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1bNHlYdEXNBBHab1kiYaD35Xc3hNIyR8J&export=download",
"path": "/home/user/SummerSales.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/SummerSales.xlsx"
}
}
],
"trajectory": "trajectories/f654bf9a-dea2-472d-a877-edeeb12d7462",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "SummerSales.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1ZAJNtz0wjVM_-CS5yxAjyS_-qXap-7Rz&export=download",
"dest": "7_SummerSales_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/SummerSales.xlsx",
"dest": "SummerSales.xlsx"
},
"options": {
"rules": [
{
"type": "chart",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"chart_props": [
"type"
]
},
{
"type": "pivot_table",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"pivot_props": [
"col_fields",
"filter",
"row_fields",
"data_fields"
]
}
]
}
}
}

96
evaluation_examples/examples/libreoffice_calc/fe29cdf3-d317-47b3-a657-d61f97f00b88.json
View File

@@ -1,96 +0,0 @@
{
"id": "fe29cdf3-d317-47b3-a657-d61f97f00b88",
"snapshot": "libreoffice_calc",
"instruction": "Calculate the total revenue for each month in a new sheet and draw a bar chart for the results.",
"source": "SheetCopilot@61",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1I29YyV7zFdNqbsQw0SWD9pDuLz3oHlge&export=download",
"path": "/home/user/EntireSummerSales.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/EntireSummerSales.xlsx"
}
}
],
"trajectory": "trajectories/fe29cdf3-d317-47b3-a657-d61f97f00b88",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "EntireSummerSales.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1_gUOT7TuqIk3g-wn5wG1gZfxkwMJ0rDK&export=download",
"dest": "12_EntireSummerSales_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/EntireSummerSales.xlsx",
"dest": "EntireSummerSales.xlsx"
},
"options": {
"rules": [
{
"type": "chart",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"chart_props": [
"type"
]
},
{
"type": "pivot_table",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"pivot_props": [
"col_fields",
"filter",
"row_fields",
"data_fields"
]
}
]
}
}
}

79
evaluation_examples/examples/libreoffice_impress/f0a334af-f91b-4c03-b578-aac9bec2b543.json
View File

@@ -1,79 +0,0 @@
{
"id": "f0a334af-f91b-4c03-b578-aac9bec2b543",
"snapshot": "libreoffice_impress",
"instruction": "Insert the video Movie_countdown_2.mov on the Desktop into my current slide, please.",
"source": "https://www.libreofficehelp.com/insert-video-impress-presentation/#Inserting_a_Video_in_Impress",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1vvRkrxOK_sFPX9PLFniFqrdNEZ2pQnPP&export=download&authuser=0&confirm=t&uuid=71964a12-2d0a-4c71-9375-2f9ec15de1ad&at=APZUnTX_B-T2GeZPS7ZmchMQ6E7m:1705481285721",
"path": "/home/user/Desktop/Movie_activities_TURKEY.pptx"
}
]
}
},
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1S4lACtBb40Ff0DEjB2bG2tzr2qWwQLGd&export=download&authuser=0&confirm=t&uuid=a28c123e-5371-4e17-82c2-ed7b1f05b728&at=APZUnTW_rlUPV6mM4RjS0R6dMSv4:1705469776913",
"path": "/home/user/Desktop/Movie_countdown_2.mov"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/Desktop/Movie_activities_TURKEY.pptx"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"libreoffice_impress"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "Movie_countdown_2.pptx - LibreOffice Impress",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey('ctrl', 's');"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "contains_mp4_video",
"result": {
"type": "vm_file",
"path": "/home/user/Desktop/Movie_activities_TURKEY.pptx",
"dest": "Movie_activities_TURKEY.pptx"
}
}
}

67
evaluation_examples/examples/libreoffice_writer/41c621f7-3544-49e1-af8d-dafd0f834f75.json
View File

@@ -1,67 +0,0 @@
{
"id": "41c621f7-3544-49e1-af8d-dafd0f834f75",
"snapshot": "libreoffice_writer",
"instruction": "I added annotations starting with a \"#\" next to the sentences that my students wrote. I want my annotations to stand out more, so I highlighted them in yellow. Can you help me with this favor? I'm having a hard time coloring the annotations one by one. By the way, remember to remove the # sign after highlighting the text part. Thanks!",
"source": "https://superuser.com/questions/1668018/how-to-auto-format-lines-in-libre-office-writer",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1WsEBs6RS-j6lvx_DFk5xTK-HdEkIDcPy&export=download&authuser=0&confirm=t&uuid=aa012ca0-f651-474f-bd84-6b86d5260817&at=APZUnTU3RImLCGSgOkUpUGKyYCrB:1706018377717",
"path": "/home/user/Desktop/How_to_read_a_scientific_article.docx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/Desktop/How_to_read_a_scientific_article.docx"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"libreoffice_writer"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "How_to_read_a_scientific_article.docx - LibreOffice Writer",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; import time; pyautogui.hotkey('ctrl', 's'); time.sleep(0.5); "
]
}
}
],
"func": "compare_highlighted_text",
"expected": {
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=1x2gplRDN1AOnRWiqfqmJqN9JTQ_x4sPu&export=download&authuser=0&confirm=t&uuid=ea6b0a61-fd06-4823-b253-05473c77c192&at=APZUnTUxWWFB_TOKLR9chabErm7b:1706018376493",
"dest": "How_to_read_a_scientific_article_Gold.docx"
},
"result": {
"type": "vm_file",
"path": "/home/user/Desktop/How_to_read_a_scientific_article.docx",
"dest": "How_to_read_a_scientific_article.docx"
}
}
}

67
evaluation_examples/examples/libreoffice_writer/45d61a06-6545-4422-97b7-bc76cfa964c1.json
View File

@@ -1,67 +0,0 @@
{
"id": "45d61a06-6545-4422-97b7-bc76cfa964c1",
"snapshot": "libreoffice_writer",
"instruction": "Replace all newlines with paragraph marks in LibreOffice Writer",
"source": "https://stackoverflow.com/questions/71685737/how-to-replace-all-newlines-with-paragraph-marks-in-libreoffice-write",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=16lQcSkw-JQ_v8Sg0HkCtnOzyK-4cok8N&export=download&authuser=0&confirm=t&uuid=a3f833ae-2572-4cf3-8a21-6d250e689415&at=APZUnTUfn24NGMtXEzz2Nf7cFLjt:1704975857398",
"path": "/home/user/Desktop/NOVEL_Submission_Guidelines.docx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/Desktop/NOVEL_Submission_Guidelines.docx"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"libreoffice_writer"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "NOVEL_Submission_Guidelines.docx - LibreOffice Writer",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; import time; pyautogui.hotkey('ctrl', 's'); time.sleep(0.5); "
]
}
}
],
"func": "compare_line_spacing",
"expected": {
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=1LaS5ObaOsbyKX1M17vi8ZseZwawgvNmf&export=download&authuser=0&confirm=t&uuid=db523e81-fa22-4002-97ff-e5dff92106a7&at=APZUnTVnT3ZYOGW7ZQdeW4SZP7mX:1704975993684",
"dest": "NOVEL_Submission_Guidelines_Gold.docx"
},
"result": {
"type": "vm_file",
"path": "/home/user/Desktop/NOVEL_Submission_Guidelines.docx",
"dest": "NOVEL_Submission_Guidelines.docx"
}
}
}

67
evaluation_examples/examples/libreoffice_writer/663876c7-3471-43db-ba51-f410b13d9d7d.json
View File

@@ -1,67 +0,0 @@
{
"id": "663876c7-3471-43db-ba51-f410b13d9d7d",
"snapshot": "libreoffice_writer",
"instruction": "Insert the equation \"(a + b)^2 = a^2 + 2 a b + b^2\" at the position of the cursor.",
"source": "https://askubuntu.com/questions/319593/how-to-type-science-equations-in-libre-office",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1J3--srr-Fmt2z-wOAyPDmO5GoiJMkUvZ&export=download&authuser=0&confirm=t&uuid=5f275f3d-ab7d-4d27-848a-8012af4bcf7f&at=APZUnTVe5ucwe1Q0oVi9jwiY5PF7:1704971494071",
"path": "/home/user/Desktop/Factoring_Perfect_Square_Trinomials.docx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/Desktop/Factoring_Perfect_Square_Trinomials.docx"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"libreoffice_writer"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "Factoring_Perfect_Square_Trinomials.docx - LibreOffice Writer",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; import time; pyautogui.hotkey('ctrl', 's'); time.sleep(0.5); "
]
}
}
],
"func": "compare_insert_equation",
"expected": {
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=1QGfyQUPEjOX8osycnjR8E5yHeIEGccKI&export=download&authuser=0&confirm=t&uuid=174491d6-7855-4323-9fa5-5146fde48c4a&at=APZUnTXA8bIcIbtw9mUN-K-IU9bT:1704971524974",
"dest": "Factoring_Perfect_Square_Trinomials_Gold.docx"
},
"result": {
"type": "vm_file",
"path": "/home/user/Desktop/Factoring_Perfect_Square_Trinomials.docx",
"dest": "Factoring_Perfect_Square_Trinomials.docx"
}
}
}

52
evaluation_examples/examples/multi_apps/3eb2a122-a5e3-4f89-9820-f7fa1a582969.json
View File

@@ -1,52 +0,0 @@
{
"id": "3eb2a122-a5e3-4f89-9820-f7fa1a582969",
"snapshot": "multiapps",
"instruction": "Please search online for the submission deadline and venue of the ICLR main conference in 2035, and copy it to my clipboard. If not yet publicized, copy None.",
"source": "author",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "command",
"parameters":{
"command": "echo password | sudo -S apt install xsel && xsel -bc",
"shell": "true"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"os", "chrome"
],
"evaluator": {
"func": "is_in_vm_clickboard",
"expected": {
"type": "vm_command_line",
"command": "xsel --clipboard --output",
"shell": "true"
},
"result": {
"type": "rule",
"rules": {
"expected": ["None"]
}
}
}
}

70
evaluation_examples/examples/multi_apps/65e62ec6-4603-4c67-b4d2-07830deb285b.json
View File

@@ -1,70 +0,0 @@
{
"id": "65e62ec6-4603-4c67-b4d2-07830deb285b",
"snapshot": "multiapps",
"instruction": "I've recently become very interested in large language models. I tried entering some questions into several large language models and stored the answers in a file named \"answers.json\" under Desktop. Now, I want to focus only on the answers from GPT-4. Please help me copy all the GPT-4 answers into a Word document named \"results.docx\" under Desktop, one answer per paragraph.",
"source": "",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1V2Ic9V3_5sxwynRMkLCDyqwBVUNe7PSK&export=download",
"path": "/home/user/Desktop/answers.json"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/Desktop/answers.json"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"libreoffice_writer"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "results.docx - LibreOffice Writer",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; import time; pyautogui.hotkey('ctrl', 's'); time.sleep(0.5); "
]
}
}
],
"func": "compare_docx_files_and_ignore_new_lines",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1cLS9dtb-6Yg_VtcFjNbovw6CE04vWuFl&export=download",
"dest": "results_Gold.docx"
},
"result": {
"type": "vm_file",
"path": "/home/user/Desktop/results.docx",
"dest": "results.docx"
},
"options": {
"ignore_blanks": false
}
}
}

69
evaluation_examples/examples/multi_apps/bb7db4c2-30b5-4be7-8dd7-b8c4ec7d3108.json
View File

@@ -1,69 +0,0 @@
{
"id": "bb7db4c2-30b5-4be7-8dd7-b8c4ec7d3108",
"snapshot": "gimp",
"instruction": "I have a background image named 'anmi.png'. I need the image to be enhanced for better sharpness, as 'anmi_sharper.png'. Next, please use it as the background image for my 'index.html' page.",
"source": "",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?export=download&id=1c5YIFwlO204Nz7dno68D_I2ib1uXRyHN",
"path": "/home/user/Desktop/anmi.png"
},
{
"url": "https://drive.google.com/uc?export=download&id=1d7vM939tJQ_vQLSODNWWfW749tEcomBQ",
"path": "/home/user/Desktop/index.html"
}
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"gimp",
"/home/user/Desktop/anmi.png"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"gimp",
"vs_code"
],
"evaluator": {
"func": [
"check_sharper",
"check_html_background_image"
],
"result": [
{
"type": "vm_file",
"path": "/home/user/Desktop/anmi_sharper.png",
"dest": "anmi_sharper.png"
},
{
"type": "vm_file",
"path": "/home/user/Desktop/index.html",
"dest": "index.html"
}
],
"expected": [
{
"type": "vm_file",
"path": "/home/user/Desktop/anmi.png",
"dest": "anmi.png"
},
{
"type": "rule",
"rules": {
"type:": "value",
"value": "anmi_sharper.png"
}
}
]
}
}

26
evaluation_examples/examples/multi_apps/d28853f4-500a-4749-b9dc-79c3576e759b.json
View File

@@ -1,26 +0,0 @@
{
"id": "d28853f4-500a-4749-b9dc-79c3576e759b",
"snapshot": "libreoffice_calc",
"instruction": "Hey there! So, I've got this bit of a situation and I'm hoping you can help me out. I've been working on gathering research for this big project at work, and I've ended up with a bunch of PDF files from various sources. Each PDF contains some really crucial information that I need, but here's the kicker - I need all of this info to be in one place where I can easily access and edit it, like in a Word document or a README file.\n\nThe PDFs are a mix of things - some are reports with statistics and findings, others are articles with key insights, and a few are just informational brochures with important dates and details. What I need is for someone to go through each PDF, extract all the relevant information, and then organize it into a single document. I'm talking about making sure that all the stats, insights, dates, and details from each PDF are neatly compiled, so I don't miss anything.\n\nAnd to make things a bit more complicated, some of these PDFs are scanned images of documents, so the text isn't directly selectable. I guess that means you might need to manually type out some parts or find a way to convert the images to text that can be copied.\n\nOnce everything's been compiled into this one document, could you save it as both a Word doc and a README file? I'd like to have it in these two formats so I can easily share it with my team and also have a version that's ready to be uploaded to our project's repository.\n\nOh, and could you make sure to organize the information by the source PDF? Like, maybe start each section with the title of the PDF or a brief description of its contents, followed by all the extracted info from that PDF. This way, it'll be easier for me and the team to trace back to the original sources if we need to.\n\nI know it's a lot to ask, but having all this information consolidated and organized is going to be a huge help for moving forward with the project. Thanks a bunch for helping me tackle this!",
"source": "authors",
"config": [
],
"trajectory": "trajectories/d28853f4-500a-4749-b9dc-79c3576e759b",
"related_apps": [
],
"evaluator": {
"postconfig": [],
"func": "",
"result": {
},
"expected": {
},
"options": {
}
}
}

59
evaluation_examples/examples/os/0b35aee5-6f2a-4c71-b2da-aed0105fdbde.json
View File

@@ -1,59 +0,0 @@
{
"id": "0b35aee5-6f2a-4c71-b2da-aed0105fdbde",
"snapshot": "os",
"instruction": "Calculate the md5 sum of \"submission.cpp\" with less sensitivity to superficial changes like comments or whitespace",
"source": "NL2Bash",
"config": [
{
"type": "execute",
"parameters": {
"command": "echo password | sudo -S apt-get install astyle cpp md5sum -y",
"shell": true
}
},
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1UiDgRdPqGGPmklZyXhwO1-UyOlhJsxt0&export=download&authuser=0&confirm=t&uuid=7795d6f5-87df-4ebb-8540-e9756362736a&at=APZUnTVk-7AnKL4ofVZGKQeHxjHY:1707987053722",
"path": "/home/user/Desktop/submission.cpp"
}
]
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; import time; pyautogui.click(960, 540); time.sleep(0.5);"
]
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; import time; pyautogui.hotkey(\"ctrl\", \"alt\", \"t\"); time.sleep(0.5);"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"os"
],
"evaluator": {
"func": "check_include_exclude",
"result": {
"type": "vm_terminal_output"
},
"expected": {
"type": "calc_insensitive_md5"
}
}
}

36
evaluation_examples/examples/os/43c2d64c-bab5-4dcb-a30c-b888321c319a.json
View File

@@ -1,36 +0,0 @@
{
"id": "43c2d64c-bab5-4dcb-a30c-b888321c319a",
"snapshot": "os",
"instruction": "Could you please help me create a dir named 'test' in the root directory of current computer?",
"source": "https://ubuntu.com/tutorials/command-line-for-beginners#4-creating-folders-and-files",
"config": [
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; import time; pyautogui.click(960, 540); time.sleep(0.5);"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"os"
],
"evaluator": {
"func": "exact_match",
"result": {
"type": "vm_command_line",
"command": "[ -d '/test' ] && echo 'Directory exists.' || echo 'Directory does not exist.'",
"shell": true
},
"expected": {
"type": "rule",
"rules":{
"expected": "Directory exists.\n"
}
}
}
}

18
evaluation_examples/examples/os/4d2b519e-e872-4100-8ea3-fe71ab0f9133.json
View File

@@ -1,18 +0,0 @@
{
"id": "4d2b519e-e872-4100-8ea3-fe71ab0f9133",
"snapshot": "os",
"instruction": "Could you please help me to add a new entry \"/home/david/pear/bin\" to the PATH variable in the ZSH terminal?",
"source": "https://stackoverflow.com/questions/11530090/adding-a-new-entry-to-the-path-variable-in-zsh",
"trajectory": "trajectories/",
"config": [],
"related_apps": [
"os"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
}
}
}

18
evaluation_examples/examples/os/5c433d22-ed9a-4e31-91f5-54cf3e8acd63.json
View File

@@ -1,18 +0,0 @@
{
"id": "5c433d22-ed9a-4e31-91f5-54cf3e8acd63",
"snapshot": "os",
"instruction": "I want to change my system language to Chinese (simplified). Can you help me?",
"source": "https://help.ubuntu.com/lts/ubuntu-help/session-language.html.zh-CN",
"trajectory": "trajectories/",
"config": [],
"related_apps": [
"os"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
}
}
}

63
evaluation_examples/examples/os/6ebbfb01-ea72-4226-a2a6-dc428e111ed2.json
View File

@@ -1,63 +0,0 @@
{
"id": "6ebbfb01-ea72-4226-a2a6-dc428e111ed2",
"snapshot": "os",
"instruction": "Could you please help me to set Bash as my default shell on the current Ubuntu system?",
"source": "https://superuser.com/questions/46748/how-do-i-make-bash-my-default-shell-on-ubuntu",
"trajectory": "trajectories/",
"config": [
{
"type": "execute",
"parameters": {
"command": "echo password | sudo -S apt-get install zsh -y",
"shell": true
}
},
{
"type": "execute",
"parameters": {
"command": "echo password | sudo -S chsh -s $(which zsh)",
"shell": true
}
},
{
"type": "execute",
"parameters": {
"command": "echo password | sudo -S loginctl terminate-user user",
"shell": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 10
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; import time; time.sleep(2); pyautogui.press(\"enter\"); pyautogui.type(\"password\"); time.sleep(2); pyautogui.press(\"enter\");"
]
}
}
],
"related_apps": [
"os"
],
"evaluator": {
"func": "exact_match",
"result": {
"type": "vm_command_line",
"command": "echo $SHELL",
"shell": true
},
"expected": {
"type": "rule",
"rules":{
"expected": "/bin/bash\n"
}
}
}
}

29
evaluation_examples/examples/os/765d2b74-88a7-4d50-bf51-34e4106fd24a.json
View File

@@ -1,29 +0,0 @@
{
"id": "765d2b74-88a7-4d50-bf51-34e4106fd24a",
"snapshot": "os",
"instruction": "Can you help me delete the \"test\" file on my desktop?",
"source": "https://help.ubuntu.com/lts/ubuntu-help/files-delete.html.en",
"config": [
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; import time; pyautogui.click(960, 540); time.sleep(0.5);"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"os"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
}
}
}

50
evaluation_examples/examples/os/7688b85f-87a4-4e4a-b2f8-f3d6c3f29b82.json
View File

@@ -1,50 +0,0 @@
{
"id": "7688b85f-87a4-4e4a-b2f8-f3d6c3f29b82",
"snapshot": "os",
"instruction": "Can you move the file 'todo.txt' on the Desktop to the directory 'done/' on the Desktop?",
"source": "https://ubuntu.com/tutorials/command-line-for-beginners#5-moving-and-manipulating-files",
"config": [
{
"type": "execute",
"parameters": {
"command": "echo 'password' | sudo -S touch ~/Desktop/todo.txt && sudo mkdir ~/Desktop/done",
"shell": true
}
},
{
"type": "execute",
"parameters": {
"command": "echo 'password' | sudo -S chmod 777 ~/Desktop/todo.txt && sudo chmod 777 ~/Desktop/done",
"shell": true
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; import time; pyautogui.click(960, 540); time.sleep(0.5);"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"os"
],
"evaluator": {
"func": "exact_match",
"result": {
"type": "vm_command_line",
"command": "if [ -f ~/Desktop/done/todo.txt ]; then echo 'File exists.'; else echo 'File does not exist.'; fi",
"shell": true
},
"expected": {
"type": "rule",
"rules":{
"expected": "File exists.\n"
}
}
}
}

41
evaluation_examples/examples/os/ae039631-2b12-4637-84f6-c67d51511be3.json
View File

@@ -1,41 +0,0 @@
{
"id": "ae039631-2b12-4637-84f6-c67d51511be3",
"snapshot": "os",
"instruction": "Could you please help me check out my current default browser?",
"source": "https://ubuntu.com/tutorials/command-line-for-beginners#5-moving-and-manipulating-files",
"config": [
{
"type": "execute",
"parameters": {
"command": "xdg-settings set default-web-browser firefox.desktop"
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; import time; pyautogui.click(960, 540); time.sleep(0.5);"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"os"
],
"evaluator": {
"func": "exact_match",
"result": {
"type": "vm_command_line",
"command": "xdg-settings get default-web-browser"
},
"expected": {
"type": "rule",
"rules":{
"expected": "firefox.desktop"
}
}
}
}

34
evaluation_examples/examples/os/c56de254-a3ec-414e-81a6-83d2ce8c41fa.json
View File

@@ -1,34 +0,0 @@
{
"id": "c56de254-a3ec-414e-81a6-83d2ce8c41fa",
"snapshot": "os",
"instruction": "I want to install the lxml package on my ubuntu system. Can you help me?",
"source": "https://superuser.com/questions/28426/how-to-extract-text-with-ocr-from-a-pdf-on-linux",
"config": [
{
"type": "execute",
"parameters": {
"command": "sudo aptget update && sudo apt-get install -y python3",
"shell": true
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"os"
],
"evaluator": {
"func": "exact_match",
"result": {
"type": "vm_command_line",
"command": "python3 -c \"import lxml\" >/dev/null 2>&1 && echo \"lxml is installed\" || echo \"lxml is not installed\"",
"shell": true
},
"expected": {
"type": "rule",
"rules":{
"expected": "lxml is installed\n"
}
}
}
}

45
evaluation_examples/examples/os/cc9d4f34-1ca0-4a1b-8ff2-09302696acb9.json
View File

@@ -1,45 +0,0 @@
{
"id": "cc9d4f34-1ca0-4a1b-8ff2-09302696acb9",
"snapshot": "os",
"instruction": "Currently, the program my_process.sh is running in the system and I want to end the process. Can you help me?",
"source": "https://stackoverflow.com/questions/9346211/how-to-kill-a-process-on-a-port-on-ubuntu",
"config": [
{
"type": "execute",
"parameters": {
"command": "echo -e '#!/bin/bash\n\nwhile true; do\necho \"Running my_process...\"\nsleep 1\ndone' > my_process.sh && chmod +x my_process.sh && nohup ./my_process.sh > /dev/null 2>&1 &",
"shell": true
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"os"
],
"evaluator": {
"postconfig": [
{
"type": "sleep",
"parameters": {
"seconds": 5
}
}
],
"func": "check_include_exclude",
"result": {
"type": "vm_command_line",
"command": "ps -ef | grep my_process.sh",
"shell": true
},
"expected": {
"type": "rule",
"rules": {
"include": [
],
"exclude": [
"/bin/sh ./my_process.sh"
]
}
}
}
}

48
evaluation_examples/examples/os/ddc75b62-7311-4af8-bfb3-859558542b36.json
View File

@@ -1,48 +0,0 @@
{
"id": "ddc75b62-7311-4af8-bfb3-859558542b36",
"snapshot": "os",
"instruction": "I want to uninstall the Mahjongg on my system. Can you help me?",
"source": "https://help.ubuntu.com/lts/ubuntu-help/addremove-remove.html.en",
"trajectory": "trajectories/",
"config": [
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; import time; pyautogui.click(960, 540); time.sleep(0.5);"
]
}
}
],
"related_apps": [
"os"
],
"evaluator": {
"postconfig": [
{
"type": "sleep",
"parameters": {
"seconds": 1
}
}
],
"func": "check_include_exclude",
"result": {
"type": "vm_command_line",
"command": "dpkg -l | grep mahjongg",
"shell": true
},
"expected": {
"type": "rule",
"rules": {
"include": [
],
"exclude": [
"mahjongg"
]
}
}
}
}

17
evaluation_examples/examples/os/f10b16e1-c160-4cb3-989f-7b2ec89bc073.json
View File

@@ -1,17 +0,0 @@
{
"id": "f10b16e1-c160-4cb3-989f-7b2ec89bc073",
"snapshot": "os",
"instruction": "Please install the latest version of the GNOME Desktop on the current Ubuntu system.",
"source": "https://www.wikihow.com/Install-Gnome-on-Ubuntu",
"trajectory": "trajectories/",
"related_apps": [
"os"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
}
}
}

27
evaluation_examples/examples/template.json
View File

@@ -1,27 +0,0 @@
{
"id": "",
"snapshot": "libreoffice_calc",
"instruction": "",
"source": "",
"config": [
{
"type": "",
"parameters": {}
}
],
"trajectory": "trajectories/",
"related_apps": [
"app1",
"app2"
],
"evaluator": {
"postconfig": [],
"func": "func",
"result": {
"type": ""
},
"expected": {
"type": ""
}
}
}

0
evaluation_examples/examples/thunderbird/c9e7eaf2-b1a1-4efc-a982-721972fa9f02.json → evaluation_examples/examples/thunderbird/08c73485-7c6d-4681-999d-919f5c32dcfa.json
View File

0
evaluation_examples/examples/thunderbird/94760984-3ff5-41ee-8347-cf1af709fea0.json → evaluation_examples/examples/thunderbird/10a730d5-d414-4b40-b479-684bed1ae522.json
View File

0
evaluation_examples/examples/thunderbird/7b6c7e24-c58a-49fc-a5bb-d57b80e5b4c3.json → evaluation_examples/examples/thunderbird/15c3b339-88f7-4a86-ab16-e71c58dcb01e.json
View File

84
evaluation_examples/examples/thunderbird/37b9808f-b2b4-4177-ab00-9ddfae4bad27.json
View File

@@ -1,84 +0,0 @@
{
"id": "37b9808f-b2b4-4177-ab00-9ddfae4bad27",
"snapshot": "thunderbird",
"instruction": "Please schedule thunderbird to turn off at 16:00",
"source": "https://www.quora.com/How-can-I-schedule-Mozilla-Thunderbird-to-turn-off-automatically",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1EHLRWzBCOsyERkSMUnTF2pnsR0n6ZvtR&export=download&authuser=0&confirm=t&uuid=de09bd5e-bef8-499a-b599-c642af190e10&at=APZUnTXqOsQkxl0zMSX6R1Sgp_v3:1704362491712",
"path": "/home/user/thunderbird-profile.tar.gz"
}
]
}
},
{
"type": "execute",
"parameters": {
"command": [
"tar",
"-xzv",
"--recursive-unlink",
"-f",
"/home/user/thunderbird-profile.tar.gz",
"-C",
"/home/user/"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"/usr/bin/thunderbird"
]
}
}
],
"evaluator": {
"postconfig": [
{
"type": "command",
"parameters": {
"command": ["timedatectl", "set-ntp", "off"]
}
},
{
"type": "command",
"parameters": {
"command": ["timedatectl", "set-time", "16:00"]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 2.0
}
},
{
"type": "execute",
"parameters": {
"command": "ps -eF |grep thunderbird",
"shell": true,
"stdout": "thunderbird.ps"
}
}
],
"func": "check_list",
"result": {
"type": "cache_file",
"path": "thunderbird.ps"
},
"expected": {
"type": "rule",
"rules": {
"unexpect": [
"/usr/lib/thunderbird/thunderbird"
]
}
}
}
}

53
evaluation_examples/examples/thunderbird/3d1682a7-0fb0-49ae-a4dc-a73afd2d06d5.json.nosetup
View File

@@ -1,53 +0,0 @@
{
"id": "3d1682a7-0fb0-49ae-a4dc-a73afd2d06d5",
"snapshot": "thunderbird",
"instruction": "Add a star to every email in local Bills folder",
"source": "https://support.mozilla.org/en-US/kb/organize-your-messages-using-filters",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1EHLRWzBCOsyERkSMUnTF2pnsR0n6ZvtR&export=download&authuser=0&confirm=t&uuid=de09bd5e-bef8-499a-b599-c642af190e10&at=APZUnTXqOsQkxl0zMSX6R1Sgp_v3:1704362491712",
"path": "/home/user/thunderbird-profile.tar.gz"
}
]
}
}
],
"trajectory": "trajectories/3d1682a7-0fb0-49ae-a4dc-a73afd2d06d5",
"related_apps": [
"thunderbird"
],
"evaluator": {
"postconfig": [
{
"type": "close_window",
"parameters": {
"window_name": "Mail.thunderbird",
"strict": true,
"by_class": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"result": {
"type": "vm_file",
"path": "/home/user/.thunderbird/t5q2a5hp.default-release/global-messages-db.sqlite",
"dest": "global-messages-db.sqlite"
},
"func": "run_sqlite3",
"expected": {
"type": "rule",
"rules": {
"sql": "select sum(1) > 0 from messageAttributes where attributeID = 58 and value = 1 and messageID in (select id from messages where folderID = 13);"
}
}
}
}

0
evaluation_examples/examples/thunderbird/6766f2b8-8a72-417f-a9e5-56fcaa735837.json → evaluation_examples/examples/thunderbird/3f28fe4f-5d9d-4994-a456-efd78cfae1a3.json
View File

0
evaluation_examples/examples/thunderbird/480bcfea-d68f-4aaa-a0a9-2589ef319381.json → evaluation_examples/examples/thunderbird/3f49d2cc-f400-4e7d-90cc-9b18e401cc31.json
View File

0
evaluation_examples/examples/thunderbird/e1e75309-3ddb-4d09-92ec-de869c928143.json → evaluation_examples/examples/thunderbird/5203d847-2572-4150-912a-03f062254390.json
View File

58
evaluation_examples/examples/thunderbird/6766f2b8-8a72-417f-a9e5-56fcaa735837.json.nosetup
View File

@@ -1,58 +0,0 @@
{
"id": "6766f2b8-8a72-417f-a9e5-56fcaa735837",
"snapshot": "thunderbird",
"instruction": "Set up a signature using my name and affiliation. My name is Anonym and my affiliation is XYZ Lab.",
"source": "https://www.adsigner.com/user-manual/signatures/setup-email-client-thunderbird/#:~:text=is%20probably%20hidden.-,Right%20click%20on%20the%20empty%20space%20at%20the%20top%20of,signature%20from%20a%20file%20instead.",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1EHLRWzBCOsyERkSMUnTF2pnsR0n6ZvtR&export=download&authuser=0&confirm=t&uuid=de09bd5e-bef8-499a-b599-c642af190e10&at=APZUnTXqOsQkxl0zMSX6R1Sgp_v3:1704362491712",
"path": "/home/user/thunderbird-profile.tar.gz"
}
]
}
}
],
"trajectory": "trajectories/6766f2b8-8a72-417f-a9e5-56fcaa735837",
"related_apps": [
"thunderbird"
],
"evaluator": {
"postconfig": [
{
"type": "close_window",
"parameters": {
"window_name": "Mail.thunderbird",
"strict": true,
"by_class": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"result": {
"type": "vm_file",
"path": "/home/user/.thunderbird/t5q2a5hp.default-release/prefs.js",
"dest": "thunder-prefs.js"
},
"expected": {
"type": "rule",
"rules": {
"expect": {
"mail.identity.id1.htmlSigText": {
"method": "re.S",
"ref": "Anonym.+XYZ Lab"
}
}
}
},
"func": "check_thunderbird_prefs"
}
}

0
evaluation_examples/examples/thunderbird/12086550-11c0-466b-b367-1d9e75b3910e.json → evaluation_examples/examples/thunderbird/7b1e1ff9-bb85-49be-b01d-d6424be18cd0.json
View File

0
evaluation_examples/examples/thunderbird/35253b65-1c19-4304-8aa4-6884b8218fc0.json → evaluation_examples/examples/thunderbird/9b7bc335-06b5-4cd3-9119-1a649c478509.json
View File

0
evaluation_examples/examples/thunderbird/06fe7178-4491-4589-810f-2e2bc9502122.json → evaluation_examples/examples/thunderbird/9bc3cc16-074a-45ac-9bdc-b2a362e1daf3.json
View File

0
evaluation_examples/examples/thunderbird/2ad9387a-65d8-4e33-ad5b-7580065a27ca.json → evaluation_examples/examples/thunderbird/a10b69e1-6034-4a2b-93e1-571d45194f75.json
View File

0
evaluation_examples/examples/thunderbird/99146c54-4f37-4ab8-9327-5f3291665e1e.json → evaluation_examples/examples/thunderbird/a1af9f1c-50d5-4bc3-a51e-4d9b425ff638.json
View File

77
evaluation_examples/examples/thunderbird/d088f539-cab4-4f9a-ac92-9999fc3a656e.json.nosetup
View File

@@ -1,77 +0,0 @@
{
"id": "d088f539-cab4-4f9a-ac92-9999fc3a656e",
"snapshot": "thunderbird",
"instruction": "Attach the my AWS bill to the email. The bill is stored at ~/aws-bill.pdf. Don't close it or send it. I haven't finish all the contents.",
"source": "https://support.mozilla.org/en-US/kb/how-use-attachments",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1JDUxe8Cs0D9La9ECoYbHJAIQ95DZfkDT&export=download&authuser=0&confirm=t&uuid=1e0f94d8-4fb1-4f9b-878a-516cf4a7ebc4&at=APZUnTXHBZKTuW_vQUzi-1XKuAYg:1705242554801",
"path": "/home/user/aws-bill.pdf"
},
{
"url": "https://drive.usercontent.google.com/download?id=1EHLRWzBCOsyERkSMUnTF2pnsR0n6ZvtR&export=download&authuser=0&confirm=t&uuid=de09bd5e-bef8-499a-b599-c642af190e10&at=APZUnTXqOsQkxl0zMSX6R1Sgp_v3:1704362491712",
"path": "/home/user/thunderbird-profile.tar.gz"
},
{
"url": "https://drive.usercontent.google.com/download?id=17LutYTkEXhM__sxvrdldar7p-eQba4Pm&export=download&authuser=0&confirm=t&uuid=34730e1c-0fac-401a-ab91-102a47f02224&at=APZUnTX4eFTnG9vnYlQEJX6N0jqP:1705227498314",
"path": "/home/user/.aws-bill-mail-body.html"
}
]
}
}
],
"trajectory": "trajectories/d088f539-cab4-4f9a-ac92-9999fc3a656e",
"related_apps": [
"thunderbird"
],
"evaluator": {
"postconfig": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1abb7PPPRGGy3elpq2vTXe2aKTMOrbm7c&export=download&authuser=0&confirm=t&uuid=652a3d4c-278e-499c-bb26-58d0f70aa317&at=APZUnTXs_ZTZzOF3QrBa_rMjMr08:1705287009269",
"path": "/home/user/show-thunderbird-attachments.py"
}
]
}
},
{
"type": "execute",
"parameters": {
"command": ["pip", "install", "cssselect"]
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"/home/user/show-thunderbird-attachments.py",
"New-month AWS Bill",
"aws-bill.pdf"
],
"stdout": "check-attachments.output"
}
}
],
"func": "check_list",
"result": {
"type": "cache_file",
"path": "check-attachments.output"
},
"expected": {
"type": "rule",
"rules": {
"expect": [
"Attachment added!"
]
}
}
}
}

0
evaluation_examples/examples/thunderbird/d088f539-cab4-4f9a-ac92-9999fc3a656e.json → evaluation_examples/examples/thunderbird/d38192b0-17dc-4e1d-99c3-786d0117de77.json
View File

0
evaluation_examples/examples/thunderbird/3d1682a7-0fb0-49ae-a4dc-a73afd2d06d5.json → evaluation_examples/examples/thunderbird/dd84e895-72fd-4023-a336-97689ded257c.json
View File

0
evaluation_examples/examples/thunderbird/bb5e4c0d-f964-439c-97b6-bdb9747de3f4.json → evaluation_examples/examples/thunderbird/dfac9ee8-9bc4-4cdc-b465-4a4bfcd2f397.json
View File

59
evaluation_examples/examples/thunderbird/e1e75309-3ddb-4d09-92ec-de869c928143.json.nosetup
View File

@@ -1,59 +0,0 @@
{
"id": "e1e75309-3ddb-4d09-92ec-de869c928143",
"snapshot": "thunderbird",
"instruction": "Create a local folder called \"Promotions\" and create a filter to auto move the inbox emails whose subject contains “discount” to the new folder",
"source": "https://support.mozilla.org/en-US/kb/organize-your-messages-using-filters",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1EHLRWzBCOsyERkSMUnTF2pnsR0n6ZvtR&export=download&authuser=0&confirm=t&uuid=de09bd5e-bef8-499a-b599-c642af190e10&at=APZUnTXqOsQkxl0zMSX6R1Sgp_v3:1704362491712",
"path": "/home/user/thunderbird-profile.tar.gz"
}
]
}
}
],
"trajectory": "trajectories/e1e75309-3ddb-4d09-92ec-de869c928143",
"related_apps": [
"thunderbird"
],
"evaluator": {
"postconfig": [
{
"type": "close_window",
"parameters": {
"window_name": "Message Filters",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "check_thunderbird_filter",
"result": {
"type": "vm_file",
"path": "/home/user/.thunderbird/t5q2a5hp.default-release/ImapMail/outlook.office365.com/msgFilterRules.dat",
"dest": "msgFilterRules.dat"
},
"expected": {
"type": "rule",
"rules": {
"expect": [
{
"enabled": "yes",
"action": "Move to folder",
"actionValue": "mailbox://nobody@Local%20Folders/Promotions",
"condition": ["AND (subject,contains,discount)"]
}
]
}
}
}
}

0
evaluation_examples/examples/thunderbird/030eeff7-b492-4218-b312-701ec99ee0cc.json → evaluation_examples/examples/thunderbird/f201fbc3-44e6-46fc-bcaa-432f9815454c.json
View File

18
evaluation_examples/examples/vlc/0d95d28a-9587-433b-a805-1fbe5467d598.json
View File

@@ -1,18 +0,0 @@
{
"id": "0d95d28a-9587-433b-a805-1fbe5467d598",
"snapshot": "chrome",
"instruction": "Could you help me open the folder containing the current video I am playing?",
"source": "https://superuser.com/questions/1299036/vlc-how-to-open-the-folder-of-the-current-playing-video?noredirect=1&lq=1",
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"vlc"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
}
}
}

12
evaluation_examples/examples/vlc/a1c3ab35-02de-4999-a7ed-2fd12c972c6e.json
View File

@@ -1,12 +0,0 @@
{
"id": "a1c3ab35-02de-4999-a7ed-2fd12c972c6e",
"snapshot": "base_setup",
"instruction": "Could you help me compress the video to MPEG-4 format and save with name with prefix _?",
"source": "https://www.quora.com/How-do-I-compress-a-video-with-VLC",
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"vlc"
],
"evaluator": "evaluation_dir"
}

18
evaluation_examples/examples/vlc/d1ba14d0-fef8-4026-8418-5b581dc68ca0.json
View File

@@ -1,18 +0,0 @@
{
"id": "d1ba14d0-fef8-4026-8418-5b581dc68ca0",
"snapshot": "chrome",
"instruction": "Could you help me make VLC Media Player to repeatedly play a video from the beginning to its midpoint? I'm analyzing the first half of a film for a class project, and continuously replaying this specific section would greatly help my detailed review and analysis.",
"source": "https://superuser.com/questions/306154/how-to-use-a-b-repeat-feature-of-vlc",
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"vlc"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
}
}
}

12
evaluation_examples/examples/vlc/d70666e4-7348-42c7-a06a-664094c5df3c.json
View File

@@ -1,12 +0,0 @@
{
"id": "d70666e4-7348-42c7-a06a-664094c5df3c",
"snapshot": "base_setup",
"instruction": "Add logo watermark to the top right corner (20px, 1800px) of the video, the logo file is in SAVE_PATH",
"source": "https://www.youtube.com/watch?v=XHprwDJ0-fU&t=436s",
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"vlc"
],
"evaluator": "evaluation_dir"
}

62
evaluation_examples/examples/vs_code/30167b0c-976b-491b-a9e5-7747607c6a3c.json
View File

@@ -1,62 +0,0 @@
{
"id": "30167b0c-976b-491b-a9e5-7747607c6a3c",
"snapshot": "vscode",
"instruction": "Please help me find the file that contains \"import openai\" in the current VS Code project and open that file.",
"source": "https://download.microsoft.com/download/8/A/4/8A48E46A-C355-4E5C-8417-E6ACD8A207D4/VisualStudioCode-TipsAndTricks-Vol.1.pdf",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://codeload.github.com/onlyphantom/llm-python/zip/refs/heads/main",
"path": "/home/user/Downloads/llm-python-main.zip"
}
]
}
},
{
"type": "execute",
"parameters": {
"command": [
"/bin/bash",
"-c",
"cd /home/user/Downloads && unzip -q llm-python-main.zip"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"code",
"/home/user/Downloads/llm-python-main/"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Visual Studio Code"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"vscode"
],
"evaluator": {
"func": "check_json_settings",
"expected": {
"type": "rule",
"rules": {
"expected": {}
}
},
"result": {
"type": "vm_file",
"path": "/home/user/.config/Code/User/settings.json",
"dest": "settings.json"
}
}
}

39
evaluation_examples/examples/vs_code/ae506c68-352c-4094-9caa-ee9d42052317.json
View File

@@ -1,39 +0,0 @@
{
"id": "ae506c68-352c-4094-9caa-ee9d42052317",
"snapshot": "vscode",
"instruction": "Please help me store the full terminal history of my VS Code terminal into \"/home/user/Desktop/history.txt\".",
"source": "",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"code"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Visual Studio Code"
}
}
],
"trajectory": "trajectories/ae506c68-352c-4094-9caa-ee9d42052317",
"related_apps": [
"vscode"
],
"evaluator": {
"func": "compare_text_file",
"expected": {
"type": "cloud_file",
"path": "",
"dest": "gold_history.txt"
},
"result": {
"type": "vm_file",
"path": "/home/user/Desktop/history.txt",
"dest": "history.txt"
}
}
}

0
evaluation_examples/examples/Windows/excel/3aaa4e37-dc91-482e-99af-132a612d40f3.json → evaluation_examples/examples_windows/excel/3aaa4e37-dc91-482e-99af-132a612d40f3.json
View File

0
evaluation_examples/examples/Windows/excel/4188d3a4-077d-46b7-9c86-23e1a036f6c1.json → evaluation_examples/examples_windows/excel/4188d3a4-077d-46b7-9c86-23e1a036f6c1.json
View File

0
evaluation_examples/examples/Windows/excel/51b11269-2ca8-4b2a-9163-f21758420e78.json → evaluation_examples/examples_windows/excel/51b11269-2ca8-4b2a-9163-f21758420e78.json
View File

0
evaluation_examples/examples/Windows/excel/6054afcb-5bab-4702-90a0-b259b5d3217c.json → evaluation_examples/examples_windows/excel/6054afcb-5bab-4702-90a0-b259b5d3217c.json
View File

0
evaluation_examples/examples/Windows/excel/7a4e4bc8-922c-4c84-865c-25ba34136be1.json → evaluation_examples/examples_windows/excel/7a4e4bc8-922c-4c84-865c-25ba34136be1.json
View File

0
evaluation_examples/examples/Windows/excel/7efeb4b1-3d19-4762-b163-63328d66303b.json → evaluation_examples/examples_windows/excel/7efeb4b1-3d19-4762-b163-63328d66303b.json
View File

0
evaluation_examples/examples/Windows/excel/8b1ce5f2-59d2-4dcc-b0b0-666a714b9a14.json → evaluation_examples/examples_windows/excel/8b1ce5f2-59d2-4dcc-b0b0-666a714b9a14.json
View File

0
evaluation_examples/examples/Windows/excel/a9f325aa-8c05-4e4f-8341-9e4358565f4f.json → evaluation_examples/examples_windows/excel/a9f325aa-8c05-4e4f-8341-9e4358565f4f.json
View File

0
evaluation_examples/examples/Windows/excel/abed40dc-063f-4598-8ba5-9fe749c0615d.json → evaluation_examples/examples_windows/excel/abed40dc-063f-4598-8ba5-9fe749c0615d.json
View File

0
evaluation_examples/examples/Windows/excel/eb03d19a-b88d-4de4-8a64-ca0ac66f426b.json → evaluation_examples/examples_windows/excel/eb03d19a-b88d-4de4-8a64-ca0ac66f426b.json
View File

0
evaluation_examples/examples/Windows/excel/ecb0df7a-4e8d-4a03-b162-053391d3afaf.json → evaluation_examples/examples_windows/excel/ecb0df7a-4e8d-4a03-b162-053391d3afaf.json
View File

0
evaluation_examples/examples/Windows/multi_app/09a37c51-e625-49f4-a514-20a773797a8a.json → evaluation_examples/examples_windows/multi_app/09a37c51-e625-49f4-a514-20a773797a8a.json
View File

Some files were not shown because too many files have changed in this diff Show More