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

Merge branch 'main' of https://github.com/xlang-ai/DesktopEnv

Browse Source
This commit is contained in:
tsuky_chen
2024-03-04 21:44:17 +08:00
parent e42f5e2a8f e6d4ed7fd6
commit 0ad9c5b3a4
6 changed files with 254 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
evaluation_examples/examples/multi_apps/26660ad1-6ebb-4f59-8cba-a8432dfe8d38.json Normal file
View File

@@ -0,0 +1,25 @@
{
"id": "26660ad1-6ebb-4f59-8cba-a8432dfe8d38",
"snapshot": "libreoffice_calc",
"instruction": "I want to test the quality of the network environment my laptop is currently in. Please measure my network situation through speedtest.net, export the measurement results, and save them to ~/Test/Speed.",
"source": "authors",
"config": [
],
"trajectory": "trajectories/26660ad1-6ebb-4f59-8cba-a8432dfe8d38",
"related_apps": [
],
"evaluator": {
"postconfig": [],
"func": "",
"result": {
},
"expected": {
},
"options": {
}
}
}

64
evaluation_examples/examples/multi_apps/36037439-2044-4b50-b9d1-875b5a332143.json Normal file
View File

@@ -0,0 +1,64 @@
{
"id": "36037439-2044-4b50-b9d1-875b5a332143",
"snapshot": "libreoffice_calc",
"instruction": "Could you please pull up the Google Scholar page of the corresponding author for me in Chrome?",
"source": "authors",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1iTjv59rn8vcvUsh2-M7T5BLyNoutCwYo&export=download&authuser=0&confirm=t&uuid=cc13ea06-8d21-4d15-adb4-8fec94304bde&at=APZUnTX9ydwrAV0UPVKzYS9-LBlH:1709520068240",
"path": "/home/user/Desktop/shi17a.pdf"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/Desktop/shi17a.pdf"
}
},
{
"type": "sleep",
"parameters": {
"seconds": 2
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; import time; pyautogui.hotkey('f11'); time.sleep(0.5); pyautogui.click(960, 540); time.sleep(0.5); pyautogui.scroll(-40)"
]
}
}
],
"trajectory": "trajectories/36037439-2044-4b50-b9d1-875b5a332143",
"related_apps": [
"OS",
"Chrome"
],
"evaluator": {
"func": "is_expected_url_pattern_match",
"result": {
"type": "active_url_from_accessTree",
"goto_prefix": "https://"
},
"expected": {
"type": "rule",
"rules": {
"type": "url",
"url": "?hl=en&",
"expected": [
"https://scholar.google.com/citations",
"user=qRAQ5BsAAAAJ"
]
}
}
}
}

54
evaluation_examples/examples/multi_apps/a82b78bb-7fde-4cb3-94a4-035baf10bcf0.json Normal file
View File

@@ -0,0 +1,54 @@
{
"id": "a82b78bb-7fde-4cb3-94a4-035baf10bcf0",
"snapshot": "libreoffice_calc",
"instruction": "I'm really enjoying this paper. Could you please find the personal webpages of the first author and the last three authors, and add them to a browser bookmark folder named 'Liked Authors'?",
"source": "authors",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1IlJ8kU5MlR6OqJHchsSUJzLCmcrG-8N7&export=download&authuser=0&confirm=t&uuid=d2a1810f-edea-4bfd-9d79-e668b9f11876&at=APZUnTVv_eqtC86YzkEU8_jIhC9W:1709522229162",
"path": "/home/user/Desktop/2206.08853.pdf"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/Desktop/2206.08853.pdf"
}
},
{
"type": "sleep",
"parameters": {
"seconds": 2
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; import time; pyautogui.hotkey('f11'); time.sleep(0.5); pyautogui.click(960, 540); time.sleep(0.5); pyautogui.scroll(-20)"
]
}
}
],
"trajectory": "trajectories/a82b78bb-7fde-4cb3-94a4-035baf10bcf0",
"related_apps": [
],
"evaluator": {
"postconfig": [],
"func": "",
"result": {
},
"expected": {
},
"options": {
}
}
}

76
evaluation_examples/examples/multi_apps/d1acdb87-bb67-4f30-84aa-990e56a09c92.json
View File

@@ -53,51 +53,75 @@
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "MUST_VISIT.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"libreoffice",
"--convert-to",
"csv:Text - txt - csv (StarCalc):44,34,UTF-8,,,,false,true,true,false,false,1",
"--outdir",
"/home/user/Desktop",
"/home/user/Desktop/MUST_VISIT.xlsx"
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 1.0
}
}
],
"func": "compare_table",
"result": {
"type": "vm_file",
"path": [
"/home/user/Desktop/MUST_VISIT.xlsx",
"/home/user/Desktop/MUST_VISIT-Sheet1.csv"
],
"dest": [
"MUST_VISIT.xlsx",
"MUST_VISIT-Sheet1.csv"
],
"multi": true
"path": "/home/user/Desktop/MUST_VISIT.xlsx",
"dest": "MUST_VISIT.xlsx"
},
"expected": {
"type": "cloud_file",
"path": [
"https://drive.google.com/uc?id=1MV6jBvRbbYwPqeFTd_nX40xzyltNhphl&export=download",
"https://drive.google.com/uc?id=1CGoRQDLw9-Ai7daq3qCz0o9kYSZB2WNn&export=download"
],
"dest": [
"MUST_VISIT-gt.xlsx",
"MUST_VISIT-gt-Sheet1.csv"
],
"multi": true
"path": "https://drive.google.com/uc?id=1MV6jBvRbbYwPqeFTd_nX40xzyltNhphl&export=download",
"dest": "MUST_VISIT-gt.xlsx"
},
"options": {
"rules": [
{
"type": "sheet_print",
"type": "sheet_fuzzy",
"sheet_idx0": "RNSheet1",
"sheet_idx1": "ENSheet1"
"sheet_idx1": "ENSheet1",
"rules": [
{
"range": ["A1:A6", "D1:D6"],
"type": "exact_match"
},
{
"range": ["B1:B6"],
"type": "fuzzy_match",
"threshold": 85,
"normalization": [
["Rd", "Road"],
["St", "Street"]
],
"ignore_case": true
},
{
"range": ["C1:C6"],
"type": "includes",
"trim_leadings": "+ ",
"ignore_chars": " ()-"
}
]
}
]
}