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

Merge branch 'zdy'

Browse Source
This commit is contained in:
David Chang
2024-03-20 14:26:26 +08:00
parent b3f1238d43 6149061621
commit 99fa5ccc2b
9 changed files with 754 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
desktop_env/server/main.py
View File

@@ -545,12 +545,14 @@ def _create_pywinauto_node(node: BaseWrapper, depth: int = 0, flag: Optional[str
node_role_name = "".join( map( lambda ch: ch if ch.isidentifier()\
or ch in {"-"}\
or ch.isalnum()
else "-"
else "-"
, node_role_name
)
)
if node_role_name.strip() == "":
node_role_name = "unknown"
if not node_role_name[0].isalpha():
node_role_name = "tag" + node_role_name
xml_node = lxml.etree.Element(
node_role_name,

132
evaluation_examples/examples/Windows/multi_app/46407397-a7d5-4c6b-92c6-dbe038b1457b.json Normal file
View File

@@ -0,0 +1,132 @@
{
"id": "46407397-a7d5-4c6b-92c6-dbe038b1457b",
"snapshot": "chrome",
"instruction": "Help me export charts, graph or other images from docx files received in email \"Lecture Document\" in Notes folder and upload these png files to the figures/ folder in Google Drive for later use (use numbers to name them).",
"source": "https://marketplace.uipath.com/listings/merge-pdfs-from-gmail-email-attachments-and-upload-to-gogle-drive",
"config": [
{
"type": "googledrive",
"parameters": {
"settings_file": "evaluation_examples/settings/googledrive/settings.yml",
"operation": ["delete"],
"args": [
{
"query": "title = 'figures' and 'root' in parents and mimeType = 'application/vnd.google-apps.folder'",
"trash": false
}
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"C:\Program Files\Google\Chrome\Application\chrome.exe",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": "nc -l -p 9222 |nc 127.0.0.1 1337",
"shell": true
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://news.google.com",
"https://x.com"
]
}
},
{
"type": "login",
"parameters": {
"settings_file": "evaluation_examples/settings/google/settings.json",
"platform": "googledrive"
}
},
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=18jdi0OanMtAQenm4ODTivsxTSzdj4HUV&export=download&authuser=0&confirm=t&uuid=e858d3cc-4535-4419-a651-8856ac517d19&at=APZUnTW7g4ygfrkKTPBWCO13twRj:1706611460571",
"path": "/home/user/thunderbird-profile.tar.gz"
}
]
}
},
{
"type": "execute",
"parameters": {
"command": [
"tar",
"-xz",
"--recursive-unlink",
"-f",
"/home/user/thunderbird-profile.tar.gz",
"-C",
"/home/user/"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"/usr/bin/thunderbird"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"thunderbird",
"chrome"
],
"evaluator": {
"func": "compare_image_list",
"result": {
"type": "googledrive_file",
"settings_file": "evaluation_examples/settings/googledrive/settings.yml",
"query_list": [
[
"title = 'figures' and trashed = false and 'root' in parents and mimeType = 'application/vnd.google-apps.folder'",
"title = '1.png' and trashed = false"
],
[
"title = 'figures' and trashed = false and 'root' in parents and mimeType = 'application/vnd.google-apps.folder'",
"title = '2.png' and trashed = false"
],
[
"title = 'figures' and trashed = false and 'root' in parents and mimeType = 'application/vnd.google-apps.folder'",
"title = '3.png' and trashed = false"
]
],
"dest": [
"1.png",
"2.png",
"3.png"
]
},
"expected": {
"type": "cloud_file",
"path": [
"https://drive.usercontent.google.com/download?id=19J5tzWjx9hdo-n0MC3upzAntVMa8WUgk&export=download&authuser=0&confirm=t&uuid=be790579-8db9-4bd2-a757-beb27af386af&at=APZUnTVM2PjNDXhlwFZ6WAFdNVsD:1706497547717",
"https://drive.usercontent.google.com/download?id=1S04RpR5dk80LylIYGvA4e3sAUBd6wdlQ&export=download&authuser=0&confirm=t&uuid=b302de03-04f7-455c-ab0c-b3cbbeb6929a&at=APZUnTVD8zMZGO1_GWaFUm1cNXul:1706497555463",
"https://drive.usercontent.google.com/download?id=11NRLh93RTzEd0Cy-cYwMyNJSFG7-vP9c&export=download&authuser=0&confirm=t&uuid=02500115-dea3-481a-af4f-a723d9a62169&at=APZUnTW9-gENlsyfdIPA4PTA0emh:1706497560874"
],
"dest": [
"1_gold.png",
"2_gold.png",
"3_gold.png"
],
"multi": true,
"gives": [0, 1, 2]
}
}
}

18
evaluation_examples/examples/Windows/multi_app/6d72aad6-187a-4392-a4c4-ed87269c51cf.json Normal file
View File

@@ -0,0 +1,18 @@
{
"id": "6d72aad6-187a-4392-a4c4-ed87269c51cf",
"snapshot": "libreoffice_calc",
"instruction": "Could you please converting MS Office PowerPoint presentation to video and play it with VLC?",
"source": "https://superuser.com/questions/923171/converting-openoffice-impress-presentation-to-video-without-screen-recording",
"config": [
],
"trajectory": "trajectories/6d72aad6-187a-4392-a4c4-ed87269c51cf",
"related_apps": [
"excel",
"powerpoint",
"word",
"vlc"
],
"evaluator": {
"func": "infeasible"
}
}

174
evaluation_examples/examples/Windows/multi_app/74d5859f-ed66-4d3e-aa0e-93d7a592ce41.json Normal file
View File

@@ -0,0 +1,174 @@
{
"id": "74d5859f-ed66-4d3e-aa0e-93d7a592ce41",
"snapshot": "chrome",
"instruction": "Help me to set up an initial web extension project with help of the web tool, tagging it \"happy-extension v0.0.1\". Leave description blank for now. Include a background script and browser action, while other features are not required. Remember to unzip the auto-generated folder into \"~/Projects\".",
"source": "authors",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://webext.eu"
]
}
},
{
"type": "execute",
"parameters": {
"command": [
"mkdir",
"-p",
"/home/user/Projects"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"nautilus",
"/home/user/Projects"
]
}
}
],
"trajectory": "trajectories/74d5859f-ed66-4d3e-aa0e-93d7a592ce41",
"related_apps": [
"chrome",
"os"
],
"evaluator": {
"func": [
"check_json",
"diff_text_file",
"diff_text_file",
"diff_text_file",
"diff_text_file"
],
"result": [
{
"type": "vm_file",
"path": "/home/user/Projects/happy-extension/manifest.json",
"dest": "manifest.json"
},
{
"type": "vm_file",
"path": "/home/user/Projects/happy-extension/background_script.js",
"dest": "background_script.js"
},
{
"type": "vm_file",
"path": "/home/user/Projects/happy-extension/browserAction/index.html",
"dest": "index.html"
},
{
"type": "vm_file",
"path": "/home/user/Projects/happy-extension/browserAction/style.css",
"dest": "style.css"
},
{
"type": "vm_file",
"path": "/home/user/Projects/happy-extension/browserAction/script.js",
"dest": "script.js"
}
],
"expected": [
{
"type": "rule",
"rules": {
"expect": [
{
"key": [
"name"
],
"method": "eq",
"ref": "happy-extension"
},
{
"key": [
"version"
],
"method": "eq",
"ref": "0.0.1"
},
{
"key": [
"background",
"scripts"
],
"method": "eq",
"ref": [
"background_script.js"
]
},
{
"key": [
"browser_action",
"default_icon"
],
"method": "eq",
"ref": {
"64": "icons/icon.png"
}
},
{
"key": [
"browser_action",
"default_popup"
],
"method": "eq",
"ref": "browserAction/index.html"
},
{
"key": [
"browser_action",
"default_title"
],
"method": "eq",
"ref": "happy-extension"
}
]
}
},
{
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1t5Llhn6seDUXVs-eILu6CjwFEQL9Z5Qm&export=download",
"dest": "background_script.js"
},
{
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=19fMAsWd6q4ElLdOceJ-otHbxRJA_pc_U&export=download",
"dest": "index.html"
},
{
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1fwfiRPjdug8uh6z23RFO1JtlGH_L_Hl_&export=download",
"dest": "style.css"
},
{
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=14YYnhCfRtHQNk8M4fBPaUQeteoFMGBsA&export=download",
"dest": "script.js"
}
]
}
}

97
evaluation_examples/examples/Windows/multi_app/897e3b53-5d4d-444b-85cb-2cdc8a97d903.json Normal file
View File

@@ -0,0 +1,97 @@
{
"id": "897e3b53-5d4d-444b-85cb-2cdc8a97d903",
"snapshot": "chrome",
"instruction": "I have a LibreOffice Writer file form.docx on the desktop. Help me convert it to PDF format and store the PDF in the forms/ folder in my Google Drive.",
"source": "https://marketplace.uipath.com/listings/convert-word-file-to-pdf-and-store-in-onedrive",
"config": [
{
"type": "googledrive",
"parameters": {
"settings_file": "evaluation_examples/settings/googledrive/settings.yml",
"operation": ["delete"],
"args": [
{
"query": "title = 'form.pdf' or title = 'form.docx' or title = 'form.docx.pdf' or title = 'forms'",
"trash": false
}
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://www.zhihu.com/",
"https://www.coursera.org/",
"https://www.deepl.com",
"https://www.wikidata.org/wiki/Wikidata:Main_Page"
]
}
},
{
"type": "login",
"parameters": {
"settings_file": "evaluation_examples/settings/google/settings.json",
"platform": "googledrive"
}
},
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=18TvzE8jnULU2g9XJsT-TaPEKcLGNVfu0&export=download&authuser=0&confirm=t&uuid=d914e031-9aa6-431b-81c0-73fcb87af027&at=APZUnTUx56WM_I3gnhHo-eZX__kx:1706158167271",
"path": "/home/user/Desktop/form.docx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/Desktop/form.docx"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"libreoffice_writer",
"chrome"
],
"evaluator": {
"func": "compare_pdfs",
"result": {
"type": "googledrive_file",
"settings_file": "evaluation_examples/settings/googledrive/settings.yml",
"query": [
"title = 'forms' and mimeType = 'application/vnd.google-apps.folder' and trashed = false",
"( title = 'form.pdf' or title = 'form.docx.pdf' ) and trashed = false"
],
"dest": "form.pdf"
},
"expected": {
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=118wb7zmG8yP7DS1cImP9-GcOeKib3fLp&export=download&authuser=0&confirm=t&uuid=b82542fa-7731-4014-8ebc-d940f0fb83fe&at=APZUnTVkmL9rk3EpA0Ak5JLPEnJZ:1706101389421",
"dest": "form_gold.pdf"
}
}
}

112
evaluation_examples/examples/Windows/multi_app/b5062e3e-641c-4e3a-907b-ac864d2e7652.json Normal file
View File

@@ -0,0 +1,112 @@
{
"id": "b5062e3e-641c-4e3a-907b-ac864d2e7652",
"snapshot": "libreoffice_calc",
"instruction": "Please help me to extract the name, e-mail, and affiliation of the first author from each paper in the folder and organize them in an Excel table. Include headers for each field. Sort the authors by their full names alphabetically and save the table as \"~/authors.xlsx\".",
"source": "authors",
"config": [
{
"type": "command",
"parameters": {
"command": [
"mkdir",
"-p",
"/home/user/Documents/Papers"
]
}
},
{
"type": "download",
"parameters": {
"files": [
{
"path": "/home/user/Documents/Papers/zhang_appagent.pdf",
"url": "https://arxiv.org/pdf/2312.13771.pdf"
},
{
"path": "/home/user/Documents/Papers/niu_screenagent.pdf",
"url": "https://arxiv.org/pdf/2402.07945.pdf"
},
{
"path": "/home/user/Documents/Papers/koh_visualwebarena.pdf",
"url": "https://arxiv.org/pdf/2401.13649.pdf"
},
{
"path": "/home/user/Documents/Papers/deng_mind2web.pdf",
"url": "https://papers.nips.cc/paper_files/paper/2023/file/5950bf290a1570ea401bf98882128160-Paper-Datasets_and_Benchmarks.pdf"
}
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"nautilus",
"/home/user/Documents/Papers"
]
}
}
],
"trajectory": "trajectories/b5062e3e-641c-4e3a-907b-ac864d2e7652",
"related_apps": [
"libreoffice_calc",
"os"
],
"evaluator": {
"postconfig": [
{
"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",
"/home/user/authors.xlsx"
]
}
}
],
"func": "compare_table",
"result": {
"type": "vm_file",
"path": "/home/user/authors.xlsx",
"dest": "authors.xlsx"
},
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1fttbvfHuoQfsQUk3fVXkJsCu231jhnQj&export=download",
"dest": "authors-gt.xlsx"
},
"options": {
"rules": [
{
"type": "sheet_fuzzy",
"sheet_idx0": "RNSheet1",
"sheet_idx1": "ENSheet1",
"rules": [
{
"range": ["A1:C1"],
"type": "includes",
"ignore_case": true
},
{
"range": ["A2:B5"],
"type": "exact_match",
"trim_leadings": " ",
"trim_trailings": " "
},
{
"range": ["C2:C5"],
"type": "exact_match",
"trim_leadings": " ",
"trim_trailings": " ",
"ignore_case": true
}
]
}
]
}
}
}

98
evaluation_examples/examples/Windows/multi_app/c867c42d-a52d-4a24-8ae3-f75d256b5618.json Normal file
View File

@@ -0,0 +1,98 @@
{
"id": "c867c42d-a52d-4a24-8ae3-f75d256b5618",
"snapshot": "thunderbird",
"instruction": "Please assist me in exporting my contacts of Personal Address Book from Thunderbird into contacts.csv file in the desktop and convert it to .xlsx with Libreoffice Calc.",
"source": "https://www.sync.blue/en/sync/mozilla-thunderbird/google-sheets/",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"libreoffice",
"--calc"
]
}
},
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1wKXmJ14dnxSzdy9ZF_ePWU7zpevY6Dry&export=download&authuser=0&confirm=t&uuid=9b476c95-8eee-4a9a-8cee-c3620d5ce250&at=APZUnTUzDeeeMNr34DB1vEnBK6N7:1706719624132",
"path": "/home/user/thunderbird-profile.tar.gz"
}
]
}
},
{
"type": "execute",
"parameters": {
"command": [
"tar",
"--recursive-unlink",
"-xz",
"-f",
"/home/user/thunderbird-profile.tar.gz",
"-C",
"/home/user/"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"/usr/bin/thunderbird"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"thunderbird",
"libreoffice_calc"
],
"evaluator": {
"func": [
"compare_csv",
"compare_table"
],
"conj": "and",
"result": [
{
"type": "vm_file",
"path": "/home/user/Desktop/contacts.csv",
"dest": "contacts.csv"
},
{
"type": "vm_file",
"path": "/home/user/Desktop/contacts.xlsx",
"dest": "contacts.xlsx"
}
],
"expected": [
{
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=1StwASpAR2ALq2Y1vugGsdUJptg6FwjEm&export=download&authuser=0&confirm=t&uuid=56339e19-b889-4da1-ab72-5e0b90f13fff&at=APZUnTVWFF2pBrtWU_hXgzfbrWP2:1706719668676",
"dest": "contacts_gold.csv"
},
{
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=1s25eUpvkMzSm6p_WA7O13t6mVqmkxr2C&export=download&authuser=0&confirm=t&uuid=901cbd32-6026-4391-a5cc-989e1047cf7c&at=APZUnTUs27mZceDshB_f9Tx4PFyz:1706719610831",
"dest": "contacts_gold.xlsx"
}
],
"options": [
{},
{
"rules": [
{
"type": "sheet_data",
"sheet_idx0": "RI0",
"sheet_idx1": "EI0"
}
]
}
]
}
}

73
evaluation_examples/examples/Windows/multi_app/da52d699-e8d2-4dc5-9191-a2199e0b6a9b.json Normal file
View File

@@ -0,0 +1,73 @@
{
"id": "da52d699-e8d2-4dc5-9191-a2199e0b6a9b",
"snapshot": "libreoffice_calc",
"instruction": "Examine the spreadsheet on the desktop, which contains a record of books read in 2022. Take the website https://howlongtoread.com/ as a reference to identify the book with the slowest reading pace, measured in words per day. I have an empty document named 'book_list_result.docx' on the desktop; please open it and record the title there.",
"source": "GAIA",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1JGZNCShtmpu7A8Z8lkjc8hdFEAMXZVvh&export=download&authuser=0&confirm=t&uuid=67063da6-2a72-4ed2-92b2-ade508439ce4&at=APZUnTUgS17YjX-D0oSvALwnPosB:1709368886960",
"path": "/home/user/Desktop/2023_validation_Book_Reading_Rate.xlsx"
},
{
"url": "https://drive.usercontent.google.com/download?id=1iySmK8zvTzgmERH7KQuESP05NBsMunhV&export=download&authuser=0&confirm=t&uuid=130f6cee-0f9a-4f2e-a84d-89a3b302f350&at=APZUnTXugQOTOApe1_zxUbafo2Sp:1709369519349",
"path": "/home/user/Desktop/book_list_result.docx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/Desktop/2023_validation_Book_Reading_Rate.xlsx"
}
}
],
"trajectory": "trajectories/da52d699-e8d2-4dc5-9191-a2199e0b6a9b",
"related_apps": [
"libreoffice_calc",
"chrome",
"libreoffice_writer"
],
"evaluator": {
"func": "compare_docx_files",
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "book_list_result.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); "
]
}
}
],
"expected": {
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=1rpvOlHZO0AqC85od8pJtx8YcDPljcejN&export=download&authuser=0&confirm=t&uuid=24a3a5e3-a188-4a41-ad01-a4709dc1c0b6&at=APZUnTWx56rr8-iTuXkfV5poOK-I:1709369145446",
"dest": "book_list_result_Gold.docx"
},
"result": {
"type": "vm_file",
"path": "/home/user/Desktop/book_list_result.docx",
"dest": "book_list_result.docx"
}
}
}

47
evaluation_examples/examples/Windows/multi_app/f918266a-b3e0-4914-865d-4faa564f1aef.json Normal file
View File

@@ -0,0 +1,47 @@
{
"id": "f918266a-b3e0-4914-865d-4faa564f1aef",
"snapshot": "vscode",
"instruction": "Please complete the code and retrieve the output from the Python script 'calculator.py' located on the desktop and save it as 'log.txt' in the same directory as the Python file.",
"source": "GAIA",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1l09TnSiXo-qOK2UazcIdrT_M6JwTfzq7&export=download&authuser=0&confirm=t&uuid=80bd550f-f3a6-4b69-ae0f-221c12b11fd9&at=APZUnTWgUlKuIDJZmkr0Q9Bze3w_:1709784652645",
"path": "/home/user/Desktop/calculator.zip"
}
]
}
},
{
"type": "execute",
"parameters": {
"command": [
"/bin/bash",
"-c",
"unzip /home/user/Desktop/calculator.zip -d /home/user/Desktop/ && rm -rf /home/user/Desktop/calculator.zip"
]
}
}
],
"trajectory": "trajectories/f918266a-b3e0-4914-865d-4faa564f1aef",
"related_apps": [
"vscode",
"os"
],
"evaluator": {
"func": "compare_text_file",
"expected": {
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=1-14AgA1nHNL22VD_3QtRzWaMjIBa3RvJ&export=download&authuser=0&confirm=t&uuid=6aa05bf1-4964-4f7b-8983-d28540b4053b&at=APZUnTXuJgDHIYA2FZl3A_OQJEOF:1709881263131",
"dest": "log_Gold.txt"
},
"result": {
"type": "vm_file",
"path": "/home/user/Desktop/log.txt",
"dest": "log.txt"
}
}
}