feat: Migrate OSWorld files to HuggingFace cache with comprehensive documentation
- Add detailed README for file cache repository - Implement migration script with retry logic and browser simulation - Support automatic file type detection and deduplication - Ensure reliable hosting for OSWorld evaluation files
This commit is contained in:
Timothyxxx
@@ -1,112 +1,118 @@
|
||||
{
|
||||
"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
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
"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://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/b5062e3e-641c-4e3a-907b-ac864d2e7652/authors-gt.xlsx",
|
||||
"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
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user