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
2025-05-28 04:29:37 +08:00
parent a845824f06
commit 34748567a5
317 changed files with 12630 additions and 12008 deletions

View File

@@ -7,7 +7,13 @@
{
"type": "execute",
"parameters": {
"command": ["mkdir", "-p", "/home/user/Documents/Finance/receipts", "/home/user/Documents/Projects/OSWorld", "/home/user/.local/share/applications"]
"command": [
"mkdir",
"-p",
"/home/user/Documents/Finance/receipts",
"/home/user/Documents/Projects/OSWorld",
"/home/user/.local/share/applications"
]
}
},
{
@@ -23,7 +29,11 @@
{
"type": "execute",
"parameters": {
"command": ["cp", "/usr/share/applications/google-chrome.desktop", "/home/user/.local/share/applications"]
"command": [
"cp",
"/usr/share/applications/google-chrome.desktop",
"/home/user/.local/share/applications"
]
}
},
{
@@ -41,44 +51,85 @@
{
"type": "execute",
"parameters": {
"command": ["update-desktop-database"]
"command": [
"update-desktop-database"
]
}
},
{
"type": "download",
"parameters": {
"files": [
{"path": "/home/user/Documents/Finance/receipts/aws-invoice-2308.pdf", "url": "https://drive.google.com/uc?id=1pV-QpTEcQ77bXxpnSMed8Aoiw8sFswUx&export=download"},
{"path": "/home/user/Documents/Finance/receipts/aws-invoice-2309.pdf", "url": "https://drive.google.com/uc?id=12W14E90w773CGA63PMvUTwa1JrkOC1sZ&export=download"},
{"path": "/home/user/Documents/Finance/receipts/aws-invoice-2310.pdf", "url": "https://drive.google.com/uc?id=1OgfgrmPRoZlspQX5VJKfEjWljdKL3DMI&export=download"},
{"path": "/home/user/Documents/Finance/receipts/aws-invoice-2311.pdf", "url": "https://drive.google.com/uc?id=1siXXOnpNRMFyEdH5Qq4Wcmhuhi9L5vqV&export=download"},
{"path": "/home/user/Documents/Finance/receipts/aws-invoice-2312.pdf", "url": "https://drive.google.com/uc?id=1mqQMYAazTSr31Xem8X6T7b6xhsOalfjQ&export=download"},
{"path": "/home/user/Documents/Finance/receipts/X-receipt-2312.pdf", "url": "https://drive.google.com/uc?id=140FJGYni2Vvr7C1FplDXeaMZ14BLxcVj&export=download"},
{"path": "/home/user/Documents/Finance/tally_book.xlsx", "url": "https://drive.google.com/uc?id=10rtn4ZsF6K9vqPvZ9MNKeTQLbZhBdJEI&export=download"},
{"path": "/home/user/.projects.tar.xz", "url": "https://drive.google.com/uc?id=1cZH3OcNAPCTL3cSPDuWp-E8VzkS1_ynP&export=download"}
{
"path": "/home/user/Documents/Finance/receipts/aws-invoice-2308.pdf",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/48c46dc7-fe04-4505-ade7-723cba1aa6f6/invoice0123456789-2308.pdf"
},
{
"path": "/home/user/Documents/Finance/receipts/aws-invoice-2309.pdf",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/48c46dc7-fe04-4505-ade7-723cba1aa6f6/invoice0123456789-2309.pdf"
},
{
"path": "/home/user/Documents/Finance/receipts/aws-invoice-2310.pdf",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/48c46dc7-fe04-4505-ade7-723cba1aa6f6/invoice0123456789-2310.pdf"
},
{
"path": "/home/user/Documents/Finance/receipts/aws-invoice-2311.pdf",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/48c46dc7-fe04-4505-ade7-723cba1aa6f6/invoice0123456789-2311.pdf"
},
{
"path": "/home/user/Documents/Finance/receipts/aws-invoice-2312.pdf",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/48c46dc7-fe04-4505-ade7-723cba1aa6f6/invoice0123456789-2312.pdf"
},
{
"path": "/home/user/Documents/Finance/receipts/X-receipt-2312.pdf",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/48c46dc7-fe04-4505-ade7-723cba1aa6f6/Receipt-0123-4567.pdf"
},
{
"path": "/home/user/Documents/Finance/tally_book.xlsx",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/48c46dc7-fe04-4505-ade7-723cba1aa6f6/tally_book.xlsx"
},
{
"path": "/home/user/.projects.tar.xz",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/48c46dc7-fe04-4505-ade7-723cba1aa6f6/projects.tar.xz"
}
]
}
},
{
"type": "execute",
"parameters": {
"command": ["tar", "-xJvf", "/home/user/.projects.tar.xz", "-C", "/home/user/Documents/Projects/OSWorld"]
"command": [
"tar",
"-xJvf",
"/home/user/.projects.tar.xz",
"-C",
"/home/user/Documents/Projects/OSWorld"
]
}
}
],
"trajectory": "trajectories/48c46dc7-fe04-4505-ade7-723cba1aa6f6",
"related_apps": ["chrome", "os"],
"related_apps": [
"chrome",
"os"
],
"evaluator": {
"postconfig": [
{
"type": "execute",
"parameters": {
"command": ["wmctrl", "-lx"],
"command": [
"wmctrl",
"-lx"
],
"stdout": "wmctrl.out"
}
}
],
"func": ["check_list", "is_expected_tabs"],
"func": [
"check_list",
"is_expected_tabs"
],
"result": [
{
"type": "cache_file",
@@ -102,9 +153,12 @@
"type": "rule",
"rules": {
"type": "url",
"urls": ["https://github.com", "https://docs.python.org/3/"]
"urls": [
"https://github.com",
"https://docs.python.org/3/"
]
}
}
]
}
}
}