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

@@ -7,62 +7,103 @@
{
"type": "execute",
"parameters": {
"command": ["mkdir", "-p", "/home/user/Documents/Finance/receipts", "/home/user/Documents/Projects"]
"command": [
"mkdir",
"-p",
"/home/user/Documents/Finance/receipts",
"/home/user/Documents/Projects"
]
}
},
{
"type": "download",
"parameters": {
"files": [
{"path": "/home/user/Documents/Finance/receipts/aws-invoice-2308.pdf", "url": "https://drive.google.com/uc?id=1azRFXf4A7fvW0S7r9upHvleMEi-92hHM&export=download"},
{"path": "/home/user/Documents/Finance/receipts/aws-invoice-2309.pdf", "url": "https://drive.google.com/uc?id=1x-lpHm8U4U7uRPZ74-9wq9KzW2R55ln1&export=download"},
{"path": "/home/user/Documents/Finance/receipts/aws-invoice-2310.pdf", "url": "https://drive.google.com/uc?id=1pcrgV9G6NO4ekMEQBiupwXtq6mmke7b_&export=download"},
{"path": "/home/user/Documents/Finance/receipts/aws-invoice-2311.pdf", "url": "https://drive.google.com/uc?id=1JzbCK_nIY8X_3QZjnkzTtb-cRoq9zNT-&export=download"},
{"path": "/home/user/Documents/Finance/receipts/X-receipt-2312.pdf", "url": "https://drive.google.com/uc?id=1QzWjNzvNosG_yQr7VVonvYb3cUYF5f3u&export=download"},
{"path": "/home/user/Documents/Finance/tally_book.xlsx", "url": "https://drive.google.com/uc?id=13yuLhBPmouoWR-DybfgaIbWUOxbY_jhL&export=download"},
{"path": "/home/user/.projects.tar.xz", "url": "https://drive.google.com/uc?id=1oJcxpjqF474Wm16i1aZc8DlCEfAvc4t_&export=download"},
{
"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"
}
{
"path": "/home/user/Documents/Finance/receipts/aws-invoice-2308.pdf",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/415ef462-bed3-493a-ac36-ca8c6d23bf1b/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/415ef462-bed3-493a-ac36-ca8c6d23bf1b/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/415ef462-bed3-493a-ac36-ca8c6d23bf1b/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/415ef462-bed3-493a-ac36-ca8c6d23bf1b/invoice0123456789-2311.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/415ef462-bed3-493a-ac36-ca8c6d23bf1b/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/415ef462-bed3-493a-ac36-ca8c6d23bf1b/tally_book.xlsx"
},
{
"path": "/home/user/.projects.tar.xz",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/415ef462-bed3-493a-ac36-ca8c6d23bf1b/projects.tar.xz"
},
{
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/415ef462-bed3-493a-ac36-ca8c6d23bf1b/thunderbird-profile.tar.gz",
"path": "/home/user/thunderbird-profile.tar.gz"
}
]
}
},
{
"type": "execute",
"parameters": {
"command": ["tar", "-xJvf", "/home/user/.projects.tar.xz", "-C", "/home/user/Documents/Projects"]
"command": [
"tar",
"-xJvf",
"/home/user/.projects.tar.xz",
"-C",
"/home/user/Documents/Projects"
]
}
},
{
"type": "execute",
"parameters": {
"command": [
"tar",
"-xzv",
"--recursive-unlink",
"-f",
"/home/user/thunderbird-profile.tar.gz",
"-C",
"/home/user/"
]
}
},
{
"type": "launch",
"type": "execute",
"parameters": {
"command": ["thunderbird"]
"command": [
"tar",
"-xzv",
"--recursive-unlink",
"-f",
"/home/user/thunderbird-profile.tar.gz",
"-C",
"/home/user/"
]
}
},
{
"type": "launch",
"parameters": {
"command": ["nautilus", "/home/user/Documents/Finance"]
"command": [
"thunderbird"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"nautilus",
"/home/user/Documents/Finance"
]
}
}
],
"trajectory": "trajectories/415ef462-bed3-493a-ac36-ca8c6d23bf1b",
"related_apps": ["thunderbird", "libreoffice_calc", "os"],
"related_apps": [
"thunderbird",
"libreoffice_calc",
"os"
],
"evaluator": {
"postconfig": [
{
@@ -98,19 +139,29 @@
"type": "download",
"parameters": {
"files": [
{"path": "/home/user/.aws-invoice-2312.pdf", "url": "https://drive.google.com/uc?id=1RqbulzKG_HeYb1GZmLABOzlohlFg02UU&export=download"}
{
"path": "/home/user/.aws-invoice-2312.pdf",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/415ef462-bed3-493a-ac36-ca8c6d23bf1b/invoice0123456789-2312.pdf"
}
]
}
},
{
"type": "execute",
"parameters": {
"command": ["diff", ".aws-invoice-2312.pdf", "/home/user/Documents/Finance/receipts/aws-invoice-2312.pdf"],
"command": [
"diff",
".aws-invoice-2312.pdf",
"/home/user/Documents/Finance/receipts/aws-invoice-2312.pdf"
],
"stdout": "diff.out"
}
}
],
"func": ["compare_table", "check_list"],
"func": [
"compare_table",
"check_list"
],
"result": [
{
"type": "vm_file",
@@ -125,7 +176,7 @@
"expected": [
{
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1x8m-korGI1PhJm8PAQVTlWYKneK4WKvn&export=download",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/415ef462-bed3-493a-ac36-ca8c6d23bf1b/tally_book_gt.xlsx",
"dest": "tally_book_gt.xlsx"
},
{
@@ -150,4 +201,4 @@
{}
]
}
}
}