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

@@ -1,73 +1,73 @@
{
"id": "f8cfa149-d1c1-4215-8dac-4a0932bad3c2",
"snapshot": "chrome",
"instruction": "Could you help me copy the data in Cell B6 in this Libreoffice Calc file and search it in the Chrome browser.",
"source": "https://superuser.com/questions/1803088/libreoffice-calc-clears-clipboard",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1MHk40tzMiyOwNbRj1W-_A-nIisk1TbuM&export=download&authuser=0&confirm=t&uuid=a8674a99-fb5f-4aeb-98ca-338197d73890&at=APZUnTW2thoQGMqgEyD0lNcRISJ_:1706006672423",
"path": "/home/user/cell_search.xlsx"
}
]
}
},
"id": "f8cfa149-d1c1-4215-8dac-4a0932bad3c2",
"snapshot": "chrome",
"instruction": "Could you help me copy the data in Cell B6 in this Libreoffice Calc file and search it in the Chrome browser.",
"source": "https://superuser.com/questions/1803088/libreoffice-calc-clears-clipboard",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"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://en.wikipedia.org/wiki/Main_Page",
"https://pytorch.org/tutorials/",
"https://releases.ubuntu.com/"
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/cell_search.xlsx"
}
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/f8cfa149-d1c1-4215-8dac-4a0932bad3c2/file.xls",
"path": "/home/user/cell_search.xlsx"
}
],
"trajectory": "trajectories/",
"related_apps": [
"libreoffice_calc",
"chrome"
],
"evaluator": {
"func": "is_expected_search_query",
"result": {
"type": "active_tab_info"
},
"expected": {
"type": "rule",
"rules": {
"expect": {
"pattern": "www\\.google\\.com.*?/search\\?q=Nereida&"
}
]
}
},
{
"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://en.wikipedia.org/wiki/Main_Page",
"https://pytorch.org/tutorials/",
"https://releases.ubuntu.com/"
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/cell_search.xlsx"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"libreoffice_calc",
"chrome"
],
"evaluator": {
"func": "is_expected_search_query",
"result": {
"type": "active_tab_info"
},
"expected": {
"type": "rule",
"rules": {
"expect": {
"pattern": "www\\.google\\.com.*?/search\\?q=Nereida&"
}
}
}
}
}