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

feat: Migrate OSWorld files to HuggingFace cache with comprehensive documentation

Browse Source 
- 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
Download Patch File Download Diff File Expand all files Collapse all files

146
evaluation_examples/examples/multi_apps/ce2b64a2-ddc1-4f91-8c7d-a88be7121aac.json
View File

@@ -1,80 +1,88 @@
{
"id": "ce2b64a2-ddc1-4f91-8c7d-a88be7121aac",
"snapshot": "multiapps",
"instruction": "There are several pictures of mountains in my Pictures directory, but I don’t know the names of these mountains. Please help me identify these pictures and change the names of these pictures to the names of the mountains in the pictures.",
"source": "authors",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1sKdxRx4Uxs-wxohYkmxPfxOUpw72BINV&export=download&authuser=0&confirm=t&uuid=2cd18b66-93a6-4771-a92b-a1b1f0adf12d&at=APZUnTUvT9iZ0IdRnnNf1ys4mZaE:1709972639977",
"path": "/home/user/Pictures/picture1.jpg"
}
]
}
},
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1XLBhnopqQrTw3bxRWOyfTCslfawFyOaZ&export=download&authuser=0&confirm=t&uuid=f41a09c1-8319-4a50-b8c3-4fc58ba51c00&at=APZUnTV3uiv7wKiSvoCekJG_aVo3:1710051227101",
"path": "/home/user/Pictures/picture2.jpg"
}
]
}
},
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1ie3rhHzsW293xhnmgeZm6wQj_uaFmPS7&export=download&authuser=0&confirm=t&uuid=633c8b0c-0d3f-4f07-a772-945148956244&at=APZUnTX6OIN5YfudwPVT3Mxntd9E:1709972650733",
"path": "/home/user/Pictures/picture3.jpg"
}
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome", "os", "image"
],
"evaluator": {
"postconfig":[
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1eWGQ3z-Ps5p784NZjj9KyhHfX7NbHgWd&export=download&authuser=0&confirm=t&uuid=8ba167f4-8669-477b-89ee-a8f6996f43d7&at=APZUnTWShYYueBb8hRnrjjabU1ZD:1709972787510",
"path": "/home/user/Desktop/image_script.py"
}
]
"id": "ce2b64a2-ddc1-4f91-8c7d-a88be7121aac",
"snapshot": "multiapps",
"instruction": "There are several pictures of mountains in my Pictures directory, but I don’t know the names of these mountains. Please help me identify these pictures and change the names of these pictures to the names of the mountains in the pictures.",
"source": "authors",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/ce2b64a2-ddc1-4f91-8c7d-a88be7121aac/picture1.jpg",
"path": "/home/user/Pictures/picture1.jpg"
}
]
}
},
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/ce2b64a2-ddc1-4f91-8c7d-a88be7121aac/picture2.jpg",
"path": "/home/user/Pictures/picture2.jpg"
}
]
}
},
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/ce2b64a2-ddc1-4f91-8c7d-a88be7121aac/picture3.jpg",
"path": "/home/user/Pictures/picture3.jpg"
}
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome",
"os",
"image"
],
"evaluator": {
"postconfig": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/ce2b64a2-ddc1-4f91-8c7d-a88be7121aac/image_script.py",
"path": "/home/user/Desktop/image_script.py"
}
]
}
],
"func": "check_direct_json_object",
"result":{
"type": "vm_command_line",
"command":"python /home/user/Desktop/image_script.py",
"shell": "true"
}
],
"func": "check_direct_json_object",
"result": {
"type": "vm_command_line",
"command": "python /home/user/Desktop/image_script.py",
"shell": "true"
},
"expected": {
"type": "rule",
"rules":{
"expected":{
"ec076282f61ba74642e94b5a6a1250c6988204d59d9b02936606b6b8ef1e4433": ["Kilimanjaro"],
"6ed4239ecc2be3ec15ad65a78c5c823b9004d640b8cc83a6a7af5930f354de91": ["Himalayas", "Everest", "Sagarmatha"],
"79f45d40d8413d4e81f1b9734ea39e58622cafd79e12bab32959643fc245147c": ["Hua", "hua"]
"rules": {
"expected": {
"ec076282f61ba74642e94b5a6a1250c6988204d59d9b02936606b6b8ef1e4433": [
"Kilimanjaro"
],
"6ed4239ecc2be3ec15ad65a78c5c823b9004d640b8cc83a6a7af5930f354de91": [
"Himalayas",
"Everest",
"Sagarmatha"
],
"79f45d40d8413d4e81f1b9734ea39e58622cafd79e12bab32959643fc245147c": [
"Hua",
"hua"
]
},
"expect_in_result": true
}
}
}
}
}