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

174
evaluation_examples/examples/libreoffice_calc/1de60575-bb6e-4c3d-9e6a-2fa699f9f197.json
View File

@@ -1,88 +1,88 @@
{
"id": "1de60575-bb6e-4c3d-9e6a-2fa699f9f197",
"snapshot": "libreoffice_calc",
"instruction": "Summarize the total revenue for each promotion type in a new sheet (Sheet2) with the promotion names as the column headers.",
"source": "SheetCopilot@55",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?id=1I29YyV7zFdNqbsQw0SWD9pDuLz3oHlge&export=download",
"path": "/home/user/EntireSummerSales.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/EntireSummerSales.xlsx"
}
}
],
"trajectory": "trajectories/1de60575-bb6e-4c3d-9e6a-2fa699f9f197",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "EntireSummerSales.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 3.0
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1khzLf5AIlvdtKJQTPJksY8MFohpATeHG&export=download",
"dest": "6_EntireSummerSales_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/EntireSummerSales.xlsx",
"dest": "EntireSummerSales.xlsx"
},
"options": {
"rules": [
{
"type": "pivot_table",
"sheet_idx0": "RNSheet2",
"sheet_idx1": "ENSheet2",
"pivot_props": [
"col_fields",
"filter",
"row_fields",
"data_fields"
]
}
]
}
}
}
"id": "1de60575-bb6e-4c3d-9e6a-2fa699f9f197",
"snapshot": "libreoffice_calc",
"instruction": "Summarize the total revenue for each promotion type in a new sheet (Sheet2) with the promotion names as the column headers.",
"source": "SheetCopilot@55",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/libreoffice_calc/1de60575-bb6e-4c3d-9e6a-2fa699f9f197/EntireSummerSales.xlsx",
"path": "/home/user/EntireSummerSales.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/EntireSummerSales.xlsx"
}
}
],
"trajectory": "trajectories/1de60575-bb6e-4c3d-9e6a-2fa699f9f197",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "EntireSummerSales.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 3.0
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/libreoffice_calc/1de60575-bb6e-4c3d-9e6a-2fa699f9f197/6_EntireSummerSales_gt1.xlsx",
"dest": "6_EntireSummerSales_gt1.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/EntireSummerSales.xlsx",
"dest": "EntireSummerSales.xlsx"
},
"options": {
"rules": [
{
"type": "pivot_table",
"sheet_idx0": "RNSheet2",
"sheet_idx1": "ENSheet2",
"pivot_props": [
"col_fields",
"filter",
"row_fields",
"data_fields"
]
}
]
}
}
}