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

112
evaluation_examples/examples/libreoffice_calc/347ef137-7eeb-4c80-a3bb-0951f26a8aff.json
View File

@@ -1,32 +1,32 @@
{
"id": "347ef137-7eeb-4c80-a3bb-0951f26a8aff",
"snapshot": "libreoffice_calc",
"instruction": "Here are two tables recording the per-month costs in 2019 and 2020. I want to create two column bar charts reflecting per-month cost variations for each year from these data. Help me, Mr. Assistant!",
"source": "https://www.youtube.com/watch?v=bgO40-CjYNY",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1GOEacGTLP4EfGS8YwO9aGmmPgud5EavT&export=download&authuser=0&confirm=t&uuid=3971675c-3a76-4f89-863f-7f8afa59c3c5&at=APZUnTWaQ4_l1IiXsAR8VbjKf4uZ:1703595929357",
"path": "/home/user/Create_column_charts_using_statistics.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/Create_column_charts_using_statistics.xlsx"
}
}
],
"trajectory": "trajectories/347ef137-7eeb-4c80-a3bb-0951f26a8aff",
"id": "347ef137-7eeb-4c80-a3bb-0951f26a8aff",
"snapshot": "libreoffice_calc",
"instruction": "Here are two tables recording the per-month costs in 2019 and 2020. I want to create two column bar charts reflecting per-month cost variations for each year from these data. Help me, Mr. Assistant!",
"source": "https://www.youtube.com/watch?v=bgO40-CjYNY",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/libreoffice_calc/347ef137-7eeb-4c80-a3bb-0951f26a8aff/Create_column_charts_using_statistics.xlsx",
"path": "/home/user/Create_column_charts_using_statistics.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/Create_column_charts_using_statistics.xlsx"
}
}
],
"trajectory": "trajectories/347ef137-7eeb-4c80-a3bb-0951f26a8aff",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"evaluator": {
"postconfig": [
{
"type": "activate_window",
@@ -58,34 +58,34 @@
}
}
],
"func": "compare_table",
"result": {
"type": "vm_file",
"path": "/home/user/Create_column_charts_using_statistics.xlsx",
"dest": "Create_column_charts_using_statistics.xlsx"
},
"expected": {
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=1yiTCGZvGccWET9u8K7looD3ybH7PO9gb&export=download&authuser=0&confirm=t&uuid=65f54a6f-bb2e-40c3-8a76-091d785a5aca&at=APZUnTVbeO6maMvzItLvSwdBEZoM:1703595892144",
"dest": "Create_column_charts_using_statistics_gold.xlsx"
},
"options": {
"rules": [
{
"type": "chart",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"chart_props": [
"type",
"direction"
]
},
{
"type": "sheet_data",
"sheet_idx0": 0,
"sheet_idx1": "EI0"
}
]
}
}
}
"func": "compare_table",
"result": {
"type": "vm_file",
"path": "/home/user/Create_column_charts_using_statistics.xlsx",
"dest": "Create_column_charts_using_statistics.xlsx"
},
"expected": {
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/libreoffice_calc/347ef137-7eeb-4c80-a3bb-0951f26a8aff/Create_column_charts_using_statistics_gold.xlsx",
"dest": "Create_column_charts_using_statistics_gold.xlsx"
},
"options": {
"rules": [
{
"type": "chart",
"sheet_idx0": 0,
"sheet_idx1": "EI0",
"chart_props": [
"type",
"direction"
]
},
{
"type": "sheet_data",
"sheet_idx0": 0,
"sheet_idx1": "EI0"
}
]
}
}
}