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

130
evaluation_examples/examples/multi_apps/da922383-bfa4-4cd3-bbad-6bebab3d7742.json
View File

@@ -1,75 +1,75 @@
{
"id": "da922383-bfa4-4cd3-bbad-6bebab3d7742",
"snapshot": "multiapps",
"instruction": "I browsed a lot of interesting blog articles today. I hope to store these articles in my local designated folder just like zotero stores papers. Please download the blogs opening now in pdf format and save them in their tile to /home/user/Documents/Blog.",
"source": "authors",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
"id": "da922383-bfa4-4cd3-bbad-6bebab3d7742",
"snapshot": "multiapps",
"instruction": "I browsed a lot of interesting blog articles today. I hope to store these articles in my local designated folder just like zotero stores papers. Please download the blogs opening now in pdf format and save them in their tile to /home/user/Documents/Blog.",
"source": "authors",
"config": [
{
"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://lilianweng.github.io/posts/2023-06-23-agent/",
"https://lilianweng.github.io/posts/2024-02-05-human-data-quality/"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome",
"os"
],
"evaluator": {
"postconfig": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/da922383-bfa4-4cd3-bbad-6bebab3d7742/script.py",
"path": "/home/user/Desktop/script.py"
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://lilianweng.github.io/posts/2023-06-23-agent/",
"https://lilianweng.github.io/posts/2024-02-05-human-data-quality/"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome", "os"
],
"evaluator": {
"postconfig":[
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1fm4wqp91_3yzVSlenc9k2Tlh3-7QuRvu&export=download&authuser=0&confirm=t&uuid=5bb46f9e-ef04-4b52-bceb-a88f0058f696&at=APZUnTU6aWNzsiqLwAlyr_8pxKUd:1709971656456",
"path": "/home/user/Desktop/script.py"
}
]
}
},
{
"type": "execute",
"parameters": {
"command": "pip install PyMuPDF",
"shell": "true"
}
]
}
],
"func": "exact_match",
"result":{
"type": "vm_command_line",
"command":"python /home/user/Desktop/script.py",
"shell": "true"
},
{
"type": "execute",
"parameters": {
"command": "pip install PyMuPDF",
"shell": "true"
}
}
],
"func": "exact_match",
"result": {
"type": "vm_command_line",
"command": "python /home/user/Desktop/script.py",
"shell": "true"
},
"expected": {
"type": "rule",
"rules":{
"rules": {
"expected": "[1, 1]\n"
}
}
}
}
}