Files
sci-gui-agent-benchmark/evaluation_examples/examples/multi_apps/82e3c869-49f6-4305-a7ce-f3e64a0618e7.json
Tianbao Xie bba367b8bc fix: fix multiapps tasks (#231)
* Update JSON example for multi_apps: change snapshot name and specify presenter in instructions for clarity.

* Enhance PDF image comparison in chrome.py by adding existence checks for input files and improving image extraction logic. Introduce image hashing for similarity scoring with a configurable threshold. Update docs.py to support fuzzy matching in DOCX file comparisons, allowing for similarity scoring based on text content. Modify example JSON to enable fuzzy matching option.

---------

Co-authored-by: yuanmengqi <yuanmengqi@mail.ustc.edu.cn>
2025-07-03 16:58:43 +08:00

114 lines
4.1 KiB
JSON

{
"id": "82e3c869-49f6-4305-a7ce-f3e64a0618e7",
"snapshot": "multi_apps",
"instruction": "Please sift through the folder with all the event photos taken by our photographer. I need you to extract the photos featuring the presenters (a.k.a. Tao Yu) and place them in a separate folder named 'presenter'. Then, compress this folder into a zip file named 'presenter.zip' so I can easily share it with others later.",
"source": "authors",
"config": [
{
"type": "command",
"parameters": {
"command": [
"mkdir",
"-p",
"/home/user/Desktop/IDS LLM seminar/"
]
}
},
{
"type": "download",
"parameters": {
"files": [
{
"path": "/home/user/Desktop/IDS LLM seminar/DSC00659.jpg",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/82e3c869-49f6-4305-a7ce-f3e64a0618e7/DSC00659.jpg"
},
{
"path": "/home/user/Desktop/IDS LLM seminar/DSC00657.jpg",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/82e3c869-49f6-4305-a7ce-f3e64a0618e7/DSC00657.jpg"
},
{
"path": "/home/user/Desktop/IDS LLM seminar/DSC00574.jpg",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/82e3c869-49f6-4305-a7ce-f3e64a0618e7/DSC00574.jpg"
},
{
"path": "/home/user/Desktop/IDS LLM seminar/DSC00554.jpg",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/82e3c869-49f6-4305-a7ce-f3e64a0618e7/DSC00554.jpg"
},
{
"path": "/home/user/Desktop/IDS LLM seminar/DSC00495.jpg",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/82e3c869-49f6-4305-a7ce-f3e64a0618e7/DSC00495.jpg"
},
{
"path": "/home/user/Desktop/IDS LLM seminar/DSC00454.jpg",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/82e3c869-49f6-4305-a7ce-f3e64a0618e7/DSC00454.jpg"
}
]
}
}
],
"trajectory": "trajectories/82e3c869-49f6-4305-a7ce-f3e64a0618e7",
"related_apps": [
"os",
"image"
],
"evaluator": {
"postconfig": [
{
"type": "execute",
"parameters": {
"command": [
"rm",
"-rf",
"/home/user/Desktop/presenter"
]
}
},
{
"type": "execute",
"parameters": {
"command": [
"unzip",
"/home/user/Desktop/presenter.zip",
"-d",
"/home/user/Desktop"
]
}
}
],
"func": "compare_image_list",
"result": {
"type": "vm_file",
"path": [
"/home/user/Desktop/presenter/DSC00657.jpg",
"/home/user/Desktop/presenter/DSC00574.jpg",
"/home/user/Desktop/presenter/DSC00554.jpg",
"/home/user/Desktop/presenter/DSC00495.jpg"
],
"dest": [
"DSC00657.jpg",
"DSC00574.jpg",
"DSC00554.jpg",
"DSC00495.jpg"
],
"multi": "true"
},
"expected": {
"type": "cloud_file",
"path": [
"https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/82e3c869-49f6-4305-a7ce-f3e64a0618e7/DSC00657.jpg",
"https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/82e3c869-49f6-4305-a7ce-f3e64a0618e7/DSC00574.jpg",
"https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/82e3c869-49f6-4305-a7ce-f3e64a0618e7/DSC00554.jpg",
"https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/82e3c869-49f6-4305-a7ce-f3e64a0618e7/DSC00495.jpg"
],
"dest": [
"DSC00657_gold.jpg",
"DSC00574_gold.jpg",
"DSC00554_gold.jpg",
"DSC00495_gold.jpg"
],
"multi": "true"
}
},
"proxy": false
}