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

Update examples

Browse Source
This commit is contained in:
Timothyxxx
2024-03-06 15:05:47 +08:00
parent e6d4ed7fd6
commit f21d685108
4 changed files with 293 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

49
evaluation_examples/examples/multi_apps/337d318b-aa07-4f4f-b763-89d9a2dd013f.json Normal file
View File

@@ -0,0 +1,49 @@
{
"id": "337d318b-aa07-4f4f-b763-89d9a2dd013f",
"snapshot": "libreoffice_calc",
"instruction": "Cross-check the invoices with the bank statements and identify any discrepancies. Then pull out the invoices that don't match the statements and put them in the \"problematic\" folder.",
"source": "authors",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"path": "/home/user/Desktop/invoice TII-20220301-90.pdf",
"url": "https://drive.google.com/uc?id=13y1Dkh9dJUaWeMSk6pg_UY-R7K4bhAJM&export=download"
},
{
"path": "/home/user/Desktop/Invoice # GES-20220215-82.pdf",
"url": "https://drive.google.com/uc?id=1zZYJQVpbGmqT_eH0x9Z5O7WoIFrQo3sN&export=download"
},
{
"path": "/home/user/Desktop/Invoice # 243729.pdf",
"url": "https://drive.google.com/uc?id=1a7fnWpsAdFQkFWl2BqAA_gTwlZ6nvGAx&export=download"
},
{
"path": "/home/user/Desktop/Bank-Statement.pdf",
"url": "https://drive.google.com/uc?id=1-KS6p0aip56iPmH4okhXZhLgqVwrcjfw&export=download"
}
]
}
}
],
"trajectory": "trajectories/337d318b-aa07-4f4f-b763-89d9a2dd013f",
"related_apps": [
"os",
"pdf"
],
"evaluator": {
"func": "compare_pdfs",
"result": {
"type": "vm_file",
"path": "/home/user/Desktop/problematic/Invoice # 243729.pdf",
"dest": "Invoice # 243729.pdf"
},
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1a7fnWpsAdFQkFWl2BqAA_gTwlZ6nvGAx&export=download",
"dest": "Invoice # 243729 Gold.pdf"
}
}
}

89
evaluation_examples/examples/multi_apps/82e3c869-49f6-4305-a7ce-f3e64a0618e7.json Normal file
View File

@@ -0,0 +1,89 @@
{
"id": "82e3c869-49f6-4305-a7ce-f3e64a0618e7",
"snapshot": "libreoffice_calc",
"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 and place them in a separate folder named 'presenter'. Then, compress this folder into a zip file 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://drive.google.com/uc?id=1NjnSab2aEtJytYajM9FqeXsLm4ItxTsJ&export=download"
},
{
"path": "/home/user/Desktop/IDS LLM seminar/DSC00657.jpg",
"url": "https://drive.google.com/uc?id=1untYr5vS_wCVd3-5cfdUegBBILT4tHzF&export=download"
},
{
"path": "/home/user/Desktop/IDS LLM seminar/DSC00574.jpg",
"url": "https://drive.google.com/uc?id=1V3g4z2QhIHx48LbeaNx31nMosxYPgtzY&export=download"
},
{
"path": "/home/user/Desktop/IDS LLM seminar/DSC00554.jpg",
"url": "https://drive.google.com/uc?id=1DNz3iZmNk6-dazqXilOFkRpgUahU57zd&export=download"
},
{
"path": "/home/user/Desktop/IDS LLM seminar/DSC00495.jpg",
"url": "https://drive.google.com/uc?id=1_crKe2tdI4Kjg0Xop8vHo7yN9KACJTJF&export=download"
},
{
"path": "/home/user/Desktop/IDS LLM seminar/DSC00454.jpg",
"url": "https://drive.google.com/uc?id=1t9L7fVQVxjovTQufetlogulIctn7DF_L&export=download"
}
]
}
}
],
"trajectory": "trajectories/82e3c869-49f6-4305-a7ce-f3e64a0618e7",
"related_apps": [
"os",
"image"
],
"evaluator": {
"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://drive.google.com/uc?id=1untYr5vS_wCVd3-5cfdUegBBILT4tHzF&export=download",
"https://drive.google.com/uc?id=1V3g4z2QhIHx48LbeaNx31nMosxYPgtzY&export=download",
"https://drive.google.com/uc?id=1DNz3iZmNk6-dazqXilOFkRpgUahU57zd&export=download",
"https://drive.google.com/uc?id=1_crKe2tdI4Kjg0Xop8vHo7yN9KACJTJF&export=download"
],
"dest": [
"DSC00657_gold.jpg",
"DSC00574_gold.jpg",
"DSC00554_gold.jpg",
"DSC00495_gold.jpg"
],
"multi": "true"
}
}
}

54
evaluation_examples/examples/multi_apps/8e116af7-7db7-4e35-a68b-b0939c066c78.json Normal file
View File

@@ -0,0 +1,54 @@
{
"id": "8e116af7-7db7-4e35-a68b-b0939c066c78",
"snapshot": "libreoffice_calc",
"instruction": "Please update my bookkeeping sheet with the recent transactions from the provided folder, detailing my expenses over the past few days.",
"source": "authors",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"path": "/home/user/Desktop/my_bookkeeping.xlsx",
"url": "https://drive.google.com/uc?id=1QOSpTZPFzFZeC0tng4Gfws544LFln836&export=download"
},
{
"path": "/home/user/Desktop/receipt_0.jpeg",
"url": "https://drive.google.com/uc?id=1b0BRc-BzXObVCUEonJfRbDsrgxZugj3U&export=download"
},
{
"path": "/home/user/Desktop/receipt_1.jpg",
"url": "https://drive.google.com/uc?id=1S-JBDqwEf7Z_JXDItK_F4BOHgScTjlyN&export=download"
},
{
"path": "/home/user/Desktop/receipt_2.jpg",
"url": "https://drive.google.com/uc?id=1Ys2abZi9_0y8sxuj2vCbC0OhjC6YdrC-&export=download"
},
{
"path": "/home/user/Desktop/receipt_3.pdf",
"url": "https://drive.google.com/uc?id=1sKvBbGDpmUkv891xTqX7w5dtEvchQahd&export=download"
},
{
"path": "/home/user/Desktop/receipt_4.jpg",
"url": "https://drive.google.com/uc?id=1kW7xH5bc2jRaKGDKHDrgSehTrPgkyzkc&export=download"
}
]
}
}
],
"trajectory": "trajectories/8e116af7-7db7-4e35-a68b-b0939c066c78",
"related_apps": [
"",
""
],
"evaluator": {
"postconfig": [],
"func": "",
"result": {
},
"expected": {
},
"options": {
}
}
}

101
evaluation_examples/examples/multi_apps/deec51c9-3b1e-4b9e-993c-4776f20e8bb2.json Normal file
View File

@@ -0,0 +1,101 @@
{
"id": "deec51c9-3b1e-4b9e-993c-4776f20e8bb2",
"snapshot": "libreoffice_calc",
"instruction": "Find a paper list of all the new foundation language models issued on 11st Oct. 2023 via arxiv daily, and organize it into the sheet I opened.",
"source": "authors",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"path": "/home/user/Desktop/New Large Language Models.xlsx",
"url": "https://drive.google.com/uc?id=1NJFAUDzatd5TbBqXeCy3-ok4BWj-xayT&export=download"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/Desktop/New Large Language Models.xlsx"
}
}
],
"trajectory": "trajectories/deec51c9-3b1e-4b9e-993c-4776f20e8bb2",
"related_apps": [
"libreoffice_calc",
"chrome",
"os"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "New Large Language Models.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": 1.0
}
}
],
"func": "compare_table",
"result": {
"type": "vm_file",
"path": "/home/user/Desktop/New Large Language Models.xlsx",
"dest": "New Large Language Models.xlsx"
},
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1BHOyjFo72b74YKWTqPMaoNvCzICkos-G&export=download",
"dest": "New Large Language Models Gold.xlsx"
},
"options": {
"rules": [
{
"type": "sheet_fuzzy",
"sheet_idx0": "RNSheet1",
"sheet_idx1": "ENSheet1",
"rules": [
{
"range": [
"B2:B5",
"C2:C5"
],
"type": "exact_match"
},
{
"range": [
"A2:A5"
],
"type": "fuzzy_match",
"threshold": 90,
"ignore_case": true
}
]
}
]
}
}
}