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

update all ids in experiment_screenshot.py

Browse Source
This commit is contained in:
Jason Lee
2024-03-13 21:06:55 +08:00
parent 670e20a248 a7782338d8
commit cee3b93009
24 changed files with 945 additions and 384 deletions
Download Patch File Download Diff File Expand all files Collapse all files

199
evaluation_examples/examples/multi_apps/0c825995-5b70-4526-b663-113f4c999dd2.json
View File

@@ -1,94 +1,109 @@
{
"id": "0c825995-5b70-4526-b663-113f4c999dd2",
"snapshot": "libreoffice_calc",
"instruction": "I'm working on a comprehensive report for our environmental policy review meeting next week. I need to integrate key insights from an important document, which is a guidebook on the Green Economy, where I'm particularly interested in the 'Introduction' section. Could you extract this section and compile them into a new Google Doc named 'environment_policy_report (draft)' under /environment_policy folder? This will significantly aid in our discussion on aligning our environmental policies with sustainable and green economic practices. Thanks!",
"source": "authors",
"config": [
{
"type": "googledrive",
"parameters": {
"settings_file": "evaluation_examples/settings/googledrive/settings.yml",
"operation": ["delete"],
"args": [
{
"query": "title = 'environment_policy_report (draft).doc' or title = 'environment_policy_report (draft).docx' or title = 'environment_policy_report (draft)'",
"trash": false
}
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "login",
"parameters": {
"settings_file": "evaluation_examples/settings/google/settings.json",
"platform": "googledrive"
}
},
{
"type": "command",
"parameters": {
"command": ["mkdir", "-p", "/home/user/Desktop/wwf"]
}
},
{
"type": "download",
"parameters": {
"files": [
{"path": "/home/user/Desktop/wwf/lpr_living_planet_report_2016.pdf", "url": "https://drive.google.com/uc?id=19NCdw_MVP6nH5nC6okYYe8U1mJABfTRK&export=download"},
{"path": "/home/user/Desktop/wwf/279c656a32_ENGLISH_FULL.pdf", "url": "https://drive.google.com/uc?id=1ckH1NetfImQ9EyONTO-ZFWA8m8VIUFvD&export=download"},
{"path": "/home/user/Desktop/wwf/7g37j96psg_WWF_AR2021_spreads.pdf", "url": "https://drive.google.com/uc?id=1cxLTzmqDKMomOyvho29lvFvhRnb0Y8__&export=download"},
{"path": "/home/user/Desktop/GE Guidebook.pdf", "url": "https://drive.google.com/uc?id=1KzC_R3eI3Rmgwz5bkcI8Ohv7ebOrU-Is&export=download"},
{"path": "/home/user/Desktop/assessing_and_reporting_water_quality(q&a).pdf", "url": "https://drive.google.com/uc?id=1LFojf3Weflv3fVdrZrgTY1iUaRdbT9kG&export=download"}
]
}
}
],
"trajectory": "trajectories/0c825995-5b70-4526-b663-113f4c999dd2",
"related_apps": [
"libreoffice_calc",
"chrome",
"os"
],
"evaluator": {
"func": "compare_docx_files",
"result": {
"type": "googledrive_file",
"settings_file": "evaluation_examples/settings/googledrive/settings.yml",
"path_list": [
[
"environment_policy_report (draft).docx"
]
],
"dest": [
"environment_policy_report (draft).docx"
]
},
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1A2ti9JncAfIa6ks7FTJWHtYlZo-68FtM&export=download",
"dest": "environment_policy_report (draft)_gold.docx"
},
"options": {
"content_only": true
}
}
"id": "0c825995-5b70-4526-b663-113f4c999dd2",
"snapshot": "libreoffice_calc",
"instruction": "I'm working on a comprehensive report for our environmental policy review meeting next week. I need to integrate key insights from an important document, which is a guidebook on the Green Economy, where I'm particularly interested in the 'Introduction' section. Could you extract this section and compile them into a new Google Doc named 'environment_policy_report (draft)' under /environment_policy folder? This will significantly aid in our discussion on aligning our environmental policies with sustainable and green economic practices. Thanks!",
"source": "authors",
"config": [
{
"type": "googledrive",
"parameters": {
"settings_file": "evaluation_examples/settings/googledrive/settings.yml",
"operation": [
"delete"
],
"args": [
{
"query": "title = 'environment_policy_report (draft).doc' or title = 'environment_policy_report (draft).docx' or title = 'environment_policy_report (draft)'",
"trash": false
}
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "login",
"parameters": {
"settings_file": "evaluation_examples/settings/google/settings.json",
"platform": "googledrive"
}
},
{
"type": "command",
"parameters": {
"command": [
"mkdir",
"-p",
"/home/user/Desktop/wwf"
]
}
},
{
"type": "download",
"parameters": {
"files": [
{
"path": "/home/user/Desktop/wwf/lpr_living_planet_report_2016.pdf",
"url": "https://drive.google.com/uc?id=19NCdw_MVP6nH5nC6okYYe8U1mJABfTRK&export=download"
},
{
"path": "/home/user/Desktop/wwf/279c656a32_ENGLISH_FULL.pdf",
"url": "https://drive.google.com/uc?id=1ckH1NetfImQ9EyONTO-ZFWA8m8VIUFvD&export=download"
},
{
"path": "/home/user/Desktop/wwf/7g37j96psg_WWF_AR2021_spreads.pdf",
"url": "https://drive.google.com/uc?id=1cxLTzmqDKMomOyvho29lvFvhRnb0Y8__&export=download"
},
{
"path": "/home/user/Desktop/GE Guidebook.pdf",
"url": "https://drive.google.com/uc?id=1KzC_R3eI3Rmgwz5bkcI8Ohv7ebOrU-Is&export=download"
},
{
"path": "/home/user/Desktop/assessing_and_reporting_water_quality(q&a).pdf",
"url": "https://drive.google.com/uc?id=1LFojf3Weflv3fVdrZrgTY1iUaRdbT9kG&export=download"
}
]
}
}
],
"trajectory": "trajectories/0c825995-5b70-4526-b663-113f4c999dd2",
"related_apps": [
"libreoffice_calc",
"chrome",
"os"
],
"evaluator": {
"func": "compare_docx_files",
"result": {
"type": "googledrive_file",
"settings_file": "evaluation_examples/settings/googledrive/settings.yml",
"path": ["environment_policy", "environment_policy_report (draft)"],
"dest": "environment_policy_report (draft).docx"
},
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1A2ti9JncAfIa6ks7FTJWHtYlZo-68FtM&export=download",
"dest": "environment_policy_report (draft)_gold.docx"
},
"options": {
"content_only": true
}
}
}

4
evaluation_examples/examples/multi_apps/0e5303d4-8820-42f6-b18d-daf7e633de21.json
View File

@@ -90,6 +90,10 @@
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=1Ej2iHG8p-QJe7FZQpPIIS82BHOlFAUQM&export=download&authuser=0&confirm=t",
"dest": "gold_lecture_slides.zip"
},
"options": {
"file_path": "lecture_slides",
"file_type": "pdf"
}
}
}

2
evaluation_examples/examples/multi_apps/3c8f201a-009d-4bbe-8b65-a6f8b35bb57f.json
View File

@@ -1,7 +1,7 @@
{
"id": "3c8f201a-009d-4bbe-8b65-a6f8b35bb57f",
"snapshot": "gimp",
"instruction": "Use `gdown` to download the image from \"https://drive.google.com/uc?export=download&id=1i8j5dGS57sA07jEuPNAlQW-sn5uqUnuK\", and then use GIMP to compress it to under 600KB. Resize if needed.",
"instruction": "Download the image from \"https://drive.google.com/uc?export=download&id=1i8j5dGS57sA07jEuPNAlQW-sn5uqUnuK\", and then use GIMP to compress it to under 600KB. Resize if needed.",
"source": "",
"config": [
{

2
evaluation_examples/examples/multi_apps/415ef462-bed3-493a-ac36-ca8c6d23bf1b.json
View File

@@ -57,7 +57,7 @@
{
"type": "launch",
"parameters": {
"command": ["nautilus"]
"command": ["nautilus", "/home/user/Documents/Finance"]
}
}
],

2
evaluation_examples/examples/multi_apps/42f4d1c7-4521-4161-b646-0a8934e36081.json
View File

@@ -1,7 +1,7 @@
{
"id": "42f4d1c7-4521-4161-b646-0a8934e36081",
"snapshot": "gimp",
"instruction": "Configure VS Code to edit GIMP script-fu scripts effectively by installing lisp extension. Test by writing code to resizing the image as 128 * 128 as \"resized.png\"",
"instruction": "Configure VS Code to edit GIMP script-fu scripts effectively by installing lisp extension. Test by writing code to resize the image \"character.png\" to 128 * 128 as \"resized.png\".",
"source": "",
"config": [
{

2
evaluation_examples/examples/multi_apps/4c26e3f3-3a14-4d86-b44a-d3cedebbb487.json
View File

@@ -37,7 +37,7 @@
},
"result": {
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=1lpRSXEoZq3ENOG5ekaAsBQSNv5ig0mDr&export=download&authuser=0&confirm=t&uuid=4cb10a33-81b3-4814-a969-f469832e33e5&at=APZUnTWN3pyiVpS003vLOgCcq2gu:1709710047375",
"path": "https://drive.usercontent.google.com/download?id=13if1UwZ5ay6ADAVW2jp3rcyvAEBse6MJ&export=download&authuser=0&confirm=t&uuid=2ea03068-1874-4240-baa1-f8bb2f917a99&at=APZUnTXq6dVlASg819jCaI1A-rm2:1710136385956",
"dest": "image_original.png"
}
}

2
evaluation_examples/examples/multi_apps/69acbb55-d945-4927-a87b-8480e1a5bb7e.json
View File

@@ -45,7 +45,7 @@
"rules": {
"include": [],
"exclude": [
"ModuleNotFoundError: No module named"
"Error:"
]
}
}

8
evaluation_examples/examples/multi_apps/91190194-f406-4cd6-b3f9-c43fac942b22.json
View File

@@ -11,10 +11,6 @@
{
"url": "https://drive.google.com/uc?export=download&id=1bmSRNNh4JkF6izrKrmynUHarf0pFES50",
"path": "/home/user/Desktop/cola.png"
},
{
"url": "https://drive.google.com/uc?export=download&id=1MayrIPJWRK7cMEVe3TxYmgkAbVMrYcQA",
"path": "/home/user/Desktop/cropped_gold.png"
}
]
}
@@ -43,8 +39,8 @@
"dest": "cropped.png"
},
"expected": {
"type": "vm_file",
"path": "/home/user/Desktop/cropped_gold.png",
"type": "cloud_file",
"path": "https://drive.google.com/uc?export=download&id=1MayrIPJWRK7cMEVe3TxYmgkAbVMrYcQA",
"dest": "cropped_gold.png"
}
}

2
evaluation_examples/examples/multi_apps/98e8e339-5f91-4ed2-b2b2-12647cb134f4.json
View File

@@ -1,7 +1,7 @@
{
"id": "98e8e339-5f91-4ed2-b2b2-12647cb134f4",
"snapshot": "vs_code",
"instruction": "Merge the contents of all .txt files from your vscode project into a single document in Writer. No merging separator is needed. Ensure to set the overall font size of the document to 10.",
"instruction": "Merge the contents of all .txt files from your vscode project into a single document \"concat.docx\" on Desktop with libreoffice writer. No merging separator is needed. Ensure to set the overall font size of the document to 10.",
"source": "",
"config": [
{

4
evaluation_examples/examples/multi_apps/b337d106-053f-4d37-8da0-7f9c4043a66b.json
View File

@@ -1,7 +1,7 @@
{
"id": "b337d106-053f-4d37-8da0-7f9c4043a66b",
"snapshot": "os",
"instruction": "Recently, I've been exploring the use of the Vim editor for code editing. However, the default settings don't display line numbers in Vim editor. Please search the internet for a tutorial on adding line numbers in Vim and setting it as default for my local Vim.",
"instruction": "Recently, I've been exploring the use of the Vim editor for code editing. However, the default settings don't display line numbers in Vim editor. Please search the Internet for a tutorial on adding absolute line numbers in Vim and setting it as default for my local Vim.",
"source": "authors",
"config": [
{
@@ -52,7 +52,7 @@
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1CyhWjUS2oov4Fzc0VRwTh6LiS2Qu-T_8&export=download&authuser=0&confirm=t&uuid=9d0e2c62-895c-4bb3-a057-30cae60329ed&at=APZUnTVngSwARjYsWSmhSyHAqwID:1709647023362",
"url": "https://drive.usercontent.google.com/download?id=1CyhWjUS2oov4Fzc0VRwTh6LiS2Qu-T_8&export=download&authuser=0&confirm=t&uuid=384ea31d-c9ae-4e81-be19-42035c563014&at=APZUnTU9lsYwMLfWb7RIizGr1D7H:1710085473758",
"path": "eval.sh"
}
]

8
evaluation_examples/examples/multi_apps/d68204bf-11c1-4b13-b48b-d303c73d4bf6.json
View File

@@ -11,10 +11,6 @@
{
"url": "https://drive.google.com/uc?export=download&id=1CPGW_OZsfSWDdTU7CFrTjpzSAASyLy4w",
"path": "/home/user/Desktop/tilearray.png"
},
{
"url": "https://drive.google.com/uc?export=download&id=1aHwmnxL2CKEh_FhVpevY452-BQH2t5rG",
"path": "/home/user/Desktop/rearranged_gold.png"
}
]
}
@@ -43,8 +39,8 @@
"dest": "rearranged.png"
},
"expected": {
"type": "vm_file",
"path": "/home/user/Desktop/rearranged_gold.png",
"type": "cloud_file",
"path": "https://drive.google.com/uc?export=download&id=1aHwmnxL2CKEh_FhVpevY452-BQH2t5rG",
"dest": "rearranged_gold.png"
}
}

2
evaluation_examples/examples/multi_apps/da922383-bfa4-4cd3-bbad-6bebab3d7742.json
View File

@@ -1,7 +1,7 @@
{
"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/Blogs.",
"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": [
{