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

Update multiple-apps examples and eval (WIP)

Browse Source
This commit is contained in:
Timothyxxx
2024-03-02 20:41:01 +08:00
parent 0554703c01
commit 9c5269be3a
7 changed files with 316 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

67
evaluation_examples/examples/multi_apps/0c825995-5b70-4526-b663-113f4c999dd2.json
View File

@@ -1,9 +1,48 @@
{
"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)'? This will significantly aid in our discussion on aligning our environmental policies with sustainable and green economic practices. Thanks!",
"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": {
@@ -30,16 +69,26 @@
"os"
],
"evaluator": {
"postconfig": [],
"func": "",
"result": {
"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": {
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1A2ti9JncAfIa6ks7FTJWHtYlZo-68FtM&export=download",
"dest": "environment_policy_report (draft)_gold.docx"
},
"options": {
"options": {
"content_only": true
}
}
}