Files
sci-gui-agent-benchmark/evaluation_examples/examples/multi_apps/dd60633f-2c72-42ba-8547-6f2c8cb0fdb0.json

55 lines
1.4 KiB
JSON

{
"id": "dd60633f-2c72-42ba-8547-6f2c8cb0fdb0",
"snapshot": "multiapps",
"instruction": "I ran some simple code demos on the currently open google colab, and I think the effect is pretty good. Please help me extract the code in all code boxes, merge it into a \"task.py\" file and store it in the local Home directory.",
"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://colab.research.google.com/github/stanfordnlp/dspy/blob/main/intro.ipynb#scrollTo=L1BHAoL_LRd7"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome",
"os",
"writer"
],
"evaluator": {
"func": "compare_python_pure_text",
"result": {
"type": "vm_file",
"path": "/home/user/colab.py",
"dest": "colab.py"
},
"expected": {
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/dd60633f-2c72-42ba-8547-6f2c8cb0fdb0/Colab%20Gold.py",
"dest": "colab_Gold.py"
}
},
"proxy": true
}