136 lines
3.3 KiB
JSON
136 lines
3.3 KiB
JSON
{
|
|||
|
|
"cases": "lab03-challenge2.json",
|
||
|
|
"webhook": "my-quality-report",
|
||
|
|
"passed": 0,
|
||
|
|
"total": 4,
|
||
|
|
"results": [
|
||
|
|
{
|
||
|
|
"case": "검사도 품질 기록 (직원 · 티켓 · FAQ)",
|
||
|
|
"webhook": "http://localhost:8800/quality-log/list",
|
||
|
|
"run": 1,
|
||
|
|
"passed": false,
|
||
|
|
"problems": [
|
||
|
|
"count = 1 (expected 3)",
|
||
|
|
"items.0.dataset = faq (expected employee)",
|
||
|
|
"items.0.score = 0.8333 (expected 0.4444)",
|
||
|
|
"items.1.dataset = null (expected ticket)",
|
||
|
|
"items.2.dataset = null (expected faq)"
|
||
|
|
],
|
||
|
|
"seconds": 0.0,
|
||
|
|
"status": 200,
|
||
|
|
"request": {},
|
||
|
|
"response": {
|
||
|
|
"count": 1,
|
||
|
|
"items": [
|
||
|
|
{
|
||
|
|
"batch": "B-3",
|
||
|
|
"dataset": "faq",
|
||
|
|
"total": 6,
|
||
|
|
"valid": 5,
|
||
|
|
"quarantined": 1,
|
||
|
|
"rejected": false,
|
||
|
|
"score": 0.8333,
|
||
|
|
"codes": {
|
||
|
|
"answer_too_short": 1
|
||
|
|
},
|
||
|
|
"at": "2026-11-01T18:11:10"
|
||
|
|
}
|
||
|
|
]
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"case": "데이터셋마다 나눠 보기",
|
||
|
|
"webhook": "my-quality-report",
|
||
|
|
"run": 1,
|
||
|
|
"passed": false,
|
||
|
|
"problems": [
|
||
|
|
"count = 1 (expected 3)",
|
||
|
|
"by_dataset.employee.avg_score = null (expected 0.4444)",
|
||
|
|
"by_dataset.ticket.avg_score = null (expected 0.2222)",
|
||
|
|
"by_dataset.faq.avg_score = null (expected 0.8333)"
|
||
|
|
],
|
||
|
|
"seconds": 0.2,
|
||
|
|
"status": 200,
|
||
|
|
"request": {},
|
||
|
|
"response": {
|
||
|
|
"count": 1,
|
||
|
|
"batches": [
|
||
|
|
{
|
||
|
|
"batch": "B-3",
|
||
|
|
"score": 0.8333,
|
||
|
|
"rejected": false,
|
||
|
|
"total": 6
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"avg_score": 0.8333,
|
||
|
|
"worst_batch": "B-3",
|
||
|
|
"rejected_batches": 0,
|
||
|
|
"top_codes": [
|
||
|
|
{
|
||
|
|
"code": "answer_too_short",
|
||
|
|
"count": 1
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"trend": "그대로"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"case": "가장 나쁜 데이터셋 · 그 이유",
|
||
|
|
"webhook": "my-quality-report",
|
||
|
|
"run": 1,
|
||
|
|
"passed": false,
|
||
|
|
"problems": [
|
||
|
|
"worst_dataset = null (expected ticket)",
|
||
|
|
"by_dataset.employee.top_code = null (expected bad_format:email)"
|
||
|
|
],
|
||
|
|
"seconds": 0.1,
|
||
|
|
"status": 200,
|
||
|
|
"request": {},
|
||
|
|
"response": {
|
||
|
|
"count": 1,
|
||
|
|
"batches": [
|
||
|
|
{
|
||
|
|
"batch": "B-3",
|
||
|
|
"score": 0.8333,
|
||
|
|
"rejected": false,
|
||
|
|
"total": 6
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"avg_score": 0.8333,
|
||
|
|
"worst_batch": "B-3",
|
||
|
|
"rejected_batches": 0,
|
||
|
|
"top_codes": [
|
||
|
|
{
|
||
|
|
"code": "answer_too_short",
|
||
|
|
"count": 1
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"trend": "그대로"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"case": "한 데이터셋만 (앞의 칸은 그대로)",
|
||
|
|
"webhook": "my-quality-report",
|
||
|
|
"run": 1,
|
||
|
|
"passed": false,
|
||
|
|
"problems": [
|
||
|
|
"count = 0 (expected 1)",
|
||
|
|
"worst_batch = null (expected TK-1)"
|
||
|
|
],
|
||
|
|
"seconds": 0.0,
|
||
|
|
"status": 200,
|
||
|
|
"request": {
|
||
|
|
"dataset": "ticket"
|
||
|
|
},
|
||
|
|
"response": {
|
||
|
|
"count": 0,
|
||
|
|
"batches": [],
|
||
|
|
"avg_score": 0,
|
||
|
|
"worst_batch": null,
|
||
|
|
"rejected_batches": 0,
|
||
|
|
"top_codes": [],
|
||
|
|
"trend": "그대로"
|
||
|
|
}
|
||
|
|
}
|
||
|
|
]
|
||
|
|
}
|