59 lines
2.8 KiB
Python
59 lines
2.8 KiB
Python
|
"""知识块粒度选择的单元测试。
|
||
|
|
|
||
|
|
背景是实测的三次翻车，每条判据都对应其中一次：
|
||
|
|
|
||
|
|
1. 客户问「起投多少」和「风险高吗」时命中同一块（整个产品小节），拿到**完全相同**的
|
||
|
|
整节内容，看起来像客服没听懂问题——所以把表格行拆成了行级子块。
|
||
|
|
2. 拆细之后「介绍一下」又被某一行抢答（返回"产品期限 90天封闭期"）——所以要能换回整节。
|
||
|
|
3. 两次判据写错：用"含连字符"认子块时，整节块自己的编号 PROD-901 被误判成子块；
|
||
|
|
用"不含两位数字后缀"认整节块时，FAQ 块全被误判成整节块、把正确答案挤出了 top1。
|
||
|
|
"""
|
||
|
|
|
||
|
|
from app.service.agent.implementations.customer_service import CustomerServiceAgent
|
||
|
|
from app.service.knowledge_search_service import KnowledgeSearchService
|
||
|
|
|
||
|
|
|
||
|
|
def test_parent_of_recognises_row_blocks() -> None:
|
||
|
|
assert KnowledgeSearchService._parent_of("PROD-007-04") == "PROD-007"
|
||
|
|
|
||
|
|
|
||
|
|
def test_parent_of_rejects_section_blocks() -> None:
|
||
|
|
"""整节块的编号本身就含连字符（PROD-901），不能被当成子块。"""
|
||
|
|
assert KnowledgeSearchService._parent_of("PROD-901") is None
|
||
|
|
assert KnowledgeSearchService._parent_of("FAQ-0016") is None
|
||
|
|
assert KnowledgeSearchService._parent_of("HNW-003") is None
|
||
|
|
|
||
|
|
|
||
|
|
def test_section_chosen_for_overview_question() -> None:
|
||
|
|
"""客户问整节时，用父块替掉抢答的那一行。"""
|
||
|
|
child = {"doc_id": "PROD-007-05", "title": "手册 · 2.1 南方季季盈90天 · 产品期限"}
|
||
|
|
parent = {"doc_id": "PROD-007", "content": "整节内容"}
|
||
|
|
|
||
|
|
assert CustomerServiceAgent._prefer_section(
|
||
|
|
"南方季季盈90天介绍一下", child, [child, parent]
|
||
|
|
) is parent
|
||
|
|
|
||
|
|
|
||
|
|
def test_row_kept_when_question_names_the_field() -> None:
|
||
|
|
"""客户问的正是那一行时不能换成整节，否则"聚焦"就白做了。"""
|
||
|
|
child = {"doc_id": "PROD-007-04", "title": "手册 · 2.1 南方季季盈90天 · 起投金额"}
|
||
|
|
parent = {"doc_id": "PROD-007", "content": "整节内容"}
|
||
|
|
|
||
|
|
assert CustomerServiceAgent._prefer_section(
|
||
|
|
"季季盈90天起投多少", child, [child, parent]
|
||
|
|
) is child
|
||
|
|
|
||
|
|
|
||
|
|
def test_missing_parent_falls_back_to_row() -> None:
|
||
|
|
"""父块没带回来时仍用子块：宁可答得窄，也不要拿不相干的块搪塞。"""
|
||
|
|
child = {"doc_id": "PROD-007-05", "title": "手册 · 2.1 南方季季盈90天 · 产品期限"}
|
||
|
|
|
||
|
|
assert CustomerServiceAgent._prefer_section("介绍一下", child, [child]) is child
|
||
|
|
|
||
|
|
|
||
|
|
def test_plain_block_is_not_treated_as_section() -> None:
|
||
|
|
"""FAQ 这类独立块没有子块挂在下面，不该被当成整节块。"""
|
||
|
|
plain = {"doc_id": "FAQ-0016", "title": "基金赎回到账需要多长时间?"}
|
||
|
|
|
||
|
|
assert CustomerServiceAgent._prefer_section("基金赎回几天到账", plain, [plain]) is plain
|