326 lines
16 KiB
Python
326 lines
16 KiB
Python
|
"""把 knowledge/ 下的文档切成可检索知识块，输出 JSONL（临时脚本，跑完即删）。
|
|||
|
|
|
|||
|
|
切片粒度决定检索质量。这里采用**叶子标题**策略：一个标题若其后没有更深的标题，
|
|||
|
|
它就是一个切分点。相比"按固定级别切"，这个策略同时满足了三种真实情况：
|
|||
|
|
|
|||
|
|
- 有的条款带 `#### X.Y` 子条款（如反洗钱第九条 9.1–9.4）→ 按子条款切，粒度更细；
|
|||
|
|
- 有的条款没有子条款（如反洗钱第十一条）→ 自己就是叶子，单独成块，不会被并进上一块；
|
|||
|
|
- 有的章没有小节（如企业信息「一、公司基本信息」）→ 章本身就是叶子，内容不会丢。
|
|||
|
|
|
|||
|
|
标题路径保留完整上级链；若切分点本身不是「第X条」（例如反洗钱第十三条下的
|
|||
|
|
`### 第一类：资金流转异常`），会把最近的条款名补进路径，避免块失去归属。
|
|||
|
|
纯「目录」块直接丢弃。
|
|||
|
|
"""
|
|||
|
|
|
|||
|
|
import json
|
|||
|
|
import re
|
|||
|
|
from pathlib import Path
|
|||
|
|
|
|||
|
|
HEADING = re.compile(r"^(#{1,6})\s+(.+?)\s*$")
|
|||
|
|
CLAUSE = re.compile(r"^第[一二三四五六七八九十百]+条")
|
|||
|
|
|
|||
|
|
# 每个文件的入库配置：集合、编号前缀、可见性、版本与生效日期（取自文档头部）
|
|||
|
|
SOURCES: dict[str, dict[str, str]] = {
|
|||
|
|
"policy/个人投资者适当性管理指南.md": {
|
|||
|
|
"collection": "fin_policy_collection", "prefix": "POL-AST", "visibility": "public",
|
|||
|
|
"version": "V3.2", "effective_date": "2024-01-15", "doc_no": "JR-AST-2024-001",
|
|||
|
|
"tags": "适当性,C1-C5,R1-R5,双录,冷静期",
|
|||
|
|
},
|
|||
|
|
# 反洗钱合规操作手册**不入客服知识库**：本业务只做公募基金，不涉及银行转账与资金划付，
|
|||
|
|
# 反洗钱属后续风控模块职责；且该手册标注「内部机密」、第十六条禁止向客户透露可疑交易
|
|||
|
|
# 信息，混入面向客户的知识库存在制度性冲突。
|
|||
|
|
"policy/理财产品销售管理办法.md": {
|
|||
|
|
"collection": "fin_policy_collection", "prefix": "POL-SPM", "visibility": "public",
|
|||
|
|
"version": "V3.0", "effective_date": "2024-02-01", "doc_no": "JR-SPM-2024-003",
|
|||
|
|
"tags": "理财产品销售,双录,冷静期,费率,投诉",
|
|||
|
|
},
|
|||
|
|
"product/个人理财产品手册.md": {
|
|||
|
|
"collection": "fin_product_collection", "prefix": "PROD", "visibility": "public",
|
|||
|
|
"version": "V2.8", "effective_date": "", "doc_no": "",
|
|||
|
|
"tags": "基金,银行理财,保险,费率,申赎",
|
|||
|
|
},
|
|||
|
|
# 只取「客户分层标准」与「各层级专属权益」两章：家族信托、资产配置流程、客户经理
|
|||
|
|
# 考核指标、隐私应急预案属内部管理内容，客户咨询用不到，不入库。
|
|||
|
|
"product/高净值客户服务规范.md": {
|
|||
|
|
"collection": "fin_product_collection", "prefix": "HNW", "visibility": "public",
|
|||
|
|
"version": "V2.1", "effective_date": "", "doc_no": "",
|
|||
|
|
"tags": "高净值,VIP分级,层级权益,费率优惠",
|
|||
|
|
"allow_chapters": ["一、", "二、"],
|
|||
|
|
},
|
|||
|
|
"company/企业信息.md": {
|
|||
|
|
"collection": "fin_faq_collection", "prefix": "COMP", "visibility": "public",
|
|||
|
|
"version": "", "effective_date": "", "doc_no": "",
|
|||
|
|
"tags": "公司信息,金融牌照,资质",
|
|||
|
|
},
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
|
|||
|
|
def leaf_split_points(marks: list[tuple[int, int, str]]) -> set[int]:
|
|||
|
|
"""叶子标题的行号集合：其后没有更深标题的标题。"""
|
|||
|
|
points: set[int] = set()
|
|||
|
|
for position, (index, level, _title) in enumerate(marks):
|
|||
|
|
following = marks[position + 1] if position + 1 < len(marks) else None
|
|||
|
|
if following is not None and following[1] > level:
|
|||
|
|
continue # 有子标题，不是叶子
|
|||
|
|
points.add(index)
|
|||
|
|
return points
|
|||
|
|
|
|||
|
|
|
|||
|
|
def chunk_markdown(text: str) -> list[dict[str, str]]:
|
|||
|
|
lines = text.splitlines()
|
|||
|
|
marks: list[tuple[int, int, str]] = []
|
|||
|
|
for index, line in enumerate(lines):
|
|||
|
|
match = HEADING.match(line)
|
|||
|
|
if match:
|
|||
|
|
marks.append((index, len(match.group(1)), match.group(2).strip()))
|
|||
|
|
marks_by_line = {index: (level, title) for index, level, title in marks}
|
|||
|
|
split_points = leaf_split_points(marks)
|
|||
|
|
|
|||
|
|
stack: dict[int, str] = {}
|
|||
|
|
chunks: list[dict[str, str]] = []
|
|||
|
|
buffer: list[str] = []
|
|||
|
|
meta: dict[str, str] | None = None
|
|||
|
|
last_clause = ""
|
|||
|
|
|
|||
|
|
def has_body() -> bool:
|
|||
|
|
return any(not HEADING.match(line) and line.strip() for line in buffer)
|
|||
|
|
|
|||
|
|
def flush() -> None:
|
|||
|
|
nonlocal buffer, meta
|
|||
|
|
if meta is not None and has_body():
|
|||
|
|
body = "\n".join(buffer).strip()
|
|||
|
|
if body:
|
|||
|
|
chunks.append({**meta, "content": body})
|
|||
|
|
buffer = []
|
|||
|
|
|
|||
|
|
for index, line in enumerate(lines):
|
|||
|
|
mark = marks_by_line.get(index)
|
|||
|
|
if mark is not None:
|
|||
|
|
level, title = mark
|
|||
|
|
stack[level] = title
|
|||
|
|
for deeper in [key for key in stack if key > level]:
|
|||
|
|
del stack[deeper]
|
|||
|
|
if CLAUSE.match(title):
|
|||
|
|
last_clause = title
|
|||
|
|
if index in split_points:
|
|||
|
|
flush()
|
|||
|
|
# 所属章取「最近的上级标题」，而不是最外层文档标题（sorted 后取首个会拿到 h1）
|
|||
|
|
ancestors = [key for key in stack if key < level]
|
|||
|
|
chapter = stack[max(ancestors)] if ancestors else ""
|
|||
|
|
path = [stack[key] for key in sorted(stack) if key <= level]
|
|||
|
|
if not CLAUSE.match(title) and last_clause and last_clause not in path:
|
|||
|
|
path = [item for item in (chapter, last_clause) if item] + [title]
|
|||
|
|
meta = {"title": " · ".join(path), "chapter": chapter, "section": title}
|
|||
|
|
buffer.append(line)
|
|||
|
|
flush()
|
|||
|
|
return [chunk for chunk in chunks if chunk["section"].strip() != "目录"]
|
|||
|
|
|
|||
|
|
|
|||
|
|
def chunk_qa(text: str) -> list[dict[str, str]]:
|
|||
|
|
chunks: list[dict[str, str]] = []
|
|||
|
|
for line in text.splitlines():
|
|||
|
|
line = line.strip()
|
|||
|
|
if not line or "\t" not in line:
|
|||
|
|
continue
|
|||
|
|
question, _, answer = line.partition("\t")
|
|||
|
|
chunks.append({
|
|||
|
|
"title": question.strip(),
|
|||
|
|
"chapter": "高频问答",
|
|||
|
|
"section": question.strip(),
|
|||
|
|
"content": f"问：{question.strip()}\n答：{answer.strip()}",
|
|||
|
|
})
|
|||
|
|
return chunks
|
|||
|
|
|
|||
|
|
|
|||
|
|
TABLE_ROW = re.compile(r"^\|(.+)\|\s*$")
|
|||
|
|
LEADING_NUMBER = re.compile(r"^\d+(?:\.\d+)*\s*")
|
|||
|
|
|
|||
|
|
|
|||
|
|
def expand_table_rows(chunk: dict[str, str], parent_id: str) -> list[dict[str, object]]:
|
|||
|
|
"""把 Markdown 表格的每一行拆成自解释的小块（父块照旧保留）。
|
|||
|
|
|
|||
|
|
为什么需要：现在的粒度是"一个叶子标题 = 一块"，产品手册里就是**整个产品小节**
|
|||
|
|
（表格 + 说明）成一块。于是客户问「起投多少」和问「风险高吗」命中同一块、拿到
|
|||
|
|
**完全相同**的整节内容——客户会觉得客服没听懂问题，只是把说明书重贴一遍。
|
|||
|
|
顺带地，整节几百字的向量是"整节的混合语义"，与"起投多少"这种具体小问题相似度
|
|||
|
|
天然偏低（实测该问句向量 top1 只有 0.6291，够不到 0.75 门槛）。
|
|||
|
|
|
|||
|
|
小块必须**自解释**：只回「1万元」客户不知道说的是哪个产品，所以带上产品名与行标签。
|
|||
|
|
父块保留，客户问「这个产品怎么样」时仍要能拿到完整一节。
|
|||
|
|
|
|||
|
|
## 2026-09-15 修掉的 bug：表头被当成数据行
|
|||
|
|
|
|||
|
|
原实现用「**第一个非分隔行**」当表头（`if not header: header = cells`），而 `header`
|
|||
|
|
从不重置。于是**同一节里出现第二张表格时，它的表头行被当成数据行**，产出形如
|
|||
|
|
「第九条 问卷内容及评分标准：选项 分值」的**零信息量碎片**：
|
|||
|
|
《个人投资者适当性管理指南》第九条下有 16 张问卷表格 → 15 条碎片，且**正文逐字相同**。
|
|||
|
|
检索时它们必然互相打平（实测把「风险评估问卷怎么评分」的 top1/次优差压到 **0.002**，
|
|||
|
|
客服按"中置信需领先 ≥0.07"判并列 → 转人工），把真正有内容的块挤到第 5 名。
|
|||
|
|
|
|||
|
|
修法：markdown 表格的表头**只可能是紧邻分隔行 `|---|---|` 之前的那一行**，所以按分隔行
|
|||
|
|
认表头，用 `prev` 延迟一行判断。修后块数 636 → 617，正文完全相同的组从 1 组 15 块降到 0。
|
|||
|
|
"""
|
|||
|
|
blocks: list[dict[str, object]] = []
|
|||
|
|
name = LEADING_NUMBER.sub("", chunk["section"]).strip() or chunk["section"]
|
|||
|
|
|
|||
|
|
def emit(cells: list[str]) -> None:
|
|||
|
|
if len(cells) < 2:
|
|||
|
|
return
|
|||
|
|
label, value = cells[0], cells[1]
|
|||
|
|
if not label or not value:
|
|||
|
|
return
|
|||
|
|
blocks.append({
|
|||
|
|
"title": f"{chunk['title']} · {label}",
|
|||
|
|
"chapter": chunk["chapter"],
|
|||
|
|
"section": f"{name} · {label}",
|
|||
|
|
"content": f"{name}：{label} {value}",
|
|||
|
|
"parent_id": parent_id,
|
|||
|
|
})
|
|||
|
|
|
|||
|
|
prev: list[str] | None = None
|
|||
|
|
for line in chunk["content"].splitlines():
|
|||
|
|
match = TABLE_ROW.match(line.strip())
|
|||
|
|
if not match:
|
|||
|
|
continue
|
|||
|
|
cells = [cell.strip() for cell in match.group(1).split("|")]
|
|||
|
|
if all(set(cell) <= {"-", ":", " "} for cell in cells):
|
|||
|
|
# 分隔行 |---|：紧邻它之前的那一行（`prev`）是**表头**，不能当数据行 → 丢弃。
|
|||
|
|
prev = None
|
|||
|
|
continue
|
|||
|
|
if prev is not None:
|
|||
|
|
emit(prev) # 没被分隔行认领为表头的行 = 数据行
|
|||
|
|
prev = cells
|
|||
|
|
if prev is not None:
|
|||
|
|
emit(prev) # 收尾：最后一行也要处理（没有分隔行收尾的表格）
|
|||
|
|
return blocks
|
|||
|
|
|
|||
|
|
|
|||
|
|
def assert_no_duplicate_contents(records: list[dict[str, object]]) -> None:
|
|||
|
|
"""自带守卫：**正文完全相同的块必须为 0**，否则直接失败退出、不生成 jsonl。
|
|||
|
|
|
|||
|
|
为什么用这一条当守卫：表头被误当数据行时的直接后果就是"**多张表格产出逐字相同的块**"
|
|||
|
|
（第九条那 16 张问卷表 → 15 条一模一样的「…：选项 分值」）。这类块在检索里必然互相
|
|||
|
|
打平，把 top1/次优差压到 0.07 门槛之下（实测 0.002）→ 客服判并列转人工。
|
|||
|
|
本脚本是**一次性灌库脚本**、没有单测覆盖（这正是该 bug 活下来的原因），
|
|||
|
|
所以把守卫放在脚本自己的执行路径上：**每次重灌都会跑一遍**。
|
|||
|
|
|
|||
|
|
为什么不是"块长度下限"：短块本身是设计的一部分（「评审标准：管理人资质 15%」13 字，
|
|||
|
|
但它是真实的数据行、是有效答案）。**内容逐字重复**才是缺陷特征，长度不是。
|
|||
|
|
"""
|
|||
|
|
seen: dict[str, list[str]] = {}
|
|||
|
|
for record in records:
|
|||
|
|
seen.setdefault(str(record["content"]), []).append(str(record["doc_id"]))
|
|||
|
|
duplicated = {content: ids for content, ids in seen.items() if len(ids) > 1}
|
|||
|
|
if duplicated:
|
|||
|
|
detail = "\n".join(
|
|||
|
|
f" {len(ids)} 份：{content[:60]!r} → {ids[:6]}"
|
|||
|
|
for content, ids in list(duplicated.items())[:5]
|
|||
|
|
)
|
|||
|
|
raise SystemExit(
|
|||
|
|
f"知识块自检失败：有 {len(duplicated)} 组正文完全相同的块。\n"
|
|||
|
|
"这类块在检索里必然互相打平（把 top1/次优差压到 0.07 之下 → 客服转人工），"
|
|||
|
|
"通常是**表格表头被当成了数据行**（见 `expand_table_rows` 的 docstring）。\n"
|
|||
|
|
f"{detail}\n已中止，未写入 jsonl。"
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
|
|||
|
|
records: list[dict[str, object]] = []
|
|||
|
|
for relative, config in SOURCES.items():
|
|||
|
|
text = (Path("knowledge") / relative).read_text(encoding="utf-8")
|
|||
|
|
chunks = chunk_markdown(text)
|
|||
|
|
# 章节白名单：只保留指定章下的块（用于剔除内部管理章节，如高净值规范只留分级与权益）
|
|||
|
|
allowed = config.get("allow_chapters")
|
|||
|
|
if isinstance(allowed, list):
|
|||
|
|
chunks = [
|
|||
|
|
chunk for chunk in chunks
|
|||
|
|
if any(chunk["chapter"].startswith(prefix) for prefix in allowed)
|
|||
|
|
]
|
|||
|
|
for order, chunk in enumerate(chunks, 1):
|
|||
|
|
parent_id = f"{config['prefix']}-{order:03d}"
|
|||
|
|
records.append({
|
|||
|
|
"doc_id": parent_id,
|
|||
|
|
"collection": config["collection"],
|
|||
|
|
"title": chunk["title"],
|
|||
|
|
"content": chunk["content"],
|
|||
|
|
"chapter": chunk["chapter"],
|
|||
|
|
"section": chunk["section"],
|
|||
|
|
"tags": config["tags"],
|
|||
|
|
"doc_no": config["doc_no"],
|
|||
|
|
"version": config["version"],
|
|||
|
|
"effective_date": config["effective_date"],
|
|||
|
|
"expire_date": "", "source_url": "", "reviewer": "",
|
|||
|
|
"source_file": relative,
|
|||
|
|
"visibility": config["visibility"],
|
|||
|
|
"chars": len(chunk["content"]),
|
|||
|
|
})
|
|||
|
|
# 行级子块：挂在父块 doc_id 下（PROD-007-01 这种），父块编号不受新增子块影响，
|
|||
|
|
# 因此反复重跑本脚本得到的 doc_id 是稳定的。
|
|||
|
|
for row_order, block in enumerate(expand_table_rows(chunk, parent_id), 1):
|
|||
|
|
records.append({
|
|||
|
|
"doc_id": f"{parent_id}-{row_order:02d}",
|
|||
|
|
"collection": config["collection"],
|
|||
|
|
"title": block["title"],
|
|||
|
|
"content": block["content"],
|
|||
|
|
"chapter": block["chapter"],
|
|||
|
|
"section": block["section"],
|
|||
|
|
"tags": config["tags"],
|
|||
|
|
"doc_no": config["doc_no"],
|
|||
|
|
"version": config["version"],
|
|||
|
|
"effective_date": config["effective_date"],
|
|||
|
|
"expire_date": "", "source_url": "", "reviewer": "",
|
|||
|
|
"source_file": relative,
|
|||
|
|
"visibility": config["visibility"],
|
|||
|
|
"chars": len(str(block["content"])),
|
|||
|
|
})
|
|||
|
|
|
|||
|
|
for order, chunk in enumerate(
|
|||
|
|
chunk_qa((Path("knowledge") / "faq/高频问答对.txt").read_text(encoding="utf-8")), 1
|
|||
|
|
):
|
|||
|
|
records.append({
|
|||
|
|
"doc_id": f"FAQ-{order:04d}",
|
|||
|
|
"collection": "fin_faq_collection",
|
|||
|
|
"title": chunk["title"], "content": chunk["content"],
|
|||
|
|
"chapter": chunk["chapter"], "section": chunk["section"],
|
|||
|
|
"tags": "高频问答,FAQ",
|
|||
|
|
"doc_no": "", "version": "", "effective_date": "", "expire_date": "",
|
|||
|
|
"source_url": "", "reviewer": "",
|
|||
|
|
"source_file": "faq/高频问答对.txt", "visibility": "public",
|
|||
|
|
"chars": len(chunk["content"]),
|
|||
|
|
})
|
|||
|
|
|
|||
|
|
assert_no_duplicate_contents(records)
|
|||
|
|
|
|||
|
|
(Path("knowledge") / "_chunks.jsonl").write_text(
|
|||
|
|
"\n".join(json.dumps(record, ensure_ascii=False) for record in records), encoding="utf-8"
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
lines: list[str] = [f"总块数：{len(records)}\n"]
|
|||
|
|
by_collection: dict[str, list[dict[str, object]]] = {}
|
|||
|
|
for record in records:
|
|||
|
|
by_collection.setdefault(str(record["collection"]), []).append(record)
|
|||
|
|
for name, group in sorted(by_collection.items()):
|
|||
|
|
sizes = sorted(int(record["chars"]) for record in group)
|
|||
|
|
lines.append(
|
|||
|
|
f"{name}: {len(group)} 块，字符数 最小 {sizes[0]} / 中位 {sizes[len(sizes)//2]} / 最大 {sizes[-1]}"
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
lines.append("\n各文件块数：")
|
|||
|
|
by_file: dict[str, int] = {}
|
|||
|
|
for record in records:
|
|||
|
|
by_file[str(record["source_file"])] = by_file.get(str(record["source_file"]), 0) + 1
|
|||
|
|
for name, count in sorted(by_file.items()):
|
|||
|
|
lines.append(f" {name}: {count}")
|
|||
|
|
|
|||
|
|
over = [record for record in records if int(record["chars"]) > 1200]
|
|||
|
|
lines.append(f"\n超过 1200 字符的块：{len(over)} 个")
|
|||
|
|
for record in over[:10]:
|
|||
|
|
lines.append(f" {record['doc_id']} {record['chars']} 字符 {str(record['title'])[:64]}")
|
|||
|
|
|
|||
|
|
lines.append("\n反洗钱手册的块标题（核对「第一类」归属是否带上了第十三条）：")
|
|||
|
|
for record in records:
|
|||
|
|
if str(record["doc_id"]).startswith("POL-AML"):
|
|||
|
|
lines.append(f" {record['doc_id']} {int(record['chars']):>5} 字符 {str(record['title'])[:70]}")
|
|||
|
|
|
|||
|
|
Path("_chunks_report.txt").write_text("\n".join(lines), encoding="utf-8")
|
|||
|
|
print(f"已生成 {len(records)} 块 → knowledge/_chunks.jsonl；报告见 _chunks_report.txt")
|