53d9e003af
- 回忆录：事实边界补充允许清单；传记文体示例与 JSON 叙事要求对齐 - default 职业提示 occupation_context；cadre/military 退休语境 - GET 章节读路径零写入，prepare_chapter_read_view + markdown_for_response - 文本归一抽到 core/text_normalize；移除弃用 reply 策略与 recompose_chapters_for_story - ConversationService：WS 连接/用户段落/结束对话；对外错误固定文案 - 测试：HTTP 脱敏契约、章节读视图、occupation 与 background_voice
73 lines
2.2 KiB
Python
73 lines
2.2 KiB
Python
"""口述/聊天输入的确定性规则与可选 LLM 纠错（供 conversation 与 memoir 共用）。"""
|
||
|
||
from __future__ import annotations
|
||
|
||
import json
|
||
import re
|
||
from typing import Any
|
||
|
||
from app.core.langchain_llm import invoke_json_object
|
||
from app.core.logging import get_logger
|
||
from app.features.memoir.memoir_images.json_payload import extract_json_payload
|
||
|
||
logger = get_logger(__name__)
|
||
|
||
_MEI_KANSHANG_RE = re.compile(r"美(?=看上[我你他她它])")
|
||
|
||
|
||
def apply_oral_rules(text: str) -> str:
|
||
"""确定性规则；保守替换，仅覆盖高频误听误打模式。"""
|
||
s = text or ""
|
||
if not s:
|
||
return s
|
||
return _MEI_KANSHANG_RE.sub("没", s)
|
||
|
||
|
||
def llm_normalize_text(
|
||
text: str,
|
||
llm: Any,
|
||
*,
|
||
max_input_chars: int,
|
||
max_tokens: int,
|
||
agent_name: str,
|
||
) -> str | None:
|
||
"""仅修正明显错字与同音字，不增事实；失败返回 None。"""
|
||
if not llm or not (text or "").strip():
|
||
return None
|
||
t = (text or "").strip()
|
||
if len(t) > max_input_chars:
|
||
logger.debug(
|
||
"event=llm_text_normalize_skip reason=input_too_long len={} max={}",
|
||
len(t),
|
||
max_input_chars,
|
||
)
|
||
return None
|
||
prompt = f"""你是口述转写纠错助手。只修正明显的同音错别字、别字与标点，使句子通顺可读。
|
||
禁止增加事实、不补充细节、不摘要、不改写句式风格；不得新增人名、地名、数字、事件。
|
||
若原文已通顺或无法确定错误，则照抄输入。
|
||
|
||
【用户口述】
|
||
{t}
|
||
|
||
**JSON 输出**：只输出一个合法 JSON 对象。
|
||
{{"normalized_text": "纠错后的完整文本（与输入等意，仅修错字与标点）"}}
|
||
|
||
只输出 JSON，不要其它文字。"""
|
||
try:
|
||
raw = invoke_json_object(
|
||
llm,
|
||
prompt,
|
||
max_tokens=max_tokens,
|
||
agent=agent_name,
|
||
)
|
||
data = json.loads(extract_json_payload(raw))
|
||
if not isinstance(data, dict):
|
||
return None
|
||
out = (data.get("normalized_text") or "").strip()
|
||
if not out:
|
||
return None
|
||
return out
|
||
except Exception as e:
|
||
logger.warning("llm_normalize_text 失败 {}: {}", agent_name, e)
|
||
return None
|