Create-knowledge-find-decode/creation_knowledge/stages/split.py

"""拆分：把帖子拆成一个或多个 What/Why/How 知识片段。"""
from __future__ import annotations

from typing import Optional

from creation_knowledge.integrations.llm import ChatFn, default_chat
from creation_knowledge.models import ExtractedContent, KnowledgeItem, Post
from creation_knowledge.prompts import load_prompt
from creation_knowledge.stages._common import content_for_llm, norm_text, norm_types

SYSTEM = "你是创作知识拆分助手，原文有什么提什么，不编造。"


def _to_item(raw: dict) -> Optional[KnowledgeItem]:
    what = norm_text(raw.get("what"))
    why = norm_text(raw.get("why"))
    how = norm_text(raw.get("how"))
    # knowledge_types 以非空字段为准（模型给的若不一致，用实际有内容的对齐）
    types = norm_types(raw.get("knowledge_types"))
    actual = [t for t, v in (("what", what), ("why", why), ("how", how)) if v]
    types = [t for t in types if t in actual] or actual
    if not types:
        return None  # 三个都空，丢弃
    title = norm_text(raw.get("title")) or (what or why or how or "")[:20]
    evidence = [e for e in (raw.get("evidence") or []) if norm_text(e)]
    return KnowledgeItem(
        title=title, knowledge_types=types, what=what, why=why, how=how,
        evidence=[str(e).strip() for e in evidence],
    )


def split_post(
    post: Post,
    content: ExtractedContent,
    *,
    chat: Optional[ChatFn] = None,
    env_file: str = ".env",
) -> list[KnowledgeItem]:
    chat = chat or default_chat(env_file)
    user = load_prompt("split").format(
        title=post.title or "(无)",
        topics="、".join(post.topic_list) or "(无)",
        content=content_for_llm(post, content) or "(空)",
    )
    data = chat(SYSTEM, user)
    items = [_to_item(raw) for raw in (data.get("items") or [])]
    return [it for it in items if it is not None]