feat(knowledge): 可跳转 wikilink + 真实相关 note + 一对话多页
- [[wikilink]] 解析器:note id / vault_path / 标题 / vault 元页 / missing
- 前端 MarkdownRenderer 把非数字 [[...]] 渲染成可点链接,元页弹窗查看,缺失置灰
- vault 脚手架补建项目 hub 页,三个结构性链接(index/taxonomy/hub)始终可跳
- capture 时按标题+摘要+区分性标签检索同主题 note,注入真实 [[标题]] 到 Related + 记 related 图谱边
- LLM 提取支持 notes[] 数组,一次对话拆 1~4 页并按标题互链(multi_note_enabled 开关)
- 新增接口 POST /resolve、GET /notes/{id}/wikilinks、GET /vault-page
- 新增配置 related_notes_enabled / related_notes_limit / multi_note_enabled
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
1 parent
92a46003f8
commit
df3fac1032
13 files changed
+668
-72
No files matched your search
+161
-52
@@ -40,21 +40,30 @@ _SYSTEM_PROMPT = """\
|
||||
references(外部来源汇总)、decision(架构/设计决策)、journal(会话纪要)。
|
||||
- 用中文输出。
|
||||
|
||||
一次对话可能只讲一个主题,也可能覆盖多个相互独立的主题。请把它拆成 1~4 页知识:
|
||||
- 默认只产出 **1 页**;只有当对话明确包含**多个彼此独立、可各自成文**的主题时才拆成多页。
|
||||
- 每一页聚焦单一主题,标题与 summary 必须彼此区分,不要把同一结论拆到多页。
|
||||
- 不值得沉淀时返回空的 notes 数组。
|
||||
|
||||
只输出一个 JSON 对象,不要任何额外文字或 Markdown 代码块,结构如下:
|
||||
{
|
||||
"should_ingest": true,
|
||||
"reason": "为什么值得/不值得沉淀",
|
||||
"title": "简洁的知识标题(不超过 40 字)",
|
||||
"summary": "1-2 句话概括这页知识",
|
||||
"category": "synthesis",
|
||||
"context": "问题背景或触发场景,1-3 句",
|
||||
"findings": ["结论/要点(陈述式,可含 ^[inferred])", "..."],
|
||||
"reasoning": "为什么成立、取舍、不确定性",
|
||||
"implications": ["后续建议/风险/下一步", "..."],
|
||||
"tags": ["标签1", "标签2"],
|
||||
"entities": [{"name": "实体名", "type": "technology|concept|person|org|product|other"}],
|
||||
"relations": [{"from": "实体A", "to": "实体B", "type": "uses|relates_to|part_of|depends_on"}],
|
||||
"confidence": 0.0
|
||||
"notes": [
|
||||
{
|
||||
"title": "简洁的知识标题(不超过 40 字)",
|
||||
"summary": "1-2 句话概括这页知识",
|
||||
"category": "synthesis",
|
||||
"context": "问题背景或触发场景,1-3 句",
|
||||
"findings": ["结论/要点(陈述式,可含 ^[inferred])", "..."],
|
||||
"reasoning": "为什么成立、取舍、不确定性",
|
||||
"implications": ["后续建议/风险/下一步", "..."],
|
||||
"tags": ["标签1", "标签2"],
|
||||
"entities": [{"name": "实体名", "type": "technology|concept|person|org|product|other"}],
|
||||
"relations": [{"from": "实体A", "to": "实体B", "type": "uses|relates_to|part_of|depends_on"}],
|
||||
"confidence": 0.0
|
||||
}
|
||||
]
|
||||
}"""
|
||||
|
||||
|
||||
@@ -128,7 +137,78 @@ def _render_body(data: dict[str, Any], title: str, related: list[str], sources:
|
||||
)
|
||||
|
||||
|
||||
async def extract_thread_llm(
|
||||
def _notes_from_data(data: dict[str, Any]) -> list[dict[str, Any]]:
|
||||
"""Normalize the LLM JSON into a list of per-note dicts.
|
||||
|
||||
Accepts the multi-note shape ``{"notes": [...]}`` as well as the legacy
|
||||
single-note shape (``{"title": ..., "findings": ...}``) for backward
|
||||
compatibility. Notes without any title/findings are dropped.
|
||||
"""
|
||||
raw_notes = data.get("notes")
|
||||
if isinstance(raw_notes, list):
|
||||
candidates = [n for n in raw_notes if isinstance(n, dict)]
|
||||
elif data.get("title") or data.get("findings") or data.get("context"):
|
||||
candidates = [data] # legacy single-object output
|
||||
else:
|
||||
candidates = []
|
||||
return [n for n in candidates if str(n.get("title") or "").strip() or n.get("findings")]
|
||||
|
||||
|
||||
def _build_note_draft(
|
||||
note_data: dict[str, Any],
|
||||
*,
|
||||
thread_id: str,
|
||||
thread_title: str | None,
|
||||
turns: list[dict[str, str]],
|
||||
title_override: str | None,
|
||||
tags: list[str] | None,
|
||||
project_name: str | None,
|
||||
sources: list[SourceDraft],
|
||||
source_key_suffix: str = "",
|
||||
) -> NoteDraft:
|
||||
"""Render one note dict into a :class:`NoteDraft`."""
|
||||
category = str(note_data.get("category") or "synthesis").strip().lower()
|
||||
if category not in _VALID_CATEGORIES:
|
||||
category = "synthesis"
|
||||
|
||||
final_title = (title_override or "").strip() or str(note_data.get("title") or "").strip() or extractor._auto_title(thread_title, turns)
|
||||
summary = str(note_data.get("summary") or "").strip()
|
||||
related = extractor.related_links(project_name)
|
||||
body = _render_body(note_data, final_title, related, sources)
|
||||
|
||||
base_tags = list(tags or [])
|
||||
llm_tags = note_data.get("tags") if isinstance(note_data.get("tags"), list) else []
|
||||
for tag in [*llm_tags, project_name or "deerflow", "knowledge-base"]:
|
||||
tag = str(tag).strip()
|
||||
if tag and tag not in base_tags:
|
||||
base_tags.append(tag)
|
||||
|
||||
try:
|
||||
confidence = float(note_data.get("confidence") or 0.7)
|
||||
except (TypeError, ValueError):
|
||||
confidence = 0.7
|
||||
|
||||
entities = note_data.get("entities") if isinstance(note_data.get("entities"), list) else []
|
||||
relations = note_data.get("relations") if isinstance(note_data.get("relations"), list) else []
|
||||
|
||||
return NoteDraft(
|
||||
title=final_title,
|
||||
summary=summary or final_title,
|
||||
content_md=body,
|
||||
category=category,
|
||||
source_type="thread",
|
||||
source_id=thread_id,
|
||||
tags=base_tags,
|
||||
confidence=max(0.0, min(confidence, 1.0)),
|
||||
related=related,
|
||||
sources=sources,
|
||||
entities=[e for e in entities if isinstance(e, dict) and e.get("name")],
|
||||
relations=[r for r in relations if isinstance(r, dict) and r.get("from") and r.get("to")],
|
||||
source_key=f"thread:{thread_id}{source_key_suffix}",
|
||||
)
|
||||
|
||||
|
||||
async def extract_thread_llm_multi(
|
||||
messages: list[dict[str, Any]],
|
||||
*,
|
||||
thread_id: str,
|
||||
@@ -141,15 +221,19 @@ async def extract_thread_llm(
|
||||
max_messages: int = 80,
|
||||
model_name: str | None = None,
|
||||
max_input_chars: int = 12000,
|
||||
) -> NoteDraft | None:
|
||||
"""Distill a thread into a :class:`NoteDraft` via the LLM.
|
||||
allow_multi: bool = True,
|
||||
max_notes: int = 4,
|
||||
) -> list[NoteDraft]:
|
||||
"""Distill a thread into one *or several* cross-linkable knowledge notes.
|
||||
|
||||
Returns ``None`` when there is nothing to sediment **or** the LLM path
|
||||
fails — callers should fall back to the rule-based extractor.
|
||||
The LLM may split a conversation that covers multiple independent topics into
|
||||
several declarative notes. Returns ``[]`` when there is nothing to sediment
|
||||
or the LLM path fails — callers should fall back to the rule-based extractor.
|
||||
When ``allow_multi`` is false only the first note is kept.
|
||||
"""
|
||||
turns = extractor.split_turns(messages, max_messages=max_messages)
|
||||
if not turns:
|
||||
return None
|
||||
return []
|
||||
sources = sources or []
|
||||
|
||||
try:
|
||||
@@ -168,47 +252,72 @@ async def extract_thread_llm(
|
||||
data = _parse_json(raw)
|
||||
except Exception:
|
||||
logger.exception("Knowledge LLM extraction failed for thread %s; using rule-based fallback", thread_id)
|
||||
return None
|
||||
return []
|
||||
|
||||
if not data:
|
||||
return None
|
||||
return []
|
||||
|
||||
category = str(data.get("category") or "synthesis").strip().lower()
|
||||
if category not in _VALID_CATEGORIES:
|
||||
category = "synthesis"
|
||||
note_dicts = _notes_from_data(data)
|
||||
if not note_dicts:
|
||||
return []
|
||||
if not allow_multi:
|
||||
note_dicts = note_dicts[:1]
|
||||
else:
|
||||
note_dicts = note_dicts[: max(1, max_notes)]
|
||||
|
||||
final_title = (title or "").strip() or str(data.get("title") or "").strip() or extractor._auto_title(thread_title, turns)
|
||||
summary = str(data.get("summary") or "").strip()
|
||||
related = extractor.related_links(project_name)
|
||||
body = _render_body(data, final_title, related, sources)
|
||||
drafts: list[NoteDraft] = []
|
||||
for i, nd in enumerate(note_dicts):
|
||||
# The user-supplied title override only applies to a single-note result;
|
||||
# multi-note splits keep each note's own LLM title.
|
||||
override = title if (len(note_dicts) == 1) else None
|
||||
suffix = "" if len(note_dicts) == 1 else f"#{i}"
|
||||
drafts.append(
|
||||
_build_note_draft(
|
||||
nd,
|
||||
thread_id=thread_id,
|
||||
thread_title=thread_title,
|
||||
turns=turns,
|
||||
title_override=override,
|
||||
tags=tags,
|
||||
project_name=project_name,
|
||||
sources=sources,
|
||||
source_key_suffix=suffix,
|
||||
)
|
||||
)
|
||||
return drafts
|
||||
|
||||
base_tags = list(tags or [])
|
||||
llm_tags = data.get("tags") if isinstance(data.get("tags"), list) else []
|
||||
for tag in [*llm_tags, project_name or "deerflow", "knowledge-base"]:
|
||||
tag = str(tag).strip()
|
||||
if tag and tag not in base_tags:
|
||||
base_tags.append(tag)
|
||||
|
||||
try:
|
||||
confidence = float(data.get("confidence") or 0.7)
|
||||
except (TypeError, ValueError):
|
||||
confidence = 0.7
|
||||
async def extract_thread_llm(
|
||||
messages: list[dict[str, Any]],
|
||||
*,
|
||||
thread_id: str,
|
||||
thread_title: str | None = None,
|
||||
mode: str = "summary",
|
||||
title: str | None = None,
|
||||
tags: list[str] | None = None,
|
||||
project_name: str | None = "deerflow",
|
||||
sources: list[SourceDraft] | None = None,
|
||||
max_messages: int = 80,
|
||||
model_name: str | None = None,
|
||||
max_input_chars: int = 12000,
|
||||
) -> NoteDraft | None:
|
||||
"""Distill a thread into a single :class:`NoteDraft` (backward-compatible).
|
||||
|
||||
entities = data.get("entities") if isinstance(data.get("entities"), list) else []
|
||||
relations = data.get("relations") if isinstance(data.get("relations"), list) else []
|
||||
|
||||
return NoteDraft(
|
||||
title=final_title,
|
||||
summary=summary or final_title,
|
||||
content_md=body,
|
||||
category=category,
|
||||
source_type="thread",
|
||||
source_id=thread_id,
|
||||
tags=base_tags,
|
||||
confidence=max(0.0, min(confidence, 1.0)),
|
||||
related=related,
|
||||
Thin wrapper over :func:`extract_thread_llm_multi` that returns the first
|
||||
note, or ``None`` when nothing was produced.
|
||||
"""
|
||||
drafts = await extract_thread_llm_multi(
|
||||
messages,
|
||||
thread_id=thread_id,
|
||||
thread_title=thread_title,
|
||||
mode=mode,
|
||||
title=title,
|
||||
tags=tags,
|
||||
project_name=project_name,
|
||||
sources=sources,
|
||||
entities=[e for e in entities if isinstance(e, dict) and e.get("name")],
|
||||
relations=[r for r in relations if isinstance(r, dict) and r.get("from") and r.get("to")],
|
||||
source_key=f"thread:{thread_id}",
|
||||
max_messages=max_messages,
|
||||
model_name=model_name,
|
||||
max_input_chars=max_input_chars,
|
||||
allow_multi=False,
|
||||
)
|
||||
return drafts[0] if drafts else None
|
||||
Reference in new issue
Block a user