feat(knowledge): 支持文件导入沉淀知识,知识图谱可视化随主题切换

- 后端新增 /api/knowledge/ingest/file:上传 md/txt/pdf/word/ppt/excel,
  转 Markdown 后走 wiki-capture LLM 蒸馏为陈述式知识笔记,失败回退逐字草稿
- service.capture_file + 文档专用蒸馏提示词,按主题拆分 1~4 页
- 知识图谱导出 HTML 支持 ?theme=light|dark,布局稳定后冻结,
  按度数缩放节点,悬停/点击聚焦邻居
- 前端知识库页新增「导入文件」对话框与 ingestKnowledgeFile API
- 智能体问答页与简介侧边栏 UI 优化;批量人物蒸馏脚本提取正文逻辑修正

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
吉鑫升andClaude Opus 4.8 committed 2026-06-11 10:25:27 +08:00
1 parent 17bb3715d1
commit 3845d5090b
14 files changed
+1040 -352

No files matched your search

@@ -84,6 +84,46 @@ references(外部来源汇总)、decision(架构/设计决策)、journal
}"""
_DOC_SYSTEM_PROMPT = """\
你是知识库整理专家,遵循 obsidian-wiki 的 wiki-capture 规范,把一篇**文档**提炼成\
**陈述式知识(declarative knowledge)**,而不是照抄原文。
要求:
- 只保留高价值内容:核心结论、关键事实、定义、流程、数据、决策与其依据。
- 丢弃:目录、页眉页脚、版权声明、重复的样板文字、无意义的排版噪声。
- 用自己的话重组为结构化知识,不要逐段复制原文。
- 推断内容用 ^[inferred] 标记,不确定/冲突用 ^[ambiguous] 标记。
- 分类 category 取值之一:synthesis(分析/方案/结论)、concepts(概念/框架)、\
references(外部来源汇总)、decision(架构/设计决策)、journal(纪要)。
- 用中文输出。
一篇文档可能只讲一个主题,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**;只有当文档明确包含**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。
- 文档没有可沉淀的知识时返回空的 notes 数组。
只输出一个 JSON 对象,不要任何额外文字或 Markdown 代码块,结构与对话提炼一致:
{
"should_ingest": true,
"reason": "为什么值得/不值得沉淀",
"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": "文档背景或适用场景,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
}
]
}"""
def _build_transcript(turns: list[dict[str, str]], sources: list[SourceDraft], *, max_chars: int) -> str:
parts: list[str] = []
for i, t in enumerate(turns, 1):
@@ -171,21 +211,27 @@ def _notes_from_data(data: dict[str, Any]) -> list[dict[str, Any]]:
def _build_note_draft(
note_data: dict[str, Any],
*,
thread_id: str,
thread_title: str | None,
turns: list[dict[str, str]],
source_type: str,
source_id: str | None,
source_key: str,
fallback_title: 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`."""
"""Render one note dict into a :class:`NoteDraft`.
Source-agnostic: the caller supplies ``source_type`` / ``source_id`` /
``source_key`` and a ``fallback_title`` (used when neither the user override
nor the LLM produced a usable title), so both thread and document capture
share one renderer.
"""
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)
final_title = (title_override or "").strip() or str(note_data.get("title") or "").strip() or fallback_title
summary = str(note_data.get("summary") or "").strip()
related = extractor.related_links(project_name)
body = _render_body(note_data, final_title, related, sources)
@@ -210,15 +256,15 @@ def _build_note_draft(
summary=summary or final_title,
content_md=body,
category=category,
source_type="thread",
source_id=thread_id,
source_type=source_type,
source_id=source_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}",
source_key=source_key,
)
@@ -293,6 +339,7 @@ async def extract_thread_llm_multi(
else:
note_dicts = note_dicts[: max(1, max_notes)]
fallback_title = extractor._auto_title(thread_title, turns)
drafts: list[NoteDraft] = []
for i, nd in enumerate(note_dicts):
# The user-supplied title override only applies to a single-note result;
@@ -302,14 +349,100 @@ async def extract_thread_llm_multi(
drafts.append(
_build_note_draft(
nd,
thread_id=thread_id,
thread_title=thread_title,
turns=turns,
source_type="thread",
source_id=thread_id,
source_key=f"thread:{thread_id}{suffix}",
fallback_title=fallback_title,
title_override=override,
tags=tags,
project_name=project_name,
sources=sources,
)
)
return drafts
async def extract_document_llm_multi(
text: str,
*,
doc_id: str,
doc_title: str | None = None,
title: str | None = None,
tags: list[str] | None = None,
project_name: str | None = "zncm",
sources: list[SourceDraft] | None = None,
model_name: str | None = None,
max_input_chars: int = 12000,
allow_multi: bool = True,
max_notes: int = 4,
) -> list[NoteDraft]:
"""Distill an imported **document** into one *or several* knowledge notes.
Mirrors :func:`extract_thread_llm_multi` but takes raw document text (already
converted to Markdown/plain text) instead of a conversation. Returns ``[]``
when the LLM path fails (callers fall back to a verbatim note); raises
:class:`LLMRejectedIngest` when the model deliberately judges the document
worthless. Resulting notes carry ``source_type="file"``.
"""
text = (text or "").strip()
if not text:
return []
sources = sources or []
try:
from langchain_core.messages import HumanMessage, SystemMessage
from deerflow.models import create_chat_model
model = create_chat_model(name=model_name or None, thinking_enabled=False)
body = text if len(text) <= max_input_chars else text[:max_input_chars] + "\n…(已截断)"
header = f"文档标题:{doc_title}\n\n" if doc_title else ""
prompt = [
SystemMessage(content=_DOC_SYSTEM_PROMPT + "\n\n" + WIKI_CAPTURE_GUIDANCE),
HumanMessage(content=f"以下是一篇文档,请按规范提炼为知识 JSON:\n\n{header}{body}"),
]
response = await model.ainvoke(prompt)
raw = response.content if isinstance(response.content, str) else str(response.content)
data = _parse_json(raw)
except Exception:
logger.exception("[knowledge] document %s — LLM extraction call failed; using rule-based fallback", doc_id)
return []
if not data:
logger.warning("[knowledge] document %s — LLM returned no parsable JSON; using rule-based fallback", doc_id)
return []
note_dicts = _notes_from_data(data)
if not note_dicts:
reason = str(data.get("reason") or "")[:200]
if _is_falsey(data.get("should_ingest")):
logger.warning("[knowledge] document %s SKIPPED — model judged not worth ingesting: %s", doc_id, reason)
raise LLMRejectedIngest(reason or "no knowledge value")
logger.warning(
"[knowledge] document %s — LLM produced no notes (should_ingest=%s, reason=%r); using rule-based fallback",
doc_id,
data.get("should_ingest"),
reason,
)
return []
note_dicts = note_dicts[:1] if not allow_multi else note_dicts[: max(1, max_notes)]
fallback_title = (doc_title or title or "文档知识").strip() or "文档知识"
drafts: list[NoteDraft] = []
for i, nd in enumerate(note_dicts):
override = title if (len(note_dicts) == 1) else None
suffix = "" if len(note_dicts) == 1 else f"#{i}"
drafts.append(
_build_note_draft(
nd,
source_type="file",
source_id=doc_id,
source_key=f"file:{doc_id}{suffix}",
fallback_title=fallback_title,
title_override=override,
tags=tags,
project_name=project_name,
sources=sources,
source_key_suffix=suffix,
)
)
return drafts