feat: 产品内知识库(obsidian-wiki 兼容 vault)

后端:新增自包含 deerflow.knowledge 模块(models/repository/schemas/
extractor/sources/markdown_vault/manifest/obsidian_adapter/exporter/
search/service),通过 deps.py 装配为 app.state.knowledge_service,
挂载 /api/knowledge 路由;config.yaml 增加 knowledge 配置段,
AppConfig 注册 KnowledgeConfig,ORM 注册 4 张 knowledge_* 表。

前端:新增知识库页面(KnowledgeBasePage/KnowledgeGraphPage)、
core/knowledge api/hooks/types、聊天侧 knowledge-save-trigger,
侧边栏增加「知识库」入口。

知识库为全局共享,不做 user_id 隔离,写入记录 created_by/updated_by
作为审计。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
AdministratorandClaude Opus 4.8 committed 2026-06-08 17:38:28 +08:00
1 parent 80d2db6315
commit cc99ebba81
28 files changed
+3590 -6

No files matched your search

@@ -0,0 +1,282 @@
"""KnowledgeService — high-level orchestration for the knowledge base.
Ties together the repository (DB mirror), the :class:`ObsidianWikiAdapter`
(Markdown vault + index/log/hot/manifest + graph export) and the extractor
(thread/search → :class:`NoteDraft`). The Gateway router only talks to this
service; everything obsidian-wiki specific stays inside the ``knowledge``
module.
"""
from __future__ import annotations
import logging
from pathlib import Path
from typing import Any
from deerflow.config.knowledge_config import KnowledgeConfig
from deerflow.config.runtime_paths import runtime_home
from deerflow.knowledge import extractor
from deerflow.knowledge.markdown_vault import MarkdownVault
from deerflow.knowledge.obsidian_adapter import ObsidianWikiAdapter
from deerflow.knowledge.repository import KnowledgeRepository
from deerflow.knowledge.schemas import NoteDraft, normalize_source_type, normalize_status
from deerflow.knowledge.search import search_notes
from deerflow.knowledge.sources import from_reference_batches, from_search_results
logger = logging.getLogger(__name__)
class EmptyThreadError(ValueError):
"""Raised when a thread has no sediment-able content."""
def _resolve_vault_dir(vault_dir: str) -> Path:
path = Path(vault_dir)
if path.is_absolute():
return path.resolve()
return (runtime_home() / vault_dir).resolve()
class KnowledgeService:
"""Application-facing knowledge base API."""
def __init__(self, repo: KnowledgeRepository, config: KnowledgeConfig) -> None:
self.repo = repo
self.config = config
self.project_name = config.project_name
vault_root = _resolve_vault_dir(config.vault_dir)
self.adapter = ObsidianWikiAdapter(
vault_root,
project_name=config.project_name,
export_html=config.export.graph_html_enabled,
export_json=config.export.graph_json_enabled,
)
try:
self.adapter.ensure_ready()
except Exception: # pragma: no cover - vault init best-effort
logger.exception("Failed to initialize knowledge vault at %s", vault_root)
# -- internal helpers -------------------------------------------------
async def _persist_draft(self, draft: NoteDraft, *, created_by: str | None) -> dict[str, Any]:
"""Create a DB row, write the vault file, attach sources, return note."""
note = await self.repo.create_note(
title=draft.title,
summary=draft.summary,
content_md=draft.content_md,
source_type=draft.source_type,
source_id=draft.source_id,
status=draft.status,
confidence=draft.confidence,
tags=draft.tags,
created_by=created_by,
)
note_id = note["id"]
try:
rel = self.adapter.write_note(note_id, draft, created=note["created_at"], updated=note["updated_at"], status=draft.status)
await self.repo.set_vault_path(note_id, rel)
note["vault_path"] = rel
except Exception:
logger.exception("Failed to write knowledge note %s to vault", note_id)
if draft.sources:
await self.repo.add_sources(note_id, draft.sources, created_by=created_by)
return await self.repo.get_note(note_id) or note
# -- capture ----------------------------------------------------------
async def capture_thread(
self,
*,
thread_id: str,
messages: list[dict[str, Any]],
thread_title: str | None = None,
mode: str = "summary",
title: str | None = None,
status: str = "approved",
tags: list[str] | None = None,
include_sources: bool = True,
reference_batches: list[dict[str, Any]] | None = None,
created_by: str | None = None,
skip_existing: bool = False,
) -> dict[str, Any]:
"""Sediment a thread into a knowledge note.
Returns ``{"note": <note>, "created": bool}``. Raises
:class:`EmptyThreadError` when there is nothing worth keeping.
"""
if skip_existing:
existing = await self.repo.find_by_source("thread", thread_id)
if existing is None and self.adapter.manifest.has_source(f"thread:{thread_id}"):
existing = await self.repo.find_by_source("thread", thread_id)
if existing:
return {"note": existing, "created": False}
sources = []
if include_sources and reference_batches:
sources = from_reference_batches(reference_batches, thread_id=thread_id, max_items=self.config.max_source_items)
draft = extractor.extract_thread(
messages,
thread_id=thread_id,
thread_title=thread_title,
mode=mode,
title=title,
tags=tags,
project_name=self.project_name,
sources=sources,
max_messages=self.config.max_thread_messages,
)
if draft is None:
raise EmptyThreadError(f"Thread {thread_id} has no sediment-able content")
draft.status = normalize_status(status)
note = await self._persist_draft(draft, created_by=created_by)
return {"note": note, "created": True}
async def capture_search(
self,
*,
query: str,
results: list[dict[str, Any]] | None,
thread_id: str | None = None,
message_id: str | None = None,
title: str | None = None,
tags: list[str] | None = None,
status: str = "approved",
created_by: str | None = None,
) -> dict[str, Any]:
"""Sediment search/tool results into a reference note."""
sources = from_search_results(query, results, thread_id=thread_id, message_id=message_id, max_items=self.config.max_source_items)
draft = extractor.extract_search(query, sources, thread_id=thread_id, project_name=self.project_name, title=title, tags=tags)
draft.status = normalize_status(status)
return await self._persist_draft(draft, created_by=created_by)
async def create_manual_note(
self,
*,
title: str,
content_md: str,
tags: list[str] | None = None,
status: str = "approved",
summary: str | None = None,
created_by: str | None = None,
) -> dict[str, Any]:
"""Create a note directly from product-edited Markdown."""
# Strip any frontmatter the user may have pasted; vault writer adds its own.
_, body = MarkdownVault.parse(content_md)
body = body or content_md
base_tags = list(tags or [])
for default in (self.project_name, "knowledge-base"):
if default and default not in base_tags:
base_tags.append(default)
draft = NoteDraft(
title=title.strip() or "知识笔记",
summary=(summary or body.strip().splitlines()[0] if body.strip() else "")[:280],
content_md=body,
category="synthesis",
source_type="manual",
source_id=None,
status=normalize_status(status),
tags=base_tags,
confidence=0.5,
related=extractor.related_links(self.project_name),
)
return await self._persist_draft(draft, created_by=created_by)
# -- CRUD -------------------------------------------------------------
async def list_notes(
self,
*,
keyword: str | None = None,
tag: str | None = None,
source_type: str | None = None,
status: str | None = None,
limit: int = 20,
offset: int = 0,
) -> dict[str, Any]:
items, total = await self.repo.list_notes(
keyword=keyword,
tag=tag,
source_type=normalize_source_type(source_type) if source_type else None,
status=status,
limit=limit,
offset=offset,
)
return {"items": items, "total": total}
async def get_note(self, note_id: str) -> dict[str, Any] | None:
return await self.repo.get_note(note_id)
async def update_note(
self,
note_id: str,
*,
title: str | None = None,
content_md: str | None = None,
tags: list[str] | None = None,
status: str | None = None,
summary: str | None = None,
updated_by: str | None = None,
) -> dict[str, Any] | None:
current = await self.repo.get_note(note_id, with_sources=False)
if current is None:
return None
body = content_md
if body is not None:
_, parsed = MarkdownVault.parse(body)
body = parsed or body
note = await self.repo.update_note(
note_id,
title=title,
summary=summary,
content_md=body,
status=normalize_status(status) if status else None,
tags=tags,
updated_by=updated_by,
)
if note is None:
return None
try:
rel = self.adapter.update_note_file(
note_id,
current.get("vault_path"),
title=note["title"],
content_md=note["content_md"],
tags=note.get("tags") or [],
status=note["status"],
summary=note.get("summary") or "",
category="synthesis",
created=note["created_at"],
updated=note["updated_at"],
)
if rel and rel != current.get("vault_path"):
await self.repo.set_vault_path(note_id, rel)
except Exception:
logger.exception("Failed to update knowledge note %s in vault", note_id)
return await self.repo.get_note(note_id)
async def delete_note(self, note_id: str, *, updated_by: str | None = None, hard: bool = False) -> bool:
"""Soft delete (archive) by default; hard delete removes the vault file."""
current = await self.repo.get_note(note_id, with_sources=False)
if current is None:
return False
note = await self.repo.set_status(note_id, "archived", updated_by=updated_by)
try:
self.adapter.archive_note(note_id, current.get("vault_path"), updated=(note or current)["updated_at"])
if hard and current.get("vault_path"):
self.adapter.vault.delete_note(current["vault_path"])
self.adapter.manifest.remove_page(note_id)
except Exception:
logger.exception("Failed to archive knowledge note %s in vault", note_id)
return True
# -- search & graph ---------------------------------------------------
async def search(self, query: str, *, mode: str = "keyword", limit: int = 8) -> list[dict[str, Any]]:
return await search_notes(self.repo, query, mode=mode, limit=limit)
async def export_graph(self) -> dict[str, Any]:
from deerflow.utils.time import now_iso
notes = await self.repo.list_all()
result = self.adapter.export_graph(notes, updated=now_iso())
return {"files": result["files"], "stats": result["stats"]}
def export_file_path(self, filename: str) -> Path | None:
return self.adapter.export_file_path(filename)