AdministratorandClaude Opus 4.8
683cc6d76e
- embeddings.py：OpenAI 兼容 embedding 客户端，未配置时关键词兜底
- chunking.py + knowledge_embeddings 表：Markdown 分块与向量索引（Python 余弦）
- search.py：keyword/vector/hybrid 三种模式，向量不可用自动降级
- 笔记创建/更新自动重建向量索引；新增 /reindex 维护接口
- KnowledgeRagMiddleware：按对话级开关 knowledge_rag_enabled 注入 <knowledge-context>，接入 lead agent 中间件链（默认随 config.knowledge.rag_enabled）
- service.build_rag_context（wiki-query 风格分层召回）
- 笔记版本快照（knowledge_note_versions）+ GET /notes/{id}/versions
- 前端：聊天页「知识库」对话级 RAG 开关 + 类型字段
- 新增 entities/relations 表（阶段四预置）
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
142 lines
6.7 KiB
Python
142 lines
6.7 KiB
Python
"""ORM models for the product knowledge base.
|
|
|
|
Tables mirror the obsidian-wiki vault into the database so the product can
|
|
list, filter, search and audit notes quickly without re-parsing Markdown. The
|
|
vault Markdown remains the source-of-truth for ``content_md`` / frontmatter /
|
|
graph; these rows are an index + audit layer.
|
|
|
|
The knowledge base is **global / shared** — there is no ``user_id`` isolation.
|
|
Writes record ``created_by`` / ``updated_by`` for auditing only.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from datetime import UTC, datetime
|
|
|
|
from sqlalchemy import Float, ForeignKey, Integer, String, Text, UniqueConstraint
|
|
from sqlalchemy.orm import Mapped, mapped_column
|
|
|
|
from deerflow.persistence.base import Base
|
|
from deerflow.persistence.types import BeijingDateTime, PortableJSON, PortableLongText
|
|
|
|
|
|
class KnowledgeNoteRow(Base):
|
|
"""Knowledge note main table (mirrors ``knowledge_notes``)."""
|
|
|
|
__tablename__ = "knowledge_notes"
|
|
|
|
id: Mapped[str] = mapped_column(String(64), primary_key=True)
|
|
title: Mapped[str] = mapped_column(String(512))
|
|
summary: Mapped[str | None] = mapped_column(Text)
|
|
content_md: Mapped[str] = mapped_column(PortableLongText())
|
|
vault_path: Mapped[str | None] = mapped_column(String(1024), index=True)
|
|
source_type: Mapped[str] = mapped_column(String(64), index=True)
|
|
source_id: Mapped[str | None] = mapped_column(String(256), index=True)
|
|
status: Mapped[str] = mapped_column(String(32), default="approved", index=True)
|
|
confidence: Mapped[float] = mapped_column(Float, default=0.0)
|
|
created_by: Mapped[str | None] = mapped_column(String(128), index=True)
|
|
updated_by: Mapped[str | None] = mapped_column(String(128))
|
|
created_at: Mapped[datetime] = mapped_column(BeijingDateTime(), default=lambda: datetime.now(UTC), index=True)
|
|
updated_at: Mapped[datetime] = mapped_column(BeijingDateTime(), default=lambda: datetime.now(UTC), onupdate=lambda: datetime.now(UTC), index=True)
|
|
|
|
|
|
class KnowledgeSourceRow(Base):
|
|
"""Knowledge source table (mirrors ``knowledge_sources``)."""
|
|
|
|
__tablename__ = "knowledge_sources"
|
|
|
|
id: Mapped[str] = mapped_column(String(64), primary_key=True)
|
|
note_id: Mapped[str] = mapped_column(String(64), ForeignKey("knowledge_notes.id", ondelete="CASCADE"), index=True)
|
|
source_type: Mapped[str] = mapped_column(String(64))
|
|
thread_id: Mapped[str | None] = mapped_column(String(128), index=True)
|
|
message_id: Mapped[str | None] = mapped_column(String(128))
|
|
tool_name: Mapped[str | None] = mapped_column(String(128))
|
|
title: Mapped[str | None] = mapped_column(String(512))
|
|
url: Mapped[str | None] = mapped_column(Text)
|
|
snippet: Mapped[str | None] = mapped_column(Text)
|
|
raw_json: Mapped[str | None] = mapped_column(PortableLongText())
|
|
created_by: Mapped[str | None] = mapped_column(String(128))
|
|
created_at: Mapped[datetime] = mapped_column(BeijingDateTime(), default=lambda: datetime.now(UTC))
|
|
|
|
|
|
class KnowledgeTagRow(Base):
|
|
"""Tag table (mirrors ``knowledge_tags``)."""
|
|
|
|
__tablename__ = "knowledge_tags"
|
|
|
|
id: Mapped[str] = mapped_column(String(64), primary_key=True)
|
|
name: Mapped[str] = mapped_column(String(128), unique=True, index=True)
|
|
created_at: Mapped[datetime] = mapped_column(BeijingDateTime(), default=lambda: datetime.now(UTC))
|
|
|
|
|
|
class KnowledgeNoteTagRow(Base):
|
|
"""Note ↔ tag join table (mirrors ``knowledge_note_tags``)."""
|
|
|
|
__tablename__ = "knowledge_note_tags"
|
|
__table_args__ = (UniqueConstraint("note_id", "tag_id", name="uq_knowledge_note_tags"),)
|
|
|
|
note_id: Mapped[str] = mapped_column(String(64), ForeignKey("knowledge_notes.id", ondelete="CASCADE"), primary_key=True)
|
|
tag_id: Mapped[str] = mapped_column(String(64), ForeignKey("knowledge_tags.id", ondelete="CASCADE"), primary_key=True)
|
|
|
|
|
|
class KnowledgeEmbeddingRow(Base):
|
|
"""Per-chunk embedding index (phase 2, mirrors ``knowledge_embeddings``).
|
|
|
|
The vector is stored as a JSON float array; first-release similarity is
|
|
computed in Python (no external vector DB). ``vector_id`` is reserved for a
|
|
future external store mapping.
|
|
"""
|
|
|
|
__tablename__ = "knowledge_embeddings"
|
|
|
|
id: Mapped[str] = mapped_column(String(64), primary_key=True)
|
|
note_id: Mapped[str] = mapped_column(String(64), ForeignKey("knowledge_notes.id", ondelete="CASCADE"), index=True)
|
|
chunk_index: Mapped[int] = mapped_column(Integer, default=0)
|
|
content: Mapped[str] = mapped_column(Text)
|
|
vector: Mapped[list] = mapped_column(PortableJSON(), default=list)
|
|
vector_id: Mapped[str | None] = mapped_column(String(256))
|
|
created_at: Mapped[datetime] = mapped_column(BeijingDateTime(), default=lambda: datetime.now(UTC))
|
|
|
|
|
|
class KnowledgeNoteVersionRow(Base):
|
|
"""Immutable snapshot of a note before each update (phase 3 versioning)."""
|
|
|
|
__tablename__ = "knowledge_note_versions"
|
|
|
|
id: Mapped[str] = mapped_column(String(64), primary_key=True)
|
|
note_id: Mapped[str] = mapped_column(String(64), ForeignKey("knowledge_notes.id", ondelete="CASCADE"), index=True)
|
|
title: Mapped[str] = mapped_column(String(512))
|
|
summary: Mapped[str | None] = mapped_column(Text)
|
|
content_md: Mapped[str] = mapped_column(PortableLongText())
|
|
status: Mapped[str] = mapped_column(String(32))
|
|
tags_json: Mapped[list] = mapped_column(PortableJSON(), default=list)
|
|
edited_by: Mapped[str | None] = mapped_column(String(128))
|
|
created_at: Mapped[datetime] = mapped_column(BeijingDateTime(), default=lambda: datetime.now(UTC), index=True)
|
|
|
|
|
|
class KnowledgeEntityRow(Base):
|
|
"""Knowledge entity (phase 4, mirrors ``knowledge_entities``)."""
|
|
|
|
__tablename__ = "knowledge_entities"
|
|
__table_args__ = (UniqueConstraint("name", "entity_type", name="uq_knowledge_entities_name_type"),)
|
|
|
|
id: Mapped[str] = mapped_column(String(64), primary_key=True)
|
|
name: Mapped[str] = mapped_column(String(256), index=True)
|
|
entity_type: Mapped[str | None] = mapped_column(String(64))
|
|
created_at: Mapped[datetime] = mapped_column(BeijingDateTime(), default=lambda: datetime.now(UTC))
|
|
|
|
|
|
class KnowledgeRelationRow(Base):
|
|
"""Relation between notes/entities (phase 4, mirrors ``knowledge_relations``)."""
|
|
|
|
__tablename__ = "knowledge_relations"
|
|
|
|
id: Mapped[str] = mapped_column(String(64), primary_key=True)
|
|
from_note_id: Mapped[str | None] = mapped_column(String(64), index=True)
|
|
to_note_id: Mapped[str | None] = mapped_column(String(64), index=True)
|
|
from_entity_id: Mapped[str | None] = mapped_column(String(64), index=True)
|
|
to_entity_id: Mapped[str | None] = mapped_column(String(64), index=True)
|
|
relation_type: Mapped[str] = mapped_column(String(128))
|
|
weight: Mapped[float] = mapped_column(Float, default=1.0)
|
|
created_at: Mapped[datetime] = mapped_column(BeijingDateTime(), default=lambda: datetime.now(UTC))
|