feat(phase3): Task1 embedding链路验证 - embo-01(1536维)+pgvector检索打通

2026-05-26 10:33:25 +08:00
parent d40d46a434
commit 1325807257
6 changed files with 390 additions and 0 deletions
@@ -0,0 +1,55 @@
+"""
+知识库模型 — SQLModel
+对应 knowledge_items 和 knowledge_embeddings 两张表
+embedding 字段使用 pgvector.Vector（对应 PG vector(1536)）
+"""
+
+from datetime import datetime, date
+from typing import Optional, Any
+
+from sqlalchemy import Column, DateTime as SADateTime, Text, Integer
+from sqlalchemy.dialects.postgresql import JSONB
+from sqlalchemy.sql import func as sa_func
+from sqlmodel import Field, SQLModel
+
+from pgvector.sqlalchemy import Vector
+
+
+class KnowledgeItem(SQLModel, table=True):
+    """知识库条目（knowledge_items）"""
+    __tablename__ = "knowledge_items"
+
+    id: Optional[int] = Field(default=None, primary_key=True)
+    title: str = Field(max_length=300)
+    content_md: Optional[str] = Field(default=None)
+    source_type: str = Field(default="manual", max_length=30)
+    source_file_name: Optional[str] = Field(default=None, max_length=300)
+    source_url: Optional[str] = Field(default=None, max_length=1000)
+    author: Optional[str] = Field(default=None, max_length=100)
+    publish_date: Optional[date] = Field(default=None)
+    tags: Any = Field(default=None, sa_column=Column(JSONB, default=[]))
+    related_entities: Any = Field(default=None, sa_column=Column(JSONB, default=[]))
+    related_concepts: Any = Field(default=None, sa_column=Column(JSONB, default=[]))
+    created_at: datetime | None = Field(
+        default=None,
+        sa_column=Column(SADateTime(timezone=True), nullable=False, server_default=sa_func.now()),
+    )
+    updated_at: datetime | None = Field(
+        default=None,
+        sa_column=Column(SADateTime(timezone=True), nullable=False, server_default=sa_func.now()),
+    )
+
+
+class KnowledgeEmbedding(SQLModel, table=True):
+    """知识库向量（knowledge_embeddings）"""
+    __tablename__ = "knowledge_embeddings"
+
+    id: Optional[int] = Field(default=None, primary_key=True)
+    knowledge_id: int = Field(foreign_key="knowledge_items.id", index=True)
+    chunk_index: int = Field(default=0)
+    chunk_text: str = Field(sa_column=Column(Text, nullable=False))
+    embedding: Any = Field(sa_column=Column(Vector(1536), nullable=False))
+    created_at: datetime | None = Field(
+        default=None,
+        sa_column=Column(SADateTime(timezone=True), nullable=False, server_default=sa_func.now()),
+    )