refactor: 移除 PostgreSQL 支持，简化为纯 SQLite 部署

- config.py: DATABASE_URL 默认值改为 SQLite - database.py: 移除 PostgreSQL 分支，简化为纯 SQLite - models/base.py: 移除 pgvector 导入和条件分支 - search_service.py: 移除 _search_postgres 方法 - import_service.py: 移除 pgvector 相关代码 - requirements.txt: 移除 asyncpg/alembic/pgvector 依赖 - pyproject.toml: 同步移除相关依赖 - docker-compose.yml: 移除 db 服务，- 删除 alembic.ini/Dockerfile.db/sql 目录 - README.md: 更新文档，移除 PostgreSQL 相关内容适合 NAS 等资源受限环境的轻量级部署
2026-04-14 14:50:53 +08:00
parent f60b45358d
commit 496e11e26e
14 changed files with 112 additions and 697 deletions
--- a/app/models/base.py
+++ b/app/models/base.py
@@ -1,26 +1,18 @@
 """
-SQLAlchemy 基础模型 + 通用 Mixin
-提供 DeclarativeBase、时间戳 Mixin 和公共序列化方法
-兼容 PostgreSQL（pgvector）和 SQLite（本地开发）
+ORM 模型定义
+
+SQLite 数据库模型，使用 Text 存储 JSON 格式的向量。
 """

 from __future__ import annotations

+import json
 from datetime import datetime
 from typing import Any, Dict

 from sqlalchemy import DateTime, Float, Integer, String, Text, func
 from sqlalchemy.orm import DeclarativeBase, Mapped, mapped_column

-from app.database import IS_SQLITE
-
-# SQLite 下不使用 pgvector，用 Text 存储向量（JSON 格式）
-if IS_SQLITE:
-    VectorType = Text
-else:
-    from pgvector.sqlalchemy import Vector
-    VectorType = Vector
-

 class Base(DeclarativeBase):
    """所有 ORM 模型的基类"""
@@ -28,96 +20,83 @@ class Base(DeclarativeBase):


 class TimestampMixin:
-    """
-    时间戳 Mixin，为模型自动添加 created_at / updated_at 字段。
-    """
+    """时间戳 Mixin"""
+
    created_at: Mapped[datetime] = mapped_column(
-        DateTime(timezone=True),
-        server_default=func.now(),
-        comment="创建时间",
+        DateTime, default=func.now(), comment="创建时间"
    )
    updated_at: Mapped[datetime] = mapped_column(
-        DateTime(timezone=True),
-        server_default=func.now(),
-        onupdate=func.now(),
-        comment="更新时间",
+        DateTime, default=func.now(), onupdate=func.now(), comment="更新时间"
    )

-    def to_dict(self) -> Dict[str, Any]:
-        """将模型实例转换为字典"""
-        result: Dict[str, Any] = {}
-        for column in self.__table__.columns:  # type: ignore[attr-defined]
-            value = getattr(self, column.name, None)
-            if isinstance(value, datetime):
-                value = value.isoformat()
-            elif hasattr(value, "tolist"):
-                value = value.tolist()
-            result[column.name] = value
-        return result
-
-
-# ──────────────────────────── 业务模型 ────────────────────────────

 class KnowledgePage(Base, TimestampMixin):
-    """知识页面模型"""
+    """知识页面"""
    __tablename__ = "knowledge_pages"

    id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
    title: Mapped[str] = mapped_column(String(500), nullable=False, comment="页面标题")
-    content: Mapped[str] = mapped_column(Text, nullable=False, comment="页面正文内容")
-    source_file: Mapped[str | None] = mapped_column(String(500), nullable=True, comment="来源文件名")
-    course_name: Mapped[str | None] = mapped_column(String(200), nullable=True, comment="课程名称")
-    teacher_name: Mapped[str | None] = mapped_column(String(100), nullable=True, comment="讲师名称")
-    live_date: Mapped[str | None] = mapped_column(String(20), nullable=True, comment="直播日期")
-    page_number: Mapped[int | None] = mapped_column(Integer, nullable=True, comment="原始页码")
-    metadata_json: Mapped[str | None] = mapped_column(Text, nullable=True, comment="额外元数据")
+    content: Mapped[str] = mapped_column(Text, nullable=False, comment="页面内容")
+    source: Mapped[str | None] = mapped_column(String(200), nullable=True, comment="来源文件名")
+    page_number: Mapped[int | None] = mapped_column(Integer, nullable=True, comment="原文件页码")
+    # 向量嵌入（JSON 格式存储）
+    embedding: Mapped[str | None] = mapped_column(Text, nullable=True, comment="向量嵌入（JSON）")

+    @property
+    def embedding_vector(self) -> list[float] | None:
+        if self.embedding is None:
+            return None
+        return json.loads(self.embedding)

-class KnowledgeChunk(Base, TimestampMixin):
-    """知识分块模型"""
-    __tablename__ = "knowledge_chunks"
-
-    id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
-    page_id: Mapped[int] = mapped_column(Integer, nullable=False, index=True, comment="关联页面 ID")
-    chunk_index: Mapped[int] = mapped_column(Integer, nullable=False, comment="分块序号")
-    content: Mapped[str] = mapped_column(Text, nullable=False, comment="分块文本内容")
-    embedding: Mapped[list | None] = mapped_column(
-        VectorType(768) if not IS_SQLITE else Text,
-        nullable=True,
-        comment="嵌入向量",
-    )
-    search_vector: Mapped[Any | None] = mapped_column(
-        Text, nullable=True, comment="全文搜索向量（仅 PG）",
-    )
-
-    def to_dict(self) -> Dict[str, Any]:
-        result = super().to_dict()
-        result.pop("embedding", None)
-        result.pop("search_vector", None)
-        return result
+    @embedding_vector.setter
+    def embedding_vector(self, value: list[float] | None):
+        self.embedding = json.dumps(value) if value else None


 class OCRImage(Base, TimestampMixin):
-    """OCR 图片记录模型"""
+    """OCR 图片记录"""
    __tablename__ = "ocr_images"

    id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
    file_path: Mapped[str] = mapped_column(String(500), nullable=False, comment="图片文件路径")
-    ocr_text: Mapped[str | None] = mapped_column(Text, nullable=True, comment="OCR 识别全文")
-    confidence: Mapped[float | None] = mapped_column(Float, nullable=True, comment="平均置信度")
+    original_filename: Mapped[str | None] = mapped_column(String(200), nullable=True, comment="原始文件名")
+    ocr_text: Mapped[str | None] = mapped_column(Text, nullable=True, comment="OCR 识别文本")
+    confidence: Mapped[float | None] = mapped_column(Float, nullable=True, comment="OCR 置信度")
    provider: Mapped[str | None] = mapped_column(String(50), nullable=True, comment="OCR 提供商")
-    status: Mapped[str] = mapped_column(String(20), default="pending", comment="处理状态")
-    error_message: Mapped[str | None] = mapped_column(Text, nullable=True, comment="错误信息")
-    tags: Mapped[str | None] = mapped_column(Text, nullable=True, comment="LLM 提取的标签，JSON 数组格式")
-    story_summary: Mapped[str | None] = mapped_column(Text, nullable=True, comment="Qwen3-8B 提炼的故事摘要")
+    status: Mapped[str] = mapped_column(
+        String(20), default="pending", comment="状态: pending/processing/completed/failed"
+    )
+    tags: Mapped[str | None] = mapped_column(Text, nullable=True, comment="关键词标签（JSON 数组）")
+    story_summary: Mapped[str | None] = mapped_column(Text, nullable=True, comment="故事摘要")
+    blocks: Mapped[str | None] = mapped_column(Text, nullable=True, comment="OCR 文本块（JSON）")

-    def to_dict(self) -> Dict[str, Any]:
-        result = super().to_dict()
-        # 将 tags 从 JSON 字符串解析为列表返回
-        if result.get("tags") and isinstance(result["tags"], str):
-            try:
-                import json
-                result["tags"] = json.loads(result["tags"])
-            except (json.JSONDecodeError, TypeError):
-                pass
-        return result
+    @property
+    def tags_list(self) -> list[str]:
+        if self.tags is None:
+            return []
+        return json.loads(self.tags)
+
+    @tags_list.setter
+    def tags_list(self, value: list[str]):
+        self.tags = json.dumps(value) if value else None
+
+    @property
+    def blocks_list(self) -> list[dict]:
+        if self.blocks is None:
+            return []
+        return json.loads(self.blocks)
+
+    @blocks_list.setter
+    def blocks_list(self, value: list[dict]):
+        self.blocks = json.dumps(value) if value else None
+
+
+class WebsiteSettings(Base):
+    """网站设置（单例）"""
+    __tablename__ = "website_settings"
+
+    key: Mapped[str] = mapped_column(String(100), primary_key=True, comment="设置键")
+    value: Mapped[str | None] = mapped_column(Text, nullable=True, comment="设置值（JSON）")
+    updated_at: Mapped[datetime] = mapped_column(
+        DateTime, default=func.now(), onupdate=func.now(), comment="更新时间"
+    )