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

app/services/import_service.py

@@ -14,7 +14,6 @@ from sqlalchemy import text
 from sqlalchemy.ext.asyncio import AsyncSession
 
 from app.config import settings
-from app.database import IS_SQLITE
 
 logger = logging.getLogger(__name__)
 
@@ -343,21 +342,13 @@ class ImportService:
 
         # 批量插入
         for idx, (chunk_text, embedding) in enumerate(zip(chunks, embeddings)):
-            if IS_SQLITE:
-                # SQLite: 向量存为 JSON 文本
-                import json as _json
-                embedding_str = _json.dumps(embedding) if embedding else None
-                sql = text("""
-                    INSERT INTO knowledge_chunks (page_id, chunk_index, content, embedding)
-                    VALUES (:page_id, :chunk_index, :content, :embedding)
-                """)
-            else:
-                # PostgreSQL: 使用 pgvector 类型
-                embedding_str = "[" + ",".join(str(x) for x in embedding) + "]" if embedding else None
-                sql = text("""
-                    INSERT INTO knowledge_chunks (page_id, chunk_index, content, embedding)
-                    VALUES (:page_id, :chunk_index, :content, :embedding::vector)
-                """)
+            # SQLite: 向量存为 JSON 文本
+            import json as _json
+            embedding_str = _json.dumps(embedding) if embedding else None
+            sql = text("""
+                INSERT INTO knowledge_chunks (page_id, chunk_index, content, embedding)
+                VALUES (:page_id, :chunk_index, :content, :embedding)
+            """)
             await self.db.execute(sql, {
                 "page_id": page_id,
                 "chunk_index": idx,
@@ -365,14 +356,6 @@ class ImportService:
                 "embedding": embedding_str,
             })
 
-        # 更新全文搜索向量（仅 PostgreSQL）
-        if not IS_SQLITE:
-            await self.db.execute(text("""
-                UPDATE knowledge_chunks
-                SET search_vector = to_tsvector('chinese_zh', content)
-                WHERE page_id = :page_id
-            """), {"page_id": page_id})
-
         await self.db.flush()
         return len(chunks)