Support other databases

Currently, the framework relies on DuckDB to persist the results. However, it would be nice to have support for other databases as well and to benefit from ORMs and other perks of Python libraries that connect to many databases, like SQLAlchemy.

No file or test is named. Start by locating the existing DuckDB persistence path, then clarify which databases and SQLAlchemy integration are in scope. Done means the supported database choices and integration behavior are defined and covered by tests.

由索引模型根据 Issue 内容生成。