Are there any best practices for configuration?

First, I want to say that as someone with no machine learning experience, I really like this project. It's ready to use out of the box, and the concept is very simple.

However, due to my lack of experience in machine learning, I don't have much expertise in how to configure each setting in the configuration options according to the current project's environment. For example, how many should be set for `n_jobs`, and what factors determine this value?

Is it possible to add documentation about configuration best practices?

Use the configuration options and the `n_jobs` example in the issue as the starting point. Review how these settings relate to the project's environment, then document practical configuration guidance and the factors affecting `n_jobs`; the work is done when newcomers can choose settings with clear best-practice guidance.

Written by the indexing model from the issue text.