How to pre-train or finetune LLM with structured dataset, so the LLM can reason the relationships between data objects

Models
1

I want to train LLM with structured dataset such as database with multiple tables. Here is an simple example:
t_user:

id name
1 Jason
2 Eric
3 David

t_book:

id title
1 Gone with The Wind
2 Brave New World
3 Native Son

t_bookstore:

id name
1 The Book Nook
2 The Literary Loft
3 Wordsmith Books

t_order:

user_id bookstore_id book_id
1 2 1
1 2 2
2 3 3

After training the LLM, it can reason on this relational database. Such as when I ask:
how many books did Jason buy in The Literary Loft bootstore? It can answers: 2 books, Gone with The Wind and Brave New World.

How can I prepare the corpus from the database and train the LLM ?

I have searched for some solutions, such as ask the LLM to transform prompts to sql queries, but that’s not what I want.

2

what about What is Table Question Answering? - Hugging Face

3

Table Question Answering seems can handle only one table, can’t reason relationships between multiple tables, are there any other suggestions?

4

There is at least one model for multi table qa.will this work for your data?