I want to understand the entire processing workflow of DB Assistant. I noticed that the task node responsible for generating SQL depends on three data inputs retrieved from the knowledge base: ddd_input, d_input, and sql_input. Additionally, different knowledge bases are specified for each of them in the default template. I would like to understand how to build these three knowledge bases and what the specific contents should be.
Describe your problem
I want to understand the entire processing workflow of DB Assistant. I noticed that the task node responsible for generating SQL depends on three data inputs retrieved from the knowledge base: ddd_input, d_input, and sql_input. Additionally, different knowledge bases are specified for each of them in the default template. I would like to understand how to build these three knowledge bases and what the specific contents should be.