I want to finetune an LLM to the text to sql generation, and I want to execute that sql on multiple databases example: “I want to know the total number of students in LA”, and I specify database1, and database2 database1 has 300 student , and database2 has 200 the response should be “500 students”, the issues here is that the column names and the table names could be different (Student_name and Namestudent) what's the correct approach to do so?
now I only have a langchain sql agent that uses openai to generate the SQL and it can only query one database