Hey guys, i’m currently building an ai app that has an llm to write a sql query which i can then used to fetch the data from a postresql database.
My current approach is that i pass the llm with the table schema as well as some sample data (top 5 data in the table) for it to have some context.
However, the issue im currently facing is that the items the llm is adding to the sql query does not actually exists in the table.
Is my current approach good enough or should i consider switching to using embeddings ?