SQL is also an API querying language. The primary difference is that SQL is designed to query relational data (rows and columns), while GraphQL graph data (tree-like structures).
The parent is questioning how useful GraphQL is as a relational query language or if the suggestion centres around moving to the database speaking in graphs. Conceivably, the data storage could still follow what suits the relational model internally with some kind of ORM-style engine that sits in the middle to translate relations to graphs for the GraphQL query processor, but at that point you could argue that the database is a graph database.
The parent is questioning how useful GraphQL is as a relational query language or if the suggestion centres around moving to the database speaking in graphs. Conceivably, the data storage could still follow what suits the relational model internally with some kind of ORM-style engine that sits in the middle to translate relations to graphs for the GraphQL query processor, but at that point you could argue that the database is a graph database.