Query generation based on natural language question and semantic data

A method comprising:

• receiving, by a hardware processor, a request to answer a natural language question generated by a user;
• using, by the hardware processor, a set of large language models to generate a structured language data query for a data store based on semantic data and the natural language question, the semantic data comprising a semantic model that provides a semantic description of at least a portion of a schema of the data store, the semantic model comprising a structured representation of the data store, the semantic model being defined by one or more logical tables, an individual logical table of the one or more logical tables semantically describing a data store table of the data store or a data store view of the data store, the individual logical table comprising one or more logical columns, and an individual logical column of the individual logical table semantically describing an underlying column of the data store table or the data store view;
• and
• in response the set of large language models successfully generating the structured language data query:
• determining, by the hardware processor, whether the structured language data query is valid;
• and
• in response to determining that the structured language data query is valid:
• causing, by the hardware processor, the structured language data query to be performed on the data store;
• receiving, by the hardware processor, a query result from the data store responsive to the structured language data query;
• generating, by the hardware processor, a response that comprises the query result, the response being responsive to request;
• and
• sending, by the hardware processor, the response back to a sender of the request.

A machine-readable storage medium, the machine-readable storage medium including instructions that when executed by a machine, cause the machine to perform operations comprising:

• receiving a multi-turn conversation that comprises:
• at least one prior natural language question and corresponding answer;
• and
• a recent natural language question;
• converting the multi-turn conversation into a single-turn natural language question using a large language model;
• using a set of large language models to generate a structured language data query for a data store based on semantic data and the single-turn natural language question, the semantic data comprising a semantic model that provides a semantic description of at least a portion of a schema of the data store, the semantic model comprising a structured representation of the data store, the semantic model being defined by one or more logical tables, an individual logical table of the one or more logical tables semantically describing a data store table of the data store or a data store view of the data store, the individual logical table comprising one or more logical columns, and an individual logical column of the individual logical table semantically describing an underlying column of the data store table or the data store view;
• and
• in response the set of large language models successfully generating the structured language data query:
• determining whether the structured language data query is valid;
• and
• in response to determining that the structured language data query is valid:
• causing the structured language data query to be performed on the data store;
• receiving a query result from the data store responsive to the structured language data query;
• generating a response that comprises the query result, the response being responsive to request;
• and
• sending the response back to a sender of the request.