Method, apparatus, and computer-readable medium for domain-specific execution of natural language queries

An apparatus for domain-specific execution of natural language queries, the apparatus comprising:

• one or more processors;
• and
• one or more memories operatively coupled to at least one of the one or more processors and having instructions stored thereon that, when executed by at least one of the one or more processors, cause at least one of the one or more processors to:
• receive a natural language query in a user interface, the natural language query comprising a plurality of query terms and requesting data from an enterprise data catalog;
• identify one or more nouns in the plurality of query terms;
• query an entity index based at least in part on the one or more nouns to identify one or more class entities corresponding to the one or more nouns and one or more class attributes corresponding to the one or more class entities, the entity index being generated based at least in part on an entity graph corresponding to the enterprise data catalog, the entity graph comprising a plurality of nodes and a plurality of edges between the plurality of nodes, wherein the plurality of nodes correspond to a plurality of concepts and the plurality of edges correspond to a plurality of relationships between the plurality of concepts;
• generate one or more structured query language (SQL) queries corresponding to the natural language query based at least in part on providing the one or more class entities and the one or more class attributes as context to a large language model (LLM), the one or more SQL queries comprising one or more SQL terms;
• transform the one or more SQL queries into one or more domain specific language (DSL) queries based at least in part on the one or more SQL terms, one or more additional terms semantically related to the one or more SQL terms, and one or more DSL mapping rules configured to map SQL to DSL;
• execute the DSL query on the enterprise data catalog to identify one or more results corresponding to the natural language query;
• and
• transmit the one or more results in the user interface.

At least one non-transitory computer-readable medium storing computer-readable instructions for domain-specific execution of natural language queries that, when executed by one or more computing devices, cause at least one of the one or more computing devices to:

• receive a natural language query in a user interface, the natural language query comprising a plurality of query terms and requesting data from an enterprise data catalog;
• identify one or more nouns in the plurality of query terms;
• query an entity index based at least in part on the one or more nouns to identify one or more class entities corresponding to the one or more nouns and one or more class attributes corresponding to the one or more class entities, the entity index being generated based at least in part on an entity graph corresponding to the enterprise data catalog, the entity graph comprising a plurality of nodes and a plurality of edges between the plurality of nodes, wherein the plurality of nodes correspond to a plurality of concepts and the plurality of edges correspond to a plurality of relationships between the plurality of concepts;
• generate one or more structured query language (SQL) queries corresponding to the natural language query based at least in part on providing the one or more class entities and the one or more class attributes as context to a large language model (LLM), the one or more SQL queries comprising one or more SQL terms;
• transform the one or more SQL queries into one or more domain specific language (DSL) queries based at least in part on the one or more SQL terms, one or more additional terms semantically related to the one or more SQL terms, and one or more DSL mapping rules configured to map SQL to DSL;
• execute the DSL query on the enterprise data catalog to identify one or more results corresponding to the natural language query;
• and
• transmit the one or more results in the user interface.