Generative business intelligence

A non-transitory computer-readable medium comprising instructions that, responsive to execution by a processing device, causes the processing device to perform operations comprising:

• receiving a question as a natural language string;
• obtaining a plurality of previously generated synthetic questions that corresponds to a domain associated with a computing device that originated the question from the user;
• determining a subset of the previously generated synthetic questions that are semantically similar to the natural language string;
• determining one or more fragments based on the natural language string by providing the subset of the previously generated synthetic questions that are semantically similar to the natural language string, question fragments corresponding to the subset of the previously generated synthetic questions, and the natural language string to a large language model, wherein the subset of the previously generated synthetic questions that are semantically similar to the natural language string and the question fragments are utilized by the large language model to constrain the determination of the one or more fragments based on the natural language string;
• identifying one or more query operators based on the one or more fragments, wherein the identifying the one or more query operators comprises identifying a plurality of query components in the fragments, wherein the plurality of query components comprises one or more of:
• dimensions, measures, grouping, aggregation, ordering, advanced analysis, and combinations thereof;
• constructing a structured query tree based on the one or more query operators;
• executing at least a portion of the structured query tree on a data source, wherein the data source comprises one or more of a database, a data warehouse, an object store, and combinations thereof;
• receiving, from the data source, an output result based on the execution;
• generating a response based on the output result;
• and
• providing the response to a user.

A system comprising:

• a memory with instructions stored thereon;
• and
• a processing device, coupled to the memory, the processing device configured to access the memory and execute the instructions, wherein the instructions cause the processing device to perform operations including:
• receiving a question as a natural language string;
• obtaining a plurality of previously generated synthetic questions that corresponds to a domain associated with a computing device that originated the question from the user;
• determining a subset of the previously generated synthetic questions that are semantically similar to the natural language string;
• determining one or more fragments based on the natural language string by providing the subset of the previously generated synthetic questions that are semantically similar to the natural language string, question fragments corresponding to the subset of the previously generated synthetic questions, and the natural language string to a large language model, wherein the subset of the previously generated synthetic questions that are semantically similar to the natural language string and the question fragments are utilized by the large language model to constrain the determination of the one or more fragments based on the natural language string;
• identifying one or more query operators based on the one or more fragments, wherein the identifying the one or more query operators comprises identifying a plurality of query components in the fragments, wherein the plurality of query components comprises one or more of:
• dimensions, measures, grouping, aggregation, ordering, advanced analysis, and combinations thereof;
• constructing a structured query tree based on the one or more query operators;
• executing at least a portion of the structured query tree on a data source, wherein the data source comprises one or more of a database, a data warehouse, an object store, and combinations thereof;
• receiving, from the data source, an output result based on the execution;
• generating a response based on the output result;
• and
• providing the response to a user.