DAX Generation (NL → DAX)

Overview

Rule-based + LLM fallback generator that turns a natural-language question against a Model into a DAX query.

What gets generated

Stage	Component	Output
Runtime	EasyFabric Runtime (EFR)	easyfabric.generate_dax_from_question

EasyFabric Runtime

generate_dax_from_question

def generate_dax_from_question(question: str,
                               model: Model,
                               power_bi_model: Optional[PowerBIModel] = None,
                               use_llm_fallback: bool = True) -> str

Generate DAX query from a natural language question using hybrid approach.

Arguments:

• question - Natural language query (e.g., "Give me top 10 Cities by Revenue")
• model - Analytical Model with table/column metadata
• power_bi_model - Optional Power BI model configuration
• use_llm_fallback - Whether to use LLM for low-confidence queries

Returns:

DAX query string

Raises:

• AmbiguousQueryError - If question maps to multiple entities without clear intent
• InvalidQueryError - If question cannot be parsed into valid DAX

Related data classes

• easyfabric.AmbiguousQueryError
• easyfabric.InvalidQueryError