Skip to content
RelationalAI Docs

Verbalizer

relationalai.agent.cortex.verbalize

Abstract base class for verbalizing RAI model structure and semantics.

Verbalizers control how model information is presented to Cortex agents. They provide two levels of explanation:

  • Model-level: Overall structure, relationships, and available concepts
  • Concept-level: Detailed business rules for specific concepts

Implement this interface to customize how your models are explained to agents.

Methods

Section titled “Methods”

.explain_model()

Section titled “.explain_model()”
Verbalizer.explain_model() -> str

Return comprehensive explanation of the model’s structure and relationships.

Returns:

  • str - A natural language explanation of the model.

.explain_concept()

Section titled “.explain_concept()”
Verbalizer.explain_concept(concept: str) -> str

Return detailed explanation of business rules for a specific concept.

Parameters:

  • concept

    (str) - The name of the concept to explain.

Returns:

  • str - A natural language explanation of the concept.

Inheritance Hierarchy

Section titled “Inheritance Hierarchy”
Verbalizerabc.ABC

Subclassed By

Section titled “Subclassed By”
 agent > cortex > verbalize
├──  ModelVerbalizer
└──  SourceCodeVerbalizer

Used By

Section titled “Used By”
 agent > cortex > tool
├──  DefaultTool
└──  ToolRegistry
    └──  add