📄️ Overview
The Denzing Metadata framework provides a structured blueprint for describing your data's organization, format, structure, and underlying relationships. This metadata is essential for enabling Large Language Models (LLMs) to accurately understand business definitions, KPIs, and context.
📄️ Schema Layer
The Schema layer is the foundational element of the Denzing Metadata framework. It contains the physical schema-level information for your data sources, encompassing column-level details, primary keys, and brief descriptions.
📄️ Semantics Layer
The Semantics layer is the second hierarchical level in the Denzing Metadata framework. It defines the meaning and context associated with the raw data, ensuring that LLMs can interpret metrics and KPIs correctly based on their intended purpose. This layer builds upon the foundational Schema, and information defined at the Schema level can be overridden here.
📄️ Metadata Generation
In Denzing, once an agent is created, the metadata generation process begins automatically. This process involves compiling and structuring essential information about the agent—such as its configuration, data sources, and behavioral context—so that it can operate effectively and respond accurately during user interactions.