Category: Key Terms
What is a semantic layer?
A semantic layer is the shared business meaning of metrics and dimensions above raw tables. Learn how it stops three versions of revenue, where it sits in the…
Fine-tuning vs RAG
Fine-tuning changes how a model behaves; RAG fetches your documents at ask time. Learn when each helps, when to combine them, and why neither replaces data quality or…
What is an embedding?
An embedding turns text (or other data) into a list of numbers so machines can measure similarity. Learn what those vectors are for, how search and RAG use…
What is a feature store?
A feature store is shared plumbing for ML inputs: define features once, train and serve them consistently, and reduce train-serve skew. Learn when you need one, what offline…
What is grain in data?
Grain answers one question: what does one row mean? Learn how mismatched grain creates double counting, silent joins, and three versions of revenue, plus a checklist you can…
