Agentic AI Reference Architecture

Knowledge & Data · Data artifact

Text Cleaning Profile

Data artifactKnowledge & DataKnowledge & Dataarc:TextCleaningProfile

A configuration artifact setting cleaning aggressiveness, such as case and punctuation preservation, per source type or language.

Responsibility. Parameterizes how aggressively text is cleaned for each source type.

Also known as: Per-source cleaning profile

configuresText Normalizer: configuresText Normalizer
Direct neighbourhood (hover for relationship types)

Relationships

configures structural

Sources

  1. Ch6.3A: T. Nguyen, "ETL Pipeline Fundamentals," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 6.3A. ISBN: 9798244538229.