Agentic AI Reference Architecture

Knowledge & Data · Data store

Document Metadata Store

Data storeKnowledge & DataKnowledge & Dataarc:DocumentMetadataStore

A persistent store of per-document and per-chunk metadata (source, version, attributes) used to filter retrieval results and to attribute citations to source documents.

Responsibility. Holds document metadata for retrieval filtering and citation.

Also known as: Metadata store

is written byis read byis read byis read byIngestion Pipeline Orchestrator: is written byIngestion Pipeline Orche…Retriever: is read byRetrieverCitation Extractor: is read byCitation ExtractorKnowledge Base Backup Service: is read byKnowledge Base Backup Se…
Direct neighbourhood (hover for relationship types)

Relationships

is read by dependency

is written by dependency

Design guidance

Classification

Quality attributes
Transparency and accountability (NIST AI RMF: accountable and transparent)Reliability (ISO/IEC 25010 | NIST AI RMF: valid and reliable)

Sources

  1. Ch6.5: T. Nguyen, "Production RAG Systems," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 6.5. ISBN: 9798244538229.