Agentic AI Reference Architecture

Knowledge & Data · Software component

Graph-Enhanced Retriever

Software componentKnowledge & DataKnowledge & Dataarc:GraphEnhancedRetriever

A hybrid retriever that returns semantically retrieved chunks annotated with relationship metadata drawn from the knowledge graph.

Responsibility. Annotates retrieved chunks with relationship metadata from the graph.

Also known as: Graph-enhanced RAG

Variant of Hybrid Retriever abstract

When to choose. Choose when retrieved chunks need relationship context invisible to vector search (authorship, employment history, contradictions between documents).

specializesalternative toalternative toHybrid Retriever: specializesHybrid RetrieverParallel Fusion Retriever: alternative toParallel Fusion RetrieverRetrieval-Augmented Graph Retriever: alternative toRetrieval-Augmented Grap…
Direct neighbourhood (hover for relationship types)

Relationships

alternative to variability

Classification

Patterns
Relationship metadata enrichment
Quality attributes
Functional suitability: correctness and validity (ISO/IEC 25010 | NIST AI RMF: valid)
Risks mitigated
LLM missing relational context of retrieved documents

Sources

  1. Ch1.7B: T. Nguyen, "Relational Reasoning with Knowledge Graphs - Hybrid RAG+KG Integration," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 1.7B. ISBN: 9798244538229.