Retrieval-Augmented Graph Retriever

Software componentKnowledge & DataKnowledge & Dataarc:RetrievalAugmentedGraphRetriever

A hybrid retriever that uses vector search to find relevant chunks, extracts and links their entities, then traverses only the subgraph around those entities.

Responsibility. Scopes graph traversal to subgraphs seeded by entities from vector-retrieved chunks.

Also known as: Retrieval-augmented knowledge graph, RAG-seeded subgraph expansion, Three-stage hybrid semantic memory retrieval

Variant of Hybrid Retriever abstract

When to choose. Choose when the graph is too large for exhaustive traversal (millions of nodes, billions of edges) and vector search can identify the entities around which to scope traversal.

Direct neighbourhood (hover for relationship types)

Relationships

invokes dependency

reads dependency

Knowledge Graph Store abstract Ch5.8

alternative to variability

Quantitative guidance

As stated by the sources; verify before use.

Reduces the traversal search space from millions of nodes to hundreds (Ch1.7B).
Vector stage narrows millions of documents to the top ~50 (or ~20 in the rivers example) before graph reasoning (Ch5.8).

Classification

Patterns: Vector search -> entity extraction -> subgraph expansionVector search, then entity/relation extraction or graph lookup, then combined reasoning
Quality attributes: Performance efficiency (ISO/IEC 25010)Functional suitability: correctness and validity (ISO/IEC 25010 | NIST AI RMF: valid)
Risks mitigated: Computationally prohibitive exhaustive graph traversal

Sources

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.
Ch5.8: T. Nguyen, "Semantic Memory," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 5.8. ISBN: 9798244538229.