Agentic AI Reference Architecture

Knowledge & Data · Software component

Keyword Retriever

Software componentKnowledge & DataKnowledge & Dataarc:KeywordRetriever

A retriever that ranks documents by sparse keyword (lexical) matching against the query rather than by embedding similarity.

Responsibility. Retrieves documents by lexical keyword match.

Also known as: Sparse keyword search, Sparse retriever, BM25 retriever, Keyword search fallback

Variant of Retriever abstract

When to choose. Choose alongside dense vector search when sparse keyword matching can return results faster, run in parallel to cut retrieval latency.

specializesis failover foris routed to bysends data tois invoked byreadsRetriever: specializesRetrieverVector Retriever: is failover forVector RetrieverGraceful Degradation Manager: is routed to byGraceful Degradation Man…Reranker: sends data toRerankerDense-Sparse Hybrid Retriever: is invoked byDense-Sparse Hybrid Retr…Lexical Index Store: readsLexical Index Store
Direct neighbourhood (hover for relationship types)

Relationships

is invoked by dependency

reads dependency

is routed to by dynamic

sends data to dynamic

is failover for control

Classification

Patterns
Two-stage retrieve-then-rerankBM25Learned sparse encodersTF-IDF variants
Technologies
BM25
Quality attributes
Performance efficiency (ISO/IEC 25010)
Risks mitigated
Dense-embedding blind spots: specialized terminology, acronyms, exact phrases, rare entity names

Sources

  1. Ch2.9: T. Nguyen, "Streaming and Real-Time Responses," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 2.9. ISBN: 9798244538229.
  2. Ch3.4: T. Nguyen, "Tuning Model Parameters for Production Performance," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 3.4. ISBN: 9798244538229.
  3. Ch6.1: T. Nguyen, "Embeddings and RAG Fundamentals," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 6.1. ISBN: 9798244538229.
  4. 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.
  5. 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.
  6. Ref7.07: E. Li, V. Bellotti, R. Kraus, and R. Kao, "Build a retrieval-augmented generation (RAG) agent with NVIDIA Nemotron," NVIDIA Technical Blog, Sep. 23, 2025. [Online]. Available: https://developer.nvidia.com/blog/build-a-rag-agent-with-nvidia-nemotron/