Retriever

Software componentKnowledge & DataKnowledge & DataVariation point (abstract)arc:Retriever

An abstract software component that fetches the information needed to answer a query from an indexed knowledge source.

Responsibility. Fetches query-relevant knowledge for downstream answer generation.

Also known as: Retrieval Component, Retrieval layer, Retrieval tool

Direct neighbourhood (hover for relationship types)

Variants

Variant	When to choose
Dense-Sparse Hybrid Retriever	Choose in latency-sensitive RAG agents where retrieval dominates time-to-first-token.
Graph Retriever	Choose when queries require following typed relationships across multiple hops (e.g., conflict-of-interest chains, investor overlap).
Hybrid Retriever abstract	Choose when queries need both semantic similarity and relationship traversal.
Keyword Retriever	Choose alongside dense vector search when sparse keyword matching can return results faster, run in parallel to cut retrieval latency.
Multimodal Retriever abstract	—
Vector Retriever abstract	Choose when queries need conceptual understanding or semantic similarity across varied terminology (simple Q&A, documentation search, customer support).

Relationships

is routed to by dynamic

receives data from dynamic

Query Complexity Classifier Ch3.4

sends data to dynamic

Context Assembler abstract Ch1.7B Ch2.9 +1
Context Compressor Ch3.4
Reranker abstract Ch6.5

fails over to control

Parametric Answer Generator Ch6.6

has access controlled by control

Action Policy Engine Ch3.3

is failover for control

Question Decomposer Ch6.6

is guarded by control

Retrieval Rail Ch7.1A Ch9.4 +1

is orchestrated by control

is evaluated by assurance

is monitored by assurance

Design guidance

SHOULD be selected by query characteristics (semantic similarity vs. relational traversal) rather than assuming more capabilities yield better results.
SHOULD limit retrieved document count; quality often plateaus after 5-7 documents.
SHOULD favour recall-oriented strategies in multi-hop settings, retrieving broader sets and relying on reasoning to filter.
SHOULD limit top-k to the 2-4 most relevant chunks instead of 10+.
SHOULD be evaluated for precision and recall before deployment; improve ranking and indexing if precision is below 70%.
SHOULD defer retrieval until reasoning reveals a specific information gap, where the added retrieval latency is acceptable.
SHOULD prefer retrieval quality over quantity; irrelevant, contradictory or outdated documents can perform worse than parametric knowledge alone.

Quantitative guidance

As stated by the sources; verify before use.

Retrieval contributes 50-70% of TTFT in RAG agents, often 2-4 s (Ch2.9).
Fetching 20 documents takes about twice as long as 10 (Ch2.9).
HotpotQA full-wiki setting requires retrieval over more than 5 million Wikipedia paragraphs (Ch3.3).
E-commerce: ~30% of tokens came from excessive retrieval context (Ch3.10).
Poor-quality retrieval can increase hallucination rates compared with no retrieval (Ch3.10).
Lazy retrieval accumulates ~15,000 targeted tokens instead of ~50,000 proactively retrieved tokens (Ch5.9).
Codebase analysis: full 200,000-token load 34% correct vs curated 30,000-50,000 tokens 81% (87% expert baseline); 6.2x fewer tokens, 2.4x higher accuracy, latency 47 s -> 12 s (Ch5.9).
Retrieval recall target 90%+, precision target 80%+; retrieval stage 100-300 ms (Ch6.5).

Classification

Patterns: Retrieval-augmented generationAdaptive retrieval depth by query complexityLazy (on-demand) retrievalCurated multi-stage retrieval over large codebases
Quality attributes: Functional suitability: correctness and validity (ISO/IEC 25010 | NIST AI RMF: valid)Performance efficiency (ISO/IEC 25010)
Risks mitigated: Retrieval failures propagating to the LLM

Sources

Ch1.7A: T. Nguyen, "Relational Reasoning with Knowledge Graphs - The Fundamentals, Integration, and Extraction," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 1.7A. ISBN: 9798244538229.
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.
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.
Ch3.2: T. Nguyen, "Compare Agent Performance Across Tasks and Datasets," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 3.2. ISBN: 9798244538229.
Ch3.3: T. Nguyen, "Web Navigation and Interaction Benchmarks," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 3.3. ISBN: 9798244538229.
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.
Ch3.9: T. Nguyen, "Reasoning Quality," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 3.9. ISBN: 9798244538229.
Ch3.10: T. Nguyen, "Efficiency Metrics," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 3.10. ISBN: 9798244538229.
Ch5.9: T. Nguyen, "Working Memory," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 5.9. ISBN: 9798244538229.
Ch6.4: T. Nguyen, "Data Quality Fundamentals," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 6.4. ISBN: 9798244538229.
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.
Ch6.6: T. Nguyen, "Query Decomposition and Adaptive Retrieval," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 6.6. ISBN: 9798244538229.
Ch7.1A: T. Nguyen, "Advanced Implementation with Nvidia NEMO Framework and Nvlink," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 7.1A. ISBN: 9798244538229.
Ch7.1B: T. Nguyen, "Nvidia NIM and Colang," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 7.1B. ISBN: 9798244538229.
Ch7.5: T. Nguyen, "NeMo Curator, Riva Speech AI & Multimodal Integration," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 7.5. ISBN: 9798244538229.
Ch9.4: T. Nguyen, "Fairness and Bias Mitigation," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 9.4. ISBN: 9798244538229.
Ch9.5: T. Nguyen, "Constitutional AI," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 9.5. ISBN: 9798244538229.
Ch10.1: T. Nguyen, "Conversational UI," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 10.1. ISBN: 9798244538229.
Ref6.01: S. Schürch, "How to Make Your LLM More Accurate with RAG & Fine-Tuning," Towards Data Science, Mar. 11, 2025. [Online]. Available: https://towardsdatascience.com/how-to-make-your-llm-more-accurate-with-rag-fine-tuning/
Ref7.03: NVIDIA, "Overview," NVIDIA NeMo Guardrails Library Developer Guide. Accessed: Sep. 27, 2026. [Online]. Available: https://docs.nvidia.com/nemo/guardrails/about-nemo-guardrails-library/overview
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/
Ref7.14: "NVIDIA Agentic AI Platform Ecosystem Integration," unpublished reference note (14-NVIDIA-Ecosystem-Integration.md), Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam supplementary materials, 2026. unpublished note