Exact Vector Search Retriever

Software componentKnowledge & DataKnowledge & Dataarc:ExactVectorSearchRetriever

A vector retriever that computes similarity against every stored vector to return the exact top-K results deterministically.

Responsibility. Retrieves the exact nearest vectors reproducibly.

Also known as: Brute-force / exhaustive vector search, Brute-force search, Exhaustive linear scan

Variant of Vector Retriever abstract

When to choose. Choose when deterministic, reproducible retrieval is required (scientific experiments, compliance audits, A/B testing), accepting slower queries.

Direct neighbourhood (hover for relationship types)

Relationships

reads dependency

Vector Index Store abstract Ch6.2A

alternative to variability

Approximate Vector Search Retriever Ch5.8 Ch6.2A

Quantitative guidance

As stated by the sources; verify before use.

Exact search costs O(N x D): ~1 billion FLOPs per query for 1M x 1024-dim vectors; 100 QPS needs ~100 billion ops/s, missing sub-100 ms targets (Ch6.2A).

Classification

Quality attributes: Reliability (ISO/IEC 25010 | NIST AI RMF: valid and reliable)Transparency and accountability (NIST AI RMF: accountable and transparent)
Risks mitigated: Non-deterministic retrieval undermining audits and experiments

Sources

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.
Ch6.2A: T. Nguyen, "Vector Database Selection," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 6.2A. ISBN: 9798244538229.