Knowledge & Data · Data artifact

Vector Search Configuration

Data artifactKnowledge & DataKnowledge & Dataarc:VectorSearchConfig

A query-time configuration setting ANN search depth (ef) and result count (k), adjustable per query without rebuilding the index.

Responsibility. Specifies the runtime accuracy/latency trade-off of each vector search.

Also known as: search_params, Runtime accuracy dial

Direct neighbourhood (hover for relationship types)

Relationships

configures structural

Approximate Vector Search Retriever Ch6.2A

Design guidance

MUST set ef >= k; typically ef = 2-5x k.
SHOULD tune ef dynamically from latency and recall monitoring, reserving higher ef for high-stakes queries.

Quantitative guidance

As stated by the sources; verify before use.

ef=50 ~90% Recall@10, ef=100 ~95%, ef=200 ~98%; diminishing returns beyond 200 (Ch6.2A).

Classification

Patterns: Per-query-class ef (e.g., 50 autocomplete, 100 standard, 200 background analysis)Adaptive ef retry on low confidence

Sources

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.