Chunking Policy

Data artifactKnowledge & DataKnowledge & Dataarc:ChunkingPolicy

A configuration fixing target chunk size, overlap, minimum chunk size and boundary-seeking order for a document chunker.

Responsibility. Parameterizes how documents are segmented into retrievable chunks.

Also known as: Chunking parameters, Chunking strategy

Direct neighbourhood (hover for relationship types)

Relationships

As stated by the sources; verify before use.

512-token target, 50-token overlap, 100-token minimum chunk (Ch6.3A).
128-256-token chunks improved precision but hurt recall; 1024-2048-token chunks improved context completeness but reduced precision (Ch6.3A).

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.
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/