Experience · Data artifact

RAG Query API Schema

Data artifactExperienceExperience & Human Oversightarc:RAGQueryAPISchema

A typed request/response contract for a RAG service that bounds query length and retrieval parameters and structures answers with sources, timing breakdown, token usage and cache status.

Responsibility. Defines and validates the RAG service request/response contract.

Also known as: QueryRequest / QueryResponse models, API contract

Direct neighbourhood (hover for relationship types)

Relationships

constrains control

REST Agent API Ch6.5

Design guidance

SHOULD reject malformed queries at the API boundary and return answers with citations and confidence or timing metadata.

Quantitative guidance

As stated by the sources; verify before use.

Example bounds: query 3-500 characters, top_k 1-20, hybrid alpha 0-1 (Ch6.5).

Classification

Patterns: Schema-driven request validationSelf-documenting OpenAPI contract
Technologies: PydanticOpenAPI
Risks mitigated: Malformed or oversized queriesUnbounded prompt length from excessive top_k

Sources

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.