0 / 0
Context relevance evaluation metric
Last updated: Feb 07, 2025
Context relevance evaluation metric

The context relevance metric measures how relevant the context that your model retrieves is with the question that is specified in the prompt.

Metric details

Context relevance is a retrieval quality metric for generative AI quality evaluations that measures the quality of how retrieval systems rank relevant contexts.

Scope

The context relevance metric evaluates generative AI assets only.

  • Types of AI assets: Prompt templates
  • Generative AI tasks: Retrieval Augmented Generation (RAG)
  • Supported languages: English

Scores and values

The context relevance metric score indicates the relevance of the retrieved contexts to the question in the prompt. Higher scores indicate that the context is more relevant to the question in the prompt. When multiple context variables exist, scores are generated when the metric is calculated with fine-tuned models only.

Range of values: 0.0-1.0

Settings

  • Thresholds:
    • Lower limit: 0
    • Upper limit: 1

Parent topic: Evaluation metrics