Contents

init(allPass:percentagePass:)

Creates a new tool-call expectations evaluator.

Declaration

init(allPass: Metric, percentagePass: Metric)

Parameters

  • allPass:

    The metric for the strict pass or fail result.

  • percentagePass:

    The metric for the partial score result.

Discussion

The evaluator evaluates expectations once and produces two columns: a strict score (pass or fail) and a partial score (proportion matched).

let allPassMetric = Metric("Tools All Pass")
let percentagePassMetric = Metric("Tools Percentage Pass")

let evaluator = ToolCallEvaluator<ModelSample<String>>(
    allPass: allPassMetric,
    percentagePass: percentagePassMetric
)