Function createCorrectnessEvaluator

createCorrectnessEvaluator<
RecordType extends Record<string, unknown> = CorrectnessEvaluationRecord,
>(
args: CorrectnessEvaluatorArgs<RecordType>,
): ClassificationEvaluator<RecordType>
Creates a correctness evaluator function.

This function returns an evaluator that determines whether a given output is factually accurate, complete, logically consistent, and uses precise terminology.
Type Parameters
- RecordType extends Record<string, unknown> = CorrectnessEvaluationRecord
Parameters
- args: CorrectnessEvaluatorArgs<RecordType>
  The arguments for creating the correctness evaluator.
  - Optionalchoices?: ClassificationChoicesMap
  - OptionalinputMapping?: ObjectMapping<RecordType>
    The mapping of the input to evaluate to the shape that the evaluator expects
  - model: LanguageModel
  - Optionalname?: string
  - OptionaloptimizationDirection?: OptimizationDirection
  - OptionalpromptTemplate?: PromptTemplate
  - Optionaltelemetry?: TelemetryConfig
Returns ClassificationEvaluator<RecordType>
An evaluator function that takes a CorrectnessEvaluationRecord and returns a classification result indicating whether the output is correct or incorrect.
Example
```
const evaluator = createCorrectnessEvaluator({ model: openai("gpt-4o-mini") });
const result = await evaluator.evaluate({
  input: "What is the capital of France?",
  output: "Paris is the capital of France.",
});
console.log(result.label); // "correct" or "incorrect"
```
- Defined in llm/createCorrectnessEvaluator.ts:52