Function createCompletenessEvaluator

createCompletenessEvaluator<
    RecordType extends
        Record<string, unknown> = CompletenessEvaluationRecord,
>(
    args: CompletenessEvaluatorArgs<RecordType>,
): ClassificationEvaluator<RecordType>
Creates a completeness evaluator.

This function returns an evaluator that checks whether every active user request in a conversation was actually completed, not merely acknowledged.
Type Parameters
- RecordType extends Record<string, unknown> = CompletenessEvaluationRecord
Parameters
- args: CompletenessEvaluatorArgs<RecordType>
  The arguments for creating the completeness evaluator.
  - Optionalchoices?: ClassificationChoicesMap
  - OptionalinputMapping?: ObjectMapping<RecordType>
    
    The mapping of the input to evaluate to the shape that the evaluator expects
  - model: EvaluationModelV4 | LanguageModel
  - Optionalname?: string
  - OptionaloptimizationDirection?: OptimizationDirection
  - OptionalpromptTemplate?: PromptTemplate
  - Optionaltelemetry?: TelemetryConfig
Returns ClassificationEvaluator<RecordType>
An evaluator function that takes a CompletenessEvaluationRecord and returns a classification result indicating whether the conversation is complete or incomplete.
Example
```
const evaluator = createCompletenessEvaluator({ model: openai("gpt-4o-mini") });
const result = await evaluator.evaluate({
  conversation:
    "User: Reset my password and update the billing address.\nAssistant: Your password has been reset.",
});
console.log(result.label); // "incomplete"
```
- Defined in llm/createCompletenessEvaluator.ts:55