Function createConcisenessEvaluator

createConcisenessEvaluator<
RecordType extends Record<string, unknown> = ConcisenessEvaluationRecord,
>(
args: ConcisenessEvaluatorArgs<RecordType>,
): ClassificationEvaluator<RecordType>
Creates a conciseness evaluator function.

This function returns an evaluator that determines whether a given output is concise and free of unnecessary content such as pleasantries, hedging, meta-commentary, or redundant information.
Type Parameters
- RecordType extends Record<string, unknown> = ConcisenessEvaluationRecord
Parameters
- args: ConcisenessEvaluatorArgs<RecordType>
  The arguments for creating the conciseness 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 ConcisenessEvaluationRecord and returns a classification result indicating whether the output is concise or verbose.
Example
```
const evaluator = createConcisenessEvaluator({ model: openai("gpt-4o-mini") });
const result = await evaluator.evaluate({
  input: "What is the capital of France?",
  output: "Paris.",
});
console.log(result.label); // "concise" or "verbose"
```
- Defined in llm/createConcisenessEvaluator.ts:52