Module Values.EvaluationDatasetMetricConfigSource

Defines the prompt datasets, built-in metric names and custom metric names, and the task type.

Sourcetype nonrec t = {
  1. taskType : EvaluationTaskType.t;
    (*

    The the type of task you want to evaluate for your evaluation job. This applies only to model evaluation jobs and is ignored for knowledge base evaluation jobs.

    *)
  2. dataset : EvaluationDataset.t;
    (*

    Specifies the prompt dataset.

    *)
  3. metricNames : EvaluationMetricNames.t;
    (*

    The names of the metrics you want to use for your evaluation job. For knowledge base evaluation jobs that evaluate retrieval only, valid values are "Builtin.ContextRelevance", "Builtin.ContextCoverage". For knowledge base evaluation jobs that evaluate retrieval with response generation, valid values are "Builtin.Correctness", "Builtin.Completeness", "Builtin.Helpfulness", "Builtin.LogicalCoherence", "Builtin.Faithfulness", "Builtin.Harmfulness", "Builtin.Stereotyping", "Builtin.Refusal". For automated model evaluation jobs, valid values are "Builtin.Accuracy", "Builtin.Robustness", and "Builtin.Toxicity". In model evaluation jobs that use a LLM as judge you can specify "Builtin.Correctness", "Builtin.Completeness", "Builtin.Faithfulness", "Builtin.Helpfulness", "Builtin.Coherence", "Builtin.Relevance", "Builtin.FollowingInstructions", "Builtin.ProfessionalStyleAndTone", You can also specify the following responsible AI related metrics only for model evaluation job that use a LLM as judge "Builtin.Harmfulness", "Builtin.Stereotyping", and "Builtin.Refusal". For human-based model evaluation jobs, the list of strings must match the name parameter specified in HumanEvaluationCustomMetric.

    *)
}
Sourceval context_ : string
Sourceval make : taskType:EvaluationTaskType.t -> dataset:EvaluationDataset.t -> metricNames:EvaluationMetricNames.t -> unit -> t
Sourceval to_value : t -> [> `Structure of (string * [> `Enum of string | `List of [> `String of EvaluationMetricName.t ] list | `Structure of (string * [> `String of EvaluationDatasetName.t | `Structure of (string * [> `String of S3Uri.t ]) list ]) list ]) list ]
Sourceval to_query : t -> Awso.Client.Query.t
Sourceval of_xml : Awso.Xml.t -> t
Sourceval of_string : string -> t
Sourceval of_json : Yojson.Safe.t -> t
Sourceval to_json : t -> Yojson.Safe.t