CfnEvaluatorProps
- class aws_cdk.aws_bedrockagentcore.CfnEvaluatorProps(*, evaluator_config, evaluator_name, level, description=None, tags=None)
Bases:
objectProperties for defining a
CfnEvaluator.- Parameters:
evaluator_config (
Union[IResolvable,EvaluatorConfigProperty,Dict[str,Any]]) – The configuration that defines how an evaluator assesses agent performance.evaluator_name (
str) – The name of the evaluator. Must be unique within your account.level (
str)description (
Optional[str]) – The description of the evaluator.tags (
Optional[Sequence[Union[CfnTag,Dict[str,Any]]]]) – A list of tags to assign to the evaluator.
- See:
- ExampleMetadata:
fixture=_generated
Example:
from aws_cdk import CfnTag # The code below shows an example of how to instantiate this type. # The values are placeholders you should change. from aws_cdk import aws_bedrockagentcore as bedrockagentcore # additional_model_request_fields: Any cfn_evaluator_props = bedrockagentcore.CfnEvaluatorProps( evaluator_config=bedrockagentcore.CfnEvaluator.EvaluatorConfigProperty( llm_as_aJudge=bedrockagentcore.CfnEvaluator.LlmAsAJudgeEvaluatorConfigProperty( instructions="instructions", model_config=bedrockagentcore.CfnEvaluator.EvaluatorModelConfigProperty( bedrock_evaluator_model_config=bedrockagentcore.CfnEvaluator.BedrockEvaluatorModelConfigProperty( model_id="modelId", # the properties below are optional additional_model_request_fields=additional_model_request_fields, inference_config=bedrockagentcore.CfnEvaluator.InferenceConfigurationProperty( max_tokens=123, temperature=123, top_p=123 ) ) ), rating_scale=bedrockagentcore.CfnEvaluator.RatingScaleProperty( categorical=[bedrockagentcore.CfnEvaluator.CategoricalScaleDefinitionProperty( definition="definition", label="label" )], numerical=[bedrockagentcore.CfnEvaluator.NumericalScaleDefinitionProperty( definition="definition", label="label", value=123 )] ) ) ), evaluator_name="evaluatorName", level="level", # the properties below are optional description="description", tags=[CfnTag( key="key", value="value" )] )
Attributes
- description
The description of the evaluator.
- evaluator_config
The configuration that defines how an evaluator assesses agent performance.
- evaluator_name
The name of the evaluator.
Must be unique within your account.
- level
-
- Type:
see
- tags
A list of tags to assign to the evaluator.