get_evaluator¶
Operation¶
get_evaluator
¶
get_evaluator(request: GetEvaluatorInput | GetEvaluatorInputDict | None = None, /, *, plugins: list[Plugin] | None = None, **kwargs: Unpack[GetEvaluatorInputDict]) -> GetEvaluatorOutput
Retrieves detailed information about an evaluator, including its configuration, status, and metadata. Works with both built-in and custom evaluators.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
request
|
GetEvaluatorInput | GetEvaluatorInputDict | None
|
The input as a model or dictionary. Pass this or keyword arguments, not both. |
None
|
plugins
|
list[Plugin] | None
|
A list of callables that modify the configuration dynamically. Changes made by these plugins only apply for the duration of the operation execution and will not affect any other operation invocations. |
None
|
**kwargs
|
Unpack[GetEvaluatorInputDict]
|
The input fields as keyword arguments. |
{}
|
Returns:
| Type | Description |
|---|---|
GetEvaluatorOutput
|
An instance of |
get_evaluator
async
¶
get_evaluator(request: GetEvaluatorInput | GetEvaluatorInputDict | None = None, /, *, plugins: list[Plugin] | None = None, **kwargs: Unpack[GetEvaluatorInputDict]) -> GetEvaluatorOutput
Retrieves detailed information about an evaluator, including its configuration, status, and metadata. Works with both built-in and custom evaluators.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
request
|
GetEvaluatorInput | GetEvaluatorInputDict | None
|
The input as a model or dictionary. Pass this or keyword arguments, not both. |
None
|
plugins
|
list[Plugin] | None
|
A list of callables that modify the configuration dynamically. Changes made by these plugins only apply for the duration of the operation execution and will not affect any other operation invocations. |
None
|
**kwargs
|
Unpack[GetEvaluatorInputDict]
|
The input fields as keyword arguments. |
{}
|
Returns:
| Type | Description |
|---|---|
GetEvaluatorOutput
|
An instance of |
Input¶
Pass the input as keyword arguments, a positional dictionary, or a positional model object. Pass plugins separately as a keyword argument.
GetEvaluatorInputDict
¶
Bases: TypedDict
Dictionary form of GetEvaluatorInput.
Attributes¶
evaluator_id
instance-attribute
¶
The unique identifier of the evaluator to retrieve. Can be a built-in evaluator ID (e.g., Builtin.Helpfulness) or a custom evaluator ID.
included_data
instance-attribute
¶
included_data: str | None
Controls which data is returned in the response. ALL_DATA (default)
returns the full evaluator including decrypted instructions and rating
scale. For evaluators encrypted with a customer managed KMS key, this
requires kms:Decrypt permission on the key. METADATA_ONLY returns
evaluator metadata and model configuration without instructions or
rating scale, and does not require any KMS permissions.
GetEvaluatorInput
dataclass
¶
Bases: _SerdeShape
Dataclass for GetEvaluatorInput structure.
Attributes¶
evaluator_id
class-attribute
instance-attribute
¶
evaluator_id: str | None = ...
The unique identifier of the evaluator to retrieve. Can be a built-in evaluator ID (e.g., Builtin.Helpfulness) or a custom evaluator ID.
included_data
class-attribute
instance-attribute
¶
included_data: str | None = ...
Controls which data is returned in the response. ALL_DATA (default)
returns the full evaluator including decrypted instructions and rating
scale. For evaluators encrypted with a customer managed KMS key, this
requires kms:Decrypt permission on the key. METADATA_ONLY returns
evaluator metadata and model configuration without instructions or
rating scale, and does not require any KMS permissions.
Output¶
GetEvaluatorOutput
dataclass
¶
Bases: _SerdeShape
Dataclass for GetEvaluatorOutput structure.
Attributes¶
description
class-attribute
instance-attribute
¶
description: str | None = ...
The description of the evaluator.
evaluator_arn
instance-attribute
¶
evaluator_arn: str
The Amazon Resource Name (ARN) of the evaluator.
evaluator_config
instance-attribute
¶
evaluator_config: EvaluatorConfig
The configuration of the evaluator, including LLM-as-a-Judge or code-based settings.
evaluator_type
class-attribute
instance-attribute
¶
evaluator_type: str | None = ...
The kind of evaluator resource. Valid values:
-
Builtin-- An Amazon Web Services-managed global evaluator. -
ThirdParty-- An Amazon Web Services-managed global evaluator from a third-party provider. -
Custom-- A customer-created evaluator. -
CustomCode-- A customer-created code-based evaluator. -
CustomDerived-- A customer-created evaluator derived from an existing base evaluator.
kms_key_arn
class-attribute
instance-attribute
¶
kms_key_arn: str | None = ...
The Amazon Resource Name (ARN) of the customer managed KMS key used to encrypt the evaluator's sensitive data. This field is only present for evaluators encrypted with a customer managed key.
level
instance-attribute
¶
level: str
The evaluation level (TOOL_CALL, TRACE, or SESSION) that
determines the scope of evaluation.
locked_for_modification
class-attribute
instance-attribute
¶
locked_for_modification: bool | None = ...
Whether the evaluator is locked for modification due to being referenced by active online evaluation configurations.
provider
class-attribute
instance-attribute
¶
provider: str | None = ...
The source of the evaluator's logic: Amazon Web Services, a third-party library, or you.
response_metadata
class-attribute
instance-attribute
¶
Metadata about the response that produced this output. Use this to recover the request identifiers a service's support team needs in order to investigate a call. Members of the metadata are individually optional.