invoke_guardrail_checks¶
Operation¶
async
¶
invoke_guardrail_checks(input: InvokeGuardrailChecksInput, plugins: list[Plugin] | None = None) -> InvokeGuardrailChecksOutput
Evaluates messages against inline guardrail checks. You specify the check configurations directly in the request, and Amazon Bedrock returns per-check results with severity or confidence scores.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
input
|
InvokeGuardrailChecksInput
|
An instance of |
required |
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
|
Returns:
| Type | Description |
|---|---|
InvokeGuardrailChecksOutput
|
An instance of |
Input¶
dataclass
¶
Dataclass for InvokeGuardrailChecksInput structure.
Attributes¶
class-attribute
instance-attribute
¶
checks: GuardrailChecksConfig | None = None
The inline check configurations that specify which guardrail checks to run against the messages.
class-attribute
instance-attribute
¶
messages: list[GuardrailChecksMessage] | None = None
The messages to evaluate against the specified guardrail checks. Each message includes a role and one or more content blocks.
Output¶
dataclass
¶
Dataclass for InvokeGuardrailChecksOutput structure.
Attributes¶
instance-attribute
¶
results: GuardrailChecksResults
The per-check results containing findings from the guardrail evaluation.
instance-attribute
¶
usage: GuardrailChecksUsageResults
The per-check text unit consumption for the guardrail evaluation.