apply_guardrail¶
Operation¶
async
¶
apply_guardrail(input: ApplyGuardrailInput, plugins: list[Plugin] | None = None) -> ApplyGuardrailOutput
The action to apply a guardrail.
For troubleshooting some of the common errors you might encounter when
using the ApplyGuardrail API, see Troubleshooting Amazon Bedrock API
Error
Codes
in the Amazon Bedrock User Guide
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
input
|
ApplyGuardrailInput
|
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 |
|---|---|
ApplyGuardrailOutput
|
An instance of |
Input¶
dataclass
¶
Dataclass for ApplyGuardrailInput structure.
Attributes¶
class-attribute
instance-attribute
¶
content: list[GuardrailContentBlock] | None = None
The content details used in the request to apply the guardrail.
class-attribute
instance-attribute
¶
guardrail_identifier: str | None = None
The guardrail identifier used in the request to apply the guardrail.
class-attribute
instance-attribute
¶
guardrail_version: str | None = None
The guardrail version used in the request to apply the guardrail.
class-attribute
instance-attribute
¶
output_scope: GuardrailOutputScope | None = None
Specifies the scope of the output that you get in the response. Set to
FULL to return the entire output, including any detected and
non-detected entries in the response for enhanced debugging.
Note that the full output scope doesn't apply to word filters or regex in sensitive information filters. It does apply to all other filtering policies, including sensitive information with filters that can detect personally identifiable information (PII).
class-attribute
instance-attribute
¶
source: GuardrailContentSource | None = None
The source of data used in the request to apply the guardrail.
Output¶
dataclass
¶
Dataclass for ApplyGuardrailOutput structure.
Attributes¶
instance-attribute
¶
action: GuardrailAction
The action taken in the response from the guardrail.
class-attribute
instance-attribute
¶
action_reason: str | None = None
The reason for the action taken when harmful content is detected.
instance-attribute
¶
assessments: list[GuardrailAssessment]
The assessment details in the response from the guardrail.
class-attribute
instance-attribute
¶
guardrail_coverage: GuardrailCoverage | None = None
The guardrail coverage details in the apply guardrail response.
instance-attribute
¶
outputs: list[GuardrailOutputContent]
The output details in the response from the guardrail.
instance-attribute
¶
usage: GuardrailUsage
The usage details in the response from the guardrail.