Policy: AWS > Bedrock > Guardrail > Settings > Content Policy > Hate Filter Input Strength
Filter strength applied to hate-speech content in model input. Defaults to the AWS-recommended baseline (MEDIUM); set to HIGH to tighten or NONE to disable input filtering for this category. The HATE filter is included in the enforced filtersConfig when this OR the matching output strength is non-NONE; if both are NONE, the HATE filter is removed from the guardrail entirely.
Targets
This policy targets the following resource types:
Primary Policy
This policy is used with the following primary policy:
Controls
Setting this policy configures this control:
Policy Packs
This policy setting is used by the following policy packs:
Policy Specification
Schema Type | |
|---|---|
Default | |
Valid Values [YAML] |
|
Examples [YAML] | HIGH |
Category
In Your Workspace
Developers
- tmod:@turbot/turbot#/control/categories/security
- tmod:@turbot/aws-bedrock#/policy/types/bedrockGuardrailSettingsContentPolicyHateFilterInputStrength
- turbot graphql policy-type --id "tmod:@turbot/aws-bedrock#/policy/types/bedrockGuardrailSettingsContentPolicyHateFilterInputStrength"
- turbot graphql policy-settings --filter "policyTypeId:tmod:@turbot/aws-bedrock#/policy/types/bedrockGuardrailSettingsContentPolicyHateFilterInputStrength"
Get Policy TypeGet Policy Settings
Category URI
Policy Type URI
GraphQL
CLI