rpk ai guardrail update
Update a Guardrail.
| This command was introduced in ai version 0.2.94. |
Flags
| Value | Type | Description |
|---|---|---|
|
string |
Etag. |
|
string |
Name shown in the UI, up to 253 characters. Defaults to the identifier. |
|
string |
Notes shown with the guardrail in the UI, up to 1,024 characters. |
|
string |
Returned when an input policy blocks a prompt. 1 to 500 characters. Shared by every input-blocking policy. |
|
string |
Returned when an output policy blocks a response. 1 to 500 characters. Shared by every output-blocking policy. |
|
bool |
Turns the whole guardrail on or off. While off, no policy runs and configuration is kept. Changes take effect within about 30 seconds. (true when set; pass |
|
string |
AWS region where the Bedrock guardrail is created, for example us-east-1. Content filters, contextual grounding, and automated reasoning aren’t available in every region. (required in its group). |
|
string |
Supplies AWS credentials and region. Selecting a provider doesn’t attach the guardrail to it. |
|
bool |
Default chain. (selects this credentials mode; takes no value). |
|
string |
Secret store key that holds the AWS access key ID, in UPPER_SNAKE_CASE (for example, AWS_ACCESS_KEY_ID). The credentials need permission to manage Bedrock guardrails in the configured region. (required in its group). |
|
string |
Secret store key that holds the AWS secret access key, in UPPER_SNAKE_CASE (for example, AWS_SECRET_ACCESS_KEY). (required in its group). |
|
string |
ARN of the IAM role to assume through STS (arn:aws:iam::<account-id>:role/<role-name>). The trust policy must allow Redpanda to assume the role, and the role must be able to manage Bedrock guardrails in the configured region. Creating the guardrail calls AWS, so before you create it, the trust policy must require the External ID <environment ID>/guardrail/<guardrail name>. A role in another AWS account, or one whose trust policy names a whole account, must be under the /redpanda-adp/ path. (required in its group). |
|
string |
Session name recorded in CloudTrail for calls this guardrail makes. Defaults to a Redpanda-supplied name. |
|
bool |
Turns all content categories on or off. Configuration is kept while off. Categories run only while the guardrail is enabled. (true when set; pass |
|
string |
Detection sensitivity. Low flags only high-confidence matches. High flags any non-negligible match. None records a score without acting. (one of: none, low, medium, high). |
|
string |
Action on a match. None records the match and passes content through. Block returns the blocked input or output message and stops the request. (one of: none, block). |
|
strings |
Content types to inspect. Text only when empty. Image requires a region and model with multimodal guardrail support. (one of: text, image; repeatable; replaces the full list on update). |
|
string |
Detection sensitivity. Low flags only high-confidence matches. High flags any non-negligible match. None records a score without acting. (one of: none, low, medium, high). |
|
string |
Action on a match. None records the match and passes content through. Block returns the blocked input or output message and stops the request. (one of: none, block). |
|
strings |
Content types to inspect. Text only when empty. Image requires a region and model with multimodal guardrail support. (one of: text, image; repeatable; replaces the full list on update). |
|
string |
Detection sensitivity. Low flags only high-confidence matches. High flags any non-negligible match. None records a score without acting. (one of: none, low, medium, high). |
|
string |
Action on a match. None records the match and passes content through. Block returns the blocked input or output message and stops the request. (one of: none, block). |
|
strings |
Content types to inspect. Text only when empty. Image requires a region and model with multimodal guardrail support. (one of: text, image; repeatable; replaces the full list on update). |
|
string |
Detection sensitivity. Low flags only high-confidence matches. High flags any non-negligible match. None records a score without acting. (one of: none, low, medium, high). |
|
string |
Action on a match. None records the match and passes content through. Block returns the blocked input or output message and stops the request. (one of: none, block). |
|
strings |
Content types to inspect. Text only when empty. Image requires a region and model with multimodal guardrail support. (one of: text, image; repeatable; replaces the full list on update). |
|
string |
Detection sensitivity. Low flags only high-confidence matches. High flags any non-negligible match. None records a score without acting. (one of: none, low, medium, high). |
|
string |
Action on a match. None records the match and passes content through. Block returns the blocked input or output message and stops the request. (one of: none, block). |
|
strings |
Content types to inspect. Text only when empty. Image requires a region and model with multimodal guardrail support. (one of: text, image; repeatable; replaces the full list on update). |
|
string |
Detection sensitivity. Low flags only high-confidence matches. High flags any non-negligible match. None records a score without acting. (one of: none, low, medium, high). |
|
string |
Action on a match. None records the match and passes content through. Block returns the blocked input or output message and stops the request. (one of: none, block). |
|
strings |
Content types to inspect. Text only when empty. Image requires a region and model with multimodal guardrail support. (one of: text, image; repeatable; replaces the full list on update). |
|
string |
Detection sensitivity. Low flags only high-confidence matches. High flags any non-negligible match. None records a score without acting. (one of: none, low, medium, high). |
|
string |
Action on a match. None records the match and passes content through. Block returns the blocked input or output message and stops the request. (one of: none, block). |
|
strings |
Content types to inspect. Text only when empty. Image requires a region and model with multimodal guardrail support. (one of: text, image; repeatable; replaces the full list on update). |
|
string |
Detection sensitivity. Low flags only high-confidence matches. High flags any non-negligible match. None records a score without acting. (one of: none, low, medium, high). |
|
string |
Action on a match. None records the match and passes content through. Block returns the blocked input or output message and stops the request. (one of: none, block). |
|
strings |
Content types to inspect. Text only when empty. Image requires a region and model with multimodal guardrail support. (one of: text, image; repeatable; replaces the full list on update). |
|
string |
Detection sensitivity. Low flags only high-confidence matches. High flags any non-negligible match. None records a score without acting. (one of: none, low, medium, high). |
|
string |
Action on a match. None records the match and passes content through. Block returns the blocked input or output message and stops the request. (one of: none, block). |
|
strings |
Content types to inspect. Text only when empty. Image requires a region and model with multimodal guardrail support. (one of: text, image; repeatable; replaces the full list on update). |
|
string |
Detection sensitivity. Low flags only high-confidence matches. High flags any non-negligible match. None records a score without acting. (one of: none, low, medium, high). |
|
string |
Action on a match. None records the match and passes content through. Block returns the blocked input or output message and stops the request. (one of: none, block). |
|
strings |
Content types to inspect. Text only when empty. Image requires a region and model with multimodal guardrail support. (one of: text, image; repeatable; replaces the full list on update). |
|
string |
Detection sensitivity. Low flags only high-confidence matches. High flags any non-negligible match. None records a score without acting. (one of: none, low, medium, high). |
|
string |
Action on a match. None records the match and passes content through. Block returns the blocked input or output message and stops the request. (one of: none, block). |
|
strings |
Content types to inspect. Text only when empty. Image requires a region and model with multimodal guardrail support. (one of: text, image; repeatable; replaces the full list on update). |
|
string |
Detection sensitivity. Low flags only high-confidence matches. High flags any non-negligible match. None records a score without acting. (one of: none, low, medium, high). |
|
string |
Action on a match. None records the match and passes content through. Block returns the blocked input or output message and stops the request. (one of: none, block). |
|
strings |
Content types to inspect. Text only when empty. Image requires a region and model with multimodal guardrail support. (one of: text, image; repeatable; replaces the full list on update). |
|
bool |
Turns word filtering on or off. Configuration is kept while off. Matching is exact and case-insensitive, so misspellings and paraphrases don’t match. (true when set; pass |
|
stringArray |
Custom word groups. Every word in a group shares the group’s input and output action. Up to 10,000 words across all groups. (repeatable; protojson object; replaces the full list on update). |
|
stringArray |
Platform-curated word lists, such as the AWS-managed profanity list, with an action per direction. (repeatable; protojson object; replaces the full list on update). |
|
bool |
Turns denied topics on or off. Configuration is kept while off. Matching is semantic, so paraphrases and misspellings match. (true when set; pass |
|
stringArray |
Topics denied by meaning, each with a name, definition, and optional examples. 1 to 30 topics. (repeatable; name (bare values comma-split) or protojson object; replaces the full list on update). |
|
bool |
Turns sensitive-information detection on or off. Configuration is kept while off. (true when set; pass |
|
stringArray |
Rules for the 31 built-in entity types, such as email address, phone number, credit card number, or US Social Security number. One rule per type. (repeatable; protojson object; replaces the full list on update). |
|
stringArray |
RE2 patterns for identifiers the built-in types don’t cover, such as internal account IDs. Bedrock doesn’t support lookahead or lookbehind. (repeatable; name (bare values comma-split) or protojson object; replaces the full list on update). |
|
bool |
Turns contextual grounding on or off. Configuration is kept while off. Checks run on output only and require a grounding source and query in the request. (true when set; pass |
|
bool |
Turns this check on or off independently. Configuration is kept while off. (true when set; pass |
|
float |
Minimum score from 0.0 to 0.99. The action fires below it. Higher values flag more responses. |
|
string |
Action on a low score. None records the result and passes the response through. Block returns the blocked output message and stops the request. (one of: none, block). |
|
bool |
Turns this check on or off independently. Configuration is kept while off. (true when set; pass |
|
float |
Minimum score from 0.0 to 0.99. The action fires below it. Higher values flag more responses. |
|
string |
Action on a low score. None records the result and passes the response through. Block returns the blocked output message and stops the request. (one of: none, block). |
|
bool |
Turns automated reasoning on or off. Configuration is kept while off. Findings are added to the response trace. Requests are never blocked. (true when set; pass |
|
strings |
ARNs of one or two published Bedrock Automated Reasoning policies. Each ARN ends in a numeric version such as :1. DRAFT versions are rejected. (repeatable; replaces the full list on update). |
|
float |
Confidence required for a definitive finding, from 0.0 to 1.0. Lower-confidence results are reported as ambiguous. |
|
string |
AWS region of the companion Bedrock guardrail for delegated families, for example us-east-1. Feature availability varies by region. (required in its group). |
|
string |
Identifier of a Bedrock LLM provider whose AWS credentials the delegated families use. |
|
bool |
Default chain. (selects this credentials mode; takes no value). |
|
string |
Secret store key that holds the AWS access key ID, in UPPER_SNAKE_CASE (for example, AWS_ACCESS_KEY_ID). The credentials need permission to manage Bedrock guardrails in the configured region. (required in its group). |
|
string |
Secret store key that holds the AWS secret access key, in UPPER_SNAKE_CASE (for example, AWS_SECRET_ACCESS_KEY). (required in its group). |
|
string |
ARN of the IAM role to assume through STS (arn:aws:iam::<account-id>:role/<role-name>). The trust policy must allow Redpanda to assume the role, and the role must be able to manage Bedrock guardrails in the configured region. Creating the guardrail calls AWS, so before you create it, the trust policy must require the External ID <environment ID>/guardrail/<guardrail name>. A role in another AWS account, or one whose trust policy names a whole account, must be under the /redpanda-adp/ path. (required in its group). |
|
string |
Session name recorded in CloudTrail for calls this guardrail makes. Defaults to a Redpanda-supplied name. |
|
string |
Engine for word filters. Local runs in the gateway and keeps text in the cluster. Bedrock runs in the companion guardrail. Unset uses the platform default. (one of: local, bedrock). |
|
bool |
Runs the local engine alongside Bedrock and reports differences without enforcing them. Not yet available. (true when set; pass |
|
bool |
Turns word filtering on or off. Configuration is kept while off. Matching is exact and case-insensitive, so misspellings and paraphrases don’t match. (true when set; pass |
|
stringArray |
Custom word groups. Every word in a group shares the group’s input and output action. Up to 10,000 words across all groups. (repeatable; protojson object; replaces the full list on update). |
|
stringArray |
Platform-curated word lists, such as the profanity list, with an action per direction. (repeatable; protojson object; replaces the full list on update). |
|
string |
Engine for custom patterns. Local runs in the gateway and keeps text in the cluster. Bedrock runs in the companion guardrail. Unset uses the platform default. (one of: local, bedrock). |
|
bool |
Runs the local engine alongside Bedrock and reports differences without enforcing them. Not yet available. (true when set; pass |
|
bool |
Turns custom-pattern detection on or off. Configuration is kept while off. (true when set; pass |
|
stringArray |
RE2 patterns for identifiers the built-in types don’t cover, such as internal account IDs. Lookahead and lookbehind aren’t supported. (repeatable; name (bare values comma-split) or protojson object; replaces the full list on update). |
|
string |
Engine for built-in PII entities. Local runs in the gateway and keeps text in the cluster. Bedrock runs in the companion guardrail. Unset uses the platform default. (one of: local, bedrock). |
|
bool |
Runs the local engine alongside Bedrock and reports differences without enforcing them. Not yet available. (true when set; pass |
|
bool |
Turns sensitive-information detection on or off. Configuration is kept while off. (true when set; pass |
|
stringArray |
Rules for the 31 built-in entity types, such as email address, phone number, credit card number, or US Social Security number. (repeatable; protojson object; replaces the full list on update). |
|
string |
Engine for prompt attacks. Local runs in the gateway and keeps text in the cluster. Bedrock runs in the companion guardrail. Unset uses the platform default. (one of: local, bedrock). |
|
bool |
Runs the local engine alongside Bedrock and reports differences without enforcing them. Not yet available. (true when set; pass |
|
bool |
Turns prompt-attack detection on or off. (true when set; pass |
|
string |
Detection sensitivity. Low flags only high-confidence matches. High flags any non-negligible match. None records a score without acting. (one of: none, low, medium, high). |
|
string |
Action on a match. None records the match and passes content through. Block returns the blocked input message and stops the request. (one of: none, block). |
|
strings |
Content types to inspect. Text only when empty. Image requires engine support. (one of: text, image; repeatable; replaces the full list on update). |
|
string |
Engine for harm categories. Local runs in the gateway and keeps text in the cluster. Bedrock runs in the companion guardrail. Unset uses the platform default. (one of: local, bedrock). |
|
bool |
Runs the local engine alongside Bedrock and reports differences without enforcing them. Not yet available. (true when set; pass |
|
bool |
Turns all content categories on or off. Configuration is kept while off. Categories run only while the guardrail is enabled. (true when set; pass |
|
string |
Detection sensitivity. Low flags only high-confidence matches. High flags any non-negligible match. None records a score without acting. (one of: none, low, medium, high). |
|
string |
Action on a match. None records the match and passes content through. Block returns the blocked input or output message and stops the request. (one of: none, block). |
|
strings |
Content types to inspect. Text only when empty. Image requires engine support. (one of: text, image; repeatable; replaces the full list on update). |
|
string |
Detection sensitivity. Low flags only high-confidence matches. High flags any non-negligible match. None records a score without acting. (one of: none, low, medium, high). |
|
string |
Action on a match. None records the match and passes content through. Block returns the blocked input or output message and stops the request. (one of: none, block). |
|
strings |
Content types to inspect. Text only when empty. Image requires engine support. (one of: text, image; repeatable; replaces the full list on update). |
|
string |
Detection sensitivity. Low flags only high-confidence matches. High flags any non-negligible match. None records a score without acting. (one of: none, low, medium, high). |
|
string |
Action on a match. None records the match and passes content through. Block returns the blocked input or output message and stops the request. (one of: none, block). |
|
strings |
Content types to inspect. Text only when empty. Image requires engine support. (one of: text, image; repeatable; replaces the full list on update). |
|
string |
Detection sensitivity. Low flags only high-confidence matches. High flags any non-negligible match. None records a score without acting. (one of: none, low, medium, high). |
|
string |
Action on a match. None records the match and passes content through. Block returns the blocked input or output message and stops the request. (one of: none, block). |
|
strings |
Content types to inspect. Text only when empty. Image requires engine support. (one of: text, image; repeatable; replaces the full list on update). |
|
string |
Detection sensitivity. Low flags only high-confidence matches. High flags any non-negligible match. None records a score without acting. (one of: none, low, medium, high). |
|
string |
Action on a match. None records the match and passes content through. Block returns the blocked input or output message and stops the request. (one of: none, block). |
|
strings |
Content types to inspect. Text only when empty. Image requires engine support. (one of: text, image; repeatable; replaces the full list on update). |
|
string |
Detection sensitivity. Low flags only high-confidence matches. High flags any non-negligible match. None records a score without acting. (one of: none, low, medium, high). |
|
string |
Action on a match. None records the match and passes content through. Block returns the blocked input or output message and stops the request. (one of: none, block). |
|
strings |
Content types to inspect. Text only when empty. Image requires engine support. (one of: text, image; repeatable; replaces the full list on update). |
|
string |
Detection sensitivity. Low flags only high-confidence matches. High flags any non-negligible match. None records a score without acting. (one of: none, low, medium, high). |
|
string |
Action on a match. None records the match and passes content through. Block returns the blocked input or output message and stops the request. (one of: none, block). |
|
strings |
Content types to inspect. Text only when empty. Image requires engine support. (one of: text, image; repeatable; replaces the full list on update). |
|
string |
Detection sensitivity. Low flags only high-confidence matches. High flags any non-negligible match. None records a score without acting. (one of: none, low, medium, high). |
|
string |
Action on a match. None records the match and passes content through. Block returns the blocked input or output message and stops the request. (one of: none, block). |
|
strings |
Content types to inspect. Text only when empty. Image requires engine support. (one of: text, image; repeatable; replaces the full list on update). |
|
string |
Detection sensitivity. Low flags only high-confidence matches. High flags any non-negligible match. None records a score without acting. (one of: none, low, medium, high). |
|
string |
Action on a match. None records the match and passes content through. Block returns the blocked input or output message and stops the request. (one of: none, block). |
|
strings |
Content types to inspect. Text only when empty. Image requires engine support. (one of: text, image; repeatable; replaces the full list on update). |
|
string |
Detection sensitivity. Low flags only high-confidence matches. High flags any non-negligible match. None records a score without acting. (one of: none, low, medium, high). |
|
string |
Action on a match. None records the match and passes content through. Block returns the blocked input or output message and stops the request. (one of: none, block). |
|
strings |
Content types to inspect. Text only when empty. Image requires engine support. (one of: text, image; repeatable; replaces the full list on update). |
|
string |
Engine for denied topics. Local runs in the gateway and keeps text in the cluster. Bedrock runs in the companion guardrail. Unset uses the platform default. (one of: local, bedrock). |
|
bool |
Runs the local engine alongside Bedrock and reports differences without enforcing them. Not yet available. (true when set; pass |
|
bool |
Turns denied topics on or off. Configuration is kept while off. Matching is semantic, so paraphrases and misspellings match. (true when set; pass |
|
stringArray |
Topics denied by meaning, each with a name, definition, and optional examples. 1 to 30 topics. (repeatable; name (bare values comma-split) or protojson object; replaces the full list on update). |
|
string |
Engine for grounding. Local runs in the gateway. Bedrock runs in the companion guardrail. Unset uses the platform default. (one of: local, bedrock). |
|
bool |
Runs the local engine alongside Bedrock and reports differences without enforcing them. Not yet available. (true when set; pass |
|
bool |
Turns contextual grounding on or off. Checks run on output only and require a grounding source and query in the request. (true when set; pass |
|
bool |
Turns this check on or off independently. (true when set; pass |
|
float |
Minimum score from 0.0 to 0.99. The action fires below it. |
|
string |
Action on a low score. None records the result. Block returns the blocked output message. (one of: none, block). |
|
bool |
Turns this check on or off independently. (true when set; pass |
|
float |
Minimum score from 0.0 to 0.99. The action fires below it. |
|
string |
Action on a low score. None records the result. Block returns the blocked output message. (one of: none, block). |
|
string |
Automated reasoning is available only on Amazon Bedrock, so its engine can’t be set to local. (one of: local, bedrock). |
|
bool |
Shadow evaluation is not available for automated reasoning. (true when set; pass |
|
bool |
Turns automated reasoning on or off. Findings are added to the response trace. Requests are never blocked. (true when set; pass |
|
strings |
ARNs of one or two published Bedrock Automated Reasoning policies. Each ARN ends in a numeric version such as :1. DRAFT versions are rejected. (repeatable; replaces the full list on update). |
|
float |
Confidence required for a definitive finding, from 0.0 to 1.0. Lower-confidence results are reported as ambiguous. |
|
stringArray |
Tags. (repeatable key=value; replaces the full map on update). |
|
string |
manifest to update from (YAML or JSON; "-" for stdin); flags override file values. |
|
bool |
print the request that would be sent (with the computed update mask) and exit without calling the server. |
|
strings |
field paths to clear (added to the update mask with the field unset), for example, |
|
strings |
override the inferred update mask with exactly these paths help for update. |
Global flags
| Value | Type | Description |
|---|---|---|
|
string |
Redpanda or |
|
stringArray |
Override |
|
bool |
Ignore |
|
string |
|
|
bool |
Enable verbose logging. |