AWS bedrock documentation change
Summary
Updated documentation headings and content formatting for ApplyGuardrail API, including terminology changes (e.g. 'Configuring' to 'Specify'), code formatting improvements, and example response structure updates
Security assessment
Changes focus on improving documentation clarity and structure rather than addressing security vulnerabilities. While the content discusses security-related features (PII detection, content filtering), these were already present in previous version. No new security capabilities or vulnerability mitigations are introduced.
Diff
diff --git a/bedrock/latest/userguide/guardrails-use-independent-api.md b/bedrock/latest/userguide/guardrails-use-independent-api.md index 5966e3869..1a87622dc 100644 --- a//bedrock/latest/userguide/guardrails-use-independent-api.md +++ b//bedrock/latest/userguide/guardrails-use-independent-api.md @@ -5 +5 @@ -Calling the ApplyGuardrail API in your app flowConfiguring the guardrail to use with ApplyGuardrail APIExamples of ApplyGuardrail API use casesReturning full assessment output in the ApplyGuardrail API +Call ApplyGuardrail in your application flowSpecify the guardrail to use with ApplyGuardrailExample use cases of ApplyGuardrailReturn full output in ApplyGuardrail response @@ -13 +13 @@ You can use the `ApplyGuardrail` API to assess any text using your pre-configure -Feature of the `ApplyGuardrail` API: +Features of the `ApplyGuardrail` API include: @@ -15 +15 @@ Feature of the `ApplyGuardrail` API: - * Content Validation – You can send any text input or output to the `ApplyGuardrail` API to compare it with your defined topic avoidance rules, content filters, PII detectors, and word block lists. You can evaluate user inputs and FM generated outputs independently. + * **Content validation** – You can send any text input or output to the `ApplyGuardrail` API to compare it with your defined topic avoidance rules, content filters, PII detectors, and word block lists. You can evaluate user inputs and FM generated outputs independently. @@ -17 +17 @@ Feature of the `ApplyGuardrail` API: - * Flexible Deployment – You can integrate the `ApplyGuardrail` API anywhere in your application flow to validate data before processing or serving results to the user. For example, if you are using a RAG application, you can now evaluate the user input prior to performing the retrieval, instead of waiting until the final response generation. + * **Flexible deployment** – You can integrate the `ApplyGuardrail` API anywhere in your application flow to validate data before processing or serving results to the user. For example, if you are using a RAG application, you can now evaluate the user input prior to performing the retrieval, instead of waiting until the final response generation. @@ -19 +19 @@ Feature of the `ApplyGuardrail` API: - * Decoupled from FMs. – `ApplyGuardrail` API is decoupled from foundational models. You can now use Guardrails without invoking Foundation Models. You can use the assessment results to design the experience on your generative AI application. + * **Decoupled from foundation models** – `ApplyGuardrail` API is decoupled from foundational models. You can now use Guardrails without invoking Foundation Models. You can use the assessment results to design the experience on your generative AI application. @@ -26 +26 @@ Feature of the `ApplyGuardrail` API: - * Calling the ApplyGuardrail API in your app flow + * Call ApplyGuardrail in your application flow @@ -28 +28 @@ Feature of the `ApplyGuardrail` API: - * Configuring the guardrail to use with ApplyGuardrail API + * Specify the guardrail to use with ApplyGuardrail @@ -30 +30 @@ Feature of the `ApplyGuardrail` API: - * Examples of ApplyGuardrail API use cases + * Example use cases of ApplyGuardrail @@ -32 +32 @@ Feature of the `ApplyGuardrail` API: - * Returning full assessment output in the ApplyGuardrail API + * Return full output in ApplyGuardrail response @@ -37 +37 @@ Feature of the `ApplyGuardrail` API: -## Calling the ApplyGuardrail API in your app flow +## Call ApplyGuardrail in your application flow @@ -39 +39 @@ Feature of the `ApplyGuardrail` API: -The request allows customer to pass all their content that should be guarded using their defined Guardrails. The source field should be set to “INPUT” when the content to evaluated is from a user, typically the LLM prompt. The source should be set to “OUTPUT” when the model output Guardrails should be enforced, typically an LLM response. +The request allows customer to pass all their content that should be guarded using their defined Guardrails. The source field should be set to `INPUT` when the content to evaluated is from a user (typically the input prompt to the LLM). The source should be set to `OUTPUT` when the model output guardrails should be enforced (typically the LLM response). @@ -41 +41 @@ The request allows customer to pass all their content that should be guarded usi -## Configuring the guardrail to use with ApplyGuardrail API +## Specify the guardrail to use with ApplyGuardrail @@ -43 +43 @@ The request allows customer to pass all their content that should be guarded usi -You specify configuration information for the guardrail in the `guardrailConfig` input parameter. The configuration includes the ID and the version of the guardrail that you want to use. You can also enable tracing for the guardrail, which provides information about the content that the guardrail blocked. +When using `ApplyGuardrail`, you specify the ``guardrailIdentifier`` and ``guardrailVersion`` of the guardrail that you want to use. You can also enable tracing for the guardrail, which provides information about the content that the guardrail blocks. @@ -45 +45 @@ You specify configuration information for the guardrail in the `guardrailConfig` -ApplyGuardrail API Request +ApplyGuardrail API request @@ -53,2 +52 @@ ApplyGuardrail API Request - "content": [ - { + "content": [{ @@ -58,2 +56 @@ ApplyGuardrail API Request - }, - ] + }, ] @@ -62,2 +59 @@ ApplyGuardrail API Request - -ApplyGuardrail API Response +ApplyGuardrail API response @@ -161 +157 @@ ApplyGuardrail API Response -## Examples of ApplyGuardrail API use cases +## Example use cases of ApplyGuardrail @@ -189 +185 @@ Request example -Response if Guardrails did not intervene +Response if guardrails did not intervene @@ -220 +215 @@ Response example - "text": "Configured guardrial canned message, i.e cannot respond", + "text": "Configured guardrail canned message, i.e cannot respond" @@ -257,2 +252 @@ Guardrails intervened with name masking (name is masked) - "outputs": [ - { + "outputs": [{ @@ -262 +256 @@ Guardrails intervened with name masking (name is masked) - "text": "Hello {NAME}, ABC Cars are reliable..", + "text": "Hello {NAME}, ABC Cars are reliable ..." @@ -334 +327 @@ Output example -## Returning full assessment output in the ApplyGuardrail API +## Return full output in ApplyGuardrail response