AWS bedrock documentation change
Summary
Fixed typographical errors in sensitive information filters and contextual grounding checks documentation
Security assessment
Changes involve minor punctuation corrections (curly quotes to straight quotes) without altering security functionality or addressing vulnerabilities.
Diff
diff --git a/bedrock/latest/userguide/guardrails-components.md b/bedrock/latest/userguide/guardrails-components.md index 7d82a3e89..04ae6b942 100644 --- a//bedrock/latest/userguide/guardrails-components.md +++ b//bedrock/latest/userguide/guardrails-components.md @@ -21 +21 @@ You can configure the following filters with Amazon Bedrock Guardrails: - * **Sensitive information filters** — Can help you detect sensitive content such as Personally Identifiable Information (PII) in standard formats or custom regex entities in user inputs and FM responses. This filter is a probabilistic maching learning (ML) based solution that is context dependent. It detects sensitive information based on the context within input prompts or model responses. Based on your use case, you can block or mask inputs and responses containing sensitive information. For example, you can redact users’ personal information while generating summaries from customer and agent conversation transcripts. + * **Sensitive information filters** — Can help you detect sensitive content such as Personally Identifiable Information (PII) in standard formats or custom regex entities in user inputs and FM responses. This filter is a probabilistic maching learning (ML) based solution that is context dependent. It detects sensitive information based on the context within input prompts or model responses. Based on your use case, you can block or mask inputs and responses containing sensitive information. For example, you can redact users' personal information while generating summaries from customer and agent conversation transcripts. @@ -23 +23 @@ You can configure the following filters with Amazon Bedrock Guardrails: - * **Contextual grounding checks** — Can help you detect and filter hallucinations in model responses if they are not grounded (factually inaccurate or add new information) in the source information or are irrelevant to the user’s query. For example, you can block or flag responses in RAG (retrieval-augmented generation) applications, if the model responses deviate from the information in the retrieved passages or doesn’t answer the question from the user. + * **Contextual grounding checks** — Can help you detect and filter hallucinations in model responses if they are not grounded (factually inaccurate or add new information) in the source information or are irrelevant to the user's query. For example, you can block or flag responses in RAG (retrieval-augmented generation) applications, if the model responses deviate from the information in the retrieved passages or doesn't answer the question from the user.