Amazon Bedrock Guardrails enable you to implement safeguards for your generative AI applications based on your use cases and responsible AI policies. Starting today, we are excited to announce that Amazon Bedrock Guardrails adds multilingual capabilities with support for Spanish and French languages.
Amazon Bedrock Guardrails help you implement safeguards for building safe, generative AI applications by filtering undesirable content, redacting personally identifiable information (PII), and enhancing content safety and privacy. You can configure policies for content filters, denied topics, word filters, PII redaction, and contextual grounding checks to tailor safeguards to your specific use cases and responsible AI policies.
With support for Spanish and French languages, a wider set of users in multiple geographies can now use Bedrock Guardrails to build safer generative AI applications based on their use cases and responsible AI policies.
To learn more about Amazon Bedrock Guardrails, see the product page and the technical documentation.
Source:: Amazon AWS