Generative AI - How to use Apply Guardrail to protect PII data with AWS Bedrock API & Lambda !

In this video, I am going to demonstrate a revision of previously published workshop on how to build a serverless GenAI solution to create call center transcript summary via a Rest API, Lambda and AWS Bedrock Converse API and protect the sensitive information like PII using guardrail policy.
On July 10, 2024, during the AWS New York Summit, AWS announced the introduction of the Apply Guardrail feature for its Generative AI services. Amazon Bedrock, already a standout service in the AWS lineup, gains further flexibility with this new feature, allowing developers to decouple the guardrail from Large Language Model (LLM) invocation using Bedrock.
In June 2024, AWS added support for guardrails via the Converse API. However, a challenge I encountered was that guardrail policies were being applied to both input and response. With additional code for guard content, I was able to accomplish the desired result however it was additional lines of code to meet the use case requirements.
Here's a link to my previous video on how to apply guardrails using the Converse API to protect Personally Identifiable Information (PII). ( • Generative AI - Create... )