article thumbnail

Redacting PII data at The Very Group with Amazon Comprehend

AWS Machine Learning

This is guest post by Andy Whittle, Principal Platform Engineer – Application & Reliability Frameworks at The Very Group. At The Very Group , which operates digital retailer Very, security is a top priority in handling data for millions of customers. Some decisions had to be made to enable the solution.

article thumbnail

Use AWS PrivateLink to set up private access to Amazon Bedrock

AWS Machine Learning

It allows developers to build and scale generative AI applications using FMs through an API, without managing infrastructure. Customers are building innovative generative AI applications using Amazon Bedrock APIs using their own proprietary data.

APIs 130
Insiders

Sign Up for our Newsletter

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

article thumbnail

Build a foundation model (FM) powered customer service bot with agents for Amazon Bedrock

AWS Machine Learning

The structured prompts include a sequence of question-thought-action-observation examples. The action is an API that the model can invoke from an allowed set of APIs. Action groups are tasks that the agent can perform autonomously. It, then, uses the API schema to invoke corresponding code in the Lambda function.

APIs 92
article thumbnail

Provide live agent assistance for your chatbot users with Amazon Lex and Talkdesk cloud contact center

AWS Machine Learning

For example, the following figure shows screenshots of a chatbot transitioning a customer to a live agent chat (courtesy of WaFd Bank). If the request to the Talkdesk API is successful, a Talkdesk conversation ID is returned to Amazon Lex. Solution overview The following diagram illustrates the solution architecture.

article thumbnail

Knowledge Bases for Amazon Bedrock now supports metadata filtering to improve retrieval accuracy

AWS Machine Learning

For example, you can use legal documents with similar terms for different contexts, or movies that have a similar plot released in different years. Filters on the operating system or application version, for example, can help avoid retrieving obsolete or irrelevant documents. Metadata can be string, number, or Boolean.

APIs 111
article thumbnail

Use the Amazon SageMaker and Salesforce Data Cloud integration to power your Salesforce apps with AI/ML

AWS Machine Learning

Although we use a specific algorithm to train the model in our example, you can use any algorithm that you find appropriate for your use case. When a version of the model in the Amazon SageMaker Model Registry is approved, the endpoint is exposed as an API with Amazon API Gateway using a custom Salesforce JSON Web Token (JWT) authorizer.

APIs 82
article thumbnail

Amazon SageMaker Feature Store now supports cross-account sharing, discovery, and access

AWS Machine Learning

For example, in an application that recommends a music playlist, features could include song ratings, listening duration, and listener demographics. SageMaker Feature Store now makes it effortless to share, discover, and access feature groups across AWS accounts. Features are inputs to ML models used during training and inference.