Remove Accountability Remove APIs Remove Government
article thumbnail

Centralize model governance with SageMaker Model Registry Resource Access Manager sharing

AWS Machine Learning

We recently announced the general availability of cross-account sharing of Amazon SageMaker Model Registry using AWS Resource Access Manager (AWS RAM) , making it easier to securely share and discover machine learning (ML) models across your AWS accounts. Human oversight : Including human involvement in AI decision-making processes.

article thumbnail

Amazon Bedrock launches Session Management APIs for generative AI applications (Preview)

AWS Machine Learning

Amazon Bedrock announces the preview launch of Session Management APIs, a new capability that enables developers to simplify state and context management for generative AI applications built with popular open source frameworks such as LangGraph and LlamaIndex. Building generative AI applications requires more than model API calls.

APIs 108
Insiders

Sign Up for our Newsletter

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

Trending Sources

article thumbnail

Enable Amazon Bedrock cross-Region inference in multi-account environments

AWS Machine Learning

Importantly, cross-Region inference prioritizes the connected Amazon Bedrock API source Region when possible, helping minimize latency and improve overall responsiveness. The customers AWS accounts that are allowed to use Amazon Bedrock are under an Organizational Unit (OU) called Sandbox. Sonnet v2 model using cross-Region inference.

article thumbnail

Build a multi-tenant generative AI environment for your enterprise on AWS

AWS Machine Learning

We also dive deeper into access patterns, governance, responsible AI, observability, and common solution designs like Retrieval Augmented Generation. It also uses a number of other AWS services such as Amazon API Gateway , AWS Lambda , and Amazon SageMaker. API Gateway is serverless and hence automatically scales with traffic.

article thumbnail

Considerations for addressing the core dimensions of responsible AI for Amazon Bedrock applications

AWS Machine Learning

For now, we consider eight key dimensions of responsible AI: Fairness, explainability, privacy and security, safety, controllability, veracity and robustness, governance, and transparency. When using the RetrieveAndGenerate API, the output includes the generated response, the source attribution, and the retrieved text chunks.

APIs 108
article thumbnail

Automate building guardrails for Amazon Bedrock using test-driven development

AWS Machine Learning

As companies of all sizes continue to build generative AI applications, the need for robust governance and control mechanisms becomes crucial. Prerequisites Before you start, make sure you have the following prerequisites in place: Create an AWS account , or sign in to your existing account.

APIs 110
article thumbnail

Govern generative AI in the enterprise with Amazon SageMaker Canvas

AWS Machine Learning

This is crucial for compliance, security, and governance. In this post, we analyze strategies for governing access to Amazon Bedrock and SageMaker JumpStart models from within SageMaker Canvas using AWS Identity and Access Management (IAM) policies. We provide code examples tailored to common enterprise governance scenarios.