Home icon

Use Amazon Bedrock tooling with Amazon SageMaker JumpStart models

Machine Learning Blog



This article announces a new capability that allows users to deploy over 100 models from Amazon SageMaker JumpStart and register them with Amazon Bedrock, enabling seamless access through Bedrock APIs.

  • Users can now deploy SageMaker JumpStart models and use Amazon Bedrock features like Knowledge Bases and Guardrails
  • The Converse API provides a consistent interface for interacting with different models
  • Developers can now use a single API to invoke models from Amazon Bedrock and SageMaker JumpStart
  • The integration allows for advanced capabilities like Retrieval Augmented Generation (RAG) and content filtering
  • The feature is available in all AWS Regions where Amazon Bedrock is supported

The walkthrough demonstrates how to deploy a Gemma 2 9B Instruct model, register it with Bedrock, and use it with various Bedrock APIs and features like knowledge bases and guardrails.



Go to article

The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.

Related articles

Dec 3
2024
Announcing Amazon Bedrock IDE in preview as part of Amazon SageMaker Unified Studio
Mar 13
2025
Amazon Bedrock’s capabilities now generally available within Amazon SageMaker Unified Studio
Jul 9
2025
Configure fine-grained access to Amazon Bedrock models using Amazon SageMaker Unified Studio
Mar 26
2025
Amazon SageMaker JumpStart adds fine-tuning support for models in a private model hub

The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.