Jupyternaut with Amazon Bedrock¶
(Return to the Chat Interface page)
Bedrock supports many language model providers such as Amazon, Anthropic, Arcee AI, AutoGluon, BRIA AI, Camb.ai, Cohere, DeepSeek, Google, HuggingFace, IBM, Inception, Liquid AI, Meta, Mistral AI, Moonshot, NVIDIA, OpenAI, Qwen, Stability, Writer, etc., this is a sample of the many providers that are available. To use the base models from any supported provider make sure to enable them in Amazon Bedrock by using the AWS console. You should also select embedding models in Bedrock in addition to language completion models if you intend to use retrieval augmented generation (RAG) on your documents.
Go to Amazon Bedrock and select Model Access as shown here:
Click through on Model Catalog to see all the available models. Serverless foundation models are now automatically enabled across all AWS commercial regions when first invoked in your account, so you can start using them instantly. You no longer need to manually activate model access through this page. Note that for Anthropic models, some first-time users may need to submit use case details before they can access the model. For serverless models served from AWS Marketplace, a user with AWS Marketplace permissions must invoke the model once to enable it account-wide. After this one-time enablement, all users can access the model without needing these permissions.
Account administrators retain full control over model access through IAM policies and Service Control Policies to restrict model access as needed.
To get started, simply select a model from the Model catalog and open it in the playground or invoke the model using the InvokeModel or Converse API operations. Note that for Anthropic models, some first-time users may need to submit use case details before they can access the model. Review our documentation for the complete list of available models.
All Bedrock serverless foundation model EULAs can be accessed here. EULAs can also be accessed from the model details page in the Model catalog.
You may now select a chosen Bedrock model from the drop-down menu box titled Chat model in the Jupyternaut settings tab (via the Settings dropdown). An example of the bedrock provider models is shown:
If your provider requires an API key, please enter it in the box that will show for that provider. Make sure to click on Save Changes to ensure that the inputs have been saved.