GENREL04-BP02 Implement a model catalog
Model catalogs store and manage model versions. They act as a reliable store for models which may need to be deployed or rolled back at any time. They also facilitate decoupled deployment automation.
Desired outcome: When implemented, this best practice improves the reliability of your generative AI workload by helping to make sure the deployed model is the appropriate model for the given use case.
Benefits of establishing this best practice: Manage change through automation - Implementing a model catalog helps to automate the process of deploying and rolling back model versions.
Level of risk exposed if this best practice is not established: Low
Implementation guidance
Model catalogs provide a centralized location to review models, model version, and model cards. Traditionally, model catalogs are meant to store model artifacts developed by customers. Foundation models are rarely developed from scratch, and as a result, foundation model catalogs should maintain first-party models, third-party models, and custom models developed from third-party models.
Customers should consider implementing a model catalog for foundation models that records and tracks model access, model versions, and model card information. Consider using the Amazon Bedrock model catalog in the AWS Management Console to track available models. Amazon Bedrock's model catalog facilitates model subscriptions to third-party models in the Amazon Bedrock Marketplace as well. Model catalogs should provide a central location for model management, particularly if there is a need to roll back to a particular model or model version.
Implementation steps
-
Navigate to the model catalog in Amazon Bedrock.
-
Select a model from the catalog.
-
Select the appropriate option from the list (for example, open in playground or customize).
-
For self-hosted models, consider the bring your own endpoint feature.
Resources
Related practices:
Related guides, videos, and documentation:
Related examples:
