AI integration with Amazon Bedrock

Note: This feature is available in Enterprise and AWS editions only.

Table of contents

• Model settings

To use Amazon Bedrock as an AI provider in CloudBeaver, set it up like this:

1. As an administrator, open the AWS console and go to IAM (Identity and Access Management)
2. Create or use an IAM user/account that has permissions to use Bedrock, and generate an Access Key ID and Secret Access Key for this user
3. Insert credentials into CloudBeaver's Model Settings
4. Enter the Region and Model
5. Save changes

Model settings

Setting	Description	default
Model	Choose the AI model. Use Load model list to refresh the available models. You can also type a model name manually.
Region	AWS region where Bedrock is enabled for your account, such as us-east-1 or eu-central-1.
AWS Access key	Your AWS access key with permissions to call Amazon Bedrock.
AWS Secret key	Your AWS secret key.
AWS Session token	Session token for temporary AWS credentials, such as those issued by STS or federated authentication.
3rd party role name	Name of the AWS IAM role to assume when using cross-account or third-party access.
Context size	A larger number allows the AI to use more data for better answers but may slow down response time.
Temperature	Control AI's creativity from 0.0 (more precise) to 0.9 (more diverse). Note that higher temperature can lead to less predictable results.	0.0
Write AWS Bedrock queries to debug log	Log Bedrock requests for troubleshooting and debugging purposes.	off
Cross-account access	Enable access to Amazon Bedrock across AWS accounts using an assumed role.	off