Amazon Bedrock
Last updated
Last updated
Amazon Bedrock integration allows you to bring your own Amazon Bedrock API Key and models into LLM Labs. This feature enhances security compliance by giving you complete control and privacy over your data. By using your own Large Language Models (LLMs), you can ensure that sensitive information remains within your organization's ecosystem.
Navigate to the Models page under LLM Labs menu.
Open My models tab, and click the Manage providers button.
Choose Amazon Bedrock as the provider, and insert your external ID, Role ARN, and Region.
Once you have connected your Amazon Bedrock Models to LLM Labs, you will see a list of available LLM Models that you have already deployed in Amazon Bedrock. You can immediately use these models within LLM Labs.
Choose Roles and then choose Create role.
Choose Custom trust policy in the trusted entity type section.
Paste the following configurations in custom trust policy. Don't forget to replace the ExternalID.
After that, click on Next.
In the Add permissions section, pick the policy AmazonBedrockFullAccess. Then, click on Next.
Enter a Role name and a Description (optional).
Choose Create role.
After that, back on the Roles page, click on your newly created role.
Copy the Role ARN from the page and paste it in Amazon Bedrock manage provider dialog. And click Add Credentials to connect.
To disconnect Amazon Bedrock from Datasaur, follow these steps:
Go to the Models page under the LLM Labs menu.
Open My models tab and select Manage providers.
Click View details next to the Amazon Bedrock provider.
Click Disconnect and confirm the action.
The models will be accessible to all workspace members for use in their projects. Additionally, only the Admin can remove the Amazon Bedrock provider from the workspace.
Open the IAM console at .
Datasaur supports a wide range of models available in Amazon Bedrock. You can find the list of supported models here: .
Additionally, you can bring your own fine-tuned models from Amazon Bedrock into Datasaur, allowing for greater customization and performance tailored to your specific use cases. .
