You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
By default, all of the AWS SDKs (including boto3) attempt to dynamically retrieve temporary credentials using a "metadata endpoint" on EC2 instances, Lambda Functions, and AWS Fargate tasks. This authentication mechanism avoids the requirement of providing static credentials from an AWS IAM User account, in favor of creating an IAM Role identity.
According to the documentation for MetaGPT, the only supported authentication mechanism for Amazon Bedrock is to create an IAM User, with a static access key and secret key.
Could you please support using the default IAM Instance Profile, which requires no additional configuration, provided that MetaGPT is running on AWS Fargate or EC2 instances?
Boto3 will look in several locations when searching for credentials. The mechanism in which Boto3 looks for credentials is to search through a list of possible locations and stop as soon as it finds credentials. The order in which Boto3 searches for credentials is:
Passing credentials as parameters in the boto3.client() method
Passing credentials as parameters when creating a Session object
Environment variables
Assume role provider
Assume role with web identity provider
AWS IAM Identity Center credential provider
Shared credential file (~/.aws/credentials)
AWS config file (~/.aws/config)
Boto2 config file (/etc/boto.cfg and ~/.boto)
Container credential provider
Instance metadata service on an Amazon EC2 instance that has an IAM role configured.
I'm referring to 10 and 11 in the above screenshot, rather than specifying static credentials.
Honestly, it's quite possible that MetaGPT already supports this authentication mechanism for Bedrock, but I don't see documentation (for MetaGPT) on how to configure it to use the default credential chain.
The text was updated successfully, but these errors were encountered:
Feature description
By default, all of the AWS SDKs (including
boto3
) attempt to dynamically retrieve temporary credentials using a "metadata endpoint" on EC2 instances, Lambda Functions, and AWS Fargate tasks. This authentication mechanism avoids the requirement of providing static credentials from an AWS IAM User account, in favor of creating an IAM Role identity.According to the documentation for MetaGPT, the only supported authentication mechanism for Amazon Bedrock is to create an IAM User, with a static access key and secret key.
Could you please support using the default IAM Instance Profile, which requires no additional configuration, provided that MetaGPT is running on AWS Fargate or EC2 instances?
In AWS Fargate, it's called a "Task Role": https://docs.aws.amazon.com/AmazonECS/latest/developerguide/task-iam-roles.html
For EC2 instances it's called the "IAM Instance Profile": https://docs.aws.amazon.com/IAM/latest/UserGuide/id_roles_use_switch-role-ec2_instance-profiles.html
Here's the
boto3
documentation that describes the process that the AWS SDK uses to "find" credentials: https://boto3.amazonaws.com/v1/documentation/api/latest/guide/credentials.htmlBoto3 will look in several locations when searching for credentials. The mechanism in which Boto3 looks for credentials is to search through a list of possible locations and stop as soon as it finds credentials. The order in which Boto3 searches for credentials is:
I'm referring to 10 and 11 in the above screenshot, rather than specifying static credentials.
Honestly, it's quite possible that MetaGPT already supports this authentication mechanism for Bedrock, but I don't see documentation (for MetaGPT) on how to configure it to use the default credential chain.
The text was updated successfully, but these errors were encountered: