本文為英文版的機器翻譯版本，如內容有任何歧義或不一致之處，概以英文版為準。
在 Amazon Bedrock 中使用您的 SageMaker AI JumpStart 模型
您可以註冊從 Amazon SageMaker JumpStart 部署到 Amazon Bedrock 的模型。使用 Amazon Bedrock，您可以在多個端點後方託管模型。您也可以使用 Amazon Bedrock 功能，例如代理程式和知識庫。如需使用 Amazon Bedrock 模型的詳細資訊，請參閱 https://docs.aws.amazon.com/bedrock/latest/userguide/amazon-bedrock-marketplace.html。
重要
若要將模型遷移至 Amazon Bedrock，我們建議您將 AmazonBedrockFullAccess 政策連接至您的 IAM 角色。如果您無法連接 受管政策，請確定您的 IAM 角色具有下列許可：
{ "Version": "2012-10-17", "Statement": [ { "Sid": "BedrockAll", "Effect": "Allow", "Action": [ "bedrock:*" ], "Resource": "*" }, { "Sid": "DescribeKey", "Effect": "Allow", "Action": [ "kms:DescribeKey" ], "Resource": "arn:*:kms:*:::*" }, { "Sid": "APIsWithAllResourceAccess", "Effect": "Allow", "Action": [ "iam:ListRoles", "ec2:DescribeVpcs", "ec2:DescribeSubnets", "ec2:DescribeSecurityGroups" ], "Resource": "*" }, { "Sid": "MarketplaceModelEndpointMutatingAPIs", "Effect": "Allow", "Action": [ "sagemaker:CreateEndpoint", "sagemaker:CreateEndpointConfig", "sagemaker:CreateModel", "sagemaker:CreateInferenceComponent", "sagemaker:DeleteInferenceComponent", "sagemaker:DeleteEndpoint", "sagemaker:UpdateEndpoint" ], "Resource": [ "arn:aws:sagemaker:*:*:endpoint/*", "arn:aws:sagemaker:*:*:endpoint-config/*", "arn:aws:sagemaker:*:*:model/*" ], "Condition": { "StringEquals": { "aws:CalledViaLast": "bedrock.amazonaws.com" } } }, { "Sid": "BedrockEndpointTaggingOperations", "Effect": "Allow", "Action": [ "sagemaker:AddTags", "sagemaker:DeleteTags" ], "Resource": [ "arn:aws:sagemaker:*:*:endpoint/*", "arn:aws:sagemaker:*:*:endpoint-config/*", "arn:aws:sagemaker:*:*:model/*" ] }, { "Sid": "MarketplaceModelEndpointNonMutatingAPIs", "Effect": "Allow", "Action": [ "sagemaker:DescribeEndpoint", "sagemaker:DescribeEndpointConfig", "sagemaker:DescribeModel", "sagemaker:DescribeInferenceComponent", "sagemaker:ListEndpoints", "sagemaker:ListTags" ], "Resource": [ "arn:aws:sagemaker:*:*:endpoint/*", "arn:aws:sagemaker:*:*:endpoint-config/*", "arn:aws:sagemaker:*:*:model/*" ], "Condition": { "StringEquals": { "aws:CalledViaLast": "bedrock.amazonaws.com" } } }, { "Sid": "BedrockEndpointInvokingOperations", "Effect": "Allow", "Action": [ "sagemaker:InvokeEndpoint", "sagemaker:InvokeEndpointWithResponseStream" ], "Resource": [ "arn:aws:sagemaker:*:*:endpoint/*" ], "Condition": { "StringEquals": { "aws:CalledViaLast": "bedrock.amazonaws.com" } } }, { "Sid": "DiscoveringMarketplaceModel", "Effect": "Allow", "Action": [ "sagemaker:DescribeHubContent" ], "Resource": [ "arn:aws:sagemaker:*:aws:hub-content/SageMakerPublicHub/Model/*", "arn:aws:sagemaker:*:aws:hub/SageMakerPublicHub" ] }, { "Sid": "AllowMarketplaceModelsListing", "Effect": "Allow", "Action": [ "sagemaker:ListHubContents" ], "Resource": "arn:aws:sagemaker:*:aws:hub/SageMakerPublicHub" }, { "Sid": "RetrieveSubscribedMarketplaceLicenses", "Effect": "Allow", "Action": [ "license-manager:ListReceivedLicenses" ], "Resource": [ "*" ] }, { "Sid": "PassRoleToSageMaker", "Effect": "Allow", "Action": [ "iam:PassRole" ], "Resource": [ "arn:aws:iam::*:role/*Sagemaker*ForBedrock*" ], "Condition": { "StringEquals": { "iam:PassedToService": [ "sagemaker.amazonaws.com", "bedrock.amazonaws.com" ] } } }, { "Sid": "PassRoleToBedrock", "Effect": "Allow", "Action": [ "iam:PassRole" ], "Resource": "arn:aws:iam::*:role/*AmazonBedrock*", "Condition": { "StringEquals": { "iam:PassedToService": [ "bedrock.amazonaws.com" ] } } } ] }
重要
Amazon Bedrock 完整存取政策僅提供 Amazon Bedrock API 的許可。若要在 中使用 Amazon Bedrock AWS Management Console，您的 IAM 角色也必須具有下列許可：
{ "Sid": "AllowConsoleS3AccessForBedrockMarketplace", "Effect": "Allow", "Action": [ "s3:GetObject", "s3:GetBucketCORS", "s3:ListBucket", "s3:ListBucketVersions", "s3:GetBucketLocation" ], "Resource": "*" }
如果您要撰寫自己的政策，則必須包含允許 資源的 Amazon Bedrock Marketplace 動作的政策陳述式。例如，下列政策允許 Amazon Bedrock 為您已部署到端點的模型使用 InvokeModel操作。
{ "Version": "2012-10-17", "Statement": [ { "Sid": "BedrockAll", "Effect": "Allow", "Action": [ "bedrock:InvokeModel" ], "Resource": [ "arn:aws:bedrock:AWS 區域:111122223333:marketplace/example-model-endpoint/all-access" ] }, { "Sid": "VisualEditor1", "Effect": "Allow", "Action": ["sagemaker:InvokeEndpoint"], "Resource": "arn:aws:sagemaker:AWS 區域:111122223333:endpoint/*", "Condition": { "StringEquals": { "aws:ResourceTag/project": "example-project-id", "aws:CalledViaLast": "bedrock.amazonaws.com" } } } ] }
部署模型之後，您可以在 Amazon Bedrock 中使用模型。若要查看您是否可以在 Amazon Bedrock 中使用，請在 Studio UI 中導覽至模型詳細資訊卡。如果模型卡顯示已就緒，則可以向 Amazon Bedrock 註冊模型。
重要
根據預設，Amazon SageMaker JumpStart 會停用您所部署模型的網路存取。如果您已啟用網路存取，您將無法搭配 Amazon Bedrock 使用模型。如果您想要搭配 Amazon Bedrock 使用模型，則必須在網路存取停用的情況下重新部署模型。
若要搭配 Amazon Bedrock 使用，請導覽至端點詳細資訊頁面，然後選擇 Studio UI 右上角的搭配使用 Bedrock。看到快顯視窗後，選擇註冊到 Bedrock。
