AWS bedrock documentation change
Summary
Restructured inference setup documentation to include on-demand deployment option and updated Provisioned Throughput guidance
Security assessment
Operational documentation update about deployment options and billing models. No security controls added or vulnerabilities addressed in visible changes.
Diff
diff --git a/bedrock/latest/userguide/model-customization-use.md b/bedrock/latest/userguide/model-customization-use.md index c532944f9..3275c791c 100644 --- a//bedrock/latest/userguide/model-customization-use.md +++ b//bedrock/latest/userguide/model-customization-use.md @@ -5 +5 @@ -# Use a custom model +# Set up inference for a custom model @@ -7 +7 @@ -Before you can use a customized model, you need to purchase Provisioned Throughput for it. For more information about Provisioned Throughput, see [Increase model invocation capacity with Provisioned Throughput in Amazon Bedrock](./prov-throughput.html). You can then use the resulting provisioned model for inference. Choose the tab for your preferred method, and then follow the steps: +After you create a custom model, you can set up inference using one of the following options: @@ -9 +9 @@ Before you can use a customized model, you need to purchase Provisioned Throughp -Console + * **Purchase Provisioned Throughput** – Purchase Provisioned Throughput for your model to set up dedicated compute capacity with guaranteed throughput for consistent performance and lower latency. @@ -10,0 +11 @@ Console +For more information about Provisioned Throughput, see [Increase model invocation capacity with Provisioned Throughput in Amazon Bedrock](./prov-throughput.html). For more information about using custom models with Provisioned Throughput, see [Purchase Provisioned Throughput for a custom model](./custom-model-use-pt.html). @@ -12 +13 @@ Console -###### To purchase Provisioned Throughput for a custom model. + * **Deploy custom model for on-demand inference (only Amazon Nova models)** – To set up on-demand inference, you deploy the model with a custom model deployment. After you deploy the model, you invoke it using the ARN for the custom model deployment. With on-demand inference, you only pay for what you use and you don't need to set up provisioned compute resources. @@ -14 +15 @@ Console - 1. Sign in to the AWS Management Console with an IAM identity that has permissions to use the Amazon Bedrock console. Then, open the Amazon Bedrock console at [https://console.aws.amazon.com/bedrock/](https://console.aws.amazon.com/bedrock/). +For more information about deploying custom models for on-demand inference, see [Deploy a custom model for on-demand inference](./deploy-custom-model-on-demand.html). @@ -16 +16,0 @@ Console - 2. From the left navigation pane, choose **Custom models** under **Foundation models**. @@ -18 +17,0 @@ Console - 3. In the **Models** tab, choose the radio button next to the model for which you want to buy Provisioned Throughput or select the model name to navigate to the details page. @@ -20 +18,0 @@ Console - 4. Select **Purchase Provisioned Throughput**. @@ -22 +20 @@ Console - 5. For more details, follow the steps at [Purchase a Provisioned Throughput for an Amazon Bedrock model](./prov-thru-purchase.html). +###### Topics @@ -24 +22 @@ Console - 6. After purchasing Provisioned Throughput for your custom model, follow the steps at [Use a Provisioned Throughput with an Amazon Bedrock resource](./prov-thru-use.html). + * [Purchase Provisioned Throughput for a custom model](./custom-model-use-pt.html) @@ -25,0 +24 @@ Console + * [Deploy a custom model for on-demand inference](./deploy-custom-model-on-demand.html) @@ -29,8 +27,0 @@ Console -When you carry out any operation that supports usage of custom models, you will see your custom model as an option in the model selection menu. - -API - - -To purchase Provisioned Throughput for a custom model, follow the steps at [Purchase a Provisioned Throughput for an Amazon Bedrock model](./prov-thru-purchase.html) to send a [CreateProvisionedModelThroughput](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_CreateProvisionedModelThroughput.html) (see link for request and response formats and field details) request with a [Amazon Bedrock control plane endpoint](https://docs.aws.amazon.com/general/latest/gr/bedrock.html#br-cp). Use the name or ARN of your custom model as the `modelId`. The response returns a `provisionedModelArn` that you can use as the `modelId` when making an [InvokeModel](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_InvokeModel.html) or [InvokeModelWithResponseStream](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_InvokeModelWithResponseStream.html) request. - -[See code examples](./model-customization-code-samples.html) @@ -46 +37 @@ View details about a custom model -Share a model for another account to use +Purchase Provisioned Throughput for a custom model