Amazon Bedrock Runtime code examples for the SDK for .NET

Overview

Shows how to use the AWS SDK for .NET to work with Amazon Bedrock Runtime.

Amazon Bedrock Runtime is a fully managed service that makes it easy to use foundation models from third-party providers and Amazon.

⚠ Important

• Running this code might result in charges to your AWS account. For more details, see AWS Pricing and Free Tier.
• Running the tests might result in charges to your AWS account.
• We recommend that you grant your code least privilege. At most, grant only the minimum permissions required to perform the task. For more information, see Grant least privilege.
• This code is not tested in every AWS Region. For more information, see AWS Regional Services.

Code examples

Prerequisites

For prerequisites, see the README in the dotnetv3 folder.

Scenarios

Code examples that show you how to accomplish a specific task by calling multiple functions within the same service.

• Tool use with the Converse API

Amazon Nova

• Converse
• ConverseStream
• Scenario: Tool use with the Converse API

Amazon Nova Canvas

• InvokeModel

Anthropic Claude

• InvokeModelWithResponseStream

Cohere Command

• InvokeModel: Command R and R+
• InvokeModelWithResponseStream: Command R and R+

Meta Llama

• InvokeModel
• InvokeModelWithResponseStream

Mistral AI

• InvokeModel
• InvokeModelWithResponseStream

Run the examples

Instructions

For general instructions to run the examples, see the README in the dotnetv3 folder.

Some projects might include a settings.json file. Before compiling the project, you can change these values to match your own account and resources. Alternatively, add a settings.local.json file with your local settings, which will be loaded automatically when the application runs.

After the example compiles, you can run it from the command line. To do so, navigate to the folder that contains the .csproj file and run the following command:

dotnet run

Alternatively, you can run the example from within your IDE.

Tool use with the Converse API

This example shows you how to build a typical interaction between an application, a generative AI model, and connected tools or APIs to mediate interactions between the AI and the outside world. It uses the example of connecting an external weather API to the AI model so it can provide real-time weather information based on user input.

Tests

⚠ Running tests might result in charges to your AWS account.

To find instructions for running these tests, see the README in the dotnetv3 folder.

Additional resources

• Amazon Bedrock Runtime User Guide
• Amazon Bedrock Runtime API Reference
• SDK for .NET Amazon Bedrock Runtime reference

Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.

SPDX-License-Identifier: Apache-2.0