开始使用 Anthropic Claude Cohere Command Meta Llama Mistral AI Stable Image Core

使用 Amazon Bedrock 运行时示例 SDK for .NET (v4)

以下代码示例向您展示了如何使用带有 Amazon Bedrock Runtime 的 AWS SDK for .NET (v4) 来执行操作和实现常见场景。

每个示例都包含一个指向完整源代码的链接，您可以从中找到有关如何在上下文中设置和运行代码的说明。

主题

开始使用
Anthropic Claude
Cohere Command
Meta Llama
Mistral AI
Stable Image Core

开始使用

以下代码示例展示了如何开始使用 Amazon Bedrock 运行时。

SDK for .NET (v4)

注意

还有更多相关信息 GitHub。在 AWS 代码示例存储库中查找完整示例，了解如何进行设置和运行。



using Amazon;
using Amazon.BedrockRuntime;
using Amazon.BedrockRuntime.Model;

namespace BedrockRuntimeActions;

/// <summary>
/// This example shows how to use the Converse API to send a text message
/// to Amazon Bedrock.
/// </summary>
internal class HelloBedrockRuntime
{
    static async Task Main(string[] args)
    {
        // Create a Bedrock Runtime client in the AWS Region you want to use.
        // You can change the region to match your setup.
        var client = new AmazonBedrockRuntimeClient(RegionEndpoint.USWest2);

        // Set the model ID, e.g., Claude Haiku.
        // The "global." prefix enables cross-region inference, allowing the request
        // to be routed to the nearest available region for the specified model.
        var modelId = "global.anthropic.claude-haiku-4-5-20251001-v1:0";

        // Define the user message.
        var userMessage = "Hi. In a short paragraph, explain what you can do.";

        // Create a request with the model ID, the user message, and an inference configuration.
        var request = new ConverseRequest
        {
            ModelId = modelId,
            Messages = new List<Message>
            {
                new Message
                {
                    Role = ConversationRole.User,
                    Content = new List<ContentBlock> { new ContentBlock { Text = userMessage } }
                }
            }
        };

        try
        {
            // Send the request to the Bedrock Runtime and wait for the response.
            var response = await client.ConverseAsync(request);

            // Extract and print the response text.
            string responseText = response?.Output?.Message?.Content?[0]?.Text ?? "";
            Console.WriteLine(responseText);
        }
        catch (AmazonBedrockRuntimeException e)
        {
            Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
            throw;
        }
    }
}

有关 API 详细信息，请参阅《AWS SDK for .NET API Reference》中的 Converse。

Anthropic Claude

以下代码示例演示如何使用 Bedrock 的 Converse API 向 Anthropic Claude 发送文本消息。

SDK for .NET (v4)

注意

还有更多相关信息 GitHub。在 AWS 代码示例存储库中查找完整示例，了解如何进行设置和运行。

使用 Bedrock 的 Converse API 向 Anthropic Claude 发送文本消息。


// Use the Converse API to send a text message to Anthropic Claude.

using System;
using System.Collections.Generic;
using Amazon;
using Amazon.BedrockRuntime;
using Amazon.BedrockRuntime.Model;

// Create a Bedrock Runtime client in the AWS Region you want to use.
var client = new AmazonBedrockRuntimeClient(RegionEndpoint.USEast1);

// Set the model ID, e.g., Claude 3 Haiku.
var modelId = "anthropic.claude-3-haiku-20240307-v1:0";

// Define the user message.
var userMessage = "Describe the purpose of a 'hello world' program in one line.";

// Create a request with the model ID, the user message, and an inference configuration.
var request = new ConverseRequest
{
    ModelId = modelId,
    Messages = new List<Message>
    {
        new Message
        {
            Role = ConversationRole.User,
            Content = new List<ContentBlock> { new ContentBlock { Text = userMessage } }
        }
    },
    InferenceConfig = new InferenceConfiguration()
    {
        MaxTokens = 512,
        Temperature = 0.5F,
        TopP = 0.9F
    }
};

try
{
    // Send the request to the Bedrock Runtime and wait for the result.
    var response = await client.ConverseAsync(request);

    // Extract and print the response text.
    string responseText = response?.Output?.Message?.Content?[0]?.Text ?? "";
    Console.WriteLine(responseText);
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

有关 API 详细信息，请参阅《AWS SDK for .NET API Reference》中的 Converse。

以下代码示例演示如何使用 Bedrock 的 Converse API 向 Anthropic Claude 发送文本消息并实时处理响应流。

SDK for .NET (v4)

注意

还有更多相关信息 GitHub。在 AWS 代码示例存储库中查找完整示例，了解如何进行设置和运行。

使用 Bedrock 的 Converse API 向 Anthropic Claude 发送文本消息并实时处理响应流。


// Use the Converse API to send a text message to Anthropic Claude
// and print the response stream.

using System;
using System.Collections.Generic;
using System.Linq;
using Amazon;
using Amazon.BedrockRuntime;
using Amazon.BedrockRuntime.Model;

// Create a Bedrock Runtime client in the AWS Region you want to use.
var client = new AmazonBedrockRuntimeClient(RegionEndpoint.USEast1);

// Set the model ID, e.g., Claude 3 Haiku.
var modelId = "anthropic.claude-3-haiku-20240307-v1:0";

// Define the user message.
var userMessage = "Describe the purpose of a 'hello world' program in one line.";

// Create a request with the model ID, the user message, and an inference configuration.
var request = new ConverseStreamRequest
{
    ModelId = modelId,
    Messages = new List<Message>
    {
        new Message
        {
            Role = ConversationRole.User,
            Content = new List<ContentBlock> { new ContentBlock { Text = userMessage } }
        }
    },
    InferenceConfig = new InferenceConfiguration()
    {
        MaxTokens = 512,
        Temperature = 0.5F,
        TopP = 0.9F
    }
};

try
{
    // Send the request to the Bedrock Runtime and wait for the result.
    var response = await client.ConverseStreamAsync(request);

    // Extract and print the streamed response text in real-time.
    foreach (var chunk in response.Stream.AsEnumerable())
    {
        if (chunk is ContentBlockDeltaEvent)
        {
            Console.Write((chunk as ContentBlockDeltaEvent).Delta.Text);
        }
    }
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

有关 API 的详细信息，请参阅 AWS SDK for .NET API 参考ConverseStream中的。

Cohere Command

以下代码示例演示如何使用 Bedrock 的 Converse API 向 Cohere Command 发送文本消息。

SDK for .NET (v4)

注意

还有更多相关信息 GitHub。在 AWS 代码示例存储库中查找完整示例，了解如何进行设置和运行。

使用 Bedrock 的 Converse API 向 Cohere Command 发送文本消息。


// Use the Converse API to send a text message to Cohere Command.

using System;
using System.Collections.Generic;
using Amazon;
using Amazon.BedrockRuntime;
using Amazon.BedrockRuntime.Model;

// Create a Bedrock Runtime client in the AWS Region you want to use.
var client = new AmazonBedrockRuntimeClient(RegionEndpoint.USEast1);

// Set the model ID, e.g., Command R.
var modelId = "cohere.command-r-v1:0";

// Define the user message.
var userMessage = "Describe the purpose of a 'hello world' program in one line.";

// Create a request with the model ID, the user message, and an inference configuration.
var request = new ConverseRequest
{
    ModelId = modelId,
    Messages = new List<Message>
    {
        new Message
        {
            Role = ConversationRole.User,
            Content = new List<ContentBlock> { new ContentBlock { Text = userMessage } }
        }
    },
    InferenceConfig = new InferenceConfiguration()
    {
        MaxTokens = 512,
        Temperature = 0.5F,
        TopP = 0.9F
    }
};

try
{
    // Send the request to the Bedrock Runtime and wait for the result.
    var response = await client.ConverseAsync(request);

    // Extract and print the response text.
    string responseText = response?.Output?.Message?.Content?[0]?.Text ?? "";
    Console.WriteLine(responseText);
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

有关 API 详细信息，请参阅《AWS SDK for .NET API Reference》中的 Converse。

以下代码示例演示如何使用 Bedrock 的 Converse API 向 Cohere Command 发送文本消息并实时处理响应流。

SDK for .NET (v4)

注意

还有更多相关信息 GitHub。在 AWS 代码示例存储库中查找完整示例，了解如何进行设置和运行。

使用 Bedrock 的 Converse API 向 Cohere Command 发送文本消息并实时处理响应流。


// Use the Converse API to send a text message to Cohere Command
// and print the response stream.

using System;
using System.Collections.Generic;
using System.Linq;
using Amazon;
using Amazon.BedrockRuntime;
using Amazon.BedrockRuntime.Model;

// Create a Bedrock Runtime client in the AWS Region you want to use.
var client = new AmazonBedrockRuntimeClient(RegionEndpoint.USEast1);

// Set the model ID, e.g., Command R.
var modelId = "cohere.command-r-v1:0";

// Define the user message.
var userMessage = "Describe the purpose of a 'hello world' program in one line.";

// Create a request with the model ID, the user message, and an inference configuration.
var request = new ConverseStreamRequest
{
    ModelId = modelId,
    Messages = new List<Message>
    {
        new Message
        {
            Role = ConversationRole.User,
            Content = new List<ContentBlock> { new ContentBlock { Text = userMessage } }
        }
    },
    InferenceConfig = new InferenceConfiguration()
    {
        MaxTokens = 512,
        Temperature = 0.5F,
        TopP = 0.9F
    }
};

try
{
    // Send the request to the Bedrock Runtime and wait for the result.
    var response = await client.ConverseStreamAsync(request);

    // Extract and print the streamed response text in real-time.
    foreach (var chunk in response.Stream.AsEnumerable())
    {
        if (chunk is ContentBlockDeltaEvent)
        {
            Console.Write((chunk as ContentBlockDeltaEvent).Delta.Text);
        }
    }
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

有关 API 的详细信息，请参阅 AWS SDK for .NET API 参考ConverseStream中的。

Meta Llama

以下代码示例演示如何使用 Bedrock 的 Converse API 向 Meta Llama 发送文本消息。

SDK for .NET (v4)

注意

还有更多相关信息 GitHub。在 AWS 代码示例存储库中查找完整示例，了解如何进行设置和运行。

使用 Bedrock 的 Converse API 向 Meta Llama 发送文本消息。


// Use the Converse API to send a text message to Meta Llama.

using System;
using System.Collections.Generic;
using Amazon;
using Amazon.BedrockRuntime;
using Amazon.BedrockRuntime.Model;

// Create a Bedrock Runtime client in the AWS Region you want to use.
var client = new AmazonBedrockRuntimeClient(RegionEndpoint.USEast1);

// Set the model ID, e.g., Llama 3 8b Instruct.
var modelId = "meta.llama3-8b-instruct-v1:0";

// Define the user message.
var userMessage = "Describe the purpose of a 'hello world' program in one line.";

// Create a request with the model ID, the user message, and an inference configuration.
var request = new ConverseRequest
{
    ModelId = modelId,
    Messages = new List<Message>
    {
        new Message
        {
            Role = ConversationRole.User,
            Content = new List<ContentBlock> { new ContentBlock { Text = userMessage } }
        }
    },
    InferenceConfig = new InferenceConfiguration()
    {
        MaxTokens = 512,
        Temperature = 0.5F,
        TopP = 0.9F
    }
};

try
{
    // Send the request to the Bedrock Runtime and wait for the result.
    var response = await client.ConverseAsync(request);

    // Extract and print the response text.
    string responseText = response?.Output?.Message?.Content?[0]?.Text ?? "";
    Console.WriteLine(responseText);
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

有关 API 详细信息，请参阅《AWS SDK for .NET API Reference》中的 Converse。

以下代码示例演示如何使用 Bedrock 的 Converse API 向 Meta Llama 发送文本消息并实时处理响应流。

SDK for .NET (v4)

注意

还有更多相关信息 GitHub。在 AWS 代码示例存储库中查找完整示例，了解如何进行设置和运行。

使用 Bedrock 的 Converse API 向 Meta Llama 发送文本消息并实时处理响应流。


// Use the Converse API to send a text message to Meta Llama
// and print the response stream.

using System;
using System.Collections.Generic;
using System.Linq;
using Amazon;
using Amazon.BedrockRuntime;
using Amazon.BedrockRuntime.Model;

// Create a Bedrock Runtime client in the AWS Region you want to use.
var client = new AmazonBedrockRuntimeClient(RegionEndpoint.USEast1);

// Set the model ID, e.g., Llama 3 8b Instruct.
var modelId = "meta.llama3-8b-instruct-v1:0";

// Define the user message.
var userMessage = "Describe the purpose of a 'hello world' program in one line.";

// Create a request with the model ID, the user message, and an inference configuration.
var request = new ConverseStreamRequest
{
    ModelId = modelId,
    Messages = new List<Message>
    {
        new Message
        {
            Role = ConversationRole.User,
            Content = new List<ContentBlock> { new ContentBlock { Text = userMessage } }
        }
    },
    InferenceConfig = new InferenceConfiguration()
    {
        MaxTokens = 512,
        Temperature = 0.5F,
        TopP = 0.9F
    }
};

try
{
    // Send the request to the Bedrock Runtime and wait for the result.
    var response = await client.ConverseStreamAsync(request);

    // Extract and print the streamed response text in real-time.
    foreach (var chunk in response.Stream.AsEnumerable())
    {
        if (chunk is ContentBlockDeltaEvent)
        {
            Console.Write((chunk as ContentBlockDeltaEvent).Delta.Text);
        }
    }
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

有关 API 的详细信息，请参阅 AWS SDK for .NET API 参考ConverseStream中的。

Mistral AI

以下代码示例演示如何使用 Bedrock 的 Converse API 向 Mistral 发送文本消息。

SDK for .NET (v4)

注意

还有更多相关信息 GitHub。在 AWS 代码示例存储库中查找完整示例，了解如何进行设置和运行。

使用 Bedrock 的 Converse API 向 Mistral 发送文本消息。


// Use the Converse API to send a text message to Mistral.

using System;
using System.Collections.Generic;
using Amazon;
using Amazon.BedrockRuntime;
using Amazon.BedrockRuntime.Model;

// Create a Bedrock Runtime client in the AWS Region you want to use.
var client = new AmazonBedrockRuntimeClient(RegionEndpoint.USEast1);

// Set the model ID, e.g., Mistral Large.
var modelId = "mistral.mistral-large-2402-v1:0";

// Define the user message.
var userMessage = "Describe the purpose of a 'hello world' program in one line.";

// Create a request with the model ID, the user message, and an inference configuration.
var request = new ConverseRequest
{
    ModelId = modelId,
    Messages = new List<Message>
    {
        new Message
        {
            Role = ConversationRole.User,
            Content = new List<ContentBlock> { new ContentBlock { Text = userMessage } }
        }
    },
    InferenceConfig = new InferenceConfiguration()
    {
        MaxTokens = 512,
        Temperature = 0.5F,
        TopP = 0.9F
    }
};

try
{
    // Send the request to the Bedrock Runtime and wait for the result.
    var response = await client.ConverseAsync(request);

    // Extract and print the response text.
    string responseText = response?.Output?.Message?.Content?[0]?.Text ?? "";
    Console.WriteLine(responseText);
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

有关 API 详细信息，请参阅《AWS SDK for .NET API Reference》中的 Converse。

以下代码示例演示如何使用 Bedrock 的 Converse API 向 Mistral 发送文本消息并实时处理响应流。

SDK for .NET (v4)

注意

还有更多相关信息 GitHub。在 AWS 代码示例存储库中查找完整示例，了解如何进行设置和运行。

使用 Bedrock 的 Converse API 向 Mistral 发送文本消息并实时处理响应流。


// Use the Converse API to send a text message to Mistral
// and print the response stream.

using System;
using System.Collections.Generic;
using System.Linq;
using Amazon;
using Amazon.BedrockRuntime;
using Amazon.BedrockRuntime.Model;

// Create a Bedrock Runtime client in the AWS Region you want to use.
var client = new AmazonBedrockRuntimeClient(RegionEndpoint.USEast1);

// Set the model ID, e.g., Mistral Large.
var modelId = "mistral.mistral-large-2402-v1:0";

// Define the user message.
var userMessage = "Describe the purpose of a 'hello world' program in one line.";

// Create a request with the model ID, the user message, and an inference configuration.
var request = new ConverseStreamRequest
{
    ModelId = modelId,
    Messages = new List<Message>
    {
        new Message
        {
            Role = ConversationRole.User,
            Content = new List<ContentBlock> { new ContentBlock { Text = userMessage } }
        }
    },
    InferenceConfig = new InferenceConfiguration()
    {
        MaxTokens = 512,
        Temperature = 0.5F,
        TopP = 0.9F
    }
};

try
{
    // Send the request to the Bedrock Runtime and wait for the result.
    var response = await client.ConverseStreamAsync(request);

    // Extract and print the streamed response text in real-time.
    foreach (var chunk in response.Stream.AsEnumerable())
    {
        if (chunk is ContentBlockDeltaEvent)
        {
            Console.Write((chunk as ContentBlockDeltaEvent).Delta.Text);
        }
    }
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

有关 API 的详细信息，请参阅 AWS SDK for .NET API 参考ConverseStream中的。

Stable Image Core

以下代码示例展示了如何在 Amazon Bedrock 上调用 St Stability.ai able Image Core 来生成图像。

SDK for .NET (v4)

注意

还有更多相关信息 GitHub。在 AWS 代码示例存储库中查找完整示例，了解如何进行设置和运行。

使用 Stable Image Core 创建镜像。



        /// <summary>
        /// Asynchronously invokes the Stability.ai Stable Image Core model to run an inference based on the provided input.
        /// </summary>
        /// <param name="prompt">The prompt that describes the image Stability.ai Stable Image Core has to generate.</param>
        /// <returns>A base-64 encoded image generated by model</returns>
        /// <remarks>
        /// The different model providers have individual request and response formats.
        /// For the format, ranges, and default values for Stability.ai Stable Image Core, refer to:
        ///     https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-diffusion-stable-image-core-text-image-request-response.html
        /// </remarks>
        public static async Task<string?> InvokeStableImageCoreAsync(string prompt, int seed)
        {
            string stableImageCoreModelId = "stability.stable-image-core-v1:1";

            AmazonBedrockRuntimeClient client = new(RegionEndpoint.USWest2);

            string payload = new JsonObject()
            {
                { "prompt", prompt },
                { "aspect_ratio", "1:1" },
                { "seed", seed },
                { "output_format", "png" }
            }.ToJsonString();

            try
            {
                InvokeModelResponse response = await client.InvokeModelAsync(new InvokeModelRequest()
                {
                    ModelId = stableImageCoreModelId,
                    Body = AWSSDKUtils.GenerateMemoryStreamFromString(payload),
                    ContentType = "application/json",
                    Accept = "application/json"
                });

                if (response.HttpStatusCode == System.Net.HttpStatusCode.OK)
                {
                    var results = JsonNode.ParseAsync(response.Body).Result?["images"]?.AsArray();

                    return results?[0]?.GetValue<string>();
                }
                else
                {
                    Console.WriteLine("InvokeModelAsync failed with status code " + response.HttpStatusCode);
                }
            }
            catch (AmazonBedrockRuntimeException e)
            {
                Console.WriteLine(e.Message);
            }
            return null;
        }

有关 API 的详细信息，请参阅 AWS SDK for .NET API 参考InvokeModel中的。

Javascript 在您的浏览器中被禁用或不可用。

要使用 Amazon Web Services 文档，必须启用 Javascript。请参阅浏览器的帮助页面以了解相关说明。

文档惯例

Amazon Bedrock

CloudFormation