文档 AWS SDK 示例 GitHub 存储库中还有更多 [S AWS DK 示例](https://github.com/awsdocs/aws-doc-sdk-examples)。

本文属于机器翻译版本。若本译文内容与英语原文存在差异，则一律以英文原文为准。

# 使用 适用于 .NET 的 SDK (v4) 的 Amazon Bedrock 运行时示例
<a name="csharp_4_bedrock-runtime_code_examples"></a>

以下代码示例向您展示了如何使用带有 Amazon Bedrock Runtime 的 适用于 .NET 的 AWS SDK (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。

**Topics**
+ [Anthropic Claude](#anthropic_claude)
+ [Cohere Command](#cohere_command)
+ [Meta Llama](#meta_llama)
+ [Mistral AI](#mistral_ai)

## Anthropic Claude
<a name="anthropic_claude"></a>

### Converse
<a name="bedrock-runtime_Converse_AnthropicClaude_csharp_4_topic"></a>

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。

**适用于 .NET 的 SDK (v4)**  
 还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/dotnetv4/Bedrock-runtime#code-examples)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《适用于 .NET 的 AWS SDK API Reference》**中的 [Converse](https://docs.aws.amazon.com/goto/DotNetSDKV4/bedrock-runtime-2023-09-30/Converse)。

### ConverseStream
<a name="bedrock-runtime_ConverseStream_AnthropicClaude_csharp_4_topic"></a>

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。

**适用于 .NET 的 SDK (v4)**  
 还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/dotnetv4/Bedrock-runtime#code-examples)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 *适用于 .NET 的 AWS SDK API 参考[ConverseStream](https://docs.aws.amazon.com/goto/DotNetSDKV4/bedrock-runtime-2023-09-30/ConverseStream)*中的。

### InvokeModel
<a name="bedrock-runtime_InvokeModel_AnthropicClaude_csharp_4_topic"></a>

以下代码示例演示如何使用调用模型 API 向 Anthropic Claude 发送文本消息。

**适用于 .NET 的 SDK (v4)**  
 还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/dotnetv4/Bedrock-runtime#code-examples)中查找完整示例，了解如何进行设置和运行。
使用调用模型 API 发送文本消息。  

```
// Use the native inference API to send a text message to Anthropic Claude.

using System;
using System.IO;
using System.Text.Json;
using System.Text.Json.Nodes;
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.";

//Format the request payload using the model's native structure.
var nativeRequest = JsonSerializer.Serialize(new
{
    anthropic_version = "bedrock-2023-05-31",
    max_tokens = 512,
    temperature = 0.5,
    messages = new[]
    {
        new { role = "user", content = userMessage }
    }
});

// Create a request with the model ID and the model's native request payload.
var request = new InvokeModelRequest()
{
    ModelId = modelId,
    Body = new MemoryStream(System.Text.Encoding.UTF8.GetBytes(nativeRequest)),
    ContentType = "application/json"
};

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

    // Decode the response body.
    var modelResponse = await JsonNode.ParseAsync(response.Body);

    // Extract and print the response text.
    var responseText = modelResponse["content"]?[0]?["text"] ?? "";
    Console.WriteLine(responseText);
}
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 *适用于 .NET 的 AWS SDK API 参考[InvokeModel](https://docs.aws.amazon.com/goto/DotNetSDKV4/bedrock-runtime-2023-09-30/InvokeModel)*中的。

## Cohere Command
<a name="cohere_command"></a>

### Converse
<a name="bedrock-runtime_Converse_CohereCommand_csharp_4_topic"></a>

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。

**适用于 .NET 的 SDK (v4)**  
 还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/dotnetv4/Bedrock-runtime#code-examples)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《适用于 .NET 的 AWS SDK API Reference》**中的 [Converse](https://docs.aws.amazon.com/goto/DotNetSDKV4/bedrock-runtime-2023-09-30/Converse)。

### ConverseStream
<a name="bedrock-runtime_ConverseStream_CohereCommand_csharp_4_topic"></a>

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。

**适用于 .NET 的 SDK (v4)**  
 还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/dotnetv4/Bedrock-runtime#code-examples)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 *适用于 .NET 的 AWS SDK API 参考[ConverseStream](https://docs.aws.amazon.com/goto/DotNetSDKV4/bedrock-runtime-2023-09-30/ConverseStream)*中的。

## Meta Llama
<a name="meta_llama"></a>

### Converse
<a name="bedrock-runtime_Converse_MetaLlama_csharp_4_topic"></a>

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。

**适用于 .NET 的 SDK (v4)**  
 还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/dotnetv4/Bedrock-runtime#code-examples)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《适用于 .NET 的 AWS SDK API Reference》**中的 [Converse](https://docs.aws.amazon.com/goto/DotNetSDKV4/bedrock-runtime-2023-09-30/Converse)。

### ConverseStream
<a name="bedrock-runtime_ConverseStream_MetaLlama_csharp_4_topic"></a>

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。

**适用于 .NET 的 SDK (v4)**  
 还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/dotnetv4/Bedrock-runtime#code-examples)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 *适用于 .NET 的 AWS SDK API 参考[ConverseStream](https://docs.aws.amazon.com/goto/DotNetSDKV4/bedrock-runtime-2023-09-30/ConverseStream)*中的。

## Mistral AI
<a name="mistral_ai"></a>

### Converse
<a name="bedrock-runtime_Converse_Mistral_csharp_4_topic"></a>

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

**适用于 .NET 的 SDK (v4)**  
 还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/dotnetv4/Bedrock-runtime#code-examples)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《适用于 .NET 的 AWS SDK API Reference》**中的 [Converse](https://docs.aws.amazon.com/goto/DotNetSDKV4/bedrock-runtime-2023-09-30/Converse)。

### ConverseStream
<a name="bedrock-runtime_ConverseStream_Mistral_csharp_4_topic"></a>

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。

**适用于 .NET 的 SDK (v4)**  
 还有更多相关信息 GitHub。在 [AWS 代码示例存储库](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/dotnetv4/Bedrock-runtime#code-examples)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 *适用于 .NET 的 AWS SDK API 参考[ConverseStream](https://docs.aws.amazon.com/goto/DotNetSDKV4/bedrock-runtime-2023-09-30/ConverseStream)*中的。