Exemples d'Amazon Bedrock Runtime utilisant SDK for .NET

Les exemples de code suivants vous montrent comment effectuer des actions et implémenter des scénarios courants à l' AWS SDK for .NET aide d'Amazon Bedrock Runtime.

Les Scénarios sont des exemples de code qui vous montrent comment accomplir des tâches spécifiques en appelant plusieurs fonctions au sein d’un même service ou combinés à d’autres Services AWS.

Chaque exemple inclut un lien vers le code source complet, où vous trouverez des instructions sur la façon de configurer et d'exécuter le code en contexte.

Scénarios

Créez une application de terrain de jeu pour interagir avec les modèles de la fondation Amazon Bedrock

L'exemple de code suivant montre comment créer des terrains de jeu pour interagir avec les modèles de fondation Amazon Bedrock selon différentes modalités.

SDK for .NET

.NET Foundation Model (FM) Playground est un exemple d'application .NET MAUI Blazor qui montre comment utiliser Amazon Bedrock à partir de code C#. Cet exemple montre comment les développeurs .NET et C# peuvent utiliser Amazon Bedrock pour créer des applications génératives basées sur l'IA. Vous pouvez tester et interagir avec les modèles de fondation Amazon Bedrock en utilisant les quatre terrains de jeu suivants :

• Un terrain de jeu pour les textes.

• Un terrain de jeu pour le chat.

• Un terrain de jeu pour le chat vocal.

• Un terrain de jeu pour l'image.

L'exemple répertorie et affiche également les modèles de base auxquels vous avez accès ainsi que leurs caractéristiques. Pour le code source et les instructions de déploiement, consultez le projet dans GitHub.

Les services utilisés dans cet exemple

• Amazon Bedrock Runtime

Créez une application de terrain de jeu pour interagir avec les modèles de la fondation Amazon Bedrock

L'exemple de code suivant montre comment créer des terrains de jeu pour interagir avec les modèles de fondation Amazon Bedrock selon différentes modalités.

SDK for .NET

.NET Foundation Model (FM) Playground est un exemple d'application .NET MAUI Blazor qui montre comment utiliser Amazon Bedrock à partir de code C#. Cet exemple montre comment les développeurs .NET et C# peuvent utiliser Amazon Bedrock pour créer des applications génératives basées sur l'IA. Vous pouvez tester et interagir avec les modèles de fondation Amazon Bedrock en utilisant les quatre terrains de jeu suivants :

• Un terrain de jeu pour les textes.

• Un terrain de jeu pour le chat.

• Un terrain de jeu pour le chat vocal.

• Un terrain de jeu pour l'image.

L'exemple répertorie et affiche également les modèles de base auxquels vous avez accès ainsi que leurs caractéristiques. Pour le code source et les instructions de déploiement, consultez le projet dans GitHub.

Les services utilisés dans cet exemple

• Amazon Bedrock Runtime

Utilisation de l'outil avec l'API Converse

L'exemple de code suivant montre comment créer une interaction typique entre une application, un modèle d'IA génératif et des outils connectés ou comment APIs arbitrer les interactions entre l'IA et le monde extérieur. Il utilise l'exemple de la connexion d'une API météo externe au modèle d'IA afin de fournir des informations météorologiques en temps réel en fonction des entrées de l'utilisateur.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Exécution principale du flux de scénarios. Ce scénario orchestre la conversation entre l'utilisateur, l'API Amazon Bedrock Converse et un outil météo.

using Amazon;
using Amazon.BedrockRuntime;
using Amazon.BedrockRuntime.Model;
using Amazon.Runtime.Documents;
using Microsoft.Extensions.DependencyInjection;
using Microsoft.Extensions.DependencyInjection.Extensions;
using Microsoft.Extensions.Hosting;
using Microsoft.Extensions.Http;
using Microsoft.Extensions.Logging;
using Microsoft.Extensions.Logging.Console;

namespace ConverseToolScenario;

public static class ConverseToolScenario
{
    /*
    Before running this .NET code example, set up your development environment, including your credentials.

    This demo illustrates a tool use scenario using Amazon Bedrock's Converse API and a weather tool.
    The script interacts with a foundation model on Amazon Bedrock to provide weather information based on user
    input. It uses the Open-Meteo API (https://open-meteo.com) to retrieve current weather data for a given location.
   */

    public static BedrockActionsWrapper _bedrockActionsWrapper = null!;
    public static WeatherTool _weatherTool = null!;
    public static bool _interactive = true;

    // Change this string to use a different model with Converse API.
    private static string model_id = "amazon.nova-lite-v1:0";

    private static string system_prompt = @"
        You are a weather assistant that provides current weather data for user-specified locations using only
        the Weather_Tool, which expects latitude and longitude. Infer the coordinates from the location yourself.
        If the user provides coordinates, infer the approximate location and refer to it in your response.
        To use the tool, you strictly apply the provided tool specification.

        - Explain your step-by-step process, and give brief updates before each step.
        - Only use the Weather_Tool for data. Never guess or make up information. 
        - Repeat the tool use for subsequent requests if necessary.
        - If the tool errors, apologize, explain weather is unavailable, and suggest other options.
        - Report temperatures in °C (°F) and wind in km/h (mph). Keep weather reports concise. Sparingly use
          emojis where appropriate.
        - Only respond to weather queries. Remind off-topic users of your purpose. 
        - Never claim to search online, access external data, or use tools besides Weather_Tool.
        - Complete the entire process until you have all required data before sending the complete response.
    "
    ;

    private static string default_prompt = "What is the weather like in Seattle?";

    // The maximum number of recursive calls allowed in the tool use function.
    // This helps prevent infinite loops and potential performance issues.
    private static int max_recursions = 5;

    public static async Task Main(string[] args)
    {
        // Set up dependency injection for the Amazon service.
        using var host = Host.CreateDefaultBuilder(args)
            .ConfigureLogging(logging =>
                logging.AddFilter("System", LogLevel.Error)
                    .AddFilter<ConsoleLoggerProvider>("Microsoft", LogLevel.Trace))
            .ConfigureServices((_, services) =>
                services.AddHttpClient()
                    .AddSingleton<IAmazonBedrockRuntime>(_ => new AmazonBedrockRuntimeClient(RegionEndpoint.USEast1)) // Specify a region that has access to the chosen model.
                    .AddTransient<BedrockActionsWrapper>()
                    .AddTransient<WeatherTool>()
                    .RemoveAll<IHttpMessageHandlerBuilderFilter>()
            )
            .Build();

        ServicesSetup(host);

        try
        {
            await RunConversationAsync();

        }
        catch (Exception ex)
        {
            Console.WriteLine(new string('-', 80));
            Console.WriteLine($"There was a problem running the scenario: {ex.Message}");
            Console.WriteLine(new string('-', 80));
        }
        finally
        {
            Console.WriteLine(
                "Amazon Bedrock Converse API with Tool Use Feature Scenario is complete.");
            Console.WriteLine(new string('-', 80));
        }
    }

    /// <summary>
    /// Populate the services for use within the console application.
    /// </summary>
    /// <param name="host">The services host.</param>
    private static void ServicesSetup(IHost host)
    {
        _bedrockActionsWrapper = host.Services.GetRequiredService<BedrockActionsWrapper>();
        _weatherTool = host.Services.GetRequiredService<WeatherTool>();
    }

    /// <summary>
    /// Starts the conversation with the user and handles the interaction with Bedrock.
    /// </summary>
    /// <returns>The conversation array.</returns>
    public static async Task<List<Message>> RunConversationAsync()
    {
        // Print the greeting and a short user guide
        PrintHeader();

        // Start with an empty conversation
        var conversation = new List<Message>();

        // Get the first user input
        var userInput = await GetUserInputAsync();

        while (userInput != null)
        {
            // Create a new message with the user input and append it to the conversation
            var message = new Message { Role = ConversationRole.User, Content = new List<ContentBlock> { new ContentBlock { Text = userInput } } };
            conversation.Add(message);

            // Send the conversation to Amazon Bedrock
            var bedrockResponse = await SendConversationToBedrock(conversation);

            // Recursively handle the model's response until the model has returned its final response or the recursion counter has reached 0
            await ProcessModelResponseAsync(bedrockResponse, conversation, max_recursions);

            // Repeat the loop until the user decides to exit the application
            userInput = await GetUserInputAsync();
        }

        PrintFooter();
        return conversation;
    }

    /// <summary>
    /// Sends the conversation, the system prompt, and the tool spec to Amazon Bedrock, and returns the response.
    /// </summary>
    /// <param name="conversation">The conversation history including the next message to send.</param>
    /// <returns>The response from Amazon Bedrock.</returns>
    private static async Task<ConverseResponse> SendConversationToBedrock(List<Message> conversation)
    {
        Console.WriteLine("\tCalling Bedrock...");

        // Send the conversation, system prompt, and tool configuration, and return the response
        return await _bedrockActionsWrapper.SendConverseRequestAsync(model_id, system_prompt, conversation, _weatherTool.GetToolSpec());
    }

    /// <summary>
    /// Processes the response received via Amazon Bedrock and performs the necessary actions based on the stop reason.
    /// </summary>
    /// <param name="modelResponse">The model's response returned via Amazon Bedrock.</param>
    /// <param name="conversation">The conversation history.</param>
    /// <param name="maxRecursion">The maximum number of recursive calls allowed.</param>
    private static async Task ProcessModelResponseAsync(ConverseResponse modelResponse, List<Message> conversation, int maxRecursion)
    {
        if (maxRecursion <= 0)
        {
            // Stop the process, the number of recursive calls could indicate an infinite loop
            Console.WriteLine("\tWarning: Maximum number of recursions reached. Please try again.");
        }

        // Append the model's response to the ongoing conversation
        conversation.Add(modelResponse.Output.Message);

        if (modelResponse.StopReason == "tool_use")
        {
            // If the stop reason is "tool_use", forward everything to the tool use handler
            await HandleToolUseAsync(modelResponse.Output, conversation, maxRecursion - 1);
        }

        if (modelResponse.StopReason == "end_turn")
        {
            // If the stop reason is "end_turn", print the model's response text, and finish the process
            PrintModelResponse(modelResponse.Output.Message.Content[0].Text);
            if (!_interactive)
            {
                default_prompt = "x";
            }
        }
    }

    /// <summary>
    /// Handles the tool use case by invoking the specified tool and sending the tool's response back to Bedrock.
    /// The tool response is appended to the conversation, and the conversation is sent back to Amazon Bedrock for further processing.
    /// </summary>
    /// <param name="modelResponse">The model's response containing the tool use request.</param>
    /// <param name="conversation">The conversation history.</param>
    /// <param name="maxRecursion">The maximum number of recursive calls allowed.</param>
    public static async Task HandleToolUseAsync(ConverseOutput modelResponse, List<Message> conversation, int maxRecursion)
    {
        // Initialize an empty list of tool results
        var toolResults = new List<ContentBlock>();

        // The model's response can consist of multiple content blocks
        foreach (var contentBlock in modelResponse.Message.Content)
        {
            if (!String.IsNullOrEmpty(contentBlock.Text))
            {
                // If the content block contains text, print it to the console
                PrintModelResponse(contentBlock.Text);
            }

            if (contentBlock.ToolUse != null)
            {
                // If the content block is a tool use request, forward it to the tool
                var toolResponse = await InvokeTool(contentBlock.ToolUse);

                // Add the tool use ID and the tool's response to the list of results
                toolResults.Add(new ContentBlock
                {
                    ToolResult = new ToolResultBlock()
                    {
                        ToolUseId = toolResponse.ToolUseId,
                        Content = new List<ToolResultContentBlock>()
                            { new ToolResultContentBlock { Json = toolResponse.Content } }
                    }
                });
            }
        }

        // Embed the tool results in a new user message
        var message = new Message() { Role = ConversationRole.User, Content = toolResults };

        // Append the new message to the ongoing conversation
        conversation.Add(message);

        // Send the conversation to Amazon Bedrock
        var response = await SendConversationToBedrock(conversation);

        // Recursively handle the model's response until the model has returned its final response or the recursion counter has reached 0
        await ProcessModelResponseAsync(response, conversation, maxRecursion);
    }

    /// <summary>
    /// Invokes the specified tool with the given payload and returns the tool's response.
    /// If the requested tool does not exist, an error message is returned.
    /// </summary>
    /// <param name="payload">The payload containing the tool name and input data.</param>
    /// <returns>The tool's response or an error message.</returns>
    public static async Task<ToolResponse> InvokeTool(ToolUseBlock payload)
    {
        var toolName = payload.Name;

        if (toolName == "Weather_Tool")
        {
            var inputData = payload.Input.AsDictionary();
            PrintToolUse(toolName, inputData);

            // Invoke the weather tool with the input data provided
            var weatherResponse = await _weatherTool.FetchWeatherDataAsync(inputData["latitude"].ToString(), inputData["longitude"].ToString());
            return new ToolResponse { ToolUseId = payload.ToolUseId, Content = weatherResponse };
        }
        else
        {
            var errorMessage = $"\tThe requested tool with name '{toolName}' does not exist.";
            return new ToolResponse { ToolUseId = payload.ToolUseId, Content = new { error = true, message = errorMessage } };
        }
    }


    /// <summary>
    /// Prompts the user for input and returns the user's response.
    /// Returns null if the user enters 'x' to exit.
    /// </summary>
    /// <param name="prompt">The prompt to display to the user.</param>
    /// <returns>The user's input or null if the user chooses to exit.</returns>
    private static async Task<string?> GetUserInputAsync(string prompt = "\tYour weather info request:")
    {
        var userInput = default_prompt;
        if (_interactive)
        {
            Console.WriteLine(new string('*', 80));
            Console.WriteLine($"{prompt} (x to exit): \n\t");
            userInput = Console.ReadLine();
        }

        if (string.IsNullOrWhiteSpace(userInput))
        {
            prompt = "\tPlease enter your weather info request, e.g. the name of a city";
            return await GetUserInputAsync(prompt);
        }

        if (userInput.ToLowerInvariant() == "x")
        {
            return null;
        }

        return userInput;
    }

    /// <summary>
    /// Logs the welcome message and usage guide for the tool use demo.
    /// </summary>
    public static void PrintHeader()
    {
        Console.WriteLine(@"
        =================================================
        Welcome to the Amazon Bedrock Tool Use demo!
        =================================================

        This assistant provides current weather information for user-specified locations.
        You can ask for weather details by providing the location name or coordinates. Weather information
        will be provided using a custom Tool and open-meteo API.

        Example queries:
        - What's the weather like in New York?
        - Current weather for latitude 40.70, longitude -74.01
        - Is it warmer in Rome or Barcelona today?

        To exit the program, simply type 'x' and press Enter.

        P.S.: You're not limited to single locations, or even to using English!
        Have fun and experiment with the app!
        ");
    }

    /// <summary>
    /// Logs the footer information for the tool use demo.
    /// </summary>
    public static void PrintFooter()
    {
        Console.WriteLine(@"
        =================================================
        Thank you for checking out the Amazon Bedrock Tool Use demo. We hope you
        learned something new, or got some inspiration for your own apps today!

        For more Bedrock examples in different programming languages, have a look at:
        https://docs.aws.amazon.com/bedrock/latest/userguide/service_code_examples.html
        =================================================
        ");
    }

    /// <summary>
    /// Logs information about the tool use.
    /// </summary>
    /// <param name="toolName">The name of the tool being used.</param>
    /// <param name="inputData">The input data for the tool.</param>
    public static void PrintToolUse(string toolName, Dictionary<string, Document> inputData)
    {
        Console.WriteLine($"\n\tInvoking tool: {toolName} with input: {inputData["latitude"].ToString()}, {inputData["longitude"].ToString()}...\n");
    }

    /// <summary>
    /// Logs the model's response.
    /// </summary>
    /// <param name="message">The model's response message.</param>
    public static void PrintModelResponse(string message)
    {
        Console.WriteLine("\tThe model's response:\n");
        Console.WriteLine(message);
        Console.WriteLine();
    }
}

L'outil météo utilisé par la démo. Ce fichier définit les spécifications de l'outil et implémente la logique permettant de récupérer les données météorologiques à l'aide de l'API Open-Meteo.

using Amazon.BedrockRuntime.Model;
using Amazon.Runtime.Documents;
using Microsoft.Extensions.Logging;

namespace ConverseToolScenario;

/// <summary>
/// Weather tool that will be invoked when requested by the Bedrock response.
/// </summary>
public class WeatherTool
{
    private readonly ILogger<WeatherTool> _logger;
    private readonly IHttpClientFactory _httpClientFactory;

    public WeatherTool(ILogger<WeatherTool> logger, IHttpClientFactory httpClientFactory)
    {
        _logger = logger;
        _httpClientFactory = httpClientFactory;
    }

    /// <summary>
    /// Returns the JSON Schema specification for the Weather tool. The tool specification
    /// defines the input schema and describes the tool's functionality.
    /// For more information, see https://json-schema.org/understanding-json-schema/reference.
    /// </summary>
    /// <returns>The tool specification for the Weather tool.</returns>
    public ToolSpecification GetToolSpec()
    {
        ToolSpecification toolSpecification = new ToolSpecification();

        toolSpecification.Name = "Weather_Tool";
        toolSpecification.Description = "Get the current weather for a given location, based on its WGS84 coordinates.";

        Document toolSpecDocument = Document.FromObject(
            new
            {
                type = "object",
                properties = new
                {
                    latitude = new
                    {
                        type = "string",
                        description = "Geographical WGS84 latitude of the location."
                    },
                    longitude = new
                    {
                        type = "string",
                        description = "Geographical WGS84 longitude of the location."
                    }
                },
                required = new[] { "latitude", "longitude" }
            });

        toolSpecification.InputSchema = new ToolInputSchema() { Json = toolSpecDocument };
        return toolSpecification;
    }

    /// <summary>
    /// Fetches weather data for the given latitude and longitude using the Open-Meteo API.
    /// Returns the weather data or an error message if the request fails.
    /// </summary>
    /// <param name="latitude">The latitude of the location.</param>
    /// <param name="longitude">The longitude of the location.</param>
    /// <returns>The weather data or an error message.</returns>
    public async Task<Document> FetchWeatherDataAsync(string latitude, string longitude)
    {
        string endpoint = "https://api.open-meteo.com/v1/forecast";

        try
        {
            var httpClient = _httpClientFactory.CreateClient();
            var response = await httpClient.GetAsync($"{endpoint}?latitude={latitude}&longitude={longitude}&current_weather=True");
            response.EnsureSuccessStatusCode();
            var weatherData = await response.Content.ReadAsStringAsync();

            Document weatherDocument = Document.FromObject(
                new { weather_data = weatherData });

            return weatherDocument;
        }
        catch (HttpRequestException e)
        {
            _logger.LogError(e, "Error fetching weather data: {Message}", e.Message);
            throw;
        }
        catch (Exception e)
        {
            _logger.LogError(e, "Unexpected error fetching weather data: {Message}", e.Message);
            throw;
        }
    }
}

L'action de l'API Converse avec une configuration d'outil.

/// <summary>
/// Wrapper class for interacting with the Amazon Bedrock Converse API.
/// </summary>
public class BedrockActionsWrapper
{
    private readonly IAmazonBedrockRuntime _bedrockClient;
    private readonly ILogger<BedrockActionsWrapper> _logger;

    /// <summary>
    /// Initializes a new instance of the <see cref="BedrockActionsWrapper"/> class.
    /// </summary>
    /// <param name="bedrockClient">The Bedrock Converse API client.</param>
    /// <param name="logger">The logger instance.</param>
    public BedrockActionsWrapper(IAmazonBedrockRuntime bedrockClient, ILogger<BedrockActionsWrapper> logger)
    {
        _bedrockClient = bedrockClient;
        _logger = logger;
    }

    /// <summary>
    /// Sends a Converse request to the Amazon Bedrock Converse API.
    /// </summary>
    /// <param name="modelId">The Bedrock Model Id.</param>
    /// <param name="systemPrompt">A system prompt instruction.</param>
    /// <param name="conversation">The array of messages in the conversation.</param>
    /// <param name="toolSpec">The specification for a tool.</param>
    /// <returns>The response of the model.</returns>
    public async Task<ConverseResponse> SendConverseRequestAsync(string modelId, string systemPrompt, List<Message> conversation, ToolSpecification toolSpec)
    {
        try
        {
            var request = new ConverseRequest()
            {
                ModelId = modelId,
                System = new List<SystemContentBlock>()
                {
                    new SystemContentBlock()
                    {
                        Text = systemPrompt
                    }
                },
                Messages = conversation,
                ToolConfig = new ToolConfiguration()
                {
                    Tools = new List<Tool>()
                    {
                        new Tool()
                        {
                            ToolSpec = toolSpec
                        }
                    }
                }
            };

            var response = await _bedrockClient.ConverseAsync(request);

            return response;
        }
        catch (ModelNotReadyException ex)
        {
            _logger.LogError(ex, "Model not ready, please wait and try again.");
            throw;
        }
        catch (AmazonBedrockRuntimeException ex)
        {
            _logger.LogError(ex, "Error occurred while sending Converse request.");
            throw;
        }
    }
}

• Pour plus de détails sur l'API, consultez Converse dans le manuel AWS SDK for .NET API Reference.

Utilisation de l'outil avec l'API Converse

L'exemple de code suivant montre comment créer une interaction typique entre une application, un modèle d'IA génératif et des outils connectés ou comment APIs arbitrer les interactions entre l'IA et le monde extérieur. Il utilise l'exemple de la connexion d'une API météo externe au modèle d'IA afin de fournir des informations météorologiques en temps réel en fonction des entrées de l'utilisateur.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Exécution principale du flux de scénarios. Ce scénario orchestre la conversation entre l'utilisateur, l'API Amazon Bedrock Converse et un outil météo.

using Amazon;
using Amazon.BedrockRuntime;
using Amazon.BedrockRuntime.Model;
using Amazon.Runtime.Documents;
using Microsoft.Extensions.DependencyInjection;
using Microsoft.Extensions.DependencyInjection.Extensions;
using Microsoft.Extensions.Hosting;
using Microsoft.Extensions.Http;
using Microsoft.Extensions.Logging;
using Microsoft.Extensions.Logging.Console;

namespace ConverseToolScenario;

public static class ConverseToolScenario
{
    /*
    Before running this .NET code example, set up your development environment, including your credentials.

    This demo illustrates a tool use scenario using Amazon Bedrock's Converse API and a weather tool.
    The script interacts with a foundation model on Amazon Bedrock to provide weather information based on user
    input. It uses the Open-Meteo API (https://open-meteo.com) to retrieve current weather data for a given location.
   */

    public static BedrockActionsWrapper _bedrockActionsWrapper = null!;
    public static WeatherTool _weatherTool = null!;
    public static bool _interactive = true;

    // Change this string to use a different model with Converse API.
    private static string model_id = "amazon.nova-lite-v1:0";

    private static string system_prompt = @"
        You are a weather assistant that provides current weather data for user-specified locations using only
        the Weather_Tool, which expects latitude and longitude. Infer the coordinates from the location yourself.
        If the user provides coordinates, infer the approximate location and refer to it in your response.
        To use the tool, you strictly apply the provided tool specification.

        - Explain your step-by-step process, and give brief updates before each step.
        - Only use the Weather_Tool for data. Never guess or make up information. 
        - Repeat the tool use for subsequent requests if necessary.
        - If the tool errors, apologize, explain weather is unavailable, and suggest other options.
        - Report temperatures in °C (°F) and wind in km/h (mph). Keep weather reports concise. Sparingly use
          emojis where appropriate.
        - Only respond to weather queries. Remind off-topic users of your purpose. 
        - Never claim to search online, access external data, or use tools besides Weather_Tool.
        - Complete the entire process until you have all required data before sending the complete response.
    "
    ;

    private static string default_prompt = "What is the weather like in Seattle?";

    // The maximum number of recursive calls allowed in the tool use function.
    // This helps prevent infinite loops and potential performance issues.
    private static int max_recursions = 5;

    public static async Task Main(string[] args)
    {
        // Set up dependency injection for the Amazon service.
        using var host = Host.CreateDefaultBuilder(args)
            .ConfigureLogging(logging =>
                logging.AddFilter("System", LogLevel.Error)
                    .AddFilter<ConsoleLoggerProvider>("Microsoft", LogLevel.Trace))
            .ConfigureServices((_, services) =>
                services.AddHttpClient()
                    .AddSingleton<IAmazonBedrockRuntime>(_ => new AmazonBedrockRuntimeClient(RegionEndpoint.USEast1)) // Specify a region that has access to the chosen model.
                    .AddTransient<BedrockActionsWrapper>()
                    .AddTransient<WeatherTool>()
                    .RemoveAll<IHttpMessageHandlerBuilderFilter>()
            )
            .Build();

        ServicesSetup(host);

        try
        {
            await RunConversationAsync();

        }
        catch (Exception ex)
        {
            Console.WriteLine(new string('-', 80));
            Console.WriteLine($"There was a problem running the scenario: {ex.Message}");
            Console.WriteLine(new string('-', 80));
        }
        finally
        {
            Console.WriteLine(
                "Amazon Bedrock Converse API with Tool Use Feature Scenario is complete.");
            Console.WriteLine(new string('-', 80));
        }
    }

    /// <summary>
    /// Populate the services for use within the console application.
    /// </summary>
    /// <param name="host">The services host.</param>
    private static void ServicesSetup(IHost host)
    {
        _bedrockActionsWrapper = host.Services.GetRequiredService<BedrockActionsWrapper>();
        _weatherTool = host.Services.GetRequiredService<WeatherTool>();
    }

    /// <summary>
    /// Starts the conversation with the user and handles the interaction with Bedrock.
    /// </summary>
    /// <returns>The conversation array.</returns>
    public static async Task<List<Message>> RunConversationAsync()
    {
        // Print the greeting and a short user guide
        PrintHeader();

        // Start with an empty conversation
        var conversation = new List<Message>();

        // Get the first user input
        var userInput = await GetUserInputAsync();

        while (userInput != null)
        {
            // Create a new message with the user input and append it to the conversation
            var message = new Message { Role = ConversationRole.User, Content = new List<ContentBlock> { new ContentBlock { Text = userInput } } };
            conversation.Add(message);

            // Send the conversation to Amazon Bedrock
            var bedrockResponse = await SendConversationToBedrock(conversation);

            // Recursively handle the model's response until the model has returned its final response or the recursion counter has reached 0
            await ProcessModelResponseAsync(bedrockResponse, conversation, max_recursions);

            // Repeat the loop until the user decides to exit the application
            userInput = await GetUserInputAsync();
        }

        PrintFooter();
        return conversation;
    }

    /// <summary>
    /// Sends the conversation, the system prompt, and the tool spec to Amazon Bedrock, and returns the response.
    /// </summary>
    /// <param name="conversation">The conversation history including the next message to send.</param>
    /// <returns>The response from Amazon Bedrock.</returns>
    private static async Task<ConverseResponse> SendConversationToBedrock(List<Message> conversation)
    {
        Console.WriteLine("\tCalling Bedrock...");

        // Send the conversation, system prompt, and tool configuration, and return the response
        return await _bedrockActionsWrapper.SendConverseRequestAsync(model_id, system_prompt, conversation, _weatherTool.GetToolSpec());
    }

    /// <summary>
    /// Processes the response received via Amazon Bedrock and performs the necessary actions based on the stop reason.
    /// </summary>
    /// <param name="modelResponse">The model's response returned via Amazon Bedrock.</param>
    /// <param name="conversation">The conversation history.</param>
    /// <param name="maxRecursion">The maximum number of recursive calls allowed.</param>
    private static async Task ProcessModelResponseAsync(ConverseResponse modelResponse, List<Message> conversation, int maxRecursion)
    {
        if (maxRecursion <= 0)
        {
            // Stop the process, the number of recursive calls could indicate an infinite loop
            Console.WriteLine("\tWarning: Maximum number of recursions reached. Please try again.");
        }

        // Append the model's response to the ongoing conversation
        conversation.Add(modelResponse.Output.Message);

        if (modelResponse.StopReason == "tool_use")
        {
            // If the stop reason is "tool_use", forward everything to the tool use handler
            await HandleToolUseAsync(modelResponse.Output, conversation, maxRecursion - 1);
        }

        if (modelResponse.StopReason == "end_turn")
        {
            // If the stop reason is "end_turn", print the model's response text, and finish the process
            PrintModelResponse(modelResponse.Output.Message.Content[0].Text);
            if (!_interactive)
            {
                default_prompt = "x";
            }
        }
    }

    /// <summary>
    /// Handles the tool use case by invoking the specified tool and sending the tool's response back to Bedrock.
    /// The tool response is appended to the conversation, and the conversation is sent back to Amazon Bedrock for further processing.
    /// </summary>
    /// <param name="modelResponse">The model's response containing the tool use request.</param>
    /// <param name="conversation">The conversation history.</param>
    /// <param name="maxRecursion">The maximum number of recursive calls allowed.</param>
    public static async Task HandleToolUseAsync(ConverseOutput modelResponse, List<Message> conversation, int maxRecursion)
    {
        // Initialize an empty list of tool results
        var toolResults = new List<ContentBlock>();

        // The model's response can consist of multiple content blocks
        foreach (var contentBlock in modelResponse.Message.Content)
        {
            if (!String.IsNullOrEmpty(contentBlock.Text))
            {
                // If the content block contains text, print it to the console
                PrintModelResponse(contentBlock.Text);
            }

            if (contentBlock.ToolUse != null)
            {
                // If the content block is a tool use request, forward it to the tool
                var toolResponse = await InvokeTool(contentBlock.ToolUse);

                // Add the tool use ID and the tool's response to the list of results
                toolResults.Add(new ContentBlock
                {
                    ToolResult = new ToolResultBlock()
                    {
                        ToolUseId = toolResponse.ToolUseId,
                        Content = new List<ToolResultContentBlock>()
                            { new ToolResultContentBlock { Json = toolResponse.Content } }
                    }
                });
            }
        }

        // Embed the tool results in a new user message
        var message = new Message() { Role = ConversationRole.User, Content = toolResults };

        // Append the new message to the ongoing conversation
        conversation.Add(message);

        // Send the conversation to Amazon Bedrock
        var response = await SendConversationToBedrock(conversation);

        // Recursively handle the model's response until the model has returned its final response or the recursion counter has reached 0
        await ProcessModelResponseAsync(response, conversation, maxRecursion);
    }

    /// <summary>
    /// Invokes the specified tool with the given payload and returns the tool's response.
    /// If the requested tool does not exist, an error message is returned.
    /// </summary>
    /// <param name="payload">The payload containing the tool name and input data.</param>
    /// <returns>The tool's response or an error message.</returns>
    public static async Task<ToolResponse> InvokeTool(ToolUseBlock payload)
    {
        var toolName = payload.Name;

        if (toolName == "Weather_Tool")
        {
            var inputData = payload.Input.AsDictionary();
            PrintToolUse(toolName, inputData);

            // Invoke the weather tool with the input data provided
            var weatherResponse = await _weatherTool.FetchWeatherDataAsync(inputData["latitude"].ToString(), inputData["longitude"].ToString());
            return new ToolResponse { ToolUseId = payload.ToolUseId, Content = weatherResponse };
        }
        else
        {
            var errorMessage = $"\tThe requested tool with name '{toolName}' does not exist.";
            return new ToolResponse { ToolUseId = payload.ToolUseId, Content = new { error = true, message = errorMessage } };
        }
    }


    /// <summary>
    /// Prompts the user for input and returns the user's response.
    /// Returns null if the user enters 'x' to exit.
    /// </summary>
    /// <param name="prompt">The prompt to display to the user.</param>
    /// <returns>The user's input or null if the user chooses to exit.</returns>
    private static async Task<string?> GetUserInputAsync(string prompt = "\tYour weather info request:")
    {
        var userInput = default_prompt;
        if (_interactive)
        {
            Console.WriteLine(new string('*', 80));
            Console.WriteLine($"{prompt} (x to exit): \n\t");
            userInput = Console.ReadLine();
        }

        if (string.IsNullOrWhiteSpace(userInput))
        {
            prompt = "\tPlease enter your weather info request, e.g. the name of a city";
            return await GetUserInputAsync(prompt);
        }

        if (userInput.ToLowerInvariant() == "x")
        {
            return null;
        }

        return userInput;
    }

    /// <summary>
    /// Logs the welcome message and usage guide for the tool use demo.
    /// </summary>
    public static void PrintHeader()
    {
        Console.WriteLine(@"
        =================================================
        Welcome to the Amazon Bedrock Tool Use demo!
        =================================================

        This assistant provides current weather information for user-specified locations.
        You can ask for weather details by providing the location name or coordinates. Weather information
        will be provided using a custom Tool and open-meteo API.

        Example queries:
        - What's the weather like in New York?
        - Current weather for latitude 40.70, longitude -74.01
        - Is it warmer in Rome or Barcelona today?

        To exit the program, simply type 'x' and press Enter.

        P.S.: You're not limited to single locations, or even to using English!
        Have fun and experiment with the app!
        ");
    }

    /// <summary>
    /// Logs the footer information for the tool use demo.
    /// </summary>
    public static void PrintFooter()
    {
        Console.WriteLine(@"
        =================================================
        Thank you for checking out the Amazon Bedrock Tool Use demo. We hope you
        learned something new, or got some inspiration for your own apps today!

        For more Bedrock examples in different programming languages, have a look at:
        https://docs.aws.amazon.com/bedrock/latest/userguide/service_code_examples.html
        =================================================
        ");
    }

    /// <summary>
    /// Logs information about the tool use.
    /// </summary>
    /// <param name="toolName">The name of the tool being used.</param>
    /// <param name="inputData">The input data for the tool.</param>
    public static void PrintToolUse(string toolName, Dictionary<string, Document> inputData)
    {
        Console.WriteLine($"\n\tInvoking tool: {toolName} with input: {inputData["latitude"].ToString()}, {inputData["longitude"].ToString()}...\n");
    }

    /// <summary>
    /// Logs the model's response.
    /// </summary>
    /// <param name="message">The model's response message.</param>
    public static void PrintModelResponse(string message)
    {
        Console.WriteLine("\tThe model's response:\n");
        Console.WriteLine(message);
        Console.WriteLine();
    }
}

L'outil météo utilisé par la démo. Ce fichier définit les spécifications de l'outil et implémente la logique permettant de récupérer les données météorologiques à l'aide de l'API Open-Meteo.

using Amazon.BedrockRuntime.Model;
using Amazon.Runtime.Documents;
using Microsoft.Extensions.Logging;

namespace ConverseToolScenario;

/// <summary>
/// Weather tool that will be invoked when requested by the Bedrock response.
/// </summary>
public class WeatherTool
{
    private readonly ILogger<WeatherTool> _logger;
    private readonly IHttpClientFactory _httpClientFactory;

    public WeatherTool(ILogger<WeatherTool> logger, IHttpClientFactory httpClientFactory)
    {
        _logger = logger;
        _httpClientFactory = httpClientFactory;
    }

    /// <summary>
    /// Returns the JSON Schema specification for the Weather tool. The tool specification
    /// defines the input schema and describes the tool's functionality.
    /// For more information, see https://json-schema.org/understanding-json-schema/reference.
    /// </summary>
    /// <returns>The tool specification for the Weather tool.</returns>
    public ToolSpecification GetToolSpec()
    {
        ToolSpecification toolSpecification = new ToolSpecification();

        toolSpecification.Name = "Weather_Tool";
        toolSpecification.Description = "Get the current weather for a given location, based on its WGS84 coordinates.";

        Document toolSpecDocument = Document.FromObject(
            new
            {
                type = "object",
                properties = new
                {
                    latitude = new
                    {
                        type = "string",
                        description = "Geographical WGS84 latitude of the location."
                    },
                    longitude = new
                    {
                        type = "string",
                        description = "Geographical WGS84 longitude of the location."
                    }
                },
                required = new[] { "latitude", "longitude" }
            });

        toolSpecification.InputSchema = new ToolInputSchema() { Json = toolSpecDocument };
        return toolSpecification;
    }

    /// <summary>
    /// Fetches weather data for the given latitude and longitude using the Open-Meteo API.
    /// Returns the weather data or an error message if the request fails.
    /// </summary>
    /// <param name="latitude">The latitude of the location.</param>
    /// <param name="longitude">The longitude of the location.</param>
    /// <returns>The weather data or an error message.</returns>
    public async Task<Document> FetchWeatherDataAsync(string latitude, string longitude)
    {
        string endpoint = "https://api.open-meteo.com/v1/forecast";

        try
        {
            var httpClient = _httpClientFactory.CreateClient();
            var response = await httpClient.GetAsync($"{endpoint}?latitude={latitude}&longitude={longitude}&current_weather=True");
            response.EnsureSuccessStatusCode();
            var weatherData = await response.Content.ReadAsStringAsync();

            Document weatherDocument = Document.FromObject(
                new { weather_data = weatherData });

            return weatherDocument;
        }
        catch (HttpRequestException e)
        {
            _logger.LogError(e, "Error fetching weather data: {Message}", e.Message);
            throw;
        }
        catch (Exception e)
        {
            _logger.LogError(e, "Unexpected error fetching weather data: {Message}", e.Message);
            throw;
        }
    }
}

L'action de l'API Converse avec une configuration d'outil.

/// <summary>
/// Wrapper class for interacting with the Amazon Bedrock Converse API.
/// </summary>
public class BedrockActionsWrapper
{
    private readonly IAmazonBedrockRuntime _bedrockClient;
    private readonly ILogger<BedrockActionsWrapper> _logger;

    /// <summary>
    /// Initializes a new instance of the <see cref="BedrockActionsWrapper"/> class.
    /// </summary>
    /// <param name="bedrockClient">The Bedrock Converse API client.</param>
    /// <param name="logger">The logger instance.</param>
    public BedrockActionsWrapper(IAmazonBedrockRuntime bedrockClient, ILogger<BedrockActionsWrapper> logger)
    {
        _bedrockClient = bedrockClient;
        _logger = logger;
    }

    /// <summary>
    /// Sends a Converse request to the Amazon Bedrock Converse API.
    /// </summary>
    /// <param name="modelId">The Bedrock Model Id.</param>
    /// <param name="systemPrompt">A system prompt instruction.</param>
    /// <param name="conversation">The array of messages in the conversation.</param>
    /// <param name="toolSpec">The specification for a tool.</param>
    /// <returns>The response of the model.</returns>
    public async Task<ConverseResponse> SendConverseRequestAsync(string modelId, string systemPrompt, List<Message> conversation, ToolSpecification toolSpec)
    {
        try
        {
            var request = new ConverseRequest()
            {
                ModelId = modelId,
                System = new List<SystemContentBlock>()
                {
                    new SystemContentBlock()
                    {
                        Text = systemPrompt
                    }
                },
                Messages = conversation,
                ToolConfig = new ToolConfiguration()
                {
                    Tools = new List<Tool>()
                    {
                        new Tool()
                        {
                            ToolSpec = toolSpec
                        }
                    }
                }
            };

            var response = await _bedrockClient.ConverseAsync(request);

            return response;
        }
        catch (ModelNotReadyException ex)
        {
            _logger.LogError(ex, "Model not ready, please wait and try again.");
            throw;
        }
        catch (AmazonBedrockRuntimeException ex)
        {
            _logger.LogError(ex, "Error occurred while sending Converse request.");
            throw;
        }
    }
}

• Pour plus de détails sur l'API, consultez Converse dans le manuel AWS SDK for .NET API Reference.

AI21 Laboratoires Jurassic-2

Converse

L'exemple de code suivant montre comment envoyer un message texte à AI21 Labs Jurassic-2 à l'aide de l'API Converse de Bedrock.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Envoyez un SMS à AI21 Labs Jurassic-2 à l'aide de l'API Converse de Bedrock.

// Use the Converse API to send a text message to AI21 Labs Jurassic-2.

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., Jurassic-2 Mid.
var modelId = "ai21.j2-mid-v1";

// 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;
}

• Pour plus de détails sur l'API, consultez Converse dans le manuel AWS SDK for .NET API Reference.

Converse

L'exemple de code suivant montre comment envoyer un message texte à AI21 Labs Jurassic-2 à l'aide de l'API Converse de Bedrock.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Envoyez un SMS à AI21 Labs Jurassic-2 à l'aide de l'API Converse de Bedrock.

// Use the Converse API to send a text message to AI21 Labs Jurassic-2.

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., Jurassic-2 Mid.
var modelId = "ai21.j2-mid-v1";

// 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;
}

• Pour plus de détails sur l'API, consultez Converse dans le manuel AWS SDK for .NET API Reference.

InvokeModel

L'exemple de code suivant montre comment envoyer un message texte à AI21 Labs Jurassic-2 à l'aide de l'API Invoke Model.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Utilisez l'API Invoke Model pour envoyer un message texte.

// Use the native inference API to send a text message to AI21 Labs Jurassic-2.

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., Jurassic-2 Mid.
var modelId = "ai21.j2-mid-v1";

// 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
{
    prompt = userMessage,
    maxTokens = 512,
    temperature = 0.5
});

// 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["completions"]?[0]?["data"]?["text"] ?? "";
    Console.WriteLine(responseText);
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

• Pour plus de détails sur l'API, reportez-vous InvokeModelà la section Référence des AWS SDK for .NET API.

InvokeModel

L'exemple de code suivant montre comment envoyer un message texte à AI21 Labs Jurassic-2 à l'aide de l'API Invoke Model.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Utilisez l'API Invoke Model pour envoyer un message texte.

// Use the native inference API to send a text message to AI21 Labs Jurassic-2.

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., Jurassic-2 Mid.
var modelId = "ai21.j2-mid-v1";

// 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
{
    prompt = userMessage,
    maxTokens = 512,
    temperature = 0.5
});

// 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["completions"]?[0]?["data"]?["text"] ?? "";
    Console.WriteLine(responseText);
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

• Pour plus de détails sur l'API, reportez-vous InvokeModelà la section Référence des AWS SDK for .NET API.

Amazon Nova

Converse

L'exemple de code suivant montre comment envoyer un message texte à Amazon Nova à l'aide de l'API Converse de Bedrock.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Envoyez un SMS à Amazon Nova à l'aide de l'API Converse de Bedrock.

// Use the Converse API to send a text message to Amazon Nova.

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., Amazon Nova Lite.
var modelId = "amazon.nova-lite-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;
}

Envoyez une conversation de messages à Amazon Nova à l'aide de l'API Converse de Bedrock avec une configuration d'outil.

/// <summary>
/// Wrapper class for interacting with the Amazon Bedrock Converse API.
/// </summary>
public class BedrockActionsWrapper
{
    private readonly IAmazonBedrockRuntime _bedrockClient;
    private readonly ILogger<BedrockActionsWrapper> _logger;

    /// <summary>
    /// Initializes a new instance of the <see cref="BedrockActionsWrapper"/> class.
    /// </summary>
    /// <param name="bedrockClient">The Bedrock Converse API client.</param>
    /// <param name="logger">The logger instance.</param>
    public BedrockActionsWrapper(IAmazonBedrockRuntime bedrockClient, ILogger<BedrockActionsWrapper> logger)
    {
        _bedrockClient = bedrockClient;
        _logger = logger;
    }

    /// <summary>
    /// Sends a Converse request to the Amazon Bedrock Converse API.
    /// </summary>
    /// <param name="modelId">The Bedrock Model Id.</param>
    /// <param name="systemPrompt">A system prompt instruction.</param>
    /// <param name="conversation">The array of messages in the conversation.</param>
    /// <param name="toolSpec">The specification for a tool.</param>
    /// <returns>The response of the model.</returns>
    public async Task<ConverseResponse> SendConverseRequestAsync(string modelId, string systemPrompt, List<Message> conversation, ToolSpecification toolSpec)
    {
        try
        {
            var request = new ConverseRequest()
            {
                ModelId = modelId,
                System = new List<SystemContentBlock>()
                {
                    new SystemContentBlock()
                    {
                        Text = systemPrompt
                    }
                },
                Messages = conversation,
                ToolConfig = new ToolConfiguration()
                {
                    Tools = new List<Tool>()
                    {
                        new Tool()
                        {
                            ToolSpec = toolSpec
                        }
                    }
                }
            };

            var response = await _bedrockClient.ConverseAsync(request);

            return response;
        }
        catch (ModelNotReadyException ex)
        {
            _logger.LogError(ex, "Model not ready, please wait and try again.");
            throw;
        }
        catch (AmazonBedrockRuntimeException ex)
        {
            _logger.LogError(ex, "Error occurred while sending Converse request.");
            throw;
        }
    }
}

• Pour plus de détails sur l'API, consultez Converse dans le manuel AWS SDK for .NET API Reference.

Converse

L'exemple de code suivant montre comment envoyer un message texte à Amazon Nova à l'aide de l'API Converse de Bedrock.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Envoyez un SMS à Amazon Nova à l'aide de l'API Converse de Bedrock.

// Use the Converse API to send a text message to Amazon Nova.

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., Amazon Nova Lite.
var modelId = "amazon.nova-lite-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;
}

Envoyez une conversation de messages à Amazon Nova à l'aide de l'API Converse de Bedrock avec une configuration d'outil.

/// <summary>
/// Wrapper class for interacting with the Amazon Bedrock Converse API.
/// </summary>
public class BedrockActionsWrapper
{
    private readonly IAmazonBedrockRuntime _bedrockClient;
    private readonly ILogger<BedrockActionsWrapper> _logger;

    /// <summary>
    /// Initializes a new instance of the <see cref="BedrockActionsWrapper"/> class.
    /// </summary>
    /// <param name="bedrockClient">The Bedrock Converse API client.</param>
    /// <param name="logger">The logger instance.</param>
    public BedrockActionsWrapper(IAmazonBedrockRuntime bedrockClient, ILogger<BedrockActionsWrapper> logger)
    {
        _bedrockClient = bedrockClient;
        _logger = logger;
    }

    /// <summary>
    /// Sends a Converse request to the Amazon Bedrock Converse API.
    /// </summary>
    /// <param name="modelId">The Bedrock Model Id.</param>
    /// <param name="systemPrompt">A system prompt instruction.</param>
    /// <param name="conversation">The array of messages in the conversation.</param>
    /// <param name="toolSpec">The specification for a tool.</param>
    /// <returns>The response of the model.</returns>
    public async Task<ConverseResponse> SendConverseRequestAsync(string modelId, string systemPrompt, List<Message> conversation, ToolSpecification toolSpec)
    {
        try
        {
            var request = new ConverseRequest()
            {
                ModelId = modelId,
                System = new List<SystemContentBlock>()
                {
                    new SystemContentBlock()
                    {
                        Text = systemPrompt
                    }
                },
                Messages = conversation,
                ToolConfig = new ToolConfiguration()
                {
                    Tools = new List<Tool>()
                    {
                        new Tool()
                        {
                            ToolSpec = toolSpec
                        }
                    }
                }
            };

            var response = await _bedrockClient.ConverseAsync(request);

            return response;
        }
        catch (ModelNotReadyException ex)
        {
            _logger.LogError(ex, "Model not ready, please wait and try again.");
            throw;
        }
        catch (AmazonBedrockRuntimeException ex)
        {
            _logger.LogError(ex, "Error occurred while sending Converse request.");
            throw;
        }
    }
}

• Pour plus de détails sur l'API, consultez Converse dans le manuel AWS SDK for .NET API Reference.

ConverseStream

L'exemple de code suivant montre comment envoyer un message texte à Amazon Nova à l'aide de l'API Converse de Bedrock et comment traiter le flux de réponses en temps réel.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Envoyez un SMS à Amazon Nova à l'aide de l'API Converse de Bedrock et traitez le flux de réponses en temps réel.

// Use the Converse API to send a text message to Amazon Nova
// 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., Amazon Nova Lite.
var modelId = "amazon.nova-lite-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;
}

• Pour plus de détails sur l'API, reportez-vous ConverseStreamà la section Référence des AWS SDK for .NET API.

ConverseStream

L'exemple de code suivant montre comment envoyer un message texte à Amazon Nova à l'aide de l'API Converse de Bedrock et comment traiter le flux de réponses en temps réel.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Envoyez un SMS à Amazon Nova à l'aide de l'API Converse de Bedrock et traitez le flux de réponses en temps réel.

// Use the Converse API to send a text message to Amazon Nova
// 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., Amazon Nova Lite.
var modelId = "amazon.nova-lite-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;
}

• Pour plus de détails sur l'API, reportez-vous ConverseStreamà la section Référence des AWS SDK for .NET API.

Scénario : utilisation de l'outil avec l'API Converse

L'exemple de code suivant montre comment créer une interaction typique entre une application, un modèle d'IA génératif et des outils connectés ou comment APIs arbitrer les interactions entre l'IA et le monde extérieur. Il utilise l'exemple de la connexion d'une API météo externe au modèle d'IA afin de fournir des informations météorologiques en temps réel en fonction des entrées de l'utilisateur.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Exécution principale du flux de scénarios. Ce scénario orchestre la conversation entre l'utilisateur, l'API Amazon Bedrock Converse et un outil météo.

using Amazon;
using Amazon.BedrockRuntime;
using Amazon.BedrockRuntime.Model;
using Amazon.Runtime.Documents;
using Microsoft.Extensions.DependencyInjection;
using Microsoft.Extensions.DependencyInjection.Extensions;
using Microsoft.Extensions.Hosting;
using Microsoft.Extensions.Http;
using Microsoft.Extensions.Logging;
using Microsoft.Extensions.Logging.Console;

namespace ConverseToolScenario;

public static class ConverseToolScenario
{
    /*
    Before running this .NET code example, set up your development environment, including your credentials.

    This demo illustrates a tool use scenario using Amazon Bedrock's Converse API and a weather tool.
    The script interacts with a foundation model on Amazon Bedrock to provide weather information based on user
    input. It uses the Open-Meteo API (https://open-meteo.com) to retrieve current weather data for a given location.
   */

    public static BedrockActionsWrapper _bedrockActionsWrapper = null!;
    public static WeatherTool _weatherTool = null!;
    public static bool _interactive = true;

    // Change this string to use a different model with Converse API.
    private static string model_id = "amazon.nova-lite-v1:0";

    private static string system_prompt = @"
        You are a weather assistant that provides current weather data for user-specified locations using only
        the Weather_Tool, which expects latitude and longitude. Infer the coordinates from the location yourself.
        If the user provides coordinates, infer the approximate location and refer to it in your response.
        To use the tool, you strictly apply the provided tool specification.

        - Explain your step-by-step process, and give brief updates before each step.
        - Only use the Weather_Tool for data. Never guess or make up information. 
        - Repeat the tool use for subsequent requests if necessary.
        - If the tool errors, apologize, explain weather is unavailable, and suggest other options.
        - Report temperatures in °C (°F) and wind in km/h (mph). Keep weather reports concise. Sparingly use
          emojis where appropriate.
        - Only respond to weather queries. Remind off-topic users of your purpose. 
        - Never claim to search online, access external data, or use tools besides Weather_Tool.
        - Complete the entire process until you have all required data before sending the complete response.
    "
    ;

    private static string default_prompt = "What is the weather like in Seattle?";

    // The maximum number of recursive calls allowed in the tool use function.
    // This helps prevent infinite loops and potential performance issues.
    private static int max_recursions = 5;

    public static async Task Main(string[] args)
    {
        // Set up dependency injection for the Amazon service.
        using var host = Host.CreateDefaultBuilder(args)
            .ConfigureLogging(logging =>
                logging.AddFilter("System", LogLevel.Error)
                    .AddFilter<ConsoleLoggerProvider>("Microsoft", LogLevel.Trace))
            .ConfigureServices((_, services) =>
                services.AddHttpClient()
                    .AddSingleton<IAmazonBedrockRuntime>(_ => new AmazonBedrockRuntimeClient(RegionEndpoint.USEast1)) // Specify a region that has access to the chosen model.
                    .AddTransient<BedrockActionsWrapper>()
                    .AddTransient<WeatherTool>()
                    .RemoveAll<IHttpMessageHandlerBuilderFilter>()
            )
            .Build();

        ServicesSetup(host);

        try
        {
            await RunConversationAsync();

        }
        catch (Exception ex)
        {
            Console.WriteLine(new string('-', 80));
            Console.WriteLine($"There was a problem running the scenario: {ex.Message}");
            Console.WriteLine(new string('-', 80));
        }
        finally
        {
            Console.WriteLine(
                "Amazon Bedrock Converse API with Tool Use Feature Scenario is complete.");
            Console.WriteLine(new string('-', 80));
        }
    }

    /// <summary>
    /// Populate the services for use within the console application.
    /// </summary>
    /// <param name="host">The services host.</param>
    private static void ServicesSetup(IHost host)
    {
        _bedrockActionsWrapper = host.Services.GetRequiredService<BedrockActionsWrapper>();
        _weatherTool = host.Services.GetRequiredService<WeatherTool>();
    }

    /// <summary>
    /// Starts the conversation with the user and handles the interaction with Bedrock.
    /// </summary>
    /// <returns>The conversation array.</returns>
    public static async Task<List<Message>> RunConversationAsync()
    {
        // Print the greeting and a short user guide
        PrintHeader();

        // Start with an empty conversation
        var conversation = new List<Message>();

        // Get the first user input
        var userInput = await GetUserInputAsync();

        while (userInput != null)
        {
            // Create a new message with the user input and append it to the conversation
            var message = new Message { Role = ConversationRole.User, Content = new List<ContentBlock> { new ContentBlock { Text = userInput } } };
            conversation.Add(message);

            // Send the conversation to Amazon Bedrock
            var bedrockResponse = await SendConversationToBedrock(conversation);

            // Recursively handle the model's response until the model has returned its final response or the recursion counter has reached 0
            await ProcessModelResponseAsync(bedrockResponse, conversation, max_recursions);

            // Repeat the loop until the user decides to exit the application
            userInput = await GetUserInputAsync();
        }

        PrintFooter();
        return conversation;
    }

    /// <summary>
    /// Sends the conversation, the system prompt, and the tool spec to Amazon Bedrock, and returns the response.
    /// </summary>
    /// <param name="conversation">The conversation history including the next message to send.</param>
    /// <returns>The response from Amazon Bedrock.</returns>
    private static async Task<ConverseResponse> SendConversationToBedrock(List<Message> conversation)
    {
        Console.WriteLine("\tCalling Bedrock...");

        // Send the conversation, system prompt, and tool configuration, and return the response
        return await _bedrockActionsWrapper.SendConverseRequestAsync(model_id, system_prompt, conversation, _weatherTool.GetToolSpec());
    }

    /// <summary>
    /// Processes the response received via Amazon Bedrock and performs the necessary actions based on the stop reason.
    /// </summary>
    /// <param name="modelResponse">The model's response returned via Amazon Bedrock.</param>
    /// <param name="conversation">The conversation history.</param>
    /// <param name="maxRecursion">The maximum number of recursive calls allowed.</param>
    private static async Task ProcessModelResponseAsync(ConverseResponse modelResponse, List<Message> conversation, int maxRecursion)
    {
        if (maxRecursion <= 0)
        {
            // Stop the process, the number of recursive calls could indicate an infinite loop
            Console.WriteLine("\tWarning: Maximum number of recursions reached. Please try again.");
        }

        // Append the model's response to the ongoing conversation
        conversation.Add(modelResponse.Output.Message);

        if (modelResponse.StopReason == "tool_use")
        {
            // If the stop reason is "tool_use", forward everything to the tool use handler
            await HandleToolUseAsync(modelResponse.Output, conversation, maxRecursion - 1);
        }

        if (modelResponse.StopReason == "end_turn")
        {
            // If the stop reason is "end_turn", print the model's response text, and finish the process
            PrintModelResponse(modelResponse.Output.Message.Content[0].Text);
            if (!_interactive)
            {
                default_prompt = "x";
            }
        }
    }

    /// <summary>
    /// Handles the tool use case by invoking the specified tool and sending the tool's response back to Bedrock.
    /// The tool response is appended to the conversation, and the conversation is sent back to Amazon Bedrock for further processing.
    /// </summary>
    /// <param name="modelResponse">The model's response containing the tool use request.</param>
    /// <param name="conversation">The conversation history.</param>
    /// <param name="maxRecursion">The maximum number of recursive calls allowed.</param>
    public static async Task HandleToolUseAsync(ConverseOutput modelResponse, List<Message> conversation, int maxRecursion)
    {
        // Initialize an empty list of tool results
        var toolResults = new List<ContentBlock>();

        // The model's response can consist of multiple content blocks
        foreach (var contentBlock in modelResponse.Message.Content)
        {
            if (!String.IsNullOrEmpty(contentBlock.Text))
            {
                // If the content block contains text, print it to the console
                PrintModelResponse(contentBlock.Text);
            }

            if (contentBlock.ToolUse != null)
            {
                // If the content block is a tool use request, forward it to the tool
                var toolResponse = await InvokeTool(contentBlock.ToolUse);

                // Add the tool use ID and the tool's response to the list of results
                toolResults.Add(new ContentBlock
                {
                    ToolResult = new ToolResultBlock()
                    {
                        ToolUseId = toolResponse.ToolUseId,
                        Content = new List<ToolResultContentBlock>()
                            { new ToolResultContentBlock { Json = toolResponse.Content } }
                    }
                });
            }
        }

        // Embed the tool results in a new user message
        var message = new Message() { Role = ConversationRole.User, Content = toolResults };

        // Append the new message to the ongoing conversation
        conversation.Add(message);

        // Send the conversation to Amazon Bedrock
        var response = await SendConversationToBedrock(conversation);

        // Recursively handle the model's response until the model has returned its final response or the recursion counter has reached 0
        await ProcessModelResponseAsync(response, conversation, maxRecursion);
    }

    /// <summary>
    /// Invokes the specified tool with the given payload and returns the tool's response.
    /// If the requested tool does not exist, an error message is returned.
    /// </summary>
    /// <param name="payload">The payload containing the tool name and input data.</param>
    /// <returns>The tool's response or an error message.</returns>
    public static async Task<ToolResponse> InvokeTool(ToolUseBlock payload)
    {
        var toolName = payload.Name;

        if (toolName == "Weather_Tool")
        {
            var inputData = payload.Input.AsDictionary();
            PrintToolUse(toolName, inputData);

            // Invoke the weather tool with the input data provided
            var weatherResponse = await _weatherTool.FetchWeatherDataAsync(inputData["latitude"].ToString(), inputData["longitude"].ToString());
            return new ToolResponse { ToolUseId = payload.ToolUseId, Content = weatherResponse };
        }
        else
        {
            var errorMessage = $"\tThe requested tool with name '{toolName}' does not exist.";
            return new ToolResponse { ToolUseId = payload.ToolUseId, Content = new { error = true, message = errorMessage } };
        }
    }


    /// <summary>
    /// Prompts the user for input and returns the user's response.
    /// Returns null if the user enters 'x' to exit.
    /// </summary>
    /// <param name="prompt">The prompt to display to the user.</param>
    /// <returns>The user's input or null if the user chooses to exit.</returns>
    private static async Task<string?> GetUserInputAsync(string prompt = "\tYour weather info request:")
    {
        var userInput = default_prompt;
        if (_interactive)
        {
            Console.WriteLine(new string('*', 80));
            Console.WriteLine($"{prompt} (x to exit): \n\t");
            userInput = Console.ReadLine();
        }

        if (string.IsNullOrWhiteSpace(userInput))
        {
            prompt = "\tPlease enter your weather info request, e.g. the name of a city";
            return await GetUserInputAsync(prompt);
        }

        if (userInput.ToLowerInvariant() == "x")
        {
            return null;
        }

        return userInput;
    }

    /// <summary>
    /// Logs the welcome message and usage guide for the tool use demo.
    /// </summary>
    public static void PrintHeader()
    {
        Console.WriteLine(@"
        =================================================
        Welcome to the Amazon Bedrock Tool Use demo!
        =================================================

        This assistant provides current weather information for user-specified locations.
        You can ask for weather details by providing the location name or coordinates. Weather information
        will be provided using a custom Tool and open-meteo API.

        Example queries:
        - What's the weather like in New York?
        - Current weather for latitude 40.70, longitude -74.01
        - Is it warmer in Rome or Barcelona today?

        To exit the program, simply type 'x' and press Enter.

        P.S.: You're not limited to single locations, or even to using English!
        Have fun and experiment with the app!
        ");
    }

    /// <summary>
    /// Logs the footer information for the tool use demo.
    /// </summary>
    public static void PrintFooter()
    {
        Console.WriteLine(@"
        =================================================
        Thank you for checking out the Amazon Bedrock Tool Use demo. We hope you
        learned something new, or got some inspiration for your own apps today!

        For more Bedrock examples in different programming languages, have a look at:
        https://docs.aws.amazon.com/bedrock/latest/userguide/service_code_examples.html
        =================================================
        ");
    }

    /// <summary>
    /// Logs information about the tool use.
    /// </summary>
    /// <param name="toolName">The name of the tool being used.</param>
    /// <param name="inputData">The input data for the tool.</param>
    public static void PrintToolUse(string toolName, Dictionary<string, Document> inputData)
    {
        Console.WriteLine($"\n\tInvoking tool: {toolName} with input: {inputData["latitude"].ToString()}, {inputData["longitude"].ToString()}...\n");
    }

    /// <summary>
    /// Logs the model's response.
    /// </summary>
    /// <param name="message">The model's response message.</param>
    public static void PrintModelResponse(string message)
    {
        Console.WriteLine("\tThe model's response:\n");
        Console.WriteLine(message);
        Console.WriteLine();
    }
}

L'outil météo utilisé par la démo. Ce fichier définit les spécifications de l'outil et implémente la logique permettant de récupérer les données météorologiques à l'aide de l'API Open-Meteo.

using Amazon.BedrockRuntime.Model;
using Amazon.Runtime.Documents;
using Microsoft.Extensions.Logging;

namespace ConverseToolScenario;

/// <summary>
/// Weather tool that will be invoked when requested by the Bedrock response.
/// </summary>
public class WeatherTool
{
    private readonly ILogger<WeatherTool> _logger;
    private readonly IHttpClientFactory _httpClientFactory;

    public WeatherTool(ILogger<WeatherTool> logger, IHttpClientFactory httpClientFactory)
    {
        _logger = logger;
        _httpClientFactory = httpClientFactory;
    }

    /// <summary>
    /// Returns the JSON Schema specification for the Weather tool. The tool specification
    /// defines the input schema and describes the tool's functionality.
    /// For more information, see https://json-schema.org/understanding-json-schema/reference.
    /// </summary>
    /// <returns>The tool specification for the Weather tool.</returns>
    public ToolSpecification GetToolSpec()
    {
        ToolSpecification toolSpecification = new ToolSpecification();

        toolSpecification.Name = "Weather_Tool";
        toolSpecification.Description = "Get the current weather for a given location, based on its WGS84 coordinates.";

        Document toolSpecDocument = Document.FromObject(
            new
            {
                type = "object",
                properties = new
                {
                    latitude = new
                    {
                        type = "string",
                        description = "Geographical WGS84 latitude of the location."
                    },
                    longitude = new
                    {
                        type = "string",
                        description = "Geographical WGS84 longitude of the location."
                    }
                },
                required = new[] { "latitude", "longitude" }
            });

        toolSpecification.InputSchema = new ToolInputSchema() { Json = toolSpecDocument };
        return toolSpecification;
    }

    /// <summary>
    /// Fetches weather data for the given latitude and longitude using the Open-Meteo API.
    /// Returns the weather data or an error message if the request fails.
    /// </summary>
    /// <param name="latitude">The latitude of the location.</param>
    /// <param name="longitude">The longitude of the location.</param>
    /// <returns>The weather data or an error message.</returns>
    public async Task<Document> FetchWeatherDataAsync(string latitude, string longitude)
    {
        string endpoint = "https://api.open-meteo.com/v1/forecast";

        try
        {
            var httpClient = _httpClientFactory.CreateClient();
            var response = await httpClient.GetAsync($"{endpoint}?latitude={latitude}&longitude={longitude}&current_weather=True");
            response.EnsureSuccessStatusCode();
            var weatherData = await response.Content.ReadAsStringAsync();

            Document weatherDocument = Document.FromObject(
                new { weather_data = weatherData });

            return weatherDocument;
        }
        catch (HttpRequestException e)
        {
            _logger.LogError(e, "Error fetching weather data: {Message}", e.Message);
            throw;
        }
        catch (Exception e)
        {
            _logger.LogError(e, "Unexpected error fetching weather data: {Message}", e.Message);
            throw;
        }
    }
}

L'action de l'API Converse avec une configuration d'outil.

/// <summary>
/// Wrapper class for interacting with the Amazon Bedrock Converse API.
/// </summary>
public class BedrockActionsWrapper
{
    private readonly IAmazonBedrockRuntime _bedrockClient;
    private readonly ILogger<BedrockActionsWrapper> _logger;

    /// <summary>
    /// Initializes a new instance of the <see cref="BedrockActionsWrapper"/> class.
    /// </summary>
    /// <param name="bedrockClient">The Bedrock Converse API client.</param>
    /// <param name="logger">The logger instance.</param>
    public BedrockActionsWrapper(IAmazonBedrockRuntime bedrockClient, ILogger<BedrockActionsWrapper> logger)
    {
        _bedrockClient = bedrockClient;
        _logger = logger;
    }

    /// <summary>
    /// Sends a Converse request to the Amazon Bedrock Converse API.
    /// </summary>
    /// <param name="modelId">The Bedrock Model Id.</param>
    /// <param name="systemPrompt">A system prompt instruction.</param>
    /// <param name="conversation">The array of messages in the conversation.</param>
    /// <param name="toolSpec">The specification for a tool.</param>
    /// <returns>The response of the model.</returns>
    public async Task<ConverseResponse> SendConverseRequestAsync(string modelId, string systemPrompt, List<Message> conversation, ToolSpecification toolSpec)
    {
        try
        {
            var request = new ConverseRequest()
            {
                ModelId = modelId,
                System = new List<SystemContentBlock>()
                {
                    new SystemContentBlock()
                    {
                        Text = systemPrompt
                    }
                },
                Messages = conversation,
                ToolConfig = new ToolConfiguration()
                {
                    Tools = new List<Tool>()
                    {
                        new Tool()
                        {
                            ToolSpec = toolSpec
                        }
                    }
                }
            };

            var response = await _bedrockClient.ConverseAsync(request);

            return response;
        }
        catch (ModelNotReadyException ex)
        {
            _logger.LogError(ex, "Model not ready, please wait and try again.");
            throw;
        }
        catch (AmazonBedrockRuntimeException ex)
        {
            _logger.LogError(ex, "Error occurred while sending Converse request.");
            throw;
        }
    }
}

• Pour plus de détails sur l'API, consultez Converse dans le manuel AWS SDK for .NET API Reference.

Scénario : utilisation de l'outil avec l'API Converse

L'exemple de code suivant montre comment créer une interaction typique entre une application, un modèle d'IA génératif et des outils connectés ou comment APIs arbitrer les interactions entre l'IA et le monde extérieur. Il utilise l'exemple de la connexion d'une API météo externe au modèle d'IA afin de fournir des informations météorologiques en temps réel en fonction des entrées de l'utilisateur.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Exécution principale du flux de scénarios. Ce scénario orchestre la conversation entre l'utilisateur, l'API Amazon Bedrock Converse et un outil météo.

using Amazon;
using Amazon.BedrockRuntime;
using Amazon.BedrockRuntime.Model;
using Amazon.Runtime.Documents;
using Microsoft.Extensions.DependencyInjection;
using Microsoft.Extensions.DependencyInjection.Extensions;
using Microsoft.Extensions.Hosting;
using Microsoft.Extensions.Http;
using Microsoft.Extensions.Logging;
using Microsoft.Extensions.Logging.Console;

namespace ConverseToolScenario;

public static class ConverseToolScenario
{
    /*
    Before running this .NET code example, set up your development environment, including your credentials.

    This demo illustrates a tool use scenario using Amazon Bedrock's Converse API and a weather tool.
    The script interacts with a foundation model on Amazon Bedrock to provide weather information based on user
    input. It uses the Open-Meteo API (https://open-meteo.com) to retrieve current weather data for a given location.
   */

    public static BedrockActionsWrapper _bedrockActionsWrapper = null!;
    public static WeatherTool _weatherTool = null!;
    public static bool _interactive = true;

    // Change this string to use a different model with Converse API.
    private static string model_id = "amazon.nova-lite-v1:0";

    private static string system_prompt = @"
        You are a weather assistant that provides current weather data for user-specified locations using only
        the Weather_Tool, which expects latitude and longitude. Infer the coordinates from the location yourself.
        If the user provides coordinates, infer the approximate location and refer to it in your response.
        To use the tool, you strictly apply the provided tool specification.

        - Explain your step-by-step process, and give brief updates before each step.
        - Only use the Weather_Tool for data. Never guess or make up information. 
        - Repeat the tool use for subsequent requests if necessary.
        - If the tool errors, apologize, explain weather is unavailable, and suggest other options.
        - Report temperatures in °C (°F) and wind in km/h (mph). Keep weather reports concise. Sparingly use
          emojis where appropriate.
        - Only respond to weather queries. Remind off-topic users of your purpose. 
        - Never claim to search online, access external data, or use tools besides Weather_Tool.
        - Complete the entire process until you have all required data before sending the complete response.
    "
    ;

    private static string default_prompt = "What is the weather like in Seattle?";

    // The maximum number of recursive calls allowed in the tool use function.
    // This helps prevent infinite loops and potential performance issues.
    private static int max_recursions = 5;

    public static async Task Main(string[] args)
    {
        // Set up dependency injection for the Amazon service.
        using var host = Host.CreateDefaultBuilder(args)
            .ConfigureLogging(logging =>
                logging.AddFilter("System", LogLevel.Error)
                    .AddFilter<ConsoleLoggerProvider>("Microsoft", LogLevel.Trace))
            .ConfigureServices((_, services) =>
                services.AddHttpClient()
                    .AddSingleton<IAmazonBedrockRuntime>(_ => new AmazonBedrockRuntimeClient(RegionEndpoint.USEast1)) // Specify a region that has access to the chosen model.
                    .AddTransient<BedrockActionsWrapper>()
                    .AddTransient<WeatherTool>()
                    .RemoveAll<IHttpMessageHandlerBuilderFilter>()
            )
            .Build();

        ServicesSetup(host);

        try
        {
            await RunConversationAsync();

        }
        catch (Exception ex)
        {
            Console.WriteLine(new string('-', 80));
            Console.WriteLine($"There was a problem running the scenario: {ex.Message}");
            Console.WriteLine(new string('-', 80));
        }
        finally
        {
            Console.WriteLine(
                "Amazon Bedrock Converse API with Tool Use Feature Scenario is complete.");
            Console.WriteLine(new string('-', 80));
        }
    }

    /// <summary>
    /// Populate the services for use within the console application.
    /// </summary>
    /// <param name="host">The services host.</param>
    private static void ServicesSetup(IHost host)
    {
        _bedrockActionsWrapper = host.Services.GetRequiredService<BedrockActionsWrapper>();
        _weatherTool = host.Services.GetRequiredService<WeatherTool>();
    }

    /// <summary>
    /// Starts the conversation with the user and handles the interaction with Bedrock.
    /// </summary>
    /// <returns>The conversation array.</returns>
    public static async Task<List<Message>> RunConversationAsync()
    {
        // Print the greeting and a short user guide
        PrintHeader();

        // Start with an empty conversation
        var conversation = new List<Message>();

        // Get the first user input
        var userInput = await GetUserInputAsync();

        while (userInput != null)
        {
            // Create a new message with the user input and append it to the conversation
            var message = new Message { Role = ConversationRole.User, Content = new List<ContentBlock> { new ContentBlock { Text = userInput } } };
            conversation.Add(message);

            // Send the conversation to Amazon Bedrock
            var bedrockResponse = await SendConversationToBedrock(conversation);

            // Recursively handle the model's response until the model has returned its final response or the recursion counter has reached 0
            await ProcessModelResponseAsync(bedrockResponse, conversation, max_recursions);

            // Repeat the loop until the user decides to exit the application
            userInput = await GetUserInputAsync();
        }

        PrintFooter();
        return conversation;
    }

    /// <summary>
    /// Sends the conversation, the system prompt, and the tool spec to Amazon Bedrock, and returns the response.
    /// </summary>
    /// <param name="conversation">The conversation history including the next message to send.</param>
    /// <returns>The response from Amazon Bedrock.</returns>
    private static async Task<ConverseResponse> SendConversationToBedrock(List<Message> conversation)
    {
        Console.WriteLine("\tCalling Bedrock...");

        // Send the conversation, system prompt, and tool configuration, and return the response
        return await _bedrockActionsWrapper.SendConverseRequestAsync(model_id, system_prompt, conversation, _weatherTool.GetToolSpec());
    }

    /// <summary>
    /// Processes the response received via Amazon Bedrock and performs the necessary actions based on the stop reason.
    /// </summary>
    /// <param name="modelResponse">The model's response returned via Amazon Bedrock.</param>
    /// <param name="conversation">The conversation history.</param>
    /// <param name="maxRecursion">The maximum number of recursive calls allowed.</param>
    private static async Task ProcessModelResponseAsync(ConverseResponse modelResponse, List<Message> conversation, int maxRecursion)
    {
        if (maxRecursion <= 0)
        {
            // Stop the process, the number of recursive calls could indicate an infinite loop
            Console.WriteLine("\tWarning: Maximum number of recursions reached. Please try again.");
        }

        // Append the model's response to the ongoing conversation
        conversation.Add(modelResponse.Output.Message);

        if (modelResponse.StopReason == "tool_use")
        {
            // If the stop reason is "tool_use", forward everything to the tool use handler
            await HandleToolUseAsync(modelResponse.Output, conversation, maxRecursion - 1);
        }

        if (modelResponse.StopReason == "end_turn")
        {
            // If the stop reason is "end_turn", print the model's response text, and finish the process
            PrintModelResponse(modelResponse.Output.Message.Content[0].Text);
            if (!_interactive)
            {
                default_prompt = "x";
            }
        }
    }

    /// <summary>
    /// Handles the tool use case by invoking the specified tool and sending the tool's response back to Bedrock.
    /// The tool response is appended to the conversation, and the conversation is sent back to Amazon Bedrock for further processing.
    /// </summary>
    /// <param name="modelResponse">The model's response containing the tool use request.</param>
    /// <param name="conversation">The conversation history.</param>
    /// <param name="maxRecursion">The maximum number of recursive calls allowed.</param>
    public static async Task HandleToolUseAsync(ConverseOutput modelResponse, List<Message> conversation, int maxRecursion)
    {
        // Initialize an empty list of tool results
        var toolResults = new List<ContentBlock>();

        // The model's response can consist of multiple content blocks
        foreach (var contentBlock in modelResponse.Message.Content)
        {
            if (!String.IsNullOrEmpty(contentBlock.Text))
            {
                // If the content block contains text, print it to the console
                PrintModelResponse(contentBlock.Text);
            }

            if (contentBlock.ToolUse != null)
            {
                // If the content block is a tool use request, forward it to the tool
                var toolResponse = await InvokeTool(contentBlock.ToolUse);

                // Add the tool use ID and the tool's response to the list of results
                toolResults.Add(new ContentBlock
                {
                    ToolResult = new ToolResultBlock()
                    {
                        ToolUseId = toolResponse.ToolUseId,
                        Content = new List<ToolResultContentBlock>()
                            { new ToolResultContentBlock { Json = toolResponse.Content } }
                    }
                });
            }
        }

        // Embed the tool results in a new user message
        var message = new Message() { Role = ConversationRole.User, Content = toolResults };

        // Append the new message to the ongoing conversation
        conversation.Add(message);

        // Send the conversation to Amazon Bedrock
        var response = await SendConversationToBedrock(conversation);

        // Recursively handle the model's response until the model has returned its final response or the recursion counter has reached 0
        await ProcessModelResponseAsync(response, conversation, maxRecursion);
    }

    /// <summary>
    /// Invokes the specified tool with the given payload and returns the tool's response.
    /// If the requested tool does not exist, an error message is returned.
    /// </summary>
    /// <param name="payload">The payload containing the tool name and input data.</param>
    /// <returns>The tool's response or an error message.</returns>
    public static async Task<ToolResponse> InvokeTool(ToolUseBlock payload)
    {
        var toolName = payload.Name;

        if (toolName == "Weather_Tool")
        {
            var inputData = payload.Input.AsDictionary();
            PrintToolUse(toolName, inputData);

            // Invoke the weather tool with the input data provided
            var weatherResponse = await _weatherTool.FetchWeatherDataAsync(inputData["latitude"].ToString(), inputData["longitude"].ToString());
            return new ToolResponse { ToolUseId = payload.ToolUseId, Content = weatherResponse };
        }
        else
        {
            var errorMessage = $"\tThe requested tool with name '{toolName}' does not exist.";
            return new ToolResponse { ToolUseId = payload.ToolUseId, Content = new { error = true, message = errorMessage } };
        }
    }


    /// <summary>
    /// Prompts the user for input and returns the user's response.
    /// Returns null if the user enters 'x' to exit.
    /// </summary>
    /// <param name="prompt">The prompt to display to the user.</param>
    /// <returns>The user's input or null if the user chooses to exit.</returns>
    private static async Task<string?> GetUserInputAsync(string prompt = "\tYour weather info request:")
    {
        var userInput = default_prompt;
        if (_interactive)
        {
            Console.WriteLine(new string('*', 80));
            Console.WriteLine($"{prompt} (x to exit): \n\t");
            userInput = Console.ReadLine();
        }

        if (string.IsNullOrWhiteSpace(userInput))
        {
            prompt = "\tPlease enter your weather info request, e.g. the name of a city";
            return await GetUserInputAsync(prompt);
        }

        if (userInput.ToLowerInvariant() == "x")
        {
            return null;
        }

        return userInput;
    }

    /// <summary>
    /// Logs the welcome message and usage guide for the tool use demo.
    /// </summary>
    public static void PrintHeader()
    {
        Console.WriteLine(@"
        =================================================
        Welcome to the Amazon Bedrock Tool Use demo!
        =================================================

        This assistant provides current weather information for user-specified locations.
        You can ask for weather details by providing the location name or coordinates. Weather information
        will be provided using a custom Tool and open-meteo API.

        Example queries:
        - What's the weather like in New York?
        - Current weather for latitude 40.70, longitude -74.01
        - Is it warmer in Rome or Barcelona today?

        To exit the program, simply type 'x' and press Enter.

        P.S.: You're not limited to single locations, or even to using English!
        Have fun and experiment with the app!
        ");
    }

    /// <summary>
    /// Logs the footer information for the tool use demo.
    /// </summary>
    public static void PrintFooter()
    {
        Console.WriteLine(@"
        =================================================
        Thank you for checking out the Amazon Bedrock Tool Use demo. We hope you
        learned something new, or got some inspiration for your own apps today!

        For more Bedrock examples in different programming languages, have a look at:
        https://docs.aws.amazon.com/bedrock/latest/userguide/service_code_examples.html
        =================================================
        ");
    }

    /// <summary>
    /// Logs information about the tool use.
    /// </summary>
    /// <param name="toolName">The name of the tool being used.</param>
    /// <param name="inputData">The input data for the tool.</param>
    public static void PrintToolUse(string toolName, Dictionary<string, Document> inputData)
    {
        Console.WriteLine($"\n\tInvoking tool: {toolName} with input: {inputData["latitude"].ToString()}, {inputData["longitude"].ToString()}...\n");
    }

    /// <summary>
    /// Logs the model's response.
    /// </summary>
    /// <param name="message">The model's response message.</param>
    public static void PrintModelResponse(string message)
    {
        Console.WriteLine("\tThe model's response:\n");
        Console.WriteLine(message);
        Console.WriteLine();
    }
}

L'outil météo utilisé par la démo. Ce fichier définit les spécifications de l'outil et implémente la logique permettant de récupérer les données météorologiques à l'aide de l'API Open-Meteo.

using Amazon.BedrockRuntime.Model;
using Amazon.Runtime.Documents;
using Microsoft.Extensions.Logging;

namespace ConverseToolScenario;

/// <summary>
/// Weather tool that will be invoked when requested by the Bedrock response.
/// </summary>
public class WeatherTool
{
    private readonly ILogger<WeatherTool> _logger;
    private readonly IHttpClientFactory _httpClientFactory;

    public WeatherTool(ILogger<WeatherTool> logger, IHttpClientFactory httpClientFactory)
    {
        _logger = logger;
        _httpClientFactory = httpClientFactory;
    }

    /// <summary>
    /// Returns the JSON Schema specification for the Weather tool. The tool specification
    /// defines the input schema and describes the tool's functionality.
    /// For more information, see https://json-schema.org/understanding-json-schema/reference.
    /// </summary>
    /// <returns>The tool specification for the Weather tool.</returns>
    public ToolSpecification GetToolSpec()
    {
        ToolSpecification toolSpecification = new ToolSpecification();

        toolSpecification.Name = "Weather_Tool";
        toolSpecification.Description = "Get the current weather for a given location, based on its WGS84 coordinates.";

        Document toolSpecDocument = Document.FromObject(
            new
            {
                type = "object",
                properties = new
                {
                    latitude = new
                    {
                        type = "string",
                        description = "Geographical WGS84 latitude of the location."
                    },
                    longitude = new
                    {
                        type = "string",
                        description = "Geographical WGS84 longitude of the location."
                    }
                },
                required = new[] { "latitude", "longitude" }
            });

        toolSpecification.InputSchema = new ToolInputSchema() { Json = toolSpecDocument };
        return toolSpecification;
    }

    /// <summary>
    /// Fetches weather data for the given latitude and longitude using the Open-Meteo API.
    /// Returns the weather data or an error message if the request fails.
    /// </summary>
    /// <param name="latitude">The latitude of the location.</param>
    /// <param name="longitude">The longitude of the location.</param>
    /// <returns>The weather data or an error message.</returns>
    public async Task<Document> FetchWeatherDataAsync(string latitude, string longitude)
    {
        string endpoint = "https://api.open-meteo.com/v1/forecast";

        try
        {
            var httpClient = _httpClientFactory.CreateClient();
            var response = await httpClient.GetAsync($"{endpoint}?latitude={latitude}&longitude={longitude}&current_weather=True");
            response.EnsureSuccessStatusCode();
            var weatherData = await response.Content.ReadAsStringAsync();

            Document weatherDocument = Document.FromObject(
                new { weather_data = weatherData });

            return weatherDocument;
        }
        catch (HttpRequestException e)
        {
            _logger.LogError(e, "Error fetching weather data: {Message}", e.Message);
            throw;
        }
        catch (Exception e)
        {
            _logger.LogError(e, "Unexpected error fetching weather data: {Message}", e.Message);
            throw;
        }
    }
}

L'action de l'API Converse avec une configuration d'outil.

/// <summary>
/// Wrapper class for interacting with the Amazon Bedrock Converse API.
/// </summary>
public class BedrockActionsWrapper
{
    private readonly IAmazonBedrockRuntime _bedrockClient;
    private readonly ILogger<BedrockActionsWrapper> _logger;

    /// <summary>
    /// Initializes a new instance of the <see cref="BedrockActionsWrapper"/> class.
    /// </summary>
    /// <param name="bedrockClient">The Bedrock Converse API client.</param>
    /// <param name="logger">The logger instance.</param>
    public BedrockActionsWrapper(IAmazonBedrockRuntime bedrockClient, ILogger<BedrockActionsWrapper> logger)
    {
        _bedrockClient = bedrockClient;
        _logger = logger;
    }

    /// <summary>
    /// Sends a Converse request to the Amazon Bedrock Converse API.
    /// </summary>
    /// <param name="modelId">The Bedrock Model Id.</param>
    /// <param name="systemPrompt">A system prompt instruction.</param>
    /// <param name="conversation">The array of messages in the conversation.</param>
    /// <param name="toolSpec">The specification for a tool.</param>
    /// <returns>The response of the model.</returns>
    public async Task<ConverseResponse> SendConverseRequestAsync(string modelId, string systemPrompt, List<Message> conversation, ToolSpecification toolSpec)
    {
        try
        {
            var request = new ConverseRequest()
            {
                ModelId = modelId,
                System = new List<SystemContentBlock>()
                {
                    new SystemContentBlock()
                    {
                        Text = systemPrompt
                    }
                },
                Messages = conversation,
                ToolConfig = new ToolConfiguration()
                {
                    Tools = new List<Tool>()
                    {
                        new Tool()
                        {
                            ToolSpec = toolSpec
                        }
                    }
                }
            };

            var response = await _bedrockClient.ConverseAsync(request);

            return response;
        }
        catch (ModelNotReadyException ex)
        {
            _logger.LogError(ex, "Model not ready, please wait and try again.");
            throw;
        }
        catch (AmazonBedrockRuntimeException ex)
        {
            _logger.LogError(ex, "Error occurred while sending Converse request.");
            throw;
        }
    }
}

• Pour plus de détails sur l'API, consultez Converse dans le manuel AWS SDK for .NET API Reference.

Toile Amazon Nova

InvokeModel

L'exemple de code suivant montre comment invoquer Amazon Nova Canvas sur Amazon Bedrock pour générer une image.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Créez une image avec Amazon Nova Canvas.

// Use the native inference API to create an image with Amazon Nova Canvas.

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.
var modelId = "amazon.nova-canvas-v1:0";

// Define the image generation prompt for the model.
var prompt = "A stylized picture of a cute old steampunk robot.";

// Create a random seed between 0 and 858,993,459
int seed = new Random().Next(0, 858993460);

//Format the request payload using the model's native structure.
var nativeRequest = JsonSerializer.Serialize(new
{
    taskType = "TEXT_IMAGE",
    textToImageParams = new
    {
        text = prompt
    },
    imageGenerationConfig = new
    {
        seed,
        quality = "standard",
        width = 512,
        height = 512,
        numberOfImages = 1
    }
});

// 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 the image data.
    var base64Image = modelResponse["images"]?[0].ToString() ?? "";

    // Save the image in a local folder
    string savedPath = AmazonNovaCanvas.InvokeModel.SaveBase64Image(base64Image);
    Console.WriteLine($"Image saved to: {savedPath}");
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

• Pour plus de détails sur l'API, reportez-vous InvokeModelà la section Référence des AWS SDK for .NET API.

InvokeModel

L'exemple de code suivant montre comment invoquer Amazon Nova Canvas sur Amazon Bedrock pour générer une image.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Créez une image avec Amazon Nova Canvas.

// Use the native inference API to create an image with Amazon Nova Canvas.

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.
var modelId = "amazon.nova-canvas-v1:0";

// Define the image generation prompt for the model.
var prompt = "A stylized picture of a cute old steampunk robot.";

// Create a random seed between 0 and 858,993,459
int seed = new Random().Next(0, 858993460);

//Format the request payload using the model's native structure.
var nativeRequest = JsonSerializer.Serialize(new
{
    taskType = "TEXT_IMAGE",
    textToImageParams = new
    {
        text = prompt
    },
    imageGenerationConfig = new
    {
        seed,
        quality = "standard",
        width = 512,
        height = 512,
        numberOfImages = 1
    }
});

// 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 the image data.
    var base64Image = modelResponse["images"]?[0].ToString() ?? "";

    // Save the image in a local folder
    string savedPath = AmazonNovaCanvas.InvokeModel.SaveBase64Image(base64Image);
    Console.WriteLine($"Image saved to: {savedPath}");
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

• Pour plus de détails sur l'API, reportez-vous InvokeModelà la section Référence des AWS SDK for .NET API.

Texte Amazon Titan

Converse

L'exemple de code suivant montre comment envoyer un message texte à Amazon Titan Text à l'aide de l'API Converse de Bedrock.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Envoyez un SMS à Amazon Titan Text à l'aide de l'API Converse de Bedrock.

// Use the Converse API to send a text message to Amazon Titan Text.

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., Titan Text Premier.
var modelId = "amazon.titan-text-premier-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;
}

• Pour plus de détails sur l'API, consultez Converse dans le manuel AWS SDK for .NET API Reference.

Converse

L'exemple de code suivant montre comment envoyer un message texte à Amazon Titan Text à l'aide de l'API Converse de Bedrock.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Envoyez un SMS à Amazon Titan Text à l'aide de l'API Converse de Bedrock.

// Use the Converse API to send a text message to Amazon Titan Text.

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., Titan Text Premier.
var modelId = "amazon.titan-text-premier-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;
}

• Pour plus de détails sur l'API, consultez Converse dans le manuel AWS SDK for .NET API Reference.

ConverseStream

L'exemple de code suivant montre comment envoyer un message texte à Amazon Titan Text à l'aide de l'API Converse de Bedrock et comment traiter le flux de réponses en temps réel.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Envoyez un SMS à Amazon Titan Text à l'aide de l'API Converse de Bedrock et traitez le flux de réponses en temps réel.

// Use the Converse API to send a text message to Amazon Titan Text
// 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., Titan Text Premier.
var modelId = "amazon.titan-text-premier-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;
}

• Pour plus de détails sur l'API, reportez-vous ConverseStreamà la section Référence des AWS SDK for .NET API.

ConverseStream

L'exemple de code suivant montre comment envoyer un message texte à Amazon Titan Text à l'aide de l'API Converse de Bedrock et comment traiter le flux de réponses en temps réel.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Envoyez un SMS à Amazon Titan Text à l'aide de l'API Converse de Bedrock et traitez le flux de réponses en temps réel.

// Use the Converse API to send a text message to Amazon Titan Text
// 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., Titan Text Premier.
var modelId = "amazon.titan-text-premier-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;
}

• Pour plus de détails sur l'API, reportez-vous ConverseStreamà la section Référence des AWS SDK for .NET API.

InvokeModel

L'exemple de code suivant montre comment envoyer un message texte à Amazon Titan Text à l'aide de l'API Invoke Model.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Utilisez l'API Invoke Model pour envoyer un message texte.

// Use the native inference API to send a text message to Amazon Titan Text.

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., Titan Text Premier.
var modelId = "amazon.titan-text-premier-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
{
    inputText = userMessage,
    textGenerationConfig = new
    {
        maxTokenCount = 512,
        temperature = 0.5
    }
});

// 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["results"]?[0]?["outputText"] ?? "";
    Console.WriteLine(responseText);
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

• Pour plus de détails sur l'API, reportez-vous InvokeModelà la section Référence des AWS SDK for .NET API.

InvokeModel

L'exemple de code suivant montre comment envoyer un message texte à Amazon Titan Text à l'aide de l'API Invoke Model.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Utilisez l'API Invoke Model pour envoyer un message texte.

// Use the native inference API to send a text message to Amazon Titan Text.

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., Titan Text Premier.
var modelId = "amazon.titan-text-premier-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
{
    inputText = userMessage,
    textGenerationConfig = new
    {
        maxTokenCount = 512,
        temperature = 0.5
    }
});

// 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["results"]?[0]?["outputText"] ?? "";
    Console.WriteLine(responseText);
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

• Pour plus de détails sur l'API, reportez-vous InvokeModelà la section Référence des AWS SDK for .NET API.

InvokeModelWithResponseStream

L'exemple de code suivant montre comment envoyer un message texte aux modèles Amazon Titan Text, à l'aide de l'API Invoke Model, et comment imprimer le flux de réponses.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Utilisez l'API Invoke Model pour envoyer un message texte et traiter le flux de réponses en temps réel.

// Use the native inference API to send a text message to Amazon Titan Text
// and print the response stream.

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., Titan Text Premier.
var modelId = "amazon.titan-text-premier-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
{
    inputText = userMessage,
    textGenerationConfig = new
    {
        maxTokenCount = 512,
        temperature = 0.5
    }
});

// Create a request with the model ID and the model's native request payload.
var request = new InvokeModelWithResponseStreamRequest()
{
    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 streamingResponse = await client.InvokeModelWithResponseStreamAsync(request);

    // Extract and print the streamed response text in real-time.
    foreach (var item in streamingResponse.Body)
    {
        var chunk = JsonSerializer.Deserialize<JsonObject>((item as PayloadPart).Bytes);
        var text = chunk["outputText"] ?? "";
        Console.Write(text);
    }
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

• Pour plus de détails sur l'API, reportez-vous InvokeModelWithResponseStreamà la section Référence des AWS SDK for .NET API.

InvokeModelWithResponseStream

L'exemple de code suivant montre comment envoyer un message texte aux modèles Amazon Titan Text, à l'aide de l'API Invoke Model, et comment imprimer le flux de réponses.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Utilisez l'API Invoke Model pour envoyer un message texte et traiter le flux de réponses en temps réel.

// Use the native inference API to send a text message to Amazon Titan Text
// and print the response stream.

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., Titan Text Premier.
var modelId = "amazon.titan-text-premier-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
{
    inputText = userMessage,
    textGenerationConfig = new
    {
        maxTokenCount = 512,
        temperature = 0.5
    }
});

// Create a request with the model ID and the model's native request payload.
var request = new InvokeModelWithResponseStreamRequest()
{
    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 streamingResponse = await client.InvokeModelWithResponseStreamAsync(request);

    // Extract and print the streamed response text in real-time.
    foreach (var item in streamingResponse.Body)
    {
        var chunk = JsonSerializer.Deserialize<JsonObject>((item as PayloadPart).Bytes);
        var text = chunk["outputText"] ?? "";
        Console.Write(text);
    }
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

• Pour plus de détails sur l'API, reportez-vous InvokeModelWithResponseStreamà la section Référence des AWS SDK for .NET API.

Anthropic Claude

Converse

L'exemple de code suivant montre comment envoyer un message texte à Anthropic Claude à l'aide de l'API Converse de Bedrock.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Envoyez un SMS à Anthropic Claude à l'aide de l'API Converse de Bedrock.

// 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;
}

• Pour plus de détails sur l'API, consultez Converse dans le manuel AWS SDK for .NET API Reference.

Converse

L'exemple de code suivant montre comment envoyer un message texte à Anthropic Claude à l'aide de l'API Converse de Bedrock.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Envoyez un SMS à Anthropic Claude à l'aide de l'API Converse de Bedrock.

// 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;
}

• Pour plus de détails sur l'API, consultez Converse dans le manuel AWS SDK for .NET API Reference.

ConverseStream

L'exemple de code suivant montre comment envoyer un message texte à Anthropic Claude à l'aide de l'API Converse de Bedrock et comment traiter le flux de réponses en temps réel.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Envoyez un SMS à Anthropic Claude à l'aide de l'API Converse de Bedrock et traitez le flux de réponses en temps réel.

// 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;
}

• Pour plus de détails sur l'API, reportez-vous ConverseStreamà la section Référence des AWS SDK for .NET API.

ConverseStream

L'exemple de code suivant montre comment envoyer un message texte à Anthropic Claude à l'aide de l'API Converse de Bedrock et comment traiter le flux de réponses en temps réel.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Envoyez un SMS à Anthropic Claude à l'aide de l'API Converse de Bedrock et traitez le flux de réponses en temps réel.

// 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;
}

• Pour plus de détails sur l'API, reportez-vous ConverseStreamà la section Référence des AWS SDK for .NET API.

InvokeModel

L'exemple de code suivant montre comment envoyer un message texte à Anthropic Claude à l'aide de l'API Invoke Model.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Utilisez l'API Invoke Model pour envoyer un message texte.

// 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;
}

• Pour plus de détails sur l'API, reportez-vous InvokeModelà la section Référence des AWS SDK for .NET API.

InvokeModel

L'exemple de code suivant montre comment envoyer un message texte à Anthropic Claude à l'aide de l'API Invoke Model.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Utilisez l'API Invoke Model pour envoyer un message texte.

// 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;
}

• Pour plus de détails sur l'API, reportez-vous InvokeModelà la section Référence des AWS SDK for .NET API.

InvokeModelWithResponseStream

L'exemple de code suivant montre comment envoyer un message texte aux modèles Anthropic Claude, à l'aide de l'API Invoke Model, et comment imprimer le flux de réponses.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Utilisez l'API Invoke Model pour envoyer un message texte et traiter le flux de réponses en temps réel.

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

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, the user message, and an inference configuration.
var request = new InvokeModelWithResponseStreamRequest()
{
    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 streamingResponse = await client.InvokeModelWithResponseStreamAsync(request);

    // Extract and print the streamed response text in real-time.
    foreach (var item in streamingResponse.Body)
    {
        var chunk = JsonSerializer.Deserialize<JsonObject>((item as PayloadPart).Bytes);
        var text = chunk["delta"]?["text"] ?? "";
        Console.Write(text);
    }
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

• Pour plus de détails sur l'API, reportez-vous InvokeModelWithResponseStreamà la section Référence des AWS SDK for .NET API.

InvokeModelWithResponseStream

L'exemple de code suivant montre comment envoyer un message texte aux modèles Anthropic Claude, à l'aide de l'API Invoke Model, et comment imprimer le flux de réponses.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Utilisez l'API Invoke Model pour envoyer un message texte et traiter le flux de réponses en temps réel.

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

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, the user message, and an inference configuration.
var request = new InvokeModelWithResponseStreamRequest()
{
    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 streamingResponse = await client.InvokeModelWithResponseStreamAsync(request);

    // Extract and print the streamed response text in real-time.
    foreach (var item in streamingResponse.Body)
    {
        var chunk = JsonSerializer.Deserialize<JsonObject>((item as PayloadPart).Bytes);
        var text = chunk["delta"]?["text"] ?? "";
        Console.Write(text);
    }
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

• Pour plus de détails sur l'API, reportez-vous InvokeModelWithResponseStreamà la section Référence des AWS SDK for .NET API.

Cohere Command

Converse

L'exemple de code suivant montre comment envoyer un message texte à Cohere Command, en utilisant l'API Converse de Bedrock.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Envoyez un message texte à Cohere Command en utilisant l'API Converse de Bedrock.

// 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;
}

• Pour plus de détails sur l'API, consultez Converse dans le manuel AWS SDK for .NET API Reference.

Converse

L'exemple de code suivant montre comment envoyer un message texte à Cohere Command, en utilisant l'API Converse de Bedrock.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Envoyez un message texte à Cohere Command en utilisant l'API Converse de Bedrock.

// 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;
}

• Pour plus de détails sur l'API, consultez Converse dans le manuel AWS SDK for .NET API Reference.

ConverseStream

L'exemple de code suivant montre comment envoyer un message texte à Cohere Command à l'aide de l'API Converse de Bedrock et comment traiter le flux de réponse en temps réel.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Envoyez un message texte à Cohere Command à l'aide de l'API Converse de Bedrock et traitez le flux de réponse en temps réel.

// 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;
}

• Pour plus de détails sur l'API, reportez-vous ConverseStreamà la section Référence des AWS SDK for .NET API.

ConverseStream

L'exemple de code suivant montre comment envoyer un message texte à Cohere Command à l'aide de l'API Converse de Bedrock et comment traiter le flux de réponse en temps réel.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Envoyez un message texte à Cohere Command à l'aide de l'API Converse de Bedrock et traitez le flux de réponse en temps réel.

// 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;
}

• Pour plus de détails sur l'API, reportez-vous ConverseStreamà la section Référence des AWS SDK for .NET API.

InvokeModel: Command R et R+

L'exemple de code suivant montre comment envoyer un message texte à Cohere Command R et R+ à l'aide de l'API Invoke Model.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Utilisez l'API Invoke Model pour envoyer un message texte.

// Use the native inference API to send a text message to Cohere Command R.

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., 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.";

//Format the request payload using the model's native structure.
var nativeRequest = JsonSerializer.Serialize(new
{
    message = userMessage,
    max_tokens = 512,
    temperature = 0.5
});

// 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["text"] ?? "";
    Console.WriteLine(responseText);
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

• Pour plus de détails sur l'API, reportez-vous InvokeModelà la section Référence des AWS SDK for .NET API.

InvokeModel: Command R et R+

L'exemple de code suivant montre comment envoyer un message texte à Cohere Command R et R+ à l'aide de l'API Invoke Model.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Utilisez l'API Invoke Model pour envoyer un message texte.

// Use the native inference API to send a text message to Cohere Command R.

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., 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.";

//Format the request payload using the model's native structure.
var nativeRequest = JsonSerializer.Serialize(new
{
    message = userMessage,
    max_tokens = 512,
    temperature = 0.5
});

// 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["text"] ?? "";
    Console.WriteLine(responseText);
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

• Pour plus de détails sur l'API, reportez-vous InvokeModelà la section Référence des AWS SDK for .NET API.

InvokeModel: lampe de commande et de commande

L'exemple de code suivant montre comment envoyer un message texte à Cohere Command à l'aide de l'API Invoke Model.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Utilisez l'API Invoke Model pour envoyer un message texte.

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

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., Command Light.
var modelId = "cohere.command-light-text-v14";

// 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
{
    prompt = userMessage,
    max_tokens = 512,
    temperature = 0.5
});

// 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["generations"]?[0]?["text"] ?? "";
    Console.WriteLine(responseText);
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

• Pour plus de détails sur l'API, reportez-vous InvokeModelà la section Référence des AWS SDK for .NET API.

InvokeModel: lampe de commande et de commande

L'exemple de code suivant montre comment envoyer un message texte à Cohere Command à l'aide de l'API Invoke Model.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Utilisez l'API Invoke Model pour envoyer un message texte.

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

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., Command Light.
var modelId = "cohere.command-light-text-v14";

// 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
{
    prompt = userMessage,
    max_tokens = 512,
    temperature = 0.5
});

// 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["generations"]?[0]?["text"] ?? "";
    Console.WriteLine(responseText);
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

• Pour plus de détails sur l'API, reportez-vous InvokeModelà la section Référence des AWS SDK for .NET API.

InvokeModelWithResponseStream: Command R et R+

L'exemple de code suivant montre comment envoyer un message texte à Cohere Command, à l'aide de l'API Invoke Model avec un flux de réponses.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Utilisez l'API Invoke Model pour envoyer un message texte et traiter le flux de réponses en temps réel.

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

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., 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.";

//Format the request payload using the model's native structure.
var nativeRequest = JsonSerializer.Serialize(new
{
    message = userMessage,
    max_tokens = 512,
    temperature = 0.5
});

// Create a request with the model ID and the model's native request payload.
var request = new InvokeModelWithResponseStreamRequest()
{
    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 streamingResponse = await client.InvokeModelWithResponseStreamAsync(request);

    // Extract and print the streamed response text in real-time.
    foreach (var item in streamingResponse.Body)
    {
        var chunk = JsonSerializer.Deserialize<JsonObject>((item as PayloadPart).Bytes);
        var text = chunk["text"] ?? "";
        Console.Write(text);
    }
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

• Pour plus de détails sur l'API, reportez-vous InvokeModelà la section Référence des AWS SDK for .NET API.

InvokeModelWithResponseStream: Command R et R+

L'exemple de code suivant montre comment envoyer un message texte à Cohere Command, à l'aide de l'API Invoke Model avec un flux de réponses.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Utilisez l'API Invoke Model pour envoyer un message texte et traiter le flux de réponses en temps réel.

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

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., 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.";

//Format the request payload using the model's native structure.
var nativeRequest = JsonSerializer.Serialize(new
{
    message = userMessage,
    max_tokens = 512,
    temperature = 0.5
});

// Create a request with the model ID and the model's native request payload.
var request = new InvokeModelWithResponseStreamRequest()
{
    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 streamingResponse = await client.InvokeModelWithResponseStreamAsync(request);

    // Extract and print the streamed response text in real-time.
    foreach (var item in streamingResponse.Body)
    {
        var chunk = JsonSerializer.Deserialize<JsonObject>((item as PayloadPart).Bytes);
        var text = chunk["text"] ?? "";
        Console.Write(text);
    }
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

• Pour plus de détails sur l'API, reportez-vous InvokeModelà la section Référence des AWS SDK for .NET API.

InvokeModelWithResponseStream: lampe de commande et de commande

L'exemple de code suivant montre comment envoyer un message texte à Cohere Command, à l'aide de l'API Invoke Model avec un flux de réponses.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Utilisez l'API Invoke Model pour envoyer un message texte et traiter le flux de réponses en temps réel.

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

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., Command Light.
var modelId = "cohere.command-light-text-v14";

// 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
{
    prompt = userMessage,
    max_tokens = 512,
    temperature = 0.5
});

// Create a request with the model ID and the model's native request payload.
var request = new InvokeModelWithResponseStreamRequest()
{
    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 streamingResponse = await client.InvokeModelWithResponseStreamAsync(request);

    // Extract and print the streamed response text in real-time.
    foreach (var item in streamingResponse.Body)
    {
        var chunk = JsonSerializer.Deserialize<JsonObject>((item as PayloadPart).Bytes);
        var text = chunk["generations"]?[0]?["text"] ?? "";
        Console.Write(text);
    }
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

• Pour plus de détails sur l'API, reportez-vous InvokeModelà la section Référence des AWS SDK for .NET API.

InvokeModelWithResponseStream: lampe de commande et de commande

L'exemple de code suivant montre comment envoyer un message texte à Cohere Command, à l'aide de l'API Invoke Model avec un flux de réponses.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Utilisez l'API Invoke Model pour envoyer un message texte et traiter le flux de réponses en temps réel.

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

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., Command Light.
var modelId = "cohere.command-light-text-v14";

// 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
{
    prompt = userMessage,
    max_tokens = 512,
    temperature = 0.5
});

// Create a request with the model ID and the model's native request payload.
var request = new InvokeModelWithResponseStreamRequest()
{
    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 streamingResponse = await client.InvokeModelWithResponseStreamAsync(request);

    // Extract and print the streamed response text in real-time.
    foreach (var item in streamingResponse.Body)
    {
        var chunk = JsonSerializer.Deserialize<JsonObject>((item as PayloadPart).Bytes);
        var text = chunk["generations"]?[0]?["text"] ?? "";
        Console.Write(text);
    }
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

• Pour plus de détails sur l'API, reportez-vous InvokeModelà la section Référence des AWS SDK for .NET API.

Méta lama

Converse

L'exemple de code suivant montre comment envoyer un message texte à Meta Llama à l'aide de l'API Converse de Bedrock.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Envoyez un SMS à Meta Llama à l'aide de l'API Converse de Bedrock.

// 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;
}

• Pour plus de détails sur l'API, consultez Converse dans le manuel AWS SDK for .NET API Reference.

Converse

L'exemple de code suivant montre comment envoyer un message texte à Meta Llama à l'aide de l'API Converse de Bedrock.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Envoyez un SMS à Meta Llama à l'aide de l'API Converse de Bedrock.

// 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;
}

• Pour plus de détails sur l'API, consultez Converse dans le manuel AWS SDK for .NET API Reference.

ConverseStream

L'exemple de code suivant montre comment envoyer un message texte à Meta Llama à l'aide de l'API Converse de Bedrock et comment traiter le flux de réponses en temps réel.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Envoyez un message texte à Meta Llama à l'aide de l'API Converse de Bedrock et traitez le flux de réponses en temps réel.

// 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;
}

• Pour plus de détails sur l'API, reportez-vous ConverseStreamà la section Référence des AWS SDK for .NET API.

ConverseStream

L'exemple de code suivant montre comment envoyer un message texte à Meta Llama à l'aide de l'API Converse de Bedrock et comment traiter le flux de réponses en temps réel.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Envoyez un message texte à Meta Llama à l'aide de l'API Converse de Bedrock et traitez le flux de réponses en temps réel.

// 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;
}

• Pour plus de détails sur l'API, reportez-vous ConverseStreamà la section Référence des AWS SDK for .NET API.

InvokeModel: Lama 3

L'exemple de code suivant montre comment envoyer un message texte à Meta Llama 3 à l'aide de l'API Invoke Model.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Utilisez l'API Invoke Model pour envoyer un message texte.

// Use the native inference API to send a text message to Meta Llama 3.

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.USWest2);

// Set the model ID, e.g., Llama 3 70b Instruct.
var modelId = "meta.llama3-70b-instruct-v1:0";

// Define the prompt for the model.
var prompt = "Describe the purpose of a 'hello world' program in one line.";

// Embed the prompt in Llama 2's instruction format.
var formattedPrompt = $@"
<|begin_of_text|><|start_header_id|>user<|end_header_id|>
{prompt}
<|eot_id|>
<|start_header_id|>assistant<|end_header_id|>
";

//Format the request payload using the model's native structure.
var nativeRequest = JsonSerializer.Serialize(new
{
    prompt = formattedPrompt,
    max_gen_len = 512,
    temperature = 0.5
});

// 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["generation"] ?? "";
    Console.WriteLine(responseText);
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

• Pour plus de détails sur l'API, reportez-vous InvokeModelà la section Référence des AWS SDK for .NET API.

InvokeModel: Lama 3

L'exemple de code suivant montre comment envoyer un message texte à Meta Llama 3 à l'aide de l'API Invoke Model.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Utilisez l'API Invoke Model pour envoyer un message texte.

// Use the native inference API to send a text message to Meta Llama 3.

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.USWest2);

// Set the model ID, e.g., Llama 3 70b Instruct.
var modelId = "meta.llama3-70b-instruct-v1:0";

// Define the prompt for the model.
var prompt = "Describe the purpose of a 'hello world' program in one line.";

// Embed the prompt in Llama 2's instruction format.
var formattedPrompt = $@"
<|begin_of_text|><|start_header_id|>user<|end_header_id|>
{prompt}
<|eot_id|>
<|start_header_id|>assistant<|end_header_id|>
";

//Format the request payload using the model's native structure.
var nativeRequest = JsonSerializer.Serialize(new
{
    prompt = formattedPrompt,
    max_gen_len = 512,
    temperature = 0.5
});

// 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["generation"] ?? "";
    Console.WriteLine(responseText);
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

• Pour plus de détails sur l'API, reportez-vous InvokeModelà la section Référence des AWS SDK for .NET API.

InvokeModelWithResponseStream: Lama 3

L'exemple de code suivant montre comment envoyer un message texte à Meta Llama 3, à l'aide de l'API Invoke Model, et comment imprimer le flux de réponse.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Utilisez l'API Invoke Model pour envoyer un message texte et traiter le flux de réponses en temps réel.

// Use the native inference API to send a text message to Meta Llama 3
// and print the response stream.

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.USWest2);

// Set the model ID, e.g., Llama 3 70b Instruct.
var modelId = "meta.llama3-70b-instruct-v1:0";

// Define the prompt for the model.
var prompt = "Describe the purpose of a 'hello world' program in one line.";

// Embed the prompt in Llama 2's instruction format.
var formattedPrompt = $@"
<|begin_of_text|><|start_header_id|>user<|end_header_id|>
{prompt}
<|eot_id|>
<|start_header_id|>assistant<|end_header_id|>
";

//Format the request payload using the model's native structure.
var nativeRequest = JsonSerializer.Serialize(new
{
    prompt = formattedPrompt,
    max_gen_len = 512,
    temperature = 0.5
});

// Create a request with the model ID and the model's native request payload.
var request = new InvokeModelWithResponseStreamRequest()
{
    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 streamingResponse = await client.InvokeModelWithResponseStreamAsync(request);

    // Extract and print the streamed response text in real-time.
    foreach (var item in streamingResponse.Body)
    {
        var chunk = JsonSerializer.Deserialize<JsonObject>((item as PayloadPart).Bytes);
        var text = chunk["generation"] ?? "";
        Console.Write(text);
    }
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

• Pour plus de détails sur l'API, reportez-vous InvokeModelWithResponseStreamà la section Référence des AWS SDK for .NET API.

InvokeModelWithResponseStream: Lama 3

L'exemple de code suivant montre comment envoyer un message texte à Meta Llama 3, à l'aide de l'API Invoke Model, et comment imprimer le flux de réponse.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Utilisez l'API Invoke Model pour envoyer un message texte et traiter le flux de réponses en temps réel.

// Use the native inference API to send a text message to Meta Llama 3
// and print the response stream.

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.USWest2);

// Set the model ID, e.g., Llama 3 70b Instruct.
var modelId = "meta.llama3-70b-instruct-v1:0";

// Define the prompt for the model.
var prompt = "Describe the purpose of a 'hello world' program in one line.";

// Embed the prompt in Llama 2's instruction format.
var formattedPrompt = $@"
<|begin_of_text|><|start_header_id|>user<|end_header_id|>
{prompt}
<|eot_id|>
<|start_header_id|>assistant<|end_header_id|>
";

//Format the request payload using the model's native structure.
var nativeRequest = JsonSerializer.Serialize(new
{
    prompt = formattedPrompt,
    max_gen_len = 512,
    temperature = 0.5
});

// Create a request with the model ID and the model's native request payload.
var request = new InvokeModelWithResponseStreamRequest()
{
    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 streamingResponse = await client.InvokeModelWithResponseStreamAsync(request);

    // Extract and print the streamed response text in real-time.
    foreach (var item in streamingResponse.Body)
    {
        var chunk = JsonSerializer.Deserialize<JsonObject>((item as PayloadPart).Bytes);
        var text = chunk["generation"] ?? "";
        Console.Write(text);
    }
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

• Pour plus de détails sur l'API, reportez-vous InvokeModelWithResponseStreamà la section Référence des AWS SDK for .NET API.

IA Mistral

Converse

L'exemple de code suivant montre comment envoyer un message texte à Mistral à l'aide de l'API Converse de Bedrock.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Envoyez un SMS à Mistral en utilisant l'API Converse de Bedrock.

// 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;
}

• Pour plus de détails sur l'API, consultez Converse dans le manuel AWS SDK for .NET API Reference.

Converse

L'exemple de code suivant montre comment envoyer un message texte à Mistral à l'aide de l'API Converse de Bedrock.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Envoyez un SMS à Mistral en utilisant l'API Converse de Bedrock.

// 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;
}

• Pour plus de détails sur l'API, consultez Converse dans le manuel AWS SDK for .NET API Reference.

ConverseStream

L'exemple de code suivant montre comment envoyer un message texte à Mistral à l'aide de l'API Converse de Bedrock et comment traiter le flux de réponses en temps réel.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Envoyez un SMS à Mistral à l'aide de l'API Converse de Bedrock et traitez le flux de réponses en temps réel.

// 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;
}

• Pour plus de détails sur l'API, reportez-vous ConverseStreamà la section Référence des AWS SDK for .NET API.

ConverseStream

L'exemple de code suivant montre comment envoyer un message texte à Mistral à l'aide de l'API Converse de Bedrock et comment traiter le flux de réponses en temps réel.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Envoyez un SMS à Mistral à l'aide de l'API Converse de Bedrock et traitez le flux de réponses en temps réel.

// 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;
}

• Pour plus de détails sur l'API, reportez-vous ConverseStreamà la section Référence des AWS SDK for .NET API.

InvokeModel

L'exemple de code suivant montre comment envoyer un message texte aux modèles Mistral à l'aide de l'API Invoke Model.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Utilisez l'API Invoke Model pour envoyer un message texte.

// Use the native inference API to send a text message to Mistral.

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., Mistral Large.
var modelId = "mistral.mistral-large-2402-v1:0";

// Define the prompt for the model.
var prompt = "Describe the purpose of a 'hello world' program in one line.";

// Embed the prompt in Mistral's instruction format.
var formattedPrompt = $"<s>[INST] {prompt} [/INST]";

//Format the request payload using the model's native structure.
var nativeRequest = JsonSerializer.Serialize(new
{
    prompt = formattedPrompt,
    max_tokens = 512,
    temperature = 0.5
});

// 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["outputs"]?[0]?["text"] ?? "";
    Console.WriteLine(responseText);
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

• Pour plus de détails sur l'API, reportez-vous InvokeModelà la section Référence des AWS SDK for .NET API.

InvokeModel

L'exemple de code suivant montre comment envoyer un message texte aux modèles Mistral à l'aide de l'API Invoke Model.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Utilisez l'API Invoke Model pour envoyer un message texte.

// Use the native inference API to send a text message to Mistral.

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., Mistral Large.
var modelId = "mistral.mistral-large-2402-v1:0";

// Define the prompt for the model.
var prompt = "Describe the purpose of a 'hello world' program in one line.";

// Embed the prompt in Mistral's instruction format.
var formattedPrompt = $"<s>[INST] {prompt} [/INST]";

//Format the request payload using the model's native structure.
var nativeRequest = JsonSerializer.Serialize(new
{
    prompt = formattedPrompt,
    max_tokens = 512,
    temperature = 0.5
});

// 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["outputs"]?[0]?["text"] ?? "";
    Console.WriteLine(responseText);
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

• Pour plus de détails sur l'API, reportez-vous InvokeModelà la section Référence des AWS SDK for .NET API.

InvokeModelWithResponseStream

L'exemple de code suivant montre comment envoyer un message texte aux modèles Mistral AI, à l'aide de l'API Invoke Model, et comment imprimer le flux de réponses.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Utilisez l'API Invoke Model pour envoyer un message texte et traiter le flux de réponses en temps réel.

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

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., Mistral Large.
var modelId = "mistral.mistral-large-2402-v1:0";

// Define the prompt for the model.
var prompt = "Describe the purpose of a 'hello world' program in one line.";

// Embed the prompt in Mistral's instruction format.
var formattedPrompt = $"<s>[INST] {prompt} [/INST]";

//Format the request payload using the model's native structure.
var nativeRequest = JsonSerializer.Serialize(new
{
    prompt = formattedPrompt,
    max_tokens = 512,
    temperature = 0.5
});

// Create a request with the model ID and the model's native request payload.
var request = new InvokeModelWithResponseStreamRequest()
{
    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 streamingResponse = await client.InvokeModelWithResponseStreamAsync(request);

    // Extract and print the streamed response text in real-time.
    foreach (var item in streamingResponse.Body)
    {
        var chunk = JsonSerializer.Deserialize<JsonObject>((item as PayloadPart).Bytes);
        var text = chunk["outputs"]?[0]?["text"] ?? "";
        Console.Write(text);
    }
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

• Pour plus de détails sur l'API, reportez-vous InvokeModelWithResponseStreamà la section Référence des AWS SDK for .NET API.

InvokeModelWithResponseStream

L'exemple de code suivant montre comment envoyer un message texte aux modèles Mistral AI, à l'aide de l'API Invoke Model, et comment imprimer le flux de réponses.

SDK for .NET

Note

Il y en a plus à ce sujet GitHub. Trouvez l’exemple complet et découvrez comment le configurer et l’exécuter dans le référentiel d’exemples de code AWS.

Utilisez l'API Invoke Model pour envoyer un message texte et traiter le flux de réponses en temps réel.

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

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., Mistral Large.
var modelId = "mistral.mistral-large-2402-v1:0";

// Define the prompt for the model.
var prompt = "Describe the purpose of a 'hello world' program in one line.";

// Embed the prompt in Mistral's instruction format.
var formattedPrompt = $"<s>[INST] {prompt} [/INST]";

//Format the request payload using the model's native structure.
var nativeRequest = JsonSerializer.Serialize(new
{
    prompt = formattedPrompt,
    max_tokens = 512,
    temperature = 0.5
});

// Create a request with the model ID and the model's native request payload.
var request = new InvokeModelWithResponseStreamRequest()
{
    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 streamingResponse = await client.InvokeModelWithResponseStreamAsync(request);

    // Extract and print the streamed response text in real-time.
    foreach (var item in streamingResponse.Body)
    {
        var chunk = JsonSerializer.Deserialize<JsonObject>((item as PayloadPart).Bytes);
        var text = chunk["outputs"]?[0]?["text"] ?? "";
        Console.Write(text);
    }
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

• Pour plus de détails sur l'API, reportez-vous InvokeModelWithResponseStreamà la section Référence des AWS SDK for .NET API.