Skip to main content
BuyLog In
ASP.NET Core Controls
Search in…
Docs > AI-powered Extensions
All docs
V25.1
    • ASP.NET Core Controls
    Prerequisites and Installation
    Supported Browsers
    Demos and Sample Apps
    DevExtreme-Based Controls
    Reporting
    Query Builder
    Rich Text Editor
    Spreadsheet
    Web Dashboard
    AI-powered Extensions
    Security Considerations
    Troubleshooting
    Redistribution and Deployment
    API Reference
    Client API Reference
    Migration from WebForms & MVC5
    Download CHM

    DevExpress AI-powered Extensions for ASP.NET Core

    • 7 minutes to read

    The links below provide instructions on how to add AI-powered functionality to DevExpress ASP.NET Core components.

    Reporting & BI Dashboard

    The DevExpress.AIIntegration.AspNetCore.Reporting NuGet package contains classes and methods required for AI-powered Extensions for ASP.NET Core Reporting Controls. Call the AddWebReportingAIIntegration method to configure AI-powered Extensions in your application.

    Examples

    The following examples integrate an AI Assistant (based on dxChat) into ASP.NET Core Dashboard and Reporting controls:

    View Example: Reporting for ASP.NET Core — Integrate Azure OpenAI-based AI Assistant View Example: BI Dashboard for ASP.NET Core — Integrate Azure OpenAI-based AI Assistant

    Demos

    Review the following Reporting AI Extensions demos:

    Run Demo: Report Viewer AI Extensions Run Demo: Report Designer AI Extensions

    How it Works

    DevExpress AI APIs leverage the Microsoft.Extensions.AI libraries for integration and interoperability with a wide range of AI services. These libraries establish a unified C# abstraction layer for standardized interaction with language models.

    This architecture decouples your application code from specific AI SDKs. You can seamlessly switch the underlying AI model or provider with minimal code modifications. For example, you can build a prototype with a locally deployed AI model and then quickly transition to an enterprise-grade online LLM provider. These changes only involve adjustments to the app’s startup logic and the installation of necessary NuGet packages.

    The IChatClient interface serves as the central mechanism for language models interaction. Currently, supported AI providers include:

    The Microsoft.Extensions.AI framework allows developers to integrate support for AI language models and services without modifying the core library. This means you can leverage third-party libraries for new AI providers or create your own custom implementation for in-house language models.

    Note

    DevExpress does not provide a REST API or include built-in LLMs/SLMs. To use AI services, you need an active Azure/OpenAI subscription to obtain the necessary REST API endpoint and key. This information must be provided at application startup to register AI clients and enable DevExpress AI-powered Extensions.

    Prerequisites

    AI Services Integration

    Follow the instructions below to register an AI model and enable DevExpress AI Services in your application.

    OpenAI

    1. Install the following NuGet packages to your project:

    2. Register the OpenAI model in the project’s entry point class:

      using Azure.AI.OpenAI;
using Microsoft.Extensions.AI;
using OpenAI;
// ...
string openAiApiKey = Environment.GetEnvironmentVariable("OPENAI_API_KEY")
    ?? throw new InvalidOperationException("OPENAI_API_KEY environment variable is not set.");
string openAiModel = "OPENAI_MODEL";
OpenAIClient openAIClient = new OpenAIClient(openAiApiKey);
IChatClient openAiChatClient = openAIClient.GetChatClient(openAiModel).AsIChatClient();
builder.Services.AddChatClient(openAiChatClient);

      • Create an environment variable named OPENAI_API_KEY and set its value to your OpenAI API key. If your application throws an exception that the variable is not found, restart your IDE or terminal to ensure they load the new variable.

        Important

        Never hardcode OpenAI API key in your source code. This is a critical security risk that can lead to unauthorized access and misuse of your account. Follow Microsoft’s guidance on safe secret management in ASP.NET Core apps.

      • Set the openAiModel variable to the OpenAI model ID.

    3. Register DevExpress AI Service in the project’s entry point class:

      builder.Services.AddDevExpressAI();

    Azure OpenAI

    1. Install the following NuGet packages to your project:

    2. Register the Azure OpenAI model in the project’s entry point class:

      using Azure.AI.OpenAI;
using Microsoft.Extensions.AI;
using System.ClientModel;
// ...
string azureOpenAiKey = Environment.GetEnvironmentVariable("AZURE_OPENAI_KEY")
    ?? throw new InvalidOperationException("AZURE_OPENAI_KEY environment variable is not set.");
string azureOpenAiEndpoint = "AZURE_OPENAI_ENDPOINT";
string azureOpenAiModel = "AZURE_OPENAI_MODEL";
AzureOpenAIClient azureOpenAIClient = new AzureOpenAIClient(
     new Uri(azureOpenAiEndpoint),
     new ApiKeyCredential(azureOpenAiKey)
);
IChatClient azureOpenAiChatClient = azureOpenAIClient.GetChatClient(azureOpenAiModel).AsIChatClient();
builder.Services.AddChatClient(azureOpenAiChatClient);

      • Create an environment variable named AZURE_OPENAI_KEY and set its value to your Azure OpenAI key. If your application throws an exception that the variable is not found, restart your IDE or terminal to ensure they load the new variable.

        Important

        Never hardcode Azure OpenAI key in your source code. This is a critical security risk that can lead to unauthorized access and misuse of your account. Follow Microsoft’s guidance on safe secret management in ASP.NET Core apps.

      • Set the azureOpenAiEndpoint variable to your Azure OpenAI endpoint.

      • Set the azureOpenAiModel variable to the Azure OpenAI model ID.

    3. Register DevExpress AI Service in the project’s entry point class:

      builder.Services.AddDevExpressAI();

    Ollama

    1. Install the following NuGet packages to your project:

    2. Register the self-hosted AI model in the project’s entry point class:

      using Microsoft.Extensions.AI;
using OllamaSharp;
// ...
string aiModel = "MODEL_NAME";
IChatClient chatClient = new OllamaApiClient("http://localhost:11434", aiModel);
builder.Services.AddChatClient(chatClient);

      Set the aiModel variable to the name of your Ollama model.

    3. Register DevExpress AI Service in the project’s entry point class:

      builder.Services.AddDevExpressAI();

    Semantic Kernel

    The Semantic Kernel SDK provides a common interface to interact with different AI services. The Kernel communicates with AI services through AI Connectors, which expose multiple AI service types from different providers.

    Semantic Kernel works with an ecosystem of ready-to-use connectors which support leading AI models from OpenAI, Google, Anthropic, DeepSeek, Mistral AI, Hugging Face, and more. You can also build custom connectors for any other service, such as your in-house language models.

    The following example connects DevExpress AI Service to Google Gemini through the Semantic Kernel SDK:

    Note

    The Google chat completion connector is currently experimental. To acknowledge this and use the feature, you must explicitly suppress the compiler warnings with the #pragma warning disable directive.

    1. Sign in to Google AI Studio.
    2. Create an API key.

    3. Install the following NuGet packages to your project:

    4. Register the Gemini model in the project’s entry point class:

      using Microsoft.Extensions.AI;
using Microsoft.SemanticKernel;
using Microsoft.SemanticKernel.ChatCompletion;
// ...
string geminiApiKey = Environment.GetEnvironmentVariable("GEMINI_API_KEY")
    ?? throw new InvalidOperationException("GEMINI_API_KEY environment variable is not set.");
string geminiAiModel = "GEMINI_MODEL";
#pragma warning disable SKEXP0070
var kernelBuilder = Kernel
    .CreateBuilder()
    .AddGoogleAIGeminiChatCompletion(geminiAiModel, geminiApiKey);
Kernel kernel = kernelBuilder.Build();
#pragma warning disable SKEXP0001
IChatClient geminiChatClient = kernel.GetRequiredService<IChatCompletionService>().AsChatClient();
builder.Services.AddChatClient(geminiChatClient);

      • Create an environment variable named GEMINI_API_KEY and set its value to your Gemini API key. If your application throws an exception that the variable is not found, restart your IDE or terminal to ensure they load the new variable.

        Important

        Never hardcode API keys in your source code. This is a critical security risk that can lead to unauthorized access and misuse of your subscriptions. Follow Microsoft’s guidance on safe secret management in ASP.NET Core apps.

      • Set the geminiAiModel variable to the Gemini model ID.

    5. Register DevExpress AI Service in the project’s entry point class:

      builder.Services.AddDevExpressAI();

    Configure Inference Parameters

    To control the AI model’s behavior and creativity, set inference parameters using IChatClient options. These parameters are configured once when you register the IChatClient service in the project’s entry point class. The settings then apply to all DevExpress AI-powered features, ensuring a consistent tone and style across your app.

    The following code snippet configures an Azure OpenAI client that is moderately creative, avoids repeating itself, and produces reasonably detailed but not excessively long responses:

    AzureOpenAIClient azureOpenAIClient = new AzureOpenAIClient(
        new Uri(azureOpenAiEndpoint),
        new ApiKeyCredential(azureOpenAiKey)
);
IChatClient azureOpenAIChatClient = azureOpenAIClient.GetChatClient(azureOpenAiModel).AsIChatClient();
IChatClient chatClient = new ChatClientBuilder(azureOpenAIChatClient)
    .ConfigureOptions(options => {
        options.Temperature = 0.7f;
        options.MaxOutputTokens = 1200;
        options.PresencePenalty = 0.5f;
    })
    .Build();
builder.Services.AddChatClient(chatClient);

    Note

    A specific IChatClient implementation might have its own internal representation of options. It may use a subset of options or ignore the provided options entirely.