Connect to GitHub Models

This page describes how consuming apps connect to a GitHub Model resource that’s already modeled in your AppHost. For the AppHost API surface — adding a model resource, API key parameters, organization configuration, and health checks — see GitHub Models hosting integration.

When you reference a GitHub Model resource from your AppHost, Aspire injects the connection information into the consuming app as environment variables. Your app can either read those environment variables directly — the pattern works the same from any language — or, in C#, use the Aspire client integrations for automatic dependency injection, health checks, and telemetry.

Connection properties

Aspire exposes each property as an environment variable named [RESOURCE]_[PROPERTY]. For instance, the Endpoint property of a resource called chat becomes CHAT_ENDPOINT.

GitHub Model resource

The GitHub Model resource exposes the following connection properties:

Property Name	Description
Endpoint	The GitHub Models inference endpoint URI, for example https://models.github.ai/inference
Key	The API key (GitHub PAT or GITHUB_TOKEN) for authentication
Model	The model identifier for inference requests, for instance openai/gpt-4o-mini

Example connection string:

Endpoint=https://models.github.ai/inference;Key=github_pat_abc123...;Model=openai/gpt-4o-mini

When an organization is configured, the endpoint includes the organization slug:

Endpoint=https://models.github.ai/orgs/my-org/inference;Key=github_pat_abc123...;Model=openai/gpt-4o-mini

Connect from your app

Pick the language your consuming app is written in. Each example assumes your AppHost adds a GitHub Model resource named chat and references it from the consuming app.

C#

For C# apps, the recommended approach is one of the Aspire client integrations. GitHub Models is OpenAI-compatible, so you can use either Aspire.Azure.AI.Inference (for the Azure AI Inference SDK) or Aspire.OpenAI (for the OpenAI SDK). Both integrations register the client through dependency injection and, optionally, register an IChatClient from Microsoft.Extensions.AI. If you’d rather read environment variables directly, see the Read environment variables section at the end of this tab.

Using Azure AI Inference

Install the client integration

Install the 📦 Aspire.Azure.AI.Inference NuGet package in the client-consuming project:

.NET CLI

.NET CLI — Add Aspire.Azure.AI.Inference package

dotnet add package Aspire.Azure.AI.Inference

Program.cs (C# file-based app)

Program.cs

#:package Aspire.Azure.AI.Inference@*

PackageReference (*.csproj)

XML — Add Aspire.Azure.AI.Inference package reference

<PackageReference Include="Aspire.Azure.AI.Inference" Version="*" />

Add a ChatCompletionsClient

In Program.cs, call AddAzureChatCompletionsClient on your IHostApplicationBuilder to register a ChatCompletionsClient:

C# — Program.cs

builder.AddAzureChatCompletionsClient(connectionName: "chat");

संकेत

The connectionName must match the GitHub Model resource name from the AppHost. For more information, see Add a GitHub Model resource.

Resolve the client through dependency injection:

C# — ExampleService.cs

public class ExampleService(ChatCompletionsClient client)
{
    // Use client...
}

Add a ChatCompletionsClient with IChatClient

Call AddChatClient after AddAzureChatCompletionsClient to also register an IChatClient from Microsoft.Extensions.AI:

C# — Program.cs

builder.AddAzureChatCompletionsClient("chat")
       .AddChatClient();

Resolve the IChatClient through dependency injection:

C# — ExampleService.cs

public class ExampleService(IChatClient chatClient)
{
    public async Task<string> GenerateAsync(string prompt)
    {
        var response = await chatClient.GetResponseAsync(prompt);
        return response.Text;
    }
}

Using OpenAI client

For models compatible with the OpenAI API (such as openai/gpt-4o-mini), you can use the OpenAI client.

Install the client integration

Install the 📦 Aspire.OpenAI NuGet package in the client-consuming project:

.NET CLI

.NET CLI — Add Aspire.OpenAI package

dotnet add package Aspire.OpenAI

Program.cs (C# file-based app)

Program.cs

#:package Aspire.OpenAI@*

PackageReference (*.csproj)

XML — Add Aspire.OpenAI package reference

<PackageReference Include="Aspire.OpenAI" Version="*" />

Add an OpenAI client

In Program.cs, call AddOpenAIClient to register an OpenAIClient:

C# — Program.cs

builder.AddOpenAIClient(connectionName: "chat");

Resolve the client through dependency injection and use the model name from the connection string:

C# — ExampleService.cs

public class ChatService(OpenAIClient client, IConfiguration config)
{
    public async Task<string> GetResponseAsync(string prompt)
    {
        var modelName = config["ConnectionStrings:chat:Model"] ?? "openai/gpt-4o-mini";
        var chatClient = client.GetChatClient(modelName);
        var response = await chatClient.CompleteChatAsync(
            [new UserChatMessage(prompt)]);
        return response.Value.Content[0].Text;
    }
}

Add an OpenAI client with IChatClient

C# — Program.cs

builder.AddOpenAIClient("chat")
       .AddChatClient();

Configuration

The Aspire OpenAI client integration supports configuration through connection strings, Microsoft.Extensions.Configuration, and inline delegates.

Connection strings. Provide a named connection string in appsettings.json:

JSON — appsettings.json

{
  "ConnectionStrings": {
    "chat": "Endpoint=https://models.github.ai/inference;Key=${GITHUB_TOKEN};Model=openai/gpt-4o-mini"
  }
}

Configuration providers. Use the Aspire:OpenAI key to load OpenAISettings:

JSON — appsettings.json

{
  "Aspire": {
    "OpenAI": {
      "DisableTracing": false,
      "DisableMetrics": false
    }
  }
}

Inline delegates.

C# — Program.cs

builder.AddOpenAIClient("chat", settings => settings.DisableTracing = true);

Observability and telemetry

The Aspire OpenAI client integration automatically configures logging, tracing, and metrics through OpenTelemetry.

टिप्पणी

Telemetry (traces and metrics) is experimental in the OpenAI .NET SDK. Enable it globally via the OpenAI.Experimental.EnableOpenTelemetry AppContext switch or the OPENAI_EXPERIMENTAL_ENABLE_OPEN_TELEMETRY=true environment variable.

Read environment variables in C#

If you prefer not to use the Aspire client integration, you can read the Aspire-injected connection properties directly:

C# — Program.cs

using Azure;
using Azure.AI.Inference;

var endpoint = Environment.GetEnvironmentVariable("CHAT_ENDPOINT");
var apiKey = Environment.GetEnvironmentVariable("CHAT_KEY");
var modelName = Environment.GetEnvironmentVariable("CHAT_MODEL");

var client = new ChatCompletionsClient(
    new Uri(endpoint!),
    new AzureKeyCredential(apiKey!));

var response = await client.CompleteAsync(new ChatCompletionsOptions
{
    Model = modelName,
    Messages = { new ChatRequestUserMessage("Hello!") },
});

Console.WriteLine(response.Value.Choices[0].Message.Content);

Go

GitHub Models exposes an OpenAI-compatible API, so you can use go-openai with a custom base URL:

Terminal

go get github.com/sashabaranov/go-openai

Read the injected environment variables and connect:

Go — main.go

package main

import (
    "context"
    "fmt"
    "os"

    openai "github.com/sashabaranov/go-openai"
)

func main() {
    // Read the Aspire-injected connection properties
    apiKey := os.Getenv("CHAT_KEY")
    endpoint := os.Getenv("CHAT_ENDPOINT")
    modelName := os.Getenv("CHAT_MODEL")

    config := openai.DefaultConfig(apiKey)
    config.BaseURL = endpoint

    client := openai.NewClientWithConfig(config)

    resp, err := client.CreateChatCompletion(
        context.Background(),
        openai.ChatCompletionRequest{
            Model: modelName,
            Messages: []openai.ChatCompletionMessage{
                {Role: openai.ChatMessageRoleUser, Content: "Hello!"},
            },
        },
    )
    if err != nil {
        panic(err)
    }

    fmt.Println(resp.Choices[0].Message.Content)
}

Python

GitHub Models exposes an OpenAI-compatible API. Install either the openai package or azure-ai-inference:

Using the openai package:

Terminal

pip install openai

Python — app.py

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["CHAT_KEY"],
    base_url=os.environ["CHAT_ENDPOINT"],
)

model_name = os.environ["CHAT_MODEL"]

response = client.chat.completions.create(
    model=model_name,
    messages=[{"role": "user", "content": "Hello!"}],
)

print(response.choices[0].message.content)

Using azure-ai-inference:

Terminal

pip install azure-ai-inference

Python — app.py

import os
from azure.ai.inference import ChatCompletionsClient
from azure.ai.inference.models import SystemMessage, UserMessage
from azure.core.credentials import AzureKeyCredential

client = ChatCompletionsClient(
    endpoint=os.environ["CHAT_ENDPOINT"],
    credential=AzureKeyCredential(os.environ["CHAT_KEY"]),
)

model_name = os.environ["CHAT_MODEL"]

response = client.complete(
    messages=[UserMessage(content="Hello!")],
    model=model_name,
)

print(response.choices[0].message.content)

TypeScript

GitHub Models exposes an OpenAI-compatible API. Use the openai npm package with a custom base URL:

Terminal

npm install openai

TypeScript — index.ts

import OpenAI from 'openai';

const client = new OpenAI({
    apiKey: process.env.CHAT_KEY,
    baseURL: process.env.CHAT_ENDPOINT,
});

const modelName = process.env.CHAT_MODEL ?? 'openai/gpt-4o-mini';

const response = await client.chat.completions.create({
    model: modelName,
    messages: [{ role: 'user', content: 'Hello!' }],
});

console.log(response.choices[0].message.content);

See also

• Get started with the GitHub Models integrations
• GitHub Models hosting integration
• GitHub Models Marketplace
• GitHub Models documentation