AzureAICommunity.Agent.Middleware.LanguageTranslationMiddleware 1.0.0

<div align="center">

🌐 AzureAICommunity – Language Translation Middleware (.NET)

Automatic language detection, translation, and response back-translation middleware for AI agent applications built on Microsoft.Extensions.AI.

**Your agent always

</div>

Overview

AzureAICommunity.Agent.Middleware.LanguageTranslationMiddleware is a plug-and-play translation layer for Microsoft.Extensions.AI chat pipelines. It automatically detects the user's language, translates incoming messages to the agent's target language, and back-translates the response — using Azure AI Translator with an optional LLM agent as fallback.

✨ Features

📦 Installation

dotnet add package AzureAICommunity.Agent.Middleware.LanguageTranslationMiddleware

🚀 Quick Start

using AzureAICommunity.Agent.Middleware.LanguageTranslationMiddleware;
using Microsoft.Extensions.AI;
using OllamaSharp;

IChatClient ollamaClient = new OllamaApiClient(new Uri("http://localhost:11434/"), "llama3.2");

// LLM-only translation (no Azure credentials required)
var client = ollamaClient
    .AsBuilder()
    .Use(inner => LanguageTranslationMiddleware
        .CreateBuilder()
        .WithTargetLanguage("en")
        .WithLLMFallback(ollamaClient)
        .Build(inner))
    .Build();

var messages = new[] { new ChatMessage(ChatRole.User, "Wie heißt die Hauptstadt von Frankreich?") };
var response = await client.GetResponseAsync(messages);
Console.WriteLine(response.Messages[0].Text); // Reply back-translated to German

⚙️ Configuration

🧑‍💻 Usage

Option 1 — Azure Translator + LLM Fallback (Recommended)

var azureConfig = new AzureTranslatorConfig(
    Key:    Environment.GetEnvironmentVariable("AZURE_TRANSLATOR_KEY")!,
    Region: Environment.GetEnvironmentVariable("AZURE_TRANSLATOR_REGION")!
);

var client = ollamaClient
    .AsBuilder()
    .Use(inner => LanguageTranslationMiddleware
        .CreateBuilder()
        .WithAzureTranslator(azureConfig)
        .WithLLMFallback(ollamaClient)
        .WithTargetLanguage("en")
        .WithMinConfidence(0.8f)
        .Build(inner))
    .Build();

Option 2 — LLM Only

var client = ollamaClient
    .AsBuilder()
    .Use(inner => LanguageTranslationMiddleware
        .CreateBuilder()
        .WithLLMFallback(ollamaClient)
        .WithTargetLanguage("en")
        .Build(inner))
    .Build();

Option 3 — Direct Construction

var azureService  = new AzureTranslationService(azureConfig);
var llmService    = new LLMTranslationService(ollamaClient);

var middleware = new LanguageTranslationMiddleware(
    inner:           ollamaClient,
    primaryService:  azureService,
    targetLanguage:  "en",
    minConfidence:   0.8f,
    fallbackService: llmService);

🔄 How It Works

User Message (any language)
        │
        ▼
┌─────────────────────────────────┐
│   LanguageTranslationMiddleware │
│  1. Detect language             │
│  2. Translate → target lang     │
└──────────────┬──────────────────┘
               │
               ▼
       Inner IChatClient
       (reasons in target lang)
               │
               ▼
┌─────────────────────────────────┐
│   LanguageTranslationMiddleware │
│  3. Back-translate response     │
│     → user's original language  │
└─────────────────────────────────┘
               │
               ▼
  Response (user's language)

🤝 Contributing

Contributions are welcome! Please open an issue to discuss what you'd like to change before submitting a pull request.

📁 Repository: https://github.com/rvinothrajendran/AgentFramework

1. Fork the repository
2. Create a feature branch (git checkout -b feature/my-feature)
3. Commit your changes (git commit -m 'Add my feature')
4. Push to the branch (git push origin feature/my-feature)
5. Open a Pull Request

👤 Author

Built and maintained by Vinoth Rajendran.

• 🐙 GitHub: github.com/rvinothrajendran — follow for more projects!
• 📺 YouTube: youtube.com/@VinothRajendran — subscribe for tutorials and demos!
• 💼 LinkedIn: linkedin.com/in/rvinothrajendran — let's connect!

📄 License

MIT © 2026 Vinoth Rajendran – AzureAICommunity