Added embedding API to C#, JS, Python and Rust SDKs

.gitignore

@@ -5,6 +5,7 @@ test.ipynb
 bin/
 obj/
 .vs/
+.vscode/
 
 # build, distribute, and bins
 build/

samples/README.md

@@ -1,14 +1,14 @@
 # Foundry Local Samples
 
-Explore complete working examples that demonstrate how to use Foundry Local — an end-to-end local AI solution that runs entirely on-device. These samples cover chat completions, audio transcription, tool calling, LangChain integration, and more.
+Explore complete working examples that demonstrate how to use Foundry Local — an end-to-end local AI solution that runs entirely on-device. These samples cover chat completions, embeddings, audio transcription, tool calling, LangChain integration, and more.
 
 > **New to Foundry Local?** Check out the [main README](../README.md) for an overview and quickstart, or visit the [Foundry Local documentation](https://learn.microsoft.com/azure/foundry-local/) on Microsoft Learn.
 
 ## Samples by Language
 
 | Language | Samples | Description |
 |----------|---------|-------------|
-| [**C#**](cs/) | 12 | .NET SDK samples including native chat, audio transcription, tool calling, model management, web server, and tutorials. Uses WinML on Windows for hardware acceleration. |
-| [**JavaScript**](js/) | 12 | Node.js SDK samples including native chat, audio transcription, Electron desktop app, Copilot SDK integration, LangChain, tool calling, web server, and tutorials. |
-| [**Python**](python/) | 9 | Python samples using the OpenAI-compatible API, including chat, audio transcription, LangChain integration, tool calling, web server, and tutorials. |
-| [**Rust**](rust/) | 8 | Rust SDK samples including native chat, audio transcription, tool calling, web server, and tutorials. |
+| [**C#**](cs/) | 13 | .NET SDK samples including native chat, embeddings, audio transcription, tool calling, model management, web server, and tutorials. Uses WinML on Windows for hardware acceleration. |
+| [**JavaScript**](js/) | 13 | Node.js SDK samples including native chat, embeddings, audio transcription, Electron desktop app, Copilot SDK integration, LangChain, tool calling, web server, and tutorials. |
+| [**Python**](python/) | 10 | Python samples using the OpenAI-compatible API, including chat, embeddings, audio transcription, LangChain integration, tool calling, web server, and tutorials. |
+| [**Rust**](rust/) | 9 | Rust SDK samples including native chat, embeddings, audio transcription, tool calling, web server, and tutorials. |

samples/cs/README.md

@@ -12,6 +12,7 @@ Both packages provide the same APIs, so the same source code works on all platfo
 | Sample | Description |
 |---|---|
 | [native-chat-completions](native-chat-completions/) | Initialize the SDK, download a model, and run chat completions. |
+| [embeddings](embeddings/) | Generate single and batch text embeddings using the Foundry Local SDK. |
 | [audio-transcription-example](audio-transcription-example/) | Transcribe audio files using the Foundry Local SDK. |
 | [foundry-local-web-server](foundry-local-web-server/) | Set up a local OpenAI-compliant web server. |
 | [tool-calling-foundry-local-sdk](tool-calling-foundry-local-sdk/) | Use tool calling with native chat completions. |

samples/cs/embeddings/Embeddings.csproj

@@ -0,0 +1,48 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <OutputType>Exe</OutputType>
+    <ImplicitUsings>enable</ImplicitUsings>
+    <Nullable>enable</Nullable>
+  </PropertyGroup>
+
+  <!-- Windows: target Windows SDK for WinML hardware acceleration -->
+  <PropertyGroup Condition="$([MSBuild]::IsOSPlatform('Windows'))">
+    <TargetFramework>net9.0-windows10.0.26100</TargetFramework>
+    <WindowsAppSDKSelfContained>false</WindowsAppSDKSelfContained>
+    <Platforms>ARM64;x64</Platforms>
+    <WindowsPackageType>None</WindowsPackageType>
+    <EnableCoreMrtTooling>false</EnableCoreMrtTooling>
+  </PropertyGroup>
+
+  <!-- Non-Windows: standard .NET -->
+  <PropertyGroup Condition="!$([MSBuild]::IsOSPlatform('Windows'))">
+    <TargetFramework>net9.0</TargetFramework>
+  </PropertyGroup>
+
+  <PropertyGroup Condition="'$(RuntimeIdentifier)'==''">
+    <RuntimeIdentifier>$(NETCoreSdkRuntimeIdentifier)</RuntimeIdentifier>
+  </PropertyGroup>
+
+  <!-- Windows: WinML for hardware acceleration -->
+  <ItemGroup Condition="$([MSBuild]::IsOSPlatform('Windows'))">
+    <PackageReference Include="Microsoft.AI.Foundry.Local.WinML" />
+  </ItemGroup>
+
+  <!-- Non-Windows: standard SDK -->
+  <ItemGroup Condition="!$([MSBuild]::IsOSPlatform('Windows'))">
+    <PackageReference Include="Microsoft.AI.Foundry.Local" />
+  </ItemGroup>
+
+  <!-- Linux GPU support -->
+  <ItemGroup Condition="'$(RuntimeIdentifier)' == 'linux-x64'">
+    <PackageReference Include="Microsoft.ML.OnnxRuntime.Gpu" />
+    <PackageReference Include="Microsoft.ML.OnnxRuntimeGenAI.Cuda" />
+  </ItemGroup>
+
+  <!-- Shared utilities -->
+  <ItemGroup>
+    <Compile Include="../Shared/*.cs" />
+  </ItemGroup>
+
+</Project>

samples/cs/embeddings/Program.cs

@@ -0,0 +1,74 @@
+// <complete_code>
+// <imports>
+using Microsoft.AI.Foundry.Local;
+// </imports>
+
+// <init>
+var config = new Configuration
+{
+    AppName = "foundry_local_samples",
+    LogLevel = Microsoft.AI.Foundry.Local.LogLevel.Information
+};
+
+// Initialize the singleton instance.
+await FoundryLocalManager.CreateAsync(config, Utils.GetAppLogger());
+var mgr = FoundryLocalManager.Instance;
+// </init>
+
+// <model_setup>
+// Get the model catalog
+var catalog = await mgr.GetCatalogAsync();
+
+// Get an embedding model
+var model = await catalog.GetModelAsync("qwen3-0.6b-embedding") ?? throw new Exception("Embedding model not found");
+
+// Download the model (the method skips download if already cached)
+await model.DownloadAsync(progress =>
+{
+    Console.Write($"\rDownloading model: {progress:F2}%");
+    if (progress >= 100f)
+    {
+        Console.WriteLine();
+    }
+});
+
+// Load the model
+Console.Write($"Loading model {model.Id}...");
+await model.LoadAsync();
+Console.WriteLine("done.");
+// </model_setup>
+
+// <single_embedding>
+// Get an embedding client
+var embeddingClient = await model.GetEmbeddingClientAsync();
+
+// Generate a single embedding
+Console.WriteLine("\n--- Single Embedding ---");
+var response = await embeddingClient.GenerateEmbeddingAsync("The quick brown fox jumps over the lazy dog");
+var embedding = response.Data[0].Embedding;
+Console.WriteLine($"Dimensions: {embedding.Count}");
+Console.WriteLine($"First 5 values: [{string.Join(", ", embedding.Take(5).Select(v => v.ToString("F6")))}]");
+// </single_embedding>
+
+// <batch_embedding>
+// Generate embeddings for multiple inputs
+Console.WriteLine("\n--- Batch Embeddings ---");
+var batchResponse = await embeddingClient.GenerateEmbeddingsAsync([
+    "Machine learning is a subset of artificial intelligence",
+    "The capital of France is Paris",
+    "Rust is a systems programming language"
+]);
+
+Console.WriteLine($"Number of embeddings: {batchResponse.Data.Count}");
+for (var i = 0; i < batchResponse.Data.Count; i++)
+{
+    Console.WriteLine($"  [{i}] Dimensions: {batchResponse.Data[i].Embedding.Count}");
+}
+// </batch_embedding>
+
+// <cleanup>
+// Tidy up - unload the model
+await model.UnloadAsync();
+Console.WriteLine("\nModel unloaded.");
+// </cleanup>
+// </complete_code>

samples/js/README.md

@@ -11,6 +11,7 @@ These samples demonstrate how to use the Foundry Local JavaScript SDK (`foundry-
 | Sample | Description |
 |--------|-------------|
 | [native-chat-completions](native-chat-completions/) | Initialize the SDK, download a model, and run non-streaming and streaming chat completions. |
+| [embeddings](embeddings/) | Generate single and batch text embeddings using the Foundry Local SDK. |
 | [audio-transcription-example](audio-transcription-example/) | Transcribe audio files using the Whisper model with streaming output. |
 | [chat-and-audio-foundry-local](chat-and-audio-foundry-local/) | Unified sample demonstrating both chat and audio transcription in one application. |
 | [electron-chat-application](electron-chat-application/) | Full-featured Electron desktop chat app with voice transcription and model management. |

samples/js/embeddings/app.js

@@ -0,0 +1,73 @@
+// <complete_code>
+// <imports>
+import { FoundryLocalManager } from 'foundry-local-sdk';
+// </imports>
+
+// Initialize the Foundry Local SDK
+console.log('Initializing Foundry Local SDK...');
+
+// <init>
+const manager = FoundryLocalManager.create({
+    appName: 'foundry_local_samples',
+    logLevel: 'info'
+});
+// </init>
+console.log('✓ SDK initialized successfully');
+
+// <model_setup>
+// Get an embedding model
+const modelAlias = 'qwen3-0.6b-embedding';
+const model = await manager.catalog.getModel(modelAlias);
+
+// Download the model
+console.log(`\nDownloading model ${modelAlias}...`);
+await model.download((progress) => {
+    process.stdout.write(`\rDownloading... ${progress.toFixed(2)}%`);
+});
+console.log('\n✓ Model downloaded');
+
+// Load the model
+console.log(`\nLoading model ${modelAlias}...`);
+await model.load();
+console.log('✓ Model loaded');
+// </model_setup>
+
+// <single_embedding>
+// Create embedding client
+console.log('\nCreating embedding client...');
+const embeddingClient = model.createEmbeddingClient();
+console.log('✓ Embedding client created');
+
+// Generate a single embedding
+console.log('\n--- Single Embedding ---');
+const response = await embeddingClient.generateEmbedding(
+    'The quick brown fox jumps over the lazy dog'
+);
+
+const embedding = response.data[0].embedding;
+console.log(`Dimensions: ${embedding.length}`);
+console.log(`First 5 values: [${embedding.slice(0, 5).map(v => v.toFixed(6)).join(', ')}]`);
+// </single_embedding>
+
+// <batch_embedding>
+// Generate embeddings for multiple inputs
+console.log('\n--- Batch Embeddings ---');
+const batchResponse = await embeddingClient.generateEmbeddings([
+    'Machine learning is a subset of artificial intelligence',
+    'The capital of France is Paris',
+    'Rust is a systems programming language'
+]);
+
+console.log(`Number of embeddings: ${batchResponse.data.length}`);
+for (let i = 0; i < batchResponse.data.length; i++) {
+    console.log(`  [${i}] Dimensions: ${batchResponse.data[i].embedding.length}`);
+}
+// </batch_embedding>
+
+// <cleanup>
+// Unload the model
+console.log('\nUnloading model...');
+await model.unload();
+console.log('✓ Model unloaded');
+// </cleanup>
+// </complete_code>

samples/js/embeddings/package.json

@@ -0,0 +1,15 @@
+{
+  "name": "embeddings",
+  "version": "1.0.0",
+  "type": "module",
+  "main": "app.js",
+  "scripts": {
+    "start": "node app.js"
+  },
+  "dependencies": {
+    "foundry-local-sdk": "latest"
+  },
+  "optionalDependencies": {
+    "foundry-local-sdk-winml": "latest"
+  }
+}

samples/python/README.md

@@ -11,6 +11,7 @@ These samples demonstrate how to use Foundry Local with Python.
 | Sample | Description |
 |--------|-------------|
 | [native-chat-completions](native-chat-completions/) | Initialize the SDK, start the local service, and run streaming chat completions. |
+| [embeddings](embeddings/) | Generate single and batch text embeddings using the Foundry Local SDK. |
 | [audio-transcription](audio-transcription/) | Transcribe audio files using the Whisper model. |
 | [web-server](web-server/) | Start a local OpenAI-compatible web server and call it with the OpenAI Python SDK. |
 | [tool-calling](tool-calling/) | Tool calling with custom function definitions (get_weather, calculate). |

samples/python/embeddings/requirements.txt

@@ -0,0 +1,2 @@
+foundry-local-sdk; sys_platform != "win32"
+foundry-local-sdk-winml; sys_platform == "win32"

samples/python/embeddings/src/app.py

@@ -0,0 +1,61 @@
+# <complete_code>
+# <imports>
+from foundry_local_sdk import Configuration, FoundryLocalManager
+# </imports>
+
+
+def main():
+    # <init>
+    # Initialize the Foundry Local SDK
+    config = Configuration(app_name="foundry_local_samples")
+    FoundryLocalManager.initialize(config)
+    manager = FoundryLocalManager.instance
+
+    # Select and load an embedding model from the catalog
+    model = manager.catalog.get_model("qwen3-0.6b-embedding")
+    model.download(
+        lambda progress: print(
+            f"\rDownloading model: {progress:.2f}%",
+            end="",
+            flush=True,
+        )
+    )
+    print()
+    model.load()
+    print("Model loaded and ready.")
+
+    # Get an embedding client
+    client = model.get_embedding_client()
+    # </init>
+
+    # <single_embedding>
+    # Generate a single embedding
+    print("\n--- Single Embedding ---")
+    response = client.generate_embedding("The quick brown fox jumps over the lazy dog")
+    embedding = response.data[0].embedding
+    print(f"Dimensions: {len(embedding)}")
+    print(f"First 5 values: {embedding[:5]}")
+    # </single_embedding>
+
+    # <batch_embedding>
+    # Generate embeddings for multiple inputs
+    print("\n--- Batch Embeddings ---")
+    batch_response = client.generate_embeddings([
+        "Machine learning is a subset of artificial intelligence",
+        "The capital of France is Paris",
+        "Rust is a systems programming language",
+    ])
+
+    print(f"Number of embeddings: {len(batch_response.data)}")
+    for i, data in enumerate(batch_response.data):
+        print(f"  [{i}] Dimensions: {len(data.embedding)}")
+    # </batch_embedding>
+
+    # Clean up
+    model.unload()
+    print("\nModel unloaded.")
+
+
+if __name__ == "__main__":
+    main()
+# </complete_code>

samples/rust/Cargo.toml

@@ -4,6 +4,7 @@ members = [
     "tool-calling-foundry-local",
     "native-chat-completions",
     "audio-transcription-example",
+    "embeddings",
     "tutorial-chat-assistant",
     "tutorial-document-summarizer",
     "tutorial-tool-calling",

samples/rust/README.md

@@ -11,6 +11,7 @@ These samples demonstrate how to use the Rust binding for Foundry Local.
 | Sample | Description |
 |--------|-------------|
 | [native-chat-completions](native-chat-completions/) | Non-streaming and streaming chat completions using the native chat client. |
+| [embeddings](embeddings/) | Generate single and batch text embeddings using the native embedding client. |
 | [audio-transcription-example](audio-transcription-example/) | Audio transcription (non-streaming and streaming) using the Whisper model. |
 | [foundry-local-webserver](foundry-local-webserver/) | Start a local OpenAI-compatible web server and call it with a standard HTTP client. |
 | [tool-calling-foundry-local](tool-calling-foundry-local/) | Tool calling with streaming responses, multi-turn conversation, and local tool execution. |

samples/rust/embeddings/Cargo.toml

@@ -0,0 +1,12 @@
+[package]
+name = "embeddings"
+version = "0.1.0"
+edition = "2021"
+description = "Native SDK embeddings (single and batch) using the Foundry Local Rust SDK"
+
+[dependencies]
+foundry-local-sdk = { path = "../../../sdk/rust" }
+tokio = { version = "1", features = ["rt-multi-thread", "macros"] }
+
+[target.'cfg(windows)'.dependencies]
+foundry-local-sdk = { path = "../../../sdk/rust", features = ["winml"] }