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

[phanindraraja]

Summary

Adds embedding support to all four Foundry Local SDKs (C#, JavaScript, Python, Rust), enabling text embedding generation through the OpenAIEmbeddingClient via the FoundryLocalCore native interop layer. Supports both single and batch input.

Changes

C# SDK

• OpenAIEmbeddingClient — Client with GenerateEmbeddingAsync(string) for single input and GenerateEmbeddingsAsync(IEnumerable<string>) for batch. Configurable via EmbeddingSettings (Dimensions, EncodingFormat).
• EmbeddingRequestResponseTypes.cs — Request DTO extending Betalgo's EmbeddingCreateRequest with FromUserInput() factory for both single and batch. Response deserialization with null-check and error handling.
• IModel.GetEmbeddingClientAsync() — New interface method, implemented in Model and ModelVariant.
• JsonSerializationContext — Registered EmbeddingCreateRequestExtended and EmbeddingCreateResponse for AOT.

JavaScript SDK

• EmbeddingClient — Client with generateEmbedding(string) and generateEmbeddings(string[]). Settings with encodingFormat validation. Shared executeRequest() for both paths.
• IModel.createEmbeddingClient() — Factory method in interface, Model, and ModelVariant.
• Exported from index.ts.

Python SDK

• EmbeddingClient — Client with generate_embedding(str) and generate_embeddings(List[str]). Uses OpenAI SDK types (EmbeddingCreateParams for request, CreateEmbeddingResponse for response). Settings with encoding_format validation via _serialize(). Patches server response to add missing object and usage fields required by the OpenAI SDK type.
• IModel.get_embedding_client() — Abstract method, implemented in Model and ModelVariant.
• Exported from openai/__init__.py.

Rust SDK

• EmbeddingClient — Client with generate_embedding(&str) and generate_embeddings(&[&str]). Uses async_openai::types::embeddings::CreateEmbeddingResponse as return type. Patches server response for missing object and usage fields. Settings with encoding_format validation. Builder pattern for dimensions() and encoding_format().
• Model.create_embedding_client() — Factory method in Model and ModelVariant.
• Added "embedding-types" feature to async-openai dependency.

Tests

All SDKs include tests for:

• Basic embedding generation (1024 dimensions, correct response structure)
• L2 normalization (norm ≈ 1.0, values within [-1, 1])
• Different inputs produce different embeddings (cosine similarity < 0.99)
• Same input produces identical embeddings (determinism)
• Batch embedding (multiple inputs → multiple results with correct indices)
• Batch results match single-input results
• Input validation (empty input, empty list)
• Known golden values (C# only)

Samples

New embeddings sample in each SDK (samples/{cs,js,python,rust}/embeddings/) demonstrating:

• SDK initialization and model setup
• Single embedding generation with dimension output
• Batch embedding generation with multiple inputs

Documentation

• All four SDK READMEs updated with embeddings feature, usage examples, and settings documentation.
• C# API docs (index.md, imodel.md, model.md, modelvariant.md, openaiembeddingclient.md).
• JS docs (README.md class index).
• Rust API docs (docs/api.md with EmbeddingClient, EmbeddingResponse, EmbeddingData reference).
• Python API reference table updated.

Test plan

• C# SDK tests pass
• Python SDK tests pass
• JS SDK tests pass
• Rust SDK tests pass
• All existing chat/audio tests unaffected

Dependencies

This PR depends on the FoundryLocalCore (neutron-server) PR that adds the "embeddings" NativeInterop command, /v1/embeddings endpoint, and batch support:
https://microsoft.visualstudio.com/windows.ai.toolkit/_git/neutron-server/pullrequest/15212502

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated (UTC)
foundry-local	Ready	Preview, Comment	Apr 16, 2026 8:21am

[Copilot]

Pull request overview

Adds OpenAI-compatible embeddings support across the Foundry Local SDKs (C#, JS, Python, Rust) by introducing embedding clients that call the native embeddings interop command, plus tests, samples, and documentation updates.

Changes:

• Introduces EmbeddingClient/OpenAIEmbeddingClient and model factory methods in Rust/JS/Python/C#.
• Adds integration/unit tests for embedding generation and batch behavior across SDKs.
• Adds new embeddings samples and updates SDK READMEs / API docs; updates Rust dependency features for embedding types.

Reviewed changes

Copilot reviewed 54 out of 55 changed files in this pull request and generated 6 comments.

Show a summary per file

File	Description
sdk/rust/tests/integration/main.rs	Registers Rust embedding integration test module.
sdk/rust/tests/integration/embedding_client_test.rs	Adds Rust integration coverage for single/batch embeddings + normalization/determinism checks.
sdk/rust/tests/integration/common/mod.rs	Adds embedding model alias constant for integration tests.
sdk/rust/src/openai/mod.rs	Exposes Rust EmbeddingClient + settings from the OpenAI module.
sdk/rust/src/openai/embedding_client.rs	Implements Rust embedding client + settings + response patching for async_openai types.
sdk/rust/src/detail/model_variant.rs	Adds create_embedding_client() factory on Rust ModelVariant.
sdk/rust/src/detail/model.rs	Adds public create_embedding_client() factory on Rust Model.
sdk/rust/docs/api.md	Documents the new Rust embeddings client API.
sdk/rust/README.md	Adds Rust README section describing embeddings usage + settings.
sdk/rust/Cargo.toml	Enables async-openai embedding types via embedding-types feature.
sdk/python/test/openai/test_embedding_client.py	Adds Python embedding tests mirroring C# suite (single/batch/normalization/determinism/validation).
sdk/python/test/conftest.py	Adds Python embedding model alias constant for tests.
sdk/python/src/openai/embedding_client.py	Implements Python EmbeddingClient + settings + response patching for OpenAI SDK types.
sdk/python/src/openai/init.py	Exports Python EmbeddingClient / EmbeddingSettings.
sdk/python/src/imodel.py	Adds Python IModel.get_embedding_client() abstract method.
sdk/python/src/detail/model_variant.py	Implements Python get_embedding_client() on ModelVariant.
sdk/python/src/detail/model.py	Implements Python get_embedding_client() on Model.
sdk/python/README.md	Adds Python README section for embeddings usage + settings.
sdk/js/test/testUtils.ts	Adds JS embedding model alias constant for tests.
sdk/js/test/openai/embeddingClient.test.ts	Adds JS embedding tests for single/batch/normalization/determinism.
sdk/js/src/openai/embeddingClient.ts	Implements JS EmbeddingClient + settings + input validation + shared request executor.
sdk/js/src/index.ts	Exports JS EmbeddingClient / EmbeddingClientSettings.
sdk/js/src/imodel.ts	Adds JS IModel.createEmbeddingClient() factory signature.
sdk/js/src/detail/modelVariant.ts	Implements createEmbeddingClient() on JS ModelVariant.
sdk/js/src/detail/model.ts	Implements createEmbeddingClient() on JS Model.
sdk/js/docs/README.md	Adds embeddings classes to JS docs index.
sdk/js/README.md	Adds JS README section for embeddings usage + settings.
sdk/cs/test/FoundryLocal.Tests/EmbeddingClientTests.cs	Adds C# embeddings test suite.
sdk/cs/src/OpenAI/EmbeddingRequestResponseTypes.cs	Adds C# embedding request DTO helpers + response parsing extensions.
sdk/cs/src/OpenAI/EmbeddingClient.cs	Adds C# OpenAIEmbeddingClient using native interop.
sdk/cs/src/IModel.cs	Adds C# IModel.GetEmbeddingClientAsync() API.
sdk/cs/src/Detail/ModelVariant.cs	Implements C# GetEmbeddingClientAsync() on model variants.
sdk/cs/src/Detail/Model.cs	Implements C# GetEmbeddingClientAsync() on models.
sdk/cs/src/Detail/JsonSerializationContext.cs	Registers embedding request/response types for source-gen JSON serialization (AOT).
sdk/cs/docs/api/microsoft.ai.foundry.local.openaiembeddingclient.md	Adds generated API doc page for C# embedding client.
sdk/cs/docs/api/microsoft.ai.foundry.local.modelvariant.md	Documents new C# GetEmbeddingClientAsync() on ModelVariant.
sdk/cs/docs/api/microsoft.ai.foundry.local.model.md	Documents new C# GetEmbeddingClientAsync() on Model.
sdk/cs/docs/api/microsoft.ai.foundry.local.imodel.md	Documents new C# IModel.GetEmbeddingClientAsync() method.
sdk/cs/docs/api/index.md	Adds OpenAIEmbeddingClient to C# docs index.
sdk/cs/README.md	Adds C# README section for embeddings usage + settings.
samples/rust/embeddings/src/main.rs	Adds Rust embeddings sample (single + batch) with model lifecycle.
samples/rust/embeddings/Cargo.toml	Adds Cargo manifest for Rust embeddings sample.
samples/rust/README.md	Lists the new Rust embeddings sample.
samples/rust/Cargo.toml	Adds embeddings sample to Rust samples workspace.
samples/python/embeddings/src/app.py	Adds Python embeddings sample (single + batch) with model lifecycle.
samples/python/embeddings/requirements.txt	Adds Python sample requirements including WinML variant on Windows.
samples/python/README.md	Lists the new Python embeddings sample.
samples/js/embeddings/package.json	Adds JS embeddings sample package manifest.
samples/js/embeddings/app.js	Adds JS embeddings sample (single + batch) with model lifecycle.
samples/js/README.md	Lists the new JS embeddings sample.
samples/cs/embeddings/Program.cs	Adds C# embeddings sample (single + batch) with model lifecycle.
samples/cs/embeddings/Embeddings.csproj	Adds C# sample project file with Win/non-Win targeting.
samples/cs/README.md	Lists the new C# embeddings sample.
samples/README.md	Updates top-level samples README to include embeddings and updated sample counts.
.gitignore	Ignores .vscode/ directory.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.