LMSupply.Embedder 0.112.0

LMSupply.Embedder

Local text embedding for .NET with automatic model downloading.

Features

• Zero-config: Models download automatically from HuggingFace
• GPU Acceleration: CUDA, DirectML (Windows), CoreML (macOS)
• Cross-platform: Windows, Linux, macOS
• Simple API: Just 2 lines of code to get started

Quick Start

using LMSupply.Embedder;

// Load the default model
await using var model = await LocalEmbedder.LoadAsync("default");

// Generate embeddings
float[] embedding = await model.EmbedAsync("Hello, world!");
Console.WriteLine($"Dimensions: {embedding.Length}");

Query/Passage Embeddings

Some models (the E5 family, Nomic) are fine-tuned with a text-prefix convention — query embeddings and document/passage embeddings need different prefixes for accurate retrieval, and text with no retrieval role (similarity, clustering) takes a third. Every entry point applies the model's own convention from its ModelInfo (a no-op for models that don't need one):

await using var model = await LocalEmbedder.LoadAsync("multilingual-e5-base");

float[] queryEmbedding = await model.EmbedQueryAsync("what is the capital of France?");
float[] passageEmbedding = await model.EmbedPassageAsync("Paris is the capital of France.");

Batch and Matryoshka-truncated (dimensions:) overloads exist for all four. A model loaded by repository id takes these from config_sentence_transformers.json (prompts and default_prompt_name), as sentence-transformers does.

Available Models

Four standard aliases (LocalEmbedder.LoadAsync("default"), etc.) plus a longer list of models loadable by their explicit short name (LocalEmbedder.LoadAsync("multilingual-e5-base")).

Aliases

Explicit models (by short name)

"Prefix" marks models fine-tuned with a prefix convention (see Query/Passage Embeddings above): "query instruction" means only the retrieval query takes one (BGE English v1.5: Represent this sentence for searching relevant passages: , applied by EmbedQueryAsync); — means the model needs no prefix and EmbedAsync/EmbedQueryAsync/EmbedPassageAsync embed its text as given.

GPU Acceleration

Do not add ONNX Runtime packages (Microsoft.ML.OnnxRuntime*): LMSupply provisions the runtime itself, and a second copy conflicts with it. ExecutionProvider.Auto uses CUDA when the CUDA 12 runtime and cuDNN 9 are installed on the machine, CoreML on macOS, and the CPU otherwise. On Windows with an AMD or Intel GPU, ONNX sessions run on the CPU (DirectML was removed in 0.67.0). See GPU acceleration.