LMSupply.Embedder 0.45.0

.NET 10.0 This package targets .NET 10.0. The package is compatible with this framework or higher. 
dotnet add package LMSupply.Embedder --version 0.45.0
                    


                    

                
NuGet\Install-Package LMSupply.Embedder -Version 0.45.0
This command is intended to be used within the Package Manager Console in Visual Studio, as it uses the NuGet module's version of Install-Package. 
<PackageReference Include="LMSupply.Embedder" Version="0.45.0" />
For projects that support PackageReference, copy this XML node into the project file to reference the package. 
<PackageVersion Include="LMSupply.Embedder" Version="0.45.0" />
                    


                            Directory.Packages.props
                        

                    

                
<PackageReference Include="LMSupply.Embedder" />
                    


                            Project file
For projects that support Central Package Management (CPM), copy this XML node into the solution Directory.Packages.props file to version the package. 
paket add LMSupply.Embedder --version 0.45.0
                    


                    

                
#r "nuget: LMSupply.Embedder, 0.45.0"
#r directive can be used in F# Interactive and Polyglot Notebooks. Copy this into the interactive tool or source code of the script to reference the package. 
#:package LMSupply.Embedder@0.45.0
#:package directive can be used in C# file-based apps starting in .NET 10 preview 4. Copy this into a .cs file before any lines of code to reference the package. 
#addin nuget:?package=LMSupply.Embedder&version=0.45.0
                    


                            Install as a Cake Addin
                        

                    

                
#tool nuget:?package=LMSupply.Embedder&version=0.45.0
                    


                            Install as a Cake Tool

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 an asymmetric text-prefix convention — query embeddings and document/passage embeddings need different prefixes for accurate retrieval. EmbedQueryAsync/EmbedPassageAsync apply the right prefix automatically from the model's ModelInfo (a no-op passthrough 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 both, mirroring EmbedAsync.

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

Alias Model Dimensions Prefix Description
default BAAI/bge-m3 1024 — 568M params, 100+ languages, 8K context, SOTA multilingual
fast intfloat/multilingual-e5-small 384 query/passage 118M params, 100+ languages, lightweight
quality BAAI/bge-m3 1024 — Same model as default; exposed separately for pipelines that explicitly request the quality tier
large intfloat/multilingual-e5-large 1024 query/passage 560M params, 100+ languages, highest dense quality (512-token context limit — use default for long documents)

Explicit models (by short name)

Model Dimensions Prefix Description
nomic-embed-text-v1.5 768 (Matryoshka 64–768) search_query/search_document 137M params, English-first, 8K context
all-mpnet-base-v2 768 — 110M params, legacy quality model, English
bge-base-en-v1.5 768 — 110M params, excellent quality, English
bge-large-en-v1.5 1024 — 335M params, highest accuracy BGE, English
e5-small-v2 384 query/passage 33M params, English
e5-base-v2 768 query/passage 110M params, excellent retrieval, English
multilingual-e5-small 384 query/passage 118M params, 100+ languages, compact
multilingual-e5-base 768 query/passage 278M params, 100+ languages, quality
multilingual-e5-large 1024 query/passage 560M params, 100+ languages, highest quality
gte-large-en-v1.5 1024 — 434M params, 8K context, highest accuracy GTE

"Prefix" marks models fine-tuned with the query/passage convention (see Query/Passage Embeddings above) — — means the model needs no prefix and EmbedQueryAsync/EmbedPassageAsync behave as a plain passthrough for it.

GPU Acceleration

# NVIDIA GPU
dotnet add package Microsoft.ML.OnnxRuntime.Gpu

# Windows (AMD/Intel/NVIDIA)
dotnet add package Microsoft.ML.OnnxRuntime.DirectML
Product Compatible and additional computed target framework versions.
.NET net10.0 is compatible.  net10.0-android was computed.  net10.0-browser was computed.  net10.0-ios was computed.  net10.0-maccatalyst was computed.  net10.0-macos was computed.  net10.0-tvos was computed.  net10.0-windows was computed. 
Compatible target framework(s)
Included target framework(s) (in package)
Learn more about Target Frameworks and .NET Standard.

NuGet packages (6)

Showing the top 5 NuGet packages that depend on LMSupply.Embedder:

Package Downloads
FluxIndex.MCP

MCP (Model Context Protocol) server implementation for FluxIndex RAG services
FluxIndex.Providers.LMSupply

LMSupply local AI embedding, reranking, and text completion provider for FluxIndex
IronHive.Host

IronHive Host - reusable AI agent host SDK (agent loop, tools, session, provider integrations) for CLI, server, and embedded surfaces
IronHive.Cli.Core

IronHive CLI Core - Agent loop, tools, session management, and provider integrations for building AI-powered CLI tools
IronHive.Host.Core

IronHive Host Core - Agent loop, tools, session management, and provider integrations for building reusable AI agent hosts (CLI, server, embedded)

GitHub repositories

This package is not used by any popular GitHub repositories.

Version Downloads Last Updated
0.45.0 0 9/3/2026
0.44.0 0 9/3/2026
0.42.10 116 8/31/2026
0.42.5 89 8/29/2026
0.42.4 103 8/27/2026
0.42.3 94 8/25/2026
0.42.2 306 8/24/2026
0.42.1 141 8/20/2026
0.42.0 137 8/18/2026
0.41.1 91 8/18/2026
0.41.0 101 8/18/2026
0.40.3 95 8/17/2026
0.40.1 105 8/16/2026
0.40.0 127 8/11/2026
0.39.0 100 8/9/2026
0.38.1 99 8/6/2026
0.38.0 93 8/6/2026
0.37.2 93 8/6/2026
0.37.1 249 7/19/2026
0.37.0 125 7/17/2026
Loading failed