RecursiveAI.OneNlp.Models.Embeddings.Multilingual 1.0.0

.NET 10.0 This package targets .NET 10.0. The package is compatible with this framework or higher. 
dotnet add package RecursiveAI.OneNlp.Models.Embeddings.Multilingual --version 1.0.0
                    


                    

                
NuGet\Install-Package RecursiveAI.OneNlp.Models.Embeddings.Multilingual -Version 1.0.0
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="RecursiveAI.OneNlp.Models.Embeddings.Multilingual" Version="1.0.0" />
For projects that support PackageReference, copy this XML node into the project file to reference the package. 
<PackageVersion Include="RecursiveAI.OneNlp.Models.Embeddings.Multilingual" Version="1.0.0" />
                    


                            Directory.Packages.props
                        

                    

                
<PackageReference Include="RecursiveAI.OneNlp.Models.Embeddings.Multilingual" />
                    


                            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 RecursiveAI.OneNlp.Models.Embeddings.Multilingual --version 1.0.0
                    


                    

                
#r "nuget: RecursiveAI.OneNlp.Models.Embeddings.Multilingual, 1.0.0"
#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 RecursiveAI.OneNlp.Models.Embeddings.Multilingual@1.0.0
#: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=RecursiveAI.OneNlp.Models.Embeddings.Multilingual&version=1.0.0
                    


                            Install as a Cake Addin
                        

                    

                
#tool nuget:?package=RecursiveAI.OneNlp.Models.Embeddings.Multilingual&version=1.0.0
                    


                            Install as a Cake Tool

RecursiveAI.OneNLP.Models.Embeddings.Multilingual

spaCy-class NLP for .NET. A multilingual sentence embedder for RecursiveAI.OneNlp: add this package and Nlp.Embed turns text in about 100 languages into a 384-value, unit-length vector. No downloads, no native code, NativeAOT and trim clean. Unaffiliated with other projects named OneNLP.

Measured. Vectors match sentence-transformers 6.2.0 to a maximum absolute difference of 3e-7 over 2,103 texts, and mteb 2.27.1 scores equal the same-harness sentence-transformers scores on every task. Against the model card, four cells are lower for sentence-transformers itself too: Banking77Classification 70.44 against 79.42, MTOPDomainClassification (en, de, es, fr) 85.59 against 88.01, AskUbuntuDupQuestions 56.42 against 57.88, and STS22 65.13 against 66.01 (66.10 under mteb 1.12.94); the others are within 0.5 of the card (STSBenchmark 84.11 against 84.01, TwentyNewsgroupsClustering 32.81 against 33.22, TwitterSemEval2015 70.75 against 70.95, SciFact 67.70 against 67.70). Size: 448.4 MiB of weights across three shard packages plus 16.3 MiB here. Lineage: the authors' weights (MIT); nothing is trained here.

using RecursiveAI.OneNlp;

float[] a = Nlp.Embed("Wie setze ich mein Passwort zurück?");
float[] b = Nlp.Embed("How do I reset my password?");
float cosine = a.Zip(b, (x, y) => x * y).Sum();   // vectors have unit length

The model is intfloat/multilingual-e5-small (MIT), exported to ONNX from the authors' published weights and run on OneModel; nothing is trained here. The 470 MB of weights are split by byte range into three ...Embeddings.Multilingual.Shard1..3 packages (NuGet's size limit), which this package depends on; the shards are joined in memory at load time. When this package and RecursiveAI.OneNlp.Models.Embeddings (English, bge) are both referenced, Nlp.Embed uses this one; call EmbeddingsModel.Load() for the English model.

The model expects "query: " / "passage: " prefixes: Nlp.Embed uses "query: " (right for similarity); for retrieval load MultilingualEmbeddingsModel.Load() and call EmbedQuery and EmbedPassage. PROVENANCE.md states the licence and the authors' training data.

Copyright (c) Recursive AI, LLC.

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

This package is not used by any NuGet packages.

GitHub repositories

This package is not used by any popular GitHub repositories.

Version Downloads Last Updated
1.0.0 0 11/8/2026

See CHANGELOG.md in the repository.