Skip to main content
net10.0

A lightweight, zero-configuration semantic reranker for .NET. Supports multiple cross-encoder models with automatic download, GPU acceleration, and HuggingFace caching.

Published
Dec 17, 2025
10mo ago
Total Downloads
24.4K
24,402

Install

dotnet add package LMSupply.Reranker --version 0.7.3
ProductVersions
.NET
net10.0

README

LMSupply.Reranker

Local semantic reranking for .NET with cross-encoder models.

Features

  • Zero-config: Models download automatically from HuggingFace
  • GPU Acceleration: CUDA, DirectML (Windows), CoreML (macOS)
  • Cross-platform: Windows, Linux, macOS
  • RAG Integration: Perfect for improving retrieval quality

Quick Start

using LMSupply.Reranker;

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

// Rerank documents
var results = await reranker.RerankAsync(
    query: "What is machine learning?",
    documents: ["ML is a branch of AI...", "The weather is nice..."],
    topK: 5);

foreach (var result in results)
    Console.WriteLine($"{result.Index}: {result.Score:F3}");

Available Models

Alias Model Size Description
default MS MARCO MiniLM L6 ~90MB Best speed/quality balance
fast MS MARCO TinyBERT ~18MB Ultra-fast, latency-critical
quality BGE Reranker Base ~440MB Higher accuracy, multilingual
large BGE Reranker Large ~1.1GB Highest accuracy
multilingual BGE Reranker v2-m3 ~1.1GB 8K context, 100+ languages

GPU Acceleration

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

# Windows (AMD/Intel/NVIDIA)
dotnet add package Microsoft.ML.OnnxRuntime.DirectML

Changes from Previous Version

No structural changes between v0.7.2 and v0.7.3.

Adoption Assessment

Assess this package against its supported frameworks, license, maintenance signals and dependency graph before making it a project standard.

Compatibility metadata lists 1 target framework; confirm the exact target used by your application.

Related Guides & Workflows

Learn how to evaluate, integrate, or audit this package in your .NET project.