Rag.NET 1.0.0

.NET 10.0

dotnet add package Rag.NET --version 1.0.0

NuGet\Install-Package Rag.NET -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="Rag.NET" Version="1.0.0" />

For projects that support PackageReference, copy this XML node into the project file to reference the package.

<PackageVersion Include="Rag.NET" Version="1.0.0" />
                    

                            Directory.Packages.props

<PackageReference Include="Rag.NET" />
                    

                            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 Rag.NET --version 1.0.0

The NuGet Team does not provide support for this client. Please contact its maintainers for support.

#r "nuget: Rag.NET, 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 Rag.NET@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=Rag.NET&version=1.0.0
                    

                            Install as a Cake Addin

#tool nuget:?package=Rag.NET&version=1.0.0
                    

                            Install as a Cake Tool

The NuGet Team does not provide support for this client. Please contact its maintainers for support.

Rag.NET

The core Retrieval-Augmented Generation pipeline for .NET: AddRagNet() wires ingestion (parse → chunk → embed → store) and retrieval (query → search → rerank → answer) into any IServiceCollection, exposed to your code as one IRagPipeline.

Install

dotnet add package Rag.NET

Setup

Rag.NET builds on Microsoft.Extensions.AI: register any IChatClient and IEmbeddingGenerator<string, Embedding<float>> (OpenAI, Azure OpenAI, Ollama, …) before calling AddRagNet(). Out of the box this package parses text and Markdown, chunks recursively, and can run entirely in memory — perfect for a first spike before you attach a real vector store package such as Rag.NET.VectorStores.PgVector.

using Microsoft.Extensions.DependencyInjection;
using Rag.NET.Abstractions;
using Rag.NET.DependencyInjection;
using Rag.NET.Storage;

// chatClient / embeddingGenerator: your Microsoft.Extensions.AI implementations.
services.AddSingleton(chatClient);
services.AddSingleton(embeddingGenerator);

services.AddSingleton<IVectorStore>(new InMemoryVectorStore()); // nothing persisted
services.AddRagNet();

Example

using Microsoft.Extensions.DependencyInjection;
using Rag.NET.Abstractions;
using Rag.NET.Models;

var pipeline = provider.GetRequiredService<IRagPipeline>();

using var stream = File.OpenRead("notes.md");
var ingested = await pipeline.IngestAsync(stream, new DocumentMetadata
{
    DocumentId  = new DocumentId("notes"),
    FileName    = "notes.md",
    ContentType = "text/markdown",
});

var response = await pipeline.AskAsync("What do the notes say about pricing?");
Console.WriteLine(response.Answer);

foreach (var source in response.Sources)
    Console.WriteLine($"[{source.Score:F2}] {source.Chunk.Text}");

RetrieveAsync returns raw ranked chunks, AskStreamingAsync streams the answer token-by-token, and the RagBuilder passed to AddRagNet(rag => …) activates self-query, parent-document retrieval, MMR, corrective RAG, conversation memory and more.

Full guide

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.

net10.0
- Microsoft.Extensions.AI.Abstractions (>= 10.9.0)
- Microsoft.Extensions.Caching.Abstractions (>= 10.0.12)
- Microsoft.Extensions.DependencyInjection (>= 10.0.12)
- Microsoft.Extensions.DependencyInjection.Abstractions (>= 10.0.12)
- Microsoft.Extensions.Logging.Abstractions (>= 10.0.12)
- Microsoft.ML.Tokenizers (>= 1.0.3)
- Microsoft.ML.Tokenizers.Data.Cl100kBase (>= 1.0.3)
- Rag.NET.Abstractions (>= 1.0.0)
- Rag.NET.QueryTechniques (>= 1.0.0)
- ZeroAlloc.Inject (>= 1.7.3)
- ZeroAlloc.Pipeline (>= 1.2.1)
- ZeroAlloc.Results (>= 1.2.0)
- ZeroAlloc.Specification (>= 1.1.0)
- ZeroAlloc.Validation (>= 1.5.6)

NuGet packages (19)

Showing the top 5 NuGet packages that depend on Rag.NET:

Package	Downloads
Rag.NET.DataProviders Shared OAuth and base class infrastructure for Rag.NET data provider connectors	503
Rag.NET.Resilience Resilience decorators for Rag.NET: the Polly retry pipeline over embedding generators and vector stores (ConfigureResilience), token-bucket rate limiting for chat and embedding calls (UseRateLimiting), and the multi-provider chat fallback chain (UseFallbackChain)	269
Rag.NET.Mediator ZeroAlloc.Mediator integration for Rag.NET	245
Rag.NET.Api ASP.NET Core REST API for Rag.NET pipelines	229
Rag.NET.Diagnostics Disposable in-memory pipeline traces for Rag.NET: the last N query executions, with chunk scores, stage latencies and guard actions	227

GitHub repositories

This package is not used by any popular GitHub repositories.

Version	Downloads	Last Updated
1.0.0	415	9/15/2026
0.1.0	611	8/11/2026