Mythosia.AI.Rag.Abstractions 6.0.0

.NET Standard 2.1

dotnet add package Mythosia.AI.Rag.Abstractions --version 6.0.0

NuGet\Install-Package Mythosia.AI.Rag.Abstractions -Version 6.0.0

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="Mythosia.AI.Rag.Abstractions" Version="6.0.0" />

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

<PackageVersion Include="Mythosia.AI.Rag.Abstractions" Version="6.0.0" />
                    

                            Directory.Packages.props

<PackageReference Include="Mythosia.AI.Rag.Abstractions" />
                    

                            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 Mythosia.AI.Rag.Abstractions --version 6.0.0

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

#r "nuget: Mythosia.AI.Rag.Abstractions, 6.0.0"

#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 Mythosia.AI.Rag.Abstractions@6.0.0

#: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=Mythosia.AI.Rag.Abstractions&version=6.0.0
                    

                            Install as a Cake Addin

#tool nuget:?package=Mythosia.AI.Rag.Abstractions&version=6.0.0
                    

                            Install as a Cake Tool

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

Mythosia.AI.Rag.Abstractions

Package Summary

Core interfaces and models for the Mythosia.AI RAG ecosystem.
This package defines the contracts that all RAG components implement — you only need this directly if you're building a custom implementation.

Interfaces

Interface	Description
`IRagPipeline`	Main pipeline contract: `ProcessAsync(query)` → `RagProcessedQuery`
`IEmbeddingProvider`	Text → vector embedding (`GetEmbeddingAsync`, `GetEmbeddingsAsync`)
`IVectorStore`	Vector storage & search (`UpsertAsync`, `SearchAsync`, `DeleteAsync`)
`IRagDiagnosticsStore`	Optional diagnostics contract (`ListAllRecordsAsync`, `ScoredListAsync`)
`ITextSplitter`	Document → chunks (`Split(RagDocument)`)
`IContextBuilder`	Search results → LLM prompt (`BuildContext(query, results)`)
`IQueryRewriter`	Rewrites queries into retrieval-ready form using conversation history, and decides whether document search is needed (search gate)
`IRetrievalStrategy`	Abstracts retrieval logic — pure vector or hybrid (BM25 + vector + RRF)
`IReranker`	Re-ranks search results post-retrieval for improved relevance

Models

Model	Description
`RagChunk`	A chunk of text with ID, content, document ID, index, and metadata
`RagDocument`	A loaded document with `Id`, `Content`, `Source`, and `Metadata` for the RAG pipeline
`RagProcessedQuery`	Pipeline output: original query, rewritten semantic query, retrieval keywords, `RequestMessageContent`, references, `RetrievalCandidates`, `SearchSkipped`, `RewriteResult`, `HasReferences` flag, and `Diagnostics`
`QueryRewriteResult`	Result of rewriting a query into retrieval-ready form, including search gate decision (`NeedsSearch`) and optional retrieval keywords. Factory methods `Pass()` and `Search()`
`ConversationTurn`	Lightweight DTO representing a single conversation turn (role + content) for `IQueryRewriter` context
`RagQueryDiagnostics`	Applied retrieval metadata (`AppliedNamespace`, `FinalTopK`, `RetrievalTopK`, `AppliedFinalMinScore`, `AppliedRetrievalMinScore`, `ElapsedMs`, `RewriteElapsedMs`)
`RagPipelineOptions`	Configuration: `DefaultScope`, `DefaultQuery`, `PromptTemplate`, `EmbeddingBatchSize`
`RagQueryOptions`	Per-request overrides: `FinalFilter`, `RetrievalDerivation`, `Namespace`, `StoreFilter`, `FinalSelection`, `ProgressAsync`
`RagFinalSelectionOptions`	Final selection policy after re-ranking (`Mode`, `RetrievalWeight`)
`RagFinalSelectionMode`	Enum: `RerankerOnly` (default) or `WeightedBlend`
`RagFilter`	Final selection policy (`TopK`, `MinScore`)
`RagRetrievalDerivation`	Controls how retrieval candidates are derived (`TopKMultiplier`, `MinScoreDivider`)
`RagRetrievalFilter`	Immutable computed retrieval filter (`TopK`, `MinScore`)
`RagProgressStage`	Enum for pipeline stage progress reporting (`QueryRewrite`, `Embedding`, `Filtering`, `Retrieval`, `Reranking`, `ContextBuild`)
`VectorRecord`	Stored vector with ID, content, embedding, metadata, namespace
`VectorSearchResult`	Search result with record and similarity score
`VectorFilter`	Filter by namespace, metadata, or minimum score

Custom Implementation Example

public class MyEmbeddingProvider : IEmbeddingProvider
{
    public int Dimensions => 768;

    public Task<float[]> GetEmbeddingAsync(string text, CancellationToken ct = default)
    {
        // Your embedding logic here
    }

    public Task<IReadOnlyList<float[]>> GetEmbeddingsAsync(
        IEnumerable<string> texts, CancellationToken ct = default)
    {
        // Batch embedding logic here
    }
}

Then register via the builder:

.WithRag(rag => rag.UseEmbedding(new MyEmbeddingProvider()))

Product	Compatible and additional computed target framework versions.
.NET	net5.0 was computed. net5.0-windows was computed. net6.0 was computed. net6.0-android was computed. net6.0-ios was computed. net6.0-maccatalyst was computed. net6.0-macos was computed. net6.0-tvos was computed. net6.0-windows was computed. net7.0 was computed. net7.0-android was computed. net7.0-ios was computed. net7.0-maccatalyst was computed. net7.0-macos was computed. net7.0-tvos was computed. net7.0-windows was computed. net8.0 was computed. net8.0-android was computed. net8.0-browser was computed. net8.0-ios was computed. net8.0-maccatalyst was computed. net8.0-macos was computed. net8.0-tvos was computed. net8.0-windows was computed. net9.0 was computed. net9.0-android was computed. net9.0-browser was computed. net9.0-ios was computed. net9.0-maccatalyst was computed. net9.0-macos was computed. net9.0-tvos was computed. net9.0-windows was computed. net10.0 was computed. 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.
.NET Core	netcoreapp3.0 was computed. netcoreapp3.1 was computed.
.NET Standard	netstandard2.1 is compatible.
MonoAndroid	monoandroid was computed.
MonoMac	monomac was computed.
MonoTouch	monotouch was computed.
Tizen	tizen60 was computed.
Xamarin.iOS	xamarinios was computed.
Xamarin.Mac	xamarinmac was computed.
Xamarin.TVOS	xamarintvos was computed.
Xamarin.WatchOS	xamarinwatchos was computed.

Compatible target framework(s)

Included target framework(s) (in package)

Learn more about Target Frameworks and .NET Standard.

.NETStandard 2.1
- Mythosia.VectorDb.Abstractions (>= 3.0.0)

NuGet packages (2)

Showing the top 2 NuGet packages that depend on Mythosia.AI.Rag.Abstractions:

Package	Downloads
Mythosia.AI.Rag RAG (Retrieval Augmented Generation) orchestration for Mythosia.AI. Implements Mythosia.AI.Rag.Abstractions v5.x. Includes RagPipeline, text splitters, context builder, OpenAI/vLLM embedding providers, hybrid search (BM25 + Vector + RRF), re-ranking (Cohere, LLM, vLLM), search gate, keyword extraction, weighted-blend final selection, progress reporting, DoclingDocument-to-RagDocument conversion, and per-query VectorFilter passthrough (StoreFilter). Depends on Mythosia.AI.Abstractions (IAIService) instead of the full Mythosia.AI implementation.	1.2K
Mythosia.VectorDb.InMemory In-memory vector store implementation for Mythosia VectorDb. Provides InMemoryVectorStore with cosine similarity TopK search, metadata filtering, namespace/scope support, upsert/delete operations, GetBatchAsync, CountAsync, IDisposable, Bm25Index keyword search, and normalized hybrid RRF scoring.	629

Package

Downloads

Mythosia.AI.Rag

RAG (Retrieval Augmented Generation) orchestration for Mythosia.AI. Implements Mythosia.AI.Rag.Abstractions v5.x. Includes RagPipeline, text splitters, context builder, OpenAI/vLLM embedding providers, hybrid search (BM25 + Vector + RRF), re-ranking (Cohere, LLM, vLLM), search gate, keyword extraction, weighted-blend final selection, progress reporting, DoclingDocument-to-RagDocument conversion, and per-query VectorFilter passthrough (StoreFilter). Depends on Mythosia.AI.Abstractions (IAIService) instead of the full Mythosia.AI implementation.

1.2K

Mythosia.VectorDb.InMemory

In-memory vector store implementation for Mythosia VectorDb. Provides InMemoryVectorStore with cosine similarity TopK search, metadata filtering, namespace/scope support, upsert/delete operations, GetBatchAsync, CountAsync, IDisposable, Bm25Index keyword search, and normalized hybrid RRF scoring.

629

GitHub repositories

This package is not used by any popular GitHub repositories.

Version	Downloads	Last Updated
6.0.0	99	3/30/2026
5.1.0	96	3/29/2026
5.0.0	171	3/22/2026
4.0.1	171	3/15/2026
4.0.0	138	3/15/2026
3.2.0	109	3/11/2026
3.1.0	133	3/7/2026
3.0.0	243	3/6/2026
2.0.0	121	3/5/2026
1.0.0	281	2/25/2026

v6.0.0: Requires Abstractions v3.0.0 — VectorFilter.ByMetadata/ByNamespace/ByScope and MetadataMatch are removed. Users of RagQueryOptions.StoreFilter must migrate to new fluent API: new VectorFilter().Where(...). No structural changes to this package's own types.