🌐 English · 한국어 · 日本語 · Français · Deutsch · Русский · Українська · 简体中文 · 繁體中文 · Tiếng Việt · ภาษาไทย · Português · Español

A modular .NET AI library for building intelligent applications.

Switch providers, add RAG, load documents — all with a unified API.

📖 Get Started  ·  API Reference  ·  GitHub ↗

---

What do I need to install?

dotnet add package Mythosia.AI                    # start here (this is all you need)
dotnet add package Mythosia.AI.Rag                # optional: when you need RAG
dotnet add package Mythosia.VectorDb.Postgres     # optional: when you need a production vector store

Step	Package	When
1	Mythosia.AI	Start here — completions, streaming, function calling, structured output (OpenAI / Claude / Gemini / Grok / DeepSeek / Perplexity)
2	Mythosia.AI.Rag	When you need RAG — text splitters, embeddings, hybrid search, reranking, InMemory vector store, and document loaders (Word / Excel / PowerPoint / PDF)
3	Mythosia.VectorDb.Postgres / Qdrant / Pinecone	When you need a production vector store instead of InMemory — pick one

Architecture

graph TD
    subgraph "🔗 Orchestration Layer"
        Rag["<b>Mythosia.AI.Rag</b><br/>RagPipeline · TextSplitters<br/>EmbeddingProviders · HybridSearch · Reranking<br/><i>netstandard2.1 · v7.5.0</i>"]
    end

    subgraph "⚡ Core AI"
        AI["<b>Mythosia.AI</b><br/>OpenAI · Anthropic · Google<br/>xAI · DeepSeek · Perplexity<br/><i>netstandard2.1 · v6.5.0</i>"]
        AIAbs["<b>Mythosia.AI.Abstractions</b><br/>IAIService · shared models<br/><i>netstandard2.1 · v2.3.0</i>"]
    end

    subgraph "🔌 Provider Packages"
        Alibaba["<b>Mythosia.AI.Providers.Alibaba</b><br/>Qwen / Alibaba provider package<br/><i>netstandard2.1 · v1.2.6</i>"]
    end

    subgraph "📄 Document Loaders"
        Office["<b>Mythosia.Documents.Office</b><br/>Word · Excel · PowerPoint<br/><i>netstandard2.1 · v1.1.0</i>"]
        Pdf["<b>Mythosia.Documents.Pdf</b><br/>PdfPig Parser<br/><i>netstandard2.1 · v1.1.1</i>"]
    end

    subgraph "📐 Composite Abstractions"
        RagAbs["<b>Mythosia.AI.Rag.Abstractions</b><br/>ITextSplitter · IEmbeddingProvider<br/>IContextBuilder · IRetrievalStrategy · IReranker<br/>RagDocument<br/><i>netstandard2.1 · v6.2.0</i>"]
    end

    subgraph "🗄️ Vector Stores — pick one or more"
        InMem["<b>Mythosia.VectorDb.InMemory</b><br/>Cosine Similarity · TopK · BM25<br/><i>netstandard2.1 · v4.1.0</i>"]
        Pine["<b>Mythosia.VectorDb.Pinecone</b><br/>Managed Index · Namespace · Scope<br/><i>netstandard2.1 · v4.0.1</i>"]
        Pg["<b>Mythosia.VectorDb.Postgres</b><br/>pgvector · HNSW · IVFFlat · HybridSearch<br/><i>net10.0 · v10.7.1</i>"]
        Qd["<b>Mythosia.VectorDb.Qdrant</b><br/>gRPC · Cosine · Euclidean · Dot · HybridSearch<br/><i>netstandard2.1 · v4.1.1</i>"]
    end

    subgraph "🧱 Foundation Abstractions"
        LoaderAbs["<b>Mythosia.Documents.Abstractions</b><br/>IDocumentLoader · IDocumentParser<br/>ParsedDocument · DoclingDocument<br/><i>netstandard2.1 · v1.2.0</i>"]
        VdbAbs["<b>Mythosia.VectorDb.Abstractions</b><br/>IVectorStore · HybridSearchAsync · VectorRecord<br/>VectorFilter · VectorSearchResult · Bm25Tokenizer<br/><i>netstandard2.1 · v4.0.1</i>"]
    end

    %% Core AI internal
    AI --> AIAbs

    %% Orchestration → dependencies
    Rag --> AIAbs
    Rag --> Office
    Rag --> Pdf
    Rag --> RagAbs
    Rag --> InMem

    %% Provider packages → core
    Alibaba --> AI

    %% Composite → Foundation
    RagAbs --> VdbAbs

    %% Loaders → Foundation
    Office --> LoaderAbs
    Pdf --> LoaderAbs

    %% VectorStores → Foundation
    InMem --> VdbAbs
    Pine --> VdbAbs
    Pg --> VdbAbs
    Qd --> VdbAbs

Loading

Demo / Test Bed (Chat UI)

This repository includes a sample Chat UI built on Mythosia.AI — launch Mythosia.AI.Samples.ChatUi to test the library in action.

Run the sample

Run Mythosia.AI.Samples.ChatUi to try it locally:

# from repo root
dotnet run --project apps/Mythosia.AI.Samples.ChatUi

2026-02-27.18-21-02.mp4

Quick Start

Basic AI Completion

using Mythosia.AI;

var service = new OpenAIService(apiKey, httpClient);
var response = await service.GetCompletionAsync("Hello!");

Streaming

await foreach (var token in service.StreamAsync("Tell me a story"))
{
    Console.Write(token);
}

Reasoning Streaming

All reasoning-capable providers (OpenAI, Claude, Gemini, Grok, DeepSeek) share the same streaming pattern:

await foreach (var content in service.StreamAsync(message, new StreamOptions().WithReasoning()))
{
    if (content.Type == StreamingContentType.Reasoning)
        Console.Write($"[Think] {content.Content}");
    else if (content.Type == StreamingContentType.Text)
        Console.Write(content.Content);
}

Function Calling

var service = new OpenAIService(apiKey, httpClient)
    .WithFunction(
        "get_weather",
        "Gets the current weather for a location",
        ("location", "The city and country", required: true),
        (string location) => $"The weather in {location} is sunny, 22C"
    );

var response = await service.GetCompletionAsync("What's the weather in Seoul?");

Structured Output (Basic)

// Deserialize LLM responses directly into C# POCOs with auto-recovery
var result = await service.GetCompletionAsync<WeatherResponse>(
    "What's the weather in Seoul?");

Structured Output (List)

// Collection types work directly — no wrapper DTO needed
var items = await service.GetCompletionAsync<List<ItemDto>>(
    "Extract all entities from this document...");

Structured Output (Streaming)

// Stream text chunks in real-time + get final deserialized object
var run = service.BeginStream(prompt).As<MyDto>();

await foreach (var chunk in run.Stream())
    Console.Write(chunk);          // real-time UI

MyDto dto = await run.Result;      // parsed & auto-repaired

Conversation Summary Policy

// Automatically summarize old messages when conversation gets long
service.ConversationPolicy = SummaryConversationPolicy.ByMessage(
    triggerCount: 20,
    keepRecentCount: 5
);

// Token-based trigger
service.ConversationPolicy = SummaryConversationPolicy.ByToken(
    triggerTokens: 3000,
    keepRecentTokens: 1000
);

// Just use as normal — summarization happens automatically
await service.GetCompletionAsync("Continue our conversation...");

// For streaming, call summarization explicitly before StreamAsync()
await service.ApplySummaryPolicyIfNeededAsync();
await foreach (var chunk in service.StreamAsync("Continue..."))
    Console.Write(chunk.Content);

// Save/restore summary across sessions
string saved = service.ConversationPolicy.CurrentSummary;
policy.LoadSummary(saved);

RAG (Retrieval-Augmented Generation)

dotnet add package Mythosia.AI.Rag

using Mythosia.AI.Rag;

var service = new AnthropicService(apiKey, httpClient)
    .WithRag(rag => rag
        .AddDocument("manual.txt")
        .AddDocument("policy.txt")
    );

var response = await service.GetCompletionAsync("What is the refund policy?");

For agent-controlled retrieval, register the store with WithAgenticRag(...) and run either RunAgentAsync(...) or RunAgentStreamAsync(...). See Mythosia.AI.Rag README for full examples.

Supported Providers

Provider	Package	Models
OpenAI	Mythosia.AI	GPT-5.5 / 5.5 Pro / 5.4 / 5.4 Mini / 5.4 Nano / 5.4 Pro / 5.3 Codex / 5.2 / 5.2 Pro / 5.2 Codex / 5.1 / 5 / 5 Pro / 5 Mini / 5 Nano, GPT-4.1 / 4.1 Mini / 4.1 Nano, GPT-4o / 4o Mini, o3 / o3 Pro
Anthropic	Mythosia.AI	Claude Opus 4.8 / 4.7 / 4.6 / 4.5 / 4.1 / 4, Sonnet 4.6 / 4.5, Haiku 4.5
Google	Mythosia.AI	Gemini 3.1 Pro Preview, Gemini 3.5 Flash, Gemini 3 Flash Preview, Gemini 3.1 Flash-Lite, Gemini 2.5 Pro/Flash/Flash-Lite
xAI	Mythosia.AI	Grok 4.3, Grok 4.20 (reasoning / non-reasoning), Grok Build 0.1, Grok 3 Mini
DeepSeek	Mythosia.AI	Chat, Reasoner
Perplexity	Mythosia.AI	Sonar, Sonar Pro, Sonar Reasoning Pro
Alibaba / Qwen	Mythosia.AI.Providers.Alibaba	Qwen Max / Plus / Turbo / Qwen3 / Qwen3.5 variants

Packages

Core

Package	NuGet	Description
Mythosia.AI		Core library — built-in providers, streaming, function calling, and multimodal support
Mythosia.AI.Abstractions		IAIService interface and shared models — lightweight contract package for libraries
Mythosia.AI.Providers.Alibaba		Alibaba / Qwen provider package built on top of Mythosia.AI

RAG

Package	NuGet	Description
Mythosia.AI.Rag		Fluent RAG extension for IAIService with .WithRag() API
Mythosia.AI.Rag.Abstractions		Interfaces and models for RAG pipeline components

Document Loaders

Package	NuGet	Description
Mythosia.Documents.Abstractions		Document loader interfaces and models (IDocumentLoader, DoclingDocument)
Mythosia.Documents.Office		OpenXml parsers for Word / Excel / PowerPoint
Mythosia.Documents.Pdf		PDF parser via PdfPig

Vector Stores

Pick one or more — all implement IVectorStore from the Abstractions package.

Package	NuGet	Description
Mythosia.VectorDb.Abstractions		IVectorStore · VectorRecord · VectorFilter contracts
Mythosia.VectorDb.InMemory		In-memory store — zero infrastructure, great for prototyping
Mythosia.VectorDb.Pinecone		Pinecone HTTP API — index/namespace/scope isolation for managed vector DB
Mythosia.VectorDb.Postgres		PostgreSQL + pgvector — HNSW / IVFFlat indexes, production-ready
Mythosia.VectorDb.Qdrant		Qdrant gRPC client — Cosine / Euclidean / Dot, auto-provisioning

Repository Structure

src/
  core/
    Mythosia.AI/                        # Core AI service library
    Mythosia.AI.Abstractions/           # IAIService interface and shared models
    Mythosia.AI.Providers.Alibaba/      # Alibaba / Qwen provider package
  loaders/
    Mythosia.Documents.Abstractions/    # Document loader contracts (IDocumentLoader, DoclingDocument)
    Mythosia.Documents.Office/          # Office document loaders (Word/Excel/PowerPoint)
    Mythosia.Documents.Pdf/             # PDF document loader
  rag/
    Mythosia.AI.Rag/                    # RAG fluent API and pipeline
    Mythosia.AI.Rag.Abstractions/       # RAG interfaces and models (RagDocument)
  vectordb/
    Mythosia.VectorDb.Abstractions/     # Vector store contracts
    Mythosia.VectorDb.InMemory/         # In-memory vector store
    Mythosia.VectorDb.Pinecone/         # Pinecone vector store
    Mythosia.VectorDb.Postgres/         # PostgreSQL + pgvector store
    Mythosia.VectorDb.Qdrant/           # Qdrant vector store
apps/                                   # Applications (samples & tools)
tests/                                  # Unit/integration test projects

Installation

dotnet add package Mythosia.AI

For advanced LINQ operations with streams:

dotnet add package System.Linq.Async

Documentation

• 📖 Full Documentation Site — DocFX-generated docs covering all features, RAG pipeline, vector stores, and API reference
• Basic Usage Guide
• Mythosia.AI README Full API reference with function calling, streaming, and model configuration
• Mythosia.AI.Rag README RAG pipeline usage and custom implementations
• Document Loaders
• Release Notes

License

This project is licensed under the MIT License.

Originally

This project was originally part of Mythosia.