Ananke.Orchestration.Knowledge 0.8.3

Ananke.Orchestration.Knowledge

Knowledge pipeline for Ananke — vector knowledge stores, document ingestion, chunking, embedding abstractions, knowledge catalogs, and optional cross-document linking.

Install

dotnet add package Ananke.Orchestration.Knowledge

Note: If you use Ananke.Orchestration, this package is already included as a transitive dependency.

Quick start

Semantic search

using Ananke.Orchestration.Knowledge;

// InMemoryKnowledgeStore for dev/test; QdrantKnowledgeStore for production
var store = new InMemoryKnowledgeStore(embeddingModel);

await store.UpsertAsync([
    new KnowledgeDocument { Id = "doc-1", Text = "Ananke is a .NET agent orchestration library." },
    new KnowledgeDocument { Id = "doc-2", Text = "Workflows are built with a fluent graph-as-code API." },
]);

var results = await store.SearchAsync("how do I build a workflow?");
// results[0].Text => "Workflows are built with a fluent graph-as-code API."

Document ingestion pipeline

using Ananke.Orchestration.Knowledge;
using Ananke.Orchestration.Knowledge.Documents;

var processor = new DocumentProcessor(
    new HttpClient(),
    [new PdfExtractor(), new MarkdownExtractor()],  // from Ananke.Documents
    new SlidingWindowChunker(),
    knowledgeStore);

await using var stream = File.OpenRead("architecture.pdf");
var result = await processor.ProcessAsync(stream, "application/pdf", sourceId: "arch-doc");
// result.ChunkCount => 42

Knowledge catalog (two-phase discovery)

using Ananke.Orchestration.Knowledge.Catalog;

var catalog = new InMemoryKnowledgeCatalog(embeddingModel);

// Wrap any store to auto-update catalog on upsert/delete
var catalogStore = new CatalogAwareKnowledgeStore(innerStore, catalog, enricher);

// Phase 1: discover relevant sources
var sources = await catalog.BrowseAsync(new CatalogBrowseOptions { Query = "deployment" });

// Phase 2: deep-search within matched sources
var chunks = await catalogStore.SearchAsync("kubernetes deployment", new SearchOptions
{
    Filter = new KnowledgeFilter { ["source"] = sources[0].Source }
});

Cross-document linking

using Ananke.Orchestration.Knowledge.Linking;

// Opt-in via DI — decorates IKnowledgeStore with graph-expanded search
services.AddKnowledgeLinking(options =>
{
    options.AutoLinkOnIngest = true;       // LLM-based post-ingestion linking
    options.SimilarityThreshold = 0.7f;    // link documents above this score
});

Key types

What this package is responsible for

• semantic search over embedded document chunks via IKnowledgeStore
• document ingestion via DocumentProcessor
• document-level discovery via IKnowledgeCatalog
• optional reranking and enrichment through CatalogAwareKnowledgeStore
• optional graph-expanded retrieval through LinkedKnowledgeStore
• grouping multiple stores plus one catalog through KnowledgeBase

This package does not depend on the workflow engine. It can be used independently in ingestion services, background jobs, and standalone search applications.

The pipeline

1. IDocumentExtractor.ExtractAsync(stream) → structured text + sections
2. IDocumentChunker.Chunk(text)            → DocumentChunk[]
3. IEmbeddingModel.EmbedBatchAsync(chunks) → float[][] vectors
4. IKnowledgeStore.UpsertAsync(documents)  → indexed in vector store
5. IKnowledgeStore.SearchAsync(query)      → ranked KnowledgeChunk[]

Optional enrichment layers compose via decoration:

IKnowledgeStore
  └─ CatalogAwareKnowledgeStore  (auto-catalogs on upsert)
      └─ LinkedKnowledgeStore    (graph-expanded search)

Package boundaries

• Ananke.Orchestration.Knowledge owns the knowledge, catalog, document, embedding, and linking contracts/implementations.
• Ananke.Documents supplies concrete extractors such as PdfExtractor and MarkdownExtractor.
• Ananke.Orchestration depends on this package and contains the bridge types that expose knowledge stores and catalogs as ToolKit tools.

This split allows vector-store and ingestion integrations to depend on the knowledge pipeline without pulling in workflow execution.

Implementations

Dependencies

• Ananke.Abstractions — for IAgentModel, IEmbeddingModel, and shared agent/message contracts
• Microsoft.Extensions.DependencyInjection.Abstractions — DI extension support
• Microsoft.Extensions.Logging.Abstractions — logging abstractions for processing components

This package has no dependency on Ananke.Orchestration — it is independent of the workflow engine.

Related packages

Documentation

Full docs, demos, and architecture: github.com/sevensamurai/Ananke

License

Apache 2.0