Ananke.Documents
0.1.0
dotnet add package Ananke.Documents --version 0.1.0
NuGet\Install-Package Ananke.Documents -Version 0.1.0
<PackageReference Include="Ananke.Documents" Version="0.1.0" />
<PackageVersion Include="Ananke.Documents" Version="0.1.0" />
<PackageReference Include="Ananke.Documents" />
paket add Ananke.Documents --version 0.1.0
#r "nuget: Ananke.Documents, 0.1.0"
#:package Ananke.Documents@0.1.0
#addin nuget:?package=Ananke.Documents&version=0.1.0
#tool nuget:?package=Ananke.Documents&version=0.1.0
Ananke.Documents
Document extractors for the Ananke knowledge pipeline — IDocumentExtractor implementations for PDF and Markdown that feed into DocumentProcessor for ingestion, chunking, embedding, and vector storage.
Install
dotnet add package Ananke.Documents
Quick start
using Ananke.Orchestration.Knowledge;
using Ananke.Documents;
var embeddingModel = OpenAIEmbeddingModel.Create(apiKey);
var knowledgeStore = new InMemoryKnowledgeStore(embeddingModel);
var processor = new DocumentProcessor(
new HttpClient(),
[new PdfExtractor(), new MarkdownExtractor()],
new SlidingWindowChunker(),
knowledgeStore);
// Extract, chunk, embed, and store in one call
await using var pdf = File.OpenRead("design-patterns.pdf");
var result = await processor.ProcessAsync(pdf, "application/pdf", "design-patterns");
// result => "8 sections, 42 chunks stored"
Extractors
| Class | Input | What it does |
|---|---|---|
PdfExtractor |
application/pdf |
Extracts text from PDF files using PdfPig, preserving headings, links, and structure as Markdown |
MarkdownExtractor |
text/markdown, text/plain |
Parses Markdown structure into normalized sections suitable for chunking |
Both implement IDocumentExtractor — you can add your own by implementing the same interface.
The pipeline
DocumentProcessor orchestrates the full ingest path:
Stream/URL → IDocumentExtractor → Markdown text
→ IDocumentChunker → text chunks
→ IEmbeddingModel → vector embeddings
→ IKnowledgeStore → stored + indexed
The same processor works from agent tool calls, background jobs, admin scripts, or HTTP endpoints.
Requirements
Ananke.Orchestration(transitive) — providesIDocumentExtractor,DocumentProcessor,IKnowledgeStore,SlidingWindowChunkerPdfPig≥ 0.1.13 (transitive)Markdig≥ 0.40.0 (transitive)
Related packages
| Package | What it adds |
|---|---|
Ananke.Orchestration |
Core knowledge pipeline: DocumentProcessor, IKnowledgeStore, InMemoryKnowledgeStore |
Ananke.Orchestration.OpenAI |
OpenAIEmbeddingModel for generating embeddings |
Ananke.Qdrant |
Qdrant-backed IKnowledgeStore for persistent, distributed storage |
Ananke |
Meta-package — includes everything |
Documentation
Full docs, demos, and architecture: github.com/sevensamurai/Ananke
License
| Product | Versions 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. |
-
net10.0
- Ananke.Orchestration (>= 0.1.0)
- Markdig (>= 1.0.1)
- PdfPig (>= 0.1.13)
NuGet packages
This package is not used by any NuGet packages.
GitHub repositories
This package is not used by any popular GitHub repositories.
| Version | Downloads | Last Updated |
|---|---|---|
| 0.1.0 | 39 | 3/3/2026 |