OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Graphrag.net

Graphrag.net is a C#/.NET GraphRAG demo implementation using Microsoft Semantic Kernel. It provides a document pipeline that extracts graph entities and relationships, creates summaries and communities, and combines graph retrieval or community-level summaries to answer questions.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Graphrag.net — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it to study or prototype a .NET GraphRAG workflow when answers should draw on entities, relationships and themes across a document collection.

Who it is for

  • C# developers integrating graph-based retrieval-augmented generation into .NET applications.
  • Teams prototyping question answering across document collections.
  • Developers studying a GraphRAG pipeline, from document chunking and graph construction through community summarization and answer generation.

Documented uses

  • Split source documents into text chunks and extract entities and relationships.
  • Build and store graph nodes, edges and vectorized text.
  • Create graph communities and generate element, community and global summaries.
  • Retrieve related graph information and generate answers from graph context or community summaries.
  • Integrate the implementation into a .NET project through NuGet and dependency injection.
Before you choose

Requirements & limits

The repository identifies the project as open source under the Apache-2.0 license and documents NuGet integration.

  • The README positions the implementation as a demo for learning GraphRAG concepts.
  • The documented model interface follows the OpenAI API format; other model services need a custom Semantic Kernel implementation or an integration layer.
  • Configuration includes model and embedding settings, graph and vector storage, chunking and search parameters.
  • The documented web project includes text and file import, Q&A and graph viewing; the library can also be integrated into another .NET application.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Configure GraphRag.Net in a .NET application

Add the NuGet package, configure the documented services and register GraphRag.Net.

Before you start

  • A .NET application using Microsoft Semantic Kernel.
  • Configuration for an OpenAI-compatible model endpoint, chat model, embedding model, database connections, text chunking and graph search.

Steps

  1. Add the GraphRag.Net NuGet package to the project.

  2. Set the GraphOpenAI, TextChunker, GraphDBConnection and GraphSys configuration sections; configure GraphSearch as needed.

  3. Bind the documented configuration sections to their option types.

  4. Register GraphRag.Net with AddGraphRagNet after loading the configuration.

  5. If adjusting prompts, copy the web project's graphPlugins directory into the application and configure its files to copy to the output directory.

Expected outcome

The package and its documented configuration and dependency-injection setup are incorporated into the application.

Guide limitations

  • The README says the LLM interface currently supports the OpenAI API format; alternative model services require a custom implementation or an integration product.
  • This setup guidance does not establish that the application has been run or that a particular model or database configuration will work.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
shuyu-labs/GraphRag.Net · Official homepage title · retained in its source language
How we review sourcesSuggest a correction