Image from [GraphRAG](https://github.com/microsoft/graphrag/blob/e7ee8cb8a53b0ca423158e0acf54f143b4938e2a/docsite/img/GraphRag-Figure1.jpg) and [Ollama](https://github.com/ollama/ollama/issues/2152)

GraphRAG Local Setup via Ollama: Pitfalls Prevention Guide

TL;DR If you just want to see the conclusion, skip to the Summary . Please note that the content discussed here is only guaranteed to work for version 0.3.2. Other versions have not been tested. Introduction GraphRAG is a new Retrieval-Augmented Generation (RAG) technology released by Microsoft. Unlike the usual RAG approach, which breaks text into chunks, vectorizes them, and stores them in a vector store, and then compares the similarity by vectorizing the user’s query, GraphRAG extracts information from text and builds a Knowledge Graph. This approach has the advantage of better understanding the complex relationships between different documents. ...

Posted on: 2024-09-11 · Edited on: 2024-09-13 · Chi-Sheng Liu