 and [Ollama](https://github.com/ollama/ollama/issues/2152)](https://static.chishengliu.com/posts/graphrag-local-ollama/cover/cover.png)
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. ...
](https://static.chishengliu.com/posts/kubernetes-operator-introduction/cover/cover.png)
 on [Unsplash](https://unsplash.com/photos/a-computer-screen-with-a-bunch-of-code-on-it-ieic5Tq8YMk?utm_content=creditCopyText&utm_medium=referral&utm_source=unsplash)](https://static.chishengliu.com/posts/opensource-pre-contribution-tips/cover/cover.jpg)

 on [Unsplash](https://unsplash.com/photos/a-close-up-of-a-text-description-on-a-computer-screen-842ofHC6MaI?utm_content=creditCopyText&utm_medium=referral&utm_source=unsplash)](https://static.chishengliu.com/posts/opensource-git-operations/cover/cover.jpg)