# Why the Author Argues Knowledge Graphs Improve RAG Over Vector Stores

DevFeed: [Why the Author Argues Knowledge Graphs Improve RAG Over Vector Stores](<https://devfeed.tech/articles/vector-stores-are-dumb-33435.md>)

Original publisher: [Read original article](<https://timkellogg.me/blog/2024/08/12/graph-ai>)

Published: 2024-08-12T00:00:00Z

Content type: opinion

Language: en

Sources: [Tim Kellogg](<https://devfeed.tech/sources/tim-kellogg.md>)

Topics: [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [graph-database](<https://devfeed.tech/topics/graph-database.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>)

Tags: [embeddings](<https://devfeed.tech/tags/embeddings.md>), [knowledge-graphs](<https://devfeed.tech/tags/knowledge-graphs.md>), [openai](<https://devfeed.tech/tags/openai.md>), [rag](<https://devfeed.tech/tags/rag.md>), [redis](<https://devfeed.tech/tags/redis.md>)

## AI overview

The author argues that vector-based retrieval-augmented generation has limited utility because embeddings represent text as single points and chunking can lose context or mix unrelated ideas. The post proposes using knowledge graphs to represent ideas and relationships more structurally for RAG.

## Source excerpt

Vector stores are used to implement the RAG pattern, but they're of limited utility. In this post I explain why I think vector-based RAG is limited and why using knowledge graphs to implement RAG is better.