GraphRAG: LLM-Derived Knowledge Graphs for RAG

Watch my colleague Jonathan Larson present on GraphRAG!

GraphRAG is a research project from Microsoft exploring the use of knowledge graphs and large language models for enhanced retrieval augmented generation. It is an end-to-end system for richly understanding text-heavy datasets by combining text extraction, network analysis, LLM prompting, and summarization.


And follow me on other platforms so you’ll never miss out on my updates!

[alexchaomander]

What scenarios do you see GraphRAG being useful for?

[alexanderbrown-dgsy]

This is basically causal grounding. We figure semantic symbolic reasoning, from an architectural perspective. Add a powerful model…something very compelling AGI-like would be the result I would assume(plus mcts sampling lol). Causal grounding is huge hole in current models.

This is dope research. Kudos.

[jcourson]

I've been doing work in the area of creating knowledge graphs for codebases. The nice thing about generating them for code (as opposed to text) is that you don't have to rely on LLM calls to recognize and generate relationships, but you can utilize language servers and language parsers for that.

[lalamaxd]

glad, i didn't skip this and watched video, thanks for sharing knowledge. seems very impressive.

[peteredmonds]

this was so well explained, nicely done. my first thoughts:

1. i'd be curious to see benchmarks with cheaper LLMs. from my experience, even much smaller models like llama-3-8b can come close to gpt-4 in this use-case (entity extraction and relationships). a little fine-tuning could likely match or surpass gpt-4 for much cheaper.

2. i wonder how this could be augmented with datasources which already have some concept of relationships, ie wikipedia, dictionaries, hypertext.

[PsyoPhlux]

Pretty soon, everyone will be graphragging their podcasts. Jre will be neat.

[ChetanVashistth]

This seems very powerful. Thanks for sharing it and explaining it well.

[andydataguy]

That final streamlit app was awesome!!

[lifedownunderse]

I really enjoyed this video! What tool did you use to visualise the POD cast graph?

[mvasa]

While RAG is a good process for eliminating hallucinations, GraphRAG makes the retrieved context richer with its relationship-building techniques. The expense is worth it. Is the result set then re-graphed, or will the same query twice be as expensive?

[filippomarino]

This could be a game-changer in both public and private-sector intelligence analysis (as I am sure you figured out.) Looking forward to additional info - but what about the private dataset's format? Is it vectorized? If so, can we assume that there are optimal and sub-optimal approaches? (IOW, is it fair to assume vectorization can significantly impact GraphRAG's performance?)

[energyexecs]

Thanks for the video. I can see a Use Case in my energy industry. Does GraphRAG work across all "modes" and "modalities"?

[mrstephanwehner]

Is there no standard comparison approach? For example one could take academic literature reviews, collect their references, throw in some more, and ask the llm system. Compare the result with the original review. There might be summaries available in the accounting and legal world, that could be used also

[TomBielecki]

I really like the addition of hierarchical agglomerative summarization, which gives holistic aanswers similar to RAPTOR RAG strategy but with the better data representation of knowledge graphs. I'll need to read the paper to understand if embeddings are used at all in this, and whether relationships are labelled or if they just have a strength value.

[Mrbeastifed]

Is there an Open source implementation of this or how could I build it into my own app?

[JasonSun]

Seems like the video was incomplete. Is there another part

[sairajpednekar]

May I know the underlying technology used for hosting the graph database? Was it Cosmos db?

[heterotic]

How is this any different then Self Organizing Maps for RAG?

[escanoxiao]

fabulous work! wondering how long it takes to form a whole vector db and plus how many tokens will it take?

[phillipmaire]

Would love the opportunity to contribute to this project, super interesting.

How easy is it to update existing knowledge graphs periodically when new data comes in? Is there a “reindexing” cost?