My friend and Neo4j CTO @prathle has written an outstanding blog post that summarizes the recent buzz around GraphRAG, what we've learned from a year of helping users build systems with Knowledge Graphs + LLMs and where we believe the space is going.

Thread below. 👇🧵 There's been an explosion of research articles in the last few months discussing how to use Knowledge Graphs in RAG systems. For good reasons!

It turns out that building a knowledge graph of your data and using it in RAG gives you several powerful advantages.

1⃣ It gives you better answers to most if not ALL questions you might ask an LLM using normal vector-only RAG. That alone will be a huge driver of GraphRAG adoption.

2⃣ In addition to that, once you've created your Knowledge Graph you get easier development thanks to data being visible when building your app. Easier to build LLM-backed applications is a BIG DEAL and sorely needed in these non-deterministic systems.

3⃣A third major advantage is that graphs can be readily understood and reasoned upon by humans as well as machines. Building with GraphRAG is therefore easier, gives you better results, and -- this is a killer in many industries -- is explainable and auditable!

Let's look at each of those benefits in turn.

Ok, this is pretty crazy.

SQL has been the lingua franca of database querying since the dawn of time.

But for the first time in over three decades (!), ISO just published a NEW database query language called GQL -- the Graph Query Language! Prior to SQL, there were a bunch of different relational query languages. But the industry came together to create one unified query language so that vendors could compete not on syntax & lockin, but on the strength of their implementations.

The goal of GQL is the same.

In my NODES keynote today, we ran a live demo of a social app with more people nodes than FB (!), backed by a trillion+ relationship graph sharded across more than 1,000 servers, executing deep, complex graph queries that return in <20 ms.

And we open sourced it for the world. I've heard people claim that "Neo4j doesn't scale" for a decade.

There's some truth to that. Graph data IS hard to scale.

But they're probably not up to date with the new Fabric architecture in Neo4j 4 & Graph Native Sharding.

So we figured it was time to show what it can do.