Keynote - GraphRAG: The Definitive Guide - A Field Guide to Patterns, Trade-offs, and Production Systems
GraphRAG has quickly become a catch-all term for everything from graph-enhanced retrieval to Text2Cypher, agent memory, and community-based summarization. That is exciting, but it also creates confusion. When people say “use GraphRAG,” what do they actually mean, and which pattern fits which problem?
This talk gives AI engineers a practical map of the GraphRAG landscape. We start with the limits of vector-only RAG, especially when data is connected, multi-hop, dynamic, or needs to be explainable. From there, we break GraphRAG into a set of core building blocks: constructing knowledge graphs from structured and unstructured data, choosing among lexical, domain, and meta graphs, and applying retrieval patterns such as guided traversal, graph-filtered search, Cypher templates, Text2Cypher, graph embeddings, query-focused summarization, and agentic retrieval.
The goal is not to present GraphRAG as one recipe, but as a toolbox with clear trade-offs. We will show when a lightweight pattern is enough, when a richer graph model pays off, and how to think about evaluation, governance, and production readiness from the start. Attendees will leave with a working mental model of GraphRAG, a taxonomy of the most useful patterns, and a decision framework for designing graph-powered GenAI systems that are accurate, explainable, and useful beyond the demo.
Generative AI gave us an abundance of content. Agentic AI is giving us something potentially more valuable, while also much more overwhelming: experience. Every tool call, coding session, workflow, decision, observation, and robot trajectory leaves behind another trace of what happened, what worked, and what didn't.
But accumulating raw piles of experience isn't the same as learning from it.
This talk explores an emerging layer in AI systems devoted not simply to storing context, but to distilling experience into durable, reusable knowledge. We'll connect ideas appearing across agent memory, semantic layers, knowledge bases, coding agents, context graphs, and even physical AI: resolving repeated observations into entities, discovering relationships and patterns, turning trajectories into reusable skills, and feeding what we've learned back into future action.
A number of knowledge primitives are competing for this layer, from the humble Markdown document and hypertext to vector embeddings, model weights, and knowledge graphs. Graphs, in particular, keep popping up. They may occupy a sweet spot: knowledge that is structured yet flexible, explicit and inspectable, portable across models and agent harnesses, and capable of generating other representations without surrendering the underlying structure. We'll pressure-test that claim, asking when the graph is useful, when it isn't, and whether increasingly capable models might eventually swallow the whole thing.
The last wave of AI was about generation. The next frontier may be about accumulation: building systems that don't just produce more experience, but get better at distilling what it means.
With RAG, you tap into a trusted data source at runtime to generate accurate LLM responses grounded in real-world information.
But RAG implementations tend to focus only on unstructured data rather than a structured source. Due to this, LLM responses might lack depth and nuance. You run a greater risk of hallucinations and providing incomplete information.
However, you can model your data with a knowledge graph, a technique called GraphRAG. This bridges structured and unstructured data to feed your LLM interconnected data. Your LLM gets the context needed to improve RAG performance, accuracy, and traceability.
Every Model Context Protocol (MCP) server you have to host comes with the same setup tax before you get to the actual work. You install a package or binary, edit a JSON configuration file, generate credentials, decide where to store them safely, restart the client, and hope the connection holds. That tax exists whether the server sits in front of a calendar, a filesystem, or a database, and it is infrastructure a developer has to run, get approved, and maintain just to let an AI client ask a question.
