Martin O'Hanlon

Martin O'Hanlon - Make LLMs make sense with GraphRAG

How do you stop LLMs from making things up? By connecting them to a knowledge graph that acts as their factual 'left brain'.

Martin O'Hanlon - Make LLMs make sense with GraphRAG
#1about 2 minutes

Understanding the problem of LLM hallucinations

Large language models are powerful but often invent facts, a problem known as hallucination, which presents made-up information as truth.

#2about 5 minutes

Demonstrating how context can ground LLM responses

A live demo in the OpenAI playground shows how an LLM hallucinates a weather report but provides a factual response when given context.

#3about 2 minutes

Introducing retrieval-augmented generation (RAG)

Retrieval-augmented generation is an architectural pattern that improves LLM outputs by augmenting the prompt with retrieved, factual information.

#4about 5 minutes

Understanding the fundamentals of graph databases

Graph databases like Neo4j model data using nodes for entities, labels for categorization, and relationships to represent connections between them.

#5about 6 minutes

Using graphs for specific, fact-based queries

While vector embeddings are good for fuzzy matching, knowledge graphs excel at providing context for highly specific, fact-based questions.

#6about 3 minutes

Demonstrating GraphRAG with a practical example

A live demo shows how adding factual context from a knowledge graph, such as a beach closure, dramatically improves the LLM's recommendation.

#7about 2 minutes

Summarizing the two main uses of GraphRAG

GraphRAG serves two key purposes: extracting entities from unstructured text to build a knowledge graph and using that graph to provide better context for LLMs.

Related jobs
Jobs that call for the skills explored in this talk.

Machine Learning Engineer

Picnic Technologies B.V.

Picnic Technologies B.V.
Amsterdam, Netherlands

Intermediate
Senior
Python
Structured Query Language (SQL)
+1

Matching moments

Unlocking LLM potential with creative prompting techniques
04:59 MIN

Unlocking LLM potential with creative prompting techniques

WeAreDevelopers LIVE – Frontend Inspirations, Web Standards and more

Increasing the value of talk recordings post-event
04:57 MIN

Increasing the value of talk recordings post-event

Cat Herding with Lions and Tigers - Christian Heilmann

Writing authentic content in the age of LLMs
07:43 MIN

Writing authentic content in the age of LLMs

Slopquatting, API Keys, Fun with Fonts, Recruiters vs AI and more - The Best of LIVE 2025 - Part 2

Prompt injection as an unsolved AI security problem
07:39 MIN

Prompt injection as an unsolved AI security problem

AI in the Open and in Browsers - Tarek Ziadé

The hardware requirements for running LLMs locally
03:55 MIN

The hardware requirements for running LLMs locally

AI in the Open and in Browsers - Tarek Ziadé

Building and iterating on an LLM-powered product
05:03 MIN

Building and iterating on an LLM-powered product

Slopquatting, API Keys, Fun with Fonts, Recruiters vs AI and more - The Best of LIVE 2025 - Part 2

Playing a game of real or fake tech headlines
04:17 MIN

Playing a game of real or fake tech headlines

WeAreDevelopers LIVE – You Don’t Need JavaScript, Modern CSS and More

Exploring the role and ethics of AI in gaming
14:06 MIN

Exploring the role and ethics of AI in gaming

Devs vs. Marketers, COBOL and Copilot, Make Live Coding Easy and more - The Best of LIVE 2025 - Part 3

Featured Partners

Related Videos

See all videos
Large Language Models ❤️ Knowledge Graphs29:11

Large Language Models ❤️ Knowledge Graphs

Michael Hunger

Graphs and RAGs Everywhere... But What Are They? - Andreas Kollegger - Neo4j46:51

Graphs and RAGs Everywhere... But What Are They? - Andreas Kollegger - Neo4j

Give Your LLMs a Left Brain27:35

Give Your LLMs a Left Brain

Stephen Chin

Knowledge graph based chatbot24:44

Knowledge graph based chatbot

Tomaz Bratanic

Building Blocks of RAG: From Understanding to Implementation26:25

Building Blocks of RAG: From Understanding to Implementation

Ashish Sharma

Carl Lapierre - Exploring Advanced Patterns in Retrieval-Augmented Generation21:17

Carl Lapierre - Exploring Advanced Patterns in Retrieval-Augmented Generation

Carl Lapierre

How to Avoid LLM Pitfalls - Mete Atamel and Guillaume Laforge42:26

How to Avoid LLM Pitfalls - Mete Atamel and Guillaume Laforge

Meta Atamel & Guillaume Laforge

Build RAG from Scratch28:04

Build RAG from Scratch

Phil Nash

Related Articles

View all articles
CH
Chris Heilmann
With AIs wide open - WeAreDevelopers at All Things Open 2025
Last week our VP of Developer Relations, Chris Heilmann, flew to Raleigh, North Carolina to present at All Things Open . An excellent event he had spoken at a few times in the past and this being the “Lucky 13” edition, he didn’t hesitate to come and...
With AIs wide open - WeAreDevelopers at All Things Open 2025
MH
Michael Hunger, Neo4j
Graph and AI Trends 2026: Why Is AI Running but Not Yet Delivering?
After a few intense years of building with AI, many teams are asking the same question: Where is the ROI? We’re shipping chatbots, copilots, and agents . But: Agents aren’t autonomous enough to own end‑to‑end workflows. Model quality degrades over t...
Graph and AI Trends 2026: Why Is AI Running but Not Yet Delivering?
DC
Daniel Cranney
Dev Digest 160: Graphs and RAGs Explained and VS Code Extension Hacks
Inside last week’s Dev Digest 160 . 🤖 How AI is reshaping UI and work 🚀 Tips on how to use Cursor most efficiently 🔒 How VS Code extensions can be a massive security issue 👩‍💻 What the move to Go for Typescript means for developers 👎 What a possible...
Dev Digest 160: Graphs and RAGs Explained and VS Code Extension Hacks

From learning to earning

Jobs that call for the skills explored in this talk.