WeAreDevelopers LIVE • Apr 15, 2025

Martin O'Hanlon - Make LLMs make sense with GraphRAG

Martin O'hanlon

Martin O'Hanlon argues vector embeddings alone cannot stop AI hallucinations. Discover how GraphRAG acts as your LLM's right brain, injecting deterministic truth into unstructured workflows.

Pause

Mute

Enter Fullscreen

#1 about 3 min

Hallucinations and factual inaccuracies in generative language models

Generative models frequently fabricate information and present it as undisputed truth when lacking access to private or updated data.

#2 about 5 min

Demonstrating language model hallucinations with custom system prompts

Injecting structured localized data into system prompts constrains conversational outputs and meaningfully reduces model hallucinations.

#3 about 3 min

Enhancing model accuracy with retrieval augmented generation patterns

Pairing language features with robust data retrieval architectures seamlessly grounds generated text in verifiable domain facts.

#4 about 5 min

Structuring connected data using graph database architectural fundamentals

Graph databases optimally organize complex ecosystems using systematically interconnected nodes and explicit relationship properties.

#5 about 5 min

Limitations of vector embeddings for precise factual querying

While vector embeddings streamline fuzzy semantic searches, they consistently struggle to reliably resolve strict arithmetic or fact-oriented constraints.

#6 about 6 min

Integrating knowledge graphs to provide verified application context

Mapping unstructured enterprise information into explicit factual networks empowers language applications to correctly evaluate nuanced logical conditions.

#7 about 2 min

Implementing graph generation and automated contextual querying methodologies

Automated extraction utilities effectively synthesize unstructured text into traversable databases to continuously supply contextual data pipelines.

Matching moments

2:26 min

Enhancing language models with graph retrieval augmented generation

1:44 min

Introduction to generative AI and knowledge graphs

Michael Hunger

Michael Hunger · WWC 2024

2:05 min

Enhancing language models with retrieval-augmented generation

Mary Grygleski

Mary Grygleski · LIVE

2:22 min

Unlocking generative AI capabilities using knowledge graphs

Zaid Zaim

Zaid Zaim +1 · WWC Europe 2026

3:29 min

Mitigating artificial intelligence hallucinations with constraints and context

Jemiah Sius

Jemiah Sius · WWC 2024

1:53 min

Overcoming language model challenges using retrieval-augmented generation

Ashish Sharma · LIVE

More from WeAreDevelopers LIVE

Aliens in Quarantine, Python Deprecates Loops, and AI Buys Old Books - Zbyszek Tenerowicz thumbnail

Aliens in Quarantine, Python Deprecates Loops, and AI Buys Old Books - Zbyszek Tenerowicz

Chris Heilmann, Daniel Cranney

WeAreDevelopers LIVE - Node and Package Security thumbnail

WeAreDevelopers LIVE - Node and Package Security

Chris Heilmann, Daniel Cranney, Zbyszek Tenerowicz

WeAreDevelopers LIVE - Streaming HTML thumbnail

WeAreDevelopers LIVE - Streaming HTML

Chris Heilmann, Daniel Cranney, Jad Joubran

WeAreDevelopers LIVE - CODE100 at WeAreDevelopers Europe thumbnail

WeAreDevelopers LIVE - CODE100 at WeAreDevelopers Europe

Chris Heilmann, Daniel Cranney, Justin Halsall, Werner Jeschko, Nicole Jeschko, Mirco Tomić

WeAreDevelopers LIVE - Web Performance in an AI World thumbnail

WeAreDevelopers LIVE - Web Performance in an AI World

Chris Heilmann, Daniel Cranney

FIFA Hack, Midjourney Does Ultrasounds, and Trampoline Traffic Lights - Nicole Jeschko and Werner Jeschko thumbnail

about 2 months ago

FIFA Hack, Midjourney Does Ultrasounds, and Trampoline Traffic Lights - Nicole Jeschko and Werner Jeschko

Chris Heilmann, Daniel Cranney

Upcoming sessions on this topic

World Congress 2026 North America

Building World-Aware Robots with Agent Memory and Context Graphs

Zaid Zaim

Developer Advocate EMEA at Neo4j | Microsoft AI MVP

Zaid Zaim

World Congress 2026 North America

Building Stuff with GenAI - The Open Minded Workshop beyond OpenAI

Andreas Erben

CTO for Applied AI and Metaverse at daenet

Andreas Erben

World Congress 2026 North America

Understanding LLM Architectures: Inside the Design of Modern Models

Jofia Jose Prakash

Enterprise AI Architect at American Chemical Society

Jofia Jose Prakash

World Congress 2026 North America

You Can’t Re-Run Sunlight: Designing ML Data Architectures for Physical AI

An Phan

Senior Data Infrastructure Engineer @ Hippo Harvest

An Phan

World Congress 2026 North America

DeepAgents: Build Multi-Agent AI Systems That Actually Work

Anjana Umapathy, Apoorva Jaiswal, Anagha Rumade

Anjana Umapathy

Apoorva Jaiswal

Anagha Rumade

World Congress 2026 North America

No Single Model to Rule Them All: Building Resilient AI Agents Across Open & Closed LLMs

Emmanuel Acheampong

Senior Manager Developer Relations at Crusoe AI

Emmanuel Acheampong

Related videos

Large Language Models ❤️ Knowledge Graphs thumbnail

WWC 2024 • almost 2 years ago

Large Language Models ❤️ Knowledge Graphs

Michael Hunger

Scaling GraphRAG: Efficient Knowledge Retrieval for AI thumbnail

WWC Europe 2026 • about 1 month ago

Scaling GraphRAG: Efficient Knowledge Retrieval for AI

Gal Shubeli

Give Your LLMs a Left Brain thumbnail

WWC 2024 • almost 2 years ago

Give Your LLMs a Left Brain

Stephen Chin

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

over 1 year ago

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

Knowledge graph based chatbot thumbnail

WWC 2023 • almost 3 years ago

Knowledge graph based chatbot

Tomaz Bratanic

Building Blocks of RAG: From Understanding to Implementation thumbnail

LIVE • over 1 year ago

Building Blocks of RAG: From Understanding to Implementation

Ashish Sharma

Related articles

MH

Michael Hunger

N

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 ow...

7 months ago

An abstract image of nodes representing a graph database

MH

Michael Hunger

CH

Chris Heilmann

Everything a Developer Needs to Know About MCP with Neo4j

In the rapidly evolving world of AI tooling and agentic workflows, one protocol is reshaping how developers build, scale, and share AI-native applications: the Model Context Protocol (MCP). If you’...

about 1 year ago

The Model Context Protocol with Neo4j (MCP for Al Agent memory and Integration

DC

Daniel Cranney

ChatGPT on AI Hallucinations: Can It Fix Its Own Mistakes?

Most of us use AI daily—whether summarizing text, organizing tasks, suggesting recipes, or even translating languages in real time. As AI chatbots become more integrated into our lives, we increasi...

over 1 year ago

A ChatGPT-style interface with the prompt 'Please give me some advice about how to handle AI hallucinations'

CH

Chris Heilmann

WWC24 Talk - Scott Hanselman - AI: Superhero or Supervillain?

Join Scott Hanselman at WWC24 to explore AI's role as a superhero or supervillain. Scott shares his 32 years of experience in software engineering, discusses AI myths, ethical dilemmas, and tech ad...

almost 2 years ago

WWC24 Talk - Scott Hanselman - AI: Superhero or Supervillain?

From learning to earning

Jobs that call for the skills explored in this talk.

15 days ago • Verified

AI Software Engineer (Germany)

Berlin, Germany

Expert €70k–100k Remote REST TypeScript AI Frameworks

29 days ago • Verified

AI & Machine Learning Engineer (all genders)

Frankfurt am Main, Germany

Experienced Remote Python Langchain Machine Learning

Data Scientist

Berlin, Germany

€80k–200k Airflow Terraform Kubernetes

Staff Developer Advocate, GitHub Security Lab

Experienced $121k–323k Remote Git Github Databases

Head of AI Applications

Oberkochen, Germany

Expert Git SBus DevOps

about 2 months ago • Verified

Senior AI Agent Software Engineer (Go, Python) (m/f/x)

Vienna, Austria

Experienced €61k–76k Remote Go Python AI Frameworks