Martin O'Hanlon

Apr 15, 2025 • WeAreDevelopers LIVE

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'.

#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.

Understanding the problem of LLM hallucinations

Demonstrating how context can ground LLM responses

Introducing retrieval-augmented generation (RAG)

Understanding the fundamentals of graph databases

Using graphs for specific, fact-based queries

Demonstrating GraphRAG with a practical example

Summarizing the two main uses of GraphRAG

Matching moments

Using Graph RAG for superior context retrieval

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

Understanding retrieval-augmented generation (RAG)

Exploring LLMs across clouds

Comparing LLM, vector search, and graph RAG approaches

Give Your LLMs a Left Brain

Using knowledge graphs to give LLMs a left brain

Give Your LLMs a Left Brain

Using RAG to enrich LLMs with proprietary data

RAG like a hero with Docling

Understanding LLMs, context windows, and RAG

Beyond Prompting: Building Scalable AI with Multi-Agent Systems and MCP

Solving LLM limitations with RAG and vector databases

Accelerating GenAI Development: Harnessing Astra DB Vector Store and Langflow for LLM-Powered Apps

Why large language models need retrieval augmented generation

Build RAG from Scratch

Featured Partners

Related Videos

How to Avoid LLM Pitfalls - Mete Atamel and Guillaume Laforge

Lies, Damned Lies and Large Language Models

Creating Industry ready solutions with LLM Models

Large Language Models ❤️ Knowledge Graphs

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

Give Your LLMs a Left Brain

Building Blocks of RAG: From Understanding to Implementation

Knowledge graph based chatbot

Related Articles

From learning to earning

(Senior) Data / Knowledge Engineers : Knowledge Graphs and Generative AI

(Senior) Researcher - Knowledge Graphs and Generative AI

ML Data Engineer - Object Detection & Active Learning

ML Data Engineer - Object Detection & Active Learning

Fullstack Web Entwickler - Next.js & AI

(Senior) Data / Knowledge Engineers : Knowledge Graphs and Generative AI

Machine Learning Expert (Llms)

Backend AI-Developer mit einer Prise MLOps

Machine Learning Ops Engineer