Michael Hunger

Aug 22, 2024 • World Congress 2024

Large Language Models ❤️ Knowledge Graphs

LLMs are trained to be helpful, not factual. Learn to stop hallucinations by grounding them in a knowledge graph, creating AI you can actually trust.

#1about 3 minutes

Addressing the key challenges of large language models

LLMs often hallucinate or lack access to private data because they are trained to be helpful, not necessarily factual.

#2about 2 minutes

Using Retrieval Augmented Generation to ground LLMs

The RAG pattern improves LLM accuracy by first retrieving relevant information from a database to provide as context for the answer.

#3about 4 minutes

Representing complex data with knowledge graphs

Knowledge graphs model data as a network of entities and relationships, making complex connections intuitive and easy to query.

#4about 3 minutes

Using LLMs to build a knowledge graph from text

LLMs can automatically extract structured entities and relationships from unstructured documents to populate a knowledge graph.

#5about 3 minutes

Demo of extracting conference data into a graph

An application ingests a conference agenda and uses an LLM to automatically build a knowledge graph of speakers and their talks.

#6about 3 minutes

Combining vector and graph search with GraphRAG

The GraphRAG pattern uses vector search to find entry points into the graph and then traverses relationships to gather richer, more relevant context.

#7about 5 minutes

Code demo of querying a graph with LangChain

A Jupyter notebook demonstrates how to use LangChain and Neo4j to execute a GraphRAG query that avoids LLM hallucinations.

#8about 3 minutes

Benefits and traceability of the GraphRAG approach

This approach provides rich context, enables explainability by tracing data sources, and allows for graph enrichment with clustering algorithms.

#9about 2 minutes

How to control and validate graph extraction quality

You can guide the LLM's extraction process with a predefined schema and validate its output against a human-created baseline for accuracy.

Name of

Remote

Intermediate

PHP

Java

Andrew Comp
Cosio Valtellino, Italy

Intermediate

TypeScript

Cards Co

Remote

Intermediate

JavaScript

TypeScript

From learning to earning

Jobs that call for the skills explored in this talk.

NLP People
Municipality of Madrid, Spain

Senior

Machine Learning

AI Engineer - Schwerpunkt Generative KI Systeme

Thalia Thalia

GIT

Docker

PyTorch

Tensorflow

Kubernetes

4Com GmbH & Co. KG

Docker

GraphQL

Kubernetes

Data analysis

Machine Learning

Understanding Recruitment Group
Barcelona, Spain

Remote

Node.js

Computer Vision

Machine Learning

Senior AI / Data Science Engineer mit Erfahrung im Bereich LLM

auteega GmbH

Senior

NoSQL

DevOps

Docker

MongoDB

PostgreSQL

Merantix AG

Machine Learning

Deutsches Medizinrechenzentrum GmbH

Remote

DevOps

Microservices

Machine Learning

Continuous Integration

Deloitte

Machine Learning

Deloitte

DevOps

Docker

PyTorch

Tensorflow

Kubernetes

Addressing the key challenges of large language models

Using Retrieval Augmented Generation to ground LLMs

Representing complex data with knowledge graphs

Using LLMs to build a knowledge graph from text

Demo of extracting conference data into a graph

Combining vector and graph search with GraphRAG

Code demo of querying a graph with LangChain

Benefits and traceability of the GraphRAG approach

How to control and validate graph extraction quality

Remote

Typescript developer

Typescript developer

Matching moments

Understanding retrieval-augmented generation (RAG)

Exploring LLMs across clouds

Introducing retrieval-augmented generation (RAG)

Martin O'Hanlon - Make LLMs make sense with GraphRAG

Why large language models need retrieval augmented generation

Build RAG from Scratch

Introducing retrieval-augmented generation to improve accuracy

Knowledge graph based chatbot

Powering real-time AI with retrieval augmented generation

Scrape, Train, Predict: The Lifecycle of Data for AI Applications

Using RAG to enrich LLMs with proprietary data

RAG like a hero with Docling

Understanding retrieval-augmented generation systems

AI Model Management Life Circles: ML Ops For Generative AI Models From Research to Deployment

Addressing the core challenges of large language models

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

Featured Partners

Related Videos

Knowledge graph based chatbot

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

Carl Lapierre - Exploring Advanced Patterns in Retrieval-Augmented Generation

Building Blocks of RAG: From Understanding to Implementation

Lies, Damned Lies and Large Language Models

Creating Industry ready solutions with LLM Models

Unlocking the Power of AI: Accessible Language Model Tuning for All

Martin O'Hanlon - Make LLMs make sense with GraphRAG

Related Articles

From learning to earning

Machine Learning Expert (Llms)

AI Engineer - Schwerpunkt Generative KI Systeme

AI Knowledge Base Developer

Machine Learning Ops Engineer

Senior AI / Data Science Engineer mit Erfahrung im Bereich LLM

AI Solution Architect

Machine Learning Engineer - AI-Features, Agenten & Multi Agenten Workflows

Conversational AI & Machine Learning Engineer

Conversational AI & Machine Learning Engineer