Michael Hunger - Large Language Models ❤️ Knowledge Graphs

#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.

2 days ago

Machine Learning Engineer

Picnic Technologies B.V.

Amsterdam, Netherlands

Intermediate

Senior

7 days ago

Senior Machine Learning Engineer (f/m/d)

MARKT-PILOT GmbH

Stuttgart, Germany

Remote

Senior

1 month ago

(Senior) Experte (w/m/d) Data & KI

Raven51 AG

Karlsruhe, Germany

Senior

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

Related Videos