Mar 19, 2025

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

Is your RAG system retrieving similar but contextually wrong information? Learn how Graph RAG leverages relationships to provide truly relevant answers.

#1about 3 minutes

Introducing Neo4j as a graph database company

Neo4j is a graph database company that has grown from a small open source project to a team of 800 people over 15 years.

#2about 2 minutes

Defining graphs with nodes and relationships

A graph database models data as nodes connected by relationships, which is more efficient than traditional relational database joins for certain queries.

#3about 3 minutes

Understanding Retrieval-Augmented Generation (RAG)

RAG enhances large language models by retrieving relevant external context from a database to augment the prompt before generating an answer.

#4about 4 minutes

Using Graph RAG for superior context retrieval

Graph RAG improves on standard RAG by using a knowledge graph to provide a distilled and highly focused context, reducing noise for the LLM.

#5about 7 minutes

Implementing Graph RAG and handling data challenges

Successfully implementing Graph RAG involves cleaning unstructured data and connecting it to business data, starting with a minimum viable graph that evolves over time.

#6about 2 minutes

Addressing data privacy and security in AI systems

Concerns about data leakage and privacy are driving companies to consider running their own local LLMs for greater control and governance.

#7about 4 minutes

The impact of open source models like DeepSeek

The rise of powerful open source LLMs like DeepSeek challenges the dominance of closed source models and changes the financial incentives in the AI industry.

#8about 5 minutes

The rise of local models and agentic systems

Smaller, specialized language models (SLMs) are enabling powerful, personalized agents that can run locally on devices like phones and watches.

#9about 4 minutes

Viewing agents as a software development pattern

Developers should view agents not as extensions of an LLM, but as a composable software design pattern for controlling and managing LLM capabilities.

#10about 4 minutes

Comparing Graph RAG with standard vector search RAG

While standard RAG uses vector similarity search, Graph RAG excels by connecting disparate pieces of information to provide crucial context that vector search often misses.

#11about 4 minutes

Why graphs can seem intimidating to developers

Graphs feel unfamiliar to many developers because they are not a native data structure in most programming languages, but pattern matching offers an intuitive way to work with them.

#12about 6 minutes

The future of AI tools and how to get started

AI tools will increasingly handle boilerplate code, and developers can start exploring graphs and GenAI by taking small, incremental steps without needing to learn everything at once.