Teach on Udemy

Turn what you know into an opportunity and reach millions around the world.

Learn More

Your cart is empty.

Keep shopping

Neo4j: Cypher, GDS, GraphQL, LLM, Knowledge Graphs for RAG

Name: Neo4j: Cypher, GDS, GraphQL, LLM, Knowledge Graphs for RAG
Rating: 4.6 (235 reviews)

Hands-on Course on Neo4j, Cypher, GDS, GraphQL, GraphRAG and Building knowledge graph from unstructured data using LLM.

Created byCramlays, Nitin Gujral

Last updated 4/2026

English

English [Auto],

What you'll learn

Graph Database: Neo4j
Cypher Query Language: Beginner to Advanced Level
Neo4j and Graph Database Use Cases
Graph Data Science Library
Basic Overview of GraphQL
Overview of Bloom
Neo4j-AI Integration- Create Knowledge graph from Unstructured Data using Open AI LLM
Overview of RAG and Graph RAG - Knowledge graph as RAG

Course content

10 sections • 62 lectures • 2h 36m total length

Course Introduction3:31
Tips and Details to Get the Most Out of This Course0:26
Introduction to Neo4j: Understanding Graph Databases0:50
Industry Applications of Neo4j: Popular Use Cases1:37
Neo4j enables fraud detection, risk assessment, and compliance in banking and finance, and powers retail recommendations, telecom network mapping, healthcare insights, and supply chain optimization.
Where Neo4j Fits Among Various Database Types1:19
Explore the database landscape by contrasting relational databases with SQL and structured data against NoSQL categories, highlighting graph databases like Neo4j for managing complex data relationships.
Property Graph Model3:36
Explore the property graph model at the core of Neo4j, where nodes, relationships with direction and type, and properties enable flexible, schema-free data representation and dynamic querying.
Lab: Property Graph Model3:06
Lab: Neo4j Setup and Installation on Windows2:43
Lab: Explore Neo4j Browser and set up initial data3:05
How to Access the Neo4j Browser in Neo4j Desktop version 2.x0:45
Setting Up Neo4j: Your Options0:53
Download resources for all hands-on/lab exercises0:01
Download resources for all hands-on/lab exercises

Introduction to Cypher Query Language0:56
Lab: Basics of Cypher Query Language2:42
General syntax of Cypher Query Language (Optional)2:24
Lab: Filtering Techniques with Cypher Query Language3:33
Lab: Aggregation in Cypher Query Language – COUNT, AVG, MIN, MAX3:09
Explore aggregation in Cypher to summarize data using count, avg, min, max, and sum. Group movies by release year and identify the actor with the most movies.
Lab: CRUD Operations in Cypher Query Language3:17
Lab: MERGE, WITH, and RETURN3:49
Use merge to create or update nodes and relationships, preventing duplicates and maintaining data integrity. Chain queries using with clause; control results with return, aggregation, distinct, limit, and order by.
Lab: How to find the Shortest Path between nodes2:21
Important Point: Ordering in Neo4j1:27
Lab: Create multiple projects and DBMS in Neo4j Desktop3:05
Create and manage multiple projects and DBMs in Neo4j's desktop, organizing environments with independent DBMs that contain multiple databases.

Introduction to Graph Data Science Library1:41
Lab: Get started with Neo4j Sandbox and GDS Library2:20
Get started with Neo4j sandbox, import flight data, and use graph data science to analyze centrality, community detection, similarity search, and shortest path while visualizing the schema and airport–city–region–country–continent relationships.
Lab: How to use the Graph Data Science library2:16
Lab: Centrality Algorithm3:24
Apply the GDS PageRank on the projected roots graph to rank airports by influence, returning node id and PageRank scores, then write and query results by IATA code.
Lab: Community Detection Algorithm1:52
Detect communities in a graph with the Louvain algorithm on the roots projection, returning node and community ids, counting airports per community and listing distinct cities, then sorting by size.
Lab: Node Similarity Algorithm3:13
Explore airport node similarity using the node similarity algorithm to identify the most similar airports by neighborhood structure, returning city, IATA code, and similarity scores.
Lab: Path Finding Algorithm1:24

Overview of GraphQL1:21
Explore how GraphQL enables flexible API queries and how Neo4j converts GraphQL requests into Cypher queries, enabling seamless access to graph data.
Lab: GraphQL Part 1 - Setup GraphQL Toolbox provided by Neo4j1:27
Lab: GraphQL Part 2- Define GraphQL Schema2:11
Lab: GraphQL Part 3- Write GraphQL Query2:17
Write and run a GraphQL query to fetch movies with their actors, using schema and query editor; apply filters to return post-2000 releases and observe nested data.
Lab: GraphQL Part 4- Mutation in GraphQL2:34

Lab: How to install APOC and GDS Plugins2:21
Install Apoc and GDS plugins in Neo4j desktop, restart DBMs, and verify with help and version commands. Then review the Neo4j folder structure for plugins, CSV imports, and data.
Lab: Load Data from a CSV file3:42
Lab: Load Data from JSON file2:48
Optional Lab: Load JSON Data from Website Using Complex Cypher4:33
Bonus Lecture: Set Up and Install Neo4j Server Edition on Windows3:46
Install Neo4j server edition on Windows with Java 17, accept the license, and start the server; then access localhost:7474 to log in and explore the sample data and schema.
Bonus Lecture: Using Bloom for Visualization4:46
Explore graph data visualization with Neo4j bloom in a sandbox, import movie data, create a blank perspective, and use search, color labeling, and saved queries for exploration.
When Not to Use Neo4j: Understanding Its Limitations1:02

Memory Allocation Recommendations in Neo4j2:12
Allocate memory in Neo4j with a balance: Java heap about 40%, page cache 50 to 70%, and OS memory 10 to 20%. Configure via neo4j.conf for improved performance and queries.
Lab: Using PROFILE and INDEX for Performance Tuning2:29
Best Practices for Writing Optimized Queries2:26
Learn best practices for writing optimized Cypher queries in Neo4j, including using indexes and constraints, profiling with explain, limiting scope, unwinding large collections, and efficient traversal.

(Optional) Quick Introductory Lecture on Generative AI for Beginners3:57
Discover what generative AI is, why it matters, and how it creates new content from text to images using patterns learned from large data sets.
Introduction to Large Language Models (LLMs) for Generative AI2:22
Explore what large language models are, how they generate language, and popular examples like GPT, Bert, Llama, and Claude, highlighting their language understanding and generative capabilities.
Building a Knowledge Graph from Unstructured Data Using LLMs2:06
Learn to build a knowledge graph from unstructured data by using a large language model for named entity recognition, extract entities and relationships, and store the graph in Neo4j.
Lab: Build KG from Unstructured Data with LLMs – Part 1: OpenAI API Key2:23
Lab: Build KG from Unstructured Data with LLMs – Part 2: Set Up Neo4j on Sandbox1:23
Lab: Build KG from Unstructured Data with LLMs – Part 3: Set Up Colab for Python1:18
Lab: Build KG from Unstructured Data with LLMs – Part 4: Python Code3:53
Lab: Build KG from Unstructured Data with LLMs – Part 5: Python Code3:04
Lab: Build KG from Unstructured Data with LLMs – Part 6: Python Code4:29
Fetch and parse Wikipedia text using the Wikipedia API library, extract entities from the artificial intelligence page, and prepare clean entity data for relationship creation in a knowledge graph.
Lab: Build KG from Unstructured Data with LLMs – Last Part: Summary3:03
Introduction to the RAG Technique (Retrieval-Augmented Generation)3:14
Explore retrieval-augmented generation, a hybrid approach that combines llms with retrieval systems to generate responses enriched with relevant, up-to-date information from external sources.
GraphRAG: Using Knowledge Graphs for RAG3:06
Graph Rag blends retrieval augmented generation with graph databases like Neo4j to enable context-rich retrieval from a knowledge graph of interconnected entities, outperforming vector databases when relationships matter for recommendations.
Step-by-Step Python Code: Knowledge Graph for RAG0:55

Requirements

Basic Knowledge of Databases and Querying
Basics of Python Programming

Description

Kindly note:

1. Demos are recorded on Windows only.

2. This course includes mostly practical use cases, datasets, and queries that are available on the official Neo4j Sandbox website. The objective is to guide you through these complex Cypher queries & concepts in an easy and time-efficient manner.

3. This course does not cover the basics of Python programming.

3. Python knowledge is required (only for the labs in Sections 8 and 9)

Course Update:

Nov 2024 - Two New sections added:

Section 8: Iteracting Neo4j from Python Program

Section 9: Emerging Trends in Neo4j and AI Integration: LLMs and GraphRAG

Welcome to "Knowledge Graph with Neo4j, Cypher, and GDS"! This comprehensive course is your gateway to mastering the powerful world of graph databases, a cutting-edge technology reshaping how we handle complex data relationships. Designed for data enthusiasts, developers, and anyone keen on exploring the frontier of data technology, this course will equip you with the skills to build and query robust knowledge graphs using Neo4j.

We begin our journey with an Introduction to Neo4j, diving into what makes graph databases unique and essential for modern data challenges. You'll learn about the architecture and core features of Neo4j, setting a solid foundation for your learning.

Next, we delve into Industry Applications of Neo4j. Through real-world case studies, you'll see how Neo4j is revolutionizing various industries, from finance to healthcare, showcasing its versatility and impact.

Understanding where Neo4j fits in the data ecosystem is crucial, so we’ll explore Where Neo4j Fits Among Various Database Types, helping you grasp its unique role compared to traditional databases.

We then focus on the Property Graph Model, the backbone of Neo4j, explaining its components and why it’s perfect for representing complex, connected data.

Our hands-on labs start with Neo4j Setup and Installation on Windows. You’ll learn how to get Neo4j up and running, explore the Neo4j Browser, and set up your initial dataset. We'll also cover different Options for Setting Up Neo4j, whether on the cloud, on-premises, or hybrid setups.

The power of querying is unlocked with an Introduction to Cypher Query Language, Neo4j’s expressive and powerful query language. You’ll master Cypher through a series of practical labs, starting with the General Syntax of Cypher and moving to more advanced topics like Filtering Techniques, Aggregation, CRUD Operations, and advanced features like MERGE, WITH, and RETURN.

In our Shortest Path lab, you’ll learn how to find the quickest route between nodes, a fundamental skill in graph analytics.

We then present an exciting challenge with our Crime Investigation Using Neo4j use case, where you'll apply what you've learned to solve a mystery.

But the learning doesn’t stop there! We move on to Understanding the Graph Data Science Library with an engaging Flights Data Use Case. Here, you’ll explore powerful algorithms in Neo4j's Graph Data Science Library through hands-on labs, including Centrality, Community Detection, Node Similarity, and Path Finding.

Performance is critical in graph databases, so we’ll cover Memory Allocation Recommendations in Neo4j and share Best Practices to Write Optimized Queries, ensuring your queries are efficient and your databases run smoothly.

We will also cover some emerging trends in Neo4j integration with AI. Here, we’ll explore what Large Language Models are and how they can be used to extract entities from unstructured data and convert them into a knowledge graph. We’ll understand this end-to-end use case with the help of Python code. Please note, this course does not teach you the basics of Python. In the end, we will cover some advanced topics like Retrieval-Augmented Generation and GraphRAG, and understand how these techniques can be used to create better context for LLMs.

By the end of this course, you'll have a thorough understanding of Neo4j, Cypher, and the Graph Data Science Library. You’ll be ready to build, query, and optimize your own knowledge graphs with confidence and expertise. Join us and take the first step towards becoming a Neo4j and graph database expert!

Who this course is for:

Data Analyst
Business Analyst
Software Engineers
Data Engineers

Neo4j: Cypher, GDS, GraphQL, LLM, Knowledge Graphs for RAG

What you'll learn

Explore related topics

Course content

Introduction to Neo4j12 lectures • 22min

Cypher Query Language10 lectures • 27min

Use Case - Flights Data: Graph Data Science Library and Its Usage7 lectures • 16min

Use Case - Crime Investigation: Advanced Cypher - UNWIND, COLLECT2 lectures • 8min

Basic Overview of GraphQL5 lectures • 10min

Miscellaneous Topics7 lectures • 23min

Performance Optimization3 lectures • 7min

Interacting with Neo4j from a Python Program2 lectures • 9min

Emerging Trends in Neo4j and AI Integration: LLMs and GraphRAG (Advanced Topic)13 lectures • 35min

Conclusion1 lecture • 1min

Requirements

Description

Who this course is for: