Build Graph Database, Knowledge Graph, GraphRAG with Neo4j

This course contains the use of artificial intelligence

Disclosure: AI tools were used only to assist in creating the course outline and course thumbnail. All instructional content, explanations, and project walkthroughs were fully created manually by the instructor.

Welcome to Build Graph Database, Knowledge Graph, Graph RAG with Neo4j course. This is a comprehensive project based course where you will learn how to build graph databases, model relationships, write Cypher queries, apply graph algorithms, and build intelligence GraphRAG. This course is a perfect combination between knowledge management and artificial intelligence, making it an ideal opportunity to practice your programming skills while improving your technical knowledge in graph databases. In the introduction session, you will learn the basic fundamentals of graph databases, such as getting to know its use cases, basic components, and the difference between graph database and relational database. Then, in the next section, we will learn how to set up a graph database in Neo4j and create a basic human resources graph database. Afterward, we will learn about Cypher Query Language, which is mainly used for creating, querying, updating, and managing data in Neo4j graph databases. In this section, we will learn how to use match, where, return, create, merge, set, delete, order by, and limit. These will help us to efficiently create, retrieve, filter, modify, and manage data in Neo4j. Then, in the next section, we will learn about graph data modelling, specifically, we are going to learn about one to many relationships, many to many relationships, and hierarchies model. This will help us to design effective graph structures and represent complex relationships between nodes and edges. Following that, we will also learn about graph algorithms and graph analytics. First, we are going to build an airport and flight route graph database in Neo4j, and then we will use graph algorithms to analyze the network, this section will cover degree centrality, page rank, shortest path, graph traversal, node similarity, and community detection. This will help us to identify important airports, analyze flight connections, and find the most optimal routes. In the next section, we will create a knowledge graph from a corporate legal case document, specifically, we are going to extract key entities, relationships, and facts and represent them as connected data in Neo4j. In addition, we are also going to use an LLM to automatically extract key entities and relationships from the legal case document, identify their connections, and then reuse the LLM to generate cypher queries that will be used to create the knowledge graph in Neo4j. Then, after that, we are going to learn about Graph Retrieval Augmented Generation. In this section, we are going to build an AI decision making assistant for real estate, where we will use a graph database that maps properties, features, locations, and their relationships, allowing the AI assistant to retrieve relevant connected information from the graph before generating recommendations. Lastly, at the end of the course, we will build three real world projects. In the first project, we are going to build a fraud analytics system using GraphRAG, where the objective is to identify confirmed fraudulent transactions and uncover connected accounts and entities. In the second project, we are going to build an access management system using GraphRAG, where the objective is to identify who has access to which resources and understand their access limitations. In the third project, we are going to build a supply chain disruption detection system using GraphRAG, where the objective is to trace supplier dependencies and identify products and components that could be affected by a supplier disruption.

Firstly, before getting into the course, we need to ask this question to ourselves, why should we learn about graph databases? Well, here is my answer. Graph databases allow us to represent complex relationships between data as connected nodes and edges, making it easier to discover connections that are difficult to identify in traditional tabular data. For example, we can connect a customer to an account, transaction, device, and address, allowing us to quickly trace relationships and uncover patterns that may be hidden across multiple tables

Below are things that you can expect to learn from this course:

• Learn the basic fundamentals of graph database

• Learn how to build human resources graph database using Python and Neo4j

• Learn about Cypher Query Language

• Learn how to use match, where, return, and create in Cypher Query Language

• Learn how to use merge, set, delete, order by, and limit in Cypher Query Language

• Learn about graph data modelling, graph algorithms, and graph analytics

• Learn how to model one to many relationship and many to many relationship

• Learn how to model hierarchies and relationship in graph database

• Learn how to build flight route graph database using Neo4j

• Learn about graph projection, degree centrality, and page rank

• Learn how to find shortest path and perform graph traversal

• Learn about node similarity and community detection

• Learn how to create knowledge graph from legal case document

• Learn how to extract entities and relationships using LLM

• Learn how to build AI decision maker assistant using GraphRAG

• Learn how to build access management system using GraphRAG

• Learn how to build fraud analytics system using GraphRAG

• Learn how to build supply chain disruption detection system using GraphRAG