Getting Started

Get an overview of the course, including the target audience, prerequisites, objectives, and structure.

We'll cover the following

Welcome to the exploration of graph RAG. This course comprehensively introduces integrating generative AI technologies with knowledge graphs, utilizing Neo4j for efficient storage and querying. We’ll explore how large language models (LLMs) and knowledge graphs can enhance AI applications, focusing on practical skills and hands-on experience with Neo4j.

Press + to interact
Knowledge graph: Things not strings
Knowledge graph: Things not strings

Course prerequisites

To get the most out of this course, you should have:

  • Basic understanding of machine learning concepts and AI technologies.

  • Familiarity with programming in Python.

  • Prior experience with database systems or a willingness to learn database fundamentals.

Expected audience

This course is intended for:

  • Data scientists and machine learning practitioners interested in understanding and applying generative AI and knowledge graphs.

  • Developers and engineers seeking to leverage LLMs and knowledge graphs for advanced AI solutions.

  • Researchers and students who want to explore the integration of LLMs with graph databases for enhanced data processing and insights.

Course structure

The course is divided into the following chapters:

  1. Understanding the path to graph RAG: We’ll explore the foundational concepts that bridge large language models and knowledge graphs, leading to graph retrieval-augmented generation (RAG) development. We’ll learn how combining LLMs with structured knowledge graphs enhances information retrieval and response accuracy in generative models.

  2. Constructing knowledge graphs: We’ll cover the fundamental techniques for building and improving knowledge graphs with LLMs.

  3. Building, storing, and querying knowledge graphs with Neo4j (a graph database): We’ll explore Neo4j’s features and how to effectively use them for knowledge graph management.

  4. Enhancing LLM capabilities with knowledge graphs: We’ll learn to integrate knowledge graphs with LLMs to enhance their information retrieval and response accuracy.

  5. Conclusion: Lastly, we’ll summarize key takeaways and provide guidance on applying the knowledge gained.

Let’s dive in!