Mydra logo
Log in
>All courses>Artificial Intelligence
Artificial Intelligence
DeepLearning.AI logo

DeepLearning.AI

Knowledge Graphs for RAG

  • up to 1 hour
  • Intermediate

This course teaches you how to leverage knowledge graphs within retrieval augmented generation (RAG) applications. You will learn to use Neo4j’s query language Cypher to manage and retrieve data stored in knowledge graphs, and build a question-answering system using Neo4j and LangChain.

  • Knowledge Graphs
  • Cypher
  • Neo4j
  • Vector Similarity Search
  • Data Retrieval

Overview

In this course, you will learn the basics of how knowledge graphs store data using nodes and edges, use Neo4j’s query language Cypher to retrieve information, add a vector index to a knowledge graph, and build a knowledge graph of text documents from scratch. You will also explore advanced techniques for connecting multiple knowledge graphs and using complex queries for comprehensive data retrieval. By the end of the course, you will be well-equipped to use knowledge graphs to uncover deeper insights in your data and enhance the performance of LLMs with structured, relevant context.

  • Web Streamline Icon: https://streamlinehq.com
    Online
    course location
  • Layers 1 Streamline Icon: https://streamlinehq.com
    English
    course language
  • Self-paced
    course format
  • Live classes
    delivered online

Who is this course for?

Developers

Anyone who wants to understand how knowledge graphs work, how to build with them, and create better RAG applications.

Data Scientists

Professionals looking to enhance their skills in structuring complex data relationships and building powerful AI applications.

AI Enthusiasts

Individuals interested in leveraging knowledge graphs to improve the output of large language models (LLMs).

This course will teach you how to leverage knowledge graphs to enhance the performance of LLMs with structured, relevant context. You will learn to use Neo4j’s query language Cypher and build a question-answering system using Neo4j and LangChain. Ideal for developers, data scientists, and AI enthusiasts looking to improve their skills in structuring complex data relationships.

Pre-Requisites

1 / 3

  • Familiarity with LangChain

  • Basic understanding of data structures

  • Experience with query languages

What will you learn?

Introduction to Knowledge Graphs
Understand the basics of how knowledge graphs store data by using nodes to represent entities and edges to represent relationships between nodes.
Using Cypher with Neo4j
Use Neo4j’s query language, Cypher, to retrieve information from a fun graph of movie and actor data.
Vector Similarity Search
Add a vector index to a knowledge graph to represent unstructured text data and find relevant texts using vector similarity search.
Building a Knowledge Graph
Build a knowledge graph of text documents from scratch, using publicly available financial and investment documents as the demo use case.
Advanced Techniques
Explore advanced techniques for connecting multiple knowledge graphs and using complex queries for comprehensive data retrieval.
Advanced Cypher Queries
Write advanced Cypher queries to retrieve relevant information from the graph and format it for inclusion in your prompt to an LLM.

Meet your instructor

  • Andreas Kollegger

    Lead for GenAI Innovation, Neo4j

    Andreas Kollegger is the Lead for GenAI Innovation at Neo4j, a company that provides graph databases. He is passionate about using technology to make the world a better place and has worked on projects for science, supporting satellite missions at NASA, and for humanity, serving medical informatics to save lives in Africa.

Upcoming cohorts

  • Dates

    start now

Free