Neo4j Graph Data Science and Large Language Model (LLM)
About This Course
This comprehensive course is designed to equip participants with the skills to leverage Neo4j Graph Data Science (GDS) and Large Language Model (LLM) technologies to enhance data-mining applications and resolve complex data challenges. Beginning with an introduction to Neo4j GDS, learners will gain an understanding of how GDS operates, including its Graph Catalog and Cypher Projections, setting a solid foundation for exploring advanced graph algorithms. These include pathfinding, community detection, node embedding, similarity analysis, and the application of weighted shortest paths for intricate data analysis.
Building on this knowledge, the course delves into Graph Machine Learning, covering essential techniques such as node classification, link prediction, and exploratory analysis. Participants will learn how to handle missing values, encode categorical variables, and implement feature normalization, with a focus on optimizing the KMeans algorithm and nearest neighbor graphs. The final segment explores the integration of Neo4j with Large Language Models (LLM), including techniques to avoid hallucination, grounding LLMs, and utilizing LLMs for query generation and narrative analytics. By the end of this course, learners will be equipped to construct graph machine learning models and perform narrative analytics using LLM models on Neo4j graph datasets, positioning them at the forefront of data science innovation.
What You'll Learn
LO1: Develop Neo4j graph data science guidelines to enhance data-mining applications.
LO2: Identify and rectify data problems using graph database algorithms.
LO3: Construct graph machine learning models to identify patterns and trends in data sets.
LO4: Perform narrative analytics using Large Language Model (LLM) models on Neo4j graph data sets.
Topics Covered"
Topic 1 Introduction to Neo4J Graph Data Science
• Overview of Neo4j Graph Data Science (GDS)
• How GDS Works
• Graph Catalog
• Cypher Projections
Topic 2 Graph Algorithms
• Path Finding
• Community Detection
• Node Embedding
• Similarity
• Shortest Paths with Cypher
• Weighted Shortest Paths
Topic 3 Graph Machine Learning
• Overview of Graph Machine Learning
• Node Classification Pipeline
• Link Prediction
• Exploratory Analysis
• Handling Missing Values
• Encoding Categorical variables
• Dimensionality reduction
• KMeans algorithm
• Feature normalization
• Optimizing KMeans algorithm
• Nearest neighbor graph
• KNN algorithm
Topic 4 Neo4j and LLM
• Introduction to Neo4j with Generative AI
• Avoiding Hallucination
• Grounding LLMs
• Vectors & Semantic Search
• Vector Indexes
• Introduction to Langchain
• Large Language Models (LLM)
• Chains
• Memory
• Agents
• Retrievers
• Using LLMs for Query Generation
• The Cypher QA Chain
• Conversational Agent
Entry Requirements
Knowledge and Skills
• Able to operate computer functions with minimum Computer Literacy Level 2 based on ICAS Computer Skills Assessment Framework
• Minimum 3 GCE ‘O’ Levels Passes including English or WPL Level 5 (Average of Reading, Listening, Speaking & Writing Scores)
Attitude
• Positive Learning Attitude
• Enthusiastic Learner
Experience
• Minimum of 1 year of working experience.
Target age group: 21-65 years old