Knowledge Graph Data Engineering for Generative AI Use Cases
1h 50mIntermediate2025-05-30
Authors
Ashleigh Faith
Course details
This advanced course bridges the gap between traditional data engineering and modern AI applications through knowledge graphs. Designed for data scientists and engineers, instructor Ashleigh Faith provides an overview of a practical framework for implementing neurosymbolic AI solutions. Learn how to assess data requirements, build robust knowledge graphs, implement efficient ETL processes, and handle complex entity resolution challenges. Along the way, Ashleigh covers real-world applications, common pitfalls, and best practices for creating maintainable, scalable knowledge graph solutions that can integrate with AI systems.
Skills covered
Neo4jOrchestrating AI SystemsAI for Data Engineers and ScientistsRole-Based AI ApplicationsAI Development Tools and PlatformsData VisualizationBuilding with AIData ScienceBusiness Analysis and StrategyBusiness Software and ToolsOpen SourceOne-Off
Concepts
Introduction
- The power of knowledge graphs in data engineering
- What you need to know for the course
Setup - Data Engineering Foundations
- What is data engineering
- Aspects of data engineering
- Importance of data engineering for semantic AI
- Use case - Two Trees Olive Oil
Extraction
- What data do you need
- Where is the data
- What state is the data in
- Translating relational to graph data
Data Modeling
- Creating your design document
- Options for data modeling
- Thinking about nodes
- Thinking about relations
- Thinking about retrieval traversal
- Thinking about updates
- Thinking about storage
Transform
- Data transformation
- Missing data
Load
- Setting up our Stardog project, part 1
- Setting up our Stardog project, part 2
- Load instances in Stardog
- Test the load
- Test the query
Using the Knowledge Graph with AI
- Architecture
- Query options
- Using a knowledge graph with AI
Conclusion
- Continuing your learning journey