Course Outline
Learn how to construct a knowledge graph (KG) pipeline for ingestion and retrieval using domain-specific ontologies, lightweight fine-tuned models, and practical engineering steps. This course includes an overview of tools like Neo4J, RDF triples, and LLM-based fact extraction, leading to the creation of a robust Retrieval-Augmented Generation (RAG) system.
Learning Outcomes
- Generate doman-specific ontologies
- Create training data and fine-tune a model
- Create an RAG ingestion/retrieval pipeline
Who Is This Course For?
- AI practitioners and engineers interested in retrieval systems.
- Developers with a passion for knowledge graphs and semantic technology.
- Beginners looking to explore RAG systems (basic Python knowledge recommended).
Prerequisites
- Interest in RAG systems and AI
- Python engineering experience useful, but not required
LevelIntermediate
Duration1 hr
Showcasing
Neo4j
Your InstructorClinton
Progress0/7 chapters complete
0%
Your certificateComplete the course to get your certificate
Why Enroll?
- Gain hands-on skills to create a full-stack knowledge graph pipeline. Learn how to use state-of-the-art tools and techniques to structure, query, and retrieve knowledge effectively. Perfect for professionals seeking advanced search solutions or enthusiasts exploring RAG-based AI systems.