About This Course

Knowledge Graphs & Graph Databases teaches you when a graph beats a relational join or a vector-similarity search, and how to build one. You will go from Cypher fundamentals to building GraphRAG pipelines with LLMs, wiring a graph up as a tool an AI agent can call, and giving agents graph-native long-term memory.

Requirements

• Comfortable writing basic Python, used throughout the GraphRAG and agent-tool sections
• Comfortable working from a terminal, with Git and Docker installed and running. You will clone the lab repo, and the hands-on lab runs Neo4j locally in a container
• An LLM API key is very useful for the LLM-driven extraction and agent sections, but not strictly required to complete the course
• No prior graph database or Cypher knowledge needed. This course teaches Cypher from the start

What You'll Learn

• Model data as nodes and relationships, and query it fluently with Cypher
• Turn unstructured documents into a knowledge graph, by hand and with an LLM doing the extraction
• Expose a graph database as a tool an AI agent can call via MCP
• Give agents graph-native long-term memory, and know when a graph is the right tool versus a semantic layer or a vector database

Hands-On

The course ends with a graded lab: stand up Neo4j locally and build a real, idempotent data-loading pipeline against it.