LLMs are often like the know-it-all at a bar - they can quickly and confidently produce realistic sounding answers to just about any question - even if the answers are complete fabrications. But an LLM can be grounded in reality by combining it with a Knowledge Graph in order to prevent hallucinations, and to prevent unauthorized access to sensitive data.

This presentation will show how knowledge graphs can be combined with LLMs to:

- eliminate hallucinations

- improve accuracy

- use current information

- enforce security and privacy

- improve reliability and explainability

- simplify access to data

- simplify ingestion of semi

-structured data

- combine vector searching with graph traversal for context-based semantic searching

We will use a Jupyter notebook in a public Github repo for a working demo.