Videos

In this session, Jonas will demonstrate how to fine-tune a large language model to generate Cypher statements from natural language input, allowing users to interact with Neo4j databases intuitively and without knowledge of #Cypher. In contrast to using third-party APIs to powerful models like GPT-4, a self-trained and self-hosted model has advantages regarding data privacy, controllability, and more. You’ll learn all about the training process, the training dataset, the associated costs, and the challenges you might encounter. #Neo4j