Cypher Generation: The Good, The Bad and The Messy

Methods for creating fine-tuning datasets for text-to-Cypher generation.

Introduction

Cypher is Neo4j’s graph query language. It was inspired and bears similarities with SQL, enabling data retrieval from knowledge graphs. Given the rise of generative AI and the widespread availability of large language models (LLMs), it is natural to ask which LLMs are capable of generating Cypher queries or how we can finetune our own model to generate Cypher from the text.

The issue presents considerable challenges, primarily …

availability bears chatgpt cypher data datasets deep-dives enabling fine-tuning genai generative good graph graphs knowledge knowledge graph knowledge graphs language language models large language large language models llms natural neo4j query retrieval sql text