Real-Time Text-to-Cypher Query Generation with Large Language Models for Graph Databases
Future Internet · 22.11.2024 · 16 (12) · 438
DOI: 10.3390/fi16120438 ↗Kurz gefasst
Fachartikel in der Zeitschrift Future Internet, online erschienen am 22.11.2024. Verfasst von Markus Hornsteiner und 5 weiteren Autor:innen. Die Arbeit wurde bisher 32-mal zitiert (Crossref) und nennt 78 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Bavarian Ministry of Economic Affairs, Regional Development and Energy.
Abstract (Originalsprache)
Based on their ability to efficiently and intuitively represent real-world relationships and structures, graph databases are gaining increasing popularity. In this context, this paper proposes an innovative integration of a Large Language Model into NoSQL databases and Knowledge Graphs to bridge the gap in field of Text-to-Cypher queries, focusing on Neo4j. Using the Design Science Research Methodology, we developed a Natural Language Interface which can receive user queries in real time, convert them into Cypher Query Language (CQL), and perform targeted queries, allowing users to choose from different graph databases. In addition, the user interaction is expanded by an additional chat function based on the chat history, as well as an error correction module, which elevates the precision of the generated Cypher statements. Our findings show that the chatbot is able to accurately and efficiently solve the tasks of database selection, chat history referencing, and CQL query generation. The developed system therefore makes an important contribution to enhanced interaction with graph databases, and provides a basis for the integration of further and multiple database technologies and LLMs, due to its modular pipeline architecture.
Förderung
- Bavarian Ministry of Economic Affairs, Regional Development and Energy
Zitieren
APA
Hornsteiner, M., Kreussel, M., Steindl, C., Ebner, F., Empl, P., & Schönig, S. (2024). Real-Time Text-to-Cypher Query Generation with Large Language Models for Graph Databases. Future Internet, 16(12), 438. https://doi.org/10.3390/fi16120438
Vancouver
Hornsteiner M, Kreussel M, Steindl C, Ebner F, Empl P, Schönig S. Real-Time Text-to-Cypher Query Generation with Large Language Models for Graph Databases. Future Internet. 2024;16(12):438. doi:10.3390/fi16120438
BibTeX
@article{Hornsteiner2024,
author = {Hornsteiner, Markus and Kreussel, Michael and Steindl, Christoph and Ebner, Fabian and Empl, Philip and Schönig, Stefan},
title = {Real-Time Text-to-Cypher Query Generation with Large Language Models for Graph Databases},
journal = {Future Internet},
year = {2024},
volume = {16},
number = {12},
pages = {438},
doi = {10.3390/fi16120438}
}
EUVIMED