Real-Time Text-to-Cypher Query Generation with Large Language Models for Graph Databases

Markus Hornsteiner, Michael Kreussel, Christoph Steindl, Fabian Ebner, Philip Empl and Stefan Schönig ()
Additional contact information
Markus Hornsteiner: Faculty of Informatics and Data Science, University of Regensburg, 93053 Regensburg, Germany
Michael Kreussel: Faculty of Informatics and Data Science, University of Regensburg, 93053 Regensburg, Germany
Christoph Steindl: Faculty of Informatics and Data Science, University of Regensburg, 93053 Regensburg, Germany
Fabian Ebner: Faculty of Informatics and Data Science, University of Regensburg, 93053 Regensburg, Germany
Philip Empl: Faculty of Informatics and Data Science, University of Regensburg, 93053 Regensburg, Germany
Stefan Schönig: Faculty of Informatics and Data Science, University of Regensburg, 93053 Regensburg, Germany

Future Internet, 2024, vol. 16, issue 12, 1-26

Abstract: 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.

Keywords: chatbot; ChatGPT; cypher language; graph database; knowledge graphs; LLM; natural language interface; Neo4j; question answering (search for similar items in EconPapers)
JEL-codes: O3 (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1999-5903/16/12/438/pdf (application/pdf)
https://www.mdpi.com/1999-5903/16/12/438/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jftint:v:16:y:2024:i:12:p:438-:d:1527136

Access Statistics for this article

Future Internet is currently edited by Ms. Grace You

More articles in Future Internet from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().