TransitGPT: a generative AI-based framework for interacting with GTFS data using large language models

Saipraneeth Devunuri () and Lewis Lehe
Additional contact information
Saipraneeth Devunuri: University of Illinois at Urbana Champaign
Lewis Lehe: University of Illinois at Urbana Champaign

Public Transport, 2025, vol. 17, issue 2, No 1, 319-345

Abstract: Abstract This paper introduces a framework that leverages Large Language Models (LLMs) to answer natural language queries about General Transit Feed Specification (GTFS) data. The framework is implemented in a chatbot called TransitGPT with open-source code. TransitGPT works by guiding LLMs to generate Python code that extracts and manipulates GTFS data relevant to a query, which is then executed on a server where the GTFS feed is stored. It can accomplish a wide range of tasks, including data retrieval, calculations and interactive visualizations, without requiring users to have extensive knowledge of GTFS or programming. The LLMs that produce the code are guided entirely by prompts, without fine-tuning or access to the actual GTFS feeds. We evaluate TransitGPT using GPT-4o and Claude-3.5-Sonnet LLMs on a benchmark dataset of 100 tasks, to demonstrate its effectiveness and versatility. The results show that TransitGPT can significantly enhance the accessibility and usability of transit data.

Keywords: Public transit; Generative AI; Large language model; Information retrieval; Prompt engineering (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s12469-025-00395-w Abstract (text/html)
Access to the full text of the articles in this series is restricted.

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:spr:pubtra:v:17:y:2025:i:2:d:10.1007_s12469-025-00395-w

Ordering information: This journal article can be ordered from
https://www.springer ... search/journal/12469

DOI: 10.1007/s12469-025-00395-w

Access Statistics for this article

Public Transport is currently edited by Stefan Voß

More articles in Public Transport from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().