Seoul Data Hub's Generative-AI Chatbot for Natural-Language Open-Data Discovery

The Seoul Metropolitan Government's Data Strategy Division launched a generative-AI chatbot inside its Seoul Data Hub open-data portal, letting residents and businesses query the city's roughly 8,100 open datasets in plain Korean instead of navigating manual catalogue menus.
The chatbot is built on retrieval-augmented generation (RAG): rather than letting a language model answer from memory, it retrieves matching datasets from the city's catalogue first and grounds its response in that retrieved content, a design the city says was chosen specifically to suppress hallucinated answers. Responses link directly to the underlying dataset pages and, where relevant, 3D or visual dashboards.
The service began as a pilot in November 2024 and was officially opened in February 2025, billed by the city as the first natural-language public-data service among Korean local governments. By 20 January 2025, during the pilot period, it had logged 67,300 cumulative views and 13,800 active users, with roughly 80% of surveyed users satisfied and about a third returning five or more times a month.
Seoul's own reporting is candid that the system does not yet return pinpoint-accurate results for every query, and describes improving retrieval precision as ongoing work rather than a solved problem — a caveat independent Korean IT press coverage of the launch corroborates without disputing the underlying figures.

Read the full analysis: https://news.seoul.go.kr/gov/archives/564644