A large language model-based chatbot system framework for urban planners

Currently, urban planners, private developers, and related stakeholders face significant challenges due to the complexity and dispersion of municipal bylaws and zoning regulations across jurisdictions. This study proposes a novel Large Language Model (LLM)-based chatbot framework¹1 GitHub: https://github.com/zhoux121/School_of_cities_AI designed to streamline access to and interpretation of these regulations. The framework integrates a hybrid database system, combining pre-collected static data from official sources with dynamically scraped real-time content, ensuring comprehensive and up-to-date information retrieval. Leveraging GPT-3.5-turbo for hierarchical text preprocessing and a dual retrieval mechanism (BM25 and cosine similarity with Reciprocal Rank Fusion), the framework achieves strong accuracy in answering regulatory queries. Evaluated across six Canadian cities, the model demonstrated 72–92 % accuracy on binary questions and 40–70 % on continuous questions, outperforming baseline models such as GPT-4o and LLaMA 3.2. This approach not only reduces administrative burdens but also enhances accessibility for stakeholders, offering a scalable solution for navigating fragmented urban policy landscapes.