Graph-based retrieval-augmented generation (GraphRAG) can capture the semantics of geoinformatics data, which can be leveraged by LLMs. We will demonstrate how to build a GraphRAG and how to write prompts so that an LLM Agent can utilize it.

National spatial data infrastructures (NSDIs) contain a wealth of information that AI-based solutions can leverage to improve operational efficiency. We propose a collaborative strategy to bring geospatial awareness into LLMs at scale by constructing GraphRAGs for LLM Agents.