Okay, so I wanted to extend our first article on AI agents and AI models and take a very gentle technical deeper dive.
Let’s ask a very simple geospatial question:
“Whatβs the straight-line distance between the Eiffel Tower and the Louvre Museum?”
Here is the python code we can use to answer this question (note, to use this code .. right-click on image .. save as .. and save the image locally .. next drop this into ChatGPT and use this prompt: Can you pull the python from this image and give me that code):
To help explain what is happening here, let’s refer back to the analogy we used in our previous article.
How It Works
Agent (Waiter Role): The geospatial_agent function acts as the coordinator:
- Takes a natural language query (locations as strings).
- Delegates tasks to specialized “chefs” (geocoding and distance models).
- Returns a human-readable answer.
Geospatial Models (Chefs):
- Geocoding Model: Uses
geopy.Nominatimto convert text addresses to coordinates. - Distance Model: Uses
geopy.geodesicto calculate accurate distances between coordinates.
Infrastructure: Free OpenStreetMap APIs (no API key required for small-scale use).
If you wanted both the simple text answer (3.28 km) shown above, and an interactive map ….
Here is that code:
That is a nice gentle introduction. In our next post we will dive a little deeper, and move off the green runs to the blue!
In the next article in the series we dive a little deeper: Geospatial AI Agents & AI Models: Introducing Prithvi β A Real Geospatial Model
Matt SheehanΒ is a Geospatial 2.0 expert. He publishes a weekly Spatial-Next Newsletter which dives deeper into advances in the geospatial world, providing important news, opinions, new research and spotlights innovators. Subscribe to the newsletterΒ here.