Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.footstep.ai/llms.txt

Use this file to discover all available pages before exploring further.

Reverse geocode: convert geographic coordinates into a human-readable address or place name. Returns the nearest matching locations sorted by proximity. You can filter by place type (venue, address, street, locality) to control the level of detail.

​
Example prompts

  • “What address is at 51.5034, -0.1276?”
  • “What’s at these coordinates: 48.8584, 2.2945?”
  • “Tell me the nearest street address to this lat/lng”
  • “What neighbourhood is this point in?”

​
What you get back

The nearest location(s) with coordinates, a full label, country, region, district (e.g. borough or municipality), locality, neighbourhood, optional confidence score (omitted when 1.0), and result type. Each result also carries the straight-line distance_meters from the input point and — when the result isn’t sitting on top of the input — a bearing_deg (0–360) plus 8-point bearing_compass (e.g. "NE"). By default returns a single result; you can ask for more. When you request multiple results and they all share the same country / region, those fields are hoisted into a top-level context object so they aren’t repeated on every row.

​
Map rendering

Responses include a render envelope with a point layer for the resolved location(s). Pass compact: true for summary-only responses. See response defaults & controls and render envelopes.

​
Example response

{
  "structuredContent": {
    "results": [
      {
        "name": "10 Downing Street",
        "label": "10 Downing Street, London, England, United Kingdom",
        "coordinates": { "lat": 51.5034, "lng": -0.1276 },
        "place_type": "address"
      }
    ],
    "render": [
      { "kind": "point", "label": "Resolved location", "data": {/* FeatureCollection */}, "bbox": [/* … */] }
    ]
  }
}