> ## 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.

# Introduction

> Natural language queries and address intelligence

## Natural Language Endpoints

The natural language endpoints accept unstructured input and return structured geospatial results. Send plain text or messy address data, get back clean coordinates, routes, and corrected addresses.

### Endpoints

| Endpoint                                                   | Description                                                                                                                              |
| ---------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------- |
| [`POST /v1/ai/query`](/api/endpoint/query)                 | Natural language to structured geospatial results. Send text like "Walking route from Kings Cross to Tower Bridge" and get back a route. |
| [`POST /v1/ai/parse-address`](/api/endpoint/parse-address) | Correct, standardize, and structure messy addresses. Fixes typos, expands abbreviations, infers missing fields.                          |

### Route narratives

The standard [route](/api/endpoint/route) and [optimise](/api/endpoint/optimize) endpoints also support natural language summaries. Pass `narrative: true` to get a human-readable description of the route:

```json theme={null}
{
  "locations": [...],
  "narrative": true
}
```

The response includes a `narrative` field:

```json theme={null}
{
  "route": {
    "distance_meters": 5765,
    "duration_seconds": 812,
    "narrative": "A 5.8km drive south through central London, about 14 minutes. Mostly flat with 12m total ascent. No tolls or motorways.",
    "terrain": { ... }
  }
}
```

### Authentication

All endpoints require an API key via the `x-api-key` header. See the [authentication guide](/authentication) for details.