[Feature] Image caption

[jtamm-red]

The feature

As a user, I would like to have informative title or caption displayed when hovering over images.

These captions should be automatically generated either from GPS data linked to the image location or through the utilization of AI-based text generation.

The response from the endpoint https://nominatim.openstreetmap.org/reverse?lat=46.093538&lon=7.30263797222222&format=json provides detailed location information, including the name of the place. For instance:

{
  "place_id": 77753094,
  "licence": "Data © OpenStreetMap contributors, ODbL 1.0. http://osm.org/copyright",
  "osm_type": "node",
  "osm_id": 3666820401,
  "lat": "46.11344",
  "lon": "7.3038939",
  "class": "place",
  "type": "hamlet",
  "place_rank": 20,
  "importance": 0.25000999999999995,
  "addresstype": "hamlet",
  "name": "Tortin",
  "display_name": "Tortin, Nendaz, Conthey, Wallis, 1997, Switzerland",
  "address": {
    "hamlet": "Tortin",
    "village": "Nendaz",
    "county": "Conthey",
    "state": "Wallis",
    "ISO3166-2-lvl4": "CH-VS",
    "postcode": "1997",
    "country": "Switzerland",
    "country_code": "ch"
  },
  "boundingbox": [
    "46.0934400",
    "46.1334400",
    "7.2838939",
    "7.3238939"
  ]
}

From this response, we can extract the name or display_name field. For example, the caption for the image would be "Tortin."

By implementing this feature, we aim to harness the power of AI to generate dynamic captions based on GPS data, elevating the user experience by providing context and relevance to each image within the platform. This AI-driven caption generation adds an informative layer to the image viewing experience, making it more engaging and user-friendly.

Platform

• Server
• Web
• Mobile