Try Gemini 1.5 models, our newest multimodal models in Vertex AI, and see what you can build with a 1M token context window. Try Gemini 1.5 models, our newest multimodal models in Vertex AI, and see what you can build with a 1M token context window.

Image text to JSON

Extract the items and prices from a fish market photo and output them in JSON.

You can query a model directly and test the results returned when using different parameter values with the Cloud console, or by calling the Vertex AI API directly.

For an example of using the Vertex AI API, see Quickstart using the Vertex AI API.
To view this sample in the Cloud console: Go to Google Cloud console

Prompt Freeform

Extract the items and prices from a fish market photo and output them in JSON.

Response

{
  "items_and_prices": [
    {
      "item": "Black Cod",
      "price": "18.99"
    },
    {
      "item": "Rainbow Trout",
      "price": "11.99"
    },
    {
      "item": "Branzino",
      "price": "14.99"
    }
  ]
}

Model:	gemini-1.5-flash-preview-0514
Temperature:	1
Max output tokens:	8192
TopK:	40
TopP:	0.95