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.

Stock Price Table as JSON

Generate key information from a stock data table and return as 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

Context: | Date | Open price | Close price | |------------|------------|-------------| | 2024-01-04 | 19.97 | 19.05 | | 2024-01-05 | 19.08 | 19.54 | | 2024-01-06 | 19.60 | 20.51 | | 2024-01-07 | 20.69 | 20.56 | | 2024-01-08 | 20.61 | 20.05 |

Query: Extract the data, open price, and close price into a JSON array, with one entry for each day. Also print the "highest_close_price_date" and "lowest_close_price_date" in the last part of the JSON array.

Response

[
  {
    "date": "2024-01-04",
    "open_price": 19.97,
    "close_price": 19.05
  },
  {
    "date": "2024-01-05",
    "open_price": 19.08,
    "close_price": 19.54
  },
  {
    "date": "2024-01-06",
    "open_price": 19.60,
    "close_price": 20.51
  },
  {
    "date": "2024-01-07",
    "open_price": 20.69,
    "close_price": 20.56
  },
  {
    "date": "2024-01-08",
    "open_price": 20.61,
    "close_price": 20.05
  },
  {
    "highest_close_price_date": "2024-01-07",
    "lowest_close_price_date": "2024-01-04"
  }
]

Model:	gemini-1.5-flash-001
Temperature:	1
Max output tokens:	8192
TopK:	40
TopP:	0.95