Generate Text Completion using Gemini

Description

Generates a text completion response bsaed on a given prompt using the Gemini models.

Project compatibility

Windows | Cross-platform

Configuration

Connection ID - The connection established in Integration Service. Access the dropdown menu to choose, add, or manage connections.
Model name - The large language model (LLM) to utilize for the completion request. Select one of the available options: Gemini Pro, Gemini Pro Vision.
Prompt - The prompt you want to use for the completion(s) generation. This field supports String type input.

Image - The image file to be used for the completion request. This field supports IResource type input. This field is displayed if you select the Gemini Pro Vision model.

Manage Properties

Use the Manage Properties wizard to configure or use any of the object's standard or custom fields. You can select fields to add them to the activity canvas. The added standard or custom fields are available in the Properties panel (in Studio Desktop) or under Show additional properties (in Studio Web).

Additional properties

Max output tokens - The maximum number of tokens that can be generated in the response. A token is approximately four characters. 100 tokens correspond to roughly 60-80 words. Specify a lower value for shorter responses and a higher value for pottentially longer responses. Default value is 2048.
Temperature - A number between 0 and 1. Higher values like 0.8 make the output more random, while lower values like 0.2 make it more focused and deterministic. Default value is 0.8.
Top p - A number between 0 and 1. The lower the number, the lesser the randomness of the result. Defaults to 0.8.
Top k - A number between 1 and 40. The higher the number, the higher the diversity of generated text. Defaults to 40.