Gemini - Generate Response | Alli Documentation

Overview

To use this template, you need a Gemini API key, which can be obtained from your Gemini account. Ensure you have a prompt ready for the text generation task. Optionally, specify a file name and folder path to save the response locally.

Variables

Name	Reference	Type	Required	Default	Options	Description
Gemini API Key	GEMINI_API_KEY	Password	✅	-	-	The API key for accessing the Gemini service.
Model	GEMINI_MODEL	Select	➖	gemini-2.5-flash	Gemini 2.5 Flash: gemini-2.5-flash Gemini 2.5 Pro: gemini-2.5-pro Gemini 2.0 Flash: gemini-2.0-flash Gemini 2.0 Flash Lite: gemini-2.0-flash-lite	The model to use for generating the response.
Prompt	GEMINI_PROMPT	Alphanumeric	✅	-	-	The prompt text to send to the Gemini API.
Destination File Name	GEMINI_DESTINATION_FILE_NAME	Alphanumeric	✅	-	-	The name of the file where the response will be saved.
Destination Folder Name	GEMINI_DESTINATION_FOLDER_NAME	Alphanumeric	➖	-	-	The folder path where the response file will be saved.
Enable Google Search	GEMINI_ENABLE_GOOGLE_SEARCH	Boolean	➖	FALSE	-	Connects the Gemini model to real-time web content
Enable Code Execution	GEMINI_ENABLE_CODE_EXECUTION	Boolean	➖	FALSE	-	When enabled, the model executes Python code and returns the results. Disable this option if you want the model to include the code itself in the response.

YAML

Below is the YAML template

YAML


source:
  template: Gemini - Generate Response
  inputs:
    GEMINI_API_KEY:
    GEMINI_MODEL: gemini-2.5-flash
    GEMINI_PROMPT:
    GEMINI_DESTINATION_FILE_NAME:
    GEMINI_DESTINATION_FOLDER_NAME:
    GEMINI_ENABLE_GOOGLE_SEARCH: 'FALSE'
    GEMINI_ENABLE_CODE_EXECUTION: 'FALSE'
  type: TEMPLATE
guardrails:
  retry_count: 1
  retry_wait: 0h0m0s
  runtime_cutoff: 1h0m0s
  exclude_exit_code_ranges:
    - 10
    - 11
    - 14
    - 205
    - 204