Required. Specify the content payload to send to the Gemini text generation endpoint for all contents. Contents coming from the Prompt Generator Snap will be correctly formatted.

Default value: N/A

Content payload:

[{"content":"What is the weather of San Francisco?","sl_role":"USER"}]

Tool payload:

[{"sl_type":"function","name":"get_weather","description":"Get the current weather in a given location","parameters":[{"name":"city","type":"STRING","description":"The city and state, e.g. San Francisco, CA","required":false}]}]

Allowed function names:

["get_weather","get_air_polution"]

The number of high-probability tokens considered for each generation step, controlling the randomness of the output. If left blank, the endpoint uses its default value.

Default value: N/A

Sequence of tokens to stop the completion at.

Default value: N/A

pay, ["amazing"], ["September", "paycheck"]

The sampling temperature to use, a decimal value between 0 and 1. If left blank, the endpoint uses its default value.

Default value: N/A

Maximum number of tokens that can be generated in the Gemini text generation foundation model. If left blank, the endpoint uses its default value.

Default value: N/A

The nucleus sampling value, which must be a decimal between 0 and 1. If left blank, the endpoint uses its default value.

Default value: N/A

Specify the persona for the model to adopt in the responses. This initial instruction guides the LLM's responses and actions.

Default value: N/A

• "You are a helpful assistant."
• "You are an experienced software developer."
• "You are a customer service representative for a tech company."

Select this checkbox to include a JSON output from the Gemini API.

Default status: Deselected

The type of tool to invoke from the built-in toolset.

• none
• vertexRagStore
• googleSearch
• googleSearchRetrieval
• enterpriseWebSearch
• codeExecution

Default value: N/A

Default value: N/A

Default value: N/A

Select the Google search mode to use.

• MODE_DYNAMIC
• MODE_UNSPECIFIED

Default value: N/A

Default value: N/A

Default value: N/A

The location of the RAG corpus.

Default value: N/A

Configuration for corpus-level document filtering.

• Vector threshold type
• Vector threshold value

Default value: N/A

• vectorSimilarityThreshold
• 0.7

Ensures the model always returns outputs that match your defined JSON Schema.

Default value: N/A

                {"title": "SimpleWeatherInfo",   "type": "object",   "properties": {     "temperature": { "type": "number", "description": "Temperature in Celsius" },     "humidity": { "type": "number", "description": "Humidity percentage" },     "condition": { "type": "string", "description": "Weather condition (e.g. Clear, Rainy)" }   },   "required": ["temperature", "condition"] }

Select this checkbox to receive a simplified response format that retains only the most commonly used fields and standardizes the output for compatibility with other models.

Default status: Deselected

Select this checkbox to enable continuation requests. If selected, the Snap will automatically request additional responses if the finish reason is maximum tokens.

Default status: Deselected

Required. The maximum number of continuation requests to be made.

Default value: N/A

Select this checkbox to enable debug mode. This mode provides the raw response in the _sl_response field and is recommended for debugging purposes only.

Default status: Deselected