The params which can be passed to the API at request time.

interface GoogleAIModelRequestParams {
    allowed_function_names?: string[];
    convertSystemMessageToHumanContent?: boolean;
    maxOutputTokens?: number;
    model?: string;
    modelName?: string;
    responseMimeType?: GoogleAIResponseMimeType;
    safetySettings?: GoogleAISafetySetting[];
    stopSequences?: string[];
    streaming?: boolean;
    temperature?: number;
    tool_choice?: string | Record<string, any>;
    tools?: GoogleAIToolType[];
    topK?: number;
    topP?: number;
}

Hierarchy (view full)

Properties

allowed_function_names?: string[]

Allowed functions to call when the mode is "any". If empty, any one of the provided functions are called.

convertSystemMessageToHumanContent?: boolean
maxOutputTokens?: number

Maximum number of tokens to generate in the completion.

model?: string

Model to use

modelName?: string

Model to use Alias for model

responseMimeType?: GoogleAIResponseMimeType

Available for gemini-1.5-pro. The output format of the generated candidate text. Supported MIME types:

  • text/plain: Text output.
  • application/json: JSON response in the candidates.
"text/plain"
safetySettings?: GoogleAISafetySetting[]
stopSequences?: string[]
streaming?: boolean

Whether or not to stream.

false
temperature?: number

Sampling temperature to use

tool_choice?: string | Record<string, any>

Force the model to use tools in a specific way.

Mode Description
"auto" The default model behavior. The model decides whether to predict a function call or a natural language response.
"any" The model must predict only function calls. To limit the model to a subset of functions, define the allowed function names in allowed_function_names.
"none" The model must not predict function calls. This behavior is equivalent to a model request without any associated function declarations.
string The string value must be one of the function names. This will force the model to predict the specified function call.

The tool configuration's "any" mode ("forced function calling") is supported for Gemini 1.5 Pro models only.

topK?: number

Top-k changes how the model selects tokens for output.

A top-k of 1 means the selected token is the most probable among all tokens in the model’s vocabulary (also called greedy decoding), while a top-k of 3 means that the next token is selected from among the 3 most probable tokens (using temperature).

topP?: number

Top-p changes how the model selects tokens for output.

Tokens are selected from most probable to least until the sum of their probabilities equals the top-p value.

For example, if tokens A, B, and C have a probability of .3, .2, and .1 and the top-p value is .5, then the model will select either A or B as the next token (using temperature).