interface YandexGPTInputs {
    apiKey?: string;
    cache?: boolean | BaseCache<Generation[]>;
    callbackManager?: CallbackManager;
    callbacks?: Callbacks;
    concurrency?: number;
    folderID?: string;
    iamToken?: string;
    maxConcurrency?: number;
    maxRetries?: number;
    maxTokens?: number;
    metadata?: Record<string, unknown>;
    model?: string;
    modelURI?: string;
    modelVersion?: string;
    onFailedAttempt?: FailedAttemptHandler;
    tags?: string[];
    temperature?: number;
    verbose?: boolean;
}

Hierarchy

  • BaseLLMParams
    • YandexGPTInputs

Implemented by

Properties

apiKey?: string

Yandex Cloud Api Key for service account with the ai.languageModels.user role.

cache?: boolean | BaseCache<Generation[]>
callbackManager?: CallbackManager

Use callbacks instead

callbacks?: Callbacks
concurrency?: number

Use maxConcurrency instead

folderID?: string

Yandex Cloud Folder ID

iamToken?: string

Yandex Cloud IAM token for service or user account with the ai.languageModels.user role.

maxConcurrency?: number

The maximum number of concurrent calls that can be made. Defaults to Infinity, which means no limit.

maxRetries?: number

The maximum number of retries that can be made for a single call, with an exponential backoff between each attempt. Defaults to 6.

maxTokens?: number

Maximum limit on the total number of tokens used for both the input prompt and the generated response.

metadata?: Record<string, unknown>
model?: string

Model name to use.

modelURI?: string

Model URI to use.

modelVersion?: string

Model version to use.

onFailedAttempt?: FailedAttemptHandler

Custom handler to handle failed attempts. Takes the originally thrown error object as input, and should itself throw an error if the input error is not retryable.

tags?: string[]
temperature?: number

What sampling temperature to use. Should be a double number between 0 (inclusive) and 1 (inclusive).

verbose?: boolean