Interface for the input parameters specific to the Writer model.

interface WriterInput {
    apiKey?: string;
    bestOf?: number;
    cache?: boolean | BaseCache<Generation[]>;
    callbackManager?: CallbackManager;
    callbacks?: Callbacks;
    concurrency?: number;
    frequencyPenalty?: number;
    logprobs?: number;
    maxConcurrency?: number;
    maxRetries?: number;
    maxTokens?: number;
    metadata?: Record<string, unknown>;
    minTokens?: number;
    model?: string;
    n?: number;
    onFailedAttempt?: FailedAttemptHandler;
    orgId?: string | number;
    presencePenalty?: number;
    tags?: string[];
    temperature?: number;
    topP?: number;
    verbose?: boolean;
}

Hierarchy

  • BaseLLMParams
    • WriterInput

Implemented by

Properties

apiKey?: string

Writer API key

bestOf?: number

Generates this many completions server-side and returns the "best"."

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

Use callbacks instead

callbacks?: Callbacks
concurrency?: number

Use maxConcurrency instead

frequencyPenalty?: number

Penalizes repeated tokens according to frequency.

logprobs?: number

Whether to return log probabilities.

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 number of tokens to generate in the completion.

metadata?: Record<string, unknown>
minTokens?: number

Minimum number of tokens to generate.

model?: string

Model to use

n?: number

Number of completions to generate.

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.

orgId?: string | number

Writer organization ID

presencePenalty?: number

Penalizes repeated tokens regardless of frequency.

tags?: string[]
temperature?: number

Sampling temperature to use

topP?: number

Total probability mass of tokens to consider at each step.

verbose?: boolean