Config

Configuration types for controlling model behavior.

Config

The Config function creates a Zod schema for parsing model configuration. All fields are optional and provider-specific.

import { Config } from "@adaline/types";

const config = Config().parse({
  temperature: 0.7,
  maxTokens: 500,
  topP: 0.9,
  frequencyPenalty: 0,
  presencePenalty: 0,
  stop: ["\n"],
});

Common Fields

temperature

number

Controls randomness. 0 is deterministic, higher values are more creative. Range: 0 to 2.

maxTokens

number

Maximum number of tokens to generate.

topP

number

Nucleus sampling threshold. Range: 0 to 1.

frequencyPenalty

number

Penalize tokens based on frequency. Range: -2 to 2.

presencePenalty

number

Penalize tokens based on presence. Range: -2 to 2.

stop

string[]

Stop sequences that halt generation.

seed

number

Random seed for deterministic outputs (provider support varies).

Embedding Config

For embedding models, the config supports:

const embeddingConfig = Config().parse({
  encodingFormat: "float",
  dimensions: 256,
});

encodingFormat

string

The encoding format for embeddings. Common values: "float", "base64".

dimensions

number

The number of dimensions for the output embeddings.

Get started

API

SDKs

Proxy

Config

Config

Config

Common Fields

Embedding Config

​Config

​Config

​Common Fields

​Embedding Config

Config

Config

Common Fields

Embedding Config