Type Alias ChatCohereInput

ChatCohereInput: {
    apiKey?: undefined | string;
    cache?: undefined | boolean | BaseCache<Generation[]>;
    callbackManager?: undefined | CallbackManager;
    callbacks?: undefined | Callbacks;
    client: undefined | CustomClient;
    maxConcurrency?: undefined | number;
    maxRetries?: undefined | number;
    metadata?: undefined | Record<string, unknown>;
    model?: undefined | string;
    onFailedAttempt?: undefined | FailedAttemptHandler;
    streamUsage?: undefined | boolean;
    streaming?: undefined | boolean;
    tags?: undefined | string[];
    temperature?: undefined | number;
    verbose?: undefined | boolean;
}

Type declaration

  • OptionalapiKey?: undefined | string

    The API key to use.

    Default

    {process.env.COHERE_API_KEY}
  • Optionalcache?: undefined | boolean | BaseCache<Generation[]>
  • OptionalcallbackManager?: undefined | CallbackManager

    Deprecated

    Use callbacks instead

  • Optionalcallbacks?: undefined | Callbacks
  • client: undefined | CustomClient
  • OptionalmaxConcurrency?: undefined | number

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

  • OptionalmaxRetries?: undefined | number

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

  • Optionalmetadata?: undefined | Record<string, unknown>
  • Optionalmodel?: undefined | string

    The name of the model to use.

    Default

    {"command"}
  • OptionalonFailedAttempt?: undefined | 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.

  • OptionalstreamUsage?: undefined | boolean

    Whether or not to include token usage when streaming. This will include an extra chunk at the end of the stream with eventType: "stream-end" and the token usage in usage_metadata.

    Default

    {true}
  • Optionalstreaming?: undefined | boolean

    Whether or not to stream the response.

    Default

    {false}
  • Optionaltags?: undefined | string[]
  • Optionaltemperature?: undefined | number

    What sampling temperature to use, between 0.0 and 2.0. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

    Default

    {0.3}
  • Optionalverbose?: undefined | boolean

Settings

Member Visibility