Interface BaseChatCohereInput

Input interface for ChatCohere

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

Hierarchy

  • BaseChatModelParams
    • BaseChatCohereInput

Properties

apiKey? cache? callbackManager? callbacks? disableStreaming? maxConcurrency? maxRetries? metadata? model? onFailedAttempt? streamUsage? streaming? tags? temperature? verbose?

Properties

OptionalapiKey

apiKey?: string

The API key to use.

Default

{process.env.COHERE_API_KEY}

Optionalcache

cache?: boolean | BaseCache<Generation[]>

OptionalcallbackManager

callbackManager?: CallbackManager

Deprecated

Use callbacks instead

Optionalcallbacks

callbacks?: Callbacks

OptionaldisableStreaming

disableStreaming?: boolean

Whether to disable streaming.

If streaming is bypassed, then stream() will defer to invoke().

  • If true, will always bypass streaming case.
  • If false (default), will always use streaming case if available.

OptionalmaxConcurrency

maxConcurrency?: number

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

OptionalmaxRetries

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.

Optionalmetadata

metadata?: Record<string, unknown>

Optionalmodel

model?: string

The name of the model to use.

Default

{"command"}

OptionalonFailedAttempt

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.

OptionalstreamUsage

streamUsage?: 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

streaming?: boolean

Whether or not to stream the response.

Default

{false}

Optionaltags

tags?: string[]

Optionaltemperature

temperature?: 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

verbose?: boolean

Settings

Member Visibility

On This Page

Properties