Interface ChatWatsonxDeployedInput

interface ChatWatsonxDeployedInput {
    authenticator?: string;
    cache?: boolean | BaseCache<Generation[]>;
    callbackManager?: CallbackManager;
    callbacks?: Callbacks;
    disableStreaming?: boolean;
    frequencyPenalty?: undefined;
    headers?: undefined;
    idOrName?: string;
    logprobs?: undefined;
    maxConcurrency?: number;
    maxRetries?: number;
    maxTokens?: undefined;
    messages?: undefined;
    metadata?: Record<string, unknown>;
    modelId?: undefined;
    n?: undefined;
    onFailedAttempt?: FailedAttemptHandler;
    presencePenalty?: undefined;
    projectId?: undefined;
    responseFormat?: undefined;
    serviceUrl: string;
    spaceId?: undefined;
    streaming?: boolean;
    tags?: string[];
    temperature?: undefined;
    timeLimit?: undefined;
    toolChoice?: undefined;
    toolChoiceOption?: undefined;
    tools?: undefined;
    topLogprobs?: undefined;
    topP?: undefined;
    verbose?: boolean;
    version: string;
    watsonxCallbacks?: RequestCallbacks<any>;
}

Hierarchy

  • BaseChatModelParams
  • WatsonxDeployedParams
  • Neverify<TextChatParams>
    • ChatWatsonxDeployedInput

Properties

authenticator? cache? callbackManager? callbacks? disableStreaming? frequencyPenalty? headers? idOrName? logprobs? maxConcurrency? maxRetries? maxTokens? messages? metadata? modelId? n? onFailedAttempt? presencePenalty? projectId? responseFormat? serviceUrl spaceId? streaming? tags? temperature? timeLimit? toolChoice? toolChoiceOption? tools? topLogprobs? topP? verbose? version watsonxCallbacks?

Properties

Optionalauthenticator

authenticator?: string

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.

OptionalfrequencyPenalty

frequencyPenalty?: undefined

Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.

Optionalheaders

headers?: undefined

OptionalidOrName

idOrName?: string

Optionallogprobs

logprobs?: undefined

Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the content of message.

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.

OptionalmaxTokens

maxTokens?: undefined

The maximum number of tokens that can be generated in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length.

Optionalmessages

messages?: undefined

The messages for this chat session.

Optionalmetadata

metadata?: Record<string, unknown>

OptionalmodelId

modelId?: undefined

The model to use for the chat completion.

Please refer to the list of models.

Optionaln

n?: undefined

How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs.

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.

OptionalpresencePenalty

presencePenalty?: undefined

Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.

OptionalprojectId

projectId?: undefined

The project that contains the resource. Either space_id or project_id has to be given.

OptionalresponseFormat

responseFormat?: undefined

The chat response format parameters.

serviceUrl

serviceUrl: string

OptionalspaceId

spaceId?: undefined

The space that contains the resource. Either space_id or project_id has to be given.

Optionalstreaming

streaming?: boolean

Optionaltags

tags?: string[]

Optionaltemperature

temperature?: undefined

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

We generally recommend altering this or top_p but not both.

OptionaltimeLimit

timeLimit?: undefined

Time limit in milliseconds - if not completed within this time, generation will stop. The text generated so far will be returned along with the `TIME_LIMIT`` stop reason. Depending on the users plan, and on the model being used, there may be an enforced maximum time limit.

OptionaltoolChoice

toolChoice?: undefined

Specifying a particular tool via {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

Only one of tool_choice_option or tool_choice must be present.

OptionaltoolChoiceOption

toolChoiceOption?: undefined

Using none means the model will not call any tool and instead generates a message.

The following options (auto and required) are not yet supported.

Using auto means the model can pick between generating a message or calling one or more tools. Using required means the model must call one or more tools.

Only one of tool_choice_option or tool_choice must be present.

Optionaltools

tools?: undefined

Tool functions that can be called with the response.

OptionaltopLogprobs

topLogprobs?: undefined

An integer specifying the number of most likely tokens to return at each token position, each with an associated log probability. The option logprobs must be set to true if this parameter is used.

OptionaltopP

topP?: undefined

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

We generally recommend altering this or temperature but not both.

Optionalverbose

verbose?: boolean

version

version: string

OptionalwatsonxCallbacks

watsonxCallbacks?: RequestCallbacks<any>

Settings

Member Visibility

On This Page

Properties