Interface WatsonxCallOptionsChat

interface WatsonxCallOptionsChat {
    callbacks?: Callbacks;
    configurable?: Record<string, any>;
    frequencyPenalty?: number;
    headers?: OutgoingHttpHeaders;
    logitBias?: JsonObject;
    logprobs?: boolean;
    ls_structured_output_format?: {
        kwargs: {
            method: string;
        };
        schema?: JsonSchema7Type;
    };
    maxCompletionTokens?: number;
    maxConcurrency?: number;
    maxRetries?: number;
    maxTokens?: number;
    metadata?: Record<string, unknown>;
    n?: number;
    presencePenalty?: number;
    projectId?: string;
    promptIndex?: number;
    recursionLimit?: number;
    responseFormat?: TextChatResponseFormat;
    runId?: string;
    runName?: string;
    seed?: number;
    signal?: AbortSignal;
    spaceId?: string;
    stop?: string[];
    streaming?: boolean;
    tags?: string[];
    temperature?: number;
    timeLimit?: number;
    timeout?: number;
    toolChoiceOption?: string;
    tool_choice?: string | TextChatParameterTools;
    tools?: TextChatParameterTools[];
    topLogprobs?: number;
    topP?: number;
    watsonxCallbacks?: RequestCallbacks<any>;
}

Hierarchy (view full)

Omit<BaseChatModelCallOptions, "stop">
WatsonxCallParams
WatsonxChatBasicOptions
- WatsonxCallOptionsChat

Properties

`Optional`callbacks

callbacks?: Callbacks

Callbacks for this call and any sub-calls (eg. a Chain calling an LLM). Tags are passed to all callbacks, metadata is passed to handle*Start callbacks.

`Optional`configurable

configurable?: Record<string, any>

Runtime values for attributes previously made configurable on this Runnable, or sub-Runnables.

`Optional`frequencyPenalty

frequencyPenalty?: number

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.

`Optional`headers

headers?: OutgoingHttpHeaders

`Optional`logitBias

logitBias?: JsonObject

Increasing or decreasing probability of tokens being selected during generation; a positive bias makes a token more likely to appear, while a negative bias makes it less likely.

`Optional`logprobs

logprobs?: boolean

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.

`Optional`ls_structured_output_format

ls_structured_output_format?: {
    kwargs: {
        method: string;
    };
    schema?: JsonSchema7Type;
}

Describes the format of structured outputs. This should be provided if an output is considered to be structured

Type declaration

kwargs: {
method: string;
}
An object containing the method used for structured output (e.g., "jsonMode").
- method: string
Optionalschema?: JsonSchema7Type
The JSON schema describing the expected output structure.

`Optional`maxCompletionTokens

maxCompletionTokens?: number

`Optional`maxConcurrency

maxConcurrency?: number

Maximum number of parallel calls to make.

`Optional`maxRetries

maxRetries?: number

`Optional`maxTokens

maxTokens?: number

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. Set to 0 for the model's configured max generated tokens. This value is now deprecated in favor of maxCompletionTokens. If specified together with maxCompletionTokens, maxTokens will be ignored.

`Optional`metadata

metadata?: Record<string, unknown>

Metadata for this call and any sub-calls (eg. a Chain calling an LLM). Keys should be strings, values should be JSON-serializable.

`Optional`n

n?: number

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.

`Optional`presencePenalty

presencePenalty?: number

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.

`Optional`projectId

projectId?: string

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

`Optional`promptIndex

promptIndex?: number

`Optional`recursionLimit

recursionLimit?: number

Maximum number of times a call can recurse. If not provided, defaults to 25.

`Optional`responseFormat

responseFormat?: TextChatResponseFormat

The chat response format parameters.

`Optional`runId

runId?: string

Unique identifier for the tracer run for this call. If not provided, a new UUID will be generated.

`Optional`runName

runName?: string

Name for the tracer run for this call. Defaults to the name of the class.

`Optional`seed

seed?: number

Random number generator seed to use in sampling mode for experimental repeatability.

`Optional`signal

signal?: AbortSignal

Abort signal for this call. If provided, the call will be aborted when the signal is aborted.

See

https://developer.mozilla.org/en-US/docs/Web/API/AbortSignal

`Optional`spaceId

spaceId?: string

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

`Optional`stop

stop?: string[]

Stop sequences are one or more strings which will cause the text generation to stop if/when they are produced as part of the output. Stop sequences encountered prior to the minimum number of tokens being generated will be ignored.

`Optional`streaming

streaming?: boolean

`Optional`tags

tags?: string[]

Tags for this call and any sub-calls (eg. a Chain calling an LLM). You can use these to filter calls.

`Optional`temperature

temperature?: number

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.

`Optional`timeLimit

timeLimit?: number

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.

`Optional`timeout

timeout?: number

Timeout for this call in milliseconds.

`Optional`toolChoiceOption

toolChoiceOption?: string

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.

`Optional`tool_choice

tool_choice?: string | TextChatParameterTools

Specifies how the chat model should use tools.

Default

undefined

Possible values:
- "auto": The model may choose to use any of the provided tools, or none.
- "any": The model must use one of the provided tools.
- "none": The model must not use any tools.
- A string (not "auto", "any", or "none"): The name of a specific tool the model must use.
- An object: A custom schema specifying tool choice parameters. Specific to the provider.

Note: Not all providers support tool_choice. An error will be thrown
if used with an unsupported model.

`Optional`tools

tools?: TextChatParameterTools[]

Tool functions that can be called with the response.

`Optional`topLogprobs

topLogprobs?: number

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.

`Optional`topP

topP?: number

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.

`Optional`watsonxCallbacks

watsonxCallbacks?: RequestCallbacks<any>

Interface WatsonxCallOptionsChat

Hierarchy (view full)

Index

Properties

Properties

Optionalcallbacks

Optionalconfigurable

OptionalfrequencyPenalty

Optionalheaders

OptionallogitBias

Optionallogprobs

Optionalls_structured_output_format

Type declaration

kwargs: { method: string; }

method: string

Optionalschema?: JsonSchema7Type

OptionalmaxCompletionTokens

OptionalmaxConcurrency

OptionalmaxRetries

OptionalmaxTokens

Optionalmetadata

Optionaln

OptionalpresencePenalty

OptionalprojectId

OptionalpromptIndex

OptionalrecursionLimit

OptionalresponseFormat

OptionalrunId

OptionalrunName

Optionalseed

Optionalsignal

See

OptionalspaceId

Optionalstop

Optionalstreaming

Optionaltags

Optionaltemperature

OptionaltimeLimit

Optionaltimeout

OptionaltoolChoiceOption

Optionaltool_choice

Default

Optionaltools

OptionaltopLogprobs

OptionaltopP

OptionalwatsonxCallbacks

Settings

On This Page

`Optional`callbacks

`Optional`configurable

`Optional`frequencyPenalty

`Optional`headers

`Optional`logitBias

`Optional`logprobs

`Optional`ls_structured_output_format

kwargs: {
method: string;
}

`Optional`schema?: JsonSchema7Type

`Optional`maxCompletionTokens

`Optional`maxConcurrency

`Optional`maxRetries

`Optional`maxTokens

`Optional`metadata

`Optional`n

`Optional`presencePenalty

`Optional`projectId

`Optional`promptIndex

`Optional`recursionLimit

`Optional`responseFormat

`Optional`runId

`Optional`runName

`Optional`seed

`Optional`signal

`Optional`spaceId

`Optional`stop

`Optional`streaming

`Optional`tags

`Optional`temperature

`Optional`timeLimit

`Optional`timeout

`Optional`toolChoiceOption

`Optional`tool_choice

`Optional`tools

`Optional`topLogprobs

`Optional`topP

`Optional`watsonxCallbacks