Class: LanguageModelUtility
Class: LanguageModelUtility
Implement local AI language models
Process: Utility
new LanguageModelUtility(initialState)
initialStateObjectcontextUsagenumbercontextWindownumber
Do not use this constructor directly outside of the class itself, as it will not be properly connected to the localAIHandler
Static Methods
The LanguageModelUtility class has the following static methods:
LanguageModelUtility.create(options) Experimental
Returns Promise<LanguageModelUtility>. Creates a new LanguageModelUtility with the provided options.
LanguageModelUtility.availability([options]) Experimental
Returns Promise<string>
Determines the availability of the language model and returns one of the following strings:
availabledownloadabledownloadingunavailable
Instance Properties
The following properties are available on instances of LanguageModelUtility:
languageModelUtility.contextUsage Experimental
A number representing how many tokens are currently in the context window.
languageModelUtility.contextWindow Experimental
A number representing the size of the context window, in tokens.
Instance Methods
The following methods are available on instances of LanguageModelUtility:
languageModelUtility.prompt(input, options) Experimental
inputLanguageModelMessage[]
Returns Promise<string> | Promise<import('stream/web').ReadableStream<string>>. Prompt the model for a response.
languageModelUtility.append(input, options) Experimental
inputLanguageModelMessage[]
Returns Promise<undefined>. Append a message without prompting for a response.
languageModelUtility.measureContextUsage(input, options) Experimental
inputLanguageModelMessage[]
Returns Promise<number>. Measure how many tokens the input would use.
languageModelUtility.clone(options) Experimental
Returns Promise<LanguageModelUtility>. Clones the LanguageModelUtility such that the
context and initial prompt should be preserved.
languageModelUtility.destroy() Experimental
Destroys the model, and any ongoing executions are aborted.