Interface IUtilityAI

Interface

IUtilityAI Defines the contract for a comprehensive Utility AI service.

interface IUtilityAI {
    utilityId: string;
    initialize(config): Promise<void>;
    summarize(textToSummarize, options?): Promise<string>;
    classifyText(textToClassify, options): Promise<ClassificationResult>;
    extractKeywords(textToAnalyze, options?): Promise<string[]>;
    tokenize(text, options?): Promise<string[]>;
    stemTokens(tokens, options?): Promise<string[]>;
    calculateSimilarity(text1, text2, options?): Promise<number>;
    analyzeSentiment(text, options?): Promise<SentimentResult>;
    detectLanguage(text, options?): Promise<LanguageDetectionResult[]>;
    normalizeText(text, options?): Promise<string>;
    generateNGrams(tokens, options): Promise<Record<number, string[][]>>;
    calculateReadability(text, options): Promise<ReadabilityResult>;
    parseJsonSafe<T>(jsonString, options?): Promise<null | T>;
    checkHealth(): Promise<{
        isHealthy: boolean;
        details?: any;
        dependencies?: {
            name: string;
            isHealthy: boolean;
            details?: any;
        }[];
    }>;
    shutdown?(): Promise<void>;
    trainModel?(trainingData, modelType, trainingOptions?): Promise<{
        success: boolean;
        message?: string;
        modelId?: string;
    }>;
    saveTrainedModel?(modelTypeOrId, pathOrStoreId?): Promise<{
        success: boolean;
        pathOrStoreId?: string;
        message?: string;
    }>;
    loadTrainedModel?(modelTypeOrId, pathOrStoreId?): Promise<{
        success: boolean;
        message?: string;
    }>;
}

Implemented by

Methods

initialize summarize classifyText extractKeywords tokenize stemTokens calculateSimilarity analyzeSentiment detectLanguage normalizeText generateNGrams calculateReadability parseJsonSafe checkHealth shutdown? trainModel? saveTrainedModel? loadTrainedModel?

Properties

utilityId

Methods

initialize

summarize

classifyText

extractKeywords

tokenize

stemTokens

calculateSimilarity

analyzeSentiment

detectLanguage

normalizeText

generateNGrams

calculateReadability

parseJsonSafe

  • parseJsonSafe<T>(jsonString, options?): Promise<null | T>

  • Parses a string that is expected to be JSON: as it is, else from inside the Markdown code fence it is or holds, which a model asked for JSON alone often answers in. An LLM-backed class sends a text that still does not parse for repair when attemptFixWithLLM is set.

    Type Parameters

    • T = any

      The expected type of the parsed JSON object.

    Parameters

    • jsonString: string

      The string to parse.

    • Optional options: ParseJsonOptions<T>

      Options for parsing and fixing.

    Returns Promise<null | T>

    The parsed object, or null if parsing and fixing fail.

checkHealth

  • checkHealth(): Promise<{
        isHealthy: boolean;
        details?: any;
        dependencies?: {
            name: string;
            isHealthy: boolean;
            details?: any;
        }[];
    }>

  • Returns Promise<{
        isHealthy: boolean;
        details?: any;
        dependencies?: {
            name: string;
            isHealthy: boolean;
            details?: any;
        }[];
    }>

Optional shutdown

Optional trainModel

  • trainModel(trainingData, modelType, trainingOptions?): Promise<{
        success: boolean;
        message?: string;
        modelId?: string;
    }>

  • Parameters

    • trainingData: any[]
    • modelType: string
    • Optional trainingOptions: Record<string, any>

    Returns Promise<{
        success: boolean;
        message?: string;
        modelId?: string;
    }>

Optional saveTrainedModel

  • saveTrainedModel(modelTypeOrId, pathOrStoreId?): Promise<{
        success: boolean;
        pathOrStoreId?: string;
        message?: string;
    }>

  • Parameters

    • modelTypeOrId: string
    • Optional pathOrStoreId: string

    Returns Promise<{
        success: boolean;
        pathOrStoreId?: string;
        message?: string;
    }>

Optional loadTrainedModel

  • loadTrainedModel(modelTypeOrId, pathOrStoreId?): Promise<{
        success: boolean;
        message?: string;
    }>

  • Parameters

    • modelTypeOrId: string
    • Optional pathOrStoreId: string

    Returns Promise<{
        success: boolean;
        message?: string;
    }>

Properties

Readonly utilityId

utilityId: string

Settings

Member Visibility

Theme

On This Page

initializesummarizeclassifyTextextractKeywordstokenizestemTokenscalculateSimilarityanalyzeSentimentdetectLanguagenormalizeTextgenerateNGramscalculateReadabilityparseJsonSafecheckHealthshutdowntrainModelsaveTrainedModelloadTrainedModelutilityId