Class: LLMUtilityAI

Defined in: packages/agentos/src/cognition/nlp/ai_utilities/LLMUtilityAI.ts:105

Interface

IUtilityAI Defines the contract for a comprehensive Utility AI service.

Implements

• IUtilityAI
• IPromptEngineUtilityAI

Constructors

Constructor

new LLMUtilityAI(utilityId?): LLMUtilityAI

Defined in: packages/agentos/src/cognition/nlp/ai_utilities/LLMUtilityAI.ts:111

Parameters

utilityId?

string

Returns

LLMUtilityAI

Properties

utilityId

readonly utilityId: string

Defined in: packages/agentos/src/cognition/nlp/ai_utilities/LLMUtilityAI.ts:106

Implementation of

IUtilityAI.utilityId

Methods

analyzeSentiment()

analyzeSentiment(text, options?): Promise<SentimentResult>

Defined in: packages/agentos/src/cognition/nlp/ai_utilities/LLMUtilityAI.ts:479

Parameters

text

string

options?

SentimentAnalysisOptions

Returns

Promise<SentimentResult>

Implementation of

IUtilityAI.analyzeSentiment

---

calculateReadability()

calculateReadability(text, options): Promise<ReadabilityResult>

Defined in: packages/agentos/src/cognition/nlp/ai_utilities/LLMUtilityAI.ts:665

Parameters

text

string

options

ReadabilityOptions

Returns

Promise<ReadabilityResult>

Implementation of

IUtilityAI.calculateReadability

---

calculateSimilarity()

calculateSimilarity(text1, text2, options?): Promise<number>

Defined in: packages/agentos/src/cognition/nlp/ai_utilities/LLMUtilityAI.ts:594

Parameters

text1

string

text2

string

options?

SimilarityOptions

Returns

Promise<number>

Implementation of

IUtilityAI.calculateSimilarity

---

checkHealth()

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

Defined in: packages/agentos/src/cognition/nlp/ai_utilities/LLMUtilityAI.ts:791

Returns

Promise<{ dependencies?: object[]; details?: any; isHealthy: boolean; }>

Implementation of

IUtilityAI.checkHealth

---

classifyText()

classifyText(textToClassify, options): Promise<ClassificationResult>

Defined in: packages/agentos/src/cognition/nlp/ai_utilities/LLMUtilityAI.ts:399

Parameters

textToClassify

string

options

ClassificationOptions

Returns

Promise<ClassificationResult>

Implementation of

IUtilityAI.classifyText

---

detectLanguage()

detectLanguage(text, options?): Promise<LanguageDetectionResult[]>

Defined in: packages/agentos/src/cognition/nlp/ai_utilities/LLMUtilityAI.ts:526

Parameters

text

string

options?

LanguageDetectionOptions

Returns

Promise<LanguageDetectionResult[]>

Implementation of

IUtilityAI.detectLanguage

---

extractKeywords()

extractKeywords(textToAnalyze, options?): Promise<string[]>

Defined in: packages/agentos/src/cognition/nlp/ai_utilities/LLMUtilityAI.ts:455

Parameters

textToAnalyze

string

options?

KeywordExtractionOptions

Returns

Promise<string[]>

Implementation of

IUtilityAI.extractKeywords

---

generateNGrams()

generateNGrams(tokens, options): Promise<Record<number, string[][]>>

Defined in: packages/agentos/src/cognition/nlp/ai_utilities/LLMUtilityAI.ts:645

Parameters

tokens

string[]

options

NGramOptions

Returns

Promise<Record<number, string[][]>>

Implementation of

IUtilityAI.generateNGrams

---

initialize()

initialize(config): Promise<void>

Defined in: packages/agentos/src/cognition/nlp/ai_utilities/LLMUtilityAI.ts:115

Parameters

config

LLMUtilityAIConfig

Returns

Promise<void>

Implementation of

IUtilityAI.initialize

---

loadTrainedModel()

loadTrainedModel(): Promise<{ message?: string; success: boolean; }>

Defined in: packages/agentos/src/cognition/nlp/ai_utilities/LLMUtilityAI.ts:819

Returns

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

Implementation of

IUtilityAI.loadTrainedModel

---

normalizeText()

normalizeText(text, options?): Promise<string>

Defined in: packages/agentos/src/cognition/nlp/ai_utilities/LLMUtilityAI.ts:621

Parameters

text

string

options?

TextNormalizationOptions

Returns

Promise<string>

Implementation of

IUtilityAI.normalizeText

---

parseJsonSafe()

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

Defined in: packages/agentos/src/cognition/nlp/ai_utilities/LLMUtilityAI.ts:321

The JSON the text holds, read as StatisticalUtilityAI reads it (parseReplyJson: the text as it is, else inside the first Markdown code fence it holds, backticks inside a sentence opening none, with a language tag or none and with words before or after it, up to the first later line that starts with as many backticks as opened the fence or more), then a check against targetSchema with Ajv when given, as StatisticalUtilityAI checks it: the standard formats checked, a keyword or a format Ajv does not know passed over, and a value coerced to the type its schema names where it can (targetSchemaChecks). With attemptFixWithLLM, a text that fails either is sent for repair, up to maxRepairAttempts times (1 unless it is a whole number of 1 or more), each repair on the text the last one answered, whose answer is read the same way, on llmModelIdForFix (else jsonFixerModelId, else defaultModelId) and llmProviderIdForFix (else defaultProviderId). A repair request names targetSchema when given, and the schema's errors when the text parsed and failed it. Answers null when no repair parses and passes the schema, or a repair call fails. No text can pass a targetSchema that Ajv cannot compile, that takes the draft-07 meta-schema's $id or that is marked $async: the call answers null at once, with a warning, and asks for no repair.

Type Parameters

T

T = any

Parameters

jsonString

string

options?

ParseJsonOptions<T>

Returns

Promise<T | null>

Implementation of

IUtilityAI.parseJsonSafe

---

saveTrainedModel()

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

Defined in: packages/agentos/src/cognition/nlp/ai_utilities/LLMUtilityAI.ts:816

Returns

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

Implementation of

IUtilityAI.saveTrainedModel

---

shutdown()

shutdown(): Promise<void>

Defined in: packages/agentos/src/cognition/nlp/ai_utilities/LLMUtilityAI.ts:823

Returns

Promise<void>

Implementation of

IUtilityAI.shutdown

---

stemTokens()

stemTokens(tokens, _options?): Promise<string[]>

Defined in: packages/agentos/src/cognition/nlp/ai_utilities/LLMUtilityAI.ts:588

Parameters

tokens

string[]

_options?

StemmingOptions

Returns

Promise<string[]>

Implementation of

IUtilityAI.stemTokens

---

summarize()

summarize(textToSummarize, options?): Promise<string>

Defined in: packages/agentos/src/cognition/nlp/ai_utilities/LLMUtilityAI.ts:267

Parameters

textToSummarize

string

options?

SummarizationOptions

Returns

Promise<string>

Implementation of

IUtilityAI.summarize

---

summarizeConversationHistory()

summarizeConversationHistory(messages, targetTokenCount, modelInfo, preserveImportantMessages?): Promise<{ finalTokenCount: number; messagesSummarized: number; originalTokenCount: number; summaryMessages: ConversationMessage[]; }>

Defined in: packages/agentos/src/cognition/nlp/ai_utilities/LLMUtilityAI.ts:717

Summarizes conversation history to fit within token constraints, attempting to preserve key information.

Parameters

messages

readonly ConversationMessage[]

The array of conversation messages to summarize.

targetTokenCount

number

The desired maximum token count for the summary.

modelInfo

Readonly<ModelTargetInfo>

Information about the model for which the summary is being prepared.

preserveImportantMessages?

boolean

If true, attempt to identify and keep important messages verbatim.

Returns

Promise<{ finalTokenCount: number; messagesSummarized: number; originalTokenCount: number; summaryMessages: ConversationMessage[]; }>

A summary (which might be a single system message or a condensed list of messages), and metadata about the summarization.

Implementation of

IPromptEngineUtilityAI.summarizeConversationHistory

---

summarizeRAGContext()

summarizeRAGContext(context, targetTokenCount, modelInfo, preserveSourceAttribution?): Promise<{ finalTokenCount: number; originalTokenCount: number; preservedSources?: string[]; summary: string; }>

Defined in: packages/agentos/src/cognition/nlp/ai_utilities/LLMUtilityAI.ts:762

Summarizes retrieved RAG context to fit token limits, ideally preserving source attribution if possible.

Parameters

context

The RAG context to summarize.

string | readonly object[]

targetTokenCount

number

The desired maximum token count for the summarized context.

modelInfo

Readonly<ModelTargetInfo>

Information about the model.

preserveSourceAttribution?

boolean

If true, attempt to retain source information in the summary.

Returns

Promise<{ finalTokenCount: number; originalTokenCount: number; preservedSources?: string[]; summary: string; }>

The summarized text and metadata.

Implementation of

IPromptEngineUtilityAI.summarizeRAGContext

---

tokenize()

tokenize(text, options?): Promise<string[]>

Defined in: packages/agentos/src/cognition/nlp/ai_utilities/LLMUtilityAI.ts:559

Parameters

text

string

options?

TokenizationOptions

Returns

Promise<string[]>

Implementation of

IUtilityAI.tokenize

---

trainModel()

trainModel(): Promise<{ message?: string; modelId?: string; success: boolean; }>

Defined in: packages/agentos/src/cognition/nlp/ai_utilities/LLMUtilityAI.ts:813

Returns

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

Implementation of

IUtilityAI.trainModel