Interface: IngestionStatsDto

@kortexya/reasoninglayer

---

@kortexya/reasoninglayer / Ingestion / IngestionStatsDto

Interface: IngestionStatsDto

Defined in: src/types/ingestion.ts:576

Ingestion statistics.

Remarks

Comprehensive statistics from the ingestion pipeline including chunk processing, entity extraction, deduplication, relations, and quality metrics.

Properties

chunksFailed

chunksFailed: number

Defined in: src/types/ingestion.ts:578

Number of chunks that failed extraction.

---

chunksProcessed

chunksProcessed: number

Defined in: src/types/ingestion.ts:580

Number of text chunks processed.

---

communityStats?

optional communityStats: CommunityStatsDto

Defined in: src/types/ingestion.ts:582

Community detection statistics (GraphRAG-style clustering).

---

entitiesCreated

entitiesCreated: number

Defined in: src/types/ingestion.ts:584

Number of new entities created.

---

entitiesExtracted

entitiesExtracted: number

Defined in: src/types/ingestion.ts:586

Number of entities extracted from text.

---

entitiesFilteredLowQuality?

optional entitiesFilteredLowQuality: number

Defined in: src/types/ingestion.ts:588

Number of entities filtered out due to low-quality names.

---

entitiesMerged

entitiesMerged: number

Defined in: src/types/ingestion.ts:590

Number of entities merged (deduplicated).

---

entitiesPendingReview

entitiesPendingReview: number

Defined in: src/types/ingestion.ts:592

Number of entities pending human review.

---

estimatedCostUsd?

optional estimatedCostUsd: number | null

Defined in: src/types/ingestion.ts:594

Estimated USD cost of LLM API calls (if model pricing is available).

---

failedChunks?

optional failedChunks: ChunkFailureDto[]

Defined in: src/types/ingestion.ts:596

Details of failed chunks (first 5).

---

groundingStats?

optional groundingStats: GroundingStatsDto

Defined in: src/types/ingestion.ts:598

Entity grounding statistics (linking to external ontologies).

---

model?

optional model: string | null

Defined in: src/types/ingestion.ts:600

LLM model used for extraction.

---

pipelineQuality?

optional pipelineQuality: PipelineQualityStatsDto

Defined in: src/types/ingestion.ts:602

Pipeline quality statistics (inference rules, validation, feedback loop).

---

processingTimeMs

processingTimeMs: number

Defined in: src/types/ingestion.ts:604

Processing time in milliseconds.

---

referencesResolved

referencesResolved: number

Defined in: src/types/ingestion.ts:606

Number of references resolved.

---

referencesUnresolved

referencesUnresolved: number

Defined in: src/types/ingestion.ts:608

Number of unresolved references (residuated).

---

relationsExtracted

relationsExtracted: number

Defined in: src/types/ingestion.ts:610

Number of relations extracted from text.

---

relationsIntegrated

relationsIntegrated: number

Defined in: src/types/ingestion.ts:612

Number of relations integrated as features on entities.

---

sortNames

sortNames: string[]

Defined in: src/types/ingestion.ts:614

Names of created/reused sorts.

---

sortsCreated

sortsCreated: number

Defined in: src/types/ingestion.ts:616

Number of new sorts created.

---

sortsReused

sortsReused: number

Defined in: src/types/ingestion.ts:618

Number of existing sorts reused.

---

termIds

termIds: string[]

Defined in: src/types/ingestion.ts:620

IDs of created/updated terms.

---

tokenUsage?

optional tokenUsage: TokenUsageDto

Defined in: src/types/ingestion.ts:622

Token usage from LLM API calls during this ingestion.