Skip to main content

Interface: ExtractedImage

Defined in: packages/agentos/src/cognition/memory/io/facade/types.ts:737

An image extracted from a document during ingestion.

Properties​

caption?​

optional caption: string

Defined in: packages/agentos/src/cognition/memory/io/facade/types.ts:753

Auto-generated or OCR-derived caption. Present when a vision LLM is configured and extractImages: true.

data​

data: Buffer

Defined in: packages/agentos/src/cognition/memory/io/facade/types.ts:741

Raw image bytes (PNG, JPEG, WebP, etc.).

embedding?​

optional embedding: number[]

Defined in: packages/agentos/src/cognition/memory/io/facade/types.ts:764

Dense embedding of the image caption or visual content. Only present when embeddings were computed during extraction.

mimeType​

mimeType: string

Defined in: packages/agentos/src/cognition/memory/io/facade/types.ts:747

MIME type of data.

Example​

'image/png' | 'image/jpeg'

pageNumber?​

optional pageNumber: number

Defined in: packages/agentos/src/cognition/memory/io/facade/types.ts:758

Page number the image appears on (1-based, PDF/DOCX).