Full extracted text content of the document.
Document-level metadata (title, author, page count, etc.).
Optional chunksPre-chunked segments, present when chunking was requested during load.
Optional imagesImages extracted from the document.
Populated only when IngestionConfig.extractImages is true.
Optional tablesStructured tables extracted from the document.
The format that was detected or used to parse the document.
'pdf' | 'md' | 'docx' | 'txt'
The parsed representation of a document returned by
Memory.load(). Contains full text, optional chunks, and any extracted images/tables.