ExtractedDocument class

Document extracted by the core extraction pipeline.

extract and extract_batch return an ExtractionResult envelope whose results field contains these per-document payloads.

Constructors

ExtractedDocument({required String content, required String mimeType, required Metadata metadata, ExtractionMethod? extractionMethod, required List<Table> tables, required DocumentCounts counts, List<String>? detectedLanguages, List<LanguageConfidence>? detectedLanguageConfidences, List<Chunk>? chunks, List<ExtractedImage>? images, List<PageContent>? pages, List<Element>? elements, DjotContent? djotContent, List<OcrElement>? ocrElements, DocumentStructure? document, List<Keyword>? extractedKeywords, double? qualityScore, required List<ProcessingWarning> processingWarnings, List<PdfAnnotation>? annotations, List<ArchiveEntry>? children, List<ExtractedUri>? uris, List<DocumentRevision>? revisions, String? structuredOutput, String? codeIntelligence, List<LlmUsage>? llmUsage, List<Entity>? entities, DocumentSummary? summary, ExtractionConfidence? extractionConfidence, Translation? translation, List<PageClassification>? pageClassifications, RedactionReport? redactionReport, required List<Formula> formulas, required List<PdfFormField> formFields, List<OcrPageFailure>? ocrPageFailures})

const

Properties

annotations → List<PdfAnnotation>?

PDF annotations extracted from the document.

final

children → List<ArchiveEntry>?

Nested extraction results from archive contents.

final

chunks → List<Chunk>?

Text chunks when chunking is enabled.

final

codeIntelligence → String?

Code intelligence results from tree-sitter analysis.

final

content → String

Plain-text representation of the extracted document content.

final

counts → DocumentCounts

Cheap structural counts (pages, tables, images).

final

detectedLanguageConfidences → List<LanguageConfidence>?

Structured per-language detection results: confidence, document share, script, and reliability, alongside the ISO-code-only detected_languages (#261).

final

detectedLanguages → List<String>?

ISO 639-1 language codes detected in the document content.

final

djotContent → DjotContent?

Rich Djot content structure (when extracting Djot documents).

final

document → DocumentStructure?

Structured document tree (when document structure extraction is enabled).

final

elements → List<Element>?

Semantic elements when element-based result format is enabled.

final

entities → List<Entity>?

Named entities detected in content by the NER post-processor.

final

extractedKeywords → List<Keyword>?

Extracted keywords when keyword extraction is enabled.

final

extractionConfidence → ExtractionConfidence?

Confidence score computed by the heuristics pipeline.

final

extractionMethod → ExtractionMethod?

Extraction strategy used to produce the returned text.

final

formFields → List<PdfFormField>

Form fields extracted from a PDF's AcroForm or XFA structure.

final

formulas → List<Formula>

Mathematical formulas recognized in the document.

final

hashCode → int

The hash code for this object.

no setter, override

images → List<ExtractedImage>?

Extracted images from the document.

final

llmUsage → List<LlmUsage>?

LLM token usage and cost data for all LLM calls made during this extraction.

final

metadata → Metadata

Document-level metadata (author, title, dates, format-specific fields).

final

mimeType → String

MIME type of the source document (e.g. "application/pdf").

final

ocrElements → List<OcrElement>?

OCR elements with full spatial and confidence metadata.

final

ocrPageFailures → List<OcrPageFailure>?

Pages whose OCR failed while extraction continued, in the order the failures were reported.

final

pageClassifications → List<PageClassification>?

Per-page classifications produced by the page-classification post-processor.

final

pages → List<PageContent>?

Per-page content when page extraction is enabled.

final

processingWarnings → List<ProcessingWarning>

Non-fatal warnings collected during processing pipeline stages.

final

qualityScore → double?

Text cleanliness/readability score from quality analysis.

final

redactionReport → RedactionReport?

Audit report of redactions applied by the redaction post-processor.

final

revisions → List<DocumentRevision>?

Tracked changes embedded in the source document.

final

runtimeType → Type

A representation of the runtime type of the object.

no setter, inherited

structuredOutput → String?

Structured extraction output from LLM-based JSON schema extraction.

final

summary → DocumentSummary?

Summary of content produced by the summarisation post-processor.

final

tables → List<Table>

Tables extracted from the document, each with structured cell data.

final

translation → Translation?

Translation of content produced by the translation post-processor.

final

uris → List<ExtractedUri>?

URIs/links discovered during document extraction.

final

Methods

noSuchMethod(Invocation invocation) → dynamic

Invoked when a nonexistent method or property is accessed.

inherited

toString() → String

A string representation of this object.

inherited

Operators

operator ==(Object other) → bool

The equality operator.

override