parse node converts raw documents (PDFs, images) into Doclo’s intermediate representation (DocumentIR) with text content and layout information.
Basic Usage
Configuration Options
Options Reference
| Option | Type | Default | Description |
|---|---|---|---|
provider | OCRProvider | VLMProvider | Required | Provider for parsing |
format | 'text' | 'markdown' | 'html' | 'text' | Output format |
describeFigures | boolean | false | Describe charts/diagrams (VLM only) |
includeImages | boolean | false | Extract embedded images |
citations | CitationConfig | - | Citation tracking configuration |
consensus | ConsensusConfig | - | Multi-run voting for accuracy |
chunked | object | - | Large document chunking |
reasoning | object | - | Extended reasoning (VLM only) |
additionalInstructions | string | - | Custom parsing guidance |
Output Format
Text Format (Default)
Line-by-line output with position data:Markdown Format
Preserves document structure (tables, headers, lists):HTML Format
Rich formatting with semantic structure:Provider Types
OCR Provider
Use for text-heavy documents requiring high accuracy:VLM Provider
Use for visual documents or when you need structure detection:Large Document Handling
For PDFs with many pages, use chunking to avoid timeouts and memory issues:Citation Tracking
Enable line-level citations for source tracking:lineId (e.g., p1_l5 for page 1, line 5) that can be referenced during extraction.
Extended Reasoning
For VLM providers that support it, enable extended reasoning:Custom Instructions
Add parsing guidance:Output: DocumentIR
The parse node outputs aDocumentIR object: