Upstage Document Transformer

Overview

The Upstage Document Parser is an advanced document transformation service that uses Upstage AI's document parsing API to extract structured content from PDFs, images, and other document formats. It provides intelligent document analysis with OCR capabilities, supporting multiple output formats optimized for downstream processing.

Service Information

Property	Value
Service Name	Upstage document parser
Status	Enabled
Compatible Nodes	Transform Content

When to Use This Service

The Upstage Document Parser is ideal for:

Complex document layouts requiring intelligent parsing
PDFs with mixed content (text, images, tables, forms)
Scanned documents needing OCR processing
Documents requiring structured format conversion
Business documents with forms and tables
Multi-format document processing workflows

API Requirements

This service requires:

Upstage AI → API Key: Valid Upstage AI API key with document parsing capabilities enabled on your project

Parameters

Document Parsing Parameters

Parameter	Type	Default	Options	Description
Output format	Choice	markdown	markdown, html, text	Format for the parsed document output
Include coordinates	Boolean	false	-	Include bounding box coordinates for text elements
OCR mode	Choice	auto	auto, force, none	OCR processing mode for scanned documents

OCR Mode Options

Auto (detect if OCR needed) - Automatically determines if OCR is required