Mistral AI OCR Transformer

Overview

Mistral AI Document OCR is an advanced optical character recognition service that transforms PDFs, Office documents (DOCX, PPTX), and images into structured text. It uses Mistral AI's latest OCR model to extract text with high accuracy, supporting both Markdown and structured JSON output formats.

Service Information

Property	Value
Service Name	Mistral AI document OCR
Status	Enabled
Compatible Nodes	Transform Content

When to Use This Service

Mistral AI OCR is ideal for:

Scanned PDFs and documents without selectable text
Office documents (DOCX, PPTX) requiring text extraction
Images containing text (PNG, JPG, etc.)
Documents requiring structured JSON output
Multi-page documents with mixed content types
Documents needing high-accuracy OCR processing

API Requirements

This service requires:

Mistral AI → API Key: Valid Mistral AI API key with OCR capabilities enabled on your project

Parameters

OCR Parameters

Parameter	Type	Default	Options	Description
Result format	Choice	Markdown	Markdown, JSON Structured	Output format for the OCR results
Select pages	Text	all	(comma-separated numbers or 'all')	Specify which pages to process. Use comma-separated page numbers (e.g., "1,3,5") or "all" for all pages

Conditional Parameters

When Result format is set to "JSON Structured":