The PDF OCR Reader node extracts text from scanned or image-based PDF documents using AI vision models. It supports advanced handwriting recognition, multilingual input, and structured output for use in automation flows.<hr><h2>Node Overview</h2>Purpose: Convert non-text PDFs into structured, readable text Usage: Document digitization, handwriting recognition, form extraction Model Requirement: Requires AI vision models for processing<hr><h2>Node Inputs</h2><h3>Required</h3><ul class="accent-bullets"><li>File Name Upload or select a PDF from your MergePoint storage</li></ul><hr><h3>Optional</h3><ul class="accent-bullets"><li>Use Link Read from a publicly accessible PDF URL</li><li>Specify Pages Limit processing to specific page numbers or ranges (e.g., <code class="inline-code-shadow bg-gray-100 border border-gray-200/60 dark:border-gray-800 font-medium dark:bg-gray-700/60 text-gray-700 dark:text-gray-200 font-mono text-md px-1 py-0.5 rounded-[0.2rem] [&amp;::before]:content-none [&amp;::after]:content-none">1-3</code>, <code class="inline-code-shadow bg-gray-100 border border-gray-200/60 dark:border-gray-800 font-medium dark:bg-gray-700/60 text-gray-700 dark:text-gray-200 font-mono text-md px-1 py-0.5 rounded-[0.2rem] [&amp;::before]:content-none [&amp;::after]:content-none">5</code>, <code class="inline-code-shadow bg-gray-100 border border-gray-200/60 dark:border-gray-800 font-medium dark:bg-gray-700/60 text-gray-700 dark:text-gray-200 font-mono text-md px-1 py-0.5 rounded-[0.2rem] [&amp;::before]:content-none [&amp;::after]:content-none">7-10</code>)</li><li>Split PDF Content by Page Returns a list where each item contains extracted text from one page Useful for workflows that need per-page parsing</li><li>Image Model Choose the AI model to use for OCR (see Available Models below)</li><li>Temperature Controls OCR creativity/accuracy (range: 0–1). Lower is more precise, higher allows for softer interpretation.</li><li>Cache Response Enable to store results and avoid reprocessing the same file</li></ul><hr><h3>Show As Input Options</h3>Enable dynamic control from previous nodes:<ul class="accent-bullets"><li><code class="inline-code-shadow bg-gray-100 border border-gray-200/60 dark:border-gray-800 font-medium dark:bg-gray-700/60 text-gray-700 dark:text-gray-200 font-mono text-md px-1 py-0.5 rounded-[0.2rem] [&amp;::before]:content-none [&amp;::after]:content-none">Temperature</code></li></ul><hr><h2>Node Output</h2><ul class="accent-bullets"><li>PDF Contents Returns either:<ul class="accent-bullets"><li>A single string (full document)</li><li>A list of page-level strings (if "Split by Page" is enabled)</li></ul></li></ul><hr><h2>Node Functionality</h2>This node can:<ul class="accent-bullets"><li>Perform OCR on image-based PDFs</li><li>Read printed text and handwriting</li><li>Handle multi-page documents</li><li>Detect content in various layouts and languages</li><li>Accept file uploads or public URLs</li></ul><hr><h2>Common Use Cases</h2><h3>1. Scanned Contracts</h3>Input: <code class="inline-code-shadow bg-gray-100 border border-gray-200/60 dark:border-gray-800 font-medium dark:bg-gray-700/60 text-gray-700 dark:text-gray-200 font-mono text-md px-1 py-0.5 rounded-[0.2rem] [&amp;::before]:content-none [&amp;::after]:content-none">contracts_scanned.pdf</code> Setup: Advanced model, all pages Output: Searchable legal text Use Case: Document archiving and search<hr><h3>2. Receipts / Invoices</h3>Input: <code class="inline-code-shadow bg-gray-100 border border-gray-200/60 dark:border-gray-800 font-medium dark:bg-gray-700/60 text-gray-700 dark:text-gray-200 font-mono text-md px-1 py-0.5 rounded-[0.2rem] [&amp;::before]:content-none [&amp;::after]:content-none">expenses_receipts.pdf</code> Setup: Split by page, mid-range temperature Output: Line items per page Use Case: Automated expense reporting<hr><h3>3. Handwritten Notes</h3>Input: <code class="inline-code-shadow bg-gray-100 border border-gray-200/60 dark:border-gray-800 font-medium dark:bg-gray-700/60 text-gray-700 dark:text-gray-200 font-mono text-md px-1 py-0.5 rounded-[0.2rem] [&amp;::before]:content-none [&amp;::after]:content-none">meeting_notes_handwritten.pdf</code> Setup: Claude Sonnet or GPT-4.1 Vision Output: Parsed, readable notes Use Case: Digitizing notebooks and whiteboard scans

Nodes

PDF OCR Reader

Invoice Data Extraction

Proforma Invoice Association

Outlook → Salesforce Email & Note Capture Workflow

Use Cases & Solutions

Form Studio

Getting Started

Task List Panel

Assigning Tasks 

All Tasks in One Dynamic, Smart Table

Approve / Reject Tasks

Human-in-the-Loop

Layout Components

Button Components

Input Components

Select Components

Data Table Component

Build Any UI

Triggers 101

Manual Trigger

Scheduled Trigger

Triggers

Google Sheets Writer

Web Search

Step Output

Data

Chat

Info Access

Chat best practices 

Mergepoint Chat

Creating Knowledge

Collections Management

Data Sources & Sync

AI Optimization

Enrichment Tool

Advanced Features

Mergebase

How to Submit a Feedback (Bug, Feature, or Enhancement)

Contact Us

Roles & Permissions

Administration

Docs

Mergepoint