# Verify and correct PDF OCR text with MinerU and Qwen2.5-VL: n8n workflow

> Runs on demand. It calls services over plain HTTP rather than through connectors. 13 steps, 2 loops or waits: a working afternoon to understand properly.

Source: https://millionrounds.com/workflow/verify-and-correct-pdf-ocr-text-with-mineru-and-qwen2-5-vl (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [Documents and files](https://millionrounds.com/workflows?category=Documents+and+files#library)

# Verify and correct PDF OCR text with MinerU and Qwen2.5-VL

Runs on demand. It calls services over plain HTTP rather than through connectors. 13 steps, 2 loops or waits: a working afternoon to understand properly.

Medium

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fverify-and-correct-pdf-ocr-text-with-mineru-and-qwen2-5-vl)

**13 steps** Medium: a working afternoon

**0** Branches: places the flow splits

**2** Loops or waits

**0** Services by connector: it calls them over plain HTTP

## The flow

Logic 6 Service 7

The steps in the order they run, from what starts it.

- 1 **Read/Write Files from Disk** Read Write File *Service*
- 2 **PDF Convert** Pdf Convert *Service*
- 3 **Split Out** Split Out *Logic*
- 4 **HTTP Request5** Http Request *Service*
- 5 **Code in JavaScript3** Code *Logic*
- 6 **HTTP Request7** Http Request *Service*
- 7 **Loop Over Items** Split In Batches *Logic*
- 8 **Read/Write Files from Disk1** Read Write File *Service*
- 9 **Edit Fields** Set *Logic*
- 10 **Wait** Wait *Logic*
- 11 **Extract from File** Extract From File *Service*
- 12 **Aggregate** Aggregate *Logic*
- 13 **HTTP Request12** Http Request *Service*

## How it's built

- **Starts on:** Nothing automatic; you run it
- **Steps:** 13, 2 loops or waits
- **Size:** Medium: a working afternoon
- **Connects to:** Nothing by connector; it calls services over plain HTTP
- **Model:** None. This is plumbing, not judgement

## Questions

What does it need to run?

An n8n account. You connect your own accounts after importing it; none are included.

What starts it?

Nothing starts it automatically. You run it by hand.

Does it use AI?

No. Every step is fixed logic or a call to a service, so it does the same thing every time.

How long does it take to set up?

Plan an afternoon. 13 steps is enough that you should read each one before running it.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

**Before you run it**

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 13 steps before you point it at anything that matters.

## Run it in n8n

- **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n)
- **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fverify-and-correct-pdf-ocr-text-with-mineru-and-qwen2-5-vl)
- **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts.

Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind.

## Workflows like it

Also documents and files, with the same services where possible, closest in size first.

- [**Analyze keywords from top Upwork talent profiles with Apify** 13 steps · Google Sheets](https://millionrounds.com/workflow/analyze-keywords-from-top-upwork-talent-profiles-with-apify)
- [**Archive weekly web page snapshots into a single PDF** 13 steps](https://millionrounds.com/workflow/archive-weekly-web-page-snapshots-into-a-single-pdf)
- [**Automated upload & send a large file with TransferNow** 13 steps](https://millionrounds.com/workflow/automated-upload-and-send-a-large-file-with-transfernow)
- [**Automated workflow backup to Google Drive** 13 steps · Google Drive](https://millionrounds.com/workflow/automated-workflow-backup-to-google-drive)
- [**Backup Squarespace code injections to GitHub** 13 steps · GitHub](https://millionrounds.com/workflow/backup-squarespace-code-injections-to-github)
- [**Backup workflows to Git repository on Gitea** 13 steps](https://millionrounds.com/workflow/backup-workflows-to-git-repository-on-gitea)