Extract from pdf - Multiple files are bound together in this PDF Package

Questions
1

Describe the problem/error/question

I am trying to use an extract from PDF, and I ahve a bunch of files that come up with this text instead of the text from the PDF.

I have also tried sending to mistral ocr api, get the same thing back. If I download and open in adobe or another pdf program, it has a single page from what I can tell.

So not sure if its some older pdf format that just does not get reconginised or not? Only thing i really find online is to download adobe and open it not in a web browser, but that does not help haha

What is the error message (if any)?

Getting a weird message instead of the text:
Multiple files are bound together in this PDF Package.\n\nAdobe recommends using Adobe Reader or Adobe Acrobat version 8 or later to work with\ndocuments contained within a PDF Package. By updating to the latest version, you’ll enjoy\nthe following benefits:\n\n• Efficient, integrated PDF viewing\n\n• Easy printing\n\n• Quick searches\n\nDon’t have the latest version of Adobe Reader?\n\nClick here to download the latest version of Adobe Reader\n\nIf you already have Adobe Reader 8,\nclick a file in this PDF Package to view it.\n\n

Please share your workflow

The only relevance is the extract from pdf, its a file downloaded from sharepoint and its a pdf.

Share the output returned by the last node

Information on your n8n setup

  • n8n version: 1.120.4
  • Database (default: SQLite): postgres
  • n8n EXECUTIONS_PROCESS setting (default: own, main):
  • Running n8n via (Docker, npm, n8n cloud, desktop app):docker
  • Operating system:ubuntu 22
2

Hi,

I am using cloud login and also facing the same issue. after adding node “Extract from File” with “Extract from PDF” , does not extract text. I have tried different type of PDF file. still issue remain the same.

I have connected n8n “Form” node “File” option with uploaded binary file and and assign to “AI Agent” node with Input and system prompt. It is still not extracting text from PDF.

3

I believe that tool will only extract from fields that exist in the PDF. I send my PDF’s into an OCR node and extract the text that way.

4

Sadly its not an OCR issue.

Its that when n8n nodes open it, it gets that weird adobe message and you cannot see the contents.

But opening it in your desktop you see the files/pdf in it and can read it