Workflow: Extract Images and specific Text Content from .docx

Questions
,
1

Hey,

I want to upload a .docx (a briefing) to a Custom GPT, which then sends it via webhook to an n8n workflow. In n8n, specific images from a defined section of the document should be extracted and analyzed using ChatGPT Vision.

For this analysis, I also want to provide additional text from another specific section of the document to give the AI more context. Based on this information, the AI (Claude 3.5 Sonnet prefered) should generate alt texts for each image. Finally, the results should be inserted back into a specific location within the same .docx file.

Has anyone done this before, or does anyone know exactly which n8n nodes I need and the best approach to achieve this?

Best regards

2

It looks like your topic is missing some important information. Could you provide the following if applicable.

  • n8n version:
  • Database (default: SQLite):
  • n8n EXECUTIONS_PROCESS setting (default: own, main):
  • Running n8n via (Docker, npm, n8n cloud, desktop app):
  • Operating system:
4

This topic was automatically closed 90 days after the last reply. New replies are no longer allowed.