Image interprertation using chatgpt node

問題
1

Hello everyone
I have a simple question, I would like to be able to feed the gpt node a binary document (image) and I am looking to generate a description of this document
I have a simplistic vision that this could be accomplished using a simple workflow

image
image1098×288 21.3 KB

But obviously this is too simple and does not work and I was wondering if anyone did something similar before or has an idea on how to accomplish this ?

Rad

  • n8n version : 1.11.0 (AI branch)
  • Ubuntu Server / Docker
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:
3

Passing files is usually that easy.

I don’t think the OpenAi node has the functionality to reply to a chat with an image, you may need to do a custom API request to make it work. Here’s OpenAi’s docs.