AI Agent: Rate limit reached error

Questions
1

For a store, I need to assign a product to the correct category.

I have a table with 1,500 rows, each containing a category.

I ask a ChatGPT agent to find the best category in the table based on the product’s name and description.

When I do this manually, GPT-4o always finds the best category.

However, when I integrate it into an n8n workflow, I encounter an OpenAI: Rate limit reached error with the GPT-4o model. I suspect this is due to the size of the data in my table.

It works with the GPT-4o-mini model, but the results provided by the AI are often less accurate.

Is there a better approach to categorize my products?

TY

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

Hey @presta_melt , OpenAI rate limits are explained in https://platform.openai.com/docs/guides/rate-limits. It is tier based. The post also talks about possible mitigation of the errors.

4

TY, I’m aware of this.

But the WF raise the error with only one request…

5

Check the workflow logs to see what is really happening behind the scene and how the tokens usage is spread across the AI interactions.

1 Like