Hello all,
I am running into this issue, as apparently a lot of people did. The problem is not really billing, as the details of the error say: “You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs: https://platform.openai.com/docs/guides/error-codes/api-errors.”
Some people said it was a bug on OpenAI side and that after a couple of days it was solved, while for others it was not.
I have tried changing the key, waiting a couple of hours, and even a day without sending requests, but the error persists. So, has anyone here found the root cause and have a solution or suggestions?
Then I thought if the problem is OpenAI, so i switch to gemeni. Asking the second question, gemeni gave me the same type of error: “the service is getting too many request from you”. So, i think the problem then is something else, but do not know what that would be. Any suggestion/hint would be much appreciated.
I used n8n ver:2.4.6
Hi @Salime_Dashti I am assuming everything on the pinecone node and its configurations are working , maybe trying openRouter and Groq like services would give us more lead on this, hope this helps.
In n8n, a single user prompt can result in multiple model requests depending on your workflow structure. This often happens when your input is split into many chunks like in summarization chains where each chunk triggers one API call, multiple items or loops reach an AI Agent or chat model node causing it to run several times, or several tools or branches feed into the same AI node increasing how often it’s triggered.
To confirm this, test with a simple workflow using a manual trigger plus a single LLM node with no Agent, tools, or vector store. If that works reliably, the issue is likely your workflow architecture rather than the model provider. Reducing the number of tools or branches feeding the AI node, avoiding unintended loops, and cleaning up inputs so only one item reaches the AI node at a time usually helps.
@Anshul_Namdev as beginner i am not sure what they are and what they would do.
@tamy.santos Tamy, I have tried to add a basic LLM chain with the Gemeni chat. As you anticipated, that works fine.
The workflow I have shared is part of a 3 workflows, that one supposed to fill the pinecone databases with the emails saved in a Doc file, the second, prepare a message to be emailed by getting the email body and who to email, and the third workflow to actually send it. This is part of a n8n training course.
I guess i will continue with a simpler way of doing the same to see if I run to the same issue.
@Salime_Dashti Please consider reading pinecone docs in n8n before using it, and a simpler approach like an LLM chain is good but AI agent gets you a lot in the same table, according to your use case AI agent would be suitable but for testing this is enough, let me know what is the issue now.
Let us know how it goes.