N8n Crashing on Pinecone Vector Store – Memory Error in Cloud & Local Setup

Questions
1

Describe the problem/error/question

The app seems to crash on the Pinecone Vector Store. I have tried this actually locally hosted and then started a trial on the cloud version of n8n to see if it was any different and it was the same each time.

What is the error message (if any)?

Though this is the error message - it restarted my cloud version and crashed my local version. Execution stopped at this node

n8n may have run out of memory while running this execution. More context and tips on how to avoid this in the docs

Please share your workflow

I am using the template at Chat with GitHub API Documentation: RAG-Powered Chatbot with Pinecone & OpenAI | n8n workflow template

Information on your n8n setup

  • n8n version: 1.82.3
  • Database (default: SQLite): SQLite
  • n8n EXECUTIONS_PROCESS setting (default: own, main): Whatever is default
  • Running n8n via (Docker, npm, n8n cloud, desktop app): n8n cloud
  • Operating system:
2

hello @gavsto

Does it crush on a particular node or any node?

3

It seemed to be between the recursive data loader and the character splitter. I’ve been playing about since and I do think this actually is memory related. I was loading a 2.5 meg JSON and it was splitting basically every element in it. I think that overloaded it.

What’s interesting is clearly the template above worked at some point and no longer does so either there is a bug, the JSON used changed in some way or the instance it has been tested on had more RAM maybe?

Even then is it expected for application to essentially crash and reset?

4

Maybe n8n cloud doesn’t have much memory, as LLMs required quite big instances.

5

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