N8N Flow not using correct Supabase Table for Rag Flow

[bamboo_ave]

I created a flow as a RAG - the issue is it’s using the wrong table in supabase for the RAG. It’s using the table I used when I first set up my first vector store node. I’ve done everything possible to switch it to switch tables but not finding any solutions. I’m not sure if this is a big and how to get it to stop pulling from a Table that doesn’t even exist anymore.

I attached a screenshot of the flow as well.

For more information, I made a quick loom video: RAG System Setup Issues | Loom

Appreciate any help. Note - I disconnected the credentials to supabase and reset the workplace, then connected supabase again and still the same issue.

I’m using N8N cloud, on the latest version & on Macbook!

[n8n]

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:

[Sudhanshu_Sharma]

Hi there,

I hope you’re doing well.

Could you please share the exact steps you took when you first set up your Supabase? I’m specifically interested in how you inserted data into your Supabase vector store.

The reason I’m asking is that when setting up the Supabase vector store, we also need to specify the match function, which is responsible for searching through the database.

I recommend trying this guide:
Supabase Vector Store Quickstart

For further reference, you can check out this YouTube tutorial:
YouTube Tutorial

So, may the problem you are facing is due to following reason:-
Your table name is not the same which is mentioned in the match function…

So you need to update the match function to update the table name…

I hope, I am making sense, but still if you need help…you can always chat here.