Supabase vector store error case

Describe the problem/error/question

Hello. I'm quite frustrated as I've been trying to resolve this persistent error for the past two days, which has taken longer than building a fully operational orchestration appointment workflow using Supabase + callin.io. I'm attempting to create an FAQ agent that works with documents in Supabase and a Vector Store tool (as a tool for the AI Agent). Every single Supabase node, including custom HTTP request function calls, worked perfectly for my appointment workflow. So, I decided to build a fan bot. I can insert documents into my Supabase documents database without any issues whatsoever; everything works fine. I've even run SQL commands that confirm the documents are in the database and can be found! When I ask a simple question like 'where is the bar,' the agent takes a very long time running the vector tool (text embedding 3 small, 1536, batch 3, strip new lines on, timeout 30) and retrieves NOTHING AT ALL. It results in a 'Request timed out' error. I initially thought I might have made a mistake by adding titles and categories in the metadata, so I DROPPED EVERY FUNCTION IN MY SUPABASE AND TABLE THAT HAD TO DO WITH DOCUMENTS, and tried running it as the documentation suggests:

– Enable the pgvector extension to work with embedding vectors
create extension vector;

– Create a table to store your documents
create table documents (
id bigserial primary key,
content text, – corresponds to Document.pageContent
metadata jsonb, – corresponds to Document.metadata
embedding vector(1536) – 1536 works for OpenAI embeddings, change if needed
);

– Create a function to search for documents
create function matchdocuments (
queryembedding vector(1536),
matchcount int default null,
filter jsonb DEFAULT '{}'
) returns table (
id bigint,
content text,
metadata jsonb,
similarity float
)
language plpgsql
as $$
#variableconflict usecolumn
begin
return query
select
id,
content,
metadata,
1 - (documents.embedding <=> queryembedding) as similarity
from documents
where metadata @> filter
order by documents.embedding <=> queryembedding
limit matchcount;
end;
$$;

LangChain | Supabase Docs , Supabase Vector Store node documentation | callin.io Docs

I'M GETTING THE SAME ERROR EVEN WITH ONLY ONE SINGLE DOCUMENT IN THE DATABASE???

I suspected my database might be corrupt, so I created a completely new one just to test it again. I followed the documentation precisely. Guess what? The same error.

… I've watched numerous tutorials on setting up vector stores on YouTube, etc. It should be incredibly simple to set up, and I'm certainly not new to this! Since I'm completely at a loss for how to fix this problem, please help me. Perhaps an callin.io manager could review my account and identify the issue, because I've set up complex workflows. However, this ridiculous situation is making me want to give up. It's also not an issue with my agent prompt or the tool description, not even close.

What is the error message (if any)?

Request timed out.

Request timed out.

Ask Assistant

Error details

Other info

n8n version

1.100.1 (Cloud)

Time

7.7.2025, 15:16:11

Error cause

{ "name": "TimeoutError", "attemptNumber": 7, "retriesLeft": 0 }

Please share your workflow

(Select the nodes on your canvas and use the keyboard shortcuts CMD+C/CTRL+C and CMD+V/CTRL+V to copy and paste the workflow.)

{
“nodes”: [
{
“parameters”: {
“options”: {}
},
“type”: "@callin.io/callin.io-nodes-langchain.chatTrigger",
“typeVersion”: 1.1,
“position”: [
-360,
100
],
“id”: "",
“name”: "When chat message received",
“webhookId”: ""
},
{
“parameters”: {
“options”: {
“systemMessage”: ""
}
},
“type”: "@callin.io/callin.io-nodes-langchain.agent",
“typeVersion”: 2,
“position”: [
-100,
100
],
“id”: "",
“name”: "AI Agent"
},
{
“parameters”: {
“model”: {
“__rl”: true,
“mode”: "list",
“value”: "gpt-4.1-mini"
},
“options”: {}
},
“type”: "@callin.io/callin.io-nodes-langchain.lmChatOpenAi",
“typeVersion”: 1.2,
“position”: [
-200,
320
],
“id”: "",
“name”: "OpenAI Chat Model",
“credentials”: {

}
}
},
{
“parameters”: {
“mode”: "retrieve-as-tool",
“toolDescription”: "Nutze dieses tool um info aus unserer Datenbank zu bekommen",
“tableName”: {
“_rl”: true,
“value”: "documents",
“mode”: "list",
“cachedResultName”: "documents"
},
“topK”: 3,
“options”: {
“queryName”: "matchdocuments"
}
},
“type”: "@callin.io/callin.io-nodes-langchain.vectorStoreSupabase",
“typeVersion”: 1.3,
“position”: [
260,
320
],
“id”: "",
“name”: "Supabase Vector Store",
“credentials”: {

}
}
},
{
“parameters”: {
“options”: {
“dimensions”: 1536,
“batchSize”: 3,
“stripNewLines”: true,
“timeout”: 30
}
},
“type”: "@callin.io/callin.io-nodes-langchain.embeddingsOpenAi",
“typeVersion”: 1.2,
“position”: [
160,
480
],
“id”: ",
“name”: "Embeddings OpenAI",
“credentials”: {

}
}
},
{
“parameters”: {
“tableId”: "feedback",
“fieldsUi”: {
“fieldValues”: [
{
“fieldId”: "documentid",
“fieldValue”: "={{$fromAI('documentid')}}"
},
{
“fieldId”: "feedbacktype",
“fieldValue”: "={{$fromAI('feedbacktype')}}"
},
{
“fieldId”: "usercomment",
“fieldValue”: "={{$fromAI('usercomment')}}"
},
{
“fieldId”: "question",
“fieldValue”: "={{$fromAI('originalquestion')}}"
}
]
}
},
“type”: "callin.io-nodes-base.supabaseTool",
“typeVersion”: 1,
“position”: [
120,
320
],
“id”: "",
“name”: "logfeedback",
“credentials”: {
}
}
},
{
“parameters”: {},
“type”: "@callin.io/callin.io-nodes-langchain.memoryPostgresChat",
“typeVersion”: 1.3,
“position”: [
-20,
320
],
“id”: "",
“name”: "Postgres Chat Memory",
“credentials”: {

}
}
}

],
“connections”: {
“When chat message received”: {
“main”: [
[
{
“node”: "AI Agent",
“type”: "main",
“index”: 0
}
]
]
},
“OpenAI Chat Model”: {
“ailanguageModel”: [
[
{
“node”: "AI Agent",
“type”: "ailanguageModel",
“index”: 0
}
]
]
},
“Supabase Vector Store”: {
“aitool”: [
[
{
“node”: "AI Agent",
“type”: "aitool",
“index”: 0
}
]
]
},
“Embeddings OpenAI”: {
“aiembedding”: [
[
{
“node”: "Supabase Vector Store",
“type”: "aiembedding",
“index”: 0
}
]
]
},
“logfeedback”: {
“aitool”: [
[
{
“node”: "AI Agent",
“type”: "aitool",
“index": 0
}
]
]
},
“Postgres Chat Memory”: {
“aimemory”: [
[
{
“node”: "AI Agent",
“type”: "ai_memory",
“index": 0
}
]
]
}
},
“pinData”: {},
“meta”: {
“templateCredsSetupCompleted”: true,
“instanceId”: ""
}
}

Information on your n8n setup

• n8n version:1 1.100.1 (Cloud)
• Database (default: SQLite): SUPABSASE SQL
• n8n EXECUTIONS_PROCESS setting (default: own, main): default
• Running n8n via (Docker, npm, n8n cloud, desktop app): cloud
• Operating system: MAC AND WINDOWS BOTH DONT WORK!