I am using a self-hosted n8n instance with version 1.91.3. I cannot connect the Chat node to the AI Agent node, and the AI Agent node does not look like what is shown in the tutorial.
What is the error message (if any)?
no message
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”: “@n8n /n8n-nodes-langchain.chatTrigger”,
“typeVersion”: 1.1,
“position”: [
0,
0
],
“id”: “2e588b2b-e44f-48c5-be33-b2cec875db50”,
“name”: “When chat message received”,
“webhookId”: “df176a5a-a798-45b8-a2b7-17730e261c5d”
}
],
“connections”: {
“When chat message received”: {
“main”: [
]
}
},
“pinData”: {},
“meta”: {
“templateCredsSetupCompleted”: true,
“instanceId”: “6a2273868aafb37dd639ac7e446cad25c48e69f9c94440a318487d4f19c3e2eb”
}
}
{
“nodes”: [
{
“parameters”: {
“options”: {}
},
“type”: “@n8n /n8n-nodes-langchain.agent”,
“typeVersion”: 1.9,
“position”: [
220,
0
],
“id”: “88521ee7-a7cd-44aa-aa34-2174d6a1cfd4”,
“name”: “AI Agent”
}
],
“connections”: {},
“pinData”: {},
“meta”: {
“templateCredsSetupCompleted”: true,
“instanceId”: “6a2273868aafb37dd639ac7e446cad25c48e69f9c94440a318487d4f19c3e2eb”
}
}
Share the output returned by the last node
Information on your n8n setup
n8n version: 1.91.3
Database (default: SQLite): pg
n8n EXECUTIONS_PROCESS setting (default: own, main): default
Running n8n via (Docker, npm, n8n cloud, desktop app): docker
Operating system: amazon-linux x86-64
1 Like
Did you copy this from anywhere?
Sometimes when importing it references the wrong nodes I’ve noticed especially on newer version.
I pasted in, and got this:
So, seems more issue in env
There seems to be an issue initialising the node properly, so it could need a restart? Do you have any community nodes installed also?
I copy from tutorial doc , and I’ve restarted it several times. I’m using docker-compose here and haven’t install any community nodes yet.
services:
n8n:
restart: always
image: n8nio/n8n:1.91.3
ports:
- "5678:5678"
environment:
- N8N_BASIC_AUTH_ACTIVE=true
- N8N_BASIC_AUTH_USER=admin
- N8N_BASIC_AUTH_PASSWORD=securepassword
- N8N_HOST=your.url
- N8N_PROTOCOL=https
- WEBHOOK_TUNNEL_URL=https://your.url
- WEBHOOK_URL=https://your.url
- N8N_EXTERNAL_URL=https://your.url
- DB_TYPE=postgresdb
- DB_POSTGRESDB_HOST=postgres # Name of the PostgreSQL service in Docker Compose
- DB_POSTGRESDB_DATABASE=n8n
- DB_POSTGRESDB_USER=n8n
- DB_POSTGRESDB_PASSWORD=securepassword
- EXECUTIONS_MODE=regular
- NODE_FUNCTION_ALLOW_EXTERNAL=nodemailer
- N8N_PUSH_BACKEND=websocket
- N8N_PAYLOAD_SIZE_MAX=268435456
- N8N_ENCRYPTION_KEY=rHrdmVuJuhUeA7JDKtkoqQfRZ9wd58lGPmz28JIHu1k=
depends_on:
- postgres # Ensures PostgreSQL starts before n8n
volumes:
- ./.n8n:/root/.n8n
postgres:
restart: always
image: postgres:latest
environment:
- POSTGRES_DB=n8n
- POSTGRES_USER=n8n
- POSTGRES_PASSWORD=securepassword
volumes:
- ./pgdata:/var/lib/postgresql/data
Catorpilor:
{
“nodes”: [
{
“parameters”: {
“options”: {}
},
“type”: “@n8n /n8n-nodes-langchain.chatTrigger”,
“typeVersion”: 1.1,
“position”: [
0,
0
],
“id”: “2e588b2b-e44f-48c5-be33-b2cec875db50”,
“name”: “When chat message received”,
“webhookId”: “df176a5a-a798-45b8-a2b7-17730e261c5d”
}
],
“connections”: {
“When chat message received”: {
“main”: [
]
}
},
“pinData”: {},
“meta”: {
“templateCredsSetupCompleted”: true,
“instanceId”: “6a2273868aafb37dd639ac7e446cad25c48e69f9c94440a318487d4f19c3e2eb”
}
}
{
“nodes”: [
{
“parameters”: {
“options”: {}
},
“type”: “@n8n /n8n-nodes-langchain.agent”,
“typeVersion”: 1.9,
“position”: [
220,
0
],
“id”: “88521ee7-a7cd-44aa-aa34-2174d6a1cfd4”,
“name”: “AI Agent”
}
],
“connections”: {},
“pinData”: {},
“meta”: {
“templateCredsSetupCompleted”: true,
“instanceId”: “6a2273868aafb37dd639ac7e446cad25c48e69f9c94440a318487d4f19c3e2eb”
}
}
Did you copy this from anywhere?
Sometimes when importing it references the wrong nodes I’ve noticed especially on newer version.
I pasted in, and got this:
So, seems more issue in env
There seems to be an issue initialising the node properly, so it could need a restart? Do you have any community nodes installed also?
Thx, my problem was solved.
I was using Caddy as a reverse proxy, and I accidentally added some Content-Security-Policy
configs which I was not quite understand
After I removed those and restarted the instance.
It worked like a charm.
1 Like
system
Closed
May 27, 2025, 10:34am
6
This topic was automatically closed 7 days after the last reply. New replies are no longer allowed.