Route omnichannel customer support with Ollama and Postgres pgvector
Ready for 3.0What this workflow does
This workflow has 20 nodes and runs when an HTTP POST request hits its webhook URL (plus 2 other triggers). Along the way it connects Postgres.
How it runs
Trigger: When an HTTP POST request hits its webhook URL (plus 2 other triggers).
- Normalize and validate (Code): runs custom JavaScript code
- Invalid request? (If): checks a condition and branches into true / false
- Reject inbound (Respond to Webhook): sends the response back to the webhook caller
- Persist and fetch memory (Postgres): run a query
- Duplicate event? (If): checks a condition and branches into true / false
- Acknowledge duplicate (Respond to Webhook): sends the response back to the webhook caller
- Embed question (HTTP Request): calls an HTTP API
- Retrieve approved knowledge (Postgres): run a query
- Classify and draft (HTTP Request): calls an HTTP API
- Route and guardrail (Code): runs custom JavaScript code
…plus 7 more steps. See the full node list below.
Services it uses
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (7)
- Webhook
n8n-nodes-base.webhook - Code
n8n-nodes-base.code - If
n8n-nodes-base.if - Respond to Webhook
n8n-nodes-base.respondToWebhook - Postgres
n8n-nodes-base.postgres - HTTP Request
n8n-nodes-base.httpRequest - Edit Fields (Set)
n8n-nodes-base.set
From the author
Quick overview This workflow receives customer messages via webhook from chat, email, or social channels, stores conversation history in Postgres (pgvector), retrieves relevant knowledge, and uses Ollama to draft a guarded reply or create a human handoff,…