Query and edit UnoPim product catalogs with OpenAI GPT-4o and Slack
UnknownWhat this workflow does
This AI workflow has 18 nodes and runs when a chat message arrives. Along the way it connects Google Sheets, Slack, Linear and OpenAI Chat Model and 1 more.
How it runs
Trigger: When a chat message arrives.
- Settings (Edit Fields (Set)): sets 3 fields: locale, channel, allowWrites
- Catalog agent (AI Agent): runs an AI agent, with model: Answer with GPT-4o; 6 tools (List families, List products, List attributes, Update a product…); memory: Conversation memory
- Read the outcome (Code): runs custom JavaScript code
- Route the outcome (Switch): routes items into 3 branches
- Re-read the product (Uno Pim): get (product)
- Open a data quality issue (Linear): create (issue)
- Return the answer (Edit Fields (Set)): sets 1 field: answer
- Append to the change log (Google Sheets): append
- Announce the change (Slack): uses Slack
Services it uses
Before you upgrade to n8n 3.0
We can't fully verify this one: it relies on 2 community packages, and n8n 3.0 turns unverified community packages off by default (N8N_UNVERIFIED_PACKAGES_ENABLED=false).
- Check that n8n-nodes-unopim is verified or supports 3.0 (used in Re-read the product).
- Check that n8n-nodes-unopim is verified or supports 3.0 (used in List products, Look up a product, Update a product).
Nodes used (12)
- Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - Edit Fields (Set)
n8n-nodes-base.set - AI Agent
@n8n/n8n-nodes-langchain.agent - Code
n8n-nodes-base.code - Switch
n8n-nodes-base.switch - Uno Pim
n8n-nodes-unopim.unoPim - Google Sheets
n8n-nodes-base.googleSheets - Slack
n8n-nodes-base.slack - Linear
n8n-nodes-base.linear - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Uno Pim Tool
n8n-nodes-unopim.unoPimTool
From the author
Quick overview A chat window for your UnoPim catalog. An OpenAI GPT-4o agent answers questions about your products and writes catalog data back through six UnoPim tools. Every reply is then routed by the workflow itself: a write is read back from UnoPim to…