Create an automated customer support assistant with GPT-4o and GoHighLevel SMS
Needs changesWhat this workflow does
This AI workflow has 34 nodes and runs on a schedule (every 4 days at ={{ 12 }}:00) (plus 1 other trigger). Along the way it connects Embeddings OpenAI, OpenAI Chat Model, Redis Chat Memory and HighLevel and 1 more. It also calls services.leadconnectorhq.com and api.brightdata.com over HTTP.
How it runs
Trigger: On a schedule (every 4 days at ={{ 12 }}:00) (plus 1 other trigger).
- Set Website URL (Edit Fields (Set)): sets 1 field: website_url
- If: checks a condition and branches into true / false
- Bright Data: uses Bright Data
- Look Up GHL Contact by ID (HighLevel): get
- HTML: parses or builds HTML
- Set Website URL (Edit Fields (Set)): sets 1 field: website_url
- Simple Vector Store: stores documents in the Simple vector store, with embeddings: Embeddings OpenAI; document loader: Default Data Loader
- Get sitemap (HTTP Request): calls an HTTP API
- Split Out: splits a list into separate items
- AI Agent: runs an AI agent, with model: OpenAI Chat Model; 1 tool (Simple Vector Store); memory: Redis Chat Memory
…plus 15 more steps. See the full node list below.
Services it uses
HTTP calls to: services.leadconnectorhq.com, api.brightdata.com
Scraping pages by hand? Firecrawl is a simpler option (10% off for new users).
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in AI Agent (v1.8): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) AI Agent (v1.8) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (22)
- HTML
n8n-nodes-base.html - Simple Vector Store
@n8n/n8n-nodes-langchain.vectorStoreInMemory - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Recursive Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter - AI Agent
@n8n/n8n-nodes-langchain.agent - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Split Out
n8n-nodes-base.splitOut - Filter
n8n-nodes-base.filter - Redis Chat Memory
@n8n/n8n-nodes-langchain.memoryRedisChat - Schedule Trigger
n8n-nodes-base.scheduleTrigger - Bright Data
n8n-nodes-brightdata.brightData - Edit Fields (Set)
n8n-nodes-base.set - HTTP Request
n8n-nodes-base.httpRequest - Webhook
n8n-nodes-base.webhook - Wait
n8n-nodes-base.wait - HighLevel
n8n-nodes-base.highLevel - If
n8n-nodes-base.if - XML
n8n-nodes-base.xml - Merge
n8n-nodes-base.merge - Remove Duplicates
n8n-nodes-base.removeDuplicates - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches
From the author
📌 AI Agent via GoHighLevel SMS with Website-Based Knowledgebase This n8n workflow enables an AI agent to interact with users through GoHighLevel SMS, leveraging a knowledgebase dynamically built by scraping the company's website. --- ❓ Problem It Solves…