Skip to main content

Create an automated customer support assistant with GPT-4o and GoHighLevel SMS

Workflow preview

Workflow preview
100%
Create an automated customer support assistant with GPT-4o and GoHighLevel SMS preview
Open on n8n.io

Important notice

This workflow is provided as-is. Please review and test before using in production.

1. Workflow Overview

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 b...

Best for

  • Support Chatbot automation workflows
  • AI RAG automation workflows
  • advanced n8n builders looking for reusable templates

Tools used

n8n-nodes-base.html, @n8n/n8n-nodes-langchain.vectorstoreinmemory, @n8n/n8n-nodes-langchain.embeddingsopenai, @n8n/n8n-nodes-langchain.documentdefaultdataloader, @n8n/n8n-nodes-langchain.textsplitterrecursivecharactertextsplitter, @n8n/n8n-nodes-langchain.agent, @n8n/n8n-nodes-langchain.lmchatopenai, n8n-nodes-base.splitout

Source and attribution

This workflow is cataloged by N8N Workflows and links back to its original n8n.io source page by Cyril Nicko Gaspar.

Original n8n.io source

1.1 Workflow description

Title
Create an automated customer support assistant with GPT-4o and GoHighLevel SMS
Workflow name
Create an automated customer support assistant with GPT-4o and GoHighLevel SMS

๐Ÿ“Œ 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.


โ“ Problem It Solves

Traditional customer support systems often require manual data entry and lack real-time updates from the company's website. This workflow automates the process by:

  • Scraping the company's website at set intervals to update the knowledgebase.
  • Integrating with GoHighLevel SMS to provide users with timely and accurate information.
  • Utilizing AI to interpret user queries and fetch relevant information from the updated knowledgebase.

๐Ÿงฐ Pre-requisites

Before deploying this workflow, ensure you have:

  • An active n8n instance (self-hosted or cloud).
  • A valid OpenAI API key (or any compatible AI model).
  • A Bright Data account with Web Unlocker setup.
  • A GoHighLevel SMS LeadConnector account.
  • A GoHighLevel Marketplace App configured with the necessary scopes.
  • Installed n8n-nodes-brightdata community node for Bright Data integration (if self-hosted).

โš™๏ธ Setup Instructions

1. Install the Bright Data Community Node in n8n

For self-hosted n8n instances:

  • Navigate to Settings โ†’ Community Nodes.
  • Click on Install.
  • In the search bar, enter n8n-nodes-brightdata.
  • Select the node from the list and click Install.

Docs: https://docs.n8n.io/integrations/community-nodes/installation/gui-install

2. Configure Bright Data Credentials
  • Obtain your API key from Bright Data.
  • In n8n, go to Credentials โ†’ New, select HTTP Request.
    • Set authentication to Header Auth.
    • In Name, enter Authorization.
    • In Value, enter Bearer <your_api_key_from_Bright_Data>.
    • Save the credentials.
3. Configure OpenAI Credentials
  • Add your OpenAI API key to the relevant nodes.
  • If you want to use a different model, replace all OpenAI nodes accordingly.
4. Set Up GoHighLevel Integration
a. Create a GoHighLevel Marketplace App
locations.readonly contacts.readonly contacts.write opportunities.readonly opportunities.write users.readonly conversations/message.readonly conversations/message.write
  • Add your n8n OAuth Redirect URL as a redirect URI in the app settings.
  • Save and copy the Client ID and Client Secret.
b. Configure GoHighLevel Credentials in n8n
  • Go to Credentials โ†’ New
  • Choose OAuth2 API
  • Input:
    • Client ID
    • Client Secret
    • Authorization URL: https://auth.gohighlevel.com/oauth/authorize
    • Access Token URL: https://auth.gohighlevel.com/oauth/token
    • Scopes:
      locations.readonly contacts.readonly contacts.write opportunities.readonly opportunities.write users.readonly conversations/message.readonly conversations/message.write
      
  • Save and authenticate to complete setup.

Docs: https://docs.n8n.io/integrations/builtin/credentials/highlevel


๐Ÿ”„ Workflow Functionality (Summary)

  • Scheduled Scraping: Scrapes website at user-defined intervals.
  • Edit Fields node: User defines the homepage or site to scrape.
  • Bright Data Node (self-hosted) OR HTTP Node (cloud users) used to perform scraping.
  • Knowledgebase Update: The scraped content is stored or indexed.
  • GoHighLevel SMS: Incoming user queries are received through SMS.
  • AI Processing: AI matches queries to relevant content.
  • Response Delivery: AI-generated answers are sent back via SMS.

๐Ÿงฉ Use Cases

  • Customer Support Automation: Provide instant, accurate responses.
  • Lead Qualification: Automatically answer potential customer inquiries.
  • Internal Knowledge Distribution: Keep staff updated via SMS based on website info.

๐Ÿ› ๏ธ Customization

  • Scraping URLs: Adjust targets in the Edit Fields node.
  • Model Swap: Replace OpenAI nodes to use a different LLM.
  • Format Response: Customize output to match your tone or brand.
  • Other Channels: Expand to include chat apps or email responses.
  • Vector Databases: It is advisable to store the data into a third-party vector database services like Pinecone, Supabase, etc.
  • Chat Memory Node: This workflow is using Redis as a chat memory but you can use N8N built-in chat memory.

โœ… Summary

This n8n workflow combines Bright Dataโ€™s scraping tools and GoHighLevelโ€™s SMS interface with AI query handling to deliver a real-time, conversational support experience. Ideal for businesses that want to turn their website into a live knowledge source via SMS, this agent keeps itself updated, smart, and customer-ready.

1.2 Logical Blocks

This catalog entry is organized from the workflow JSON. The node-level section below shows the executable blocks available for review before importing the template.

2. Block-by-Block Analysis

Block 1 - HTML

Type / Role
n8n-nodes-base.html - html
Config choices
Version 1.2

Block 2 - Simple Vector Store

Type / Role
@n8n/n8n-nodes-langchain.vectorStoreInMemory - vectorStoreInMemory
Config choices
Version 1

Block 3 - Embeddings OpenAI

Type / Role
@n8n/n8n-nodes-langchain.embeddingsOpenAi - embeddingsOpenAi
Config choices
Version 1.2

Block 4 - Default Data Loader

Type / Role
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - documentDefaultDataLoader
Config choices
Version 1

Block 5 - Recursive Character Text Splitter

Type / Role
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter - textSplitterRecursiveCharacterTextSplitter
Config choices
Version 1

Block 6 - AI Agent

Type / Role
@n8n/n8n-nodes-langchain.agent - agent
Config choices
Version 1.8

Block 7 - OpenAI Chat Model

Type / Role
@n8n/n8n-nodes-langchain.lmChatOpenAi - lmChatOpenAi
Config choices
Version 1.2

Block 8 - Simple Vector Store1

Type / Role
@n8n/n8n-nodes-langchain.vectorStoreInMemory - vectorStoreInMemory
Config choices
Version 1

Block 9 - Embeddings OpenAI1

Type / Role
@n8n/n8n-nodes-langchain.embeddingsOpenAi - embeddingsOpenAi
Config choices
Version 1.2

Block 10 - Split Out

Type / Role
n8n-nodes-base.splitOut - splitOut
Config choices
Version 1

Block 11 - Filter

Type / Role
n8n-nodes-base.filter - filter
Config choices
Version 2.2

Block 12 - HTML1

Type / Role
n8n-nodes-base.html - html
Config choices
Version 1.2

Block 13 - Redis Chat Memory

Type / Role
@n8n/n8n-nodes-langchain.memoryRedisChat - memoryRedisChat
Config choices
Version 1.4

Block 14 - Schedule Trigger

Type / Role
n8n-nodes-base.scheduleTrigger - scheduleTrigger
Config choices
Version 1.2

Block 15 - BrightData

Type / Role
n8n-nodes-brightdata.brightData - brightData
Config choices
Version 1

Block 16 - Set Website URL

Type / Role
n8n-nodes-base.set - set
Config choices
Version 3.4

Block 17 - BrightData1

Type / Role
n8n-nodes-brightdata.brightData - brightData
Config choices
Version 1

Block 18 - Send SMS via GHL

Type / Role
n8n-nodes-base.httpRequest - httpRequest
Config choices
Version 4.2

Block 19 - Webhook from GHL - SMS Reply Trigger

Type / Role
n8n-nodes-base.webhook - webhook
Config choices
Version 2

Block 20 - Wait

Type / Role
n8n-nodes-base.wait - wait
Config choices
Version 1.1

Block 21 - Simple Vector Store2

Type / Role
@n8n/n8n-nodes-langchain.vectorStoreInMemory - vectorStoreInMemory
Config choices
Version 1

Block 22 - Set Website URL1

Type / Role
n8n-nodes-base.set - set
Config choices
Version 3.4

Block 23 - Look Up GHL Contact by ID

Type / Role
n8n-nodes-base.highLevel - highLevel
Config choices
Version 2

Block 24 - Direct API access via HTTP

Type / Role
n8n-nodes-base.httpRequest - httpRequest
Config choices
Version 4.2

Showing the first 24 of 43 workflow blocks. Download the JSON for the full node graph.

3. Summary Table

Workflow Create an automated customer support assistant with GPT-4o and GoHighLevel SMS
Complexity advanced
Nodes 43
Categories Support Chatbot, AI RAG
Author Cyril Nicko Gaspar
Published 19 May 2025

4. Reproducing the Workflow from Scratch

  1. 1. Download the workflow JSON

    Use the JSON export at /data/workflows/4223/4223.json as the source template for this automation.

  2. 2. Import the template into n8n

    Open n8n, import the downloaded JSON, and review each node before activating the workflow.

  3. 3. Configure credentials and variables

    Replace placeholder credentials, API keys, webhook URLs, account IDs, and environment-specific values with your own settings.

  4. 4. Test with sample data

    Run the workflow manually or in a staging workspace, inspect node output, and confirm downstream systems receive the expected data.

  5. 5. Activate and monitor

    Enable the workflow only after testing, then monitor executions, errors, and rate limits during the first production runs.

5. General Notes & Resources

Review imported nodes carefully before activation. This catalog entry is intended to help you inspect the workflow structure, understand required services, and find related templates faster.

Node names, credentials, schedules, webhook paths, and external service limits may need adjustment for your workspace.

Frequently asked questions

What does Create an automated customer support assistant with GPT-4o and GoHighLevel SMS do?

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 b...

What do I need before importing this workflow?

Review the workflow JSON, configure any required credentials in n8n, and test the automation in a safe workspace before using it in production.

Can I customize this workflow?

Yes. Use the block-by-block analysis and the downloadable JSON to inspect each node, then adjust credentials, prompts, schedules, filters, or destinations for your Support Chatbot, AI RAG use case.