RAG & app with WordPress content
Workflow Description
An advanced template integrating Retrieval-Augmented Generation (RAG) with WordPress content to build an intelligent agent that extracts information from a vector database and answers user queries based on your site content with precision and speed.
How it works
- 1.Load WordPress content and split it into processable text segments
- 2.Convert segments into embedding vectors via OpenAI and store them in the database
- 3.Receive user queries through a chat interface and route them to an intelligent agent that searches vectors
- 4.Retrieve relevant search results from Supabase or Postgres
- 5.Generate a contextual response from the agent based on retrieved content
- 6.Send the reply to the user via webhook or web interface
Use cases
- Build a smart customer support system that automatically answers frequently asked questions from WordPress knowledge bases
- Create a virtual website assistant that understands your blog content and provides relevant answers instantly
- Develop an intelligent search engine that returns contextually relevant results instead of traditional keyword-based search
Requirements
- Active OpenAI account with sufficient permissions to generate embeddings and intelligent responses
- WordPress integration with API keys to connect and retrieve content
- Postgres or Supabase database configured to store vectors and associated metadata
- Enabled chat trigger to receive and process user messages
Service Value
Ideal as a smart automation service combining integrations and AI to produce ready-to-use results.
Apps Used
Details
How to Use
- 1.Click "Download Template"
- 2.Open your n8n dashboard
- 3.Go to Workflows > Import from File
- 4.Select downloaded file and configure credentials
Nodes Used (53)
When clicking ‘Test workflow’
Manual Trigger
Embeddings OpenAI
OpenAI
Default Data Loader
Document Default Data Loader
Token Splitter
Text Splitter Token Splitter
Embeddings OpenAI1
OpenAI
OpenAI Chat Model
OpenAI
Postgres Chat Memory
Memory Postgres Chat
Respond to Webhook
Webhook
Set fields
Set
Embeddings OpenAI2
OpenAI
Default Data Loader1
Document Default Data Loader
Token Splitter1
Text Splitter Token Splitter
Markdown1
Markdown
Postgres
Postgres
Aggregate
Aggregate
Aggregate1
Aggregate
Aggregate2
Aggregate
Sticky Note
Sticky Note
Sticky Note1
Sticky Note
Sticky Note2
Sticky Note
Wordpress - Get all posts
Wordpress
Wordpress - Get all pages
Wordpress
Sticky Note3
Sticky Note
Set fields1
Set
Filter - Only published & unprotected content
Filter
HTML To Markdown
Markdown
Supabase - Store workflow execution
Supabase
Sticky Note4
Sticky Note
Every 30 seconds
Schedule Trigger
Sticky Note5
Sticky Note
Wordpress - Get posts modified after last workflow execution
HTTP Request
Wordpress - Get posts modified after last workflow execution1
HTTP Request
Set fields2
Set
Filter - Only published and unprotected content
Filter
Loop Over Items
Split In Batches
Set fields3
Set
Set fields4
Set
Store documents on Supabase
Vector Store Supabase
Store workflow execution id and timestamptz
Supabase
Aggregate documents
Aggregate
Sticky Note6
Sticky Note
Sticky Note7
Sticky Note
Postgres - Create documents table
Postgres
Postgres - Create workflow execution history table
Postgres
Merge Wordpress Posts and Pages
Merge
Merge retrieved WordPress posts and pages
Merge
Postgres - Filter on existing documents
Postgres
Supabase - Delete row if documents exists
Supabase
Switch
Switch
When chat message received
Chat Trigger
Supabase - Retrieve documents from chatinput
Vector Store Supabase
AI Agent
Agent
Supabase Vector Store
Vector Store Supabase