AI personal assistant with GPT-4o, RAG & voice for WhatsApp using Supabase
Needs changesNeeds changes. This template uses 1 thing(s) that n8n 3.0 removes: AI Agent v1 (old agent modes). 1 breaking item(s) found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 64 nodes and runs when an HTTP GET request hits its webhook URL. Along the way it connects OpenAI Chat Model, Redis, OpenAI and Postgres and 5 more.
How it runs
Trigger: When an HTTP GET request hits its webhook URL.
- config (Edit Fields (Set)): sets or maps fields
- auth (If): checks a condition and branches into true / false
- mensagem_tipo (Switch): routes items into branches
- arquivo_id (Edit Fields (Set)): sets or maps fields
- Convert to File: converts data to a file
- base (Edit Fields (Set)): sets or maps fields
- edit (Edit Fields (Set)): sets or maps fields
- deletar_arquivos_antigos (Supabase): uses Supabase
- OpenAI: uses OpenAI
- Convert to File: converts data to a file
…plus 36 more steps. See the full node list below.
Services it uses
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 recepcionista (v1.6), classificador_de_intencao (v1.7): 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) recepcionista (v1.6), classificador_de_intencao (v1.7) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (24)
- OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Convert to File
n8n-nodes-base.convertToFile - Edit Fields (Set)
n8n-nodes-base.set - If
n8n-nodes-base.if - Wait
n8n-nodes-base.wait - Redis
n8n-nodes-base.redis - OpenAI
@n8n/n8n-nodes-langchain.openAi - Postgres
n8n-nodes-base.postgres - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Recursive Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter - Supabase
n8n-nodes-base.supabase - Extract from File
n8n-nodes-base.extractFromFile - Supabase Vector Store
@n8n/n8n-nodes-langchain.vectorStoreSupabase - Call n8n Workflow Tool
@n8n/n8n-nodes-langchain.toolWorkflow - Postgres Chat Memory
@n8n/n8n-nodes-langchain.memoryPostgresChat - Switch
n8n-nodes-base.switch - Aggregate
n8n-nodes-base.aggregate - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - Merge
n8n-nodes-base.merge - Execute Sub-workflow
n8n-nodes-base.executeWorkflow - Webhook
n8n-nodes-base.webhook - AI Agent
@n8n/n8n-nodes-langchain.agent - Vector Store Question Answer Tool
@n8n/n8n-nodes-langchain.toolVectorStore
From the author
🧠 Intelligent AI Assistant with RAG & Voice for WhatsApp – Built with GPT-4o & Supabase --- 📌 About this workflow and its creator Hi! I’m Amanda, a creator of intelligent automations using n8n and Make. I’ve been building AI-powered workflows for over 2…