Build a WhatsApp assistant for text, audio & images using GPT-4o & Evolution API
UnknownWhat this workflow does
This AI workflow has 43 nodes and runs when an HTTP POST request hits its webhook URL. Along the way it connects OpenAI, Redis, OpenAI Chat Model and Postgres Chat Memory and 1 more.
How it runs
Trigger: When an HTTP POST request hits its webhook URL.
- Parse Message Data (Edit Fields (Set)): sets 7 fields: event, instance, remoteJid…
- Filter: keeps only the items that match a condition
- Wait: waits 2 seconds
- Mark as Read (Evolution Api): read messages (chat api)
- Route by Message Type (Switch): routes items into 4 branches
- Extract Text (Edit Fields (Set)): sets 1 field: input
- Extract Audio Base (Edit Fields (Set)): sets 1 field: data
- Extract Image Base (Edit Fields (Set)): sets 1 field: data
- Extract Document Base (Edit Fields (Set)): sets 1 field: data
- Send Unsupported Message (Evolution Api): work with messages api
…plus 25 more steps. See the full node list below.
Services it uses
Before you upgrade to n8n 3.0
We can't fully verify this one: it relies on 1 community package, and n8n 3.0 turns unverified community packages off by default (N8N_UNVERIFIED_PACKAGES_ENABLED=false).
- Check that n8n-nodes-evolution-api is verified or supports 3.0 (used in Mark as Read, Send Unsupported Message, Send Image).
Nodes used (19)
- Webhook
n8n-nodes-base.webhook - Edit Fields (Set)
n8n-nodes-base.set - Filter
n8n-nodes-base.filter - Wait
n8n-nodes-base.wait - Evolution Api
n8n-nodes-evolution-api.evolutionApi - Switch
n8n-nodes-base.switch - Convert to File
n8n-nodes-base.convertToFile - OpenAI
@n8n/n8n-nodes-langchain.openAi - No Operation, do nothing
n8n-nodes-base.noOp - Redis
n8n-nodes-base.redis - If
n8n-nodes-base.if - AI Agent
@n8n/n8n-nodes-langchain.agent - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Postgres Chat Memory
@n8n/n8n-nodes-langchain.memoryPostgresChat - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Split Out
n8n-nodes-base.splitOut - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - Aggregate
n8n-nodes-base.aggregate
From the author
Build an intelligent WhatsApp assistant that automatically responds to customer messages using AI. This template uses the Evolution API community node for WhatsApp integration and OpenAI for natural language processing, with built-in conversation memory…