AI WhatsApp Chatbot with RAG: Automate Text, Voice, Image & PDF Responses
Needs changesWhat this workflow does
This AI workflow has 47 nodes and runs on Rapiwa events. Along the way it connects HTTP Request, Google Sheets, OpenAI and OpenAI Chat Model and 2 more.
How it runs
Trigger: On Rapiwa events.
- Route Types (Switch): routes items into branches
- Generates AI responses, maintains context, retrieves info (AI Agent): runs an AI agent, with model: OpenAI; 2 tools (Think, Research); memory: Memory
- Downloads audio from message URL (HTTP Request): calls an HTTP API
- Fetches image data via HTTP request (HTTP Request): calls an HTTP API
- Download Document (HTTP Request): calls an HTTP API
- Save Message status in sheet (Google Sheets): uses Google Sheets
- Rapiwa: uses Rapiwa
- Transcribes and analyzes (OpenAI): uses OpenAI
- Processes audio and generates a response (AI Agent): runs an AI agent, with model: OpenAI; 2 tools (Think, Research); memory: Memory
- Analyzes the image content (OpenAI): uses OpenAI
…plus 15 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 Generates AI responses, maintains context, retrieves info (v1.9), Processes audio and generates a response (v1.9), Summarizes audio for concise replies (v1.9)…: 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) Generates AI responses, maintains context, retrieves info (v1.9), Processes audio and generates a response (v1.9), Summarizes audio for concise replies (v1.9), Processes the image analysis and generates a response (v1.9), Analyzes the document and generates a response (v1.9) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (18)
- Extract from File
n8n-nodes-base.extractFromFile - Edit Fields (Set)
n8n-nodes-base.set - Code
n8n-nodes-base.code - HTTP Request
n8n-nodes-base.httpRequest - Switch
n8n-nodes-base.switch - Rapiwa Trigger
n8n-nodes-rapiwa.rapiwaTrigger - AI Agent Tool
@n8n/n8n-nodes-langchain.agentTool - Http Request Tool
n8n-nodes-base.httpRequestTool - Google Sheets Tool
n8n-nodes-base.googleSheetsTool - Think Tool
@n8n/n8n-nodes-langchain.toolThink - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - No Operation, do nothing
n8n-nodes-base.noOp - Rapiwa
n8n-nodes-rapiwa.rapiwa - Google Sheets
n8n-nodes-base.googleSheets - AI Agent
@n8n/n8n-nodes-langchain.agent - OpenAI
@n8n/n8n-nodes-langchain.openAi - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Google Docs Tool
n8n-nodes-base.googleDocsTool
From the author
Who it's for This n8n workflow creates an intelligent WhatsApp customer support bot that can handle text, image, audio, and document messages. The workflow automatically processes incoming messages through different AI agents, maintains conversation context,…