# Build RAG-powered WhatsApp chatbots for docs with OpenAI: n8n workflow

> Started by an incoming WhatsApp message, and works across Google Docs and WhatsApp. It puts OpenAI behind a retrieval step, so answers are drawn from...

Source: https://millionrounds.com/workflow/build-rag-powered-whatsapp-chatbots-for-docs-with-openai (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [Chat assistants](https://millionrounds.com/workflows?category=Chat+assistants#library)

# Build RAG-powered WhatsApp chatbots for docs with OpenAI

Started by an incoming WhatsApp message, and works across Google Docs and WhatsApp. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 32 steps, 2 branches: large, and worth reading before you trust it with anything live.

Large Calls a model: OpenAI Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fbuild-rag-powered-whatsapp-chatbots-for-docs-with-openai)

**32 steps** Large: read it before trusting it with anything live

**2** Branches: places the flow splits

**0** Loops or waits

**2** Services it connects to

## The flow

Starts it 2 Model 11 Logic 7 Service 12

The steps in the order they run, from what starts it.

- 1 **OpenAI Chat Model** Lm Chat Open Ai *Model*
- 2 **Embeddings OpenAI** Embeddings Open Ai *Model*
- 3 **When clicking "Execute Workflow"** Manual trigger *Starts it*
- 4 **Simple Memory** Memory Buffer Window *Model*
- 5 **Document Chunker** Text Splitter Recursive Character Text Splitter *Model*
- 6 **OpenAI Embeddings Generator** Embeddings Open Ai *Model*
- 7 **WhatsApp Trigger** Whats App trigger *Starts it*
- 8 **Knowledge Base Agent** Agent *Model*
- 9 **MongoDB Vector Search** Vector Store Mongo DBAtlas *Model*
- 10 **Google Docs Importer** Google Docs *Service*
- 11 **Document Section Loader** Document Default Data Loader *Model*
- 12 **MongoDB Vector Store Inserter** Vector Store Mongo DBAtlas *Model*
- 13 **Route Types** Switch *Logic*
- 14 **Send Response** Whats App *Service*
- 15 **Map text prompt** Set *Logic*
- 16 **Gets WhatsApp Voicemail Source URL** Whats App *Service*
- 17 **Gets WhatsApp Image Source URL** Whats App *Service*
- 18 **Gets WhatsApp Document Source URL** Whats App *Service*
- 19 **Download Voicemail** Http Request *Service*
- 20 **Download Image** Http Request *Service*
- 21 **Download Document** Http Request *Service*
- 22 **OpenAI** Open Ai *Model*
- 23 **OpenAI1** Open Ai *Model*
- 24 **Map file extensions** Code *Logic*
- 25 **Map image prompt** Set *Logic*
- 26 **Route Document Types** Switch *Logic*
- 27 **Map document prompt** Set *Logic*
- 28 **Extract from PDF** Extract From File *Service*
- 29 **Map JSON** Set *Logic*
- 30 **Extract from XLS** Extract From File *Service*
- 31 **Extract from XLSX** Extract From File *Service*
- 32 **Send Unsupported Response** Whats App *Service*

## How it's built

- **Starts on:** An incoming WhatsApp message
- **Steps:** 32, with 2 branches
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Google Docs, WhatsApp
- **Model:** OpenAI
- **Retrieval:** Answers are drawn from documents you supply, not from the model alone

## Questions

What does it need to run?

An n8n account, plus your own Google Docs and WhatsApp accounts, and a key for OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on an incoming WhatsApp message.

Does it use AI?

Yes. It calls OpenAI. Its answers draw on documents you give it, not on the model alone. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 32 steps it is large: read it before trusting it with anything live.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

**Before you run it**

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 32 steps before you point it at anything that matters.

## Run it in n8n

- **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n)
- **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fbuild-rag-powered-whatsapp-chatbots-for-docs-with-openai)
- **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts.

Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind.

## Connects to

Each opens the other workflows that use it.

[Google Docs](https://millionrounds.com/workflows?service=Google+Docs#library)[WhatsApp](https://millionrounds.com/workflows?service=WhatsApp#library)

## Workflows like it

Also chat assistants, with the same services where possible, closest in size first.

- [**Run a multimodal WhatsApp AI assistant with OpenAI** 30 steps · calls a model · WhatsApp](https://millionrounds.com/workflow/run-a-multimodal-whatsapp-ai-assistant-with-openai)
- [**AI powered RAG chatbot for your docs + Google Drive + Gemini** 35 steps · calls a model · Google Docs, Google Drive](https://millionrounds.com/workflow/ai-powered-rag-chatbot-for-your-docs-google-drive-gemini)
- [**Debounce and buffer WhatsApp AI replies with Redis and Gemini** 29 steps · calls a model · Redis, WhatsApp](https://millionrounds.com/workflow/debounce-and-buffer-whatsapp-ai-replies-with-redis-and-gemin)
- [**WhatsApp chat agent with Gemini and Supabase** 28 steps · calls a model · Supabase, WhatsApp](https://millionrounds.com/workflow/whatsapp-chat-agent-with-gemini-and-supabase)
- [**AI Restaurant Virtual Waiter Chatbot for WhatsApp & Website** 27 steps · calls a model · Google Sheets, WhatsApp](https://millionrounds.com/workflow/ai-restaurant-virtual-waiter-chatbot-for-whatsapp-and-websit)
- [**AI-powered WhatsApp chatbot for text, voice, images & PDFs** 26 steps · calls a model · WhatsApp](https://millionrounds.com/workflow/ai-powered-whatsapp-chatbot-for-text-voice-images-and-pdfs)