Automation library · Documents and files

Answer product queries with WhatsApp and OpenAI

Started by an incoming WhatsApp message, and works across WhatsApp and in-memory vectors. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 18 steps, 1 branch: a working afternoon to understand properly.

MediumCalls a model: OpenAIRetrieval

18 stepsMedium: a working afternoon
1Branch: places the flow splits
0Loops or waits
2Services it connects to

The flow

Starts it 2Model 11Logic 1Service 4

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

  1. 1WhatsApp TriggerWhats App triggerStarts it
  2. 2OpenAI Chat ModelLm Chat Open AiModel
  3. 3Window Buffer MemoryMemory Buffer WindowModel
  4. 4Embeddings OpenAIEmbeddings Open AiModel
  5. 5OpenAI Chat Model1Lm Chat Open AiModel
  6. 6When clicking ‘Test workflow’Manual triggerStarts it
  7. 7Embeddings OpenAI1Embeddings Open AiModel
  8. 8Recursive Character Text SplitterText Splitter Recursive Character Text SplitterModel
  9. 9Handle Message TypesSwitchLogic
  10. 10AI Sales AgentAgentModel
  11. 11Product CatalogueVector Store In MemoryModel
  12. 12Vector Store ToolTool Vector StoreModel
  13. 13get Product BrochureHttp RequestService
  14. 14Create Product CatalogueVector Store In MemoryModel
  15. 15Default Data LoaderDocument Default Data LoaderModel
  16. 16Reply To User1Whats AppService
  17. 17Reply To UserWhats AppService
  18. 18Extract from FileExtract From FileService

How it's built

Starts on
An incoming WhatsApp message
Steps
18, with 1 branch
Size
Medium: a working afternoon
Connects to
WhatsApp, in-memory vectors
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 WhatsApp and in-memory vectors 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?

Plan an afternoon. 18 steps is enough that you should read each one before running it.

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 18 steps before you point it at anything that matters.