Automation library · Customer support

Answer customer questions and book jobs with OpenAI RAG

Started by someone opening a chat with it, and works across Gmail, Google Calendar, Google Sheets 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. 16 steps: a working afternoon to understand properly.

MediumCalls a model: OpenAIRetrieval

16 stepsMedium: a working afternoon
0Branches: places the flow splits
0Loops or waits
4Services it connects to

The flow

Starts it 2Model 10Logic 1Service 3

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

  1. 1Run once to build knowledge indexManual triggerStarts it
  2. 2Split knowledge into chunksText Splitter Recursive Character Text SplitterModel
  3. 3OpenAI embeddings for indexingEmbeddings Open AiModel
  4. 4Receive customer chat messageChat triggerStarts it
  5. 5OpenAI chat model (gpt-4o-mini)Lm Chat Open AiModel
  6. 6Conversation memoryMemory Buffer WindowModel
  7. 7OpenAI embeddings for retrievalEmbeddings Open AiModel
  8. 8business_knowledgeTool Vector StoreModel
  9. 9check_availabilityGoogle Calendar ToolService
  10. 10create_bookingGoogle Sheets ToolService
  11. 11escalate_to_humanGmail ToolService
  12. 12Edit your services, prices and policiesSetLogic
  13. 13Load knowledge as documentsDocument Default Data LoaderModel
  14. 14Build knowledge indexVector Store In MemoryModel
  15. 15AI receptionist agentAgentModel
  16. 16Search business knowledgeVector Store In MemoryModel

How it's built

Starts on
Someone opening a chat with it
Steps
16
Size
Medium: a working afternoon
Connects to
Gmail, Google Calendar, Google Sheets, 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 Gmail, Google Calendar, Google Sheets 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 someone opening a chat with it.

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. 16 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 16 steps before you point it at anything that matters.