Automation library · Research and reporting

Analyze, classify, and summarize Gmail with OpenAI RAG

Started by an arriving email, and works across Gmail, Google Sheets, Telegram 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. 20 steps, 1 branch: a working afternoon to understand properly.

MediumCalls a model: OpenAIRetrieval

Download free
20 stepsMedium: a working afternoon
1Branch: places the flow splits
0Loops or waits
4Services it connects to

The flow

Starts it 2Model 7Logic 4Service 7

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

  1. 1OpenAI Chat ModelLm Chat Open AiModel
  2. 2Gmail TriggerGmail triggerStarts it
  3. 3When clicking ‘Execute workflow’Manual triggerStarts it
  4. 4Prepare taxonomy documentsDocument Default Data LoaderModel
  5. 5Create embeddings (OpenAI)Embeddings Open AiModel
  6. 6Analyze email with RAG agentAgentModel
  7. 7Fetch full Gmail messageGmailService
  8. 8Get row(s) in sheetGoogle SheetsService
  9. 9Vector store, taxonomy indexVector Store In MemoryModel
  10. 10Vector store retriever (RAG tool)Vector Store In MemoryModel
  11. 11Parse AI analysis resultSetLogic
  12. 12Normalize email fieldsSetLogic
  13. 13Store processed emailGoogle SheetsService
  14. 14Check for new taxonomy itemsIfLogic
  15. 15Load taxonomy datasetGoogle SheetsService
  16. 16Generate audio summaryOpen AiModel
  17. 17Get next taxonomy IDCodeLogic
  18. 18Send audio summary to TelegramTelegramService
  19. 19Append new taxonomy entryGoogle SheetsService
  20. 20Notify admin about taxonomy updateTelegramService

How it's built

Starts on
An arriving email
Steps
20, with 1 branch
Size
Medium: a working afternoon
Connects to
Gmail, Google Sheets, Telegram, 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 Sheets, Telegram 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 arriving email.

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. 20 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 20 steps before you point it at anything that matters.