Automation library · AI assistants

Personalized email automation with Google Docs and Pinecone

Started by someone opening a chat with it, and works across Gmail, Google Docs and Pinecone. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 18 steps: a working afternoon to understand properly.

MediumCalls a model: OpenAIRetrieval

Download free
18 stepsMedium: a working afternoon
0Branches: places the flow splits
0Loops or waits
3Services it connects to

The flow

Starts it 3Model 13Service 2

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

  1. 1When clicking ‘Test workflow’Manual triggerStarts it
  2. 2Embeddings OpenAIEmbeddings Open AiModel
  3. 3Recursive Character Text SplitterText Splitter Recursive Character Text SplitterModel
  4. 4When Executed by Another WorkflowExecute Workflow triggerStarts it
  5. 5OpenAI Chat ModelLm Chat Open AiModel
  6. 6GmailGmail ToolService
  7. 7When chat message receivedChat triggerStarts it
  8. 8OpenAI Chat Model1Lm Chat Open AiModel
  9. 9send_mailTool WorkflowModel
  10. 10OpenAI Chat Model2Lm Chat Open AiModel
  11. 11Embeddings OpenAI1Embeddings Open AiModel
  12. 12Get a documentGoogle DocsService
  13. 13Pinecone Vector StoreVector Store PineconeModel
  14. 14Default Data LoaderDocument Default Data LoaderModel
  15. 15AI AgentAgentModel
  16. 16AI Agent1AgentModel
  17. 17Vectorstore MailsTool Vector StoreModel
  18. 18Pinecone Vector Store1Vector Store PineconeModel

How it's built

Starts on
Someone opening a chat with it
Steps
18
Size
Medium: a working afternoon
Connects to
Gmail, Google Docs, Pinecone
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 Docs and Pinecone 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. 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.