Automation library · AI assistants

Build a chatbot trained on your internal company data in 20mins

Started by someone opening a chat with it, and works across Google Drive and Pinecone. It puts Gemini behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 15 steps: a working afternoon to understand properly.

MediumCalls a model: GeminiRetrieval

15 stepsMedium: a working afternoon
0Branches: places the flow splits
0Loops or waits
2Services it connects to

The flow

Starts it 3Model 11Service 1

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

  1. 1Embeddings Google GeminiEmbeddings Google GeminiModel
  2. 2Recursive Character Text SplitterText Splitter Recursive Character Text SplitterModel
  3. 3Embeddings Google Gemini (retrieval)Embeddings Google GeminiModel
  4. 4Google Drive File UpdatedGoogle Drive triggerStarts it
  5. 5Google Drive File CreatedGoogle Drive triggerStarts it
  6. 6Window Buffer MemoryMemory Buffer WindowModel
  7. 7When chat message receivedChat triggerStarts it
  8. 8Google Gemini Chat ModelLm Chat Google GeminiModel
  9. 9Google Gemini Chat Model (retrieval)Lm Chat Google GeminiModel
  10. 10Pinecone Vector StoreVector Store PineconeModel
  11. 11Default Data LoaderDocument Default Data LoaderModel
  12. 12Pinecone Vector Store (Retrieval)Vector Store PineconeModel
  13. 13Download File From Google DriveGoogle DriveService
  14. 14AI AgentAgentModel
  15. 15Vector Store ToolTool Vector StoreModel

How it's built

Starts on
Someone opening a chat with it
Steps
15
Size
Medium: a working afternoon
Connects to
Google Drive, Pinecone
Model
Gemini
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 Drive and Pinecone accounts, and a key for Gemini. 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 Gemini. 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. 15 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 15 steps before you point it at anything that matters.