The flow
Starts it 2Model 8Logic 3Service 2
The steps in the order they run, from what starts it.
- 1When clicking ‘Execute workflow’Manual triggerStarts it
- 2Embeddings HuggingFace InferenceEmbeddings Hugging Face InferenceModel
- 3Default Data LoaderDocument Default Data LoaderModel
- 4When chat message receivedChat triggerStarts it
- 5Embeddings HuggingFace Inference2Embeddings Hugging Face InferenceModel
- 6Knowledge DatabaseGoogle SheetsService
- 7Generate & Store EmbeddingsVector Store In MemoryModel
- 8Retrieve & Score EmbeddingsVector Store In MemoryModel
- 9Forward Chat MessageMergeLogic
- 10Extract QuestionsSetLogic
- 11Determine Question TypeIfLogic
- 12Chat ModelGoogle GeminiModel
- 13Get Respective AnswersGoogle SheetsService
- 14Respond to Chat1ChatModel
- 15Respond to ChatChatModel
How it's built
- Starts on
- Someone opening a chat with it
- Steps
- 15, with 1 branch
- Size
- Medium: a working afternoon
- Connects to
- Google Sheets, in-memory vectors
- 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 Sheets and in-memory vectors 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.
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.