The flow
Starts it 1Model 8Logic 3Service 2
The steps in the order they run, from what starts it.
- 1DeepSeek LLMLm Chat Deep SeekModel
- 2OpenAI EmbeddingsEmbeddings Open AiModel
- 3GPT-4o-mini LLMLm Chat Open AiModel
- 4Teacher Session MemoryMemory Buffer WindowModel
- 5Chat TriggerChat triggerStarts it
- 6Classifier MemoryMemory Buffer WindowModel
- 7Intent ClassifierAgentModel
- 8Book Knowledge BaseVector Store PineconeModel
- 9AI Teacher AgentAgentModel
- 10Merge Input and PromptMergeLogic
- 11Fetch System PromptGoogle SheetsService
- 12Log Q&A to SheetsGoogle SheetsService
- 13Aggregate FieldsAggregateLogic
- 14Format Response OutputSetLogic
How it's built
- Starts on
- Someone opening a chat with it
- Steps
- 14
- Size
- Medium: a working afternoon
- Connects to
- Google Sheets, Pinecone
- Model
- DeepSeek, 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 Google Sheets and Pinecone accounts, and a key for DeepSeek and 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 DeepSeek and 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. 14 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 14 steps before you point it at anything that matters.