The flow
Starts it 2Model 11Service 1
The steps in the order they run, from what starts it.
- 1Embeddings Google GeminiEmbeddings Google GeminiModel
- 2Recursive Character Text SplitterText Splitter Recursive Character Text SplitterModel
- 3Embeddings Google Gemini (retrieval)Embeddings Google GeminiModel
- 4Window Buffer MemoryMemory Buffer WindowModel
- 5When chat message receivedChat triggerStarts it
- 6Google Gemini Chat ModelLm Chat Google GeminiModel
- 7Google Gemini Chat Model (retrieval)Lm Chat Google GeminiModel
- 8Schedule TriggerSchedule triggerStarts it
- 9Pinecone Vector StoreVector Store PineconeModel
- 10Default Data LoaderDocument Default Data LoaderModel
- 11Pinecone Vector Store (Retrieval)Vector Store PineconeModel
- 12AI AgentAgentModel
- 13Vector Store ToolTool Vector StoreModel
- 14Scrape website dataApifyService
How it's built
- Starts on
- Someone opening a chat with it
- Steps
- 14
- Size
- Medium: a working afternoon
- Connects to
- Apify, 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 Apify 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. 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.