The flow
Starts it 2Model 8Logic 6Service 2
The steps in the order they run, from what starts it.
- 1When clicking ‘Execute workflow’Manual triggerStarts it
- 2Embeddings OpenAIEmbeddings Open AiModel
- 3Document LoaderDocument Default Data LoaderModel
- 4When chat message receivedChat triggerStarts it
- 5Chat MemoryMemory Buffer WindowModel
- 6OpenAI Chat ModelLm Chat Open AiModel
- 7OpenAI EmbeddingsEmbeddings Open AiModel
- 8Map Website URLsFirecrawlService
- 9Store in Vector DatabaseVector Store PineconeModel
- 10Customer Support AgentAgentModel
- 11Pinecone Vector StorageVector Store PineconeModel
- 12Filter and Normalize URLsCodeLogic
- 13Process URLs One by OneSplit In BatchesLogic
- 14Fetch Page ContentHttp RequestService
- 15Extract HTML and URLSetLogic
- 16Clean HTML to TextCodeLogic
- 17Check Text LengthIfLogic
- 18Split Text into ChunksCodeLogic
How it's built
- Starts on
- Someone opening a chat with it
- Steps
- 18, with 1 branch, 1 loop or waits
- Size
- Medium: a working afternoon
- Connects to
- 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 Pinecone account, 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.
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.