The flow
Starts it 3Model 2Logic 2Service 5
The steps in the order they run, from what starts it.
- 1WebhookWebhookStarts it
- 2When clicking ‘Execute workflow’Manual triggerStarts it
- 3Google Vertex Chat ModelLm Chat Google VertexModel
- 4Embend User MessageHttp RequestService
- 5Content for the TrainingGoogle DocsService
- 6Basic LLM ChainChain LlmModel
- 7Search EmbeddingsHttp RequestService
- 8Splitting into ChunksCodeLogic
- 9Respond to WebhookRespond To WebhookStarts it
- 10AggregateAggregateLogic
- 11Embedding Uploaded documentHttp RequestService
- 12Save the embedding in DBSupabaseService
How it's built
- Starts on
- Another system calling it
- Steps
- 12
- Size
- Medium: a working afternoon
- Connects to
- Google Docs, Supabase
- Model
- A language model, family not declared
Questions
What does it need to run?
An n8n account, plus your own Google Docs and Supabase accounts, and a key for a language model. You connect your own accounts after importing it; none are included.
What starts it?
It starts on another system calling it.
Does it use AI?
Yes. It calls a language model. Model calls are billed by the provider, not by n8n.
How long does it take to set up?
Plan an afternoon. 12 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 12 steps before you point it at anything that matters.