The flow
Starts it 2Model 2Logic 9Service 5
The steps in the order they run, from what starts it.
- 1OpenAI Chat Model1Lm Chat Open AiModel
- 2When fetching a dataset rowEvaluation triggerStarts it
- 3When chat message receivedChat triggerStarts it
- 4AI AgentAgentModel
- 5Remap InputSetLogic
- 6EvaluationEvaluationService
- 7Set Input FieldsSetLogic
- 8No Operation, do nothingNo OpLogic
- 9Get Embeddings1Http RequestService
- 10GroundTruth to ItemsSplit OutLogic
- 11Remap EmbeddingsSetLogic
- 12Get EmbeddingsHttp RequestService
- 13Create Embeddings ResultMergeLogic
- 14Remap Embeddings1SetLogic
- 15Calculate Similarity ScoreCodeLogic
- 16AggregateAggregateLogic
- 17Update OutputEvaluationService
- 18Update MetricsEvaluationService
How it's built
- Starts on
- Someone opening a chat with it
- Steps
- 18
- Size
- Medium: a working afternoon
- Connects to
- Nothing by connector; it calls services over plain HTTP
- Model
- OpenAI
Questions
What does it need to run?
An n8n 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. 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.
Before you run itNothing 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.