Automation library · AI assistants

Detect hallucinations with a local model

Started by an event in a connected app. It calls services over plain HTTP rather than through connectors. It hands the judgement calls to a local model. 13 steps: a working afternoon to understand properly.

MediumCalls a model: a local model

13 stepsMedium: a working afternoon
0Branches: places the flow splits
0Loops or waits
0Services by connector: it calls them over plain HTTP

The flow

Starts it 2Model 4Logic 7

The steps in the order they run, from what starts it.

  1. 1Ollama Chat ModelLm Chat OllamaModel
  2. 2When clicking ‘Test workflow’Manual triggerStarts it
  3. 3When Executed by Another WorkflowExecute Workflow triggerStarts it
  4. 4Ollama ModelLm OllamaModel
  5. 5Basic LLM Chain4Chain LlmModel
  6. 6Edit FieldsSetLogic
  7. 7CodeCodeLogic
  8. 8Merge1MergeLogic
  9. 9Basic LLM ChainChain LlmModel
  10. 10MergeMergeLogic
  11. 11Split Out1Split OutLogic
  12. 12FilterFilterLogic
  13. 13AggregateAggregateLogic

How it's built

Starts on
An event in a connected app
Steps
13
Size
Medium: a working afternoon
Connects to
Nothing by connector; it calls services over plain HTTP
Model
a local model

Questions

What does it need to run?

An n8n account, and a key for a local model. You connect your own accounts after importing it; none are included.

What starts it?

It starts on an event in a connected app.

Does it use AI?

Yes. It calls a local model. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Plan an afternoon. 13 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 it

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 13 steps before you point it at anything that matters.