LLMMeta Data
Payload for a Server.LLM node.
Constructors
Properties
Inference backend this node routes requests to.
sets the nodes this node reads from to complete its work when invoked
The set of InvocationTriggers configured to wake this node. The node processor checks the incoming event against this list before doing any work. An empty list means "never auto-fire" — only manual execution.
The action this node performs when it fires. Defaults to NodeAction.EXECUTE on every concrete implementation so that deserialising a payload that predates this field yields the original behaviour unchanged.
How the model should format its reply.
JSON Schema (or natural-language instruction) the model must follow when responseFormat is ResponseFormat.JSON. Defaults to LLMResult.JSON_SCHEMA so observer nodes can decode snapshot.value as LLMResult out of the box.
Upstream nodes whose values feed this one. For a filter or executor this is the data being read; for a trigger it is the value being watched.
System prompt prepended to every request. Blank means the server applies its default Krill persona automatically.