A structured output prompt is a type of prompt that produces a JSON object that follows some specific defined structure. In the conversational variant, the entire history of the conversation with the user is fed to the LLM as input to produce the object. The content template becomes the system prompt fed to the model. The model then produces a JSON object matching the given schema.
...
The output JSON object will be in whatever schema you define within the output-schema editor.
Properties
type | LLM |
needs conversation | true |
uses content template | true |
uses options template | true |
customizable output schema | true |