Creates a new evaluator with an initial version.
Payload Requirements
name must be unique within the given space.type must be template (the only supported type in this iteration).version.template_config.name is the eval column name; must match ^[a-zA-Z0-9_\s\-&()]+$.version.template_config.template is the prompt template; use {{variable}} for placeholders.version.template_config.classification_choices maps choice labels to numeric scores (e.g. {"relevant": 1, "irrelevant": 0}). When omitted, the evaluator produces freeform output.id, created_at, updated_at, created_by_user_id) are rejected on input.Most Arize AI endpoints require authentication. For those endpoints that require authentication, include your API key in the request header using the format
Body containing evaluator creation parameters with an initial version
Space global ID (base64)
Evaluator name (must be unique within the space)
Evaluator type. Only template is supported in this iteration.
template, code The initial version for the evaluator
Evaluator description
Returns the created evaluator with its initial version
An evaluator defines reusable evaluation logic that can be attached to evaluation tasks. The type field determines the kind of evaluation: template (LLM-based template evaluation) or code (custom code evaluation).
The unique identifier for the evaluator
The name of the evaluator
The evaluator type: template (LLM-based) or code (custom code)
template, code The unique identifier for the space the evaluator belongs to
When the evaluator was created
When the evaluator was last updated
The unique identifier for the user who created the evaluator
The resolved version of the evaluator
The description of the evaluator