Settings Input / Output Advanced History

Input dataset

Input Dataset Format *

Input column *

Output column

Ground truth column

Context column

Outputs

Evaluation id

If empty, defaults to a random value. Limited to a-z, 0-9 and _. Specify same id as other Model Evaluation to overwrite.

Evaluation name

If empty, defaults to the date and time of evaluation

Labels

Can contain variables in ${} notation, which are expanded when the recipe is run.
A Model Evaluation will include dynamically generated evaluation:date and evaluationDataset:dataset-name labels, that you may override there.

Metrics

Evaluation metrics will be stored in the evaluation store and the metrics dataset. The highlighted metrics below are the recommended metrics associated with your task. A summary table on the right provides details on the required data for each metric. Learn more about metrics

Metrics to compute *

{{ metric.label }}

Required columns by metric
Input	Output	Ground Truth	Context

LLM-as-a-judge metrics computation

Define LLM connection to use for metrics computation (see metrics help for when each is required).

Embedding LLM

Completion LLM

Custom Metrics

Add custom evaluation metrics to score model on.

Warning: You do not have permission to run arbitrary code. The recipe will fail if it includes custom metrics and is run by a user not having this permission.

Input dataset

Outputs

Metrics

LLM-as-a-judge metrics computation

Custom Metrics

Python environment

Container configuration

Execution configuration

Completion LLM parameters

Metric configuration