Create Metric

Create a metric for evaluating your products.

Returns

Returns a Metric object for the given parameters, or None if an error occurs.

Examples

AI Evaluation

metric = galtea.metrics.create(
    name="accuracy_v1_" + run_identifier,
    evaluator_model_name="GPT-4.1",
    source="partial_prompt",
    judge_prompt="Determine whether the actual output is equivalent to the expected output",
    evaluation_params=["input", "actual_output", "expected_output"],
    tags=["custom", "accuracy"],
    description="A custom accuracy metric.",
)

Human Evaluation

metric = galtea.metrics.create(
    name="human_eval_v1_" + run_identifier,
    source="human_evaluation",
    judge_prompt="Review the actual output and score it based on helpfulness, accuracy, and tone. Score 1 if the response is helpful and accurate. Score 0 if it is unhelpful or incorrect.",
    evaluation_params=["input", "actual_output", "expected_output"],
    user_group_ids=[user_group_id],
    tags=["human", "quality"],
    description="A human evaluation metric scored by QA annotators.",
)

Self-Hosted

metric = galtea.metrics.create(
    name="accuracy_v1_self_" + run_identifier,
    source="self_hosted",
    tags=["custom", "accuracy"],
    description="A custom accuracy metric calculated by our custom score function.",
)

Parameters

name · string · required

The name of the metric.

test_type · string

Deprecated. This parameter is ignored and will be removed in a future release.

evaluator_model_name · string

The name of the model used to evaluate the metric. Required for metrics using judge_prompt.

Available models:

• "Claude-Sonnet-4.5"
• "Claude-Sonnet-3.7"
• "GPT-4.1-mini"
• "Gemini-2.5-Flash-Lite"
• "Gemini-2.5-Flash"
• "Gemini-2.0-flash"
• "GPT-4o"
• "GPT-4.1"

It should not be provided if the metric is “self hosted” (has no judge_prompt) since it does not require a model for evaluation.

judge_prompt · string

A custom prompt that defines the evaluation logic for the metric. For AI Evaluation metrics, write the evaluation criteria and scoring rubric — Galtea will prepend the selected evaluation_params automatically. For Human Evaluation metrics, this serves as the annotation rubric. If omitted, the metric is considered a deterministic “Custom Score” metric.

source · string

The evaluation method for the metric. Possible values:

• "partial_prompt" — AI Evaluation: You provide the core evaluation criteria and rubric. Galtea dynamically constructs the final prompt by prepending selected evaluation parameters to your criteria.
• "human_evaluation" — Human Evaluation: Human annotators manually review and score evaluations using the annotation criteria you define. Evaluations enter a PENDING_HUMAN status and are completed when an annotator submits a score.
• "self_hosted" — Self-Hosted: For deterministic metrics scored locally using the SDK’s CustomScoreEvaluationMetric. Your custom logic runs on your infrastructure, and the resulting score is uploaded to the platform.

Other string values are sent to the API unchanged, so values added in newer API versions can be used; the API rejects invalid ones.

evaluation_params · list[string]

Evaluation parameters to include in the judge prompt. These parameters are prepended to the judge prompt to construct the final evaluation prompt. To check the available evaluation parameters, see the Evaluation Parameters section.

Only applicable for AI Evaluation and Human Evaluation metrics.

user_group_ids · list[string]

A list of user group IDs to associate with this metric. Only applicable when source is human_evaluation.

• If user group IDs are specified, only users in those groups can annotate evaluations for this metric.
• If no user group IDs are specified, any user in the organization can annotate.

tags · list[string]

Tags to categorize the metric.

description · string

A brief description of what the metric evaluates.

documentation_url · string

A URL pointing to more detailed documentation about the metric.