Judgments

Judgments are individual relevance assessments for search results returned by an evaluation run. Each judgment assigns a grade to a specific candidate within a query's result set, based on the evaluation's grading scale.

Judgments can be created manually by users or generated automatically by AI judges. When judgments are submitted, relevancy metrics for the affected queries are recalculated automatically.

📄️List judgments

Gets judgments for a query within a corpus, identified by corpus ID and query object hash (OId).

📄️Upsert judgments

Creates or updates the authenticated member's judgments. Judgments are scoped to a corpus