FAQ: Evaluation

• How do I upgrade my trace-level evaluators to observation-level evaluators?
• How do I work with observations in Neural Inverse Fast Preview (Neural Inverse v4)?
• How to create and manage Score Configs in Neural Inverse?
• How to evaluate sessions/conversations?
• How to retrieve experiment scores via UI or API/SDK?
• How to use Neural Inverse-hosted Evaluators on Dataset Runs?
• I have setup Neural Inverse, but I do not see any traces in the dashboard. How to solve this?
• What are scores in Neural Inverse and when should I use them?
• Why do observation lookups with the v3 SDK return 404?
• Why is my observation-level evaluator not executing?