To view and manage your experiments programmatically, you can use the Phoenix API. You can retrieve experiments by their dataset using the list_experiments endpoint. This allows you to access details of experiments that have been run against a specific dataset. If you need to evaluate these experiments further, you can use the evaluate_experiment function to add additional evaluations to an already run experiment, as long as you have the experiment object.Would you like more detail on how to use these API endpoints or functions? Sources:
- Experiments API
馃挕聽Hint: Mention RunLLM in the thread for followups.