Sorratat S.

Hi Team May I ask about how to run experiment by batch Normally, we run LLMs with real-time, anyway for experimentation evaluation we can use batch api with 50% lower costs. https://platform.openai.com/docs/guides/batch Example

Please feel free to share, thanks in advance.

Hi Team, I would like to ask about Authorization Do we have SSO for user level access to UI, ? when planning to use I got the question from security team Thanks in advance 🙇‍♂️

Hi Team, I was running experiment with 1 example, 3 evaluators It suppose to run to get result only 1 time, right ? But with 3 evaluators, it keep run task to get result again again How could I run task only 1 time, then eval with 3 evaluator Thanks in advance

run_experiment( dataset, run_summarizer, evaluators=evaluators, experiment_name="subgraph_summarizer", concurrency=3, )

Hi Team, I already set up project name ("agentic-dev"), it can be tracked conversation inside this project Anyway, when running experimentation, it always create new project name ("evaluators") I need suggestion, how to control project name or using ("agentic-dev") for tracing evaluations Thanks in advance