diff --git a/docs/_static/llama-stack-spec.html b/docs/_static/llama-stack-spec.html index a5ea562bf..09d4cb805 100644 --- a/docs/_static/llama-stack-spec.html +++ b/docs/_static/llama-stack-spec.html @@ -8548,7 +8548,7 @@ }, "additionalProperties": false, "title": "EvaluationTask", - "description": "A task for evaluation. To specify a task, one of the following must be provided: - `benchmark_id`: Run evaluation task against a benchmark_id - `dataset_id` and `grader_ids`: Run evaluation task against a dataset_id and a list of grader_ids - `data_source` and `grader_ids`: Run evaluation task against a data source (e.g. rows, uri, etc.) and a list of grader_ids" + "description": "A task for evaluation. To specify a task, one of the following must be provided: - `benchmark_id`: Run evaluation task against a benchmark_id. Use this when you have a curated dataset and have settled on the graders. - `dataset_id` and `grader_ids`: Run evaluation task against a dataset_id and a list of grader_ids. Use this when you have datasets and / or are iterating on your graders. - `data_source` and `grader_ids`: Run evaluation task against a data source (e.g. rows, uri, etc.) and a list of grader_ids. Prefer this when you are early in your evaluation cycle and experimenting much more with your data and graders." }, "GradeRequest": { "type": "object", diff --git a/docs/_static/llama-stack-spec.yaml b/docs/_static/llama-stack-spec.yaml index 5676c91b6..72361c50e 100644 --- a/docs/_static/llama-stack-spec.yaml +++ b/docs/_static/llama-stack-spec.yaml @@ -5924,10 +5924,14 @@ components: title: EvaluationTask description: >- A task for evaluation. To specify a task, one of the following must be provided: - - `benchmark_id`: Run evaluation task against a benchmark_id - `dataset_id` - and `grader_ids`: Run evaluation task against a dataset_id and a list of grader_ids - - `data_source` and `grader_ids`: Run evaluation task against a data source - (e.g. rows, uri, etc.) and a list of grader_ids + - `benchmark_id`: Run evaluation task against a benchmark_id. Use this when + you have a curated dataset and have settled on the graders. - `dataset_id` + and `grader_ids`: Run evaluation task against a dataset_id and a list of grader_ids. + Use this when you have datasets and / or are iterating on your graders. - + `data_source` and `grader_ids`: Run evaluation task against a data source + (e.g. rows, uri, etc.) and a list of grader_ids. Prefer this when you are + early in your evaluation cycle and experimenting much more with your data + and graders. GradeRequest: type: object properties: