Create Pseudo Label Job
Create Pseudo Label Job
POST/api/2/auto_eval/pseudo_label_job/create
Step 1 of 2: Create a new job configuration for LLM Judge labeling, to be subsequently submitted by calling SubmitPseudoLabelJob.
Request
- application/json
Body
pseudoLabelJobConfig
object
required
Partial configuration containing updates via its non-null fields.
Optional name for the job.
Optional description for the job.
ID of the main dataset to be pseudo-labeled
ID of the dataset containing few-shot examples. Optional.
ID of the actively labeled dataset. Optional. If null, this job is for active learning.
promptTemplate
object
required
The template string that defines the prompt
Reserved field. Do not use at the moment.
Possible values: [BASE_EVALUATION_METRIC_UNSPECIFIED
, BASE_EVALUATION_METRIC_FAITHFULNESS
, BASE_EVALUATION_METRIC_RELEVANCE
, BASE_EVALUATION_METRIC_TOXICITY
, BASE_EVALUATION_METRIC_QA
, BASE_EVALUATION_METRIC_SUMMARIZATION
]
If true, skip active labeling, which involves an intermediate Dataset created for human labeling.
Responses
- 200
Successful operation
- application/json
- Schema
- Example (from schema)
Schema
{
"jobId": "string"
}