CreatePseudoLabelJobRequest

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://artifacts.apis.io/lastmileai/json-schema/lastmileai-lmai-proto-webserver-v2-create-pseudo-label-job-request-schema.json",
  "title": "CreatePseudoLabelJobRequest",
  "x-generated": "2026-11-10",
  "x-method": "derived",
  "x-generator": "derive-json-schema.py",
  "x-source": "openapi/lastmileai-pseudo-label-job-api-openapi.yml#/components/schemas/lmai.proto.webserver.v2.CreatePseudoLabelJobRequest",
  "type": "object",
  "properties": {
    "pseudoLabelJobConfig": {
      "$ref": "#/$defs/lmai.proto.webserver.v2.PseudoLabelJobConfig",
      "description": "Partial configuration containing updates via its non-null fields."
    }
  },
  "required": [
    "pseudoLabelJobConfig"
  ],
  "$defs": {
    "lmai.proto.model_fine_tuning.v1.PromptTemplate": {
      "title": "PromptTemplate",
      "type": "object",
      "properties": {
        "id": {
          "type": "string"
        },
        "template": {
          "type": "string",
          "description": "The template string that defines the prompt"
        }
      },
      "required": [
        "id",
        "template"
      ]
    },
    "lmai.proto.webserver.v2.PseudoLabelJobConfig": {
      "title": "PseudoLabelJobConfig",
      "type": "object",
      "properties": {
        "name": {
          "type": "string",
          "description": "Optional name for the job."
        },
        "description": {
          "type": "string",
          "description": "Optional description for the job."
        },
        "datasetId": {
          "type": "string",
          "description": "ID of the main dataset to be pseudo-labeled"
        },
        "fewShotDatasetId": {
          "type": "string",
          "description": "ID of the dataset containing few-shot examples. Optional."
        },
        "activeLabeledDatasetId": {
          "type": "string",
          "description": "ID of the actively labeled dataset. Optional. If null, this job is for\n active learning."
        },
        "selectedColumns": {
          "type": "array",
          "items": {
            "type": "string",
            "description": "Subset of columns to be used in pseudo-labeling.\n Expected columns: input, output, ground_truth\n For example, a summarization task might not need an input column.\n By default, all columns are used."
          }
        },
        "promptTemplate": {
          "$ref": "#/$defs/lmai.proto.model_fine_tuning.v1.PromptTemplate"
        },
        "baseEvaluationMetric": {
          "type": "string",
          "enum": [
            "BASE_EVALUATION_METRIC_UNSPECIFIED",
            "BASE_EVALUATION_METRIC_FAITHFULNESS",
            "BASE_EVALUATION_METRIC_RELEVANCE",
            "BASE_EVALUATION_METRIC_TOXICITY",
            "BASE_EVALUATION_METRIC_QA",
            "BASE_EVALUATION_METRIC_SUMMARIZATION"
          ],
          "title": "BaseEvaluationMetric",
          "description": "Reserved field. Do not use  at the moment."
        },
        "skipActiveLabeling": {
          "type": "boolean",
          "description": "If true, skip active labeling, which involves an intermediate Dataset\n created for human labeling."
        }
      },
      "required": [
        "datasetId",
        "selectedColumns",
        "promptTemplate",
        "baseEvaluationMetric",
        "skipActiveLabeling"
      ],
      "description": "Configuration for LLM Judge labeling job."
    }
  }
}