DQ Dataset Definitions API

The DQ Dataset Definitions API allows you to manage dataset definitions, which are used to define DQ Jobs.

Create or update the dataset definition of a DQ Job

post

Creates or updates the dataset definition of a DQ Job. Pre-authorization requirements:

• hasRole('ROLE_ADMIN') or hasRole('ROLE_DATASET_MANAGER') or hasDatasetAccess(#datasetDef.dataset)

Authorizations

bearer-jwt

AuthorizationstringRequired

Bearer authentication header of the form Bearer <token>.

Body

application/json

datasetstringOptional

runIdstringOptional

runIdEndstringOptional

runStatestring · enumOptionalPossible values:

passFailinteger · int32Optional

passFailLimitinteger · int32Optional

jobDescriptionstringOptional

coreMaxActiveConnectionsinteger · int32Optional

linkIdstring[]Optional

licenseKeystringOptional

logFilestringOptional

logLevelstringOptional

hootOnlybooleanOptional

prettyPrintbooleanOptional

useTemplatebooleanOptional

parallelbooleanOptional

planbooleanOptional

dataPreviewOffbooleanOptional

datasetSafeOffbooleanOptional

obslimitinteger · int32Optional

pgUserstringOptional

pgPasswordstringOptional

hoststringOptional

portstringOptional

userstringOptional

alertEmailstringOptional

scheduleTimestringOptional

schemaScorenumber · doubleOptional

optionAppendstringOptional

keyDelimiterstringOptional

pipelinestring[]Optional

runDatestring · date-timeWrite-onlyOptional

runDateEndstring · date-timeWrite-onlyOptional

metaTagsstring[]Optional

connectionTypestring · enumRead-onlyOptionalPossible values:

Responses

200

Returns the created or updated dataset definition

application/json

datasetstringOptional

runIdstringOptional

runIdEndstringOptional

runStatestring · enumOptionalPossible values:

passFailinteger · int32Optional

passFailLimitinteger · int32Optional

jobDescriptionstringOptional

coreMaxActiveConnectionsinteger · int32Optional

linkIdstring[]Optional

licenseKeystringOptional

logFilestringOptional

logLevelstringOptional

hootOnlybooleanOptional

prettyPrintbooleanOptional

useTemplatebooleanOptional

parallelbooleanOptional

planbooleanOptional

dataPreviewOffbooleanOptional

datasetSafeOffbooleanOptional

obslimitinteger · int32Optional

pgUserstringOptional

pgPasswordstringOptional

hoststringOptional

portstringOptional

userstringOptional

alertEmailstringOptional

scheduleTimestringOptional

schemaScorenumber · doubleOptional

optionAppendstringOptional

keyDelimiterstringOptional

pipelinestring[]Optional

runDatestring · date-timeWrite-onlyOptional

runDateEndstring · date-timeWrite-onlyOptional

metaTagsstring[]Optional

connectionTypestring · enumRead-onlyOptionalPossible values:

post/v3/datasetDefs

HTTPcURLJavaScriptPython

POST /v3/datasetDefs HTTP/1.1
Host: <host-name>
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 7604

{
  "dataset": "text",
  "runId": "text",
  "runIdEnd": "text",
  "runState": "DRAFT",
  "passFail": 1,
  "passFailLimit": 1,
  "jobDescription": "text",
  "jobId": {
    "id": 1,
    "uuid": "123e4567-e89b-12d3-a456-426614174000"
  },
  "coreMaxActiveConnections": 1,
  "linkId": [
    "text"
  ],
  "licenseKey": "text",
  "logFile": "text",
  "logLevel": "text",
  "hootOnly": true,
  "prettyPrint": true,
  "useTemplate": true,
  "parallel": true,
  "plan": true,
  "dataPreviewOff": true,
  "datasetSafeOff": true,
  "obslimit": 1,
  "pgUser": "text",
  "pgPassword": "text",
  "host": "text",
  "port": "text",
  "user": "text",
  "alertEmail": "text",
  "scheduleTime": "text",
  "schemaScore": 1,
  "optionAppend": "text",
  "keyDelimiter": "text",
  "agentId": {
    "id": 1,
    "uuid": "123e4567-e89b-12d3-a456-426614174000"
  },
  "load": {
    "readonly": true,
    "passwordManager": "text",
    "alias": "text",
    "query": "text",
    "queryHistory": "text",
    "key": "text",
    "expression": "text",
    "addDateColumn": true,
    "zeroFillNull": true,
    "replaceNulls": "text",
    "stringMode": true,
    "operator": "text",
    "dateColumn": "text",
    "transform": "text",
    "filter": "text",
    "filterNot": "text",
    "sample": 1,
    "backRun": 1,
    "backRunBin": "MINUTE",
    "unionLookBack": true,
    "unionLookBackMinRow": 1,
    "cache": true,
    "dateFormat": "text",
    "timeFormat": "text",
    "timestamp": true,
    "filePath": "text",
    "fileQuery": "text",
    "fullFile": true,
    "fileHeader": "text",
    "inferSchema": true,
    "fileType": "text",
    "delimiter": "text",
    "fileCharSet": "text",
    "skipLines": 1,
    "avroSchema": "text",
    "xmlRowTag": "text",
    "flatten": true,
    "handleMaps": true,
    "handleMixedJson": true,
    "multiLine": true,
    "lib": "text",
    "additionalLib": "text",
    "driverName": "text",
    "connectionName": "text",
    "connectionUrl": "text",
    "userName": "text",
    "password": "text",
    "connectionProperties": {
      "ANY_ADDITIONAL_PROPERTY": "text"
    },
    "hiveNative": true,
    "hiveNativeHWC": true,
    "useSql": true,
    "columnName": "text",
    "lowerBound": "text",
    "upperBound": "text",
    "numPartitions": 1,
    "partitionNumber": 1,
    "escapeWithBackTick": true,
    "escapeWithSingleQuote": true,
    "escapeWithDoubleQuote": true,
    "escapeCharacter": "text",
    "checkHeader": true,
    "archiveConnection": "text",
    "coreFetchMode": true,
    "archiveBreaks": true,
    "ruleSerial": true
  },
  "pushdown": {
    "dataset": "text",
    "connectionName": "text",
    "maxConnections": 1,
    "sourceQuery": "text",
    "backRuns": 1,
    "backRunBin": "text",
    "dateFormatType": "text",
    "threads": 1,
    "manualSourceQuery": true,
    "key": "text",
    "sourceOutputSchema": "text",
    "sourceBreakRules": true,
    "sourceBreakOutliers": true,
    "sourceBreakDupes": true,
    "sourceBreakShapes": true,
    "sourceBreakResults": true,
    "sqlLoggingToggle": true,
    "unionLookback": true,
    "unionLookbackMin": 1
  },
  "patterns": [
    {
      "id": 1,
      "dataset": "text",
      "only": true,
      "lookback": 1,
      "key": [
        "text"
      ],
      "dateColumn": "text",
      "include": [
        "text"
      ],
      "exclude": [
        "text"
      ],
      "score": 1,
      "minSupport": 1,
      "confidence": 1,
      "limit": 1,
      "query": "text",
      "filter": "text",
      "timeBin": "MINUTE"
    }
  ],
  "dupe": {
    "on": true,
    "only": true,
    "include": [
      "text"
    ],
    "exclude": [
      "text"
    ],
    "depth": 1,
    "lowerBound": 1,
    "upperBound": 1,
    "approximate": 1,
    "limitPerDupe": 1,
    "checkHeader": true,
    "filter": "text",
    "ignoreCase": true,
    "score": 1,
    "limit": 1
  },
  "profile": {
    "on": true,
    "only": true,
    "include": [
      "text"
    ],
    "exclude": [
      "text"
    ],
    "correlation": true,
    "histogram": true,
    "semantic": true,
    "dataConceptId": 1,
    "limit": 1,
    "histogramLimit": 1,
    "score": 1,
    "behavioralDimension": "text",
    "behavioralDimensionGroup": "text",
    "behavioralValueColumn": "text",
    "behaviorScoreOff": true,
    "behaviorLookback": 1,
    "behaviorMinSupport": 1,
    "profilePushDown": [
      "text"
    ],
    "behaviorRowCheck": true,
    "behaviorTimeCheck": true,
    "behaviorMinValueCheck": true,
    "behaviorMaxValueCheck": true,
    "behaviorMeanValueCheck": true,
    "behaviorNullCheck": true,
    "behaviorEmptyCheck": true,
    "behaviorUniqueCheck": true,
    "profileStringLength": true,
    "detectStringNumerics": true,
    "detectTopnBotn": true,
    "detectScalePrecision": true,
    "adaptiveTier": "text",
    "advancedTier": true,
    "filter": "text"
  },
  "source": {
    "on": true,
    "only": true,
    "validateValues": true,
    "key": [
      "text"
    ],
    "include": [
      "text"
    ],
    "exclude": [
      "text"
    ],
    "includeSrc": [
      "text"
    ],
    "excludeSrc": [
      "text"
    ],
    "map": {
      "ANY_ADDITIONAL_PROPERTY": "text"
    },
    "score": 1,
    "limit": 1,
    "sourcePushDownCount": true,
    "checkType": true,
    "checkCase": true,
    "validateSchemaOrder": true,
    "matches": true,
    "validateValuesThreshold": 1,
    "validateValuesThresholdStrictDownScore": true,
    "validateValuesShowAll": true,
    "validateValuesIgnoreNull": true,
    "validateValuesIgnoreEmpty": true,
    "validateValuesIgnorePrecision": true,
    "validateValuesTrim": true,
    "validateValuesShowMissingKeys": true,
    "validateSrcJoinOnly": true,
    "validateValuesFilter": "text",
    "dataset": "text",
    "driverName": "text",
    "user": "text",
    "password": "text",
    "passwordManager": "text",
    "connectionName": "text",
    "connectionUrl": "text",
    "query": "text",
    "lib": "text",
    "connectionProperties": {
      "ANY_ADDITIONAL_PROPERTY": "text"
    },
    "filePath": "text",
    "fileQuery": "text",
    "fullFile": true,
    "header": "text",
    "skipLines": 1,
    "inferSchema": true,
    "fileType": "text",
    "delimiter": "text",
    "fileCharSet": "text",
    "avroSchema": "text",
    "xmlRowTag": "text",
    "flatten": true,
    "handleMaps": true,
    "handleMixedJson": true,
    "multiLine": true,
    "filterCols": [
      "text"
    ]
  },
  "rule": {
    "on": true,
    "only": true,
    "lib": "text",
    "name": "text",
    "absoluteScoring": true,
    "ruleBreakPreviewLimit": 1
  },
  "colMatch": {
    "colMatchParallelProcesses": 1,
    "colMatchDurationMins": 1,
    "colMatchBatchSize": 1,
    "level": "text",
    "fuzzyDistance": 1,
    "connectionList": [
      {
        "dataset": "text",
        "url": "text",
        "user": "text",
        "password": "text",
        "query": "text",
        "filePath": "text",
        "driver": "text",
        "driverProps": {
          "ANY_ADDITIONAL_PROPERTY": "text"
        }
      }
    ]
  },
  "spark": {
    "numExecutors": 1,
    "driverMemory": "text",
    "executorMemory": "text",
    "executorCores": 1,
    "conf": "text",
    "queue": "text",
    "master": "text",
    "principal": "text",
    "keyTab": "text",
    "deployMode": "text",
    "jars": [
      "text"
    ],
    "packages": [
      "text"
    ],
    "files": [
      "text"
    ]
  },
  "env": {
    "dataset": "text",
    "jdbcPrincipal": "text",
    "jdbcKeyTab": "text"
  },
  "record": {
    "on": true,
    "in": "text",
    "notIn": "text",
    "include": [
      "text"
    ],
    "percDeltaLimit": 1,
    "score": 1,
    "dataset": "text",
    "dateColumn": "text",
    "keyColumn": "text",
    "timeBin": "MIN",
    "by": "MIN"
  },
  "stream": {
    "type": "Kafka",
    "kafkaDef": {
      "kafkaGroup": "text",
      "kafkaBroker": "text",
      "kafkaPort": "text",
      "kafkaTopic": "text",
      "kafkaKeySerde": "text",
      "kafkaValSerde": "text",
      "kafkaSaslEnabled": true,
      "kafkaSaslService": "text",
      "kafkaSslEnabled": true,
      "streamSchemaRegistryUrl": "text",
      "streamSchemaRegistryUser": "text",
      "streamSchemaRegistryPassword": "text",
      "streamInterval": "text",
      "streamSchema": "text",
      "streamFormat": "text",
      "streamMaxLull": "text"
    }
  },
  "pipeline": [
    "text"
  ],
  "runDate": "2026-07-12T00:57:50.354Z",
  "runDateEnd": "2026-07-12T00:57:50.354Z",
  "metaTags": [
    "text"
  ],
  "outlierConfiguration": {
    "columnSensitivitySettings": [
      {
        "name": "text",
        "weight": 1,
        "unit": "DEFAULT"
      }
    ],
    "configurations": [
      {
        "id": 1,
        "key": [
          "text"
        ],
        "include": [
          "text"
        ],
        "exclude": [
          "text"
        ],
        "timeColumn": "text",
        "timeBinQuery": "text",
        "limit": 1,
        "minHistory": 1,
        "historyLimit": 1,
        "score": 1,
        "aggFunc": "text",
        "aggQuery": "text",
        "query": "text",
        "categoricalColumnConcatenation": true,
        "limitCategorical": 1,
        "measurementUnit": "text",
        "multiplierUpper": 1,
        "multiplierLower": 1,
        "record": true,
        "filter": "text",
        "combine": true,
        "categoricalConfidenceType": "text",
        "categoricalTopN": 1,
        "categoricalBottomN": 1,
        "categoricalMaxConfidence": 1,
        "categoricalMaxFrequencyPercentile": 1,
        "categoricalMinFrequency": 1,
        "categoricalMinVariance": 1,
        "categoricalMaxCategoryN": 1,
        "categoricalParallel": true,
        "categoricalAlgorithm": "text",
        "categoricalAlgorithmParameters": {
          "ANY_ADDITIONAL_PROPERTY": "text"
        },
        "categoricalAlgorithmParametersString": "text"
      }
    ],
    "only": true,
    "lookback": 1,
    "dateColumn": "text",
    "timeBin": "MIN",
    "by": "MIN",
    "q1": 1,
    "q3": 1,
    "categorical": true
  },
  "shape": {
    "enabled": true,
    "totalScore": 1,
    "sensitivity": 1,
    "maxPerCol": 1,
    "maxColSize": 1,
    "granular": true,
    "columnSettings": [
      {
        "enabled": true,
        "name": "text",
        "type": "text"
      }
    ]
  },
  "jobSchedule": {
    "enabled": true,
    "dataset": "text",
    "agentId": {
      "id": 1,
      "uuid": "123e4567-e89b-12d3-a456-426614174000"
    },
    "runDateFormat": "text",
    "scheduleFrequency": "DAILY",
    "updatedAt": "2026-07-12T00:57:50.354Z",
    "scheduleTime": "text"
  }
}

200

Returns the created or updated dataset definition

{
  "dataset": "text",
  "runId": "text",
  "runIdEnd": "text",
  "runState": "DRAFT",
  "passFail": 1,
  "passFailLimit": 1,
  "jobDescription": "text",
  "jobId": {
    "id": 1,
    "uuid": "123e4567-e89b-12d3-a456-426614174000"
  },
  "coreMaxActiveConnections": 1,
  "linkId": [
    "text"
  ],
  "licenseKey": "text",
  "logFile": "text",
  "logLevel": "text",
  "hootOnly": true,
  "prettyPrint": true,
  "useTemplate": true,
  "parallel": true,
  "plan": true,
  "dataPreviewOff": true,
  "datasetSafeOff": true,
  "obslimit": 1,
  "pgUser": "text",
  "pgPassword": "text",
  "host": "text",
  "port": "text",
  "user": "text",
  "alertEmail": "text",
  "scheduleTime": "text",
  "schemaScore": 1,
  "optionAppend": "text",
  "keyDelimiter": "text",
  "agentId": {
    "id": 1,
    "uuid": "123e4567-e89b-12d3-a456-426614174000"
  },
  "load": {
    "readonly": true,
    "passwordManager": "text",
    "alias": "text",
    "query": "text",
    "queryHistory": "text",
    "key": "text",
    "expression": "text",
    "addDateColumn": true,
    "zeroFillNull": true,
    "replaceNulls": "text",
    "stringMode": true,
    "operator": "text",
    "dateColumn": "text",
    "transform": "text",
    "filter": "text",
    "filterNot": "text",
    "sample": 1,
    "backRun": 1,
    "backRunBin": "MINUTE",
    "unionLookBack": true,
    "unionLookBackMinRow": 1,
    "cache": true,
    "dateFormat": "text",
    "timeFormat": "text",
    "timestamp": true,
    "filePath": "text",
    "fileQuery": "text",
    "fullFile": true,
    "fileHeader": "text",
    "inferSchema": true,
    "fileType": "text",
    "delimiter": "text",
    "fileCharSet": "text",
    "skipLines": 1,
    "avroSchema": "text",
    "xmlRowTag": "text",
    "flatten": true,
    "handleMaps": true,
    "handleMixedJson": true,
    "multiLine": true,
    "lib": "text",
    "additionalLib": "text",
    "driverName": "text",
    "connectionName": "text",
    "connectionUrl": "text",
    "userName": "text",
    "password": "text",
    "connectionProperties": {
      "ANY_ADDITIONAL_PROPERTY": "text"
    },
    "hiveNative": true,
    "hiveNativeHWC": true,
    "useSql": true,
    "columnName": "text",
    "lowerBound": "text",
    "upperBound": "text",
    "numPartitions": 1,
    "partitionNumber": 1,
    "escapeWithBackTick": true,
    "escapeWithSingleQuote": true,
    "escapeWithDoubleQuote": true,
    "escapeCharacter": "text",
    "checkHeader": true,
    "archiveConnection": "text",
    "coreFetchMode": true,
    "archiveBreaks": true,
    "ruleSerial": true
  },
  "pushdown": {
    "dataset": "text",
    "connectionName": "text",
    "maxConnections": 1,
    "sourceQuery": "text",
    "backRuns": 1,
    "backRunBin": "text",
    "dateFormatType": "text",
    "threads": 1,
    "manualSourceQuery": true,
    "key": "text",
    "sourceOutputSchema": "text",
    "sourceBreakRules": true,
    "sourceBreakOutliers": true,
    "sourceBreakDupes": true,
    "sourceBreakShapes": true,
    "sourceBreakResults": true,
    "sqlLoggingToggle": true,
    "unionLookback": true,
    "unionLookbackMin": 1
  },
  "patterns": [
    {
      "id": 1,
      "dataset": "text",
      "only": true,
      "lookback": 1,
      "key": [
        "text"
      ],
      "dateColumn": "text",
      "include": [
        "text"
      ],
      "exclude": [
        "text"
      ],
      "score": 1,
      "minSupport": 1,
      "confidence": 1,
      "limit": 1,
      "query": "text",
      "filter": "text",
      "timeBin": "MINUTE"
    }
  ],
  "dupe": {
    "on": true,
    "only": true,
    "include": [
      "text"
    ],
    "exclude": [
      "text"
    ],
    "depth": 1,
    "lowerBound": 1,
    "upperBound": 1,
    "approximate": 1,
    "limitPerDupe": 1,
    "checkHeader": true,
    "filter": "text",
    "ignoreCase": true,
    "score": 1,
    "limit": 1
  },
  "profile": {
    "on": true,
    "only": true,
    "include": [
      "text"
    ],
    "exclude": [
      "text"
    ],
    "correlation": true,
    "histogram": true,
    "semantic": true,
    "dataConceptId": 1,
    "limit": 1,
    "histogramLimit": 1,
    "score": 1,
    "behavioralDimension": "text",
    "behavioralDimensionGroup": "text",
    "behavioralValueColumn": "text",
    "behaviorScoreOff": true,
    "behaviorLookback": 1,
    "behaviorMinSupport": 1,
    "profilePushDown": [
      "text"
    ],
    "behaviorRowCheck": true,
    "behaviorTimeCheck": true,
    "behaviorMinValueCheck": true,
    "behaviorMaxValueCheck": true,
    "behaviorMeanValueCheck": true,
    "behaviorNullCheck": true,
    "behaviorEmptyCheck": true,
    "behaviorUniqueCheck": true,
    "profileStringLength": true,
    "detectStringNumerics": true,
    "detectTopnBotn": true,
    "detectScalePrecision": true,
    "adaptiveTier": "text",
    "advancedTier": true,
    "filter": "text"
  },
  "source": {
    "on": true,
    "only": true,
    "validateValues": true,
    "key": [
      "text"
    ],
    "include": [
      "text"
    ],
    "exclude": [
      "text"
    ],
    "includeSrc": [
      "text"
    ],
    "excludeSrc": [
      "text"
    ],
    "map": {
      "ANY_ADDITIONAL_PROPERTY": "text"
    },
    "score": 1,
    "limit": 1,
    "sourcePushDownCount": true,
    "checkType": true,
    "checkCase": true,
    "validateSchemaOrder": true,
    "matches": true,
    "validateValuesThreshold": 1,
    "validateValuesThresholdStrictDownScore": true,
    "validateValuesShowAll": true,
    "validateValuesIgnoreNull": true,
    "validateValuesIgnoreEmpty": true,
    "validateValuesIgnorePrecision": true,
    "validateValuesTrim": true,
    "validateValuesShowMissingKeys": true,
    "validateSrcJoinOnly": true,
    "validateValuesFilter": "text",
    "dataset": "text",
    "driverName": "text",
    "user": "text",
    "password": "text",
    "passwordManager": "text",
    "connectionName": "text",
    "connectionUrl": "text",
    "query": "text",
    "lib": "text",
    "connectionProperties": {
      "ANY_ADDITIONAL_PROPERTY": "text"
    },
    "filePath": "text",
    "fileQuery": "text",
    "fullFile": true,
    "header": "text",
    "skipLines": 1,
    "inferSchema": true,
    "fileType": "text",
    "delimiter": "text",
    "fileCharSet": "text",
    "avroSchema": "text",
    "xmlRowTag": "text",
    "flatten": true,
    "handleMaps": true,
    "handleMixedJson": true,
    "multiLine": true,
    "filterCols": [
      "text"
    ]
  },
  "rule": {
    "on": true,
    "only": true,
    "lib": "text",
    "name": "text",
    "absoluteScoring": true,
    "ruleBreakPreviewLimit": 1
  },
  "colMatch": {
    "colMatchParallelProcesses": 1,
    "colMatchDurationMins": 1,
    "colMatchBatchSize": 1,
    "level": "text",
    "fuzzyDistance": 1,
    "connectionList": [
      {
        "dataset": "text",
        "url": "text",
        "user": "text",
        "password": "text",
        "query": "text",
        "filePath": "text",
        "driver": "text",
        "driverProps": {
          "ANY_ADDITIONAL_PROPERTY": "text"
        }
      }
    ]
  },
  "spark": {
    "numExecutors": 1,
    "driverMemory": "text",
    "executorMemory": "text",
    "executorCores": 1,
    "conf": "text",
    "queue": "text",
    "master": "text",
    "principal": "text",
    "keyTab": "text",
    "deployMode": "text",
    "jars": [
      "text"
    ],
    "packages": [
      "text"
    ],
    "files": [
      "text"
    ]
  },
  "env": {
    "dataset": "text",
    "jdbcPrincipal": "text",
    "jdbcKeyTab": "text"
  },
  "record": {
    "on": true,
    "in": "text",
    "notIn": "text",
    "include": [
      "text"
    ],
    "percDeltaLimit": 1,
    "score": 1,
    "dataset": "text",
    "dateColumn": "text",
    "keyColumn": "text",
    "timeBin": "MIN",
    "by": "MIN"
  },
  "stream": {
    "type": "Kafka",
    "kafkaDef": {
      "kafkaGroup": "text",
      "kafkaBroker": "text",
      "kafkaPort": "text",
      "kafkaTopic": "text",
      "kafkaKeySerde": "text",
      "kafkaValSerde": "text",
      "kafkaSaslEnabled": true,
      "kafkaSaslService": "text",
      "kafkaSslEnabled": true,
      "streamSchemaRegistryUrl": "text",
      "streamSchemaRegistryUser": "text",
      "streamSchemaRegistryPassword": "text",
      "streamInterval": "text",
      "streamSchema": "text",
      "streamFormat": "text",
      "streamMaxLull": "text"
    }
  },
  "pipeline": [
    "text"
  ],
  "metaTags": [
    "text"
  ],
  "outlierConfiguration": {
    "columnSensitivitySettings": [
      {
        "name": "text",
        "weight": 1,
        "unit": "DEFAULT"
      }
    ],
    "configurations": [
      {
        "id": 1,
        "key": [
          "text"
        ],
        "include": [
          "text"
        ],
        "exclude": [
          "text"
        ],
        "timeColumn": "text",
        "timeBinQuery": "text",
        "limit": 1,
        "minHistory": 1,
        "historyLimit": 1,
        "score": 1,
        "aggFunc": "text",
        "aggQuery": "text",
        "query": "text",
        "categoricalColumnConcatenation": true,
        "limitCategorical": 1,
        "measurementUnit": "text",
        "multiplierUpper": 1,
        "multiplierLower": 1,
        "record": true,
        "filter": "text",
        "combine": true,
        "categoricalConfidenceType": "text",
        "categoricalTopN": 1,
        "categoricalBottomN": 1,
        "categoricalMaxConfidence": 1,
        "categoricalMaxFrequencyPercentile": 1,
        "categoricalMinFrequency": 1,
        "categoricalMinVariance": 1,
        "categoricalMaxCategoryN": 1,
        "categoricalParallel": true,
        "categoricalAlgorithm": "text",
        "categoricalAlgorithmParameters": {
          "ANY_ADDITIONAL_PROPERTY": "text"
        }
      }
    ],
    "only": true,
    "lookback": 1,
    "dateColumn": "text",
    "timeBin": "MIN",
    "by": "MIN",
    "q1": 1,
    "q3": 1,
    "categorical": true
  },
  "shape": {
    "enabled": true,
    "totalScore": 1,
    "sensitivity": 1,
    "maxPerCol": 1,
    "maxColSize": 1,
    "granular": true,
    "columnSettings": [
      {
        "enabled": true,
        "name": "text",
        "type": "text"
      }
    ]
  },
  "jobSchedule": {
    "enabled": true,
    "dataset": "text",
    "agentId": {
      "id": 1,
      "uuid": "123e4567-e89b-12d3-a456-426614174000"
    },
    "runDateFormat": "text",
    "scheduleFrequency": "DAILY",
    "updatedAt": "2026-07-12T00:57:50.354Z",
    "scheduleTime": "text"
  },
  "connectionType": "PULLUP"
}

Create or update the dataset definition of a DQ Job

put

Creates or updates the dataset definition of a DQ Job. Pre-authorization requirements:

• hasRole('ROLE_ADMIN') or hasRole('ROLE_DATASET_MANAGER') or hasDatasetAccess(#datasetDef.dataset)

Authorizations

bearer-jwt

AuthorizationstringRequired

Bearer authentication header of the form Bearer <token>.

Body

application/json

datasetstringOptional

runIdstringOptional

runIdEndstringOptional

runStatestring · enumOptionalPossible values:

passFailinteger · int32Optional

passFailLimitinteger · int32Optional

jobDescriptionstringOptional

coreMaxActiveConnectionsinteger · int32Optional

linkIdstring[]Optional

licenseKeystringOptional

logFilestringOptional

logLevelstringOptional

hootOnlybooleanOptional

prettyPrintbooleanOptional

useTemplatebooleanOptional

parallelbooleanOptional

planbooleanOptional

dataPreviewOffbooleanOptional

datasetSafeOffbooleanOptional

obslimitinteger · int32Optional

pgUserstringOptional

pgPasswordstringOptional

hoststringOptional

portstringOptional

userstringOptional

alertEmailstringOptional

scheduleTimestringOptional

schemaScorenumber · doubleOptional

optionAppendstringOptional

keyDelimiterstringOptional

pipelinestring[]Optional

runDatestring · date-timeWrite-onlyOptional

runDateEndstring · date-timeWrite-onlyOptional

metaTagsstring[]Optional

connectionTypestring · enumRead-onlyOptionalPossible values:

Responses

200

Returns the created or updated dataset definition

application/json

datasetstringOptional

runIdstringOptional

runIdEndstringOptional

runStatestring · enumOptionalPossible values:

passFailinteger · int32Optional

passFailLimitinteger · int32Optional

jobDescriptionstringOptional

coreMaxActiveConnectionsinteger · int32Optional

linkIdstring[]Optional

licenseKeystringOptional

logFilestringOptional

logLevelstringOptional

hootOnlybooleanOptional

prettyPrintbooleanOptional

useTemplatebooleanOptional

parallelbooleanOptional

planbooleanOptional

dataPreviewOffbooleanOptional

datasetSafeOffbooleanOptional

obslimitinteger · int32Optional

pgUserstringOptional

pgPasswordstringOptional

hoststringOptional

portstringOptional

userstringOptional

alertEmailstringOptional

scheduleTimestringOptional

schemaScorenumber · doubleOptional

optionAppendstringOptional

keyDelimiterstringOptional

pipelinestring[]Optional

runDatestring · date-timeWrite-onlyOptional

runDateEndstring · date-timeWrite-onlyOptional

metaTagsstring[]Optional

connectionTypestring · enumRead-onlyOptionalPossible values:

put/v3/datasetDefs

HTTPcURLJavaScriptPython

PUT /v3/datasetDefs HTTP/1.1
Host: <host-name>
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 7604

{
  "dataset": "text",
  "runId": "text",
  "runIdEnd": "text",
  "runState": "DRAFT",
  "passFail": 1,
  "passFailLimit": 1,
  "jobDescription": "text",
  "jobId": {
    "id": 1,
    "uuid": "123e4567-e89b-12d3-a456-426614174000"
  },
  "coreMaxActiveConnections": 1,
  "linkId": [
    "text"
  ],
  "licenseKey": "text",
  "logFile": "text",
  "logLevel": "text",
  "hootOnly": true,
  "prettyPrint": true,
  "useTemplate": true,
  "parallel": true,
  "plan": true,
  "dataPreviewOff": true,
  "datasetSafeOff": true,
  "obslimit": 1,
  "pgUser": "text",
  "pgPassword": "text",
  "host": "text",
  "port": "text",
  "user": "text",
  "alertEmail": "text",
  "scheduleTime": "text",
  "schemaScore": 1,
  "optionAppend": "text",
  "keyDelimiter": "text",
  "agentId": {
    "id": 1,
    "uuid": "123e4567-e89b-12d3-a456-426614174000"
  },
  "load": {
    "readonly": true,
    "passwordManager": "text",
    "alias": "text",
    "query": "text",
    "queryHistory": "text",
    "key": "text",
    "expression": "text",
    "addDateColumn": true,
    "zeroFillNull": true,
    "replaceNulls": "text",
    "stringMode": true,
    "operator": "text",
    "dateColumn": "text",
    "transform": "text",
    "filter": "text",
    "filterNot": "text",
    "sample": 1,
    "backRun": 1,
    "backRunBin": "MINUTE",
    "unionLookBack": true,
    "unionLookBackMinRow": 1,
    "cache": true,
    "dateFormat": "text",
    "timeFormat": "text",
    "timestamp": true,
    "filePath": "text",
    "fileQuery": "text",
    "fullFile": true,
    "fileHeader": "text",
    "inferSchema": true,
    "fileType": "text",
    "delimiter": "text",
    "fileCharSet": "text",
    "skipLines": 1,
    "avroSchema": "text",
    "xmlRowTag": "text",
    "flatten": true,
    "handleMaps": true,
    "handleMixedJson": true,
    "multiLine": true,
    "lib": "text",
    "additionalLib": "text",
    "driverName": "text",
    "connectionName": "text",
    "connectionUrl": "text",
    "userName": "text",
    "password": "text",
    "connectionProperties": {
      "ANY_ADDITIONAL_PROPERTY": "text"
    },
    "hiveNative": true,
    "hiveNativeHWC": true,
    "useSql": true,
    "columnName": "text",
    "lowerBound": "text",
    "upperBound": "text",
    "numPartitions": 1,
    "partitionNumber": 1,
    "escapeWithBackTick": true,
    "escapeWithSingleQuote": true,
    "escapeWithDoubleQuote": true,
    "escapeCharacter": "text",
    "checkHeader": true,
    "archiveConnection": "text",
    "coreFetchMode": true,
    "archiveBreaks": true,
    "ruleSerial": true
  },
  "pushdown": {
    "dataset": "text",
    "connectionName": "text",
    "maxConnections": 1,
    "sourceQuery": "text",
    "backRuns": 1,
    "backRunBin": "text",
    "dateFormatType": "text",
    "threads": 1,
    "manualSourceQuery": true,
    "key": "text",
    "sourceOutputSchema": "text",
    "sourceBreakRules": true,
    "sourceBreakOutliers": true,
    "sourceBreakDupes": true,
    "sourceBreakShapes": true,
    "sourceBreakResults": true,
    "sqlLoggingToggle": true,
    "unionLookback": true,
    "unionLookbackMin": 1
  },
  "patterns": [
    {
      "id": 1,
      "dataset": "text",
      "only": true,
      "lookback": 1,
      "key": [
        "text"
      ],
      "dateColumn": "text",
      "include": [
        "text"
      ],
      "exclude": [
        "text"
      ],
      "score": 1,
      "minSupport": 1,
      "confidence": 1,
      "limit": 1,
      "query": "text",
      "filter": "text",
      "timeBin": "MINUTE"
    }
  ],
  "dupe": {
    "on": true,
    "only": true,
    "include": [
      "text"
    ],
    "exclude": [
      "text"
    ],
    "depth": 1,
    "lowerBound": 1,
    "upperBound": 1,
    "approximate": 1,
    "limitPerDupe": 1,
    "checkHeader": true,
    "filter": "text",
    "ignoreCase": true,
    "score": 1,
    "limit": 1
  },
  "profile": {
    "on": true,
    "only": true,
    "include": [
      "text"
    ],
    "exclude": [
      "text"
    ],
    "correlation": true,
    "histogram": true,
    "semantic": true,
    "dataConceptId": 1,
    "limit": 1,
    "histogramLimit": 1,
    "score": 1,
    "behavioralDimension": "text",
    "behavioralDimensionGroup": "text",
    "behavioralValueColumn": "text",
    "behaviorScoreOff": true,
    "behaviorLookback": 1,
    "behaviorMinSupport": 1,
    "profilePushDown": [
      "text"
    ],
    "behaviorRowCheck": true,
    "behaviorTimeCheck": true,
    "behaviorMinValueCheck": true,
    "behaviorMaxValueCheck": true,
    "behaviorMeanValueCheck": true,
    "behaviorNullCheck": true,
    "behaviorEmptyCheck": true,
    "behaviorUniqueCheck": true,
    "profileStringLength": true,
    "detectStringNumerics": true,
    "detectTopnBotn": true,
    "detectScalePrecision": true,
    "adaptiveTier": "text",
    "advancedTier": true,
    "filter": "text"
  },
  "source": {
    "on": true,
    "only": true,
    "validateValues": true,
    "key": [
      "text"
    ],
    "include": [
      "text"
    ],
    "exclude": [
      "text"
    ],
    "includeSrc": [
      "text"
    ],
    "excludeSrc": [
      "text"
    ],
    "map": {
      "ANY_ADDITIONAL_PROPERTY": "text"
    },
    "score": 1,
    "limit": 1,
    "sourcePushDownCount": true,
    "checkType": true,
    "checkCase": true,
    "validateSchemaOrder": true,
    "matches": true,
    "validateValuesThreshold": 1,
    "validateValuesThresholdStrictDownScore": true,
    "validateValuesShowAll": true,
    "validateValuesIgnoreNull": true,
    "validateValuesIgnoreEmpty": true,
    "validateValuesIgnorePrecision": true,
    "validateValuesTrim": true,
    "validateValuesShowMissingKeys": true,
    "validateSrcJoinOnly": true,
    "validateValuesFilter": "text",
    "dataset": "text",
    "driverName": "text",
    "user": "text",
    "password": "text",
    "passwordManager": "text",
    "connectionName": "text",
    "connectionUrl": "text",
    "query": "text",
    "lib": "text",
    "connectionProperties": {
      "ANY_ADDITIONAL_PROPERTY": "text"
    },
    "filePath": "text",
    "fileQuery": "text",
    "fullFile": true,
    "header": "text",
    "skipLines": 1,
    "inferSchema": true,
    "fileType": "text",
    "delimiter": "text",
    "fileCharSet": "text",
    "avroSchema": "text",
    "xmlRowTag": "text",
    "flatten": true,
    "handleMaps": true,
    "handleMixedJson": true,
    "multiLine": true,
    "filterCols": [
      "text"
    ]
  },
  "rule": {
    "on": true,
    "only": true,
    "lib": "text",
    "name": "text",
    "absoluteScoring": true,
    "ruleBreakPreviewLimit": 1
  },
  "colMatch": {
    "colMatchParallelProcesses": 1,
    "colMatchDurationMins": 1,
    "colMatchBatchSize": 1,
    "level": "text",
    "fuzzyDistance": 1,
    "connectionList": [
      {
        "dataset": "text",
        "url": "text",
        "user": "text",
        "password": "text",
        "query": "text",
        "filePath": "text",
        "driver": "text",
        "driverProps": {
          "ANY_ADDITIONAL_PROPERTY": "text"
        }
      }
    ]
  },
  "spark": {
    "numExecutors": 1,
    "driverMemory": "text",
    "executorMemory": "text",
    "executorCores": 1,
    "conf": "text",
    "queue": "text",
    "master": "text",
    "principal": "text",
    "keyTab": "text",
    "deployMode": "text",
    "jars": [
      "text"
    ],
    "packages": [
      "text"
    ],
    "files": [
      "text"
    ]
  },
  "env": {
    "dataset": "text",
    "jdbcPrincipal": "text",
    "jdbcKeyTab": "text"
  },
  "record": {
    "on": true,
    "in": "text",
    "notIn": "text",
    "include": [
      "text"
    ],
    "percDeltaLimit": 1,
    "score": 1,
    "dataset": "text",
    "dateColumn": "text",
    "keyColumn": "text",
    "timeBin": "MIN",
    "by": "MIN"
  },
  "stream": {
    "type": "Kafka",
    "kafkaDef": {
      "kafkaGroup": "text",
      "kafkaBroker": "text",
      "kafkaPort": "text",
      "kafkaTopic": "text",
      "kafkaKeySerde": "text",
      "kafkaValSerde": "text",
      "kafkaSaslEnabled": true,
      "kafkaSaslService": "text",
      "kafkaSslEnabled": true,
      "streamSchemaRegistryUrl": "text",
      "streamSchemaRegistryUser": "text",
      "streamSchemaRegistryPassword": "text",
      "streamInterval": "text",
      "streamSchema": "text",
      "streamFormat": "text",
      "streamMaxLull": "text"
    }
  },
  "pipeline": [
    "text"
  ],
  "runDate": "2026-07-12T00:57:50.354Z",
  "runDateEnd": "2026-07-12T00:57:50.354Z",
  "metaTags": [
    "text"
  ],
  "outlierConfiguration": {
    "columnSensitivitySettings": [
      {
        "name": "text",
        "weight": 1,
        "unit": "DEFAULT"
      }
    ],
    "configurations": [
      {
        "id": 1,
        "key": [
          "text"
        ],
        "include": [
          "text"
        ],
        "exclude": [
          "text"
        ],
        "timeColumn": "text",
        "timeBinQuery": "text",
        "limit": 1,
        "minHistory": 1,
        "historyLimit": 1,
        "score": 1,
        "aggFunc": "text",
        "aggQuery": "text",
        "query": "text",
        "categoricalColumnConcatenation": true,
        "limitCategorical": 1,
        "measurementUnit": "text",
        "multiplierUpper": 1,
        "multiplierLower": 1,
        "record": true,
        "filter": "text",
        "combine": true,
        "categoricalConfidenceType": "text",
        "categoricalTopN": 1,
        "categoricalBottomN": 1,
        "categoricalMaxConfidence": 1,
        "categoricalMaxFrequencyPercentile": 1,
        "categoricalMinFrequency": 1,
        "categoricalMinVariance": 1,
        "categoricalMaxCategoryN": 1,
        "categoricalParallel": true,
        "categoricalAlgorithm": "text",
        "categoricalAlgorithmParameters": {
          "ANY_ADDITIONAL_PROPERTY": "text"
        },
        "categoricalAlgorithmParametersString": "text"
      }
    ],
    "only": true,
    "lookback": 1,
    "dateColumn": "text",
    "timeBin": "MIN",
    "by": "MIN",
    "q1": 1,
    "q3": 1,
    "categorical": true
  },
  "shape": {
    "enabled": true,
    "totalScore": 1,
    "sensitivity": 1,
    "maxPerCol": 1,
    "maxColSize": 1,
    "granular": true,
    "columnSettings": [
      {
        "enabled": true,
        "name": "text",
        "type": "text"
      }
    ]
  },
  "jobSchedule": {
    "enabled": true,
    "dataset": "text",
    "agentId": {
      "id": 1,
      "uuid": "123e4567-e89b-12d3-a456-426614174000"
    },
    "runDateFormat": "text",
    "scheduleFrequency": "DAILY",
    "updatedAt": "2026-07-12T00:57:50.354Z",
    "scheduleTime": "text"
  }
}

200

Returns the created or updated dataset definition

{
  "dataset": "text",
  "runId": "text",
  "runIdEnd": "text",
  "runState": "DRAFT",
  "passFail": 1,
  "passFailLimit": 1,
  "jobDescription": "text",
  "jobId": {
    "id": 1,
    "uuid": "123e4567-e89b-12d3-a456-426614174000"
  },
  "coreMaxActiveConnections": 1,
  "linkId": [
    "text"
  ],
  "licenseKey": "text",
  "logFile": "text",
  "logLevel": "text",
  "hootOnly": true,
  "prettyPrint": true,
  "useTemplate": true,
  "parallel": true,
  "plan": true,
  "dataPreviewOff": true,
  "datasetSafeOff": true,
  "obslimit": 1,
  "pgUser": "text",
  "pgPassword": "text",
  "host": "text",
  "port": "text",
  "user": "text",
  "alertEmail": "text",
  "scheduleTime": "text",
  "schemaScore": 1,
  "optionAppend": "text",
  "keyDelimiter": "text",
  "agentId": {
    "id": 1,
    "uuid": "123e4567-e89b-12d3-a456-426614174000"
  },
  "load": {
    "readonly": true,
    "passwordManager": "text",
    "alias": "text",
    "query": "text",
    "queryHistory": "text",
    "key": "text",
    "expression": "text",
    "addDateColumn": true,
    "zeroFillNull": true,
    "replaceNulls": "text",
    "stringMode": true,
    "operator": "text",
    "dateColumn": "text",
    "transform": "text",
    "filter": "text",
    "filterNot": "text",
    "sample": 1,
    "backRun": 1,
    "backRunBin": "MINUTE",
    "unionLookBack": true,
    "unionLookBackMinRow": 1,
    "cache": true,
    "dateFormat": "text",
    "timeFormat": "text",
    "timestamp": true,
    "filePath": "text",
    "fileQuery": "text",
    "fullFile": true,
    "fileHeader": "text",
    "inferSchema": true,
    "fileType": "text",
    "delimiter": "text",
    "fileCharSet": "text",
    "skipLines": 1,
    "avroSchema": "text",
    "xmlRowTag": "text",
    "flatten": true,
    "handleMaps": true,
    "handleMixedJson": true,
    "multiLine": true,
    "lib": "text",
    "additionalLib": "text",
    "driverName": "text",
    "connectionName": "text",
    "connectionUrl": "text",
    "userName": "text",
    "password": "text",
    "connectionProperties": {
      "ANY_ADDITIONAL_PROPERTY": "text"
    },
    "hiveNative": true,
    "hiveNativeHWC": true,
    "useSql": true,
    "columnName": "text",
    "lowerBound": "text",
    "upperBound": "text",
    "numPartitions": 1,
    "partitionNumber": 1,
    "escapeWithBackTick": true,
    "escapeWithSingleQuote": true,
    "escapeWithDoubleQuote": true,
    "escapeCharacter": "text",
    "checkHeader": true,
    "archiveConnection": "text",
    "coreFetchMode": true,
    "archiveBreaks": true,
    "ruleSerial": true
  },
  "pushdown": {
    "dataset": "text",
    "connectionName": "text",
    "maxConnections": 1,
    "sourceQuery": "text",
    "backRuns": 1,
    "backRunBin": "text",
    "dateFormatType": "text",
    "threads": 1,
    "manualSourceQuery": true,
    "key": "text",
    "sourceOutputSchema": "text",
    "sourceBreakRules": true,
    "sourceBreakOutliers": true,
    "sourceBreakDupes": true,
    "sourceBreakShapes": true,
    "sourceBreakResults": true,
    "sqlLoggingToggle": true,
    "unionLookback": true,
    "unionLookbackMin": 1
  },
  "patterns": [
    {
      "id": 1,
      "dataset": "text",
      "only": true,
      "lookback": 1,
      "key": [
        "text"
      ],
      "dateColumn": "text",
      "include": [
        "text"
      ],
      "exclude": [
        "text"
      ],
      "score": 1,
      "minSupport": 1,
      "confidence": 1,
      "limit": 1,
      "query": "text",
      "filter": "text",
      "timeBin": "MINUTE"
    }
  ],
  "dupe": {
    "on": true,
    "only": true,
    "include": [
      "text"
    ],
    "exclude": [
      "text"
    ],
    "depth": 1,
    "lowerBound": 1,
    "upperBound": 1,
    "approximate": 1,
    "limitPerDupe": 1,
    "checkHeader": true,
    "filter": "text",
    "ignoreCase": true,
    "score": 1,
    "limit": 1
  },
  "profile": {
    "on": true,
    "only": true,
    "include": [
      "text"
    ],
    "exclude": [
      "text"
    ],
    "correlation": true,
    "histogram": true,
    "semantic": true,
    "dataConceptId": 1,
    "limit": 1,
    "histogramLimit": 1,
    "score": 1,
    "behavioralDimension": "text",
    "behavioralDimensionGroup": "text",
    "behavioralValueColumn": "text",
    "behaviorScoreOff": true,
    "behaviorLookback": 1,
    "behaviorMinSupport": 1,
    "profilePushDown": [
      "text"
    ],
    "behaviorRowCheck": true,
    "behaviorTimeCheck": true,
    "behaviorMinValueCheck": true,
    "behaviorMaxValueCheck": true,
    "behaviorMeanValueCheck": true,
    "behaviorNullCheck": true,
    "behaviorEmptyCheck": true,
    "behaviorUniqueCheck": true,
    "profileStringLength": true,
    "detectStringNumerics": true,
    "detectTopnBotn": true,
    "detectScalePrecision": true,
    "adaptiveTier": "text",
    "advancedTier": true,
    "filter": "text"
  },
  "source": {
    "on": true,
    "only": true,
    "validateValues": true,
    "key": [
      "text"
    ],
    "include": [
      "text"
    ],
    "exclude": [
      "text"
    ],
    "includeSrc": [
      "text"
    ],
    "excludeSrc": [
      "text"
    ],
    "map": {
      "ANY_ADDITIONAL_PROPERTY": "text"
    },
    "score": 1,
    "limit": 1,
    "sourcePushDownCount": true,
    "checkType": true,
    "checkCase": true,
    "validateSchemaOrder": true,
    "matches": true,
    "validateValuesThreshold": 1,
    "validateValuesThresholdStrictDownScore": true,
    "validateValuesShowAll": true,
    "validateValuesIgnoreNull": true,
    "validateValuesIgnoreEmpty": true,
    "validateValuesIgnorePrecision": true,
    "validateValuesTrim": true,
    "validateValuesShowMissingKeys": true,
    "validateSrcJoinOnly": true,
    "validateValuesFilter": "text",
    "dataset": "text",
    "driverName": "text",
    "user": "text",
    "password": "text",
    "passwordManager": "text",
    "connectionName": "text",
    "connectionUrl": "text",
    "query": "text",
    "lib": "text",
    "connectionProperties": {
      "ANY_ADDITIONAL_PROPERTY": "text"
    },
    "filePath": "text",
    "fileQuery": "text",
    "fullFile": true,
    "header": "text",
    "skipLines": 1,
    "inferSchema": true,
    "fileType": "text",
    "delimiter": "text",
    "fileCharSet": "text",
    "avroSchema": "text",
    "xmlRowTag": "text",
    "flatten": true,
    "handleMaps": true,
    "handleMixedJson": true,
    "multiLine": true,
    "filterCols": [
      "text"
    ]
  },
  "rule": {
    "on": true,
    "only": true,
    "lib": "text",
    "name": "text",
    "absoluteScoring": true,
    "ruleBreakPreviewLimit": 1
  },
  "colMatch": {
    "colMatchParallelProcesses": 1,
    "colMatchDurationMins": 1,
    "colMatchBatchSize": 1,
    "level": "text",
    "fuzzyDistance": 1,
    "connectionList": [
      {
        "dataset": "text",
        "url": "text",
        "user": "text",
        "password": "text",
        "query": "text",
        "filePath": "text",
        "driver": "text",
        "driverProps": {
          "ANY_ADDITIONAL_PROPERTY": "text"
        }
      }
    ]
  },
  "spark": {
    "numExecutors": 1,
    "driverMemory": "text",
    "executorMemory": "text",
    "executorCores": 1,
    "conf": "text",
    "queue": "text",
    "master": "text",
    "principal": "text",
    "keyTab": "text",
    "deployMode": "text",
    "jars": [
      "text"
    ],
    "packages": [
      "text"
    ],
    "files": [
      "text"
    ]
  },
  "env": {
    "dataset": "text",
    "jdbcPrincipal": "text",
    "jdbcKeyTab": "text"
  },
  "record": {
    "on": true,
    "in": "text",
    "notIn": "text",
    "include": [
      "text"
    ],
    "percDeltaLimit": 1,
    "score": 1,
    "dataset": "text",
    "dateColumn": "text",
    "keyColumn": "text",
    "timeBin": "MIN",
    "by": "MIN"
  },
  "stream": {
    "type": "Kafka",
    "kafkaDef": {
      "kafkaGroup": "text",
      "kafkaBroker": "text",
      "kafkaPort": "text",
      "kafkaTopic": "text",
      "kafkaKeySerde": "text",
      "kafkaValSerde": "text",
      "kafkaSaslEnabled": true,
      "kafkaSaslService": "text",
      "kafkaSslEnabled": true,
      "streamSchemaRegistryUrl": "text",
      "streamSchemaRegistryUser": "text",
      "streamSchemaRegistryPassword": "text",
      "streamInterval": "text",
      "streamSchema": "text",
      "streamFormat": "text",
      "streamMaxLull": "text"
    }
  },
  "pipeline": [
    "text"
  ],
  "metaTags": [
    "text"
  ],
  "outlierConfiguration": {
    "columnSensitivitySettings": [
      {
        "name": "text",
        "weight": 1,
        "unit": "DEFAULT"
      }
    ],
    "configurations": [
      {
        "id": 1,
        "key": [
          "text"
        ],
        "include": [
          "text"
        ],
        "exclude": [
          "text"
        ],
        "timeColumn": "text",
        "timeBinQuery": "text",
        "limit": 1,
        "minHistory": 1,
        "historyLimit": 1,
        "score": 1,
        "aggFunc": "text",
        "aggQuery": "text",
        "query": "text",
        "categoricalColumnConcatenation": true,
        "limitCategorical": 1,
        "measurementUnit": "text",
        "multiplierUpper": 1,
        "multiplierLower": 1,
        "record": true,
        "filter": "text",
        "combine": true,
        "categoricalConfidenceType": "text",
        "categoricalTopN": 1,
        "categoricalBottomN": 1,
        "categoricalMaxConfidence": 1,
        "categoricalMaxFrequencyPercentile": 1,
        "categoricalMinFrequency": 1,
        "categoricalMinVariance": 1,
        "categoricalMaxCategoryN": 1,
        "categoricalParallel": true,
        "categoricalAlgorithm": "text",
        "categoricalAlgorithmParameters": {
          "ANY_ADDITIONAL_PROPERTY": "text"
        }
      }
    ],
    "only": true,
    "lookback": 1,
    "dateColumn": "text",
    "timeBin": "MIN",
    "by": "MIN",
    "q1": 1,
    "q3": 1,
    "categorical": true
  },
  "shape": {
    "enabled": true,
    "totalScore": 1,
    "sensitivity": 1,
    "maxPerCol": 1,
    "maxColSize": 1,
    "granular": true,
    "columnSettings": [
      {
        "enabled": true,
        "name": "text",
        "type": "text"
      }
    ]
  },
  "jobSchedule": {
    "enabled": true,
    "dataset": "text",
    "agentId": {
      "id": 1,
      "uuid": "123e4567-e89b-12d3-a456-426614174000"
    },
    "runDateFormat": "text",
    "scheduleFrequency": "DAILY",
    "updatedAt": "2026-07-12T00:57:50.354Z",
    "scheduleTime": "text"
  },
  "connectionType": "PULLUP"
}

Delete dataset definitions by dataset name

delete

Hard deletes dataset definitions by given dataset names. This also deletes the associated DQ Jobs and referenced data.

Authorizations

bearer-jwt

AuthorizationstringRequired

Bearer authentication header of the form Bearer <token>.

Query parameters

datasetsstring[]Required

anyRequired

Set of dataset names to delete

Responses

200

Returns a map of dataset names and their deletion status

application/json

Other propertiesbooleanOptional

delete/v3/datasetDefs

HTTPcURLJavaScriptPython

DELETE /v3/datasetDefs?datasets=text HTTP/1.1
Host: <host-name>
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*

200

Returns a map of dataset names and their deletion status

{
  "ANY_ADDITIONAL_PROPERTY": true
}

Return a list of dataset definitions by a given filter

post

Returns a list of dataset definitions by given filter criteria. Pre-authorization requirements:

• hasRole('ROLE_ADMIN') or hasRole('ROLE_CONNECTION_MANAGER')

Authorizations

bearer-jwt

AuthorizationstringRequired

Bearer authentication header of the form Bearer <token>.

Body

application/json

limitinteger · int32Optional

offsetinteger · int32Optional

searchValuestringOptional

sensitivityLabelsstring[]Optional

sourcesstring[]Optional

dataClassesstring[]Optional

columnNamesstring[]Optional

businessUnitNamesstring[]Optional

dataCategoryNamesstring[]Optional

Responses

200

Returns a list of dataset definitions by given filter

application/json

Response containing the paged information.

totalinteger · int64Optional

The total number of results.

Example: 1000

offsetinteger · int64OptionalDeprecated

The offset for the results.

Example: 10

limitinteger · int64Optional

The maximum number of results to be returned.

Example: 100

post/v3/datasetDefs/find

HTTPcURLJavaScriptPython

POST /v3/datasetDefs/find HTTP/1.1
Host: <host-name>
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 404

{
  "limit": 1,
  "offset": 1,
  "searchValue": "text",
  "sensitivityLabels": [
    "text"
  ],
  "runModes": [
    "DRAFT"
  ],
  "sources": [
    "text"
  ],
  "dataClasses": [
    "text"
  ],
  "columnNames": [
    "text"
  ],
  "businessUnitNames": [
    "text"
  ],
  "dataCategoryNames": [
    "text"
  ],
  "rowCountOptions": [
    "RC_1K"
  ],
  "columnCountOptions": [
    "CC_0_10"
  ],
  "scanCountOptions": [
    "SC_0_10"
  ],
  "integrations": [
    "DATA_INTELLIGENCE_CLOUD"
  ],
  "connectionTypes": [
    "PULLUP"
  ],
  "attributes": [
    "ALERTS"
  ]
}

200

Returns a list of dataset definitions by given filter

{
  "total": 1000,
  "limit": 100,
  "results": [
    {
      "dataset": "text",
      "datasetAlias": "text",
      "source": "text",
      "databaseName": "text",
      "tableName": "text",
      "host": "text",
      "timeZone": "text",
      "runMode": "text",
      "dataConceptId": 1,
      "sourceName": "text",
      "connType": "text",
      "ruleCount": 1,
      "alertCount": 1,
      "businessUnitName": "text",
      "dgcIntegrationActive": true,
      "dgcAssetUrl": true,
      "tags": [
        "text"
      ],
      "updateTs": "text"
    }
  ]
}

Update the Spark information of one or more datasets

patch

Bulk updates the Spark information for multiple dataset definitions. It is secured and can only be accessed by users with the 'ROLE_ADMIN' role. Pre-authorization requirements:

• hasRole('ROLE_ADMIN')

Authorizations

bearer-jwt

AuthorizationstringRequired

Bearer authentication header of the form Bearer <token>.

Query parameters

datasetsstring[]Required

numExecutorsinteger · int32Optional

driverMemorystringOptional

executorMemorystringOptional

executorCoresinteger · int32Optional

confstringOptional

masterstringOptional

deployModestringOptional

anyOptional

The deploy mode for the spark job

Responses

200

Returns the number of datasets for which the spark information was updated

application/json

integer · int32Optional

404

Some dataset not found

application/json

422

Updating agent for pushdown datasets is not allowed

patch/v3/datasetDefs/batch/spark

HTTPcURLJavaScriptPython

PATCH /v3/datasetDefs/batch/spark?datasets=text HTTP/1.1
Host: <host-name>
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*

1

Update the host information of one or more datasets

patch

Bulk updates the host information in the dataset definitions of one or more given datasets. Pre-authorization requirements:

• hasRole('ROLE_ADMIN')

Authorizations

bearer-jwt

AuthorizationstringRequired

Bearer authentication header of the form Bearer <token>.

Query parameters

datasetsstring[]Required

hoststringRequired

anyRequired

The host information to be updated

Responses

200

Returns the number of datasets for which the host information was updated

application/json

integer · int32Optional

patch/v3/datasetDefs/batch/host

HTTPcURLJavaScriptPython

PATCH /v3/datasetDefs/batch/host?datasets=text&host=text HTTP/1.1
Host: <host-name>
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*

200

Returns the number of datasets for which the host information was updated

1

Update the agent information of one or more datasets

patch

Updates the agent information for multiple dataset definitions in bulk. It is secured and can only be accessed by users with the 'ROLE_ADMIN' role. At least one of agentName, agentId or agentUuid must be provided. If agentId or agentUuid is provided, the method will update the agent information using the Identifier formed from agentId and agentUuid. If agentName is provided and agentId and agentUuid are not provided, the method will update the agent information using the agentName. Returns the number of datasets for which the agent information was updated. Pre-authorization requirements:

• hasRole('ROLE_ADMIN')

Authorizations

bearer-jwt

AuthorizationstringRequired

Bearer authentication header of the form Bearer <token>.

Query parameters

datasetsstring[]Required

agentNamestringOptional

agentIdinteger · int64Optional

agentUuidstring · uuidOptional

anyOptional

The UUID of the agent.

Responses

200

Returns the number of datasets for which the agent information was updated

application/json

integer · int32Optional

404

Some dataset not found

application/json

422

Updating agent for pushdown datasets is not allowed

patch/v3/datasetDefs/batch/agent

HTTPcURLJavaScriptPython

PATCH /v3/datasetDefs/batch/agent?datasets=text HTTP/1.1
Host: <host-name>
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*

1

Retrieve the dataset definition of a given dataset

get

Retrieves the dataset definition of a given dataset. Pre-authorization requirements:

• hasRole('ROLE_ADMIN') or hasRole('ROLE_DATASET_MANAGER') or hasDatasetAccess(#dataset)

Authorizations

bearer-jwt

AuthorizationstringRequired

Bearer authentication header of the form Bearer <token>.

Path parameters

datasetstringRequired

Dataset name

Responses

200

Returns a single dataset definition

application/json

datasetstringOptional

runIdstringOptional

runIdEndstringOptional

runStatestring · enumOptionalPossible values:

passFailinteger · int32Optional

passFailLimitinteger · int32Optional

jobDescriptionstringOptional

coreMaxActiveConnectionsinteger · int32Optional

linkIdstring[]Optional

licenseKeystringOptional

logFilestringOptional

logLevelstringOptional

hootOnlybooleanOptional

prettyPrintbooleanOptional

useTemplatebooleanOptional

parallelbooleanOptional

planbooleanOptional

dataPreviewOffbooleanOptional

datasetSafeOffbooleanOptional

obslimitinteger · int32Optional

pgUserstringOptional

pgPasswordstringOptional

hoststringOptional

portstringOptional

userstringOptional

alertEmailstringOptional

scheduleTimestringOptional

schemaScorenumber · doubleOptional

optionAppendstringOptional

keyDelimiterstringOptional

pipelinestring[]Optional

runDatestring · date-timeWrite-onlyOptional

runDateEndstring · date-timeWrite-onlyOptional

metaTagsstring[]Optional

connectionTypestring · enumRead-onlyOptionalPossible values:

404

Dataset not found

application/json

get/v3/datasetDefs/{dataset}

HTTPcURLJavaScriptPython

GET /v3/datasetDefs/{dataset} HTTP/1.1
Host: <host-name>
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*

{
  "dataset": "text",
  "runId": "text",
  "runIdEnd": "text",
  "runState": "DRAFT",
  "passFail": 1,
  "passFailLimit": 1,
  "jobDescription": "text",
  "jobId": {
    "id": 1,
    "uuid": "123e4567-e89b-12d3-a456-426614174000"
  },
  "coreMaxActiveConnections": 1,
  "linkId": [
    "text"
  ],
  "licenseKey": "text",
  "logFile": "text",
  "logLevel": "text",
  "hootOnly": true,
  "prettyPrint": true,
  "useTemplate": true,
  "parallel": true,
  "plan": true,
  "dataPreviewOff": true,
  "datasetSafeOff": true,
  "obslimit": 1,
  "pgUser": "text",
  "pgPassword": "text",
  "host": "text",
  "port": "text",
  "user": "text",
  "alertEmail": "text",
  "scheduleTime": "text",
  "schemaScore": 1,
  "optionAppend": "text",
  "keyDelimiter": "text",
  "agentId": {
    "id": 1,
    "uuid": "123e4567-e89b-12d3-a456-426614174000"
  },
  "load": {
    "readonly": true,
    "passwordManager": "text",
    "alias": "text",
    "query": "text",
    "queryHistory": "text",
    "key": "text",
    "expression": "text",
    "addDateColumn": true,
    "zeroFillNull": true,
    "replaceNulls": "text",
    "stringMode": true,
    "operator": "text",
    "dateColumn": "text",
    "transform": "text",
    "filter": "text",
    "filterNot": "text",
    "sample": 1,
    "backRun": 1,
    "backRunBin": "MINUTE",
    "unionLookBack": true,
    "unionLookBackMinRow": 1,
    "cache": true,
    "dateFormat": "text",
    "timeFormat": "text",
    "timestamp": true,
    "filePath": "text",
    "fileQuery": "text",
    "fullFile": true,
    "fileHeader": "text",
    "inferSchema": true,
    "fileType": "text",
    "delimiter": "text",
    "fileCharSet": "text",
    "skipLines": 1,
    "avroSchema": "text",
    "xmlRowTag": "text",
    "flatten": true,
    "handleMaps": true,
    "handleMixedJson": true,
    "multiLine": true,
    "lib": "text",
    "additionalLib": "text",
    "driverName": "text",
    "connectionName": "text",
    "connectionUrl": "text",
    "userName": "text",
    "password": "text",
    "connectionProperties": {
      "ANY_ADDITIONAL_PROPERTY": "text"
    },
    "hiveNative": true,
    "hiveNativeHWC": true,
    "useSql": true,
    "columnName": "text",
    "lowerBound": "text",
    "upperBound": "text",
    "numPartitions": 1,
    "partitionNumber": 1,
    "escapeWithBackTick": true,
    "escapeWithSingleQuote": true,
    "escapeWithDoubleQuote": true,
    "escapeCharacter": "text",
    "checkHeader": true,
    "archiveConnection": "text",
    "coreFetchMode": true,
    "archiveBreaks": true,
    "ruleSerial": true
  },
  "pushdown": {
    "dataset": "text",
    "connectionName": "text",
    "maxConnections": 1,
    "sourceQuery": "text",
    "backRuns": 1,
    "backRunBin": "text",
    "dateFormatType": "text",
    "threads": 1,
    "manualSourceQuery": true,
    "key": "text",
    "sourceOutputSchema": "text",
    "sourceBreakRules": true,
    "sourceBreakOutliers": true,
    "sourceBreakDupes": true,
    "sourceBreakShapes": true,
    "sourceBreakResults": true,
    "sqlLoggingToggle": true,
    "unionLookback": true,
    "unionLookbackMin": 1
  },
  "patterns": [
    {
      "id": 1,
      "dataset": "text",
      "only": true,
      "lookback": 1,
      "key": [
        "text"
      ],
      "dateColumn": "text",
      "include": [
        "text"
      ],
      "exclude": [
        "text"
      ],
      "score": 1,
      "minSupport": 1,
      "confidence": 1,
      "limit": 1,
      "query": "text",
      "filter": "text",
      "timeBin": "MINUTE"
    }
  ],
  "dupe": {
    "on": true,
    "only": true,
    "include": [
      "text"
    ],
    "exclude": [
      "text"
    ],
    "depth": 1,
    "lowerBound": 1,
    "upperBound": 1,
    "approximate": 1,
    "limitPerDupe": 1,
    "checkHeader": true,
    "filter": "text",
    "ignoreCase": true,
    "score": 1,
    "limit": 1
  },
  "profile": {
    "on": true,
    "only": true,
    "include": [
      "text"
    ],
    "exclude": [
      "text"
    ],
    "correlation": true,
    "histogram": true,
    "semantic": true,
    "dataConceptId": 1,
    "limit": 1,
    "histogramLimit": 1,
    "score": 1,
    "behavioralDimension": "text",
    "behavioralDimensionGroup": "text",
    "behavioralValueColumn": "text",
    "behaviorScoreOff": true,
    "behaviorLookback": 1,
    "behaviorMinSupport": 1,
    "profilePushDown": [
      "text"
    ],
    "behaviorRowCheck": true,
    "behaviorTimeCheck": true,
    "behaviorMinValueCheck": true,
    "behaviorMaxValueCheck": true,
    "behaviorMeanValueCheck": true,
    "behaviorNullCheck": true,
    "behaviorEmptyCheck": true,
    "behaviorUniqueCheck": true,
    "profileStringLength": true,
    "detectStringNumerics": true,
    "detectTopnBotn": true,
    "detectScalePrecision": true,
    "adaptiveTier": "text",
    "advancedTier": true,
    "filter": "text"
  },
  "source": {
    "on": true,
    "only": true,
    "validateValues": true,
    "key": [
      "text"
    ],
    "include": [
      "text"
    ],
    "exclude": [
      "text"
    ],
    "includeSrc": [
      "text"
    ],
    "excludeSrc": [
      "text"
    ],
    "map": {
      "ANY_ADDITIONAL_PROPERTY": "text"
    },
    "score": 1,
    "limit": 1,
    "sourcePushDownCount": true,
    "checkType": true,
    "checkCase": true,
    "validateSchemaOrder": true,
    "matches": true,
    "validateValuesThreshold": 1,
    "validateValuesThresholdStrictDownScore": true,
    "validateValuesShowAll": true,
    "validateValuesIgnoreNull": true,
    "validateValuesIgnoreEmpty": true,
    "validateValuesIgnorePrecision": true,
    "validateValuesTrim": true,
    "validateValuesShowMissingKeys": true,
    "validateSrcJoinOnly": true,
    "validateValuesFilter": "text",
    "dataset": "text",
    "driverName": "text",
    "user": "text",
    "password": "text",
    "passwordManager": "text",
    "connectionName": "text",
    "connectionUrl": "text",
    "query": "text",
    "lib": "text",
    "connectionProperties": {
      "ANY_ADDITIONAL_PROPERTY": "text"
    },
    "filePath": "text",
    "fileQuery": "text",
    "fullFile": true,
    "header": "text",
    "skipLines": 1,
    "inferSchema": true,
    "fileType": "text",
    "delimiter": "text",
    "fileCharSet": "text",
    "avroSchema": "text",
    "xmlRowTag": "text",
    "flatten": true,
    "handleMaps": true,
    "handleMixedJson": true,
    "multiLine": true,
    "filterCols": [
      "text"
    ]
  },
  "rule": {
    "on": true,
    "only": true,
    "lib": "text",
    "name": "text",
    "absoluteScoring": true,
    "ruleBreakPreviewLimit": 1
  },
  "colMatch": {
    "colMatchParallelProcesses": 1,
    "colMatchDurationMins": 1,
    "colMatchBatchSize": 1,
    "level": "text",
    "fuzzyDistance": 1,
    "connectionList": [
      {
        "dataset": "text",
        "url": "text",
        "user": "text",
        "password": "text",
        "query": "text",
        "filePath": "text",
        "driver": "text",
        "driverProps": {
          "ANY_ADDITIONAL_PROPERTY": "text"
        }
      }
    ]
  },
  "spark": {
    "numExecutors": 1,
    "driverMemory": "text",
    "executorMemory": "text",
    "executorCores": 1,
    "conf": "text",
    "queue": "text",
    "master": "text",
    "principal": "text",
    "keyTab": "text",
    "deployMode": "text",
    "jars": [
      "text"
    ],
    "packages": [
      "text"
    ],
    "files": [
      "text"
    ]
  },
  "env": {
    "dataset": "text",
    "jdbcPrincipal": "text",
    "jdbcKeyTab": "text"
  },
  "record": {
    "on": true,
    "in": "text",
    "notIn": "text",
    "include": [
      "text"
    ],
    "percDeltaLimit": 1,
    "score": 1,
    "dataset": "text",
    "dateColumn": "text",
    "keyColumn": "text",
    "timeBin": "MIN",
    "by": "MIN"
  },
  "stream": {
    "type": "Kafka",
    "kafkaDef": {
      "kafkaGroup": "text",
      "kafkaBroker": "text",
      "kafkaPort": "text",
      "kafkaTopic": "text",
      "kafkaKeySerde": "text",
      "kafkaValSerde": "text",
      "kafkaSaslEnabled": true,
      "kafkaSaslService": "text",
      "kafkaSslEnabled": true,
      "streamSchemaRegistryUrl": "text",
      "streamSchemaRegistryUser": "text",
      "streamSchemaRegistryPassword": "text",
      "streamInterval": "text",
      "streamSchema": "text",
      "streamFormat": "text",
      "streamMaxLull": "text"
    }
  },
  "pipeline": [
    "text"
  ],
  "metaTags": [
    "text"
  ],
  "outlierConfiguration": {
    "columnSensitivitySettings": [
      {
        "name": "text",
        "weight": 1,
        "unit": "DEFAULT"
      }
    ],
    "configurations": [
      {
        "id": 1,
        "key": [
          "text"
        ],
        "include": [
          "text"
        ],
        "exclude": [
          "text"
        ],
        "timeColumn": "text",
        "timeBinQuery": "text",
        "limit": 1,
        "minHistory": 1,
        "historyLimit": 1,
        "score": 1,
        "aggFunc": "text",
        "aggQuery": "text",
        "query": "text",
        "categoricalColumnConcatenation": true,
        "limitCategorical": 1,
        "measurementUnit": "text",
        "multiplierUpper": 1,
        "multiplierLower": 1,
        "record": true,
        "filter": "text",
        "combine": true,
        "categoricalConfidenceType": "text",
        "categoricalTopN": 1,
        "categoricalBottomN": 1,
        "categoricalMaxConfidence": 1,
        "categoricalMaxFrequencyPercentile": 1,
        "categoricalMinFrequency": 1,
        "categoricalMinVariance": 1,
        "categoricalMaxCategoryN": 1,
        "categoricalParallel": true,
        "categoricalAlgorithm": "text",
        "categoricalAlgorithmParameters": {
          "ANY_ADDITIONAL_PROPERTY": "text"
        }
      }
    ],
    "only": true,
    "lookback": 1,
    "dateColumn": "text",
    "timeBin": "MIN",
    "by": "MIN",
    "q1": 1,
    "q3": 1,
    "categorical": true
  },
  "shape": {
    "enabled": true,
    "totalScore": 1,
    "sensitivity": 1,
    "maxPerCol": 1,
    "maxColSize": 1,
    "granular": true,
    "columnSettings": [
      {
        "enabled": true,
        "name": "text",
        "type": "text"
      }
    ]
  },
  "jobSchedule": {
    "enabled": true,
    "dataset": "text",
    "agentId": {
      "id": 1,
      "uuid": "123e4567-e89b-12d3-a456-426614174000"
    },
    "runDateFormat": "text",
    "scheduleFrequency": "DAILY",
    "updatedAt": "2026-07-12T00:57:50.354Z",
    "scheduleTime": "text"
  },
  "connectionType": "PULLUP"
}

Retrieve the dataset definition of a given dataset as a command line string

get

Retrieves the dataset definition of a given dataset as a command line string. Pre-authorization requirements:

• hasRole('ROLE_ADMIN') or hasRole('ROLE_DATASET_MANAGER') or hasDatasetAccess(#dataset)

Authorizations

bearer-jwt

AuthorizationstringRequired

Bearer authentication header of the form Bearer <token>.

Path parameters

datasetstringRequired

Dataset name

Responses

200

Returns a single dataset definition as a cmdline string

application/json

cmdLinestringRequired

404

Dataset not found

application/json

422

Command line not supported for Pushdown jobs

get/v3/datasetDefs/{dataset}/cmdLine

HTTPcURLJavaScriptPython

GET /v3/datasetDefs/{dataset}/cmdLine HTTP/1.1
Host: <host-name>
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*

{
  "cmdLine": "text"
}

Retrieve a template of a new dataset definition

get

Retrieves a template of a new dataset definition with sample or default values only.

Authorizations

bearer-jwt

AuthorizationstringRequired

Bearer authentication header of the form Bearer <token>.

Responses

200

Returns a template of a new dataset definition with sample/default values only

application/json

datasetstringOptional

runIdstringOptional

runIdEndstringOptional

runStatestring · enumOptionalPossible values:

passFailinteger · int32Optional

passFailLimitinteger · int32Optional

jobDescriptionstringOptional

coreMaxActiveConnectionsinteger · int32Optional

linkIdstring[]Optional

licenseKeystringOptional

logFilestringOptional

logLevelstringOptional

hootOnlybooleanOptional

prettyPrintbooleanOptional

useTemplatebooleanOptional

parallelbooleanOptional

planbooleanOptional

dataPreviewOffbooleanOptional

datasetSafeOffbooleanOptional

obslimitinteger · int32Optional

pgUserstringOptional

pgPasswordstringOptional

hoststringOptional

portstringOptional

userstringOptional

alertEmailstringOptional

scheduleTimestringOptional

schemaScorenumber · doubleOptional

optionAppendstringOptional

keyDelimiterstringOptional

pipelinestring[]Optional

runDatestring · date-timeWrite-onlyOptional

runDateEndstring · date-timeWrite-onlyOptional

metaTagsstring[]Optional

connectionTypestring · enumRead-onlyOptionalPossible values:

get/v3/datasetDefs/template

HTTPcURLJavaScriptPython

GET /v3/datasetDefs/template HTTP/1.1
Host: <host-name>
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*

200

Returns a template of a new dataset definition with sample/default values only

{
  "dataset": "text",
  "runId": "text",
  "runIdEnd": "text",
  "runState": "DRAFT",
  "passFail": 1,
  "passFailLimit": 1,
  "jobDescription": "text",
  "jobId": {
    "id": 1,
    "uuid": "123e4567-e89b-12d3-a456-426614174000"
  },
  "coreMaxActiveConnections": 1,
  "linkId": [
    "text"
  ],
  "licenseKey": "text",
  "logFile": "text",
  "logLevel": "text",
  "hootOnly": true,
  "prettyPrint": true,
  "useTemplate": true,
  "parallel": true,
  "plan": true,
  "dataPreviewOff": true,
  "datasetSafeOff": true,
  "obslimit": 1,
  "pgUser": "text",
  "pgPassword": "text",
  "host": "text",
  "port": "text",
  "user": "text",
  "alertEmail": "text",
  "scheduleTime": "text",
  "schemaScore": 1,
  "optionAppend": "text",
  "keyDelimiter": "text",
  "agentId": {
    "id": 1,
    "uuid": "123e4567-e89b-12d3-a456-426614174000"
  },
  "load": {
    "readonly": true,
    "passwordManager": "text",
    "alias": "text",
    "query": "text",
    "queryHistory": "text",
    "key": "text",
    "expression": "text",
    "addDateColumn": true,
    "zeroFillNull": true,
    "replaceNulls": "text",
    "stringMode": true,
    "operator": "text",
    "dateColumn": "text",
    "transform": "text",
    "filter": "text",
    "filterNot": "text",
    "sample": 1,
    "backRun": 1,
    "backRunBin": "MINUTE",
    "unionLookBack": true,
    "unionLookBackMinRow": 1,
    "cache": true,
    "dateFormat": "text",
    "timeFormat": "text",
    "timestamp": true,
    "filePath": "text",
    "fileQuery": "text",
    "fullFile": true,
    "fileHeader": "text",
    "inferSchema": true,
    "fileType": "text",
    "delimiter": "text",
    "fileCharSet": "text",
    "skipLines": 1,
    "avroSchema": "text",
    "xmlRowTag": "text",
    "flatten": true,
    "handleMaps": true,
    "handleMixedJson": true,
    "multiLine": true,
    "lib": "text",
    "additionalLib": "text",
    "driverName": "text",
    "connectionName": "text",
    "connectionUrl": "text",
    "userName": "text",
    "password": "text",
    "connectionProperties": {
      "ANY_ADDITIONAL_PROPERTY": "text"
    },
    "hiveNative": true,
    "hiveNativeHWC": true,
    "useSql": true,
    "columnName": "text",
    "lowerBound": "text",
    "upperBound": "text",
    "numPartitions": 1,
    "partitionNumber": 1,
    "escapeWithBackTick": true,
    "escapeWithSingleQuote": true,
    "escapeWithDoubleQuote": true,
    "escapeCharacter": "text",
    "checkHeader": true,
    "archiveConnection": "text",
    "coreFetchMode": true,
    "archiveBreaks": true,
    "ruleSerial": true
  },
  "pushdown": {
    "dataset": "text",
    "connectionName": "text",
    "maxConnections": 1,
    "sourceQuery": "text",
    "backRuns": 1,
    "backRunBin": "text",
    "dateFormatType": "text",
    "threads": 1,
    "manualSourceQuery": true,
    "key": "text",
    "sourceOutputSchema": "text",
    "sourceBreakRules": true,
    "sourceBreakOutliers": true,
    "sourceBreakDupes": true,
    "sourceBreakShapes": true,
    "sourceBreakResults": true,
    "sqlLoggingToggle": true,
    "unionLookback": true,
    "unionLookbackMin": 1
  },
  "patterns": [
    {
      "id": 1,
      "dataset": "text",
      "only": true,
      "lookback": 1,
      "key": [
        "text"
      ],
      "dateColumn": "text",
      "include": [
        "text"
      ],
      "exclude": [
        "text"
      ],
      "score": 1,
      "minSupport": 1,
      "confidence": 1,
      "limit": 1,
      "query": "text",
      "filter": "text",
      "timeBin": "MINUTE"
    }
  ],
  "dupe": {
    "on": true,
    "only": true,
    "include": [
      "text"
    ],
    "exclude": [
      "text"
    ],
    "depth": 1,
    "lowerBound": 1,
    "upperBound": 1,
    "approximate": 1,
    "limitPerDupe": 1,
    "checkHeader": true,
    "filter": "text",
    "ignoreCase": true,
    "score": 1,
    "limit": 1
  },
  "profile": {
    "on": true,
    "only": true,
    "include": [
      "text"
    ],
    "exclude": [
      "text"
    ],
    "correlation": true,
    "histogram": true,
    "semantic": true,
    "dataConceptId": 1,
    "limit": 1,
    "histogramLimit": 1,
    "score": 1,
    "behavioralDimension": "text",
    "behavioralDimensionGroup": "text",
    "behavioralValueColumn": "text",
    "behaviorScoreOff": true,
    "behaviorLookback": 1,
    "behaviorMinSupport": 1,
    "profilePushDown": [
      "text"
    ],
    "behaviorRowCheck": true,
    "behaviorTimeCheck": true,
    "behaviorMinValueCheck": true,
    "behaviorMaxValueCheck": true,
    "behaviorMeanValueCheck": true,
    "behaviorNullCheck": true,
    "behaviorEmptyCheck": true,
    "behaviorUniqueCheck": true,
    "profileStringLength": true,
    "detectStringNumerics": true,
    "detectTopnBotn": true,
    "detectScalePrecision": true,
    "adaptiveTier": "text",
    "advancedTier": true,
    "filter": "text"
  },
  "source": {
    "on": true,
    "only": true,
    "validateValues": true,
    "key": [
      "text"
    ],
    "include": [
      "text"
    ],
    "exclude": [
      "text"
    ],
    "includeSrc": [
      "text"
    ],
    "excludeSrc": [
      "text"
    ],
    "map": {
      "ANY_ADDITIONAL_PROPERTY": "text"
    },
    "score": 1,
    "limit": 1,
    "sourcePushDownCount": true,
    "checkType": true,
    "checkCase": true,
    "validateSchemaOrder": true,
    "matches": true,
    "validateValuesThreshold": 1,
    "validateValuesThresholdStrictDownScore": true,
    "validateValuesShowAll": true,
    "validateValuesIgnoreNull": true,
    "validateValuesIgnoreEmpty": true,
    "validateValuesIgnorePrecision": true,
    "validateValuesTrim": true,
    "validateValuesShowMissingKeys": true,
    "validateSrcJoinOnly": true,
    "validateValuesFilter": "text",
    "dataset": "text",
    "driverName": "text",
    "user": "text",
    "password": "text",
    "passwordManager": "text",
    "connectionName": "text",
    "connectionUrl": "text",
    "query": "text",
    "lib": "text",
    "connectionProperties": {
      "ANY_ADDITIONAL_PROPERTY": "text"
    },
    "filePath": "text",
    "fileQuery": "text",
    "fullFile": true,
    "header": "text",
    "skipLines": 1,
    "inferSchema": true,
    "fileType": "text",
    "delimiter": "text",
    "fileCharSet": "text",
    "avroSchema": "text",
    "xmlRowTag": "text",
    "flatten": true,
    "handleMaps": true,
    "handleMixedJson": true,
    "multiLine": true,
    "filterCols": [
      "text"
    ]
  },
  "rule": {
    "on": true,
    "only": true,
    "lib": "text",
    "name": "text",
    "absoluteScoring": true,
    "ruleBreakPreviewLimit": 1
  },
  "colMatch": {
    "colMatchParallelProcesses": 1,
    "colMatchDurationMins": 1,
    "colMatchBatchSize": 1,
    "level": "text",
    "fuzzyDistance": 1,
    "connectionList": [
      {
        "dataset": "text",
        "url": "text",
        "user": "text",
        "password": "text",
        "query": "text",
        "filePath": "text",
        "driver": "text",
        "driverProps": {
          "ANY_ADDITIONAL_PROPERTY": "text"
        }
      }
    ]
  },
  "spark": {
    "numExecutors": 1,
    "driverMemory": "text",
    "executorMemory": "text",
    "executorCores": 1,
    "conf": "text",
    "queue": "text",
    "master": "text",
    "principal": "text",
    "keyTab": "text",
    "deployMode": "text",
    "jars": [
      "text"
    ],
    "packages": [
      "text"
    ],
    "files": [
      "text"
    ]
  },
  "env": {
    "dataset": "text",
    "jdbcPrincipal": "text",
    "jdbcKeyTab": "text"
  },
  "record": {
    "on": true,
    "in": "text",
    "notIn": "text",
    "include": [
      "text"
    ],
    "percDeltaLimit": 1,
    "score": 1,
    "dataset": "text",
    "dateColumn": "text",
    "keyColumn": "text",
    "timeBin": "MIN",
    "by": "MIN"
  },
  "stream": {
    "type": "Kafka",
    "kafkaDef": {
      "kafkaGroup": "text",
      "kafkaBroker": "text",
      "kafkaPort": "text",
      "kafkaTopic": "text",
      "kafkaKeySerde": "text",
      "kafkaValSerde": "text",
      "kafkaSaslEnabled": true,
      "kafkaSaslService": "text",
      "kafkaSslEnabled": true,
      "streamSchemaRegistryUrl": "text",
      "streamSchemaRegistryUser": "text",
      "streamSchemaRegistryPassword": "text",
      "streamInterval": "text",
      "streamSchema": "text",
      "streamFormat": "text",
      "streamMaxLull": "text"
    }
  },
  "pipeline": [
    "text"
  ],
  "metaTags": [
    "text"
  ],
  "outlierConfiguration": {
    "columnSensitivitySettings": [
      {
        "name": "text",
        "weight": 1,
        "unit": "DEFAULT"
      }
    ],
    "configurations": [
      {
        "id": 1,
        "key": [
          "text"
        ],
        "include": [
          "text"
        ],
        "exclude": [
          "text"
        ],
        "timeColumn": "text",
        "timeBinQuery": "text",
        "limit": 1,
        "minHistory": 1,
        "historyLimit": 1,
        "score": 1,
        "aggFunc": "text",
        "aggQuery": "text",
        "query": "text",
        "categoricalColumnConcatenation": true,
        "limitCategorical": 1,
        "measurementUnit": "text",
        "multiplierUpper": 1,
        "multiplierLower": 1,
        "record": true,
        "filter": "text",
        "combine": true,
        "categoricalConfidenceType": "text",
        "categoricalTopN": 1,
        "categoricalBottomN": 1,
        "categoricalMaxConfidence": 1,
        "categoricalMaxFrequencyPercentile": 1,
        "categoricalMinFrequency": 1,
        "categoricalMinVariance": 1,
        "categoricalMaxCategoryN": 1,
        "categoricalParallel": true,
        "categoricalAlgorithm": "text",
        "categoricalAlgorithmParameters": {
          "ANY_ADDITIONAL_PROPERTY": "text"
        }
      }
    ],
    "only": true,
    "lookback": 1,
    "dateColumn": "text",
    "timeBin": "MIN",
    "by": "MIN",
    "q1": 1,
    "q3": 1,
    "categorical": true
  },
  "shape": {
    "enabled": true,
    "totalScore": 1,
    "sensitivity": 1,
    "maxPerCol": 1,
    "maxColSize": 1,
    "granular": true,
    "columnSettings": [
      {
        "enabled": true,
        "name": "text",
        "type": "text"
      }
    ]
  },
  "jobSchedule": {
    "enabled": true,
    "dataset": "text",
    "agentId": {
      "id": 1,
      "uuid": "123e4567-e89b-12d3-a456-426614174000"
    },
    "runDateFormat": "text",
    "scheduleFrequency": "DAILY",
    "updatedAt": "2026-07-12T00:57:50.354Z",
    "scheduleTime": "text"
  },
  "connectionType": "PULLUP"
}