{ "openapi": "3.0.1", "info": { "title": "Apify Dataset QA Gate", "description": "Pass, warn, or stop Apify datasets before CRM import, enrichment, client delivery, or webhook automation.", "version": "0.1", "x-build-id": "nPTTQ6nofRFIqaVTc" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/leadops_lab~dataset-quality-auditor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-leadops_lab-dataset-quality-auditor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/leadops_lab~dataset-quality-auditor/runs": { "post": { "operationId": "runs-sync-leadops_lab-dataset-quality-auditor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/leadops_lab~dataset-quality-auditor/run-sync": { "post": { "operationId": "run-sync-leadops_lab-dataset-quality-auditor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "records": { "title": "Inline records", "type": "array", "description": "Paste raw dataset records as JSON objects. Use this or sourceDatasetId." }, "sourceDatasetId": { "title": "Source Apify dataset", "type": "string", "description": "Optional Apify Dataset ID to audit instead of inline records." }, "requiredFields": { "title": "Required CRM fields", "type": "array", "description": "Fields that must be present for a row to count as CRM-ready.", "default": [ "companyName", "domain", "email", "phone", "location" ], "items": { "type": "string" } }, "passThresholds": { "title": "Pass thresholds", "type": "object", "description": "Quality thresholds used to return PASS, WARN, or FAIL for downstream automations.", "properties": { "minCrmReadyPercent": { "title": "Minimum CRM-ready %", "type": "integer", "description": "Minimum percentage of rows that must contain all required fields for the dataset to pass.", "minimum": 0, "maximum": 100, "default": 80 }, "maxDuplicatePercent": { "title": "Maximum duplicate %", "type": "integer", "description": "Maximum allowed percentage of duplicate rows before the dataset warns or fails.", "minimum": 0, "maximum": 100, "default": 10 }, "minRequiredFieldCoveragePercent": { "title": "Minimum required field coverage %", "type": "integer", "description": "Minimum coverage percentage required for each selected required field.", "minimum": 0, "maximum": 100, "default": 70 } }, "default": { "minCrmReadyPercent": 80, "maxDuplicatePercent": 10, "minRequiredFieldCoveragePercent": 70 } }, "maxRecords": { "title": "Maximum records", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Maximum records to read and audit.", "default": 10000 }, "sampleSize": { "title": "Issue sample size", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum number of rows with missing required fields to include in sampleIssues.", "default": 25 } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }