{ "openapi": "3.0.1", "info": { "title": "Dataset Quality Gate - Schema & Data QA", "description": "Validate Apify Datasets by pasted items, Dataset ID, or Run ID before delivery, automation, or AI/RAG ingestion. Catch schema drift, missing fields, duplicates, and bad URLs/emails/dates.", "version": "0.3", "x-build-id": "N0rzlJlvaH6hLn55t" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/jy-labs~dataset-quality-gate/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-jy-labs-dataset-quality-gate", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/jy-labs~dataset-quality-gate/runs": { "post": { "operationId": "runs-sync-jy-labs-dataset-quality-gate", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/jy-labs~dataset-quality-gate/run-sync": { "post": { "operationId": "run-sync-jy-labs-dataset-quality-gate", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "reportName": { "title": "Report name", "type": "string", "description": "Name shown in the generated QA report. Use a customer, Actor, dataset, or pipeline name." }, "datasetId": { "title": "Apify Dataset ID to validate", "type": "string", "description": "Optional. Paste an Apify Dataset ID to fetch and validate its items automatically. Leave empty when using Run ID or pasted items." }, "runId": { "title": "Apify Run ID to validate", "type": "string", "description": "Optional. Paste an Actor run ID and this Actor will validate that run's default dataset. Leave empty when using Dataset ID or pasted items." }, "maxItems": { "title": "Maximum items to check", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Safety cap for fetched dataset/run items. Default is 1000, maximum is 50000. Use with validateAllItems for full-dataset pagination up to this cap.", "default": 1000 }, "validateAllItems": { "title": "Paginate through the dataset", "type": "boolean", "description": "When true, fetch multiple pages until the dataset is exhausted or maxItems is reached. When false, only one sample page is checked.", "default": false }, "itemOffset": { "title": "Item offset", "minimum": 0, "type": "integer", "description": "Number of dataset items to skip before validation. Use this to inspect a later sample page.", "default": 0 }, "itemOrder": { "title": "Item order", "enum": [ "first", "last" ], "type": "string", "description": "Validate the first stored items or the latest stored items first.", "default": "first" }, "failRunOnError": { "title": "Fail the run when the gate fails", "type": "boolean", "description": "Turn this on for CI/CD, webhooks, or scheduled automations where bad data must stop the next step. Leave off for audit/report-only mode.", "default": false }, "items": { "title": "Dataset items to validate manually", "type": "array", "description": "Optional fallback for pasted/exported JSON items. If datasetId or runId is provided, this manual sample is ignored.", "items": { "type": "object", "additionalProperties": true } }, "requiredFields": { "title": "Fields that must be present", "type": "array", "description": "Field names that must exist and be non-empty in every item, such as id, url, title, price, or email.", "items": { "type": "string" } }, "expectedSchema": { "title": "Expected field types", "type": "object", "description": "Map field names to expected top-level JSON types. Supported values: string, number, boolean, object, array, null.", "additionalProperties": true }, "uniqueFields": { "title": "Fields that must be unique", "type": "array", "description": "Field names where duplicate non-empty values should fail the quality gate, such as id, url, sku, email, or profileUrl.", "items": { "type": "string" } }, "formatRules": { "title": "URL, email, and date checks", "type": "object", "description": "Map field names to format checks. Supported values: url, email, date.", "additionalProperties": true } } }, "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 } } } } } } } } } }