{ "openapi": "3.0.1", "info": { "title": "Dataset Cleaner & Deduplicator — Quality Engine", "description": "Clean datasets, remove duplicate rows, detect missing values, normalize emails and phones, and validate schemas before exporting to CRM or databases.", "version": "0.1", "x-build-id": "eGXDxKehMaoOxMuxF" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/egeusta~dataset-quality-deduplication-engine/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-egeusta-dataset-quality-deduplication-engine", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/egeusta~dataset-quality-deduplication-engine/runs": { "post": { "operationId": "runs-sync-egeusta-dataset-quality-deduplication-engine", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/egeusta~dataset-quality-deduplication-engine/run-sync": { "post": { "operationId": "run-sync-egeusta-dataset-quality-deduplication-engine", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Records", "type": "array", "description": "Paste JSON objects or use datasetId." }, "datasetId": { "title": "Or Apify dataset ID/name", "type": "string", "description": "Read records from an accessible Apify dataset when pasted records are absent." }, "keyFields": { "title": "Duplicate key fields", "type": "array", "description": "Leave empty to compare all non-ignored fields.", "default": [] }, "ignoreFields": { "title": "Fields ignored for duplicates", "type": "array", "description": "Exclude volatile fields such as timestamps from duplicate signatures.", "default": [ "scrapedAt" ] }, "fuzzyThreshold": { "title": "Fuzzy similarity threshold", "minimum": 0.7, "maximum": 1, "type": "number", "description": "1 disables fuzzy matches; 0.90 is conservative.", "default": 0.9 }, "normalizeCase": { "title": "Normalize text case", "type": "boolean", "description": "Lowercase non-URL strings before duplicate comparison.", "default": true }, "trimWhitespace": { "title": "Normalize whitespace", "type": "boolean", "description": "Trim strings and collapse repeated whitespace before analysis.", "default": true }, "normalizeUrls": { "title": "Normalize URLs", "type": "boolean", "description": "Removes fragments and common tracking parameters; sorts remaining query parameters.", "default": true }, "removeEmptyStrings": { "title": "Convert empty strings to null", "type": "boolean", "description": "Represent blank text consistently as null in cleaned rows.", "default": false }, "validateEmailFormat": { "title": "Validate email format", "type": "boolean", "description": "Syntax only. No mailbox lookup, enrichment, or harvesting.", "default": true }, "outputMode": { "title": "Output mode", "enum": [ "cleaned_and_issues", "cleaned_only", "summary_only" ], "type": "string", "description": "Choose whether the dataset includes cleaned rows, detailed issue rows, or only the summary.", "default": "cleaned_and_issues" }, "maxRows": { "title": "Maximum rows", "minimum": 1, "maximum": 20000, "type": "integer", "description": "Hard cap on input records analyzed in one run.", "default": 5000 }, "maxComparisons": { "title": "Maximum fuzzy comparisons", "minimum": 1000, "maximum": 1000000, "type": "integer", "description": "Hard compute cap; exact duplicate detection continues after the cap.", "default": 100000 } } }, "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 } } } } } } } } } }