{ "openapi": "3.0.1", "info": { "title": "Apify Smart Dataset Comparator", "description": "Compare 2-10 Apify datasets to detect changes, new/removed records, and duplicates. Features field-level diffs, smart merging, schema validation, data cleaning, and anomaly detection. Perfect for price monitoring, lead deduplication, and data quality tracking.", "version": "1.0", "x-build-id": "oPFUJl3JyquCczUHX" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/agenscrape~apify-smart-dataset-comparator/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-agenscrape-apify-smart-dataset-comparator", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/agenscrape~apify-smart-dataset-comparator/runs": { "post": { "operationId": "runs-sync-agenscrape-apify-smart-dataset-comparator", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/agenscrape~apify-smart-dataset-comparator/run-sync": { "post": { "operationId": "run-sync-agenscrape-apify-smart-dataset-comparator", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "datasetIds": { "title": "Dataset IDs", "type": "array", "description": "List of Apify Dataset IDs to compare (2-10 datasets). Order matters - first is baseline, subsequent are compared against it.", "items": { "type": "string" } }, "datasetUrls": { "title": "Dataset URLs", "type": "array", "description": "URLs to JSON or CSV files (alternative to Dataset IDs)", "items": { "type": "string" } }, "primaryKey": { "title": "Primary Key", "type": "string", "description": "Field(s) to uniquely identify records. Use dot notation for nested fields (e.g., 'product.id'). For composite keys, use comma-separated values: 'url,sku'", "default": "id" }, "ignoreFields": { "title": "Ignore Fields", "type": "array", "description": "Fields to ignore when comparing records (e.g., timestamps, internal IDs)", "default": [], "items": { "type": "string" } }, "preset": { "title": "Comparison Preset", "enum": [ "none", "price_monitoring", "lead_lists", "seo", "real_estate" ], "type": "string", "description": "Pre-configured settings for common use cases", "default": "none" }, "sensitivity": { "title": "Comparison Sensitivity", "enum": [ "strict", "medium", "relaxed" ], "type": "string", "description": "How strict should the comparison be?", "default": "strict" }, "numericTolerance": { "title": "Numeric Tolerance (%)", "minimum": 0, "maximum": 100, "type": "integer", "description": "Ignore numeric changes smaller than this percentage (e.g., 1 = ignore changes <= 1%)", "default": 0 }, "caseSensitive": { "title": "Case Sensitive", "type": "boolean", "description": "Should string comparisons be case-sensitive?", "default": true }, "cleaningRules": { "title": "Data Cleaning Rules", "type": "object", "description": "Rules to normalize data before comparison", "default": {} }, "detectDuplicates": { "title": "Detect Duplicates", "type": "boolean", "description": "Find duplicate records within each dataset", "default": false }, "fuzzyMatching": { "title": "Fuzzy Duplicate Matching", "type": "boolean", "description": "Use fuzzy matching to find near-duplicates (Levenshtein distance)", "default": false }, "fuzzyThreshold": { "title": "Fuzzy Match Threshold", "minimum": 0.5, "maximum": 1, "type": "number", "description": "Similarity threshold for fuzzy matching (0-1, where 1 = exact match)", "default": 0.85 }, "duplicateFields": { "title": "Duplicate Detection Fields", "type": "array", "description": "Additional fields to check for near-match duplicates", "default": [], "items": { "type": "string" } }, "mergeStrategy": { "title": "Merge Strategy", "enum": [ "left_priority", "right_priority", "most_recent", "most_complete", "combine_arrays", "average_numbers" ], "type": "string", "description": "How to merge records when they exist in multiple datasets", "default": "left_priority" }, "timestampField": { "title": "Timestamp Field", "type": "string", "description": "Field name containing record timestamp (for 'most_recent' merge strategy)", "default": "timestamp" }, "fieldPriorities": { "title": "Field-Level Priorities", "type": "object", "description": "Custom merge priorities per field: left, right, max, min, average, longest, combine", "default": {} }, "validateSchema": { "title": "Validate Schema", "type": "boolean", "description": "Compare schemas across datasets and detect inconsistencies", "default": false }, "strictSchemaValidation": { "title": "Strict Schema Validation", "type": "boolean", "description": "Report all type mismatches and unexpected fields as errors", "default": false }, "outputSeparateDatasets": { "title": "Output to Separate Datasets", "type": "boolean", "description": "Save results to named datasets (changes, new_records, removed_records, merged_final, duplicates, stats)", "default": true }, "webhookUrl": { "title": "Webhook URL", "type": "string", "description": "URL to receive notification when comparison completes" } } }, "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 } } } } } } } } } }