{ "openapi": "3.0.1", "info": { "title": "Dataset Diff & Change Detector", "description": "Returns what was added, removed or changed between two Apify datasets or JSON arrays, matched by key, field by field, with an optional CSV or Excel diff report. Inputs: old and new dataset IDs or inline data, key fields. Agent-ready: pay per event (x402 and MCP), per difference found and file.", "version": "0.1", "x-build-id": "IjaN2SWS1iYXliNFm" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/nerolabs~dataset-diff-detector/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-nerolabs-dataset-diff-detector", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/nerolabs~dataset-diff-detector/runs": { "post": { "operationId": "runs-sync-nerolabs-dataset-diff-detector", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/nerolabs~dataset-diff-detector/run-sync": { "post": { "operationId": "run-sync-nerolabs-dataset-diff-detector", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "oldDatasetId": { "title": "Old dataset (the 'before' snapshot)", "type": "string", "description": "Pick an existing Apify dataset holding the earlier version of your data. Use this OR 'Old data (inline)' below, not both. Declaring it this way is what lets this Actor run with limited permissions: it may read the dataset you point at, and nothing else on your account." }, "oldData": { "title": "Old data (inline)", "type": "array", "description": "A JSON array of records for the 'before' snapshot, for ad-hoc data instead of a dataset ID." }, "newDatasetId": { "title": "New dataset (the 'after' snapshot)", "type": "string", "description": "Pick an existing Apify dataset holding the newer version of your data. Use this OR 'New data (inline)' below, not both." }, "newData": { "title": "New data (inline)", "type": "array", "description": "A JSON array of records for the 'after' snapshot, for ad-hoc data instead of a dataset ID." }, "keyFields": { "title": "Key field(s)", "type": "array", "description": "The field name(s) that uniquely identify a row across both snapshots (e.g. 'sku', 'id', or 'email'). This is what lets the Actor tell 'this row changed' apart from 'this row was removed and a different one was added'. Leave empty to match rows by their full content instead (fine for simple lists, but then any change to any field makes a row look like a remove+add pair rather than a 'changed' row).", "items": { "type": "string" } }, "compareFields": { "title": "Fields to compare", "type": "array", "description": "Optional. Only compare these specific fields when deciding if a matched row changed. Leave empty to compare every field except any listed in 'Fields to ignore' below.", "items": { "type": "string" } }, "ignoreFields": { "title": "Fields to ignore", "type": "array", "description": "Optional. Field names to exclude from comparison, useful for things like a 'scrapedAt' or 'lastChecked' timestamp that always differs between runs and would otherwise mark every row as changed.", "items": { "type": "string" } }, "includeUnchanged": { "title": "Include unchanged rows in the output", "type": "boolean", "description": "When on, rows present in both snapshots with no real difference are also written to the output dataset (charged at a much lower rate, see Pricing). Off by default, since a diff tool's whole point is usually just the things that changed.", "default": false }, "exportFormats": { "title": "Export diff report as file", "type": "array", "description": "Optional. Generate a real downloadable diff report on top of the dataset. Leave empty to skip file export entirely.", "items": { "type": "string", "enum": [ "csv", "xlsx" ], "enumTitles": [ "CSV", "Excel (.xlsx)" ] }, "default": [] }, "maxItems": { "title": "Max rows to process", "type": "integer", "description": "Safety cap on how many rows from the larger of the two snapshots to process. Leave at 0 for no cap (up to the Actor's own 100,000-row hard limit).", "default": 0 } } }, "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 } } } } } } } } } }