{ "openapi": "3.0.1", "info": { "title": "Merge & Deduplicate Datasets - Remove Duplicates", "description": "Merge Apify datasets and JSON items, remove duplicates by key fields, then pick, rename or cast fields. Reads only the datasets you pick.", "version": "0.1", "x-build-id": "YYAgPaWfjgpph1IIS" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/luxe_tasks~dataset-dedupe/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-luxe_tasks-dataset-dedupe", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/luxe_tasks~dataset-dedupe/runs": { "post": { "operationId": "runs-sync-luxe_tasks-dataset-dedupe", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/luxe_tasks~dataset-dedupe/run-sync": { "post": { "operationId": "run-sync-luxe_tasks-dataset-dedupe", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Datasets to merge", "maxItems": 20, "type": "array", "description": "Pick up to 20 datasets with the picker or paste their IDs. They are read in this order; with \"Keep\" = first, earlier datasets win. This Actor can read only the datasets you pick here (read-only)." }, "items": { "title": "Inline items (JSON)", "type": "array", "description": "Optional JSON array of objects (up to 10,000), read after the datasets. Example: [{\"url\": \"https://example.com/a\", \"name\": \"A\"}]. Leave this and the datasets empty to process a built-in 6-row sample, which has no per-row charge; the per-run start fee still applies." }, "dedupeFields": { "title": "Dedupe on fields", "type": "array", "description": "Rows with equal values in ALL of these fields are duplicates. Dot paths reach nested fields (e.g. \"seller.id\"). Leave empty to compare whole rows.", "items": { "type": "string" } }, "keep": { "title": "Keep", "enum": [ "first", "last" ], "type": "string", "description": "Which row of each duplicate group to keep: the first one read, or the last one (reads the sources twice).", "default": "first" }, "trimWhitespace": { "title": "Ignore leading/trailing spaces when comparing", "type": "boolean", "description": "\" Lamp \" and \"Lamp\" match. Output values are not changed.", "default": true }, "caseInsensitive": { "title": "Ignore letter case when comparing", "type": "boolean", "description": "\"LAMP\" and \"lamp\" match. Output values are not changed.", "default": false }, "missingKeyPolicy": { "title": "Rows with no key value", "enum": [ "keep", "drop", "group" ], "type": "string", "description": "What to do with rows where every dedupe field is missing (or empty, see below): keep them all, drop them, or treat them as one group (keep one).", "default": "keep" }, "emptyCountsAsMissing": { "title": "Treat null and empty text as missing", "type": "boolean", "description": "null and \"\" count as no value in the key fields.", "default": true }, "pickFields": { "title": "Keep only these fields", "type": "array", "description": "Top-level field names to keep in the output (input names). Leave empty to keep all.", "items": { "type": "string" } }, "omitFields": { "title": "Remove these fields", "type": "array", "description": "Top-level field names to remove (input names).", "items": { "type": "string" } }, "renameFields": { "title": "Rename fields", "type": "object", "description": "Object of old name to new name, e.g. {\"title\": \"name\"}. A renamed field replaces an existing field with the new name." }, "castFields": { "title": "Cast field types", "type": "object", "description": "Object of field name (after renaming) to type: string, number, integer or boolean, e.g. {\"price\": \"number\"}. Values that cannot be cast are kept unchanged and counted in RUN_SUMMARY." }, "escapeFormulas": { "title": "Protect against spreadsheet formulas", "type": "boolean", "description": "Prefix a single quote (') to text values that start with = + - @, tab or carriage return, so CSV/Excel exports do not run them as formulas. Turn off to keep values byte-for-byte.", "default": true }, "addSourceFields": { "title": "Add source fields", "type": "boolean", "description": "Add _sourceType, _sourceDatasetId and _sourceIndex to every output row.", "default": false }, "maxOutputRows": { "title": "Max output rows", "minimum": 0, "maximum": 2000000, "type": "integer", "description": "Stop after this many unique rows (0 or empty = no limit). Reading stops at 2,000,000 rows per run in any case." } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }