{ "openapi": "3.0.1", "info": { "title": "Dataset Deduplication & Merge - Remove Duplicates", "description": "Merge Apify datasets and remove duplicate rows by selected fields. First/last matching. $0.02/1,000 source rows; first 50 rows/run free.", "version": "0.0", "x-build-id": "Fi5G0TDDrjXT9Zdre" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ahmed.fouaad82~dataset-dedup-merge/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ahmed.fouaad82-dataset-dedup-merge", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/ahmed.fouaad82~dataset-dedup-merge/runs": { "post": { "operationId": "runs-sync-ahmed.fouaad82-dataset-dedup-merge", "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/ahmed.fouaad82~dataset-dedup-merge/run-sync": { "post": { "operationId": "run-sync-ahmed.fouaad82-dataset-dedup-merge", "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": "Source datasets", "type": "array", "description": "Select datasets to merge in this order. Grants READ access only to these datasets." }, "runIds": { "title": "Source run IDs (advanced)", "type": "array", "description": "Accessible run IDs. Private arbitrary runs cannot be read with a limited token: resolve locally using tools/resolve-runs.mjs, then provide the resulting datasetIds.", "default": [], "items": { "type": "string" } }, "keyFields": { "title": "Deduplication key fields", "type": "array", "description": "One or more dot-separated field paths. All chosen values form a composite key.", "default": [ "id" ], "items": { "type": "string" } }, "keep": { "title": "Keep representative", "enum": [ "first", "last" ], "type": "string", "description": "Keep the earliest or latest occurrence in dataset order.", "default": "first" }, "caseInsensitive": { "title": "Case-insensitive keys", "type": "boolean", "description": "Lowercase string key values only; original output is unchanged.", "default": false }, "trim": { "title": "Trim key whitespace", "type": "boolean", "description": "Trim string key values only.", "default": true }, "ignoreEmpty": { "title": "Ignore incomplete keys", "type": "boolean", "description": "Keep each row with any null, missing or empty key separate instead of merging them.", "default": true }, "onlyDuplicates": { "title": "Output only duplicate groups", "type": "boolean", "description": "One representative for each key with at least two occurrences, not every discarded row.", "default": false }, "pickFields": { "title": "Pick fields", "type": "array", "description": "Top-level output fields only. Applied after matching; omit wins over pick. Empty means no restriction.", "default": [], "items": { "type": "string" } }, "omitFields": { "title": "Omit fields", "type": "array", "description": "Top-level output fields only. Applied after matching; omit wins over pick. Empty means no restriction.", "default": [], "items": { "type": "string" } }, "batchSize": { "title": "API batch size", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Items fetched and output per batch. Lower for large rows.", "default": 1000 }, "maxItems": { "title": "Maximum source items", "minimum": 0, "type": "integer", "description": "Stop gracefully after this many source rows; zero means unlimited. Results then describe only the processed prefix. First 50 source rows processed in every run are free; pricing applies to source rows, not deduplicated output rows.", "default": 0 }, "demoMode": { "title": "Use built-in example when no sources are selected", "type": "boolean", "description": "With no source datasets/run IDs, deduplicate four synthetic product rows into three examples. Real sources always take precedence. Disable to require a source.", "default": 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 }, "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 } } } } } } } } } }