{ "openapi": "3.0.1", "info": { "title": "Dataset Dedupe Merger", "description": "Merge multiple datasets into one clean dataset. Removes duplicates with exact, normalized, or fuzzy matching, unifies field names, and keeps the most complete version of every record — with missing fields back-filled from discarded duplicates. Built for cleaning multi-scraper output.", "version": "0.0", "x-build-id": "tTJZJPCYVv4DLDr9z" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/inestimable_zoysia~dataset-dedupe-merger/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-inestimable_zoysia-dataset-dedupe-merger", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/inestimable_zoysia~dataset-dedupe-merger/runs": { "post": { "operationId": "runs-sync-inestimable_zoysia-dataset-dedupe-merger", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/inestimable_zoysia~dataset-dedupe-merger/run-sync": { "post": { "operationId": "run-sync-inestimable_zoysia-dataset-dedupe-merger", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "datasetIds", "dedupeFields" ], "properties": { "datasetIds": { "title": "Datasets to merge", "type": "array", "description": "One or more datasets to merge and deduplicate. Order matters for the 'first'/'last' keep strategies." }, "dedupeFields": { "title": "Deduplication fields", "type": "array", "description": "Field name(s) that define a duplicate. Rows matching on ALL of these fields are considered duplicates. Examples: ['email'] or ['name', 'address']. Supports dot notation for nested fields (e.g. 'contact.email').", "items": { "type": "string" } }, "matchMode": { "title": "Match mode", "enum": [ "exact", "normalized", "fuzzy" ], "type": "string", "description": "How field values are compared. 'exact' = byte-for-byte. 'normalized' = case-insensitive, whitespace/punctuation stripped, phone numbers reduced to digits. 'fuzzy' = normalized + similarity matching for near-duplicates like \"Joe's Pizza\" vs \"Joes Pizza LLC\".", "default": "normalized" }, "fuzzyThreshold": { "title": "Fuzzy similarity threshold", "minimum": 50, "maximum": 100, "type": "integer", "description": "Only used in fuzzy mode. Similarity percentage (50–100) required to consider two values a match. 85 is a good default: catches typos and suffix noise without merging genuinely different records.", "default": 85 }, "blockingField": { "title": "Blocking field (fuzzy mode, large datasets)", "type": "string", "description": "Optional but strongly recommended for fuzzy mode on 10k+ rows. Rows are only fuzzy-compared when they share the same normalized value in this field (e.g. 'zipCode' or 'city'). Keeps large jobs fast." }, "fieldMapping": { "title": "Field mapping (rename before merge)", "type": "object", "description": "Optional map of source field → target field, applied to every row before merging. Example: {\"businessName\": \"name\", \"company_name\": \"name\"} unifies differently-named columns across datasets." }, "keepStrategy": { "title": "Keep strategy", "enum": [ "first", "last", "mostComplete" ], "type": "string", "description": "Which record survives when duplicates are found. 'mostComplete' keeps the row with the fewest empty fields and back-fills its missing values from the discarded duplicates (best for lead lists).", "default": "mostComplete" }, "outputFields": { "title": "Output fields", "type": "array", "description": "Optional. If set, output rows contain only these fields, in this order.", "items": { "type": "string" } } } }, "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 } } } } } } } } } }