{ "openapi": "3.0.1", "info": { "title": "Fuzzy Dedupe: Find Near-Duplicate Rows in Datasets", "description": "Find near-duplicates that exact dedup misses: 'Acme Inc.' vs 'ACME, Inc', 'Main St.' vs 'Main Street'. Fuzzy match names, addresses, phones, URLs across Apify datasets; mark or merge clusters with reasons. Empty input = free demo. $0.50 per 1,000 rows.", "version": "0.1", "x-build-id": "erLJcfJrnQp1faVbE" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ucchiii~dataset-fuzzy-dedupe/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ucchiii-dataset-fuzzy-dedupe", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/ucchiii~dataset-fuzzy-dedupe/runs": { "post": { "operationId": "runs-sync-ucchiii-dataset-fuzzy-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/ucchiii~dataset-fuzzy-dedupe/run-sync": { "post": { "operationId": "run-sync-ucchiii-dataset-fuzzy-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", "maxItems": 20, "type": "array", "description": "Apify datasets to compare (the 'defaultDatasetId' of a finished run, e.g. 'WkzbQMuFYuamGv3YF'). Up to 20; rows from all datasets are compared with each other. You can paste a dataset URL from Apify Console too. Leave empty to run a free demo on sample data (not charged)." }, "matchFields": { "title": "Fields to compare", "type": "array", "description": "List of objects: field (column name, dots for nested like 'address.city'), type (name, address, phone, url or text) and weight (default 1, higher = counts more). name: ignores case, punctuation and legal suffixes (Inc, LLC, Ltd, GmbH, 株式会社). address: street abbreviations and full-width characters. phone: digits only. url: host only. text: plain fuzzy text. If empty, a field called 'name' is compared." }, "threshold": { "title": "Match threshold (0.5-1)", "minimum": 0.5, "maximum": 1, "type": "number", "description": "Minimum weighted similarity for two rows to be treated as the same. Default 0.9. Lower finds more (and riskier) matches; 1 means identical after normalization.", "default": 0.9 }, "mode": { "title": "Mode", "enum": [ "mark", "merge" ], "type": "string", "description": "'mark' keeps every row and adds clusterId, isPrimary, matchScore and matchReason. 'merge' outputs one row per cluster: the most complete row plus mergedRowIds.", "default": "mark" }, "blockingKey": { "title": "Speed-up: blocking key", "enum": [ "firstLetters", "postalCode", "domain", "none" ], "type": "string", "description": "Only rows sharing the key are compared, which keeps big datasets fast. Rows with different keys are never matched, so pick a key that duplicates share (typos in the first letters can hide a match). Default: first letters.", "default": "firstLetters" }, "blockingField": { "title": "Blocking field", "type": "string", "description": "Column the blocking key is taken from (e.g. 'name', 'address', 'zip', 'website'). Leave empty to use the first match field of a suitable type." }, "blockingLength": { "title": "Blocking: number of letters", "minimum": 1, "maximum": 10, "type": "integer", "description": "For the 'first letters' key: how many characters of the normalized value to use (1 to 10). Shorter = safer but slower.", "default": 3 }, "maxRows": { "title": "Max rows", "minimum": 1, "maximum": 200000, "type": "integer", "description": "Hard cap on rows processed per run (at most 200,000). Rows beyond the cap are ignored and not charged. Also useful as a cost limit.", "default": 200000 } } }, "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 } } } } } } } } } }