{ "openapi": "3.0.1", "info": { "title": "🧽 Dataset Deduplicator - Clean Any Scraped Dataset", "description": "🧽 Upload any dataset — scraped rows, a RAG corpus, an export — and get back exact AND near-duplicates removed, plus a per-field data quality report. ✅ MinHash + LSH banding finds near-duplicate text at scale without O(n²) pairwise comparison.", "version": "1.0", "x-build-id": "hiUxapSn440GMmew5" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/that_red_bird~dataset-deduplicator/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-that_red_bird-dataset-deduplicator", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/that_red_bird~dataset-deduplicator/runs": { "post": { "operationId": "runs-sync-that_red_bird-dataset-deduplicator", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/that_red_bird~dataset-deduplicator/run-sync": { "post": { "operationId": "run-sync-that_red_bird-dataset-deduplicator", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "records": { "title": "Records", "type": "array", "description": "The dataset to clean, as an array of flat row objects. Combine freely with datasetIds. Nested arrays/objects per row are not supported.", "default": [ { "title": "Best wireless headphones 2024", "body": "These wireless headphones deliver excellent sound quality and battery life for the price." }, { "title": "Best wireless headphones 2024", "body": "These wireless headphones deliver excellent sound quality and battery life for the price." }, { "title": "Best wireless headphones of 2024", "body": "These wireless headphones deliver great sound quality and long battery life for the price." }, { "title": "Top budget laptops this year", "body": "A roundup of the best budget laptops you can buy right now, covering performance and battery." } ] }, "datasetIds": { "title": "Source dataset IDs", "type": "array", "description": "Apify dataset IDs to pull additional rows from (e.g. the output of a scraping actor). Rows are appended to \"records\" before deduplication.", "items": { "type": "string" } }, "idField": { "title": "ID field", "type": "string", "description": "Field to use as each record's identifier in the output (e.g. \"url\" or \"sku\"). Leave empty to auto-generate an id (R000001, R000002, ...)." }, "textFields": { "title": "Text fields to compare (advanced)", "type": "array", "description": "Which fields hold free text to check for near-duplicates. Leave empty to auto-detect long string columns (average length above \"Auto-detect text length threshold\").", "items": { "type": "string" } }, "textFieldMinAvgLength": { "title": "Auto-detect text length threshold", "minimum": 5, "maximum": 1000, "type": "integer", "description": "When textFields is empty, a column is treated as free text if its average string length across the sampled rows is at least this many characters.", "default": 40 }, "similarityThreshold": { "title": "Near-duplicate similarity threshold (0-100)", "minimum": 1, "maximum": 100, "type": "integer", "description": "Two records are treated as near-duplicates when their text overlap (Jaccard similarity over shingles) is at or above this. Higher = fewer false merges, more missed near-duplicates. Expressed 0-100; 80 means 0.80.", "default": 80 }, "shingleSize": { "title": "Shingle size (words)", "minimum": 2, "maximum": 10, "type": "integer", "description": "Length of the word n-grams used to fingerprint each document. Smaller catches shorter edits but is noisier; larger is stricter. Short text automatically falls back to character shingles instead.", "default": 3 }, "numHashes": { "title": "MinHash signature size", "minimum": 8, "maximum": 256, "type": "integer", "description": "How many hash functions make up each document's MinHash signature. Higher gives a more accurate similarity estimate for candidate generation but costs more CPU. Must be >= numBands.", "default": 32 }, "numBands": { "title": "LSH bands", "minimum": 2, "maximum": 128, "type": "integer", "description": "How many bands the MinHash signature is split into for LSH bucketing. More bands catch weaker matches (higher recall, more candidate pairs to verify); fewer bands are stricter and faster.", "default": 8 }, "maxBucketSize": { "title": "Max LSH bucket size", "minimum": 10, "maximum": 20000, "type": "integer", "description": "An LSH bucket larger than this is skipped when generating candidate pairs, to avoid an O(n²) blowup if many records hash into the same bucket (e.g. many rows with blank text).", "default": 500 }, "includeKept": { "title": "Include kept records", "type": "boolean", "description": "Emit the deduplicated, cleaned records (type: \"kept\").", "default": true }, "includeRemoved": { "title": "Include removed duplicates", "type": "boolean", "description": "Emit every removed row (type: \"duplicate\") with the id of the record it duplicates, the similarity score, and whether it was an exact or near match.", "default": true }, "includeQualityReport": { "title": "Include quality report", "type": "boolean", "description": "Emit one summary row (type: \"qualityReport\") with per-field completeness/uniqueness/type-consistency/outliers and an overall 0-100 quality score.", "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 } } }, "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 } } } } } } } } } }