{
"openapi": "3.0.1",
"info": {
"title": "Dataset Toolkit: Dedupe, Merge, Filter, Convert",
"description": "Merge Apify datasets and CSV, JSON, JSONL, XLSX or Parquet files, remove duplicates (exact, normalized or fuzzy), filter with simple rules, flatten, sort, select and rename fields, then export to CSV, Excel, JSON or Parquet. Streams large data. Priced per 1,000 rows.",
"version": "1.0",
"x-build-id": "4zsjVfWU8vmqEhyp0"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/tinplatelabs~dataset-toolkit/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-tinplatelabs-dataset-toolkit",
"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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/tinplatelabs~dataset-toolkit/runs": {
"post": {
"operationId": "runs-sync-tinplatelabs-dataset-toolkit",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/tinplatelabs~dataset-toolkit/run-sync": {
"post": {
"operationId": "run-sync-tinplatelabs-dataset-toolkit",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": "Apify dataset IDs",
"type": "array",
"description": "Datasets to read, e.g. the output of a scraper run: pick them or paste dataset IDs (or username~dataset-name). Another user's dataset must be shared with you or public. Read page by page, so size is not limited by memory."
},
"fileUrls": {
"title": "File URLs",
"type": "array",
"description": "Public URLs of CSV, TSV, JSON (array), JSON Lines, XLSX (first sheet) or Parquet files, optionally gzip-compressed. Format is detected from the extension, Content-Type or content. Up to 1 GB each.",
"items": {
"type": "string"
}
},
"items": {
"title": "Inline items",
"type": "array",
"description": "Rows given directly as a JSON array of objects, e.g. from an AI agent or an API call. Read before datasets and files."
},
"fileFormat": {
"title": "File format",
"enum": [
"auto",
"csv",
"tsv",
"json",
"jsonl",
"xlsx",
"parquet"
],
"type": "string",
"description": "Force the format of every file URL. Auto detects it per file.",
"default": "auto"
},
"csvDelimiter": {
"title": "CSV delimiter",
"enum": [
"auto",
",",
";",
"\\t",
"|"
],
"type": "string",
"description": "Delimiter of CSV files. Auto picks the most frequent of , ; tab | in the header line.",
"default": "auto"
},
"sourceField": {
"title": "Source column",
"type": "string",
"description": "Name of a column recording where each row came from (inline, dataset:<id> or the file URL), e.g. _source. Empty = no column. Ignored by whole-row dedupe."
},
"flatten": {
"title": "Flatten nested fields",
"enum": [
"none",
"objects",
"all"
],
"type": "string",
"description": "Turn nested JSON into columns before filtering: objects makes address.city columns; all also splits arrays (tags.0). Without flattening, nested values become JSON text in CSV/XLSX.",
"default": "none"
},
"flattenSeparator": {
"title": "Flatten separator",
"type": "string",
"description": "Joins nested names when flattening, e.g. . or /.",
"default": "."
},
"filter": {
"title": "Filter",
"type": "string",
"description": "Keep only rows matching this rule, e.g. price >= 10 and country in [\"CA\", \"US\"] and not email empty. Operators: = != < <= > >= contains startswith endswith matches (regex) in exists empty, combined with and / or / not and parentheses. Nested fields: address.city; names with spaces in `backticks`. See the README."
},
"dedupe": {
"title": "Remove duplicates",
"enum": [
"none",
"exact",
"normalized",
"fuzzy"
],
"type": "string",
"description": "exact: identical values. normalized: ignores case, extra spaces and Unicode width. fuzzy: near matches such as typos (rapidfuzz similarity at least the threshold).",
"default": "none"
},
"dedupeFields": {
"title": "Dedupe on fields",
"type": "array",
"description": "Fields that identify a duplicate, e.g. email or name + city. Empty = the whole row. Rows with all these fields empty are always kept.",
"items": {
"type": "string"
}
},
"fuzzyThreshold": {
"title": "Fuzzy threshold",
"minimum": 50,
"maximum": 100,
"type": "integer",
"description": "Fuzzy mode: similarity (0-100, token sort ratio) needed to count as a duplicate. 90 catches typos and word order; lower values merge more aggressively.",
"default": 90
},
"keep": {
"title": "Which duplicate to keep",
"enum": [
"first",
"last",
"most-complete"
],
"type": "string",
"description": "Keep the first row seen, the last one, or the one with the most non-empty fields.",
"default": "first"
},
"duplicateCountField": {
"title": "Duplicate count column",
"type": "string",
"description": "Optional column name that receives how many rows were in each kept row's duplicate group, e.g. duplicates."
},
"sortBy": {
"title": "Sort by",
"type": "array",
"description": "Fields to sort by, in order. Prefix with - or add :desc for descending; add :number or :text to force a type. Numbers sort numerically (also in text), text ignores case, missing values go last. You can also sort by the duplicate count column.",
"items": {
"type": "string"
}
},
"limit": {
"title": "Max rows",
"minimum": 0,
"type": "integer",
"description": "Keep at most this many rows after filtering, dedupe and sorting. 0 = all.",
"default": 0
},
"fields": {
"title": "Keep only these fields",
"type": "array",
"description": "Output exactly these columns, in this order (nested paths like address.city allowed). Empty = all fields.",
"items": {
"type": "string"
}
},
"omitFields": {
"title": "Remove fields",
"type": "array",
"description": "Columns to drop (when 'Keep only these fields' is empty).",
"items": {
"type": "string"
}
},
"rename": {
"title": "Rename fields",
"type": "object",
"description": "Old name to new name, e.g. {\"Email Address\": \"email\"}. Applied last."
},
"exportFormats": {
"title": "Export files",
"type": "array",
"description": "Files written to the run's key-value store, with download links in the SUMMARY record. CSV, XLSX and Parquet use every column seen; nested values become JSON text.",
"items": {
"type": "string",
"enum": [
"csv",
"xlsx",
"json",
"jsonl",
"parquet"
],
"enumTitles": [
"CSV",
"Excel (XLSX)",
"JSON",
"JSON Lines",
"Parquet"
]
}
},
"exportFileName": {
"title": "Export file name",
"type": "string",
"description": "Base name of the export files (extension added).",
"default": "output"
},
"datasetOutput": {
"title": "Dataset output",
"enum": [
"rows",
"summary",
"none"
],
"type": "string",
"description": "rows: the processed rows go to the run's dataset. summary: one item with counts and export links (handy for agents and huge files). none: only the files and the SUMMARY record.",
"default": "rows"
}
}
},
"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
}
}
}
}
}
}
}
}
}
}