Dataset Toolbox
Pricing
Pay per usage
Go to Store0
Dataset Toolbox
Perform common actions on datasets - merge, unify, validate, transform, order fields etc.
0.0 (0)
Pricing
Pay per usage
4
Total users
28
Monthly users
2
Last modified
3 years ago
You can access the Dataset Toolbox programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
1{
2 "openapi": "3.0.1",
3 "info": {
4 "version": "0.0",
5 "x-build-id": "2J8mKVOLVIVWlLFXt"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/cyberfly~dataset-toolbox/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-cyberfly-dataset-toolbox",
16 "x-openai-isConsequential": false,
17 "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
18 "tags": [
19 "Run Actor"
20 ],
21 "requestBody": {
22 "required": true,
23 "content": {
24 "application/json": {
25 "schema": {
26 "$ref": "#/components/schemas/inputSchema"
27 }
28 }
29 }
30 },
31 "parameters": [
32 {
33 "name": "token",
34 "in": "query",
35 "required": true,
36 "schema": {
37 "type": "string"
38 },
39 "description": "Enter your Apify token here"
40 }
41 ],
42 "responses": {
43 "200": {
44 "description": "OK"
45 }
46 }
47 }
48 },
49 "/acts/cyberfly~dataset-toolbox/runs": {
50 "post": {
51 "operationId": "runs-sync-cyberfly-dataset-toolbox",
52 "x-openai-isConsequential": false,
53 "summary": "Executes an Actor and returns information about the initiated run in response.",
54 "tags": [
55 "Run Actor"
56 ],
57 "requestBody": {
58 "required": true,
59 "content": {
60 "application/json": {
61 "schema": {
62 "$ref": "#/components/schemas/inputSchema"
63 }
64 }
65 }
66 },
67 "parameters": [
68 {
69 "name": "token",
70 "in": "query",
71 "required": true,
72 "schema": {
73 "type": "string"
74 },
75 "description": "Enter your Apify token here"
76 }
77 ],
78 "responses": {
79 "200": {
80 "description": "OK",
81 "content": {
82 "application/json": {
83 "schema": {
84 "$ref": "#/components/schemas/runsResponseSchema"
85 }
86 }
87 }
88 }
89 }
90 }
91 },
92 "/acts/cyberfly~dataset-toolbox/run-sync": {
93 "post": {
94 "operationId": "run-sync-cyberfly-dataset-toolbox",
95 "x-openai-isConsequential": false,
96 "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
97 "tags": [
98 "Run Actor"
99 ],
100 "requestBody": {
101 "required": true,
102 "content": {
103 "application/json": {
104 "schema": {
105 "$ref": "#/components/schemas/inputSchema"
106 }
107 }
108 }
109 },
110 "parameters": [
111 {
112 "name": "token",
113 "in": "query",
114 "required": true,
115 "schema": {
116 "type": "string"
117 },
118 "description": "Enter your Apify token here"
119 }
120 ],
121 "responses": {
122 "200": {
123 "description": "OK"
124 }
125 }
126 }
127 }
128 },
129 "components": {
130 "schemas": {
131 "inputSchema": {
132 "type": "object",
133 "properties": {
134 "actorIds": {
135 "title": "Actor IDs",
136 "uniqueItems": true,
137 "type": "array",
138 "description": "IDs of actors to use as source of latest default datasets"
139 },
140 "datasetIds": {
141 "title": "Dataset IDs",
142 "uniqueItems": true,
143 "type": "array",
144 "description": "IDs of datasets to use as data sources directly"
145 },
146 "outputFormat": {
147 "title": "Output format",
148 "enum": [
149 "csv",
150 "json",
151 "html",
152 "xlsx"
153 ],
154 "type": "string",
155 "description": "Output file format of the result dataset",
156 "default": "json"
157 },
158 "itemsLimit": {
159 "title": "Items count limit",
160 "minimum": 1,
161 "maximum": 250000,
162 "type": "integer",
163 "description": "Limit number of items from the source datasets"
164 },
165 "manageFields": {
166 "title": "Pick/sort output fields",
167 "type": "boolean",
168 "description": "Pick top level fields from the source dataset and sort them in custom order specified below"
169 },
170 "sortedFields": {
171 "title": "Fields in this order",
172 "uniqueItems": true,
173 "type": "array",
174 "description": "Extract these fields from source datasets and sort them in specified order on output linked from dataset download link in KV"
175 },
176 "postProcessing": {
177 "title": "Enable post-processing",
178 "type": "boolean",
179 "description": "Enable post-processing of individual items"
180 },
181 "postProcessFun": {
182 "title": "Post-processing function",
183 "type": "string",
184 "description": "Function for post-processing with individual dataset item as its single argument"
185 },
186 "validateSchema": {
187 "title": "Validate output schema",
188 "type": "boolean",
189 "description": "Validates dataset items against output schema"
190 },
191 "validateOnly": {
192 "title": "Validate only (skip output)",
193 "type": "boolean",
194 "description": "Validate source items without storing them in default dataset"
195 },
196 "outputSchema": {
197 "title": "Output schema",
198 "type": "object",
199 "description": "Dataset items are validated against this schema"
200 }
201 }
202 },
203 "runsResponseSchema": {
204 "type": "object",
205 "properties": {
206 "data": {
207 "type": "object",
208 "properties": {
209 "id": {
210 "type": "string"
211 },
212 "actId": {
213 "type": "string"
214 },
215 "userId": {
216 "type": "string"
217 },
218 "startedAt": {
219 "type": "string",
220 "format": "date-time",
221 "example": "2025-01-08T00:00:00.000Z"
222 },
223 "finishedAt": {
224 "type": "string",
225 "format": "date-time",
226 "example": "2025-01-08T00:00:00.000Z"
227 },
228 "status": {
229 "type": "string",
230 "example": "READY"
231 },
232 "meta": {
233 "type": "object",
234 "properties": {
235 "origin": {
236 "type": "string",
237 "example": "API"
238 },
239 "userAgent": {
240 "type": "string"
241 }
242 }
243 },
244 "stats": {
245 "type": "object",
246 "properties": {
247 "inputBodyLen": {
248 "type": "integer",
249 "example": 2000
250 },
251 "rebootCount": {
252 "type": "integer",
253 "example": 0
254 },
255 "restartCount": {
256 "type": "integer",
257 "example": 0
258 },
259 "resurrectCount": {
260 "type": "integer",
261 "example": 0
262 },
263 "computeUnits": {
264 "type": "integer",
265 "example": 0
266 }
267 }
268 },
269 "options": {
270 "type": "object",
271 "properties": {
272 "build": {
273 "type": "string",
274 "example": "latest"
275 },
276 "timeoutSecs": {
277 "type": "integer",
278 "example": 300
279 },
280 "memoryMbytes": {
281 "type": "integer",
282 "example": 1024
283 },
284 "diskMbytes": {
285 "type": "integer",
286 "example": 2048
287 }
288 }
289 },
290 "buildId": {
291 "type": "string"
292 },
293 "defaultKeyValueStoreId": {
294 "type": "string"
295 },
296 "defaultDatasetId": {
297 "type": "string"
298 },
299 "defaultRequestQueueId": {
300 "type": "string"
301 },
302 "buildNumber": {
303 "type": "string",
304 "example": "1.0.0"
305 },
306 "containerUrl": {
307 "type": "string"
308 },
309 "usage": {
310 "type": "object",
311 "properties": {
312 "ACTOR_COMPUTE_UNITS": {
313 "type": "integer",
314 "example": 0
315 },
316 "DATASET_READS": {
317 "type": "integer",
318 "example": 0
319 },
320 "DATASET_WRITES": {
321 "type": "integer",
322 "example": 0
323 },
324 "KEY_VALUE_STORE_READS": {
325 "type": "integer",
326 "example": 0
327 },
328 "KEY_VALUE_STORE_WRITES": {
329 "type": "integer",
330 "example": 1
331 },
332 "KEY_VALUE_STORE_LISTS": {
333 "type": "integer",
334 "example": 0
335 },
336 "REQUEST_QUEUE_READS": {
337 "type": "integer",
338 "example": 0
339 },
340 "REQUEST_QUEUE_WRITES": {
341 "type": "integer",
342 "example": 0
343 },
344 "DATA_TRANSFER_INTERNAL_GBYTES": {
345 "type": "integer",
346 "example": 0
347 },
348 "DATA_TRANSFER_EXTERNAL_GBYTES": {
349 "type": "integer",
350 "example": 0
351 },
352 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
353 "type": "integer",
354 "example": 0
355 },
356 "PROXY_SERPS": {
357 "type": "integer",
358 "example": 0
359 }
360 }
361 },
362 "usageTotalUsd": {
363 "type": "number",
364 "example": 0.00005
365 },
366 "usageUsd": {
367 "type": "object",
368 "properties": {
369 "ACTOR_COMPUTE_UNITS": {
370 "type": "integer",
371 "example": 0
372 },
373 "DATASET_READS": {
374 "type": "integer",
375 "example": 0
376 },
377 "DATASET_WRITES": {
378 "type": "integer",
379 "example": 0
380 },
381 "KEY_VALUE_STORE_READS": {
382 "type": "integer",
383 "example": 0
384 },
385 "KEY_VALUE_STORE_WRITES": {
386 "type": "number",
387 "example": 0.00005
388 },
389 "KEY_VALUE_STORE_LISTS": {
390 "type": "integer",
391 "example": 0
392 },
393 "REQUEST_QUEUE_READS": {
394 "type": "integer",
395 "example": 0
396 },
397 "REQUEST_QUEUE_WRITES": {
398 "type": "integer",
399 "example": 0
400 },
401 "DATA_TRANSFER_INTERNAL_GBYTES": {
402 "type": "integer",
403 "example": 0
404 },
405 "DATA_TRANSFER_EXTERNAL_GBYTES": {
406 "type": "integer",
407 "example": 0
408 },
409 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
410 "type": "integer",
411 "example": 0
412 },
413 "PROXY_SERPS": {
414 "type": "integer",
415 "example": 0
416 }
417 }
418 }
419 }
420 }
421 }
422 }
423 }
424 }
425}Dataset Toolbox OpenAPI definition
OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Dataset Toolbox from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients:
