Query Dataset
Under maintenance
Go to Store
This Actor is under maintenance.
This Actor may be unreliable while under maintenance. Would you like to try a similar Actor instead?
See alternative ActorsQuery Dataset
pocesar/query-dataset
Query your existing datasets, map and generate a subset of your data
Developer
Paulo CesarMaintained by Community
Categories
You can access the Query Dataset 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": "s6gWu5XRxx4NkgfRY"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/pocesar~query-dataset/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-pocesar-query-dataset",
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 "$ref": "#/components/schemas/inputSchema"
27 }
28 }
29 }
30 },
31 "parameters": [
32 {
33 "name": "token",
34 "in": "query",
35 "required": true,
36 "schema": {
37 "type": "string"
38 },
39 "description": "Enter your Apify token here"
40 }
41 ],
42 "responses": {
43 "200": {
44 "description": "OK"
45 }
46 }
47 }
48 },
49 "/acts/pocesar~query-dataset/runs": {
50 "post": {
51 "operationId": "runs-sync-pocesar-query-dataset",
52 "x-openai-isConsequential": false,
53 "summary": "Executes an Actor and returns information about the initiated run in response.",
54 "tags": [
55 "Run Actor"
56 ],
57 "requestBody": {
58 "required": true,
59 "content": {
60 "application/json": {
61 "schema": {
62 "$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 "$ref": "#/components/schemas/runsResponseSchema"
85 }
86 }
87 }
88 }
89 }
90 }
91 },
92 "/acts/pocesar~query-dataset/run-sync": {
93 "post": {
94 "operationId": "run-sync-pocesar-query-dataset",
95 "x-openai-isConsequential": false,
96 "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
97 "tags": [
98 "Run Actor"
99 ],
100 "requestBody": {
101 "required": true,
102 "content": {
103 "application/json": {
104 "schema": {
105 "$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 "required": [
134 "datasetId",
135 "query"
136 ],
137 "properties": {
138 "datasetId": {
139 "title": "Dataset Id",
140 "type": "string",
141 "description": "Provide your datasetId"
142 },
143 "query": {
144 "title": "Query",
145 "type": "object",
146 "description": "Provide a MongoDB-like query using JSON"
147 },
148 "limit": {
149 "title": "Limit",
150 "type": "integer",
151 "description": "Limit how many items to get. If it's not provided, will return all found items"
152 },
153 "offset": {
154 "title": "Offset",
155 "type": "integer",
156 "description": "Will slice the data from the provided offset. The offset is relative to queried items. Can be used with 'Limit'. Defaults to 0",
157 "default": 0
158 },
159 "filterMap": {
160 "title": "Map and filter function",
161 "type": "string",
162 "description": "Provide a map function, allows you to return modified data. Returning null or undefined on this function filter the item from the output"
163 },
164 "customOperationSetup": {
165 "title": "Custom operations setup",
166 "type": "string",
167 "description": "Setup custom operations for usage on queries"
168 },
169 "deduplicationKey": {
170 "title": "De-duplication key",
171 "type": "string",
172 "description": "Key on each item to serve as a deduplication"
173 },
174 "bufferLimit": {
175 "title": "Buffer limit",
176 "type": "integer",
177 "description": "How many items to buffer in memory before pushing to the dataset",
178 "default": 50000
179 }
180 }
181 },
182 "runsResponseSchema": {
183 "type": "object",
184 "properties": {
185 "data": {
186 "type": "object",
187 "properties": {
188 "id": {
189 "type": "string"
190 },
191 "actId": {
192 "type": "string"
193 },
194 "userId": {
195 "type": "string"
196 },
197 "startedAt": {
198 "type": "string",
199 "format": "date-time",
200 "example": "2025-01-08T00:00:00.000Z"
201 },
202 "finishedAt": {
203 "type": "string",
204 "format": "date-time",
205 "example": "2025-01-08T00:00:00.000Z"
206 },
207 "status": {
208 "type": "string",
209 "example": "READY"
210 },
211 "meta": {
212 "type": "object",
213 "properties": {
214 "origin": {
215 "type": "string",
216 "example": "API"
217 },
218 "userAgent": {
219 "type": "string"
220 }
221 }
222 },
223 "stats": {
224 "type": "object",
225 "properties": {
226 "inputBodyLen": {
227 "type": "integer",
228 "example": 2000
229 },
230 "rebootCount": {
231 "type": "integer",
232 "example": 0
233 },
234 "restartCount": {
235 "type": "integer",
236 "example": 0
237 },
238 "resurrectCount": {
239 "type": "integer",
240 "example": 0
241 },
242 "computeUnits": {
243 "type": "integer",
244 "example": 0
245 }
246 }
247 },
248 "options": {
249 "type": "object",
250 "properties": {
251 "build": {
252 "type": "string",
253 "example": "latest"
254 },
255 "timeoutSecs": {
256 "type": "integer",
257 "example": 300
258 },
259 "memoryMbytes": {
260 "type": "integer",
261 "example": 1024
262 },
263 "diskMbytes": {
264 "type": "integer",
265 "example": 2048
266 }
267 }
268 },
269 "buildId": {
270 "type": "string"
271 },
272 "defaultKeyValueStoreId": {
273 "type": "string"
274 },
275 "defaultDatasetId": {
276 "type": "string"
277 },
278 "defaultRequestQueueId": {
279 "type": "string"
280 },
281 "buildNumber": {
282 "type": "string",
283 "example": "1.0.0"
284 },
285 "containerUrl": {
286 "type": "string"
287 },
288 "usage": {
289 "type": "object",
290 "properties": {
291 "ACTOR_COMPUTE_UNITS": {
292 "type": "integer",
293 "example": 0
294 },
295 "DATASET_READS": {
296 "type": "integer",
297 "example": 0
298 },
299 "DATASET_WRITES": {
300 "type": "integer",
301 "example": 0
302 },
303 "KEY_VALUE_STORE_READS": {
304 "type": "integer",
305 "example": 0
306 },
307 "KEY_VALUE_STORE_WRITES": {
308 "type": "integer",
309 "example": 1
310 },
311 "KEY_VALUE_STORE_LISTS": {
312 "type": "integer",
313 "example": 0
314 },
315 "REQUEST_QUEUE_READS": {
316 "type": "integer",
317 "example": 0
318 },
319 "REQUEST_QUEUE_WRITES": {
320 "type": "integer",
321 "example": 0
322 },
323 "DATA_TRANSFER_INTERNAL_GBYTES": {
324 "type": "integer",
325 "example": 0
326 },
327 "DATA_TRANSFER_EXTERNAL_GBYTES": {
328 "type": "integer",
329 "example": 0
330 },
331 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
332 "type": "integer",
333 "example": 0
334 },
335 "PROXY_SERPS": {
336 "type": "integer",
337 "example": 0
338 }
339 }
340 },
341 "usageTotalUsd": {
342 "type": "number",
343 "example": 0.00005
344 },
345 "usageUsd": {
346 "type": "object",
347 "properties": {
348 "ACTOR_COMPUTE_UNITS": {
349 "type": "integer",
350 "example": 0
351 },
352 "DATASET_READS": {
353 "type": "integer",
354 "example": 0
355 },
356 "DATASET_WRITES": {
357 "type": "integer",
358 "example": 0
359 },
360 "KEY_VALUE_STORE_READS": {
361 "type": "integer",
362 "example": 0
363 },
364 "KEY_VALUE_STORE_WRITES": {
365 "type": "number",
366 "example": 0.00005
367 },
368 "KEY_VALUE_STORE_LISTS": {
369 "type": "integer",
370 "example": 0
371 },
372 "REQUEST_QUEUE_READS": {
373 "type": "integer",
374 "example": 0
375 },
376 "REQUEST_QUEUE_WRITES": {
377 "type": "integer",
378 "example": 0
379 },
380 "DATA_TRANSFER_INTERNAL_GBYTES": {
381 "type": "integer",
382 "example": 0
383 },
384 "DATA_TRANSFER_EXTERNAL_GBYTES": {
385 "type": "integer",
386 "example": 0
387 },
388 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
389 "type": "integer",
390 "example": 0
391 },
392 "PROXY_SERPS": {
393 "type": "integer",
394 "example": 0
395 }
396 }
397 }
398 }
399 }
400 }
401 }
402 }
403 }
404}Query Dataset 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 Query Dataset 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:
