Dataset query engine
Try for free
No credit card required
Go to Store
Dataset query engine
jiri.spilka/dataset-query-engine
Try for free
No credit card required
Use natural language queries to retrieve results from an Apify dataset. This Actor provides a query engine that loads a dataset, executes SQL queries, and synthesizes results.
You can access the Dataset query engine programmatically from your own applications by using the Apify API. You can 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": "tFe4yglncZGViMTWK"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/jiri.spilka~dataset-query-engine/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-jiri.spilka-dataset-query-engine",
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 "$ref": "#/components/schemas/inputSchema"
27 }
28 }
29 }
30 },
31 "parameters": [
32 {
33 "name": "token",
34 "in": "query",
35 "required": true,
36 "schema": {
37 "type": "string"
38 },
39 "description": "Enter your Apify token here"
40 }
41 ],
42 "responses": {
43 "200": {
44 "description": "OK"
45 }
46 }
47 }
48 },
49 "/acts/jiri.spilka~dataset-query-engine/runs": {
50 "post": {
51 "operationId": "runs-sync-jiri.spilka-dataset-query-engine",
52 "x-openai-isConsequential": false,
53 "summary": "Executes an Actor and returns information about the initiated run in response.",
54 "tags": [
55 "Run Actor"
56 ],
57 "requestBody": {
58 "required": true,
59 "content": {
60 "application/json": {
61 "schema": {
62 "$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 "$ref": "#/components/schemas/runsResponseSchema"
85 }
86 }
87 }
88 }
89 }
90 }
91 },
92 "/acts/jiri.spilka~dataset-query-engine/run-sync": {
93 "post": {
94 "operationId": "run-sync-jiri.spilka-dataset-query-engine",
95 "x-openai-isConsequential": false,
96 "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
97 "tags": [
98 "Run Actor"
99 ],
100 "requestBody": {
101 "required": true,
102 "content": {
103 "application/json": {
104 "schema": {
105 "$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 "query",
135 "datasetId",
136 "llmProviderApiKey"
137 ],
138 "properties": {
139 "query": {
140 "title": "Text or SQL query",
141 "type": "string",
142 "description": "Provide a query to specify the data to be retrieved from a dataset. The query can be in natural language or SQL format. For SQL, use the table name 'dataset'.\n\nExamples (when your dataset contains data scraped from Google Maps):\n- Find restaurant names with reviews above 4 and with at least 100 reviews.\n- SELECT title, totalScore, reviewsCount FROM dataset;"
143 },
144 "datasetId": {
145 "title": "Dataset ID",
146 "type": "string",
147 "description": "Dataset ID to retrieve data from."
148 },
149 "modelName": {
150 "title": "OpenAI model (OpenAI is the only supported provider now)",
151 "enum": [
152 "gpt-4o-mini",
153 "gpt-4o",
154 "o1",
155 "o1-mini",
156 "o3-mini"
157 ],
158 "type": "string",
159 "description": "Specify the LLM for SQL generation and query synthesis. Currently supports OpenAI models with varying capabilities and performance characteristics.",
160 "default": "gpt-4o-mini"
161 },
162 "llmProviderApiKey": {
163 "title": "LLM Provider API key (OpenAI is the only supported provider now)",
164 "type": "string",
165 "description": "API key for accessing a Large Language Model."
166 },
167 "refreshDataset": {
168 "title": "Refresh dataset",
169 "type": "boolean",
170 "description": "In standby mode, the dataset is loaded once and reused to optimize performance. This parameter allows reloading the dataset to ensure updated data is available.",
171 "default": false
172 },
173 "limit": {
174 "title": "Limit number of dataset items used for query",
175 "type": "integer",
176 "description": "Maximum number of items to return. By default, there is no limit."
177 },
178 "offset": {
179 "title": "Number of items to skip from the start",
180 "type": "integer",
181 "description": "Number of items that should be skipped at the start. The default value is 0.",
182 "default": 0
183 },
184 "useAgent": {
185 "title": "Use AI Agent",
186 "type": "boolean",
187 "description": "When enabled, an AI Agent is used over a deterministic workflow. When to use an AI Agent? The agent can solve a broader range of tasks but can also be less reliable.",
188 "default": true
189 }
190 }
191 },
192 "runsResponseSchema": {
193 "type": "object",
194 "properties": {
195 "data": {
196 "type": "object",
197 "properties": {
198 "id": {
199 "type": "string"
200 },
201 "actId": {
202 "type": "string"
203 },
204 "userId": {
205 "type": "string"
206 },
207 "startedAt": {
208 "type": "string",
209 "format": "date-time",
210 "example": "2025-01-08T00:00:00.000Z"
211 },
212 "finishedAt": {
213 "type": "string",
214 "format": "date-time",
215 "example": "2025-01-08T00:00:00.000Z"
216 },
217 "status": {
218 "type": "string",
219 "example": "READY"
220 },
221 "meta": {
222 "type": "object",
223 "properties": {
224 "origin": {
225 "type": "string",
226 "example": "API"
227 },
228 "userAgent": {
229 "type": "string"
230 }
231 }
232 },
233 "stats": {
234 "type": "object",
235 "properties": {
236 "inputBodyLen": {
237 "type": "integer",
238 "example": 2000
239 },
240 "rebootCount": {
241 "type": "integer",
242 "example": 0
243 },
244 "restartCount": {
245 "type": "integer",
246 "example": 0
247 },
248 "resurrectCount": {
249 "type": "integer",
250 "example": 0
251 },
252 "computeUnits": {
253 "type": "integer",
254 "example": 0
255 }
256 }
257 },
258 "options": {
259 "type": "object",
260 "properties": {
261 "build": {
262 "type": "string",
263 "example": "latest"
264 },
265 "timeoutSecs": {
266 "type": "integer",
267 "example": 300
268 },
269 "memoryMbytes": {
270 "type": "integer",
271 "example": 1024
272 },
273 "diskMbytes": {
274 "type": "integer",
275 "example": 2048
276 }
277 }
278 },
279 "buildId": {
280 "type": "string"
281 },
282 "defaultKeyValueStoreId": {
283 "type": "string"
284 },
285 "defaultDatasetId": {
286 "type": "string"
287 },
288 "defaultRequestQueueId": {
289 "type": "string"
290 },
291 "buildNumber": {
292 "type": "string",
293 "example": "1.0.0"
294 },
295 "containerUrl": {
296 "type": "string"
297 },
298 "usage": {
299 "type": "object",
300 "properties": {
301 "ACTOR_COMPUTE_UNITS": {
302 "type": "integer",
303 "example": 0
304 },
305 "DATASET_READS": {
306 "type": "integer",
307 "example": 0
308 },
309 "DATASET_WRITES": {
310 "type": "integer",
311 "example": 0
312 },
313 "KEY_VALUE_STORE_READS": {
314 "type": "integer",
315 "example": 0
316 },
317 "KEY_VALUE_STORE_WRITES": {
318 "type": "integer",
319 "example": 1
320 },
321 "KEY_VALUE_STORE_LISTS": {
322 "type": "integer",
323 "example": 0
324 },
325 "REQUEST_QUEUE_READS": {
326 "type": "integer",
327 "example": 0
328 },
329 "REQUEST_QUEUE_WRITES": {
330 "type": "integer",
331 "example": 0
332 },
333 "DATA_TRANSFER_INTERNAL_GBYTES": {
334 "type": "integer",
335 "example": 0
336 },
337 "DATA_TRANSFER_EXTERNAL_GBYTES": {
338 "type": "integer",
339 "example": 0
340 },
341 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
342 "type": "integer",
343 "example": 0
344 },
345 "PROXY_SERPS": {
346 "type": "integer",
347 "example": 0
348 }
349 }
350 },
351 "usageTotalUsd": {
352 "type": "number",
353 "example": 0.00005
354 },
355 "usageUsd": {
356 "type": "object",
357 "properties": {
358 "ACTOR_COMPUTE_UNITS": {
359 "type": "integer",
360 "example": 0
361 },
362 "DATASET_READS": {
363 "type": "integer",
364 "example": 0
365 },
366 "DATASET_WRITES": {
367 "type": "integer",
368 "example": 0
369 },
370 "KEY_VALUE_STORE_READS": {
371 "type": "integer",
372 "example": 0
373 },
374 "KEY_VALUE_STORE_WRITES": {
375 "type": "number",
376 "example": 0.00005
377 },
378 "KEY_VALUE_STORE_LISTS": {
379 "type": "integer",
380 "example": 0
381 },
382 "REQUEST_QUEUE_READS": {
383 "type": "integer",
384 "example": 0
385 },
386 "REQUEST_QUEUE_WRITES": {
387 "type": "integer",
388 "example": 0
389 },
390 "DATA_TRANSFER_INTERNAL_GBYTES": {
391 "type": "integer",
392 "example": 0
393 },
394 "DATA_TRANSFER_EXTERNAL_GBYTES": {
395 "type": "integer",
396 "example": 0
397 },
398 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
399 "type": "integer",
400 "example": 0
401 },
402 "PROXY_SERPS": {
403 "type": "integer",
404 "example": 0
405 }
406 }
407 }
408 }
409 }
410 }
411 }
412 }
413 }
414}Dataset query engine 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 query engine 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:
Developer
Jiří Spilka Maintained by Apify
Actor Metrics
0 monthly users
-
0 No stars yet
Created in Feb 2025
Modified a day ago
Categories
