Diff Datasets
Try for free
No credit card required
Go to Store
Diff Datasets
pocesar/diff-datasets
Try for free
No credit card required
Take one dataset on Apify platform, compare it to another, and output the missing ones. This can also be used to output only changed items, using a compound key
Developer
Paulo CesarMaintained by Community
Actor Metrics
1 monthly user
No reviews yet
2 bookmarks
Created in Jun 2020
Modified 2 years ago
Categories
You can access the Diff Datasets 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": "JIlJRETrpgDtyTShO"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/pocesar~diff-datasets/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-pocesar-diff-datasets",
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 "$ref": "#/components/schemas/inputSchema"
27 }
28 }
29 }
30 },
31 "parameters": [
32 {
33 "name": "token",
34 "in": "query",
35 "required": true,
36 "schema": {
37 "type": "string"
38 },
39 "description": "Enter your Apify token here"
40 }
41 ],
42 "responses": {
43 "200": {
44 "description": "OK"
45 }
46 }
47 }
48 },
49 "/acts/pocesar~diff-datasets/runs": {
50 "post": {
51 "operationId": "runs-sync-pocesar-diff-datasets",
52 "x-openai-isConsequential": false,
53 "summary": "Executes an Actor and returns information about the initiated run in response.",
54 "tags": [
55 "Run Actor"
56 ],
57 "requestBody": {
58 "required": true,
59 "content": {
60 "application/json": {
61 "schema": {
62 "$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 "$ref": "#/components/schemas/runsResponseSchema"
85 }
86 }
87 }
88 }
89 }
90 }
91 },
92 "/acts/pocesar~diff-datasets/run-sync": {
93 "post": {
94 "operationId": "run-sync-pocesar-diff-datasets",
95 "x-openai-isConsequential": false,
96 "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
97 "tags": [
98 "Run Actor"
99 ],
100 "requestBody": {
101 "required": true,
102 "content": {
103 "application/json": {
104 "schema": {
105 "$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 "baseDatasetId",
135 "otherDatasetId",
136 "uniqueFields"
137 ],
138 "properties": {
139 "baseDatasetId": {
140 "title": "Base dataset",
141 "type": "string",
142 "description": "This dataset ID that will serve as base and collect the unique items."
143 },
144 "otherDatasetId": {
145 "title": "Other dataset",
146 "type": "string",
147 "description": "Only non-existing items from base will be ouput using this other dataset"
148 },
149 "uniqueFields": {
150 "title": "Data fields",
151 "type": "array",
152 "description": "Unique fields to create a compound key. For example, an unique ID field might not be unique, so you place two fields that make the item itself unique",
153 "default": [],
154 "items": {
155 "type": "string"
156 }
157 },
158 "maxBufferSize": {
159 "title": "Max Buffer size",
160 "type": "integer",
161 "description": "How many items to buffer in memory before outputting it",
162 "default": 20000
163 }
164 }
165 },
166 "runsResponseSchema": {
167 "type": "object",
168 "properties": {
169 "data": {
170 "type": "object",
171 "properties": {
172 "id": {
173 "type": "string"
174 },
175 "actId": {
176 "type": "string"
177 },
178 "userId": {
179 "type": "string"
180 },
181 "startedAt": {
182 "type": "string",
183 "format": "date-time",
184 "example": "2025-01-08T00:00:00.000Z"
185 },
186 "finishedAt": {
187 "type": "string",
188 "format": "date-time",
189 "example": "2025-01-08T00:00:00.000Z"
190 },
191 "status": {
192 "type": "string",
193 "example": "READY"
194 },
195 "meta": {
196 "type": "object",
197 "properties": {
198 "origin": {
199 "type": "string",
200 "example": "API"
201 },
202 "userAgent": {
203 "type": "string"
204 }
205 }
206 },
207 "stats": {
208 "type": "object",
209 "properties": {
210 "inputBodyLen": {
211 "type": "integer",
212 "example": 2000
213 },
214 "rebootCount": {
215 "type": "integer",
216 "example": 0
217 },
218 "restartCount": {
219 "type": "integer",
220 "example": 0
221 },
222 "resurrectCount": {
223 "type": "integer",
224 "example": 0
225 },
226 "computeUnits": {
227 "type": "integer",
228 "example": 0
229 }
230 }
231 },
232 "options": {
233 "type": "object",
234 "properties": {
235 "build": {
236 "type": "string",
237 "example": "latest"
238 },
239 "timeoutSecs": {
240 "type": "integer",
241 "example": 300
242 },
243 "memoryMbytes": {
244 "type": "integer",
245 "example": 1024
246 },
247 "diskMbytes": {
248 "type": "integer",
249 "example": 2048
250 }
251 }
252 },
253 "buildId": {
254 "type": "string"
255 },
256 "defaultKeyValueStoreId": {
257 "type": "string"
258 },
259 "defaultDatasetId": {
260 "type": "string"
261 },
262 "defaultRequestQueueId": {
263 "type": "string"
264 },
265 "buildNumber": {
266 "type": "string",
267 "example": "1.0.0"
268 },
269 "containerUrl": {
270 "type": "string"
271 },
272 "usage": {
273 "type": "object",
274 "properties": {
275 "ACTOR_COMPUTE_UNITS": {
276 "type": "integer",
277 "example": 0
278 },
279 "DATASET_READS": {
280 "type": "integer",
281 "example": 0
282 },
283 "DATASET_WRITES": {
284 "type": "integer",
285 "example": 0
286 },
287 "KEY_VALUE_STORE_READS": {
288 "type": "integer",
289 "example": 0
290 },
291 "KEY_VALUE_STORE_WRITES": {
292 "type": "integer",
293 "example": 1
294 },
295 "KEY_VALUE_STORE_LISTS": {
296 "type": "integer",
297 "example": 0
298 },
299 "REQUEST_QUEUE_READS": {
300 "type": "integer",
301 "example": 0
302 },
303 "REQUEST_QUEUE_WRITES": {
304 "type": "integer",
305 "example": 0
306 },
307 "DATA_TRANSFER_INTERNAL_GBYTES": {
308 "type": "integer",
309 "example": 0
310 },
311 "DATA_TRANSFER_EXTERNAL_GBYTES": {
312 "type": "integer",
313 "example": 0
314 },
315 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
316 "type": "integer",
317 "example": 0
318 },
319 "PROXY_SERPS": {
320 "type": "integer",
321 "example": 0
322 }
323 }
324 },
325 "usageTotalUsd": {
326 "type": "number",
327 "example": 0.00005
328 },
329 "usageUsd": {
330 "type": "object",
331 "properties": {
332 "ACTOR_COMPUTE_UNITS": {
333 "type": "integer",
334 "example": 0
335 },
336 "DATASET_READS": {
337 "type": "integer",
338 "example": 0
339 },
340 "DATASET_WRITES": {
341 "type": "integer",
342 "example": 0
343 },
344 "KEY_VALUE_STORE_READS": {
345 "type": "integer",
346 "example": 0
347 },
348 "KEY_VALUE_STORE_WRITES": {
349 "type": "number",
350 "example": 0.00005
351 },
352 "KEY_VALUE_STORE_LISTS": {
353 "type": "integer",
354 "example": 0
355 },
356 "REQUEST_QUEUE_READS": {
357 "type": "integer",
358 "example": 0
359 },
360 "REQUEST_QUEUE_WRITES": {
361 "type": "integer",
362 "example": 0
363 },
364 "DATA_TRANSFER_INTERNAL_GBYTES": {
365 "type": "integer",
366 "example": 0
367 },
368 "DATA_TRANSFER_EXTERNAL_GBYTES": {
369 "type": "integer",
370 "example": 0
371 },
372 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
373 "type": "integer",
374 "example": 0
375 },
376 "PROXY_SERPS": {
377 "type": "integer",
378 "example": 0
379 }
380 }
381 }
382 }
383 }
384 }
385 }
386 }
387 }
388}Diff Datasets 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 Diff Datasets 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:
