Dataset to HuggingFace
Try for free
3 days trial then $5.00/month - No credit card required now
Go to Store
Dataset to HuggingFace
flamboyant_leaf/datasettohuggingface
Try for free
3 days trial then $5.00/month - No credit card required now
Transfers data from Apify datasets to Hugging Face datasets. Bridges web scraping with ML platforms, enabling access to pre-trained models and collaborative tools. Customize transfer limits, streamline ML workflows, and leverage data versioning. Ideal for data scientists and ML researchers.
You can access the Dataset to HuggingFace programmatically from your own applications by using the Apify API. You can choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
1{
2 "openapi": "3.0.1",
3 "info": {
4 "version": "0.0",
5 "x-build-id": "lNnpxRX1ECQ5CrTED"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/flamboyant_leaf~datasettohuggingface/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-flamboyant_leaf-datasettohuggingface",
16 "x-openai-isConsequential": false,
17 "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
18 "tags": [
19 "Run Actor"
20 ],
21 "requestBody": {
22 "required": true,
23 "content": {
24 "application/json": {
25 "schema": {
26 "$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/flamboyant_leaf~datasettohuggingface/runs": {
50 "post": {
51 "operationId": "runs-sync-flamboyant_leaf-datasettohuggingface",
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/flamboyant_leaf~datasettohuggingface/run-sync": {
93 "post": {
94 "operationId": "run-sync-flamboyant_leaf-datasettohuggingface",
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 "apifyDatasetId",
135 "huggingFaceDatasetName",
136 "huggingFaceToken"
137 ],
138 "properties": {
139 "apifyDatasetId": {
140 "title": "Apify Dataset ID",
141 "type": "string",
142 "description": "The ID of the Apify dataset to read from. The dataset can be found here https://console.apify.com/storage/datasets"
143 },
144 "huggingFaceDatasetName": {
145 "title": "Hugging Face Dataset Name, e.g. your_username/your_dataset",
146 "type": "string",
147 "description": "The name of the Hugging Face dataset to push to, e.g. your_username/your_dataset"
148 },
149 "huggingFaceToken": {
150 "title": "Hugging Face API Token",
151 "type": "string",
152 "description": "Your Hugging Face API token for authentication, e.g. hf_xxxxxxxxxxxxxxxxxxxxxxxx"
153 },
154 "maxItems": {
155 "title": "Max Items",
156 "minimum": 0,
157 "type": "integer",
158 "description": "Maximum number of items to transfer (0 for all items)",
159 "default": 10
160 }
161 }
162 },
163 "runsResponseSchema": {
164 "type": "object",
165 "properties": {
166 "data": {
167 "type": "object",
168 "properties": {
169 "id": {
170 "type": "string"
171 },
172 "actId": {
173 "type": "string"
174 },
175 "userId": {
176 "type": "string"
177 },
178 "startedAt": {
179 "type": "string",
180 "format": "date-time",
181 "example": "2025-01-08T00:00:00.000Z"
182 },
183 "finishedAt": {
184 "type": "string",
185 "format": "date-time",
186 "example": "2025-01-08T00:00:00.000Z"
187 },
188 "status": {
189 "type": "string",
190 "example": "READY"
191 },
192 "meta": {
193 "type": "object",
194 "properties": {
195 "origin": {
196 "type": "string",
197 "example": "API"
198 },
199 "userAgent": {
200 "type": "string"
201 }
202 }
203 },
204 "stats": {
205 "type": "object",
206 "properties": {
207 "inputBodyLen": {
208 "type": "integer",
209 "example": 2000
210 },
211 "rebootCount": {
212 "type": "integer",
213 "example": 0
214 },
215 "restartCount": {
216 "type": "integer",
217 "example": 0
218 },
219 "resurrectCount": {
220 "type": "integer",
221 "example": 0
222 },
223 "computeUnits": {
224 "type": "integer",
225 "example": 0
226 }
227 }
228 },
229 "options": {
230 "type": "object",
231 "properties": {
232 "build": {
233 "type": "string",
234 "example": "latest"
235 },
236 "timeoutSecs": {
237 "type": "integer",
238 "example": 300
239 },
240 "memoryMbytes": {
241 "type": "integer",
242 "example": 1024
243 },
244 "diskMbytes": {
245 "type": "integer",
246 "example": 2048
247 }
248 }
249 },
250 "buildId": {
251 "type": "string"
252 },
253 "defaultKeyValueStoreId": {
254 "type": "string"
255 },
256 "defaultDatasetId": {
257 "type": "string"
258 },
259 "defaultRequestQueueId": {
260 "type": "string"
261 },
262 "buildNumber": {
263 "type": "string",
264 "example": "1.0.0"
265 },
266 "containerUrl": {
267 "type": "string"
268 },
269 "usage": {
270 "type": "object",
271 "properties": {
272 "ACTOR_COMPUTE_UNITS": {
273 "type": "integer",
274 "example": 0
275 },
276 "DATASET_READS": {
277 "type": "integer",
278 "example": 0
279 },
280 "DATASET_WRITES": {
281 "type": "integer",
282 "example": 0
283 },
284 "KEY_VALUE_STORE_READS": {
285 "type": "integer",
286 "example": 0
287 },
288 "KEY_VALUE_STORE_WRITES": {
289 "type": "integer",
290 "example": 1
291 },
292 "KEY_VALUE_STORE_LISTS": {
293 "type": "integer",
294 "example": 0
295 },
296 "REQUEST_QUEUE_READS": {
297 "type": "integer",
298 "example": 0
299 },
300 "REQUEST_QUEUE_WRITES": {
301 "type": "integer",
302 "example": 0
303 },
304 "DATA_TRANSFER_INTERNAL_GBYTES": {
305 "type": "integer",
306 "example": 0
307 },
308 "DATA_TRANSFER_EXTERNAL_GBYTES": {
309 "type": "integer",
310 "example": 0
311 },
312 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
313 "type": "integer",
314 "example": 0
315 },
316 "PROXY_SERPS": {
317 "type": "integer",
318 "example": 0
319 }
320 }
321 },
322 "usageTotalUsd": {
323 "type": "number",
324 "example": 0.00005
325 },
326 "usageUsd": {
327 "type": "object",
328 "properties": {
329 "ACTOR_COMPUTE_UNITS": {
330 "type": "integer",
331 "example": 0
332 },
333 "DATASET_READS": {
334 "type": "integer",
335 "example": 0
336 },
337 "DATASET_WRITES": {
338 "type": "integer",
339 "example": 0
340 },
341 "KEY_VALUE_STORE_READS": {
342 "type": "integer",
343 "example": 0
344 },
345 "KEY_VALUE_STORE_WRITES": {
346 "type": "number",
347 "example": 0.00005
348 },
349 "KEY_VALUE_STORE_LISTS": {
350 "type": "integer",
351 "example": 0
352 },
353 "REQUEST_QUEUE_READS": {
354 "type": "integer",
355 "example": 0
356 },
357 "REQUEST_QUEUE_WRITES": {
358 "type": "integer",
359 "example": 0
360 },
361 "DATA_TRANSFER_INTERNAL_GBYTES": {
362 "type": "integer",
363 "example": 0
364 },
365 "DATA_TRANSFER_EXTERNAL_GBYTES": {
366 "type": "integer",
367 "example": 0
368 },
369 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
370 "type": "integer",
371 "example": 0
372 },
373 "PROXY_SERPS": {
374 "type": "integer",
375 "example": 0
376 }
377 }
378 }
379 }
380 }
381 }
382 }
383 }
384 }
385}Dataset to HuggingFace 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 to HuggingFace 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
AIRabbitMaintained by Community
Actor Metrics
1 monthly user
-
1 bookmark
>99% runs succeeded
Created in Aug 2024
Modified 5 months ago
Categories
