LLM Dataset Processor
Try for free
No credit card required
Go to Store
LLM Dataset Processor
dusan.vystrcil/llm-dataset-processor
Try for free
No credit card required
Allows you to process output of other actors or stored dataset with single LLM prompt. It's useful if you need to enrich data, summarize content, extract specific information, or manipulate data in a structured way using AI.
You can access the LLM Dataset Processor 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": "8o87PTyWkQusnPAfF"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/dusan.vystrcil~llm-dataset-processor/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-dusan.vystrcil-llm-dataset-processor",
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 "$ref": "#/components/schemas/inputSchema"
27 }
28 }
29 }
30 },
31 "parameters": [
32 {
33 "name": "token",
34 "in": "query",
35 "required": true,
36 "schema": {
37 "type": "string"
38 },
39 "description": "Enter your Apify token here"
40 }
41 ],
42 "responses": {
43 "200": {
44 "description": "OK"
45 }
46 }
47 }
48 },
49 "/acts/dusan.vystrcil~llm-dataset-processor/runs": {
50 "post": {
51 "operationId": "runs-sync-dusan.vystrcil-llm-dataset-processor",
52 "x-openai-isConsequential": false,
53 "summary": "Executes an Actor and returns information about the initiated run in response.",
54 "tags": [
55 "Run Actor"
56 ],
57 "requestBody": {
58 "required": true,
59 "content": {
60 "application/json": {
61 "schema": {
62 "$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 "$ref": "#/components/schemas/runsResponseSchema"
85 }
86 }
87 }
88 }
89 }
90 }
91 },
92 "/acts/dusan.vystrcil~llm-dataset-processor/run-sync": {
93 "post": {
94 "operationId": "run-sync-dusan.vystrcil-llm-dataset-processor",
95 "x-openai-isConsequential": false,
96 "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
97 "tags": [
98 "Run Actor"
99 ],
100 "requestBody": {
101 "required": true,
102 "content": {
103 "application/json": {
104 "schema": {
105 "$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 "llmProviderApiKey",
135 "prompt",
136 "model",
137 "temperature",
138 "maxTokens"
139 ],
140 "properties": {
141 "inputDatasetId": {
142 "title": "Input Dataset ID",
143 "type": "string",
144 "description": "The ID of the dataset to process."
145 },
146 "model": {
147 "title": "Large Language Model",
148 "enum": [
149 "gpt-4o-mini",
150 "gpt-4o",
151 "claude-3-5-haiku-latest",
152 "claude-3-5-sonnet-latest",
153 "claude-3-opus-latest",
154 "gemini-1.5-flash",
155 "gemini-1.5-flash-8b",
156 "gemini-1.5-pro"
157 ],
158 "type": "string",
159 "description": "The LLM to use for processing. Each model has different capabilities and pricing. GPT-4o-mini and Claude 3.5 Haiku are recommended for cost-effective processing, while models like Claude 3 Opus or GPT-4o offer higher quality but at a higher cost."
160 },
161 "llmProviderApiKey": {
162 "title": "LLM Provider API Key",
163 "type": "string",
164 "description": "Your API key for the LLM Provider (e.g., OpenAI)."
165 },
166 "temperature": {
167 "title": "Temperature",
168 "type": "string",
169 "description": "Sampling temperature for the LLM API (controls randomness). We recommend using a value closer to 0 for exact results. In case of more 'creative' results, we recommend to use a value closer to 1.",
170 "default": "0.1"
171 },
172 "multipleColumns": {
173 "title": "Multiple columns in output",
174 "type": "boolean",
175 "description": "When enabled, instructs the LLM to return responses as JSON objects, creating multiple columns in the output dataset. The columns need to be named and described in the prompt. If disabled, responses are stored in a single `llmresponse` column.",
176 "default": false
177 },
178 "prompt": {
179 "title": "Prompt Template",
180 "minLength": 1,
181 "type": "string",
182 "description": "The prompt template to use for processing. You can use ${fieldName} placeholders to reference fields from the input dataset."
183 },
184 "skipItemIfEmpty": {
185 "title": "Skip item if one or more ${fields} are empty",
186 "type": "boolean",
187 "description": "When enabled, items will be skipped if any ${field} referenced in the prompt is empty, null, undefined, or contains only whitespace. This helps prevent processing incomplete data.",
188 "default": true
189 },
190 "maxTokens": {
191 "title": "Max Tokens",
192 "type": "integer",
193 "description": "Maximum number of tokens in the LLM API response for each item.",
194 "default": 300
195 },
196 "testPrompt": {
197 "title": "Test Prompt Mode",
198 "type": "boolean",
199 "description": "Test mode that processes only a limited number of items (defined by `testItemsCount`). Use this to validate your prompt and configuration before running on the full dataset. We highly recommend enabling this option first to validate your prompt because of ambiguity of the LLM responses.",
200 "default": true
201 },
202 "testItemsCount": {
203 "title": "Test Items Count",
204 "minimum": 1,
205 "type": "integer",
206 "description": "Number of items to process when `Test Prompt Mode` is enabled.",
207 "default": 3
208 }
209 }
210 },
211 "runsResponseSchema": {
212 "type": "object",
213 "properties": {
214 "data": {
215 "type": "object",
216 "properties": {
217 "id": {
218 "type": "string"
219 },
220 "actId": {
221 "type": "string"
222 },
223 "userId": {
224 "type": "string"
225 },
226 "startedAt": {
227 "type": "string",
228 "format": "date-time",
229 "example": "2025-01-08T00:00:00.000Z"
230 },
231 "finishedAt": {
232 "type": "string",
233 "format": "date-time",
234 "example": "2025-01-08T00:00:00.000Z"
235 },
236 "status": {
237 "type": "string",
238 "example": "READY"
239 },
240 "meta": {
241 "type": "object",
242 "properties": {
243 "origin": {
244 "type": "string",
245 "example": "API"
246 },
247 "userAgent": {
248 "type": "string"
249 }
250 }
251 },
252 "stats": {
253 "type": "object",
254 "properties": {
255 "inputBodyLen": {
256 "type": "integer",
257 "example": 2000
258 },
259 "rebootCount": {
260 "type": "integer",
261 "example": 0
262 },
263 "restartCount": {
264 "type": "integer",
265 "example": 0
266 },
267 "resurrectCount": {
268 "type": "integer",
269 "example": 0
270 },
271 "computeUnits": {
272 "type": "integer",
273 "example": 0
274 }
275 }
276 },
277 "options": {
278 "type": "object",
279 "properties": {
280 "build": {
281 "type": "string",
282 "example": "latest"
283 },
284 "timeoutSecs": {
285 "type": "integer",
286 "example": 300
287 },
288 "memoryMbytes": {
289 "type": "integer",
290 "example": 1024
291 },
292 "diskMbytes": {
293 "type": "integer",
294 "example": 2048
295 }
296 }
297 },
298 "buildId": {
299 "type": "string"
300 },
301 "defaultKeyValueStoreId": {
302 "type": "string"
303 },
304 "defaultDatasetId": {
305 "type": "string"
306 },
307 "defaultRequestQueueId": {
308 "type": "string"
309 },
310 "buildNumber": {
311 "type": "string",
312 "example": "1.0.0"
313 },
314 "containerUrl": {
315 "type": "string"
316 },
317 "usage": {
318 "type": "object",
319 "properties": {
320 "ACTOR_COMPUTE_UNITS": {
321 "type": "integer",
322 "example": 0
323 },
324 "DATASET_READS": {
325 "type": "integer",
326 "example": 0
327 },
328 "DATASET_WRITES": {
329 "type": "integer",
330 "example": 0
331 },
332 "KEY_VALUE_STORE_READS": {
333 "type": "integer",
334 "example": 0
335 },
336 "KEY_VALUE_STORE_WRITES": {
337 "type": "integer",
338 "example": 1
339 },
340 "KEY_VALUE_STORE_LISTS": {
341 "type": "integer",
342 "example": 0
343 },
344 "REQUEST_QUEUE_READS": {
345 "type": "integer",
346 "example": 0
347 },
348 "REQUEST_QUEUE_WRITES": {
349 "type": "integer",
350 "example": 0
351 },
352 "DATA_TRANSFER_INTERNAL_GBYTES": {
353 "type": "integer",
354 "example": 0
355 },
356 "DATA_TRANSFER_EXTERNAL_GBYTES": {
357 "type": "integer",
358 "example": 0
359 },
360 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
361 "type": "integer",
362 "example": 0
363 },
364 "PROXY_SERPS": {
365 "type": "integer",
366 "example": 0
367 }
368 }
369 },
370 "usageTotalUsd": {
371 "type": "number",
372 "example": 0.00005
373 },
374 "usageUsd": {
375 "type": "object",
376 "properties": {
377 "ACTOR_COMPUTE_UNITS": {
378 "type": "integer",
379 "example": 0
380 },
381 "DATASET_READS": {
382 "type": "integer",
383 "example": 0
384 },
385 "DATASET_WRITES": {
386 "type": "integer",
387 "example": 0
388 },
389 "KEY_VALUE_STORE_READS": {
390 "type": "integer",
391 "example": 0
392 },
393 "KEY_VALUE_STORE_WRITES": {
394 "type": "number",
395 "example": 0.00005
396 },
397 "KEY_VALUE_STORE_LISTS": {
398 "type": "integer",
399 "example": 0
400 },
401 "REQUEST_QUEUE_READS": {
402 "type": "integer",
403 "example": 0
404 },
405 "REQUEST_QUEUE_WRITES": {
406 "type": "integer",
407 "example": 0
408 },
409 "DATA_TRANSFER_INTERNAL_GBYTES": {
410 "type": "integer",
411 "example": 0
412 },
413 "DATA_TRANSFER_EXTERNAL_GBYTES": {
414 "type": "integer",
415 "example": 0
416 },
417 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
418 "type": "integer",
419 "example": 0
420 },
421 "PROXY_SERPS": {
422 "type": "integer",
423 "example": 0
424 }
425 }
426 }
427 }
428 }
429 }
430 }
431 }
432 }
433}LLM Dataset Processor 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 LLM Dataset Processor 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
Dušan VystrčilMaintained by Community
Actor Metrics
9 monthly users
-
2 bookmarks
84% runs succeeded
Created in Dec 2024
Modified a month ago
Categories
