
Markdown Header Text Splitter
2 hours trial then $20.00/month - No credit card required now

Markdown Header Text Splitter
2 hours trial then $20.00/month - No credit card required now
Split Markdown into structured chunks using header hierarchy. Built with LangChain, it preserves metadata for RAG, documentation, and analysis. Configure headers, strip content, and integrate with vector databases. Ideal for AI workflows.
Actor Metrics
2 monthly users
No reviews yet
No bookmarks yet
>99% runs succeeded
Created in Mar 2025
Modified 3 days ago
You can access the Markdown Header Text Splitter programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
1{
2 "openapi": "3.0.1",
3 "info": {
4 "version": "1.0",
5 "x-build-id": "5YJjqQg4erNExM192"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/codepoetry~markdown-splitter/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-codepoetry-markdown-splitter",
16 "x-openai-isConsequential": false,
17 "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
18 "tags": [
19 "Run Actor"
20 ],
21 "requestBody": {
22 "required": true,
23 "content": {
24 "application/json": {
25 "schema": {
26 "$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/codepoetry~markdown-splitter/runs": {
50 "post": {
51 "operationId": "runs-sync-codepoetry-markdown-splitter",
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/codepoetry~markdown-splitter/run-sync": {
93 "post": {
94 "operationId": "run-sync-codepoetry-markdown-splitter",
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 "markdown_text"
135 ],
136 "properties": {
137 "markdown_text": {
138 "title": "Markdown Text",
139 "type": "string",
140 "description": "The Markdown content to process",
141 "default": "# Header 1\nHello, World!\n## Header 2\nGoodbye, World!"
142 },
143 "headers_to_split_on": {
144 "title": "Headers to Split On",
145 "type": "array",
146 "description": "Header levels (e.g., ['#', '##'])",
147 "default": [
148 "#",
149 "##",
150 "###",
151 "####",
152 "#####",
153 "######"
154 ],
155 "items": {
156 "type": "string"
157 }
158 },
159 "strip_headers": {
160 "title": "Strip Headers",
161 "type": "boolean",
162 "description": "Remove headers from chunk content",
163 "default": true
164 }
165 }
166 },
167 "runsResponseSchema": {
168 "type": "object",
169 "properties": {
170 "data": {
171 "type": "object",
172 "properties": {
173 "id": {
174 "type": "string"
175 },
176 "actId": {
177 "type": "string"
178 },
179 "userId": {
180 "type": "string"
181 },
182 "startedAt": {
183 "type": "string",
184 "format": "date-time",
185 "example": "2025-01-08T00:00:00.000Z"
186 },
187 "finishedAt": {
188 "type": "string",
189 "format": "date-time",
190 "example": "2025-01-08T00:00:00.000Z"
191 },
192 "status": {
193 "type": "string",
194 "example": "READY"
195 },
196 "meta": {
197 "type": "object",
198 "properties": {
199 "origin": {
200 "type": "string",
201 "example": "API"
202 },
203 "userAgent": {
204 "type": "string"
205 }
206 }
207 },
208 "stats": {
209 "type": "object",
210 "properties": {
211 "inputBodyLen": {
212 "type": "integer",
213 "example": 2000
214 },
215 "rebootCount": {
216 "type": "integer",
217 "example": 0
218 },
219 "restartCount": {
220 "type": "integer",
221 "example": 0
222 },
223 "resurrectCount": {
224 "type": "integer",
225 "example": 0
226 },
227 "computeUnits": {
228 "type": "integer",
229 "example": 0
230 }
231 }
232 },
233 "options": {
234 "type": "object",
235 "properties": {
236 "build": {
237 "type": "string",
238 "example": "latest"
239 },
240 "timeoutSecs": {
241 "type": "integer",
242 "example": 300
243 },
244 "memoryMbytes": {
245 "type": "integer",
246 "example": 1024
247 },
248 "diskMbytes": {
249 "type": "integer",
250 "example": 2048
251 }
252 }
253 },
254 "buildId": {
255 "type": "string"
256 },
257 "defaultKeyValueStoreId": {
258 "type": "string"
259 },
260 "defaultDatasetId": {
261 "type": "string"
262 },
263 "defaultRequestQueueId": {
264 "type": "string"
265 },
266 "buildNumber": {
267 "type": "string",
268 "example": "1.0.0"
269 },
270 "containerUrl": {
271 "type": "string"
272 },
273 "usage": {
274 "type": "object",
275 "properties": {
276 "ACTOR_COMPUTE_UNITS": {
277 "type": "integer",
278 "example": 0
279 },
280 "DATASET_READS": {
281 "type": "integer",
282 "example": 0
283 },
284 "DATASET_WRITES": {
285 "type": "integer",
286 "example": 0
287 },
288 "KEY_VALUE_STORE_READS": {
289 "type": "integer",
290 "example": 0
291 },
292 "KEY_VALUE_STORE_WRITES": {
293 "type": "integer",
294 "example": 1
295 },
296 "KEY_VALUE_STORE_LISTS": {
297 "type": "integer",
298 "example": 0
299 },
300 "REQUEST_QUEUE_READS": {
301 "type": "integer",
302 "example": 0
303 },
304 "REQUEST_QUEUE_WRITES": {
305 "type": "integer",
306 "example": 0
307 },
308 "DATA_TRANSFER_INTERNAL_GBYTES": {
309 "type": "integer",
310 "example": 0
311 },
312 "DATA_TRANSFER_EXTERNAL_GBYTES": {
313 "type": "integer",
314 "example": 0
315 },
316 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
317 "type": "integer",
318 "example": 0
319 },
320 "PROXY_SERPS": {
321 "type": "integer",
322 "example": 0
323 }
324 }
325 },
326 "usageTotalUsd": {
327 "type": "number",
328 "example": 0.00005
329 },
330 "usageUsd": {
331 "type": "object",
332 "properties": {
333 "ACTOR_COMPUTE_UNITS": {
334 "type": "integer",
335 "example": 0
336 },
337 "DATASET_READS": {
338 "type": "integer",
339 "example": 0
340 },
341 "DATASET_WRITES": {
342 "type": "integer",
343 "example": 0
344 },
345 "KEY_VALUE_STORE_READS": {
346 "type": "integer",
347 "example": 0
348 },
349 "KEY_VALUE_STORE_WRITES": {
350 "type": "number",
351 "example": 0.00005
352 },
353 "KEY_VALUE_STORE_LISTS": {
354 "type": "integer",
355 "example": 0
356 },
357 "REQUEST_QUEUE_READS": {
358 "type": "integer",
359 "example": 0
360 },
361 "REQUEST_QUEUE_WRITES": {
362 "type": "integer",
363 "example": 0
364 },
365 "DATA_TRANSFER_INTERNAL_GBYTES": {
366 "type": "integer",
367 "example": 0
368 },
369 "DATA_TRANSFER_EXTERNAL_GBYTES": {
370 "type": "integer",
371 "example": 0
372 },
373 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
374 "type": "integer",
375 "example": 0
376 },
377 "PROXY_SERPS": {
378 "type": "integer",
379 "example": 0
380 }
381 }
382 }
383 }
384 }
385 }
386 }
387 }
388 }
389}
Markdown Header Text Splitter 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 Markdown Header Text Splitter 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: