# Markdown Chunker for RAG - Heading-Aware Text Splitter (`tidybytetools/markdown-rag-chunker`) Actor

Split Markdown into chunks for RAG, vector databases and AI search. Keeps code blocks and tables whole. Each chunk has its heading path and line numbers. $0.0001 per chunk.

- **URL**: https://apify.com/tidybytetools/markdown-rag-chunker.md
- **Developed by:** [Tidy Byte Tools](https://apify.com/tidybytetools) (community)
- **Security:** Limited permissions
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $0.10 / 1,000 chunk createds

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## Markdown Chunker for RAG - Heading-Aware Text Splitter

Split Markdown into chunks for RAG, vector databases and AI search. Keeps code blocks and tables whole. Each chunk has its heading path and line numbers. $0.0001 per chunk.

### What it does

- Splits by headings first, so each chunk stays on one topic.
- Never cuts a code block or table in the middle when it fits.
- Gives each chunk an id, heading path, anchor and line numbers.
- Optional overlap between chunks.
- Ready for vector databases (one chunk per dataset row).

### Price

You pay **$0.0001** per chunk created (One chunk saved to the dataset.) There is no start fee from us. Apify adds its normal small platform cost.
Set a max cost for the run and we stop there. We never charge for work we did not save.

### How to use

1. Add links or paste your data.
2. Click **Start**.
3. Get results in the **Output** tab, or download them as CSV, Excel or JSON.

### Input

- **Markdown file links**: Links to .md files (raw GitHub links work).
- **Or paste Markdown**: Paste Markdown here.
- **Max characters per chunk**: Chunks are never longer than this.
- **Overlap characters**: Repeat this many characters from the last chunk. Up to half of max.
- **Put heading path at the top of each chunk**: Adds 'Guide > Install' above the text. Helps search.

### Good to know

- Files up to 50 MB each.
- Your data is only used for your run.
- Made by Tidy Byte Tools. Questions? Open an issue on this Actor's page.

# Actor input Schema

## `fileUrls` (type: `array`):

Links to .md files (raw GitHub links work).

## `markdownText` (type: `string`):

Paste Markdown here.

## `maxChars` (type: `integer`):

Chunks are never longer than this.

## `overlapChars` (type: `integer`):

Repeat this many characters from the last chunk. Up to half of max.

## `prefixHeadingPath` (type: `boolean`):

Adds 'Guide > Install' above the text. Helps search.

## Actor input object example

````json
{
  "markdownText": "# Guide\n\nHello.\n\n## Install\n\n```bash\npip install tool\n```\n\n## Use\n\n| a | b |\n|---|---|\n| 1 | 2 |\n",
  "maxChars": 1500,
  "overlapChars": 0,
  "prefixHeadingPath": false
}
````

# Actor output Schema

## `results` (type: `string`):

No description

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

````javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "markdownText": `# Guide

Hello.

## Install

```bash
pip install tool
````

## Use

| a | b |
|---|---|
| 1 | 2 |\`
};

// Run the Actor and wait for it to finish
const run = await client.actor("tidybytetools/markdown-rag-chunker").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

````

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = { "markdownText": """# Guide

Hello.

## Install

```bash
pip install tool
````

## Use

| a | b |
|---|---|
| 1 | 2 |
""" }

# Run the Actor and wait for it to finish

run = client.actor("tidybytetools/markdown-rag-chunker").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)

print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

````

## CLI example

```bash
echo '{
  "markdownText": "# Guide\\n\\nHello.\\n\\n## Install\\n\\n```bash\\npip install tool\\n```\\n\\n## Use\\n\\n| a | b |\\n|---|---|\\n| 1 | 2 |\\n"
}' |
apify call tidybytetools/markdown-rag-chunker --silent --output-dataset

````

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,tidybytetools/markdown-rag-chunker"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/Y1uN3LgEbvdrBUtoD/builds/wC8VRocABS0GSsmKp/openapi.json