Markdown Chunker for RAG - Heading-Aware Text Splitter avatar

Markdown Chunker for RAG - Heading-Aware Text Splitter

Pricing

from $0.10 / 1,000 chunk createds

Go to Apify Store
Markdown Chunker for RAG - Heading-Aware Text Splitter

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.

Pricing

from $0.10 / 1,000 chunk createds

Rating

0.0

(0)

Developer

Tidy Byte Tools

Tidy Byte Tools

Maintained by Community

Actor stats

0

Bookmarked

2

Total users

1

Monthly active users

3 days ago

Last modified

Categories

Security

Limited permissions

Share

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.