Small 256-token chunks for factual Q&A retrieval

Created by

CodePoetry

Actor

Markdown RAG Chunker: Document Text Splitter

Splits a document into tight 256-token chunks measured with the o200k_base tokenizer (GPT-4o family), which suit short factual lookups and FAQ-style retrieval. Each chunk keeps its section header path and exact token count.

Try for free

Markdown RAG Chunker: Document Text Splittercodepoetry/markdown-rag-chunker

Chunk index

Header path

Token count

Content

+2 fields

Input

Document URL:https://raw.githubusercontent.com/yel-hadd/markdown-rag-chunker/main/README.md

Max chunk size (tokens):256

Tokenizer:o200k_base

Output fields

Chunk index

Header path

Token count

Content

Chunk ID

Source

How it works

Sign up on Apify or log in

The Markdown RAG Chunker: Document Text Splitter Actor is ready to run with the inputs already set for "Small 256-token chunks for factual Q&A retrieval". Sign up or log in and you'll land in Apify Console with a copy of this exact task.

Start the "Small 256-token chunks for factual Q&A retrieval" task

The Markdown RAG Chunker: Document Text Splitter Actor will start running based on the input automatically. You can also change all the input fields, like document url, max chunk size (tokens), and more, to match your specific use case.

Receive the "Small 256-token chunks for factual Q&A retrieval" output

Monitor the progress in real time. You will be notified as soon as your dataset is complete and ready for review. Each result includes data such as chunk index, header path, token count, and more.

Integrate into your workflow

The final output is delivered in JSON, CSV, or Excel format, ready to be plugged into your workflow. You can also run the "Small 256-token chunks for factual Q&A retrieval" task via API.