Pricing

$0.50 / 1,000 chunks

Text Chunker: Split Text & Documents into Chunks for RAG

Split long text or documents into properly sized, sentence-aware chunks with overlap for embeddings, vector databases, and RAG pipelines. Choose recursive, sentence-boundary, or fixed-token chunking. Fetch from URLs or paste text directly. Powered by Chonkie.

Pricing

$0.50 / 1,000 chunks

Rating

0.0

(0)

Developer

Raion Al

Actor stats

Bookmarked

Total users

Monthly active users

2 days ago

Last modified

Categories

Developer tools

You can access the Text Chunker: Split Text & Documents into Chunks for RAG 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.

Python

JavaScript

CLI

OpenAPI

HTTP

MCP

$echo '{
<  "texts": [
<    "Our platform lets you connect a data source, transform records with a visual pipeline builder, and publish the result to any destination without writing code. Most teams get their first pipeline running within an afternoon, and support is available by chat if you get stuck along the way.\\n\\nConnections are managed centrally. Once you authorize a data source, every pipeline in your workspace can reuse that connection, so credentials are entered once and rotated in a single place. We support more than sixty destinations, including data warehouses, spreadsheets, and webhooks, and new destinations are added every month based on customer requests submitted through the roadmap board.\\n\\nPipelines run on a schedule you define, from every five minutes to once a month, or you can trigger a run manually from the dashboard or through the API. Each run produces a detailed log you can inspect later, and failed runs send an alert to the channel you configure, whether that is email, Slack, or a custom webhook endpoint of your choosing.\\n\\nHistorical run data is retained for ninety days on paid plans and seven days on the free plan. You can export any run'\''s input and output as JSON at any time, which is useful for debugging a transform step or for feeding results into another system entirely.\\n\\nRole-based access control lets you decide who can view, edit, or run each pipeline. Workspace owners can invite teammates by email, assign them to one of four roles, and restrict sensitive connections to a specific team. Audit logs record every permission change so you always know who altered access and when.\\n\\nPricing is usage-based and scales with the number of records processed each month rather than the number of pipelines or seats, so you can add as many teammates and workflows as you like without the bill changing. A free plan covers light usage and is a good way to evaluate the product before committing to a paid tier. Enterprise customers can request a fixed-price contract with a dedicated support engineer and a custom data retention window.\\n\\nThe underlying engine retries failed steps automatically using exponential backoff, and it de-duplicates records so a retried run never writes the same row twice to your destination. If a destination is temporarily unreachable, pending records queue safely and resume delivery once the destination comes back online, so a brief outage downstream does not require you to manually replay anything.\\n\\nMonitoring is built into every workspace. A live status page shows the health of each pipeline, the average run duration over the last thirty days, and the volume of records processed per hour. You can set custom thresholds so an alert fires before a slow pipeline turns into a missed deadline, rather than only after something has already broken downstream.\\n\\nMigrating from another tool is usually the first thing new customers ask about. Our import wizard reads an existing pipeline configuration from several competing tools and recreates the equivalent steps automatically, flagging anything it could not translate so you can finish those by hand. Most migrations of a few dozen pipelines are completed within a single working day, including validation against a sample of real production data."
<  ]
<}' |
<apify call raional/text-chunker --silent --output-dataset

Text Chunker: Split Text & Documents into Chunks for RAG API through CLI

The Apify CLI is the official tool that allows you to use Text Chunker: Split Text & Documents into Chunks for RAG locally, providing convenience functions and automatic retries on errors.

Install Apify CLI

Using installation script (macOS/Linux):

$curl -fsSL https://apify.com/install-cli.sh | bash

Using installation script (Windows):

$irm https://apify.com/install-cli.ps1 | iex

Using Homebrew:

$brew install apify-cli

Using npm:

$npm install -g apify-cli

Other API clients include:

Text Chunker: Split Text & Documents into Chunks for RAG API in Python

Text Chunker: Split Text & Documents into Chunks for RAG API in JavaScript

Text Chunker: Split Text & Documents into Chunks for RAG OpenAPI definition

Text Chunker: Split Text & Documents into Chunks for RAG API

RAG Text Chunker — heading & sentence aware, Japanese ready

shoebill-dev27/rag-text-chunker

Split Markdown or plain text into retrieval-ready chunks for RAG pipelines: cuts at headings, packs whole sentences up to a size limit with optional overlap, and tags every chunk with its heading breadcrumb. Handles Japanese sentence boundaries. No LLM cost.

Shinobu Otani

Text Splitter & Chunker for RAG / LLMs

zenomastro/text-splitter-for-llm

Split text into clean, overlapping chunks ready for embeddings, vector databases, RAG and LLM context. Configurable size, overlap, and split strategy.

Rosario Vitale

Rag Content Chunker

labrat011/rag-content-chunker

Turn raw text, Markdown, or Apify datasets into token-perfect RAG chunks with deterministic IDs, source metadata, and a billing-ready summary—ready for embeddings or vector DBs without extra glue code.

mick_

RAG Post Processor - Text Cleaner & Chunker for LLM Pipelines

jalicia/rag-post-processor

Clean and chunk scraped text for RAG and LLM pipelines. Strips HTML, collapses whitespace, splits into overlapping chunks ready for embedding. Works standalone or chained after any scraper. Per-row billing.

Jordan Wagner

📄 PDF Text Extractor

scraper-engine/pdf-text-extractor

📄✨ PDF Text Extractor extracts clean text from PDF files with precision. ⚡ Perfect for data mining, document processing, and searchable archives. 🚀 Fast, reliable, and efficient for your workflow!

Scraper Engine

PDF to RAG Markdown Chunks for Embeddings

awesome_highboy/docforge

Convert PDFs into token-bounded Markdown chunks for RAG, embeddings, and vector databases (Pinecone, Chroma, Weaviate, Qdrant). Set maxTokens + overlap; get clean chunks with page number, token count, and SHA-256 content hash for dedup. JSON dataset ready for any LLM pipeline.

Adam

RAG-Ready Markdown Converter & Chunker

foxpink/apify-rag-markdown-chunker

Convert raw HTML/text into clean Markdown and split into ready-to-ingest chunks for RAG pipelines, Vector DBs, and LLM fine-tuning workflows.

Nguyễn Anh Duy

4.7

(3)

RagChunk: Semantic RAG Splitter & Markdown Cleaner

flaretool/rag-semantic-chunker

Extract, clean, and semantically split documentation URLs into token-safe chunks for Vector DBs. Built-in HTML boilerplate stripping saves up to 40% on LLM token costs.

FlareTool

PDF to Markdown for RAG & LLMs (tables, no API key needed)

vivid_astronaut/pdf-to-markdown-for-rag

Convert PDFs to clean structured Markdown for RAG and LLM ingestion. Preserves tables. Flat $0.004/page, no API key required.

BRAINIALL Team

YouTube Transcript Scraper - Captions, Subtitles & RAG API

meilimiao/yt-transcript-captions-api

Extract YouTube transcripts, captions, subtitles, timestamps, metadata, SRT, WebVTT, Markdown, and RAG-ready chunks from videos, Shorts, channels, and playlists. Works with bulk URLs and residential proxy support.