Pricing

from $0.25 / 1,000 chunk processeds

RAG Post Processor - Text Cleaner & Chunker for LLM Pipelines

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.

Pricing

from $0.25 / 1,000 chunk processeds

Rating

0.0

(0)

Developer

Jordan Wagner

Actor stats

Bookmarked

Total users

Monthly active users

21 days ago

Last modified

What it does

Strips HTML tags and boilerplate
Collapses whitespace and normalizes line breaks
Splits text into overlapping chunks (default: 1000 chars, 100 overlap)
Returns structured output with chunk index, length, and timestamp
Works standalone or chained after Website Content Crawler and similar actors

Input

Field	Type	Default	Description
`data`	array	required	Array of objects from a previous scraper. Each object needs a `text`, `content`, `body`, or `html` field.
`chunk_size`	integer	1000	Max characters per chunk
`overlap`	integer	100	Character overlap between chunks

Example input

{
  "data": [
    { "text": "Your raw scraped content goes here. It can be long, messy HTML or plain text." }
  ],
  "chunk_size": 1000,
  "overlap": 100
}

Output

Each chunk is returned as a dataset item:

{
  "original_id": "item_0",
  "chunk_index": 0,
  "total_chunks": 3,
  "chunk_text": "Cleaned and chunked text ready for embedding...",
  "chunk_length_chars": 487,
  "cleaned_at": "2026-06-20 04:46:29.330000+00:00"
}

Pricing

$0.0003 per output row. No subscription required — pay only for what you use.

Use with PowerShell

Install the companion PowerShell module to call this actor from your automation scripts:

Import-Module RAGPostProcessor
Invoke-RAGPostProcessor -InputText "Your scraped text here" -VerboseOutput

Chaining with other actors

Works directly after Website Content Crawler, Cheerio Scraper, or any actor that outputs a text or content field. Use the Apify actor-to-actor API to pipe output from a scraper straight into this processor.

Common use cases

Preparing scraped web content for vector databases (Pinecone, Weaviate, Chroma)
Cleaning LangChain / LlamaIndex document ingestion pipelines
Pre-processing data for OpenAI embeddings or similar APIs
Automating RAG pipeline data prep without custom code

AI / RAG Web Crawler

groupoject/ai-rag-web-crawler

Crawl any website and extract clean, LLM-ready Markdown chunks to feed AI agents, chatbots, and RAG pipelines. One row per embeddable chunk.

Group Oject

Website to Markdown for LLM and RAG

jeweled_jockstrap/my-actor-3

Convert any URL to clean Markdown text for AI applications. Strips HTML extracts content. For LLM training RAG pipelines and vector databases. Free Firecrawl alternative.

Juan Triviño

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

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

Website Content Pipeline for AI: Markdown, Tokens, RAG Chunks

scrapemint/website-content-crawler

Crawl any website and ship clean Markdown, plain text, and HTML for AI, LLM, and RAG pipelines. Each row carries token estimates, JSON LD metadata, link graph, and optional auto chunk splitting for vector databases. Pay per page.

Ken M

PDF → RAG Chunks (Token-Aware, Vector-Ready)

gochujang/pdf-rag-chunker

Download any PDF and chunk into semantically coherent segments ready for embedding/RAG. Configurable chunk size + overlap. Returns one row per chunk with page, char count, token estimate. Feed directly into OpenAI text-embedding-3 / Voyage / Cohere. $0.005 per PDF + $0.0002 per chunk.

Hojun Lee

AI Context Fetcher: Clean Text for RAG

sarvesh_bijawe/ai-context-fetcher-clean-text-for-rag

Instantly extracts clean, ad-free text from any URL. Designed for AI Agents, RAG pipelines, and LLM context windows.

Sarvesh Bijawe

Web to LLM Spanish — RAG-ready content extractor

fanciful_geode/web-to-llm-es

Crawls Spanish-language websites and extracts clean markdown content optimized for LLM RAG pipelines. Handles Spanish character encoding, removes boilerplate, and outputs structured chunks ready for embedding.

Ernesto de Armas

Refinery — HTML to LLM Text (Cut RAG Token Cost)

larelabs/refinery-html-to-llm-cleaner

HTML to LLM text cleaner for RAG pipelines. Strip scripts, nav & layout junk after Firecrawl or your fetch. BeautifulSoup-alternative speed. $0.002/page · 3 README demos in Console.