Japanese Text Normalizer & RAG Chunker
Pricing
from $0.07 / 1,000 1,000 characters processeds
Clean Japanese text before RAG or an LLM: full-width letters, half-width katakana, voiced marks, dashes and long vowels, letter-spaced text, broken PDF line breaks, page numbers and headers. URLs, e-mail addresses and fenced code are kept. Optional sentence-aware chunking with overlap.
You can access the Japanese Text Normalizer & RAG Chunker 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 API & Integrations in Apify Console.
$echo '{< "textFields": [< "text"< ],< "metadataFields": [< "url",< "title"< ]<}' |<apify call quietworkslab/japanese-text-normalizer --silent --output-datasetThe Apify CLI is the official tool that allows you to use Japanese Text Normalizer & RAG Chunker locally, providing convenience functions and automatic retries on errors.
Using installation script (macOS/Linux):
$curl -fsSL https://apify.com/install-cli.sh | bashUsing installation script (Windows):
$irm https://apify.com/install-cli.ps1 | iexUsing Homebrew:
$brew install apify-cliUsing npm:
$npm install -g apify-cliOther API clients include: