Skip to content
Outrich Data

Text chunker for retrieval and training

Paste text or drop documents and split them into chunks by tokens, characters, sentences, paragraphs or Markdown headings, with overlap. Chunks end on sentence boundaries where possible and never inside a word. Each chunk carries its source, position and heading, and the result downloads as JSONL. It runs in your browser.

How to use it

  1. 01Paste text or drop one or more text or Markdown files.
  2. 02Choose how to split: tokens, characters, sentences, paragraphs or headings.
  3. 03Set the chunk size and the overlap between neighboring chunks.
  4. 04Check the chunk count and the size histogram.
  5. 05Download the JSONL. Each line has source, index, text, tokens, start, end and heading.

What it does not do

  • Token counts are an estimate at about four characters per token. Exact counts depend on the model's tokenizer.
  • Sentence detection is punctuation-based, so an abbreviation such as Dr. can end a sentence early.
  • A single word longer than the chunk size is kept whole, so that chunk runs over the size.
  • It reads plain text and Markdown. Convert PDF and Word files to text first.

Questions

About the text chunker.

Is my data uploaded anywhere?
No. The tool runs entirely in your browser. Your text and files are never sent to Outrich Data or anyone else, and nothing is stored after you close the tab. You can confirm it by turning off your internet connection after the page loads: the tool keeps working.
What chunk size should I use?
For retrieval, 200 to 500 tokens with 10 to 20 percent overlap is a common starting point. Smaller chunks match questions more exactly. Larger chunks keep more context. Test both against real questions from your users.
Why add overlap?
A fact that straddles a chunk boundary can be cut in half. Overlap repeats the end of one chunk at the start of the next, so the sentence appears whole in at least one of them.
What is the heading field for?
It holds the Markdown heading path above the chunk, such as Handbook > Refunds. Storing it next to the text lets a retrieval system show where an answer came from, and adding it to the embedded text often improves matching.
Is it really free?
Yes. There is no account, no limit on the number of uses and no watermark. Files up to 50 MB are supported.

More free tools

Personal data scrubber

Strip names, emails, phones, cards, keys and addresses from text and files.

Dataset profiler

Rows, columns, tokens, date span, duplicates and personal-data columns in one report.

Column hasher and remover

Drop sensitive columns or replace them with salted hashes that still join.

CSV, JSON and JSONL converter

Convert between CSV, TSV, JSON and JSONL without breaking quoted cells.

JSONL validator

Find the broken lines in a JSONL file and see which keys are missing.

Duplicate remover

Remove repeated rows, records or log lines, keeping the first of each.

Token counter

Size text the way AI labs do: tokens, words, characters and lines.

Data card generator

Write the one-page description every data buyer asks for.

Data rights pre-check

A tailored checklist of the contracts and questions to clear before a sale.

Slack export parser

Turn a Slack workspace export into clean thread JSONL with pseudonymized users.

Email thread parser

Convert .mbox and .eml files into threaded JSONL without quoted replies.

Ticket export parser

Map help desk exports to customer and agent turns in conversation JSONL.

Chat dataset format converter

Convert and validate OpenAI, ShareGPT, Alpaca and prompt/completion datasets.

Log parser

Turn web server, syslog, logfmt and JSON logs into structured JSONL or CSV.

HTML and document text extractor

Extract clean text from HTML, Markdown, XML and JSON files in batches.

Re-identification risk checker

Measure k-anonymity and l-diversity, then preview fixes that lower the risk.

Secrets scanner

Find API keys, tokens, passwords and private keys in a repo or export before you share it.

Delivery manifest builder

Create a SHA-256 checksum manifest for a dataset delivery, with one hash to compare.

Delivery verifier

Check received files against a manifest: match, changed, missing or extra.

File checksum calculator

SHA-256 of any file, with a compare box that turns green or red.

Train, validation and test splitter

Split a dataset into train, validation and test files without leaking related rows across splits.

Dataset sampler

Pull a random, stratified or first-N sample from a file, including files too large to open.

Schema inferrer and data dictionary

Infer field types and stats from a file and export JSON Schema, a data dictionary and SQL.

Dataset diff

Compare two versions of a dataset: added, removed and changed records, plus schema changes.

Encoding and mojibake fixer

Repair garbled characters, convert files to UTF-8 and strip invisible characters.

Column toolkit

Rename, split, merge, clean, filter and sort columns with a reusable pipeline of steps.

Cleaned it up? Sell it to Outrich.

Outrich Data buys company data directly. Check in five minutes whether yours qualifies, with no call.

esc