New blogMaking an AI Agent You Can Trust With Money
logo

★ Fixed-Size chunking, visualized

Fixed-Size Chunking for RAG

Fixed-size chunking slides a window of N characters across the text. Each chunk starts N minus the overlap after the previous one, so the last few characters of one chunk repeat at the start of the next.

  • Runs in your browser
  • No signup

1,181 characters · loading tokenizer… · nothing leaves your browser

chars
chars

Counts characters, no tokenizer involved.

Fixed (chars) · 300 chars · overlap 40

5 chunks

67
avg tokens
35 / 75
min / max
40
overlap tokens
$6.70
embed 1M docs

Loading the tokenizer; token counts are estimates until it's ready.

# Refund policy for annual plans Annual plans are billed once a year, up front. This page explains when you can get money back and how long it takes. ## Eligibility You can request a full refund within 30 days of the first annual charge. After 30 days, refunds are prorated for the unused months, minus any discount you received for paying annually. Renewals follow the same rule: the 30-day window starts again on each renewal date. ## How to request a refund Open Settings, then Billing, and choose "Request refund". Pick the reason that fits best. If you are cancelling because of a bug, include the error message; it often gets fixed faster than the refund is processed. ### Processing times Card refunds usually appear within 5 to 10 business days, depending on your bank. Bank transfers can take longer. We send an email when the refund leaves our side. ## Exceptions Refunds are not available for usage-based charges such as extra API calls or storage, because those costs are incurred when you use them. Accounts closed for abuse are not eligible. ## Contact Still stuck? Email the billing team with your account ID and the last four digits of the card on file.

one chunkoverlapClick a chunk to inspect it.

Chunk inspector

Click any coloured chunk in the document to see its text, size, heading path and what it shares with its neighbours.

Chunk sizes

Tokens per chunk (estimated). A tight cluster means predictable chunks.

135445362471chunk size (tokens), bucket start

Embedding cost assumes text-embedding-3-small at $0.02 per 1M tokens (OpenAI, checked 8 Nov 2026), counting overlap twice.

Export config

Copy-ready code for the strategy and settings above. Comments flag where a library differs.

from langchain_text_splitters import CharacterTextSplitter

# Fixed windows of characters. separator="" splits per character, then merges up to chunk_size.
splitter = CharacterTextSplitter(separator="", chunk_size=300, chunk_overlap=40)
chunks = splitter.split_text(text)

Your retrieval is only as good as your chunks.

I build RAG systems with evals, so you know when the answers get better or worse.

Fix my RAG
01

How it works

Fixed-size chunking slides a window of N characters across the text. Each chunk starts N minus the overlap after the previous one, so the last few characters of one chunk repeat at the start of the next.

It ignores the document's structure completely. That makes it fast and predictable, and also the strategy most likely to cut a sentence, a table row or a code block in half.

02

When to use it

Good fit

  • Quick baselines, before you know what the documents look like.
  • Uniform text with little structure, such as transcripts or logs.
  • When you need chunk sizes to be exactly predictable for cost or batching.

Watch out for

  • Cuts mid-word and mid-sentence, so a chunk can start with half a thought.
  • Splits code blocks and tables, which then embed as noise.
  • Overlap hides the problem a little but also stores the same text twice.
03

Where to start

Start with a window that holds a full paragraph of your documents and an overlap of roughly a sentence. Then compare against recursive splitting on the same questions; structure-aware splitting usually wins on real documents.

Then test it: write down twenty real questions, check which chunks come back for each, and compare strategies on the same set. The main visualizer lets you put two strategies side by side.

04

Questions engineers actually ask

Is fixed-size chunking ever the right choice?
Yes, as a baseline and for structureless text like transcripts. For documents with headings and paragraphs, a structure-aware strategy usually retrieves better.
Why does my chunk start in the middle of a word?
Because a fixed character window doesn't look at the text. Recursive or sentence splitting avoid this by cutting at separators.
Characters or tokens?
Models and embedding limits count tokens, so token-based windows map better to limits. Characters are simpler and fine for a first look.
What chunk size should I use for RAG?
There is no universal number. A few hundred tokens with a small overlap is a common starting point, but the right size depends on your documents and questions. Build a small evaluation set and compare sizes on it.
Does my text leave the browser?
No. Splitting, tokenizing and the visualization all run in your browser. Nothing you paste is sent anywhere.
05

Other strategies

06

More from the workbench

07 · AI & LLMsToken CounterToken counts per model, cost per call and how much of the context window you are using.02 · AI & LLMsLLM API Cost CalculatorYour monthly bill across Claude, GPT, Gemini and open models, side by side.13 · AI & LLMsAI Agent vs HireThe fully loaded cost of a hire versus an AI agent doing the same work, review included.

Fine print

Tools: on the house.
Engineer: by the hour.

The visualizer was free. Production RAG with evals is what I build.

I'm Himanshu, an AI and full-stack engineer. I build MVPs, AI agents and the growth plumbing around them for early-stage startups.

Hire me →My projects