Why number the chunks?

Numbered chunks let the model cite its sources, so you can ask it to answer "using only the context above and citing chunk numbers." This makes answers traceable and reduces hallucination because the model anchors claims to specific retrieved passages.

What separator should I use?

XML-style tags (one tag per chunk) are the most robust because models rarely confuse them with content. Triple-dash and blank-line separators are lighter weight and fine for short, clean chunks. Pick based on how messy your source text is.

Does this call an embedding model or retriever?

No. This tool only formats chunks you have already retrieved from your own vector store or search index. Run your retrieval first, then paste the top-k results here to assemble the final context block.

How accurate is the token estimate?

It uses a roughly four-characters-per-token approximation, which is close for English prose. Use it as a guide to avoid blowing past your context limit; for exact counts, tokenize with your model's tokenizer.

Retrieval Context Formatter

Turn raw retrieved chunks into a clean context block

Retrieval-augmented generation lives or dies on how you present the retrieved passages to the model. Dumping concatenated chunks with no structure invites the model to blur sources together and hallucinate. This formatter takes your top-k chunks and assembles a structured, numbered, citable context block you can paste straight into a prompt.

How it works

You paste one chunk per block, separated by blank lines. If the first line of a block looks like a source label (e.g. Onboarding Guide - Step one is...), it is split out and shown as the chunk’s source. The tool then renders each chunk with your chosen separator — XML tags, triple-dash rules, or numbered headers — and optionally wraps everything in a context template that instructs the model to answer only from the context and cite chunk numbers. A live token estimate tells you whether the block fits your window.

Tips for better RAG context

Always number chunks so the model can cite them; ungrounded answers become obvious when no chunk number is referenced.
Keep source labels short and unique — a doc title plus section beats a long URL the model might echo verbatim.
Put the question after the context. Models attend most reliably to instructions that follow the data they operate on.
Watch the token estimate. If you are near the limit, retrieve fewer but higher-scoring chunks rather than truncating mid-passage.