Tools + TOFU

How do you test RAG retrieval before building the production pipeline?

A RAG sandbox lets you test retrieval before committing to architecture. Upload documents, choose a chunk size and overlap, embed them, then ask real questions and inspect which passages were retrieved and what the model did with them. You iterate on chunking, top-k and prompts in minutes, then carry the working settings into production.

Key facts

Tool typeFree browser sandbox for document ingestion and retrieval testing
Pipeline stepsUpload, chunk, embed, retrieve, generate, inspect
Settings to varyChunk size, overlap, top k and prompt template
Models30+ generation models plus embeddings from the catalogue
InspectionRetrieved passages shown alongside the generated answer
RAG statusRAG, embeddings and agents are live
Free plan2 free AI models (plugsky-micro, plugsky-lite), no card required
Product statusLive

TL;DR

  • Test retrieval quality with real documents before writing pipeline code.
  • Chunking and top-k change answers more than model choice in most systems.
  • Inspect retrieved passages, not just the final answer, to find the real failure.
  • Export winning settings — chunk size, overlap and k — into production configuration.
  • Keep the test set so the same questions can re-run after any change.

How it works, step by step

  1. Upload a representative slice of your real documents, including messy ones.
  2. Choose an initial chunk size and overlap, then embed the corpus.
  3. Ask 10-20 real questions and read the retrieved passages before the answer.
  4. Adjust chunk size, overlap and top k, and re-run the same questions.
  5. Note which combination retrieves the gold passage reliably at a sensible rank.
  6. Test generation prompts on top of the best retrieval settings.
  7. Export the winning configuration and re-run the same questions in production.
1Upload arepresentativeslice of your real2Choose an initialchunk size andoverlap, then embed3Ask 10-20 realquestions and readthe retrieved4Adjust chunk size,overlap and top k,and re-run the same5Note whichcombinationretrieves the gold6Test generationprompts on top ofthe best retrieval

Try it yourself

Open the RAG sandbox →

What the sandbox actually tests

The sandbox isolates the retrieval half of RAG so you can see it working. Documents are chunked and embedded, questions are converted into vectors, and the nearest chunks are returned alongside the generated answer. That view is the point: when an answer is wrong, you can tell within seconds whether the retriever surfaced the wrong passages or the model mishandled the right ones. Testing with a representative slice of real documents — including headers, tables and scanned text — exposes the parsing problems that toy corpora hide.

Iterating on the parameters that matter

Most RAG quality comes from three settings. Chunk size controls how much context each vector carries; too small and answers lack detail, too large and retrieval becomes imprecise. Overlap preserves meaning across boundaries, especially for procedures that span paragraphs. Top k decides how much material reaches the model: more raises recall but adds noise and tokens. Change one parameter at a time, re-run the same questions, and watch both the retrieved passages and the final answer. Embedding model choice is a fourth lever, and since Plugsky serves embeddings alongside 30+ generation models, you can test it without leaving the sandbox.

From sandbox to production

The sandbox is a decision tool, not a hosting environment. When the settings stabilise, export them: chunk size, overlap, top k, embedding model and the prompt template that worked. Recreate that pipeline in your own service, keep the same test questions as a regression suite, and monitor retrieval metrics in production — an index that drifts as documents change will silently degrade answers. Use the prompt diff and evaluator to compare production variants, and revisit settings when your corpus grows or changes shape.

Honest comparison

SettingWhat it changesSymptom when wrongFirst fix to try
Chunk sizeContext per vectorAnswers lack detail or retrieval missesHalve or double, then re-test
OverlapContinuity across chunk boundariesProcedures cut mid-stepIncrease overlap modestly
Top kHow much context reaches the modelAnswer missing or buried in noiseRaise for recall, then trim
Embedding modelSemantic matching qualityQueries miss paraphrasesTest multilingual or domain-tuned embeddings
Prompt templateHow context is usedRight passages, wrong answerConstrain the prompt to the context

Frequently asked questions

What is a RAG sandbox?

A browser environment where you upload documents, chunk and embed them, then ask questions and inspect the retrieved passages alongside the generated answer before building a production pipeline.

Do I need to write code?

No. The sandbox handles ingestion, chunking, embedding and retrieval so you can focus on choosing settings and prompts.

Which settings matter most?

Chunk size, overlap and top k usually dominate. Embedding model and generation model come next. Change one variable at a time to keep the comparison honest.

How many documents should I test with?

A representative slice is enough — a few dozen documents that include your messiest real content. Samples that are too clean hide parsing and chunking problems.

Can I reuse the settings in production?

Yes. Export chunk size, overlap, top k, embedding model and prompt, then recreate the pipeline in your own service with the same regression questions.

Does the sandbox support private documents?

Treat any hosted sandbox as a shared environment: use non-sensitive samples, and check the docs for data handling before uploading sensitive material.

How does retrieval relate to model choice?

A better model cannot fix missing context. Test retrieval first in the sandbox, then optimise the generation model on top of good retrieval.

Is there a free way to try it?

Yes. The free plan includes 2 free AI models with no card, and the sandbox is a free tool.