RAG Debugger

Debug Your RAG Pipeline

Paste a document, chunk it with different strategies, embed it, and see exactly which chunks are retrieved for your queries. Understand why your RAG system returns what it does.

Get Started

Multiple Chunking Modes

Article-based, token window, or sentence packing. Compare how different strategies affect retrieval.

Visual Chunk Explorer

See all your chunks at a glance. Retrieved chunks are highlighted with their similarity scores.

Query & Retrieve

Test queries against your index and see exactly which chunks match. Adjust top-k in real time.

LLM Answer Generation

Generate answers from retrieved chunks with strict mode. See which chunks were actually used.

How It Works

1

Paste Your Document

Paste any text document and choose your chunking strategy and parameters.

2

Build Your Index

Chunks are created and embedded using your chosen model. See them all instantly.

3

Query & Debug

Run queries and see exactly which chunks are retrieved and why.

Ready to debug your RAG pipeline?

Sign up for free and start understanding your retrieval system.

Get Started Free