RAG Chunking Strategy Evaluator

A lightweight evaluation notebook that scores retrieval quality across different chunking strategies (fixed-size, semantic, recursive) against a sample question set, so teams can pick a chunking approach with evidence instead of a guess.

What it measures

For each chunking strategy, the notebook computes retrieval precision at k against a labeled question set you provide, giving a side-by-side comparison rather than a single recommendation — the right chunking strategy is genuinely document-set dependent.