AI Runs in your browser

RAG Top-k Evaluation Calculator

Compare retrieval recall and grounded-answer rates across top-k settings using labeled per-query evaluation rows.

Input

Fields are ready to edit and update the result automatically.

Live

Result

Ready.

Results update as you edit.

Keep exploring

Related tools

RAG Retrieval Evaluation Workbook

Turn a small question-and-answer sample into recall, precision, faithfulness, and citation coverage checks before changing your model.

RAG Citation Coverage Checker

Measure claim-level citation coverage and flag missing or unknown source IDs in a manually reviewed answer sample.

RAG Chunk and Overlap Calculator

Estimate chunk count, overlap token overhead, and approximate indexed tokens from corpus size and chunk settings.

From the guide archive

Related guides

AI EngineeringChoose RAG `top_k` With a Context and Latency BudgetIncreasing top-k can raise evidence recall but also add noise, token cost, and latency. Select the candidate count from query-level evaluation instead of habit.AI EngineeringEvaluate RAG Retrieval Quality Before Changing the ModelWhen a RAG answer is wrong, a small retrieval evaluation set can tell you whether the problem is missing evidence, noisy context, or the answer layer.