Retrieval Recall Calculator
Calculate recall@k for a retrieval system used in RAG pipelines.
About Retrieval Recall Calculator
Recall@k measures what fraction of all relevant documents appear in the top-k retrieved results. In RAG, high recall@k is critical because any relevant information not retrieved cannot be used by the LLM to generate its answer.
Formula
Recall@k
recall@k = |relevant ∩ top_k| / |total_relevant|
- k
- Number of results retrieved
Worked example
With the default values below, Retrieval Recall Calculator returns Recall@k of 0.7000. Change any input above and every figure here is recalculated in your browser.
Inputs used
- Relevant Items Retrieved (in top-k)minimum 0
- 7
- Total Relevant Items in Corpusminimum 1
- 10
- k (number retrieved)minimum 1
- 10
Results
- Recall@k
- 0.7000
- Precision@k
- 0.7000
Step by step
- 1Recall@k: relevant_retrieved ÷ total_relevant= 0.7000
- 2Precision@k: relevant_retrieved ÷ k= 0.7000
Assumptions and limits
- The result is derived only from the 3 inputs listed above. Anything not among them is not part of the calculation.
- In particular, this calculator does not take inflation, tax, fees or charges or compounding frequency into account.
- Figures are rounded for display to 4 decimal places, so totals built from several rounded parts can differ slightly from the unrounded arithmetic.
How these calculators are built and tested is described on the Methodology page. If a figure looks wrong, please report it.
Frequently Asked Questions
What recall@k should I target for RAG?
Aim for recall@10 > 0.9 or recall@20 > 0.95. If the relevant chunk isn't retrieved, the LLM cannot use it regardless of its reasoning capability.
How do I improve retrieval recall?
Use hybrid search (dense + sparse/BM25), re-ranking, query expansion, smaller chunks with overlap, or fine-tuned embedding models trained on your domain.