# reval

## Docs

- [Ranking Evaluation](https://mintlify.wiki/itsubaki/reval/guides/ranking-evaluation.md): Measure the quality of search, recommendation, and retrieval systems using Precision, Recall, and NDCG
- [Text Generation Evaluation](https://mintlify.wiki/itsubaki/reval/guides/text-generation-evaluation.md): Evaluate summarization and generation quality with ROUGE and BERTScore
- [Introduction](https://mintlify.wiki/itsubaki/reval/introduction.md): reval — evaluation metrics for ranking and retrieval in Go
- [BERTScore](https://mintlify.wiki/itsubaki/reval/metrics/bert-score.md): Semantic similarity scoring using dense vector embeddings
- [NDCG](https://mintlify.wiki/itsubaki/reval/metrics/ndcg.md): Normalized Discounted Cumulative Gain with graded relevance
- [Precision](https://mintlify.wiki/itsubaki/reval/metrics/precision.md): Precision@K, Average Precision, and Mean Average Precision
- [Recall](https://mintlify.wiki/itsubaki/reval/metrics/recall.md): Recall@K for measuring retrieval completeness
- [ROUGE](https://mintlify.wiki/itsubaki/reval/metrics/rouge.md): ROUGE-1, ROUGE-L, and ROUGE-Lsum for text generation evaluation
- [Quickstart](https://mintlify.wiki/itsubaki/reval/quickstart.md): Install reval and compute your first evaluation metric in Go

## OpenAPI Specs

- [openapi](https://mintlify.wiki/itsubaki/reval/api-reference/openapi.json)