Crate mnemonist_evals 

Evaluation metrics and harness for mnemonist.

• search — retrieval quality (MRR, NDCG, precision@k, recall@k)
• embedding — embedding space quality (anisotropy, discrimination gap, intrinsic dimensionality)
• quantization — quantization fidelity (MSE, cosine distortion, recall impact)
• dataset — synthetic benchmark dataset generation
• harness — end-to-end eval runner producing structured reports

Re-exports

pub use report::EvalReport;

Modules

dataset

Synthetic benchmark dataset generation for retrieval evaluation.

embedding

Embedding quality metrics for evaluating how well embeddings distribute across the vector space.

harness

End-to-end eval harness. Orchestrates dataset generation, index construction, and metric computation into a single EvalReport.

quantization

Quantization quality evaluation.

report

Structured evaluation report.

search

Search quality metrics for evaluating retrieval results.

Enums

EvalError