vitals: Large Language Model Evaluation

A port of 'Inspect', a widely adopted 'Python' framework for large language model evaluation. Specifically aimed at 'ellmer' users who want to measure the effectiveness of their large language model-based products, the package supports prompt engineering, tool usage, multi-turn dialog, and model graded evaluations.

Version: 0.1.0
Depends: R (≥ 4.1)
Imports: cli, dplyr, ellmer (≥ 0.2.1), glue, httpuv, jsonlite, purrr, R6, rlang, rstudioapi, S7, tibble, tidyr, withr
Suggests: ggplot2, here, htmltools, knitr, ordinal, rmarkdown, testthat (≥ 3.0.0)
Published: 2025-06-24
DOI: 10.32614/CRAN.package.vitals
Author: Simon Couch ORCID iD [aut, cre], Max Kuhn [ctb], Hadley Wickham ORCID iD [ctb], Mine Cetinkaya-Rundel ORCID iD [ctb], Posit Software, PBC ROR ID [cph, fnd]
Maintainer: Simon Couch <simon.couch at posit.co>
BugReports: https://github.com/tidyverse/vitals/issues
License: MIT + file LICENSE
URL: https://github.com/tidyverse/vitals, https://vitals.tidyverse.org
NeedsCompilation: no
Materials: README NEWS
CRAN checks: vitals results

Documentation:

Reference manual: vitals.pdf
Vignettes: Getting started with vitals (source, R code)
Writing evals for your LLM product (source, R code)

Downloads:

Package source: vitals_0.1.0.tar.gz
Windows binaries: r-devel: not available, r-release: vitals_0.1.0.zip, r-oldrel: vitals_0.1.0.zip
macOS binaries: r-release (arm64): vitals_0.1.0.tgz, r-oldrel (arm64): not available, r-release (x86_64): vitals_0.1.0.tgz, r-oldrel (x86_64): vitals_0.1.0.tgz

Linking:

Please use the canonical form https://CRAN.R-project.org/package=vitals to link to this page.