The hardware and bandwidth for this mirror is donated by dogado GmbH, the Webhosting and Full Service-Cloud Provider. Check out our Wordpress Tutorial.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]dogado.de.

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: vitals_0.1.0.zip, 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.

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.
Health stats visible at Monitor.