Package: tinyeval 0.11.1

evalship

tinyeval: Evals for the AI Calls in Your R Code

Bundles 'tinyeval', one bash script that runs test cases against the AI calls in your app and checks their replies. run() starts it, and worker() answers its test cases from your R code, loaded once.

Authors:evalship [aut, cre, cph]

tinyeval_0.11.1.tar.gz
tinyeval_0.11.1.zip(r-4.7-any)tinyeval_0.11.1.zip(r-4.6-any)tinyeval_0.11.1.zip(r-4.5-any)
tinyeval_0.11.1.tgz(r-4.6-any)tinyeval_0.11.1.tgz(r-4.5-any)
tinyeval_0.11.1.tar.gz(r-4.7-any)tinyeval_0.11.1.tar.gz(r-4.6-any)
tinyeval_0.11.1.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION
card.svg |card.png
tinyeval/json (API)

# Install 'tinyeval' in R:
install.packages('tinyeval', repos = c('https://evalship-hq.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/evalship-hq/tinyeval/issues

On CRAN:

Conda:

ai-testingbashdartelixirevalsfluttergogolangjavakotlinlaravelllmllm-as-a-judgellm-evaluationphpprompt-testingrailsrubyrustswift

2.00 score 1 stars 7 scripts 3 exports 0 dependencies

Last updated from:76d25060a4 (on r-universe). Checks:9 OK. Indexed: yes.

TargetResultTimeFilesSyslog
linux-develOK84
source / vignettesOK201
linux-releaseOK105
macos-releaseOK112
macos-oldrelOK90
windows-develOK168
windows-releaseOK146
windows-oldrelOK177
wasm-releaseOK78

Exports:couldnt_runrunworker

Dependencies: