Package: vitals 0.3.0.9001

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.
Authors:
vitals_0.3.0.9001.tar.gz
vitals_0.3.0.9001.zip(r-4.7)vitals_0.3.0.9001.zip(r-4.6)vitals_0.3.0.9001.zip(r-4.5)
vitals_0.3.0.9001.tgz(r-4.6-any)vitals_0.3.0.9001.tgz(r-4.5-any)
vitals_0.3.0.9001.tar.gz(r-4.7-any)vitals_0.3.0.9001.tar.gz(r-4.6-any)
vitals_0.3.0.9001.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
vitals/json (API)
| # Install 'vitals' in R: |
| install.packages('vitals', repos = c('https://tidyverse.r-universe.dev', 'https://cloud.r-project.org')) |
Bug tracker:https://github.com/tidyverse/vitals/issues
Pkgdown/docs site:https://vitals.tidyverse.org
- are - An R Eval
Last updated from:e1ad045bba. Checks:7 NOTE, 2 OK. Indexed: yes.
| Target | Result | Time | Files | Syslog |
|---|---|---|---|---|
| linux-devel-x86_64 | NOTE | 216 | ||
| source / vignettes | OK | 268 | ||
| linux-release-x86_64 | NOTE | 188 | ||
| macos-release-arm64 | NOTE | 105 | ||
| macos-oldrel-arm64 | NOTE | 89 | ||
| windows-devel | NOTE | 108 | ||
| windows-release | NOTE | 103 | ||
| windows-oldrel | NOTE | 123 | ||
| wasm-release | OK | 144 |
Exports:detect_answerdetect_exactdetect_includesdetect_matchdetect_patterngenerategenerate_structuredmodel_graded_factmodel_graded_qaTaskvitals_bindvitals_bundlevitals_log_dirvitals_log_dir_setvitals_log_readvitals_view
Dependencies:askpassclicorocpp11curldplyrellmerfastmapgenericsgluehttpuvhttr2jsonlitelaterlifecyclemagrittropensslotelpillarpkgconfigpromisespurrrR6RcpprlangS7stringistringrsystibbletidyrtidyselectutf8vctrswithr
Readme and manuals
Help Manual
| Help page | Topics |
|---|---|
| An R Eval | are |
| Convert a chat to a solver function | generate |
| Convert a chat to a solver function with structured output | generate_structured |
| Scoring with string detection | detect_answer detect_exact detect_includes detect_match detect_pattern scorer_detect |
| Model-based scoring | model_graded_fact model_graded_qa scorer_model |
| Creating and evaluating tasks | Task |
| Concatenate task samples for analysis | vitals_bind |
| Prepare logs for deployment | vitals_bundle |
| The log directory | vitals_log_dir vitals_log_dir_set |
| Read an eval log back into ellmer chats | vitals_log_read |
| Interactively view local evaluation logs | vitals_view |
