shipwithjev

Catalog / Tools & apps

0292GitHub

jevr

Native R client for typed questions and provider-independent answers through TypeSafe or OpenRouter.

simxnherrera/jevrREADME ↗
- [jevr](#jevr)
  - [Installation](#installation)
  - [Authentication](#authentication)
  - [Basic usage](#basic-usage)
  - [Question types](#question-types)
  - [Providers](#providers)
  - [Listing models](#listing-models)
  - [Versioned specifications and multiple
    states](#versioned-specifications-and-multiple-states)
  - [Response object](#response-object)

<!-- README.md is generated from README.Rmd. Please edit that file -->

# jevr

<!-- badges: start -->

[](https://github.com/simxnherrera/jevr/actions/workflows/R-CMD-check.yaml)
<!-- badges: end -->

`jevr` is an R client for [JEV / TypeSafe System
One](https://docs.typesafe.ai/concepts/system-one). It sends a state and
a set of typed questions to a model and returns structured answers that
can be used directly in R.

JEV is designed for structured decisions rather than conversational
chat. The package supports multiple questions in one evaluation,
probabilities, confidence, usage, and provider metadata.

## Installation

Install the development version from GitHub:

``` r
install.packages("pak")
pak::pak("simxnherrera/jevr")
```

Once `jevr` is available on CRAN, the stable version can be installed
with:

``` r
install.packages("jevr")
```

## Authentication

Set the API key for the provider you want to use in your `.Renviron`
file:

``` r
usethis::edit_r_environ()
```

``` text
# Direct TypeSafe requests
TYPESAFE_API_KEY=your_typesafe_key

# OpenRouter requests
OPENROUTER_API_KEY=your_openrouter_key
```

Keys are read when `jev_ask()` is called and are not included in
returned objects.

## Basic usage

Define one or more questions, then pass them together with the state to
`jev_ask()`:

``` r
library(jevr)

questions <- list(
  department = jev_choice(
    instructions = "Which team should handle this?",
 

Also filed under Tools & apps

  1. 0616

    Jevstiller: distill Jev calls into a local model

    A self-hosted proxy that trains a local model on Jev's answers. It served 72% of Banking77 locally at 15 ms, with a 2% audit and a bound on disagreement.

    tomerglick57 · Tools & apps · 15 ms local

  2. 0611

    Scruple: code checks for what linters miss

    Semantic-aware linting with System One models: rules you can state in a sentence, checked against your code by Jev.

    @nalexpeae · Tools & apps

  3. 0606

    Algolia-style Postgres search with a Jev reranker

    Typo tolerance, typeahead, barcodes and facet counts in plain Postgres SQL, plus an optional Jev step that asks one question per top-10 result.

    @alex_forman1 · Tools & apps

  4. 0604

    Virtual Closet: outfits from closet videos

    built a virtual closet & outfit generator from raw closet videos. classification + semantic search thanks to jev 🥰. clueless closet dreams finally coming to life

    @maitreemervana · Tools & apps