Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/irudnyts/openai
An R package-wrapper around OpenAI API
https://github.com/irudnyts/openai
api ml nlp openai package r
Last synced: 3 months ago
JSON representation
An R package-wrapper around OpenAI API
- Host: GitHub
- URL: https://github.com/irudnyts/openai
- Owner: irudnyts
- License: other
- Created: 2022-05-10T11:12:59.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2024-01-26T20:12:11.000Z (10 months ago)
- Last Synced: 2024-08-12T00:53:54.077Z (3 months ago)
- Topics: api, ml, nlp, openai, package, r
- Language: R
- Homepage: https://irudnyts.github.io/openai/
- Size: 1.9 MB
- Stars: 162
- Watchers: 8
- Forks: 28
- Open Issues: 33
-
Metadata Files:
- Readme: README.Rmd
- License: LICENSE
Awesome Lists containing this project
- jimsghstars - irudnyts/openai - An R package-wrapper around OpenAI API (R)
README
---
output: github_document
---
```{r, include = FALSE}
knitr::opts_chunk$set(
collapse = TRUE,
comment = "#>",
fig.path = "man/figures/README-",
out.width = "100%"
)
```
# openai 
[](https://github.com/irudnyts/openai/actions)
[](https://app.codecov.io/gh/irudnyts/openai?branch=main)
[](https://CRAN.R-project.org/package=openai)
[](https://cranlogs.r-pkg.org/badges/grand-total/openai?color=brightgreen)
> :warning: **Note:** :warning: OpenAI introduced major changes in package's version 1.0.0. Since the idea of this package is to mimic OpenAI's official Python package, from now on, everything will be re-written in object-oriented way. Current implementation will be gradually and gently depricated. One can install the development verion using:
>```
> remotes::install_github("irudnyts/openai", ref = "r6")
> ```
> Then, the code will look like:
> ```
> library(openai)
> client <- OpenAI()
> completion <- client$chat$completions$create(
> model = "gpt-3.5-turbo",
> messages = list(list("role" = "user", "content" = "What's up?"))
> )
> ```
## Overview
`{openai}` is an R wrapper of OpenAI API endpoints. This package covers Models, Completions, Chat, Edits, Images, Embeddings, Audio, Files, Fine-tunes, Moderations, and legacy Engines endpoints. The latter endpoints, namely Engines, are left for backward compatibility and will be removed soon.
## Installation
The easiest way to install `{openai}` from CRAN is to use the "official" `install.packages()` function:
```{r, eval = FALSE}
install.packages("openai")
```
You can also install the development version of `{openai}` from [GitHub](https://github.com/), which uses the latest version of official OpenAI's Python package:
```{r, eval = FALSE}
if (!require(remotes))
install.packages("remotes")
remotes::install_github("irudnyts/openai", ref = "r6")
```
## Authentication
To use the OpenAI API, you need to provide an API key. First, sign up for OpenAI API on [this page](https://openai.com/api/). Once you signed up and logged in, you need to open [this page](https://platform.openai.com), click on **Personal**, and select **View API keys** in drop-down menu. You can then copy the key by clicking on the green text **Copy**.
By default, functions of `{openai}` will look for `OPENAI_API_KEY` environment variable. If you want to set a global environment variable, you can use the following command (where `xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx` should be replaced with your actual key):
```{r, eval = FALSE}
Sys.setenv(
OPENAI_API_KEY = 'xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx'
)
```
Otherwise, you can add the key to the `.Renviron` file of the project. The following commands will open `.Renviron` for editing:
```{r, eval = FALSE}
if (!require(usethis))
install.packages("usethis")
usethis::edit_r_environ(scope = "project")
```
You can add the following line to the file (again, replace `xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx` with your actual key):
```{r, eval = FALSE}
OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
```
**Note:** If you are using GitHub/Gitlab, do not forget to add `.Renviron` to `.gitignore`!
Finally, you can always provide the key manually to the functions of the package.
## Example
Functions of `{openai}` have self-explanatory names. For example, to create a completion, one can use `create_completion()` function:
```{r, eval=FALSE}
library(openai)
create_completion(
model = "ada",
prompt = "Generate a question and an answer"
)
#> $id
#> [1] "cmpl-6MiImjcaCSuQYY6u8UA2Mm0rCdbEo"
#>
#> $object
#> [1] "text_completion"
#>
#> $created
#> [1] 1670871532
#>
#> $model
#> [1] "ada"
#>
#> $choices
#> text
#> 1 within 5 minutes, up to an hour depending on how your users are different and
#> index logprobs finish_reason
#> 1 0 NA length
#>
#> $usage
#> $usage$prompt_tokens
#> [1] 7
#>
#> $usage$completion_tokens
#> [1] 16
#>
#> $usage$total_tokens
#> [1] 23
```
Further, one can generate an image using DALL·E text-to-image model with `create_image()`:
```{r, eval=FALSE}
create_image("An astronaut riding a horse in a photorealistic style")
```
```{r, echo=FALSE, out.width = "256px", fig.align = "center"}
knitr::include_graphics("man/figures/astronaut.png")
```
It is also possible to use ChatGPT's `gpt-3.5-turbo` model via `create_chat_completion()`:
```{r, eval=FALSE}
create_chat_completion(
model = "gpt-3.5-turbo",
messages = list(
list(
"role" = "system",
"content" = "You are a helpful assistant."
),
list(
"role" = "user",
"content" = "Who won the world series in 2020?"
),
list(
"role" = "assistant",
"content" = "The Los Angeles Dodgers won the World Series in 2020."
),
list(
"role" = "user",
"content" = "Where was it played?"
)
)
)
#> $id
#> [1] "chatcmpl-6r7N6YXcMhg8xmVM4ohOcAmzPOy3f"
#>
#> $object
#> [1] "chat.completion"
#>
#> $created
#> [1] 1678117740
#>
#> $model
#> [1] "gpt-3.5-turbo-0301"
#>
#> $usage
#> $usage$prompt_tokens
#> [1] 56
#>
#> $usage$completion_tokens
#> [1] 19
#>
#> $usage$total_tokens
#> [1] 75
#>
#>
#> $choices
#> finish_reason index message.role
#> 1 stop 0 assistant
#> message.content
#> 1 The 2020 World Series was played at Globe Life Field in Arlington, Texas.
```
Finally, the speech-to-text [Whisper](https://openai.com/research/whisper) is available via `create_transcription()` and `create_translation()`:
```{r, eval=FALSE}
voice_sample_ua <- system.file("extdata", "sample-ua.m4a", package = "openai")
create_translation(file = voice_sample_ua, model = "whisper-1")
#> $text
#> [1] "I want to check how this model works"
```