{"Type":"Package","Package":"gptstudio","Title":"Use Large Language Models Directly in your Development\nEnvironment","Version":"0.4.0","Authors@R":"c(\nperson(\"Michel\", \"Nivard\", , \"m.g.nivard@vu.nl\", role = c(\"aut\", \"cph\")),\nperson(\"James\", \"Wade\", , \"github@jameshwade.com\", role = c(\"aut\", \"cre\", \"cph\"),\ncomment = c(ORCID = \"0000-0002-9740-1905\")),\nperson(\"Samuel\", \"Calderon\", , \"samuel.calderon@uarm.pe\", role = \"aut\",\ncomment = c(ORCID = \"0000-0001-6847-1210\"))\n)","Maintainer":"James Wade ","Description":"Large language models are readily accessible via API. This\npackage lowers the barrier to use the API inside of your development\nenvironment. For more on the API, see\n.","License":"MIT + file LICENSE","URL":"https://github.com/MichelNivard/gptstudio,\nhttps://michelnivard.github.io/gptstudio/","BugReports":"https://github.com/MichelNivard/gptstudio/issues","Depends":"R (>= 4.0)","Imports":"assertthat, bslib (>= 0.6.0), cli, colorspace, curl,\nfontawesome, glue, grDevices, htmltools, htmlwidgets, httr2,\nids, jsonlite, magrittr, purrr, R6, rlang, rstudioapi (>=\n0.12), rvest, shiny, shiny.i18n, SSEparser, stringr (>= 1.5.0),\nutils, waiter, yaml","Suggests":"AzureRMR, knitr, mockr, rmarkdown, shinytest2, spelling,\ntestthat (>= 3.0.0), withr","Config/testthat/edition":"3","Config/testthat/parallel":"true","Encoding":"UTF-8","Language":"en-US","RoxygenNote":"7.3.1","VignetteBuilder":"knitr","NeedsCompilation":"no","Packaged":"2024-05-20 13:29:30 UTC; ua21849","Author":"Michel Nivard [aut, cph],\nJames Wade [aut, cre, cph] (),\nSamuel Calderon [aut] ()","Repository":"CRAN","Date/Publication":"2024-05-21 11:21:21 UTC","repoType":"cran","tarballUrl":"ftp://cran.r-project.org/pub/R/src/contrib/gptstudio_0.4.0.tar.gz","jsonAuthors":[{"name":"Michel Nivard","email":"m.g.nivard@vu.nl","maintainer":false},{"name":"James Wade","email":"github@jameshwade.com","maintainer":true},{"name":"Samuel Calderon","email":"samuel.calderon@uarm.pe","maintainer":false}],"readme":"\n\n\n# gptstudio

\n\n\n\n[![Lifecycle:\nmaturing](https://img.shields.io/badge/lifecycle-experimental-orange.svg)](https://lifecycle.r-lib.org/articles/stages.html#experimental)\n[![CRAN\nstatus](https://www.r-pkg.org/badges/version/gptstudio)](https://CRAN.R-project.org/package=gptstudio)\n[![Codecov test\ncoverage](https://codecov.io/gh/MichelNivard/gptstudio/branch/main/graph/badge.svg)](https://app.codecov.io/gh/MichelNivard/gptstudio?branch=main)\n[![R-CMD-check](https://github.com/MichelNivard/gptstudio/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/MichelNivard/gptstudio/actions/workflows/R-CMD-check.yaml)\n[![CRAN RStudio mirror\ndownloads](http://cranlogs.r-pkg.org/badges/gptstudio)](https://www.r-pkg.org/pkg/gptstudio)\n[![CRAN RStudio mirror\ndownloads](http://cranlogs.r-pkg.org/badges/grand-total/gptstudio)](https://www.r-pkg.org/pkg/gptstudio)\n\n\n\nThe goal of gptstudio is for R programmers to easily incorporate use of\nlarge language models (LLMs) into their project workflows. These models\nappear to be a step change in our use of text for knowledge work, but\nyou should carefully consider ethical implications of using these\nmodels.\n\nFor further addins, tailored for R developers, also see the sister\npackage: [gpttools](https://jameshwade.github.io/gpttools/)\n\n## Getting Started: Installation & AI Service Setup\n\n``` r\ninstall.packages(\"gptstudio\")\n```\n\nTo get a bug fix or to use a feature from the development version, you\ncan install the development version of this package from GitHub.\n\n``` r\n# install.packages(\"pak\")\npak::pak(\"MichelNivard/gptstudio\")\n```\n\n### Available AI Services and Models\n\n| AI Service | Models | Documentation | Setup |\n|------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------|\n| [OpenAI](https://platform.openai.com) | gpt-4-turbo, gpt-4, gpt-3.5-turbo ([latest models](https://platform.openai.com/docs/models)) | [OpenAI API Docs](https://platform.openai.com/docs/api-reference) | [OpenAI Setup](https://michelnivard.github.io/gptstudio/articles/openai.html) |\n| [HuggingFace](https://huggingface.co/) | various | [HF Inference API Docs](https://huggingface.co/docs/hub/models-inference) | [HF Setup](https://michelnivard.github.io/gptstudio/articles/huggingface.html) |\n| [Anthropic](https://docs.anthropic.com/claude/docs/guide-to-anthropics-prompt-engineering-resources) | claude-2.1, claude-instant-1.2 | [Anthropic API Docs](https://docs.anthropic.com/claude/reference/getting-started-with-the-api) | [Anthropic Setup](https://michelnivard.github.io/gptstudio/articles/anthropic.html) |\n| [Ollama](https://ollama.com/) | mistral, llama2, mixtral, phi ([latest models](https://ollama.com/library)) | [Ollama API Docs](https://github.com/ollama/ollama/blob/main/docs/api.md) | [Ollama Setup](https://michelnivard.github.io/gptstudio/articles/ollama.html) |\n| [Perplexity](https://www.perplexity.ai) | pplx-7b-chat, pplx-70b-chat, pplx-7b-online, pplx-70b-online, llama-2-70b-chat, codellama-34b-instruct, mistral-7b-instruct, and mixtral-8x7b-instruct | [Perplexity API Docs](https://docs.perplexity.ai/reference/post_chat_completions) | [Perplexity Setup](https://michelnivard.github.io/gptstudio/articles/perplexity.html) |\n| [Google AI Studio](https://ai.google.dev/tutorials/ai-studio_quickstart) | Gemini and Palm (legacy) | [Google AI Studio Docs](https://ai.google.dev/docs) | [Google AI Studio Setup](https://michelnivard.github.io/gptstudio/articles/google.html) |\n| [Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-services/openai/overview) | gpt-4, gpt-3.5-turbo ([latest models](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models#gpt-4-and-gpt-4-turbo-preview)) | [Azure OpenAI API Docs](https://learn.microsoft.com/en-us/azure/ai-services/openai/quickstart?tabs=command-line,python&pivots=rest-api) | [Azure OpenAI Setup](https://michelnivard.github.io/gptstudio/articles/azure.html) |\n| [Cohere](https://cohere.com/) | command, command-light, command-nightly, command-light-nightly | [Cohere API Docs](https://docs.cohere.com/) | [Cohere Setup](https://michelnivard.github.io/gptstudio/articles/cohere.html) |\n\n### Default AI Service: OpenAI\n\nTo get started, you must first set up an API service. The package is\nconfigured to work with several AI service providers, allowing for\nflexibility and choice based on your specific needs. The default\nconfiguration is set to use OpenAI’s services. To use it you need:\n\n1. Make an OpenAI account. [Sign up here](https://openai.com/api/).\n\n2. [Create an OpenAI API\n key](https://platform.openai.com/account/api-keys) to use with the\n package.\n\n3. Set the API key up in Rstudio. See the section below on configuring\n the API key.\n\n#### Configuring OpenAI API Key\n\nTo interact with the OpenAI API, it’s required to have a valid\n`OPENAI_API_KEY` environment variable. Here are the steps to configure\nit.\n\nYou can establish this environment variable globally by including it in\nyour project’s .Renviron file. This approach ensures that the\nenvironment variable persists across all sessions as the Shiny app runs\nin the background.\n\nHere is a set of commands to open the .Renviron file for modification:\n\n``` r\nrequire(usethis)\nedit_r_environ()\n```\n\nFor a persistent setting that loads every time you launch this project,\nadd the following line to .Renviron, replacing `\"\"` with your\nactual API key:\n\n``` bash\nOPENAI_API_KEY=\"\"\n```\n\n**Caution:** If you’re using version control systems like GitHub or\nGitLab, remember to include .Renviron in your .gitignore file to prevent\nexposing your API key!\n\n**Important Note:** OpenAI API will not function without valid payment\ndetails entered into your OpenAI account. This is a restriction imposed\nby OpenAI and is unrelated to this package.\n\n### Alternative AI Service Providers\n\nWhile OpenAI is the default and currently considered one of the most\nrobust options, `gptstudio` is also compatible with other AI service\nproviders. These include\n[Anthropic](https://michelnivard.github.io/gptstudio/articles/anthropic.html),\n[HuggingFace](https://michelnivard.github.io/gptstudio/articles/huggingface.html),\n[Google AI\nStudio](https://michelnivard.github.io/gptstudio/articles/google.html),\n[Azure\nOpenAI](https://michelnivard.github.io/gptstudio/articles/azure.html),\nand\n[Perplexity](https://michelnivard.github.io/gptstudio/articles/perplexity.html).\nYou can select any of these providers based on your preference or\nspecific requirements. You can also run local models with\n[Ollama](https://michelnivard.github.io/gptstudio/articles/ollama.html).\nThis requires more setup but at the benefit of not sharing your data\nwith any third party.\n\nTo use an alternative provider, you will need to obtain the relevant API\nkey or access credentials from the chosen provider and configure them\nsimilarly.\n\n## Privacy Notice for gptstudio\n\nThis privacy notice is applicable to the R package that uses popular\nlanguage models like gpt-4 turbo and claude-2.1. By using this package,\nyou agree to adhere to the privacy terms and conditions set by the API\nservice.\n\n### Data Sharing with AI Services\n\nWhen using this R package, any text or code you highlight/select with\nyour cursor, or the prompt you enter within the built-in applications,\nwill be sent to the selected AI service provider (e.g., OpenAI,\nAnthropic, HuggingFace, Google AI Studio, Azure OpenAI) as part of an\nAPI request. This data sharing is governed by the privacy notice, rules,\nand exceptions that you agreed to with the respective service provider\nwhen creating an account.\n\n### Security and Data Usage by AI Service Providers\n\nWe cannot guarantee the security of the data you send via the API to any\nAI service provider, nor can we provide details on how each service\nprocesses or uses your data. However, these providers often state that\nthey use prompts and results to enhance their AI models, as outlined in\ntheir terms of use. Be sure to review the terms of use of the respective\nAI service provider directly.\n\n### Limiting Data Sharing\n\nThe R package is designed to share only the text or code that you\nspecifically highlight/select or include in a prompt through our\nbuilt-in applications. No other elements of your R environment will be\nshared unless you turn those features on. It is your responsibility to\nensure that you do not accidentally share sensitive data with any AI\nservice provider.\n\n**IMPORTANT: To maintain the privacy of your data, do not highlight,\ninclude in a prompt, or otherwise upload any sensitive data, code, or\ntext that should remain confidential.**\n\n## Code of Conduct\n\nPlease note that the gptstudio project is released with a [Contributor\nCode of\nConduct](https://github.com/MichelNivard/gptstudio/blob/main/.github/CODE_OF_CONDUCT.md).\nBy contributing to this project, you agree to abide by its terms.","jobInfo":{"package":"gptstudio","version":"0.4.0","parsingStatus":"success","parserVersion":2,"parsedAt":"2024-05-21T13:30:12+0000"}}

Description

Usage

Arguments

Value

Examples