Skip to contents

set up an online LLM API for subsequent tasks

Source: R/setupAgent.R
setupAgent.Rd

This function sets up an large language model API for tasks.

Usage

setupAgent(
  name = c("openai", "replicate", "generic"),
  type = NULL,
  model = NULL,
  url = NULL,
  ai_api_key = Sys.getenv("AI_API_KEY")
)

Arguments

name

A string for the name of the API, one of "openai", "replicate" or "generic". Currently supported APIs are "openai" and "replicate". If the user wishes to use another API that has similar syntax to openai API this is also supported via the the "generic" option. In this case, the user should also provide a url for the API using the

type

Specify type of model (chat or completion). This parameter only needs to be specified when using 'openai

model

LLM model you wish to use. For openAI chat model examples are:

  • 'gtp-3-5-turbo'

  • 'gtp-4'

For openAI completion models examples are:

  • 'text-curie-001'

  • 'text-davinci-002'

For replicate models examples are:

  • llama-2-70b-chat ( as '02e509c789964a7ea8736978a43525956ef40397be9033abf9fd2badfe68c9e3')

  • llama-2-13b-chat ( as 'f4e2de70d66816a838a89eeeb621910adffb0dd0baba3976c96980970978018d')

For a full list of openAI models see https://platform.openai.com/docs/models/overview/. For a full list of Replicate models, see https://replicate.com/collections/language-models.

url

the url for the API in case the API "generic" is selected. (Default: NULL)

ai_api_key

personal API key for accessing LLM

Value

A list holding agent information.

Examples

{
myAgent <- setupAgent(name="openai",type="chat",model="gpt-4",ai_api_key="my_key")

myAgent <- setupAgent(name="replicate",type=NULL,
                     model="02e509c789964a7ea8736978a43525956ef40397be9033abf9fd2badfe68c9e3",
                     ai_api_key="my_key")
}