openaiRtools (version 0.2.2)

create_chat_completion: Create a Chat Completion (Convenience Function)

Description

A shortcut that automatically creates an OpenAI client from the OPENAI_API_KEY environment variable and calls client$chat$completions$create().

Usage

create_chat_completion(messages, model = "gpt-3.5-turbo", ...)

Value

A chat completion list object. Key fields:

• $choices[[1]]$message$content — The generated text

• $usage$total_tokens — Total tokens consumed

Arguments

messages

Required. List of message objects. Each must have role ("system", "user", "assistant") and content fields.

model

Character. Model ID. Default: "gpt-3.5-turbo".

...

Additional parameters passed to ChatCompletionsClient$create(), such as temperature, max_tokens, stream, etc.

Examples

if (FALSE) {
Sys.setenv(OPENAI_API_KEY = "sk-xxxxxx")

response <- create_chat_completion(
  messages = list(list(role = "user", content = "What is machine learning?")),
  model    = "gpt-4o"
)
cat(response$choices[[1]]$message$content)

# With extra parameters
response <- create_chat_completion(
  messages    = list(list(role = "user", content = "Write a poem")),
  model       = "gpt-4o",
  temperature = 1.2,
  max_tokens  = 200
)
}