Chat with an OpenAI model

OpenAI provides a number of chat-based models, mostly under the ChatGPT brand. Note that a ChatGPT Plus membership does not grant access to the API. You will need to sign up for a developer account (and pay for it) at the developer platform.

For authentication, we recommend saving your API key to the OPENAI_API_KEY environment variable in your .Renviron file. You can easily edit this file by calling usethis::edit_r_environ().

Usage

chat_openai(
  system_prompt = NULL,
  turns = NULL,
  base_url = "https://api.openai.com/v1",
  api_key = openai_key(),
  model = NULL,
  seed = NULL,
  api_args = list(),
  echo = c("none", "text", "all")
)

Arguments

system_prompt

A system prompt to set the behavior of the assistant.

turns

A list of Turns to start the chat with (i.e., continuing a previous conversation). If not provided, the conversation begins from scratch.

base_url

The base URL to the endpoint; the default uses OpenAI.

api_key

The API key to use for authentication. You generally should not supply this directly, but instead set the OPENAI_API_KEY environment variable.

model

The model to use for the chat. The default, NULL, will pick a reasonable default, and tell you about. We strongly recommend explicitly choosing a model for all but the most casual use.

seed

Optional integer seed that ChatGPT uses to try and make output more reproducible.

api_args

Named list of arbitrary extra arguments appended to the body of every chat API call.

echo

One of the following options:

• none: don't emit any output (default when running in a function).

• text: echo text output as it streams in (default when running at the console).

• all: echo all input and output.

Note this only affects the chat() method.

Value

A Chat object.

See also

Other chatbots: chat_bedrock(), chat_claude(), chat_cortex(), chat_databricks(), chat_gemini(), chat_github(), chat_groq(), chat_ollama(), chat_perplexity()

Examples

chat <- chat_openai()
#> Using model = "gpt-4o".
chat$chat("
  What is the difference between a tibble and a data frame?
  Answer with a bulleted list
")
#> - **Class and Structure**:
#>   - A tibble is a modern version of the data frame, introduced in the 
#> `tibble` package, which is part of the tidyverse collection in R.
#>   - A data frame is the base R structure for storing tabular data.
#> 
#> - **Printing Behavior**:
#>   - Tibbles have a refined print method displaying only the first 10 rows
#> and the columns that fit on screen, providing a cleaner output.
#>   - Data frames print the whole dataset unless specifically instructed 
#> otherwise, which can be unwieldy for large datasets.
#> 
#> - **Column Types**:
#>   - Tibbles do not change the types of the input data: they respect 
#> column types and do not automatically convert strings to factors.
#>   - Data frames may automatically convert character vectors to factors 
#> unless stringsAsFactors is set to FALSE.
#> 
#> - **Subsetting**:
#>   - Subsetting a tibble with a single bracket (`[...]`) always returns a 
#> tibble, preserving the data frame structure.
#>   - With data frames, subsetting can return a vector if selecting a 
#> single column without the `drop = FALSE` argument.
#> 
#> - **Name Validation**:
#>   - Tibbles do not automatically rename or change invalid column names 
#> (e.g., names with spaces). They allow non-standard names by using 
#> backticks.
#>   - Data frames typically force names to adhere to valid R variable 
#> names, converting them as necessary.
#> 
#> - **Use within Tidyverse**:
#>   - Tibbles are integral to the tidyverse and are designed to work 
#> seamlessly with other tidy tools for data manipulation and visualization.
#>   - Data frames are the default R structure and are not as tightly 
#> integrated into the tidyverse toolkit.
#> 
#> - **Error and Warning Messages**:
#>   - Tibbles provide more user-friendly error and warning messages 
#> compared to the more generic messages returned by operations on data 
#> frames.
#> 
#> These differences make tibbles particularly useful when working within 
#> the tidyverse ecosystem, offering more intuitive and robust data handling
#> for modern data science workflows.

chat$chat("Tell me three funny jokes about statistcians")
#> Sure, here are three jokes about statisticians that might give you a 
#> chuckle:
#> 
#> 1. Why don’t statisticians play hide and seek?
#>    - Because good luck hiding from someone who always checks the outliers
#> first!
#> 
#> 2. How many statisticians does it take to change a light bulb?
#>    - Just one, but they’ll need to test 20 different light bulbs to 
#> determine the mean change time!
#> 
#> 3. Two statisticians walk into a bar. 
#>    - The third one ducks.
#> 
#> I hope these bring a smile to your face!