llm_fn | R Documentation |
Apply an LLM prompt over vectors/data frames
llm_fn(
x,
prompt,
.config,
.system_prompt = NULL,
...,
.return = c("text", "columns", "object")
)
x |
A character vector or a data.frame/tibble. |
prompt |
A glue template string. With a data-frame you may reference
columns ( |
.config |
An llm_config object. |
.system_prompt |
Optional system message (character scalar). |
... |
Passed unchanged to |
.return |
One of |
For generative mode:
.return = "text"
: character vector
.return = "columns"
: tibble with diagnostics
.return = "object"
: list of llmr_response
(or NA
on failure)
For embedding mode, always a numeric matrix.
llm_mutate()
, setup_llm_parallel()
, call_llm_broadcast()
if (interactive()) {
words <- c("excellent","awful")
cfg <- llm_config("openai","gpt-4o-mini", temperature = 0)
llm_fn(words, "Classify '{x}' as Positive/Negative.",
cfg,
.system_prompt="One word.",
.return="columns")
}
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.