Ask a large language model (LLM) any question you want about a vector of text or the text from a search_text().
Usage
llm(
text,
query,
text_col = "text",
model = llm_model(),
maxTokens = 1024,
temperature = 0.5,
top_p = 0.95,
seed = sample(1e+06:9999999, 1),
API_KEY = Sys.getenv("GROQ_API_KEY")
)Arguments
- text
The text to send to the LLM (vector of strings, or data frame with the text in a column)
- query
The query to ask of the LLM
- text_col
The name of the text column if text is a data frame
- model
the LLM model name (see
llm_model_list())- maxTokens
The maximum integer of completion tokens returned per query
- temperature
Controls randomness in responses. Lower values make responses more deterministic. Recommended range: 0.5-0.7 to prevent repetitions or incoherent outputs; valued between 0 inclusive and 2 exclusive
- top_p
Nucleus sampling threshold (between 0 and 1); usually alter this or temperature, but not both
- seed
Set for reproducible responses
- API_KEY
your API key for the LLM
Details
You will need to get your own API key from https://console.groq.com/keys. To avoid having to type it out, add it to the .Renviron file in the following format (you can use usethis::edit_r_environ() to access the .Renviron file)
GROQ_API_KEY="key_value_asdf"
See https://console.groq.com/docs for more information
Examples
# \donttest{
text <- c("hello", "number", "ten", 12)
query <- "Is this a number? Answer only 'TRUE' or 'FALSE'"
is_number <- llm(text, query)
#> You have 996 of 1000 requests left (reset in 5m45.434s) and 11900 of 12000 tokens left (reset in 498ms).
is_number
#> text answer time tokens
#> 1 hello FALSE 0.01120917 52
#> 2 number TRUE 0.01939102 52
#> 3 ten FALSE 0.01854389 52
#> 4 12 TRUE 0.01177878 52
# }