lang-help.md
In lang: Translates R Help Documentation using Large Language Models

Interaction with LLM works

Code
  lang_help("llm_classify", "mall", lang = "spanish", type = "text")
Message
  v lang - Translation complete
Output
  _C_a_t_e_g_o_r_i_z_e _d_a_t_a _a_s _o_n_e _o_f _o_p_t_i_o_n_s _g_i_v_e_n

  _D_e_s_c_r_i_p_t_i_o_n:

       Use a Large Language Model (LLM) to classify the provided text as
       one of the options provided via the 'labels' argument.

  _U_s_a_g_e:

       llm_classify(
         .data,
         col,
         labels,
         pred_name = ".classify",
         additional_prompt = ""
       )

       llm_vec_classify(x, labels, additional_prompt = "", preview = FALSE)

  _A_r_g_u_m_e_n_t_s:

     .data: A 'data.frame' or 'tbl' object that contains the text to be
            analyzed

       col: The name of the field to analyze, supports 'tidy-eval'

    labels: A character vector with at least 2 labels to classify the
            text as

  pred_name: A character vector with the name of the new column where the
            prediction will be placed

  additional_prompt: Inserts this text into the prompt sent to the LLM

         x: A vector that contains the text to be analyzed

   preview: It returns the R call that would have been used to run the
            prediction. It only returns the first record in 'x'. Defaults
            to 'FALSE' Applies to vector function only.

  _V_a_l_u_e:

       'llm_classify' returns a 'data.frame' or 'tbl' object.
       'llm_vec_classify' returns a vector that is the same length as
       'x'.

  _E_x_a_m_p_l_e_s:

       library(mall)

       data("reviews")

       llm_use("ollama", "llama3.2", seed = 100, .silent = TRUE)

       llm_classify(reviews, review, c("appliance", "computer"))

       # Use 'pred_name' to customize the new column's name
       llm_classify(
         reviews,
         review,
         c("appliance", "computer"),
         pred_name = "prod_type"
       )

       # Pass custom values for each classification
       llm_classify(reviews, review, c("appliance" ~ 1, "computer" ~ 2))

       # For character vectors, instead of a data frame, use this function
       llm_vec_classify(
         c("this is important!", "just whenever"),
         c("urgent", "not urgent")
       )

       # To preview the first call that will be made to the downstream R function
       llm_vec_classify(
         c("this is important!", "just whenever"),
         c("urgent", "not urgent"),
         preview = TRUE
       )

Code
  lang_help("llm_classify", "mall", lang = "english", type = "text")
Condition
  Error in `lang_help()`:
  ! Language already set to English, use `help()`

Code
  lang_help("nothere", lang = "spanish", type = "text")
Condition
  Error in `rd_find()`:
  ! Could not find `nothere`
  i Tip: Make sure the containing package is loaded, and the topic is spelled correctly

Code
  lang_help("nothere", "notpkg", lang = "spanish", type = "text")
Condition
  Error in `rd_find()`:
  ! Package `notpkg` not found
  i Tip: Make sure package name is spelled correctly

Code
  lang_help("nothere", "mall", lang = "spanish", type = "text")
Condition
  Error in `rd_find()`:
  ! `nothere` could not be found in `mall`
  i Tip: Make sure both are spelled correctly