LLMR (version 0.4.2)

call_llm_par: Parallel LLM Processing with Tibble-Based Experiments (Core Engine)

Description

Processes experiments from a tibble where each row contains a config and message pair. This is the core parallel processing function. Metadata columns are preserved. This function requires setting up the parallel environment using `setup_llm_parallel`.

Usage

call_llm_par(
  experiments,
  simplify = TRUE,
  tries = 10,
  wait_seconds = 2,
  backoff_factor = 2,
  verbose = FALSE,
  memoize = FALSE,
  max_workers = NULL,
  progress = FALSE,
  json_output = NULL
)

Value

A tibble containing all original columns from experiments (metadata, config, messages), plus new columns: response_text, raw_response_json (the raw JSON string from the API), success, error_message, duration (in seconds).

Arguments

experiments

A tibble/data.frame with required list-columns 'config' (llm_config objects) and 'messages' (message lists). Additional columns are treated as metadata and preserved.

simplify

Whether to cbind 'experiments' to the output data frame or not.

tries

Integer. Number of retries for each call. Default is 10.

wait_seconds

Numeric. Initial wait time (seconds) before retry. Default is 2.

backoff_factor

Numeric. Multiplier for wait time after each failure. Default is 2.

verbose

Logical. If TRUE, prints progress and debug information.

memoize

Logical. If TRUE, enables caching for identical requests.

max_workers

Integer. Maximum number of parallel workers. If NULL, auto-detects.

progress

Logical. If TRUE, shows progress bar.

json_output

Deprecated. Raw JSON string is always included as raw_response_json. This parameter is kept for backward compatibility but has no effect.

Examples

if (FALSE) {
  library(dplyr)
  library(tidyr)

  # Build experiments with expand_grid
  experiments <- expand_grid(
    condition = c("control", "treatment"),
    model_type = c("small", "large"),
    rep = 1:10
  ) |>
    mutate(
      config = case_when(
        model_type == "small" ~ list(small_config),
        model_type == "large" ~ list(large_config)
      ),
      messages = case_when(
        condition == "control" ~ list(control_messages),
        condition == "treatment" ~ list(treatment_messages)
      )
    )

  setup_llm_parallel(workers = 4)
  results <- call_llm_par(experiments, progress = TRUE)
  reset_llm_parallel()

  # All metadata preserved for analysis
  results |>
    group_by(condition, model_type) |>
    summarise(mean_response = mean(as.numeric(response_text), na.rm = TRUE))
}