Skip to contents

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

Source: R/LLM_parallel_utils.R
call_llm_par.Rd

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 = 3,
  verbose = FALSE,
  memoize = FALSE,
  max_workers = NULL,
  progress = FALSE,
  json_output = NULL
)

Arguments

experiments

A tibble/data.frame with required list-columns 'config' (llm_config objects) and 'messages' (character vector OR message list).

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 3.

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.

Value

A tibble containing all original columns plus:

  • response_text – assistant text (or NA on failure)

  • raw_response_json – raw JSON string

  • success, error_message

  • finish_reason – e.g. "stop", "length", "filter", "tool", or "error:category"

  • sent_tokens, rec_tokens, total_tokens, reasoning_tokens

  • response_id

  • duration – seconds

  • response – the full llmr_response object (or NA on failure)

The response column holds llmr_response objects on success, or NULL on failure.

Parallel Workflow

All parallel functions require the future backend to be configured. The recommended workflow is:

  1. Call setup_llm_parallel() once at the start of your script.

  2. Run one or more parallel experiments (e.g., call_llm_broadcast()).

  3. Call reset_llm_parallel() at the end to restore sequential processing.

See also

For setting up the environment: setup_llm_parallel, reset_llm_parallel. For simpler, pre-configured parallel tasks: call_llm_broadcast, call_llm_sweep, call_llm_compare. For creating experiment designs: build_factorial_experiments.

Examples

if (FALSE) { # \dontrun{
# Simple example: Compare two models on one prompt
cfg1 <- llm_config("openai", "gpt-4.1-nano")
cfg2 <- llm_config("groq", "llama-3.3-70b-versatile")

experiments <- tibble::tibble(
  model_id = c("gpt-4.1-nano", "groq-llama-3.3"),
  config = list(cfg1, cfg2),
  messages = "Count the number of the letter e in this word: Freundschaftsbeziehungen "
)

setup_llm_parallel(workers = 2)
results <- call_llm_par(experiments, progress = TRUE)
reset_llm_parallel()

print(results[, c("model_id", "response_text")])

} # }