Process a batch of prompts with a parallel chat

Usage

batch.future_chat(
  chat_env,
  prompts,
  type_spec = NULL,
  judgements = 0,
  state_path = tempfile("chat_", fileext = ".rds"),
  workers = NULL,
  chunk_size = parallel::detectCores() * 5,
  plan = "multisession",
  max_chunk_attempts = 3L,
  max_retries = 3L,
  initial_delay = 20,
  max_delay = 80,
  backoff_factor = 2,
  beep = TRUE,
  progress = TRUE,
  echo = FALSE,
  ...
)

Arguments

chat_env: The chat environment from chat_future
prompts: List of prompts to process
type_spec: Type specification for structured data extraction
judgements: Number of evaluation rounds for structured data extraction resulting in refined data
state_path: Path to save state file
workers: Number of parallel workers
chunk_size: Number of prompts each worker processes at a time
plan: Parallel backend ("multisession" or "multicore")
max_chunk_attempts: Maximum retries per failed chunk
max_retries: Maximum number of retry attempts for failed requests
initial_delay: Initial delay before first retry in seconds
max_delay: Maximum delay between retries in seconds
backoff_factor: Factor to multiply delay by after each retry
beep: Whether to play a sound on completion
progress: Whether to show progress bars
echo: Whether to display chat outputs (when progress is FALSE)
...: Additional arguments passed to the chat method

Value

A batch object with the processed results