Process a lot of prompts in parallel — chat

Processes a lot of chat prompts using parallel workers. Splits prompts into chunks for processing while maintaining state. For sequential processing, use chat_sequential().

Usage

chat_future(chat_model = NULL, ...)

Arguments

chat_model: ellmer chat model object or function (e.g., chat_openai())
...: Additional arguments passed to the underlying chat model (e.g., system_prompt)

Value

A process object (S7 class) containing:

prompts: Original input prompts
responses: Raw response data for completed prompts
completed: Number of successfully processed prompts
file: Path where batch state is saved
type: Type specification used for structured data
texts: Function to extract text responses or structured data
chats: Function to extract chat objects
progress: Function to get processing status
process: Function to process a lot of prompts

Process Method

This function provides access to the process() method for parallel processing of prompts. See ?process.future_chat for full details of the method and its parameters.

Examples

if (FALSE) { # interactive() && ellmer::has_credentials("openai")
# Create chat processor
chat <- chat_future(chat_openai(system_prompt = "Reply concisely"))

# Process prompts
response <- chat$process(
  list(
    "What is R?",
    "Explain base R versus tidyverse",
    "Explain vectors, lists, and data frames"
  )
)

# Return responses
response$texts()

# Return chat objects
response$chats()

# Check progress if interrupted
response$progress()
}