call_llm_robust: Robustly Call LLM API (Simple Retry)

In LLMR: Interface for Large Language Model APIs in R

Robustly Call LLM API (Simple Retry)

Description

Wraps call_llm to handle rate-limit errors (HTTP 429 or related "Too Many Requests" messages). It retries the call a specified number of times, now using exponential backoff. You can also choose to cache responses if you do not need fresh results each time.

Usage

call_llm_robust(
  config,
  messages,
  tries = 3,
  wait_seconds = 10,
  backoff_factor = 2,
  verbose = FALSE,
  json = FALSE,
  memoize = FALSE
)

Arguments

config	An llm_config object from llm_config.
messages	A list of message objects (or character vector for embeddings).
tries	Integer. Number of retries before giving up. Default is 3.
wait_seconds	Numeric. Initial wait time (seconds) before the first retry. Default is 10.
backoff_factor	Numeric. Multiplier for wait time after each failure. Default is 2.
verbose	Logical. If TRUE, prints the full API response.
json	Logical. If TRUE, returns the raw JSON as an attribute.
memoize	Logical. If TRUE, calls are cached to avoid repeated identical requests. Default is FALSE.

Value

The successful result from call_llm, or an error if all retries fail.

Examples

## Not run: 
  # Basic usage:
  robust_resp <- call_llm_robust(
    config = my_llm_config,
    messages = list(list(role = "user", content = "Hello, LLM!")),
    tries = 3,
    wait_seconds = 10,
    memoize = FALSE
  )
  cat("Response:", robust_resp, "\n")

## End(Not run)

LLMR documentation built on April 4, 2025, 1:11 a.m.